16 files changed, 145 insertions, 81 deletions

diff --git a/include/linux/cb710.h b/include/linux/cb710.h
index 63bc9a4d2926..8cc10411bab2 100644
--- a/include/linux/cb710.h
+++ b/include/linux/cb710.h
@@ -140,29 +140,6 @@ void cb710_dump_regs(struct cb710_chip *chip, unsigned dump);
 #include <linux/highmem.h>
 #include <linux/scatterlist.h>
 
-/**
- * cb710_sg_miter_stop_writing - stop mapping iteration after writing
- * @miter: sg mapping iter to be stopped
- *
- * Description:
- *   Stops mapping iterator @miter.  @miter should have been started
- *   started using sg_miter_start().  A stopped iteration can be
- *   resumed by calling sg_miter_next() on it.  This is useful when
- *   resources (kmap) need to be released during iteration.
- *
- *   This is a convenience wrapper that will be optimized out for arches
- *   that don't need flush_kernel_dcache_page().
- *
- * Context:
- *   IRQ disabled if the SG_MITER_ATOMIC is set.  Don't care otherwise.
- */
-static inline void cb710_sg_miter_stop_writing(struct sg_mapping_iter *miter)
-{
-	if (miter->page)
-		flush_kernel_dcache_page(miter->page);
-	sg_miter_stop(miter);
-}
-
 /*
  * 32-bit PIO mapping sg iterator
  *
@@ -171,12 +148,12 @@ static inline void cb710_sg_miter_stop_writing(struct sg_mapping_iter *miter)
  * without DMA support).
  *
  * Best-case reading (transfer from device):
- *   sg_miter_start();
+ *   sg_miter_start(, SG_MITER_TO_SG);
  *   cb710_sg_dwiter_write_from_io();
- *   cb710_sg_miter_stop_writing();
+ *   sg_miter_stop();
  *
  * Best-case writing (transfer to device):
- *   sg_miter_start();
+ *   sg_miter_start(, SG_MITER_FROM_SG);
  *   cb710_sg_dwiter_read_to_io();
  *   sg_miter_stop();
  */
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 665fa70e4094..90bba9e62286 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -179,14 +179,11 @@ struct cgroup {
 	 */
 	struct list_head release_list;
 
-	/* pids_mutex protects the fields below */
+	/* pids_mutex protects pids_list and cached pid arrays. */
 	struct rw_semaphore pids_mutex;
-	/* Array of process ids in the cgroup */
-	pid_t *tasks_pids;
-	/* How many files are using the current tasks_pids array */
-	int pids_use_count;
-	/* Length of the current tasks_pids array */
-	int pids_length;
+
+	/* Linked list of struct cgroup_pids */
+	struct list_head pids_list;
 
 	/* For RCU-protected deletion */
 	struct rcu_head rcu_head;
@@ -366,6 +363,23 @@ int cgroup_task_count(const struct cgroup *cgrp);
 int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task);
 
 /*
+ * When the subsys has to access css and may add permanent refcnt to css,
+ * it should take care of racy conditions with rmdir(). Following set of
+ * functions, is for stop/restart rmdir if necessary.
+ * Because these will call css_get/put, "css" should be alive css.
+ *
+ *  cgroup_exclude_rmdir();
+ *  ...do some jobs which may access arbitrary empty cgroup
+ *  cgroup_release_and_wakeup_rmdir();
+ *
+ *  When someone removes a cgroup while cgroup_exclude_rmdir() holds it,
+ *  it sleeps and cgroup_release_and_wakeup_rmdir() will wake him up.
+ */
+
+void cgroup_exclude_rmdir(struct cgroup_subsys_state *css);
+void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css);
+
+/*
  * Control Group subsystem type.
  * See Documentation/cgroups/cgroups.txt for details
  */
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index c56457c8334e..1219be4fb42e 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -293,7 +293,12 @@ static inline int clocksource_enable(struct clocksource *cs)
 	if (cs->enable)
 		ret = cs->enable(cs);
 
-	/* save mult_orig on enable */
+	/*
+	 * The frequency may have changed while the clocksource
+	 * was disabled. If so the code in ->enable() must update
+	 * the mult value to reflect the new frequency. Make sure
+	 * mult_orig follows this change.
+	 */
 	cs->mult_orig = cs->mult;
 
 	return ret;
@@ -309,6 +314,13 @@ static inline int clocksource_enable(struct clocksource *cs)
  */
 static inline void clocksource_disable(struct clocksource *cs)
 {
+	/*
+	 * Save mult_orig in mult so clocksource_enable() can
+	 * restore the value regardless if ->enable() updates
+	 * the value of mult or not.
+	 */
+	cs->mult = cs->mult_orig;
+
 	if (cs->disable)
 		cs->disable(cs);
 }
diff --git a/include/linux/flex_array.h b/include/linux/flex_array.h
new file mode 100644
index 000000000000..23c1ec79a31b
--- /dev/null
+++ b/include/linux/flex_array.h
@@ -0,0 +1,47 @@
+#ifndef _FLEX_ARRAY_H
+#define _FLEX_ARRAY_H
+
+#include <linux/types.h>
+#include <asm/page.h>
+
+#define FLEX_ARRAY_PART_SIZE PAGE_SIZE
+#define FLEX_ARRAY_BASE_SIZE PAGE_SIZE
+
+struct flex_array_part;
+
+/*
+ * This is meant to replace cases where an array-like
+ * structure has gotten too big to fit into kmalloc()
+ * and the developer is getting tempted to use
+ * vmalloc().
+ */
+
+struct flex_array {
+	union {
+		struct {
+			int element_size;
+			int total_nr_elements;
+			struct flex_array_part *parts[0];
+		};
+		/*
+		 * This little trick makes sure that
+		 * sizeof(flex_array) == PAGE_SIZE
+		 */
+		char padding[FLEX_ARRAY_BASE_SIZE];
+	};
+};
+
+#define FLEX_ARRAY_INIT(size, total) { { {\
+	.element_size = (size),		\
+	.total_nr_elements = (total),	\
+} } }
+
+struct flex_array *flex_array_alloc(int element_size, int total, gfp_t flags);
+int flex_array_prealloc(struct flex_array *fa, int start, int end, gfp_t flags);
+void flex_array_free(struct flex_array *fa);
+void flex_array_free_parts(struct flex_array *fa);
+int flex_array_put(struct flex_array *fa, int element_nr, void *src,
+		gfp_t flags);
+void *flex_array_get(struct flex_array *fa, int element_nr);
+
+#endif /* _FLEX_ARRAY_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0872372184fe..a36ffa5a77a4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1946,6 +1946,7 @@ extern void putname(const char *name);
 extern int register_blkdev(unsigned int, const char *);
 extern void unregister_blkdev(unsigned int, const char *);
 extern struct block_device *bdget(dev_t);
+extern struct block_device *bdgrab(struct block_device *bdev);
 extern void bd_set_size(struct block_device *, loff_t size);
 extern void bd_forget(struct inode *inode);
 extern void bdput(struct block_device *);
diff --git a/include/linux/lguest.h b/include/linux/lguest.h
index dbf2479e808e..2fb1dcbcb5aa 100644
--- a/include/linux/lguest.h
+++ b/include/linux/lguest.h
@@ -1,5 +1,7 @@
-/* Things the lguest guest needs to know.  Note: like all lguest interfaces,
- * this is subject to wild and random change between versions. */
+/*
+ * Things the lguest guest needs to know.  Note: like all lguest interfaces,
+ * this is subject to wild and random change between versions.
+ */
 #ifndef _LINUX_LGUEST_H
 #define _LINUX_LGUEST_H
 
@@ -11,32 +13,41 @@
 #define LG_CLOCK_MIN_DELTA	100UL
 #define LG_CLOCK_MAX_DELTA	ULONG_MAX
 
-/*G:031 The second method of communicating with the Host is to via "struct
+/*G:031
+ * The second method of communicating with the Host is to via "struct
  * lguest_data".  Once the Guest's initialization hypercall tells the Host where
- * this is, the Guest and Host both publish information in it. :*/
-struct lguest_data
-{
-	/* 512 == enabled (same as eflags in normal hardware).  The Guest
-	 * changes interrupts so often that a hypercall is too slow. */
+ * this is, the Guest and Host both publish information in it.
+:*/
+struct lguest_data {
+	/*
+	 * 512 == enabled (same as eflags in normal hardware).  The Guest
+	 * changes interrupts so often that a hypercall is too slow.
+	 */
 	unsigned int irq_enabled;
 	/* Fine-grained interrupt disabling by the Guest */
 	DECLARE_BITMAP(blocked_interrupts, LGUEST_IRQS);
 
-	/* The Host writes the virtual address of the last page fault here,
+	/*
+	 * The Host writes the virtual address of the last page fault here,
 	 * which saves the Guest a hypercall.  CR2 is the native register where
-	 * this address would normally be found. */
+	 * this address would normally be found.
+	 */
 	unsigned long cr2;
 
 	/* Wallclock time set by the Host. */
 	struct timespec time;
 
-	/* Interrupt pending set by the Host.  The Guest should do a hypercall
-	 * if it re-enables interrupts and sees this set (to X86_EFLAGS_IF). */
+	/*
+	 * Interrupt pending set by the Host.  The Guest should do a hypercall
+	 * if it re-enables interrupts and sees this set (to X86_EFLAGS_IF).
+	 */
 	int irq_pending;
 
-	/* Async hypercall ring.  Instead of directly making hypercalls, we can
+	/*
+	 * Async hypercall ring.  Instead of directly making hypercalls, we can
 	 * place them in here for processing the next time the Host wants.
-	 * This batching can be quite efficient. */
+	 * This batching can be quite efficient.
+	 */
 
 	/* 0xFF == done (set by Host), 0 == pending (set by Guest). */
 	u8 hcall_status[LHCALL_RING_SIZE];
diff --git a/include/linux/lguest_launcher.h b/include/linux/lguest_launcher.h
index bfefbdf7498a..495203ff221c 100644
--- a/include/linux/lguest_launcher.h
+++ b/include/linux/lguest_launcher.h
@@ -29,8 +29,10 @@ struct lguest_device_desc {
 	__u8 type;
 	/* The number of virtqueues (first in config array) */
 	__u8 num_vq;
-	/* The number of bytes of feature bits.  Multiply by 2: one for host
-	 * features and one for Guest acknowledgements. */
+	/*
+	 * The number of bytes of feature bits.  Multiply by 2: one for host
+	 * features and one for Guest acknowledgements.
+	 */
 	__u8 feature_len;
 	/* The number of bytes of the config array after virtqueues. */
 	__u8 config_len;
@@ -39,8 +41,10 @@ struct lguest_device_desc {
 	__u8 config[0];
 };
 
-/*D:135 This is how we expect the device configuration field for a virtqueue
- * to be laid out in config space. */
+/*D:135
+ * This is how we expect the device configuration field for a virtqueue
+ * to be laid out in config space.
+ */
 struct lguest_vqconfig {
 	/* The number of entries in the virtio_ring */
 	__u16 num;
@@ -61,7 +65,9 @@ enum lguest_req
 	LHREQ_EVENTFD, /* + address, fd. */
 };
 
-/* The alignment to use between consumer and producer parts of vring.
- * x86 pagesize for historical reasons. */
+/*
+ * The alignment to use between consumer and producer parts of vring.
+ * x86 pagesize for historical reasons.
+ */
 #define LGUEST_VRING_ALIGN	4096
 #endif /* _LINUX_LGUEST_LAUNCHER */
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 79b6d7fd4ac2..e5b6e33c6571 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -589,6 +589,7 @@ struct ata_device {
 #endif
 	/* n_sector is CLEAR_BEGIN, read comment above CLEAR_BEGIN */
 	u64			n_sectors;	/* size of device, if ATA */
+	u64			n_native_sectors; /* native size, if ATA */
 	unsigned int		class;		/* ATA_DEV_xxx */
 	unsigned long		unpark_deadline;
 
diff --git a/include/linux/pps.h b/include/linux/pps.h
index cfe5c7214ec6..0194ab06177b 100644
--- a/include/linux/pps.h
+++ b/include/linux/pps.h
@@ -22,6 +22,8 @@
 #ifndef _PPS_H_
 #define _PPS_H_
 
+#include <linux/types.h>
+
 #define PPS_VERSION		"5.3.6"
 #define PPS_MAX_SOURCES		16		/* should be enough... */
 
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index e5996984ddd0..9aaf5bfdad1a 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -242,6 +242,8 @@ size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents,
  */
 
 #define SG_MITER_ATOMIC		(1 << 0)	 /* use kmap_atomic */
+#define SG_MITER_TO_SG		(1 << 1)	/* flush back to phys on unmap */
+#define SG_MITER_FROM_SG	(1 << 2)	/* nop */
 
 struct sg_mapping_iter {
 	/* the following three fields can be accessed directly */
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 1488d8c81aac..e8c6c9136c97 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -394,6 +394,7 @@ extern void __do_SAK(struct tty_struct *tty);
 extern void disassociate_ctty(int priv);
 extern void no_tty(void);
 extern void tty_flip_buffer_push(struct tty_struct *tty);
+extern void tty_flush_to_ldisc(struct tty_struct *tty);
 extern void tty_buffer_free_all(struct tty_struct *tty);
 extern void tty_buffer_flush(struct tty_struct *tty);
 extern void tty_buffer_init(struct tty_struct *tty);
diff --git a/include/linux/uio.h b/include/linux/uio.h
index b7fe13883bdb..98c114323a8b 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -19,15 +19,6 @@ struct iovec
 	__kernel_size_t iov_len; /* Must be size_t (1003.1g) */
 };
 
-#ifdef __KERNEL__
-
-struct kvec {
-	void *iov_base; /* and that should *never* hold a userland pointer */
-	size_t iov_len;
-};
-
-#endif
-
 /*
  *	UIO_MAXIOV shall be at least 16 1003.1g (5.4.1.1)
  */
@@ -35,6 +26,13 @@ struct kvec {
 #define UIO_FASTIOV	8
 #define UIO_MAXIOV	1024
 
+#ifdef __KERNEL__
+
+struct kvec {
+	void *iov_base; /* and that should *never* hold a userland pointer */
+	size_t iov_len;
+};
+
 /*
  * Total number of bytes covered by an iovec.
  *
@@ -53,5 +51,6 @@ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs)
 }
 
 unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to);
+#endif
 
 #endif
diff --git a/include/linux/virtio_blk.h b/include/linux/virtio_blk.h
index be7d255fc7cf..8dab9f2b8832 100644
--- a/include/linux/virtio_blk.h
+++ b/include/linux/virtio_blk.h
@@ -20,8 +20,7 @@
 
 #define VIRTIO_BLK_ID_BYTES	(sizeof(__u16[256]))	/* IDENTIFY DATA */
 
-struct virtio_blk_config
-{
+struct virtio_blk_config {
 	/* The capacity (in 512-byte sectors). */
 	__u64 capacity;
 	/* The maximum segment size (if VIRTIO_BLK_F_SIZE_MAX) */
@@ -50,8 +49,7 @@ struct virtio_blk_config
 #define VIRTIO_BLK_T_BARRIER	0x80000000
 
 /* This is the first element of the read scatter-gather list. */
-struct virtio_blk_outhdr
-{
+struct virtio_blk_outhdr {
 	/* VIRTIO_BLK_T* */
 	__u32 type;
 	/* io priority. */
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 99f514575f6a..e547e3c8ee9a 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -79,8 +79,7 @@
  *	the dev->feature bits if it wants.
  */
 typedef void vq_callback_t(struct virtqueue *);
-struct virtio_config_ops
-{
+struct virtio_config_ops {
 	void (*get)(struct virtio_device *vdev, unsigned offset,
 		    void *buf, unsigned len);
 	void (*set)(struct virtio_device *vdev, unsigned offset,
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 9c543d6ac535..d8dd539c9f48 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -31,8 +31,7 @@
 
 #define VIRTIO_NET_S_LINK_UP	1	/* Link is up */
 
-struct virtio_net_config
-{
+struct virtio_net_config {
 	/* The config defining mac address (if VIRTIO_NET_F_MAC) */
 	__u8 mac[6];
 	/* See VIRTIO_NET_F_STATUS and VIRTIO_NET_S_* above */
@@ -41,8 +40,7 @@ struct virtio_net_config
 
 /* This is the first element of the scatter-gather list.  If you don't
  * specify GSO or CSUM features, you can simply ignore the header. */
-struct virtio_net_hdr
-{
+struct virtio_net_hdr {
 #define VIRTIO_NET_HDR_F_NEEDS_CSUM	1	// Use csum_start, csum_offset
 	__u8 flags;
 #define VIRTIO_NET_HDR_GSO_NONE		0	// Not a GSO frame
diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
index 693e0ec5afa6..e4d144b132b5 100644
--- a/include/linux/virtio_ring.h
+++ b/include/linux/virtio_ring.h
@@ -30,8 +30,7 @@
 #define VIRTIO_RING_F_INDIRECT_DESC	28
 
 /* Virtio ring descriptors: 16 bytes.  These can chain together via "next". */
-struct vring_desc
-{
+struct vring_desc {
 	/* Address (guest-physical). */
 	__u64 addr;
 	/* Length. */
@@ -42,24 +41,21 @@ struct vring_desc
 	__u16 next;
 };
 
-struct vring_avail
-{
+struct vring_avail {
 	__u16 flags;
 	__u16 idx;
 	__u16 ring[];
 };
 
 /* u32 is used here for ids for padding reasons. */
-struct vring_used_elem
-{
+struct vring_used_elem {
 	/* Index of start of used descriptor chain. */
 	__u32 id;
 	/* Total length of the descriptor chain which was used (written to) */
 	__u32 len;
 };
 
-struct vring_used
-{
+struct vring_used {
 	__u16 flags;
 	__u16 idx;
 	struct vring_used_elem ring[];