summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/Makefile3
-rw-r--r--fs/aio.c2
-rw-r--r--fs/befs/btree.c3
-rw-r--r--fs/binfmt_elf.c1
-rw-r--r--fs/bio.c2
-rw-r--r--fs/btrfs/tree-log.c48
-rw-r--r--fs/buffer.c11
-rw-r--r--fs/cifs/connect.c16
-rw-r--r--fs/direct-io.c31
-rw-r--r--fs/dlm/plock.c18
-rw-r--r--fs/ecryptfs/miscdev.c14
-rw-r--r--fs/exec.c4
-rw-r--r--fs/ext3/super.c1
-rw-r--r--fs/f2fs/f2fs.h2
-rw-r--r--fs/f2fs/gc.c2
-rw-r--r--fs/f2fs/super.c2
-rw-r--r--fs/fat/dir.c23
-rw-r--r--fs/fat/fat.h40
-rw-r--r--fs/fat/file.c5
-rw-r--r--fs/fat/inode.c74
-rw-r--r--fs/fat/nfs.c221
-rw-r--r--fs/fscache/stats.c2
-rw-r--r--fs/gfs2/aops.c2
-rw-r--r--fs/gfs2/bmap.c2
-rw-r--r--fs/gfs2/glock.c32
-rw-r--r--fs/gfs2/glock.h1
-rw-r--r--fs/gfs2/glops.c4
-rw-r--r--fs/gfs2/incore.h19
-rw-r--r--fs/gfs2/inode.c188
-rw-r--r--fs/gfs2/log.c104
-rw-r--r--fs/gfs2/lops.c32
-rw-r--r--fs/gfs2/lops.h5
-rw-r--r--fs/gfs2/meta_io.c2
-rw-r--r--fs/gfs2/rgrp.c24
-rw-r--r--fs/gfs2/rgrp.h2
-rw-r--r--fs/gfs2/super.c2
-rw-r--r--fs/gfs2/trace_gfs2.h11
-rw-r--r--fs/gfs2/trans.c7
-rw-r--r--fs/hfsplus/extents.c2
-rw-r--r--fs/hugetlbfs/inode.c2
-rw-r--r--fs/inode.c2
-rw-r--r--fs/jbd/commit.c25
-rw-r--r--fs/jbd/journal.c2
-rw-r--r--fs/jbd2/journal.c2
-rw-r--r--fs/lockd/clntlock.c3
-rw-r--r--fs/lockd/clntproc.c3
-rw-r--r--fs/namespace.c2
-rw-r--r--fs/nfs/callback.c3
-rw-r--r--fs/nfs/callback_proc.c2
-rw-r--r--fs/nfs/client.c2
-rw-r--r--fs/nfs/delegation.c121
-rw-r--r--fs/nfs/delegation.h5
-rw-r--r--fs/nfs/dir.c2
-rw-r--r--fs/nfs/file.c9
-rw-r--r--fs/nfs/inode.c8
-rw-r--r--fs/nfs/internal.h7
-rw-r--r--fs/nfs/nfs4_fs.h16
-rw-r--r--fs/nfs/nfs4client.c75
-rw-r--r--fs/nfs/nfs4filelayout.c34
-rw-r--r--fs/nfs/nfs4namespace.c43
-rw-r--r--fs/nfs/nfs4proc.c558
-rw-r--r--fs/nfs/nfs4state.c149
-rw-r--r--fs/nfs/nfs4super.c2
-rw-r--r--fs/nfs/nfs4xdr.c176
-rw-r--r--fs/nfs/objlayout/objio_osd.c2
-rw-r--r--fs/nfs/objlayout/objlayout.h2
-rw-r--r--fs/nfs/pagelist.c53
-rw-r--r--fs/nfs/pnfs.c2
-rw-r--r--fs/nfs/read.c2
-rw-r--r--fs/nfs/super.c80
-rw-r--r--fs/nfs/write.c2
-rw-r--r--fs/nfsd/nfs4state.c7
-rw-r--r--fs/nfsd/nfs4xdr.c24
-rw-r--r--fs/notify/inotify/inotify_user.c8
-rw-r--r--fs/ocfs2/dlm/dlmrecovery.c6
-rw-r--r--fs/ocfs2/ioctl.c22
-rw-r--r--fs/ocfs2/move_extents.c53
-rw-r--r--fs/proc/Makefile2
-rw-r--r--fs/proc/array.c1
-rw-r--r--fs/proc/base.c100
-rw-r--r--fs/proc/generic.c119
-rw-r--r--fs/proc/internal.h18
-rw-r--r--fs/proc/kcore.c9
-rw-r--r--fs/proc/meminfo.c1
-rw-r--r--fs/proc/mmu.c60
-rw-r--r--fs/read_write.c2
-rw-r--r--fs/sysfs/dir.c41
-rw-r--r--fs/ufs/util.c3
88 files changed, 1779 insertions, 1057 deletions
diff --git a/fs/Makefile b/fs/Makefile
index 9d53192236fc..3b2c76759ec9 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -10,7 +10,7 @@ obj-y := open.o read_write.o file_table.o super.o \
ioctl.o readdir.o select.o fifo.o dcache.o inode.o \
attr.o bad_inode.o file.o filesystems.o namespace.o \
seq_file.o xattr.o libfs.o fs-writeback.o \
- pnode.o drop_caches.o splice.o sync.o utimes.o \
+ pnode.o splice.o sync.o utimes.o \
stack.o fs_struct.o statfs.o
ifeq ($(CONFIG_BLOCK),y)
@@ -49,6 +49,7 @@ obj-$(CONFIG_FS_POSIX_ACL) += posix_acl.o xattr_acl.o
obj-$(CONFIG_NFS_COMMON) += nfs_common/
obj-$(CONFIG_GENERIC_ACL) += generic_acl.o
obj-$(CONFIG_COREDUMP) += coredump.o
+obj-$(CONFIG_SYSCTL) += drop_caches.o
obj-$(CONFIG_FHANDLE) += fhandle.o
diff --git a/fs/aio.c b/fs/aio.c
index 3f941f2a3059..1dc8786f4588 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1029,9 +1029,9 @@ static int aio_read_evt(struct kioctx *ioctx, struct io_event *ent)
spin_unlock(&info->ring_lock);
out:
- kunmap_atomic(ring);
dprintk("leaving aio_read_evt: %d h%lu t%lu\n", ret,
(unsigned long)ring->head, (unsigned long)ring->tail);
+ kunmap_atomic(ring);
return ret;
}
diff --git a/fs/befs/btree.c b/fs/befs/btree.c
index a66c9b1136e0..74e397db0b8b 100644
--- a/fs/befs/btree.c
+++ b/fs/befs/btree.c
@@ -436,8 +436,7 @@ befs_btree_read(struct super_block *sb, befs_data_stream * ds,
goto error;
}
- if ((this_node = (befs_btree_node *)
- kmalloc(sizeof (befs_btree_node), GFP_NOFS)) == NULL) {
+ if ((this_node = kmalloc(sizeof (befs_btree_node), GFP_NOFS)) == NULL) {
befs_error(sb, "befs_btree_read() failed to allocate %u "
"bytes of memory", sizeof (befs_btree_node));
goto error;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 3939829f6c5c..86af964c2425 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1137,6 +1137,7 @@ static unsigned long vma_dump_size(struct vm_area_struct *vma,
goto whole;
if (!(vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_PRIVATE))
goto whole;
+ return 0;
}
/* Do not dump I/O mapped devices or special mappings */
diff --git a/fs/bio.c b/fs/bio.c
index bb5768f59b32..b96fc6ce4855 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -1428,8 +1428,6 @@ void bio_endio(struct bio *bio, int error)
else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
error = -EIO;
- trace_block_bio_complete(bio, error);
-
if (bio->bi_end_io)
bio->bi_end_io(bio, error);
}
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 451fad96ecd1..ef96381569a4 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -317,6 +317,7 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans,
unsigned long src_ptr;
unsigned long dst_ptr;
int overwrite_root = 0;
+ bool inode_item = key->type == BTRFS_INODE_ITEM_KEY;
if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
overwrite_root = 1;
@@ -326,6 +327,9 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans,
/* look for the key in the destination tree */
ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
+ if (ret < 0)
+ return ret;
+
if (ret == 0) {
char *src_copy;
char *dst_copy;
@@ -367,6 +371,30 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans,
return 0;
}
+ /*
+ * We need to load the old nbytes into the inode so when we
+ * replay the extents we've logged we get the right nbytes.
+ */
+ if (inode_item) {
+ struct btrfs_inode_item *item;
+ u64 nbytes;
+
+ item = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ struct btrfs_inode_item);
+ nbytes = btrfs_inode_nbytes(path->nodes[0], item);
+ item = btrfs_item_ptr(eb, slot,
+ struct btrfs_inode_item);
+ btrfs_set_inode_nbytes(eb, item, nbytes);
+ }
+ } else if (inode_item) {
+ struct btrfs_inode_item *item;
+
+ /*
+ * New inode, set nbytes to 0 so that the nbytes comes out
+ * properly when we replay the extents.
+ */
+ item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item);
+ btrfs_set_inode_nbytes(eb, item, 0);
}
insert:
btrfs_release_path(path);
@@ -486,7 +514,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
int found_type;
u64 extent_end;
u64 start = key->offset;
- u64 saved_nbytes;
+ u64 nbytes = 0;
struct btrfs_file_extent_item *item;
struct inode *inode = NULL;
unsigned long size;
@@ -496,10 +524,19 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
found_type = btrfs_file_extent_type(eb, item);
if (found_type == BTRFS_FILE_EXTENT_REG ||
- found_type == BTRFS_FILE_EXTENT_PREALLOC)
- extent_end = start + btrfs_file_extent_num_bytes(eb, item);
- else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
+ found_type == BTRFS_FILE_EXTENT_PREALLOC) {
+ nbytes = btrfs_file_extent_num_bytes(eb, item);
+ extent_end = start + nbytes;
+
+ /*
+ * We don't add to the inodes nbytes if we are prealloc or a
+ * hole.
+ */
+ if (btrfs_file_extent_disk_bytenr(eb, item) == 0)
+ nbytes = 0;
+ } else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
size = btrfs_file_extent_inline_len(eb, item);
+ nbytes = btrfs_file_extent_ram_bytes(eb, item);
extent_end = ALIGN(start + size, root->sectorsize);
} else {
ret = 0;
@@ -548,7 +585,6 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
}
btrfs_release_path(path);
- saved_nbytes = inode_get_bytes(inode);
/* drop any overlapping extents */
ret = btrfs_drop_extents(trans, root, inode, start, extent_end, 1);
BUG_ON(ret);
@@ -635,7 +671,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
BUG_ON(ret);
}
- inode_set_bytes(inode, saved_nbytes);
+ inode_add_bytes(inode, nbytes);
ret = btrfs_update_inode(trans, root, inode);
out:
if (inode)
diff --git a/fs/buffer.c b/fs/buffer.c
index b4dcb34c9635..10ef81e10b20 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -865,8 +865,6 @@ try_again:
/* Link the buffer to its page */
set_bh_page(bh, page, offset);
-
- init_buffer(bh, NULL, NULL);
}
return head;
/*
@@ -2949,7 +2947,7 @@ static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh)
}
}
-int submit_bh(int rw, struct buffer_head * bh)
+int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
{
struct bio *bio;
int ret = 0;
@@ -2984,6 +2982,7 @@ int submit_bh(int rw, struct buffer_head * bh)
bio->bi_end_io = end_bio_bh_io_sync;
bio->bi_private = bh;
+ bio->bi_flags |= bio_flags;
/* Take care of bh's that straddle the end of the device */
guard_bh_eod(rw, bio, bh);
@@ -2997,6 +2996,12 @@ int submit_bh(int rw, struct buffer_head * bh)
bio_put(bio);
return ret;
}
+EXPORT_SYMBOL_GPL(_submit_bh);
+
+int submit_bh(int rw, struct buffer_head *bh)
+{
+ return _submit_bh(rw, bh, 0);
+}
EXPORT_SYMBOL(submit_bh);
/**
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 991c63c6bdd0..21b3a291c327 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1575,14 +1575,24 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
}
break;
case Opt_blank_pass:
- vol->password = NULL;
- break;
- case Opt_pass:
/* passwords have to be handled differently
* to allow the character used for deliminator
* to be passed within them
*/
+ /*
+ * Check if this is a case where the password
+ * starts with a delimiter
+ */
+ tmp_end = strchr(data, '=');
+ tmp_end++;
+ if (!(tmp_end < end && tmp_end[1] == delim)) {
+ /* No it is not. Set the password to NULL */
+ vol->password = NULL;
+ break;
+ }
+ /* Yes it is. Drop down to Opt_pass below.*/
+ case Opt_pass:
/* Obtain the value string */
value = strchr(data, '=');
value++;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index f853263cf74f..cfb816dc6d9f 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -672,12 +672,6 @@ static inline int dio_send_cur_page(struct dio *dio, struct dio_submit *sdio,
if (sdio->final_block_in_bio != sdio->cur_page_block ||
cur_offset != bio_next_offset)
dio_bio_submit(dio, sdio);
- /*
- * Submit now if the underlying fs is about to perform a
- * metadata read
- */
- else if (sdio->boundary)
- dio_bio_submit(dio, sdio);
}
if (sdio->bio == NULL) {
@@ -737,16 +731,6 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
sdio->cur_page_block +
(sdio->cur_page_len >> sdio->blkbits) == blocknr) {
sdio->cur_page_len += len;
-
- /*
- * If sdio->boundary then we want to schedule the IO now to
- * avoid metadata seeks.
- */
- if (sdio->boundary) {
- ret = dio_send_cur_page(dio, sdio, map_bh);
- page_cache_release(sdio->cur_page);
- sdio->cur_page = NULL;
- }
goto out;
}
@@ -758,7 +742,7 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
page_cache_release(sdio->cur_page);
sdio->cur_page = NULL;
if (ret)
- goto out;
+ return ret;
}
page_cache_get(page); /* It is in dio */
@@ -768,6 +752,16 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
sdio->cur_page_block = blocknr;
sdio->cur_page_fs_offset = sdio->block_in_file << sdio->blkbits;
out:
+ /*
+ * If sdio->boundary then we want to schedule the IO now to
+ * avoid metadata seeks.
+ */
+ if (sdio->boundary) {
+ ret = dio_send_cur_page(dio, sdio, map_bh);
+ dio_bio_submit(dio, sdio);
+ page_cache_release(sdio->cur_page);
+ sdio->cur_page = NULL;
+ }
return ret;
}
@@ -969,7 +963,8 @@ do_holes:
this_chunk_bytes = this_chunk_blocks << blkbits;
BUG_ON(this_chunk_bytes == 0);
- sdio->boundary = buffer_boundary(map_bh);
+ if (this_chunk_blocks == sdio->blocks_available)
+ sdio->boundary = buffer_boundary(map_bh);
ret = submit_page_section(dio, sdio, page,
offset_in_page,
this_chunk_bytes,
diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c
index 01fd5c11a7fb..f704458ea5f5 100644
--- a/fs/dlm/plock.c
+++ b/fs/dlm/plock.c
@@ -247,6 +247,7 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
struct dlm_ls *ls;
struct plock_op *op;
int rv;
+ unsigned char fl_flags = fl->fl_flags;
ls = dlm_find_lockspace_local(lockspace);
if (!ls)
@@ -258,9 +259,18 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
goto out;
}
- if (posix_lock_file_wait(file, fl) < 0)
- log_error(ls, "dlm_posix_unlock: vfs unlock error %llx",
- (unsigned long long)number);
+ /* cause the vfs unlock to return ENOENT if lock is not found */
+ fl->fl_flags |= FL_EXISTS;
+
+ rv = posix_lock_file_wait(file, fl);
+ if (rv == -ENOENT) {
+ rv = 0;
+ goto out_free;
+ }
+ if (rv < 0) {
+ log_error(ls, "dlm_posix_unlock: vfs unlock error %d %llx",
+ rv, (unsigned long long)number);
+ }
op->info.optype = DLM_PLOCK_OP_UNLOCK;
op->info.pid = fl->fl_pid;
@@ -296,9 +306,11 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
if (rv == -ENOENT)
rv = 0;
+out_free:
kfree(op);
out:
dlm_put_lockspace(ls);
+ fl->fl_flags = fl_flags;
return rv;
}
EXPORT_SYMBOL_GPL(dlm_posix_unlock);
diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c
index 412e6eda25f8..e4141f257495 100644
--- a/fs/ecryptfs/miscdev.c
+++ b/fs/ecryptfs/miscdev.c
@@ -80,13 +80,6 @@ ecryptfs_miscdev_open(struct inode *inode, struct file *file)
int rc;
mutex_lock(&ecryptfs_daemon_hash_mux);
- rc = try_module_get(THIS_MODULE);
- if (rc == 0) {
- rc = -EIO;
- printk(KERN_ERR "%s: Error attempting to increment module use "
- "count; rc = [%d]\n", __func__, rc);
- goto out_unlock_daemon_list;
- }
rc = ecryptfs_find_daemon_by_euid(&daemon);
if (!rc) {
rc = -EINVAL;
@@ -96,7 +89,7 @@ ecryptfs_miscdev_open(struct inode *inode, struct file *file)
if (rc) {
printk(KERN_ERR "%s: Error attempting to spawn daemon; "
"rc = [%d]\n", __func__, rc);
- goto out_module_put_unlock_daemon_list;
+ goto out_unlock_daemon_list;
}
mutex_lock(&daemon->mux);
if (daemon->flags & ECRYPTFS_DAEMON_MISCDEV_OPEN) {
@@ -108,9 +101,6 @@ ecryptfs_miscdev_open(struct inode *inode, struct file *file)
atomic_inc(&ecryptfs_num_miscdev_opens);
out_unlock_daemon:
mutex_unlock(&daemon->mux);
-out_module_put_unlock_daemon_list:
- if (rc)
- module_put(THIS_MODULE);
out_unlock_daemon_list:
mutex_unlock(&ecryptfs_daemon_hash_mux);
return rc;
@@ -147,7 +137,6 @@ ecryptfs_miscdev_release(struct inode *inode, struct file *file)
"bug.\n", __func__, rc);
BUG();
}
- module_put(THIS_MODULE);
return rc;
}
@@ -471,6 +460,7 @@ out_free:
static const struct file_operations ecryptfs_miscdev_fops = {
+ .owner = THIS_MODULE,
.open = ecryptfs_miscdev_open,
.poll = ecryptfs_miscdev_poll,
.read = ecryptfs_miscdev_read,
diff --git a/fs/exec.c b/fs/exec.c
index a96a4885bbbf..87e731f020fb 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -613,7 +613,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
* when the old and new regions overlap clear from new_end.
*/
free_pgd_range(&tlb, new_end, old_end, new_end,
- vma->vm_next ? vma->vm_next->vm_start : 0);
+ vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING);
} else {
/*
* otherwise, clean from old_start; this is done to not touch
@@ -622,7 +622,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
* for the others its just a little faster.
*/
free_pgd_range(&tlb, old_start, old_end, new_end,
- vma->vm_next ? vma->vm_next->vm_start : 0);
+ vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING);
}
tlb_finish_mmu(&tlb, new_end, old_end);
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index fb5120a5505c..3dc48cc8b6eb 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -2067,7 +2067,6 @@ static int ext3_fill_super (struct super_block *sb, void *data, int silent)
test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA ? "journal":
test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA ? "ordered":
"writeback");
- sb->s_flags |= MS_SNAP_STABLE;
return 0;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index cc2213afdcc7..201c8d3b0f86 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -137,7 +137,7 @@ struct extent_info {
rwlock_t ext_lock; /* rwlock for consistency */
unsigned int fofs; /* start offset in a file */
u32 blk_addr; /* start block address of the extent */
- unsigned int len; /* lenth of the extent */
+ unsigned int len; /* length of the extent */
};
/*
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 94b8a0c48453..2e3eb2d4fc30 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -222,7 +222,7 @@ static unsigned int get_gc_cost(struct f2fs_sb_info *sbi, unsigned int segno,
}
/*
- * This function is called from two pathes.
+ * This function is called from two paths.
* One is garbage collection and the other is SSR segment selection.
* When it is called during GC, it just gets a victim segment
* and it does not remove it from dirty seglist.
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index fea6e582a2ed..62e017743af6 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -82,7 +82,7 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
init_once((void *) fi);
- /* Initilize f2fs-specific inode info */
+ /* Initialize f2fs-specific inode info */
fi->vfs_inode.i_version = 1;
atomic_set(&fi->dirty_dents, 0);
fi->i_current_depth = 1;
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 165012ef363a..7a6f02caf286 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -964,6 +964,29 @@ int fat_scan(struct inode *dir, const unsigned char *name,
}
EXPORT_SYMBOL_GPL(fat_scan);
+/*
+ * Scans a directory for a given logstart.
+ * Returns an error code or zero.
+ */
+int fat_scan_logstart(struct inode *dir, int i_logstart,
+ struct fat_slot_info *sinfo)
+{
+ struct super_block *sb = dir->i_sb;
+
+ sinfo->slot_off = 0;
+ sinfo->bh = NULL;
+ while (fat_get_short_entry(dir, &sinfo->slot_off, &sinfo->bh,
+ &sinfo->de) >= 0) {
+ if (fat_get_start(MSDOS_SB(sb), sinfo->de) == i_logstart) {
+ sinfo->slot_off -= sizeof(*sinfo->de);
+ sinfo->nr_slots = 1;
+ sinfo->i_pos = fat_make_i_pos(sb, sinfo->bh, sinfo->de);
+ return 0;
+ }
+ }
+ return -ENOENT;
+}
+
static int __fat_remove_entries(struct inode *dir, loff_t pos, int nr_slots)
{
struct super_block *sb = dir->i_sb;
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index e9cc3f0d58e2..21664fcf3616 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -23,6 +23,9 @@
#define FAT_ERRORS_PANIC 2 /* panic on error */
#define FAT_ERRORS_RO 3 /* remount r/o on error */
+#define FAT_NFS_STALE_RW 1 /* NFS RW support, can cause ESTALE */
+#define FAT_NFS_NOSTALE_RO 2 /* NFS RO support, no ESTALE issue */
+
struct fat_mount_options {
kuid_t fs_uid;
kgid_t fs_gid;
@@ -34,6 +37,7 @@ struct fat_mount_options {
unsigned short shortname; /* flags for shortname display/create rule */
unsigned char name_check; /* r = relaxed, n = normal, s = strict */
unsigned char errors; /* On error: continue, panic, remount-ro */
+ unsigned char nfs; /* NFS support: nostale_ro, stale_rw */
unsigned short allow_utime;/* permission for setting the [am]time */
unsigned quiet:1, /* set = fake successful chmods and chowns */
showexec:1, /* set = only set x bit for com/exe/bat */
@@ -48,8 +52,7 @@ struct fat_mount_options {
usefree:1, /* Use free_clusters for FAT32 */
tz_set:1, /* Filesystem timestamps' offset set */
rodir:1, /* allow ATTR_RO for directory */
- discard:1, /* Issue discard requests on deletions */
- nfs:1; /* Do extra work needed for NFS export */
+ discard:1; /* Issue discard requests on deletions */
};
#define FAT_HASH_BITS 8
@@ -72,6 +75,7 @@ struct msdos_sb_info {
unsigned long root_cluster; /* first cluster of the root directory */
unsigned long fsinfo_sector; /* sector number of FAT32 fsinfo */
struct mutex fat_lock;
+ struct mutex nfs_build_inode_lock;
struct mutex s_lock;
unsigned int prev_free; /* previously allocated cluster number */
unsigned int free_clusters; /* -1 if undefined */
@@ -215,6 +219,27 @@ static inline sector_t fat_clus_to_blknr(struct msdos_sb_info *sbi, int clus)
+ sbi->data_start;
}
+static inline void fat_get_blknr_offset(struct msdos_sb_info *sbi,
+ loff_t i_pos, sector_t *blknr, int *offset)
+{
+ *blknr = i_pos >> sbi->dir_per_block_bits;
+ *offset = i_pos & (sbi->dir_per_block - 1);
+}
+
+static inline loff_t fat_i_pos_read(struct msdos_sb_info *sbi,
+ struct inode *inode)
+{
+ loff_t i_pos;
+#if BITS_PER_LONG == 32
+ spin_lock(&sbi->inode_hash_lock);
+#endif
+ i_pos = MSDOS_I(inode)->i_pos;
+#if BITS_PER_LONG == 32
+ spin_unlock(&sbi->inode_hash_lock);
+#endif
+ return i_pos;
+}
+
static inline void fat16_towchar(wchar_t *dst, const __u8 *src, size_t len)
{
#ifdef __BIG_ENDIAN
@@ -271,6 +296,8 @@ extern int fat_dir_empty(struct inode *dir);
extern int fat_subdirs(struct inode *dir);
extern int fat_scan(struct inode *dir, const unsigned char *name,
struct fat_slot_info *sinfo);
+extern int fat_scan_logstart(struct inode *dir, int i_logstart,
+ struct fat_slot_info *sinfo);
extern int fat_get_dotdot_entry(struct inode *dir, struct buffer_head **bh,
struct msdos_dir_entry **de);
extern int fat_alloc_new_dir(struct inode *dir, struct timespec *ts);
@@ -348,6 +375,7 @@ extern struct inode *fat_build_inode(struct super_block *sb,
extern int fat_sync_inode(struct inode *inode);
extern int fat_fill_super(struct super_block *sb, void *data, int silent,
int isvfat, void (*setup)(struct super_block *));
+extern int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de);
extern int fat_flush_inodes(struct super_block *sb, struct inode *i1,
struct inode *i2);
@@ -382,12 +410,8 @@ int fat_cache_init(void);
void fat_cache_destroy(void);
/* fat/nfs.c */
-struct fid;
-extern struct dentry *fat_fh_to_dentry(struct super_block *sb, struct fid *fid,
- int fh_len, int fh_type);
-extern struct dentry *fat_fh_to_parent(struct super_block *sb, struct fid *fid,
- int fh_len, int fh_type);
-extern struct dentry *fat_get_parent(struct dentry *child_dir);
+extern const struct export_operations fat_export_ops;
+extern const struct export_operations fat_export_ops_nostale;
/* helper for printk */
typedef unsigned long long llu;
diff --git a/fs/fat/file.c b/fs/fat/file.c
index 3978f8ca1823..b0b632e50ddb 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -306,6 +306,11 @@ int fat_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
struct inode *inode = dentry->d_inode;
generic_fillattr(inode, stat);
stat->blksize = MSDOS_SB(inode->i_sb)->cluster_size;
+
+ if (MSDOS_SB(inode->i_sb)->options.nfs == FAT_NFS_NOSTALE_RO) {
+ /* Use i_pos for ino. This is used as fileid of nfs. */
+ stat->ino = fat_i_pos_read(MSDOS_SB(inode->i_sb), inode);
+ }
return 0;
}
EXPORT_SYMBOL_GPL(fat_getattr);
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index acf6e479b443..4ff901632b26 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -18,7 +18,6 @@
#include <linux/pagemap.h>
#include <linux/mpage.h>
#include <linux/buffer_head.h>
-#include <linux/exportfs.h>
#include <linux/mount.h>
#include <linux/vfs.h>
#include <linux/parser.h>
@@ -385,7 +384,7 @@ static int fat_calc_dir_size(struct inode *inode)
}
/* doesn't deal with root inode */
-static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
+int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
{
struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
int error;
@@ -444,12 +443,25 @@ static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
return 0;
}
+static inline void fat_lock_build_inode(struct msdos_sb_info *sbi)
+{
+ if (sbi->options.nfs == FAT_NFS_NOSTALE_RO)
+ mutex_lock(&sbi->nfs_build_inode_lock);
+}
+
+static inline void fat_unlock_build_inode(struct msdos_sb_info *sbi)
+{
+ if (sbi->options.nfs == FAT_NFS_NOSTALE_RO)
+ mutex_unlock(&sbi->nfs_build_inode_lock);
+}
+
struct inode *fat_build_inode(struct super_block *sb,
struct msdos_dir_entry *de, loff_t i_pos)
{
struct inode *inode;
int err;
+ fat_lock_build_inode(MSDOS_SB(sb));
inode = fat_iget(sb, i_pos);
if (inode)
goto out;
@@ -469,6 +481,7 @@ struct inode *fat_build_inode(struct super_block *sb,
fat_attach(inode, i_pos);
insert_inode_hash(inode);
out:
+ fat_unlock_build_inode(MSDOS_SB(sb));
return inode;
}
@@ -655,20 +668,6 @@ static int fat_statfs(struct dentry *dentry, struct kstatfs *buf)
return 0;
}
-static inline loff_t fat_i_pos_read(struct msdos_sb_info *sbi,
- struct inode *inode)
-{
- loff_t i_pos;
-#if BITS_PER_LONG == 32
- spin_lock(&sbi->inode_hash_lock);
-#endif
- i_pos = MSDOS_I(inode)->i_pos;
-#if BITS_PER_LONG == 32
- spin_unlock(&sbi->inode_hash_lock);
-#endif
- return i_pos;
-}
-
static int __fat_write_inode(struct inode *inode, int wait)
{
struct super_block *sb = inode->i_sb;
@@ -676,7 +675,8 @@ static int __fat_write_inode(struct inode *inode, int wait)
struct buffer_head *bh;
struct msdos_dir_entry *raw_entry;
loff_t i_pos;
- int err;
+ sector_t blocknr;
+ int err, offset;
if (inode->i_ino == MSDOS_ROOT_INO)
return 0;
@@ -686,7 +686,8 @@ retry:
if (!i_pos)
return 0;
- bh = sb_bread(sb, i_pos >> sbi->dir_per_block_bits);
+ fat_get_blknr_offset(sbi, i_pos, &blocknr, &offset);
+ bh = sb_bread(sb, blocknr);
if (!bh) {
fat_msg(sb, KERN_ERR, "unable to read inode block "
"for updating (i_pos %lld)", i_pos);
@@ -699,8 +700,7 @@ retry:
goto retry;
}
- raw_entry = &((struct msdos_dir_entry *) (bh->b_data))
- [i_pos & (sbi->dir_per_block - 1)];
+ raw_entry = &((struct msdos_dir_entry *) (bh->b_data))[offset];
if (S_ISDIR(inode->i_mode))
raw_entry->size = 0;
else
@@ -761,12 +761,6 @@ static const struct super_operations fat_sops = {
.show_options = fat_show_options,
};
-static const struct export_operations fat_export_ops = {
- .fh_to_dentry = fat_fh_to_dentry,
- .fh_to_parent = fat_fh_to_parent,
- .get_parent = fat_get_parent,
-};
-
static int fat_show_options(struct seq_file *m, struct dentry *root)
{
struct msdos_sb_info *sbi = MSDOS_SB(root->d_sb);
@@ -814,8 +808,6 @@ static int fat_show_options(struct seq_file *m, struct dentry *root)
seq_puts(m, ",usefree");
if (opts->quiet)
seq_puts(m, ",quiet");
- if (opts->nfs)
- seq_puts(m, ",nfs");
if (opts->showexec)
seq_puts(m, ",showexec");
if (opts->sys_immutable)
@@ -849,6 +841,10 @@ static int fat_show_options(struct seq_file *m, struct dentry *root)
seq_puts(m, ",errors=panic");
else
seq_puts(m, ",errors=remount-ro");
+ if (opts->nfs == FAT_NFS_NOSTALE_RO)
+ seq_puts(m, ",nfs=nostale_ro");
+ else if (opts->nfs)
+ seq_puts(m, ",nfs=stale_rw");
if (opts->discard)
seq_puts(m, ",discard");
@@ -865,7 +861,7 @@ enum {
Opt_uni_xl_no, Opt_uni_xl_yes, Opt_nonumtail_no, Opt_nonumtail_yes,
Opt_obsolete, Opt_flush, Opt_tz_utc, Opt_rodir, Opt_err_cont,
Opt_err_panic, Opt_err_ro, Opt_discard, Opt_nfs, Opt_time_offset,
- Opt_err,
+ Opt_nfs_stale_rw, Opt_nfs_nostale_ro, Opt_err,
};
static const match_table_t fat_tokens = {
@@ -895,7 +891,9 @@ static const match_table_t fat_tokens = {
{Opt_err_panic, "errors=panic"},
{Opt_err_ro, "errors=remount-ro"},
{Opt_discard, "discard"},
- {Opt_nfs, "nfs"},
+ {Opt_nfs_stale_rw, "nfs"},
+ {Opt_nfs_stale_rw, "nfs=stale_rw"},
+ {Opt_nfs_nostale_ro, "nfs=nostale_ro"},
{Opt_obsolete, "conv=binary"},
{Opt_obsolete, "conv=text"},
{Opt_obsolete, "conv=auto"},
@@ -1092,6 +1090,12 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
case Opt_err_ro:
opts->errors = FAT_ERRORS_RO;
break;
+ case Opt_nfs_stale_rw:
+ opts->nfs = FAT_NFS_STALE_RW;
+ break;
+ case Opt_nfs_nostale_ro:
+ opts->nfs = FAT_NFS_NOSTALE_RO;
+ break;
/* msdos specific */
case Opt_dots:
@@ -1150,9 +1154,6 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
case Opt_discard:
opts->discard = 1;
break;
- case Opt_nfs:
- opts->nfs = 1;
- break;
/* obsolete mount options */
case Opt_obsolete:
@@ -1183,6 +1184,10 @@ out:
opts->allow_utime = ~opts->fs_dmask & (S_IWGRP | S_IWOTH);
if (opts->unicode_xlate)
opts->utf8 = 0;
+ if (opts->nfs == FAT_NFS_NOSTALE_RO) {
+ sb->s_flags |= MS_RDONLY;
+ sb->s_export_op = &fat_export_ops_nostale;
+ }
return 0;
}
@@ -1193,7 +1198,7 @@ static int fat_read_root(struct inode *inode)
struct msdos_sb_info *sbi = MSDOS_SB(sb);
int error;
- MSDOS_I(inode)->i_pos = 0;
+ MSDOS_I(inode)->i_pos = MSDOS_ROOT_INO;
inode->i_uid = sbi->options.fs_uid;
inode->i_gid = sbi->options.fs_gid;
inode->i_version++;
@@ -1256,6 +1261,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
sb->s_magic = MSDOS_SUPER_MAGIC;
sb->s_op = &fat_sops;
sb->s_export_op = &fat_export_ops;
+ mutex_init(&sbi->nfs_build_inode_lock);
ratelimit_state_init(&sbi->ratelimit, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
diff --git a/fs/fat/nfs.c b/fs/fat/nfs.c
index 499c10438ca2..93e14933dcb6 100644
--- a/fs/fat/nfs.c
+++ b/fs/fat/nfs.c
@@ -14,6 +14,18 @@
#include <linux/exportfs.h>
#include "fat.h"
+struct fat_fid {
+ u32 i_gen;
+ u32 i_pos_low;
+ u16 i_pos_hi;
+ u16 parent_i_pos_hi;
+ u32 parent_i_pos_low;
+ u32 parent_i_gen;
+};
+
+#define FAT_FID_SIZE_WITHOUT_PARENT 3
+#define FAT_FID_SIZE_WITH_PARENT (sizeof(struct fat_fid)/sizeof(u32))
+
/**
* Look up a directory inode given its starting cluster.
*/
@@ -38,63 +50,252 @@ static struct inode *fat_dget(struct super_block *sb, int i_logstart)
return inode;
}
-static struct inode *fat_nfs_get_inode(struct super_block *sb,
- u64 ino, u32 generation)
+static struct inode *fat_ilookup(struct super_block *sb, u64 ino, loff_t i_pos)
{
- struct inode *inode;
+ if (MSDOS_SB(sb)->options.nfs == FAT_NFS_NOSTALE_RO)
+ return fat_iget(sb, i_pos);
- if ((ino < MSDOS_ROOT_INO) || (ino == MSDOS_FSINFO_INO))
- return NULL;
+ else {
+ if ((ino < MSDOS_ROOT_INO) || (ino == MSDOS_FSINFO_INO))
+ return NULL;
+ return ilookup(sb, ino);
+ }
+}
+
+static struct inode *__fat_nfs_get_inode(struct super_block *sb,
+ u64 ino, u32 generation, loff_t i_pos)
+{
+ struct inode *inode = fat_ilookup(sb, ino, i_pos);
- inode = ilookup(sb, ino);
if (inode && generation && (inode->i_generation != generation)) {
iput(inode);
inode = NULL;
}
+ if (inode == NULL && MSDOS_SB(sb)->options.nfs == FAT_NFS_NOSTALE_RO) {
+ struct buffer_head *bh = NULL;
+ struct msdos_dir_entry *de ;
+ sector_t blocknr;
+ int offset;
+ fat_get_blknr_offset(MSDOS_SB(sb), i_pos, &blocknr, &offset);
+ bh = sb_bread(sb, blocknr);
+ if (!bh) {
+ fat_msg(sb, KERN_ERR,
+ "unable to read block(%llu) for building NFS inode",
+ (llu)blocknr);
+ return inode;
+ }
+ de = (struct msdos_dir_entry *)bh->b_data;
+ /* If a file is deleted on server and client is not updated
+ * yet, we must not build the inode upon a lookup call.
+ */
+ if (IS_FREE(de[offset].name))
+ inode = NULL;
+ else
+ inode = fat_build_inode(sb, &de[offset], i_pos);
+ brelse(bh);
+ }
return inode;
}
+static struct inode *fat_nfs_get_inode(struct super_block *sb,
+ u64 ino, u32 generation)
+{
+
+ return __fat_nfs_get_inode(sb, ino, generation, 0);
+}
+
+static int
+fat_encode_fh_nostale(struct inode *inode, __u32 *fh, int *lenp,
+ struct inode *parent)
+{
+ int len = *lenp;
+ struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
+ struct fat_fid *fid = (struct fat_fid *) fh;
+ loff_t i_pos;
+ int type = FILEID_FAT_WITHOUT_PARENT;
+
+ if (parent) {
+ if (len < FAT_FID_SIZE_WITH_PARENT) {
+ *lenp = FAT_FID_SIZE_WITH_PARENT;
+ return FILEID_INVALID;
+ }
+ } else {
+ if (len < FAT_FID_SIZE_WITHOUT_PARENT) {
+ *lenp = FAT_FID_SIZE_WITHOUT_PARENT;
+ return FILEID_INVALID;
+ }
+ }
+
+ i_pos = fat_i_pos_read(sbi, inode);
+ *lenp = FAT_FID_SIZE_WITHOUT_PARENT;
+ fid->i_gen = inode->i_generation;
+ fid->i_pos_low = i_pos & 0xFFFFFFFF;
+ fid->i_pos_hi = (i_pos >> 32) & 0xFFFF;
+ if (parent) {
+ i_pos = fat_i_pos_read(sbi, parent);
+ fid->parent_i_pos_hi = (i_pos >> 32) & 0xFFFF;
+ fid->parent_i_pos_low = i_pos & 0xFFFFFFFF;
+ fid->parent_i_gen = parent->i_generation;
+ type = FILEID_FAT_WITH_PARENT;
+ *lenp = FAT_FID_SIZE_WITH_PARENT;
+ }
+
+ return type;
+}
+
/**
* Map a NFS file handle to a corresponding dentry.
* The dentry may or may not be connected to the filesystem root.
*/
-struct dentry *fat_fh_to_dentry(struct super_block *sb, struct fid *fid,
+static struct dentry *fat_fh_to_dentry(struct super_block *sb, struct fid *fid,
int fh_len, int fh_type)
{
return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
fat_nfs_get_inode);
}
+static struct dentry *fat_fh_to_dentry_nostale(struct super_block *sb,
+ struct fid *fh, int fh_len,
+ int fh_type)
+{
+ struct inode *inode = NULL;
+ struct fat_fid *fid = (struct fat_fid *)fh;
+ loff_t i_pos;
+
+ switch (fh_type) {
+ case FILEID_FAT_WITHOUT_PARENT:
+ if (fh_len < FAT_FID_SIZE_WITHOUT_PARENT)
+ return NULL;
+ break;
+ case FILEID_FAT_WITH_PARENT:
+ if (fh_len < FAT_FID_SIZE_WITH_PARENT)
+ return NULL;
+ break;
+ default:
+ return NULL;
+ }
+ i_pos = fid->i_pos_hi;
+ i_pos = (i_pos << 32) | (fid->i_pos_low);
+ inode = __fat_nfs_get_inode(sb, 0, fid->i_gen, i_pos);
+
+ return d_obtain_alias(inode);
+}
+
/*
* Find the parent for a file specified by NFS handle.
* This requires that the handle contain the i_ino of the parent.
*/
-struct dentry *fat_fh_to_parent(struct super_block *sb, struct fid *fid,
+static struct dentry *fat_fh_to_parent(struct super_block *sb, struct fid *fid,
int fh_len, int fh_type)
{
return generic_fh_to_parent(sb, fid, fh_len, fh_type,
fat_nfs_get_inode);
}
+static struct dentry *fat_fh_to_parent_nostale(struct super_block *sb,
+ struct fid *fh, int fh_len,
+ int fh_type)
+{
+ struct inode *inode = NULL;
+ struct fat_fid *fid = (struct fat_fid *)fh;
+ loff_t i_pos;
+
+ if (fh_len < FAT_FID_SIZE_WITH_PARENT)
+ return NULL;
+
+ switch (fh_type) {
+ case FILEID_FAT_WITH_PARENT:
+ i_pos = fid->parent_i_pos_hi;
+ i_pos = (i_pos << 32) | (fid->parent_i_pos_low);
+ inode = __fat_nfs_get_inode(sb, 0, fid->parent_i_gen, i_pos);
+ break;
+ }
+
+ return d_obtain_alias(inode);
+}
+
+/*
+ * Rebuild the parent for a directory that is not connected
+ * to the filesystem root
+ */
+static
+struct inode *fat_rebuild_parent(struct super_block *sb, int parent_logstart)
+{
+ int search_clus, clus_to_match;
+ struct msdos_dir_entry *de;
+ struct inode *parent = NULL;
+ struct inode *dummy_grand_parent = NULL;
+ struct fat_slot_info sinfo;
+ struct msdos_sb_info *sbi = MSDOS_SB(sb);
+ sector_t blknr = fat_clus_to_blknr(sbi, parent_logstart);
+ struct buffer_head *parent_bh = sb_bread(sb, blknr);
+ if (!parent_bh) {
+ fat_msg(sb, KERN_ERR,
+ "unable to read cluster of parent directory");
+ return NULL;
+ }
+
+ de = (struct msdos_dir_entry *) parent_bh->b_data;
+ clus_to_match = fat_get_start(sbi, &de[0]);
+ search_clus = fat_get_start(sbi, &de[1]);
+
+ dummy_grand_parent = fat_dget(sb, search_clus);
+ if (!dummy_grand_parent) {
+ dummy_grand_parent = new_inode(sb);
+ if (!dummy_grand_parent) {
+ brelse(parent_bh);
+ return parent;
+ }
+
+ dummy_grand_parent->i_ino = iunique(sb, MSDOS_ROOT_INO);
+ fat_fill_inode(dummy_grand_parent, &de[1]);
+ MSDOS_I(dummy_grand_parent)->i_pos = -1;
+ }
+
+ if (!fat_scan_logstart(dummy_grand_parent, clus_to_match, &sinfo))
+ parent = fat_build_inode(sb, sinfo.de, sinfo.i_pos);
+
+ brelse(parent_bh);
+ iput(dummy_grand_parent);
+
+ return parent;
+}
+
/*
* Find the parent for a directory that is not currently connected to
* the filesystem root.
*
* On entry, the caller holds child_dir->d_inode->i_mutex.
*/
-struct dentry *fat_get_parent(struct dentry *child_dir)
+static struct dentry *fat_get_parent(struct dentry *child_dir)
{
struct super_block *sb = child_dir->d_sb;
struct buffer_head *bh = NULL;
struct msdos_dir_entry *de;
struct inode *parent_inode = NULL;
+ struct msdos_sb_info *sbi = MSDOS_SB(sb);
if (!fat_get_dotdot_entry(child_dir->d_inode, &bh, &de)) {
- int parent_logstart = fat_get_start(MSDOS_SB(sb), de);
+ int parent_logstart = fat_get_start(sbi, de);
parent_inode = fat_dget(sb, parent_logstart);
+ if (!parent_inode && sbi->options.nfs == FAT_NFS_NOSTALE_RO)
+ parent_inode = fat_rebuild_parent(sb, parent_logstart);
}
brelse(bh);
return d_obtain_alias(parent_inode);
}
+
+const struct export_operations fat_export_ops = {
+ .fh_to_dentry = fat_fh_to_dentry,
+ .fh_to_parent = fat_fh_to_parent,
+ .get_parent = fat_get_parent,
+};
+
+const struct export_operations fat_export_ops_nostale = {
+ .encode_fh = fat_encode_fh_nostale,
+ .fh_to_dentry = fat_fh_to_dentry_nostale,
+ .fh_to_parent = fat_fh_to_parent_nostale,
+ .get_parent = fat_get_parent,
+};
diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c
index 8179e8bc4a3d..40d13c70ef51 100644
--- a/fs/fscache/stats.c
+++ b/fs/fscache/stats.c
@@ -287,5 +287,5 @@ const struct file_operations fscache_stats_fops = {
.open = fscache_stats_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release,
+ .release = single_release,
};
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 24f414f0ce61..9883694f1e7c 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -1055,7 +1055,7 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask)
if (atomic_read(&bh->b_count))
goto cannot_release;
bd = bh->b_private;
- if (bd && bd->bd_ail)
+ if (bd && bd->bd_tr)
goto cannot_release;
if (buffer_pinned(bh) || buffer_dirty(bh))
goto not_possible;
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 5e83657f046e..1dc9a13ce6bb 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -787,7 +787,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
goto out_rlist;
if (gfs2_rs_active(ip->i_res)) /* needs to be done with the rgrp glock held */
- gfs2_rs_deltree(ip, ip->i_res);
+ gfs2_rs_deltree(ip->i_res);
error = gfs2_trans_begin(sdp, rg_blocks + RES_DINODE +
RES_INDIRECT + RES_STATFS + RES_QUOTA,
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index cf3515546739..9435384562a2 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -912,7 +912,7 @@ int gfs2_glock_wait(struct gfs2_holder *gh)
*/
static void handle_callback(struct gfs2_glock *gl, unsigned int state,
- unsigned long delay)
+ unsigned long delay, bool remote)
{
int bit = delay ? GLF_PENDING_DEMOTE : GLF_DEMOTE;
@@ -925,8 +925,8 @@ static void handle_callback(struct gfs2_glock *gl, unsigned int state,
gl->gl_demote_state = LM_ST_UNLOCKED;
}
if (gl->gl_ops->go_callback)
- gl->gl_ops->go_callback(gl);
- trace_gfs2_demote_rq(gl);
+ gl->gl_ops->go_callback(gl, remote);
+ trace_gfs2_demote_rq(gl, remote);
}
void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...)
@@ -1017,11 +1017,11 @@ do_cancel:
return;
trap_recursive:
- print_symbol(KERN_ERR "original: %s\n", gh2->gh_ip);
+ printk(KERN_ERR "original: %pSR\n", (void *)gh2->gh_ip);
printk(KERN_ERR "pid: %d\n", pid_nr(gh2->gh_owner_pid));
printk(KERN_ERR "lock type: %d req lock state : %d\n",
gh2->gh_gl->gl_name.ln_type, gh2->gh_state);
- print_symbol(KERN_ERR "new: %s\n", gh->gh_ip);
+ printk(KERN_ERR "new: %pSR\n", (void *)gh->gh_ip);
printk(KERN_ERR "pid: %d\n", pid_nr(gh->gh_owner_pid));
printk(KERN_ERR "lock type: %d req lock state : %d\n",
gh->gh_gl->gl_name.ln_type, gh->gh_state);
@@ -1091,7 +1091,7 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
spin_lock(&gl->gl_spin);
if (gh->gh_flags & GL_NOCACHE)
- handle_callback(gl, LM_ST_UNLOCKED, 0);
+ handle_callback(gl, LM_ST_UNLOCKED, 0, false);
list_del_init(&gh->gh_list);
if (find_first_holder(gl) == NULL) {
@@ -1279,19 +1279,6 @@ void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs)
gfs2_glock_dq(&ghs[num_gh]);
}
-/**
- * gfs2_glock_dq_uninit_m - release multiple glocks
- * @num_gh: the number of structures
- * @ghs: an array of struct gfs2_holder structures
- *
- */
-
-void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs)
-{
- while (num_gh--)
- gfs2_glock_dq_uninit(&ghs[num_gh]);
-}
-
void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state)
{
unsigned long delay = 0;
@@ -1309,7 +1296,7 @@ void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state)
}
spin_lock(&gl->gl_spin);
- handle_callback(gl, state, delay);
+ handle_callback(gl, state, delay, true);
spin_unlock(&gl->gl_spin);
if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
gfs2_glock_put(gl);
@@ -1422,7 +1409,7 @@ __acquires(&lru_lock)
spin_unlock(&lru_lock);
spin_lock(&gl->gl_spin);
if (demote_ok(gl))
- handle_callback(gl, LM_ST_UNLOCKED, 0);
+ handle_callback(gl, LM_ST_UNLOCKED, 0, false);
WARN_ON(!test_and_clear_bit(GLF_LOCK, &gl->gl_flags));
smp_mb__after_clear_bit();
if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
@@ -1547,7 +1534,7 @@ static void clear_glock(struct gfs2_glock *gl)
spin_lock(&gl->gl_spin);
if (gl->gl_state != LM_ST_UNLOCKED)
- handle_callback(gl, LM_ST_UNLOCKED, 0);
+ handle_callback(gl, LM_ST_UNLOCKED, 0, false);
spin_unlock(&gl->gl_spin);
gfs2_glock_hold(gl);
if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
@@ -1590,6 +1577,7 @@ static void dump_glock_func(struct gfs2_glock *gl)
void gfs2_gl_hash_clear(struct gfs2_sbd *sdp)
{
set_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags);
+ flush_workqueue(glock_workqueue);
glock_hash_walk(clear_glock, sdp);
flush_workqueue(glock_workqueue);
wait_event(sdp->sd_glock_wait, atomic_read(&sdp->sd_glock_disposal) == 0);
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index fd580b7861d5..69f66e3d22bf 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -201,7 +201,6 @@ extern int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number,
struct gfs2_holder *gh);
extern int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs);
extern void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs);
-extern void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs);
extern int gfs2_dump_glock(struct seq_file *seq, const struct gfs2_glock *gl);
#define GLOCK_BUG_ON(gl,x) do { if (unlikely(x)) { gfs2_dump_glock(NULL, gl); BUG(); } } while(0)
extern __printf(2, 3)
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 444b6503ebc4..c66e99c97571 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -515,12 +515,12 @@ static int trans_go_demote_ok(const struct gfs2_glock *gl)
*
* gl_spin lock is held while calling this
*/
-static void iopen_go_callback(struct gfs2_glock *gl)
+static void iopen_go_callback(struct gfs2_glock *gl, bool remote)
{
struct gfs2_inode *ip = (struct gfs2_inode *)gl->gl_object;
struct gfs2_sbd *sdp = gl->gl_sbd;
- if (sdp->sd_vfs->s_flags & MS_RDONLY)
+ if (!remote || (sdp->sd_vfs->s_flags & MS_RDONLY))
return;
if (gl->gl_demote_state == LM_ST_UNLOCKED &&
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 5c29216e9cc1..26aabd7caba7 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -31,7 +31,6 @@ struct gfs2_holder;
struct gfs2_glock;
struct gfs2_quota_data;
struct gfs2_trans;
-struct gfs2_ail;
struct gfs2_jdesc;
struct gfs2_sbd;
struct lm_lockops;
@@ -53,7 +52,7 @@ struct gfs2_log_header_host {
struct gfs2_log_operations {
void (*lo_before_commit) (struct gfs2_sbd *sdp);
- void (*lo_after_commit) (struct gfs2_sbd *sdp, struct gfs2_ail *ai);
+ void (*lo_after_commit) (struct gfs2_sbd *sdp, struct gfs2_trans *tr);
void (*lo_before_scan) (struct gfs2_jdesc *jd,
struct gfs2_log_header_host *head, int pass);
int (*lo_scan_elements) (struct gfs2_jdesc *jd, unsigned int start,
@@ -139,7 +138,7 @@ struct gfs2_bufdata {
struct list_head bd_list;
const struct gfs2_log_operations *bd_ops;
- struct gfs2_ail *bd_ail;
+ struct gfs2_trans *bd_tr;
struct list_head bd_ail_st_list;
struct list_head bd_ail_gl_list;
};
@@ -211,7 +210,7 @@ struct gfs2_glock_operations {
int (*go_lock) (struct gfs2_holder *gh);
void (*go_unlock) (struct gfs2_holder *gh);
int (*go_dump)(struct seq_file *seq, const struct gfs2_glock *gl);
- void (*go_callback) (struct gfs2_glock *gl);
+ void (*go_callback)(struct gfs2_glock *gl, bool remote);
const int go_type;
const unsigned long go_flags;
#define GLOF_ASPACE 1
@@ -433,6 +432,7 @@ struct gfs2_trans {
struct gfs2_holder tr_t_gh;
int tr_touched;
+ int tr_attached;
unsigned int tr_num_buf_new;
unsigned int tr_num_databuf_new;
@@ -440,14 +440,12 @@ struct gfs2_trans {
unsigned int tr_num_databuf_rm;
unsigned int tr_num_revoke;
unsigned int tr_num_revoke_rm;
-};
-struct gfs2_ail {
- struct list_head ai_list;
+ struct list_head tr_list;
- unsigned int ai_first;
- struct list_head ai_ail1_list;
- struct list_head ai_ail2_list;
+ unsigned int tr_first;
+ struct list_head tr_ail1_list;
+ struct list_head tr_ail2_list;
};
struct gfs2_journal_extent {
@@ -710,6 +708,7 @@ struct gfs2_sbd {
spinlock_t sd_log_lock;
+ struct gfs2_trans *sd_log_tr;
unsigned int sd_log_blks_reserved;
unsigned int sd_log_commited_buf;
unsigned int sd_log_commited_databuf;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index cc00bd1d1f87..8833a4f264e3 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -392,11 +392,15 @@ static int alloc_dinode(struct gfs2_inode *ip, u32 flags)
int error;
int dblocks = 1;
- error = gfs2_inplace_reserve(ip, RES_DINODE, flags);
+ error = gfs2_quota_lock_check(ip);
if (error)
goto out;
- error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS, 0);
+ error = gfs2_inplace_reserve(ip, RES_DINODE, flags);
+ if (error)
+ goto out_quota;
+
+ error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS + RES_QUOTA, 0);
if (error)
goto out_ipreserv;
@@ -409,6 +413,8 @@ static int alloc_dinode(struct gfs2_inode *ip, u32 flags)
out_ipreserv:
gfs2_inplace_release(ip);
+out_quota:
+ gfs2_quota_unlock(ip);
out:
return error;
}
@@ -440,59 +446,27 @@ static void gfs2_init_dir(struct buffer_head *dibh,
*/
static void init_dinode(struct gfs2_inode *dip, struct gfs2_inode *ip,
- const char *symname, struct buffer_head **bhp)
+ const char *symname)
{
- struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct gfs2_dinode *di;
struct buffer_head *dibh;
- struct timespec tv = CURRENT_TIME;
dibh = gfs2_meta_new(ip->i_gl, ip->i_no_addr);
gfs2_trans_add_meta(ip->i_gl, dibh);
- gfs2_metatype_set(dibh, GFS2_METATYPE_DI, GFS2_FORMAT_DI);
- gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
di = (struct gfs2_dinode *)dibh->b_data;
+ gfs2_dinode_out(ip, di);
- di->di_num.no_formal_ino = cpu_to_be64(ip->i_no_formal_ino);
- di->di_num.no_addr = cpu_to_be64(ip->i_no_addr);
- di->di_mode = cpu_to_be32(ip->i_inode.i_mode);
- di->di_uid = cpu_to_be32(i_uid_read(&ip->i_inode));
- di->di_gid = cpu_to_be32(i_gid_read(&ip->i_inode));
- di->di_nlink = 0;
- di->di_size = cpu_to_be64(ip->i_inode.i_size);
- di->di_blocks = cpu_to_be64(1);
- di->di_atime = di->di_mtime = di->di_ctime = cpu_to_be64(tv.tv_sec);
di->di_major = cpu_to_be32(MAJOR(ip->i_inode.i_rdev));
di->di_minor = cpu_to_be32(MINOR(ip->i_inode.i_rdev));
- di->di_goal_meta = di->di_goal_data = cpu_to_be64(ip->i_no_addr);
- di->di_generation = cpu_to_be64(ip->i_generation);
- di->di_flags = 0;
di->__pad1 = 0;
- di->di_payload_format = cpu_to_be32(S_ISDIR(ip->i_inode.i_mode) ? GFS2_FORMAT_DE : 0);
- di->di_height = 0;
di->__pad2 = 0;
di->__pad3 = 0;
- di->di_depth = 0;
- di->di_entries = 0;
memset(&di->__pad4, 0, sizeof(di->__pad4));
- di->di_eattr = 0;
- di->di_atime_nsec = cpu_to_be32(tv.tv_nsec);
- di->di_mtime_nsec = cpu_to_be32(tv.tv_nsec);
- di->di_ctime_nsec = cpu_to_be32(tv.tv_nsec);
memset(&di->di_reserved, 0, sizeof(di->di_reserved));
+ gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
switch(ip->i_inode.i_mode & S_IFMT) {
- case S_IFREG:
- if ((dip->i_diskflags & GFS2_DIF_INHERIT_JDATA) ||
- gfs2_tune_get(sdp, gt_new_files_jdata))
- di->di_flags |= cpu_to_be32(GFS2_DIF_JDATA);
- break;
case S_IFDIR:
- di->di_flags |= cpu_to_be32(dip->i_diskflags &
- GFS2_DIF_INHERIT_JDATA);
- di->di_flags |= cpu_to_be32(GFS2_DIF_JDATA);
- di->di_size = cpu_to_be64(sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode));
- di->di_entries = cpu_to_be32(2);
gfs2_init_dir(dibh, dip);
break;
case S_IFLNK:
@@ -501,63 +475,17 @@ static void init_dinode(struct gfs2_inode *dip, struct gfs2_inode *ip,
}
set_buffer_uptodate(dibh);
-
- *bhp = dibh;
-}
-
-static int make_dinode(struct gfs2_inode *dip, struct gfs2_inode *ip,
- const char *symname, struct buffer_head **bhp)
-{
- struct inode *inode = &ip->i_inode;
- struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
- int error;
-
- error = gfs2_rindex_update(sdp);
- if (error)
- return error;
-
- error = gfs2_quota_lock(dip, inode->i_uid, inode->i_gid);
- if (error)
- return error;
-
- error = gfs2_quota_check(dip, inode->i_uid, inode->i_gid);
- if (error)
- goto out_quota;
-
- error = gfs2_trans_begin(sdp, RES_DINODE + RES_QUOTA, 0);
- if (error)
- goto out_quota;
-
- init_dinode(dip, ip, symname, bhp);
- gfs2_quota_change(dip, +1, inode->i_uid, inode->i_gid);
- gfs2_trans_end(sdp);
-
-out_quota:
- gfs2_quota_unlock(dip);
- return error;
+ brelse(dibh);
}
static int link_dinode(struct gfs2_inode *dip, const struct qstr *name,
- struct gfs2_inode *ip)
+ struct gfs2_inode *ip, int arq)
{
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
- int alloc_required;
- struct buffer_head *dibh;
int error;
- error = gfs2_rindex_update(sdp);
- if (error)
- return error;
-
- error = gfs2_quota_lock(dip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
- if (error)
- goto fail;
-
- error = alloc_required = gfs2_diradd_alloc_required(&dip->i_inode, name);
- if (alloc_required < 0)
- goto fail_quota_locks;
- if (alloc_required) {
- error = gfs2_quota_check(dip, dip->i_inode.i_uid, dip->i_inode.i_gid);
+ if (arq) {
+ error = gfs2_quota_lock_check(dip);
if (error)
goto fail_quota_locks;
@@ -581,26 +509,12 @@ static int link_dinode(struct gfs2_inode *dip, const struct qstr *name,
if (error)
goto fail_end_trans;
- error = gfs2_meta_inode_buffer(ip, &dibh);
- if (error)
- goto fail_end_trans;
- set_nlink(&ip->i_inode, S_ISDIR(ip->i_inode.i_mode) ? 2 : 1);
- gfs2_trans_add_meta(ip->i_gl, dibh);
- gfs2_dinode_out(ip, dibh->b_data);
- brelse(dibh);
- return 0;
-
fail_end_trans:
gfs2_trans_end(sdp);
-
fail_ipreserv:
- if (alloc_required)
- gfs2_inplace_release(dip);
-
+ gfs2_inplace_release(dip);
fail_quota_locks:
gfs2_quota_unlock(dip);
-
-fail:
return error;
}
@@ -650,8 +564,8 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct gfs2_glock *io_gl;
int error;
- struct buffer_head *bh = NULL;
u32 aflags = 0;
+ int arq;
if (!name->len || name->len > GFS2_FNAMESIZE)
return -ENAMETOOLONG;
@@ -660,6 +574,10 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
if (error)
return error;
+ error = gfs2_rindex_update(sdp);
+ if (error)
+ return error;
+
error = gfs2_glock_nq_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
if (error)
goto fail;
@@ -674,22 +592,48 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
if (error)
goto fail_gunlock;
+ arq = error = gfs2_diradd_alloc_required(dir, name);
+ if (error < 0)
+ goto fail_gunlock;
+
inode = new_inode(sdp->sd_vfs);
- if (!inode) {
- gfs2_glock_dq_uninit(ghs);
- return -ENOMEM;
- }
+ error = -ENOMEM;
+ if (!inode)
+ goto fail_gunlock;
+
ip = GFS2_I(inode);
error = gfs2_rs_alloc(ip);
if (error)
goto fail_free_inode;
- set_bit(GIF_INVALID, &ip->i_flags);
inode->i_mode = mode;
+ set_nlink(inode, S_ISDIR(mode) ? 2 : 1);
inode->i_rdev = dev;
inode->i_size = size;
+ inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ gfs2_set_inode_blocks(inode, 1);
munge_mode_uid_gid(dip, inode);
ip->i_goal = dip->i_goal;
+ ip->i_diskflags = 0;
+ ip->i_eattr = 0;
+ ip->i_height = 0;
+ ip->i_depth = 0;
+ ip->i_entries = 0;
+
+ switch(mode & S_IFMT) {
+ case S_IFREG:
+ if ((dip->i_diskflags & GFS2_DIF_INHERIT_JDATA) ||
+ gfs2_tune_get(sdp, gt_new_files_jdata))
+ ip->i_diskflags |= GFS2_DIF_JDATA;
+ gfs2_set_aops(inode);
+ break;
+ case S_IFDIR:
+ ip->i_diskflags |= (dip->i_diskflags & GFS2_DIF_INHERIT_JDATA);
+ ip->i_diskflags |= GFS2_DIF_JDATA;
+ ip->i_entries = 2;
+ break;
+ }
+ gfs2_set_inode_flags(inode);
if ((GFS2_I(sdp->sd_root_dir->d_inode) == dip) ||
(dip->i_diskflags & GFS2_DIF_TOPDIR))
@@ -708,10 +652,13 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
if (error)
goto fail_free_inode;
- error = make_dinode(dip, ip, symname, &bh);
+ error = gfs2_trans_begin(sdp, RES_DINODE, 0);
if (error)
goto fail_gunlock2;
+ init_dinode(dip, ip, symname);
+ gfs2_trans_end(sdp);
+
error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
if (error)
goto fail_gunlock2;
@@ -725,10 +672,6 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
gfs2_set_iop(inode);
insert_inode_hash(inode);
- error = gfs2_inode_refresh(ip);
- if (error)
- goto fail_gunlock3;
-
error = gfs2_acl_create(dip, inode);
if (error)
goto fail_gunlock3;
@@ -737,18 +680,13 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
if (error)
goto fail_gunlock3;
- error = link_dinode(dip, name, ip);
+ error = link_dinode(dip, name, ip, arq);
if (error)
goto fail_gunlock3;
- if (bh)
- brelse(bh);
-
- gfs2_trans_end(sdp);
- gfs2_inplace_release(dip);
- gfs2_quota_unlock(dip);
mark_inode_dirty(inode);
- gfs2_glock_dq_uninit_m(2, ghs);
+ gfs2_glock_dq_uninit(ghs);
+ gfs2_glock_dq_uninit(ghs + 1);
d_instantiate(dentry, inode);
return 0;
@@ -769,12 +707,12 @@ fail_free_inode:
fail_gunlock:
gfs2_glock_dq_uninit(ghs);
if (inode && !IS_ERR(inode)) {
+ clear_nlink(inode);
+ mark_inode_dirty(inode);
set_bit(GIF_ALLOC_FAILED, &GFS2_I(inode)->i_flags);
iput(inode);
}
fail:
- if (bh)
- brelse(bh);
return error;
}
@@ -1151,7 +1089,9 @@ static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
- return gfs2_create_inode(dir, dentry, S_IFDIR | mode, 0, NULL, 0, 0);
+ struct gfs2_sbd *sdp = GFS2_SB(dir);
+ unsigned dsize = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode);
+ return gfs2_create_inode(dir, dentry, S_IFDIR | mode, 0, NULL, dsize, 0);
}
/**
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 9a2ca8be7647..b404f4853034 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -73,7 +73,7 @@ unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
void gfs2_remove_from_ail(struct gfs2_bufdata *bd)
{
- bd->bd_ail = NULL;
+ bd->bd_tr = NULL;
list_del_init(&bd->bd_ail_st_list);
list_del_init(&bd->bd_ail_gl_list);
atomic_dec(&bd->bd_gl->gl_ail_count);
@@ -90,7 +90,7 @@ void gfs2_remove_from_ail(struct gfs2_bufdata *bd)
static int gfs2_ail1_start_one(struct gfs2_sbd *sdp,
struct writeback_control *wbc,
- struct gfs2_ail *ai)
+ struct gfs2_trans *tr)
__releases(&sdp->sd_ail_lock)
__acquires(&sdp->sd_ail_lock)
{
@@ -99,15 +99,15 @@ __acquires(&sdp->sd_ail_lock)
struct gfs2_bufdata *bd, *s;
struct buffer_head *bh;
- list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list, bd_ail_st_list) {
+ list_for_each_entry_safe_reverse(bd, s, &tr->tr_ail1_list, bd_ail_st_list) {
bh = bd->bd_bh;
- gfs2_assert(sdp, bd->bd_ail == ai);
+ gfs2_assert(sdp, bd->bd_tr == tr);
if (!buffer_busy(bh)) {
if (!buffer_uptodate(bh))
gfs2_io_error_bh(sdp, bh);
- list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
+ list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list);
continue;
}
@@ -116,7 +116,7 @@ __acquires(&sdp->sd_ail_lock)
if (gl == bd->bd_gl)
continue;
gl = bd->bd_gl;
- list_move(&bd->bd_ail_st_list, &ai->ai_ail1_list);
+ list_move(&bd->bd_ail_st_list, &tr->tr_ail1_list);
mapping = bh->b_page->mapping;
if (!mapping)
continue;
@@ -144,15 +144,15 @@ __acquires(&sdp->sd_ail_lock)
void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc)
{
struct list_head *head = &sdp->sd_ail1_list;
- struct gfs2_ail *ai;
+ struct gfs2_trans *tr;
trace_gfs2_ail_flush(sdp, wbc, 1);
spin_lock(&sdp->sd_ail_lock);
restart:
- list_for_each_entry_reverse(ai, head, ai_list) {
+ list_for_each_entry_reverse(tr, head, tr_list) {
if (wbc->nr_to_write <= 0)
break;
- if (gfs2_ail1_start_one(sdp, wbc, ai))
+ if (gfs2_ail1_start_one(sdp, wbc, tr))
goto restart;
}
spin_unlock(&sdp->sd_ail_lock);
@@ -183,20 +183,20 @@ static void gfs2_ail1_start(struct gfs2_sbd *sdp)
*
*/
-static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
struct gfs2_bufdata *bd, *s;
struct buffer_head *bh;
- list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list,
+ list_for_each_entry_safe_reverse(bd, s, &tr->tr_ail1_list,
bd_ail_st_list) {
bh = bd->bd_bh;
- gfs2_assert(sdp, bd->bd_ail == ai);
+ gfs2_assert(sdp, bd->bd_tr == tr);
if (buffer_busy(bh))
continue;
if (!buffer_uptodate(bh))
gfs2_io_error_bh(sdp, bh);
- list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
+ list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list);
}
}
@@ -210,14 +210,14 @@ static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
static int gfs2_ail1_empty(struct gfs2_sbd *sdp)
{
- struct gfs2_ail *ai, *s;
+ struct gfs2_trans *tr, *s;
int ret;
spin_lock(&sdp->sd_ail_lock);
- list_for_each_entry_safe_reverse(ai, s, &sdp->sd_ail1_list, ai_list) {
- gfs2_ail1_empty_one(sdp, ai);
- if (list_empty(&ai->ai_ail1_list))
- list_move(&ai->ai_list, &sdp->sd_ail2_list);
+ list_for_each_entry_safe_reverse(tr, s, &sdp->sd_ail1_list, tr_list) {
+ gfs2_ail1_empty_one(sdp, tr);
+ if (list_empty(&tr->tr_ail1_list))
+ list_move(&tr->tr_list, &sdp->sd_ail2_list);
else
break;
}
@@ -229,13 +229,13 @@ static int gfs2_ail1_empty(struct gfs2_sbd *sdp)
static void gfs2_ail1_wait(struct gfs2_sbd *sdp)
{
- struct gfs2_ail *ai;
+ struct gfs2_trans *tr;
struct gfs2_bufdata *bd;
struct buffer_head *bh;
spin_lock(&sdp->sd_ail_lock);
- list_for_each_entry_reverse(ai, &sdp->sd_ail1_list, ai_list) {
- list_for_each_entry(bd, &ai->ai_ail1_list, bd_ail_st_list) {
+ list_for_each_entry_reverse(tr, &sdp->sd_ail1_list, tr_list) {
+ list_for_each_entry(bd, &tr->tr_ail1_list, bd_ail_st_list) {
bh = bd->bd_bh;
if (!buffer_locked(bh))
continue;
@@ -256,40 +256,40 @@ static void gfs2_ail1_wait(struct gfs2_sbd *sdp)
*
*/
-static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
- struct list_head *head = &ai->ai_ail2_list;
+ struct list_head *head = &tr->tr_ail2_list;
struct gfs2_bufdata *bd;
while (!list_empty(head)) {
bd = list_entry(head->prev, struct gfs2_bufdata,
bd_ail_st_list);
- gfs2_assert(sdp, bd->bd_ail == ai);
+ gfs2_assert(sdp, bd->bd_tr == tr);
gfs2_remove_from_ail(bd);
}
}
static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail)
{
- struct gfs2_ail *ai, *safe;
+ struct gfs2_trans *tr, *safe;
unsigned int old_tail = sdp->sd_log_tail;
int wrap = (new_tail < old_tail);
int a, b, rm;
spin_lock(&sdp->sd_ail_lock);
- list_for_each_entry_safe(ai, safe, &sdp->sd_ail2_list, ai_list) {
- a = (old_tail <= ai->ai_first);
- b = (ai->ai_first < new_tail);
+ list_for_each_entry_safe(tr, safe, &sdp->sd_ail2_list, tr_list) {
+ a = (old_tail <= tr->tr_first);
+ b = (tr->tr_first < new_tail);
rm = (wrap) ? (a || b) : (a && b);
if (!rm)
continue;
- gfs2_ail2_empty_one(sdp, ai);
- list_del(&ai->ai_list);
- gfs2_assert_warn(sdp, list_empty(&ai->ai_ail1_list));
- gfs2_assert_warn(sdp, list_empty(&ai->ai_ail2_list));
- kfree(ai);
+ gfs2_ail2_empty_one(sdp, tr);
+ list_del(&tr->tr_list);
+ gfs2_assert_warn(sdp, list_empty(&tr->tr_ail1_list));
+ gfs2_assert_warn(sdp, list_empty(&tr->tr_ail2_list));
+ kfree(tr);
}
spin_unlock(&sdp->sd_ail_lock);
@@ -435,7 +435,7 @@ static unsigned int calc_reserved(struct gfs2_sbd *sdp)
static unsigned int current_tail(struct gfs2_sbd *sdp)
{
- struct gfs2_ail *ai;
+ struct gfs2_trans *tr;
unsigned int tail;
spin_lock(&sdp->sd_ail_lock);
@@ -443,8 +443,9 @@ static unsigned int current_tail(struct gfs2_sbd *sdp)
if (list_empty(&sdp->sd_ail1_list)) {
tail = sdp->sd_log_head;
} else {
- ai = list_entry(sdp->sd_ail1_list.prev, struct gfs2_ail, ai_list);
- tail = ai->ai_first;
+ tr = list_entry(sdp->sd_ail1_list.prev, struct gfs2_trans,
+ tr_list);
+ tail = tr->tr_first;
}
spin_unlock(&sdp->sd_ail_lock);
@@ -600,7 +601,7 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags)
void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
{
- struct gfs2_ail *ai;
+ struct gfs2_trans *tr;
down_write(&sdp->sd_log_flush_lock);
@@ -611,9 +612,12 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
}
trace_gfs2_log_flush(sdp, 1);
- ai = kzalloc(sizeof(struct gfs2_ail), GFP_NOFS | __GFP_NOFAIL);
- INIT_LIST_HEAD(&ai->ai_ail1_list);
- INIT_LIST_HEAD(&ai->ai_ail2_list);
+ tr = sdp->sd_log_tr;
+ if (tr) {
+ sdp->sd_log_tr = NULL;
+ INIT_LIST_HEAD(&tr->tr_ail1_list);
+ INIT_LIST_HEAD(&tr->tr_ail2_list);
+ }
if (sdp->sd_log_num_buf != sdp->sd_log_commited_buf) {
printk(KERN_INFO "GFS2: log buf %u %u\n", sdp->sd_log_num_buf,
@@ -630,7 +634,8 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
sdp->sd_log_flush_head = sdp->sd_log_head;
sdp->sd_log_flush_wrapped = 0;
- ai->ai_first = sdp->sd_log_flush_head;
+ if (tr)
+ tr->tr_first = sdp->sd_log_flush_head;
gfs2_ordered_write(sdp);
lops_before_commit(sdp);
@@ -643,7 +648,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
trace_gfs2_log_blocks(sdp, -1);
log_write_header(sdp, 0);
}
- lops_after_commit(sdp, ai);
+ lops_after_commit(sdp, tr);
gfs2_log_lock(sdp);
sdp->sd_log_head = sdp->sd_log_flush_head;
@@ -653,16 +658,16 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
sdp->sd_log_commited_revoke = 0;
spin_lock(&sdp->sd_ail_lock);
- if (!list_empty(&ai->ai_ail1_list)) {
- list_add(&ai->ai_list, &sdp->sd_ail1_list);
- ai = NULL;
+ if (tr && !list_empty(&tr->tr_ail1_list)) {
+ list_add(&tr->tr_list, &sdp->sd_ail1_list);
+ tr = NULL;
}
spin_unlock(&sdp->sd_ail_lock);
gfs2_log_unlock(sdp);
trace_gfs2_log_flush(sdp, 0);
up_write(&sdp->sd_log_flush_lock);
- kfree(ai);
+ kfree(tr);
}
static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
@@ -687,6 +692,12 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
sdp->sd_jdesc->jd_blocks);
sdp->sd_log_blks_reserved = reserved;
+ if (sdp->sd_log_tr == NULL &&
+ (tr->tr_num_buf_new || tr->tr_num_databuf_new)) {
+ gfs2_assert_withdraw(sdp, tr->tr_t_gh.gh_gl);
+ sdp->sd_log_tr = tr;
+ tr->tr_attached = 1;
+ }
gfs2_log_unlock(sdp);
}
@@ -708,7 +719,6 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
log_refund(sdp, tr);
- up_read(&sdp->sd_log_flush_lock);
if (atomic_read(&sdp->sd_log_pinned) > atomic_read(&sdp->sd_log_thresh1) ||
((sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free)) >
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index a5055977a214..7318abf9d0fb 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -53,8 +53,8 @@ void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
* to in-place disk block, remove it from the AIL.
*/
spin_lock(&sdp->sd_ail_lock);
- if (bd->bd_ail)
- list_move(&bd->bd_ail_st_list, &bd->bd_ail->ai_ail2_list);
+ if (bd->bd_tr)
+ list_move(&bd->bd_ail_st_list, &bd->bd_tr->tr_ail2_list);
spin_unlock(&sdp->sd_ail_lock);
get_bh(bh);
atomic_inc(&sdp->sd_log_pinned);
@@ -94,7 +94,7 @@ static void maybe_release_space(struct gfs2_bufdata *bd)
*/
static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
- struct gfs2_ail *ai)
+ struct gfs2_trans *tr)
{
struct gfs2_bufdata *bd = bh->b_private;
@@ -109,7 +109,7 @@ static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
maybe_release_space(bd);
spin_lock(&sdp->sd_ail_lock);
- if (bd->bd_ail) {
+ if (bd->bd_tr) {
list_del(&bd->bd_ail_st_list);
brelse(bh);
} else {
@@ -117,8 +117,8 @@ static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
list_add(&bd->bd_ail_gl_list, &gl->gl_ail_list);
atomic_inc(&gl->gl_ail_count);
}
- bd->bd_ail = ai;
- list_add(&bd->bd_ail_st_list, &ai->ai_ail1_list);
+ bd->bd_tr = tr;
+ list_add(&bd->bd_ail_st_list, &tr->tr_ail1_list);
spin_unlock(&sdp->sd_ail_lock);
clear_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
@@ -480,17 +480,22 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp)
&sdp->sd_log_le_buf, 0);
}
-static void buf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+static void buf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
struct list_head *head = &sdp->sd_log_le_buf;
struct gfs2_bufdata *bd;
+ if (tr == NULL) {
+ gfs2_assert(sdp, list_empty(head));
+ return;
+ }
+
while (!list_empty(head)) {
bd = list_entry(head->next, struct gfs2_bufdata, bd_list);
list_del_init(&bd->bd_list);
sdp->sd_log_num_buf--;
- gfs2_unpin(sdp, bd->bd_bh, ai);
+ gfs2_unpin(sdp, bd->bd_bh, tr);
}
gfs2_assert_warn(sdp, !sdp->sd_log_num_buf);
}
@@ -613,7 +618,7 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
gfs2_log_write_page(sdp, page);
}
-static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
struct list_head *head = &sdp->sd_log_le_revoke;
struct gfs2_bufdata *bd;
@@ -791,16 +796,21 @@ static void databuf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
jd->jd_jid, sdp->sd_replayed_blocks, sdp->sd_found_blocks);
}
-static void databuf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+static void databuf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
struct list_head *head = &sdp->sd_log_le_databuf;
struct gfs2_bufdata *bd;
+ if (tr == NULL) {
+ gfs2_assert(sdp, list_empty(head));
+ return;
+ }
+
while (!list_empty(head)) {
bd = list_entry(head->next, struct gfs2_bufdata, bd_list);
list_del_init(&bd->bd_list);
sdp->sd_log_num_databuf--;
- gfs2_unpin(sdp, bd->bd_bh, ai);
+ gfs2_unpin(sdp, bd->bd_bh, tr);
}
gfs2_assert_warn(sdp, !sdp->sd_log_num_databuf);
}
diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h
index ba77b7da8325..87e062e05c92 100644
--- a/fs/gfs2/lops.h
+++ b/fs/gfs2/lops.h
@@ -55,12 +55,13 @@ static inline void lops_before_commit(struct gfs2_sbd *sdp)
gfs2_log_ops[x]->lo_before_commit(sdp);
}
-static inline void lops_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+static inline void lops_after_commit(struct gfs2_sbd *sdp,
+ struct gfs2_trans *tr)
{
int x;
for (x = 0; gfs2_log_ops[x]; x++)
if (gfs2_log_ops[x]->lo_after_commit)
- gfs2_log_ops[x]->lo_after_commit(sdp, ai);
+ gfs2_log_ops[x]->lo_after_commit(sdp, tr);
}
static inline void lops_before_scan(struct gfs2_jdesc *jd,
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index b059bbb5059e..1a89afb68472 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -295,7 +295,7 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int
}
if (bd) {
spin_lock(&sdp->sd_ail_lock);
- if (bd->bd_ail) {
+ if (bd->bd_tr) {
gfs2_remove_from_ail(bd);
bh->b_private = NULL;
bd->bd_bh = NULL;
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 5a51265a4341..0c5a575b513e 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -592,7 +592,7 @@ static void dump_rs(struct seq_file *seq, const struct gfs2_blkreserv *rs)
* @rs: The reservation to remove
*
*/
-static void __rs_deltree(struct gfs2_inode *ip, struct gfs2_blkreserv *rs)
+static void __rs_deltree(struct gfs2_blkreserv *rs)
{
struct gfs2_rgrpd *rgd;
@@ -605,7 +605,7 @@ static void __rs_deltree(struct gfs2_inode *ip, struct gfs2_blkreserv *rs)
RB_CLEAR_NODE(&rs->rs_node);
if (rs->rs_free) {
- /* return reserved blocks to the rgrp and the ip */
+ /* return reserved blocks to the rgrp */
BUG_ON(rs->rs_rbm.rgd->rd_reserved < rs->rs_free);
rs->rs_rbm.rgd->rd_reserved -= rs->rs_free;
rs->rs_free = 0;
@@ -619,14 +619,14 @@ static void __rs_deltree(struct gfs2_inode *ip, struct gfs2_blkreserv *rs)
* @rs: The reservation to remove
*
*/
-void gfs2_rs_deltree(struct gfs2_inode *ip, struct gfs2_blkreserv *rs)
+void gfs2_rs_deltree(struct gfs2_blkreserv *rs)
{
struct gfs2_rgrpd *rgd;
rgd = rs->rs_rbm.rgd;
if (rgd) {
spin_lock(&rgd->rd_rsspin);
- __rs_deltree(ip, rs);
+ __rs_deltree(rs);
spin_unlock(&rgd->rd_rsspin);
}
}
@@ -640,7 +640,7 @@ void gfs2_rs_delete(struct gfs2_inode *ip)
{
down_write(&ip->i_rw_mutex);
if (ip->i_res) {
- gfs2_rs_deltree(ip, ip->i_res);
+ gfs2_rs_deltree(ip->i_res);
BUG_ON(ip->i_res->rs_free);
kmem_cache_free(gfs2_rsrv_cachep, ip->i_res);
ip->i_res = NULL;
@@ -664,7 +664,7 @@ static void return_all_reservations(struct gfs2_rgrpd *rgd)
spin_lock(&rgd->rd_rsspin);
while ((n = rb_first(&rgd->rd_rstree))) {
rs = rb_entry(n, struct gfs2_blkreserv, rs_node);
- __rs_deltree(NULL, rs);
+ __rs_deltree(rs);
}
spin_unlock(&rgd->rd_rsspin);
}
@@ -1874,7 +1874,7 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, u32 requested, u32 aflags)
/* Drop reservation, if we couldn't use reserved rgrp */
if (gfs2_rs_active(rs))
- gfs2_rs_deltree(ip, rs);
+ gfs2_rs_deltree(rs);
check_rgrp:
/* Check for unlinked inodes which can be reclaimed */
if (rs->rs_rbm.rgd->rd_flags & GFS2_RDF_CHECK)
@@ -2087,7 +2087,7 @@ static void gfs2_adjust_reservation(struct gfs2_inode *ip,
if (rs->rs_free && !ret)
goto out;
}
- __rs_deltree(ip, rs);
+ __rs_deltree(rs);
}
out:
spin_unlock(&rgd->rd_rsspin);
@@ -2180,13 +2180,7 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks,
if (dinode)
gfs2_trans_add_unrevoke(sdp, block, 1);
- /*
- * This needs reviewing to see why we cannot do the quota change
- * at this point in the dinode case.
- */
- if (ndata)
- gfs2_quota_change(ip, ndata, ip->i_inode.i_uid,
- ip->i_inode.i_gid);
+ gfs2_quota_change(ip, *nblocks, ip->i_inode.i_uid, ip->i_inode.i_gid);
rbm.rgd->rd_free_clone -= *nblocks;
trace_gfs2_block_alloc(ip, rbm.rgd, block, *nblocks,
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
index 842185853f6b..5b3f4a896e6c 100644
--- a/fs/gfs2/rgrp.h
+++ b/fs/gfs2/rgrp.h
@@ -47,7 +47,7 @@ extern int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *n,
bool dinode, u64 *generation);
extern int gfs2_rs_alloc(struct gfs2_inode *ip);
-extern void gfs2_rs_deltree(struct gfs2_inode *ip, struct gfs2_blkreserv *rs);
+extern void gfs2_rs_deltree(struct gfs2_blkreserv *rs);
extern void gfs2_rs_delete(struct gfs2_inode *ip);
extern void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta);
extern void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen);
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index cab77b8ba84f..917c8e1eb4ae 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1512,7 +1512,7 @@ out_truncate:
out_unlock:
/* Error path for case 1 */
if (gfs2_rs_active(ip->i_res))
- gfs2_rs_deltree(ip, ip->i_res);
+ gfs2_rs_deltree(ip->i_res);
if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags))
gfs2_glock_dq(&ip->i_iopen_gh);
diff --git a/fs/gfs2/trace_gfs2.h b/fs/gfs2/trace_gfs2.h
index 2ee13e841e9f..20c007d747ab 100644
--- a/fs/gfs2/trace_gfs2.h
+++ b/fs/gfs2/trace_gfs2.h
@@ -159,9 +159,9 @@ TRACE_EVENT(gfs2_glock_put,
/* Callback (local or remote) requesting lock demotion */
TRACE_EVENT(gfs2_demote_rq,
- TP_PROTO(const struct gfs2_glock *gl),
+ TP_PROTO(const struct gfs2_glock *gl, bool remote),
- TP_ARGS(gl),
+ TP_ARGS(gl, remote),
TP_STRUCT__entry(
__field( dev_t, dev )
@@ -170,6 +170,7 @@ TRACE_EVENT(gfs2_demote_rq,
__field( u8, cur_state )
__field( u8, dmt_state )
__field( unsigned long, flags )
+ __field( bool, remote )
),
TP_fast_assign(
@@ -179,14 +180,16 @@ TRACE_EVENT(gfs2_demote_rq,
__entry->cur_state = glock_trace_state(gl->gl_state);
__entry->dmt_state = glock_trace_state(gl->gl_demote_state);
__entry->flags = gl->gl_flags | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0);
+ __entry->remote = remote;
),
- TP_printk("%u,%u glock %d:%lld demote %s to %s flags:%s",
+ TP_printk("%u,%u glock %d:%lld demote %s to %s flags:%s %s",
MAJOR(__entry->dev), MINOR(__entry->dev), __entry->gltype,
(unsigned long long)__entry->glnum,
glock_trace_name(__entry->cur_state),
glock_trace_name(__entry->dmt_state),
- show_glock_flags(__entry->flags))
+ show_glock_flags(__entry->flags),
+ __entry->remote ? "remote" : "local")
);
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index 88162fae27a5..7374907742a8 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -96,7 +96,8 @@ static void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks)
static void gfs2_print_trans(const struct gfs2_trans *tr)
{
- print_symbol(KERN_WARNING "GFS2: Transaction created at: %s\n", tr->tr_ip);
+ printk(KERN_WARNING "GFS2: Transaction created at: %pSR\n",
+ (void *)tr->tr_ip);
printk(KERN_WARNING "GFS2: blocks=%u revokes=%u reserved=%u touched=%d\n",
tr->tr_blocks, tr->tr_revokes, tr->tr_reserved, tr->tr_touched);
printk(KERN_WARNING "GFS2: Buf %u/%u Databuf %u/%u Revoke %u/%u\n",
@@ -135,8 +136,10 @@ void gfs2_trans_end(struct gfs2_sbd *sdp)
if (tr->tr_t_gh.gh_gl) {
gfs2_glock_dq(&tr->tr_t_gh);
gfs2_holder_uninit(&tr->tr_t_gh);
- kfree(tr);
+ if (!tr->tr_attached)
+ kfree(tr);
}
+ up_read(&sdp->sd_log_flush_lock);
if (sdp->sd_vfs->s_flags & MS_SYNCHRONOUS)
gfs2_log_flush(sdp, NULL);
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index a94f0f779d5e..fe0a76213d9e 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -533,7 +533,7 @@ void hfsplus_file_truncate(struct inode *inode)
struct address_space *mapping = inode->i_mapping;
struct page *page;
void *fsdata;
- u32 size = inode->i_size;
+ loff_t size = inode->i_size;
res = pagecache_write_begin(NULL, mapping, size, 0,
AOP_FLAG_UNINTERRUPTIBLE,
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 84e3d856e91d..523464e62849 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -110,7 +110,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
* way when do_mmap_pgoff unwinds (may be important on powerpc
* and ia64).
*/
- vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND | VM_DONTDUMP;
+ vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND;
vma->vm_ops = &hugetlb_vm_ops;
if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
diff --git a/fs/inode.c b/fs/inode.c
index f5f7c06c36fb..a898b3d43ccf 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -725,7 +725,7 @@ void prune_icache_sb(struct super_block *sb, int nr_to_scan)
* inode to the back of the list so we don't spin on it.
*/
if (!spin_trylock(&inode->i_lock)) {
- list_move_tail(&inode->i_lru, &sb->s_inode_lru);
+ list_move(&inode->i_lru, &sb->s_inode_lru);
continue;
}
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index 86b39b167c23..11bb11f48b3a 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -162,8 +162,17 @@ static void journal_do_submit_data(struct buffer_head **wbuf, int bufs,
for (i = 0; i < bufs; i++) {
wbuf[i]->b_end_io = end_buffer_write_sync;
- /* We use-up our safety reference in submit_bh() */
- submit_bh(write_op, wbuf[i]);
+ /*
+ * Here we write back pagecache data that may be mmaped. Since
+ * we cannot afford to clean the page and set PageWriteback
+ * here due to lock ordering (page lock ranks above transaction
+ * start), the data can change while IO is in flight. Tell the
+ * block layer it should bounce the bio pages if stable data
+ * during write is required.
+ *
+ * We use up our safety reference in submit_bh().
+ */
+ _submit_bh(write_op, wbuf[i], 1 << BIO_SNAP_STABLE);
}
}
@@ -667,7 +676,17 @@ start_journal_io:
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
bh->b_end_io = journal_end_buffer_io_sync;
- submit_bh(write_op, bh);
+ /*
+ * In data=journal mode, here we can end up
+ * writing pagecache data that might be
+ * mmapped. Since we can't afford to clean the
+ * page and set PageWriteback (see the comment
+ * near the other use of _submit_bh()), the
+ * data can change while the write is in
+ * flight. Tell the block layer to bounce the
+ * bio pages if stable pages are required.
+ */
+ _submit_bh(write_op, bh, 1 << BIO_SNAP_STABLE);
}
cond_resched();
diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c
index 81cc7eaff863..865c4308acb6 100644
--- a/fs/jbd/journal.c
+++ b/fs/jbd/journal.c
@@ -310,8 +310,6 @@ int journal_write_metadata_buffer(transaction_t *transaction,
new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);
/* keep subsequent assertions sane */
- new_bh->b_state = 0;
- init_buffer(new_bh, NULL, NULL);
atomic_set(&new_bh->b_count, 1);
new_jh = journal_add_journal_head(new_bh); /* This sleeps */
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index ed10991ab006..8b220f1ab54f 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -367,8 +367,6 @@ retry_alloc:
}
/* keep subsequent assertions sane */
- new_bh->b_state = 0;
- init_buffer(new_bh, NULL, NULL);
atomic_set(&new_bh->b_count, 1);
new_jh = jbd2_journal_add_journal_head(new_bh); /* This sleeps */
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index 0796c45d0d4d..01bfe7662751 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -144,6 +144,9 @@ int nlmclnt_block(struct nlm_wait *block, struct nlm_rqst *req, long timeout)
timeout);
if (ret < 0)
return -ERESTARTSYS;
+ /* Reset the lock status after a server reboot so we resend */
+ if (block->b_status == nlm_lck_denied_grace_period)
+ block->b_status = nlm_lck_blocked;
req->a_res.status = block->b_status;
return 0;
}
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index 7e529c3c45c0..9760ecb9b60f 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -550,9 +550,6 @@ again:
status = nlmclnt_block(block, req, NLMCLNT_POLL_TIMEOUT);
if (status < 0)
break;
- /* Resend the blocking lock request after a server reboot */
- if (resp->status == nlm_lck_denied_grace_period)
- continue;
if (resp->status != nlm_lck_blocked)
break;
}
diff --git a/fs/namespace.c b/fs/namespace.c
index d581e45c0a9f..341d3f564082 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1690,7 +1690,7 @@ static int do_loopback(struct path *path, const char *old_name,
if (IS_ERR(mnt)) {
err = PTR_ERR(mnt);
- goto out;
+ goto out2;
}
err = graft_tree(mnt, path);
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 5088b57b078a..cff089a412c7 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -125,6 +125,9 @@ nfs41_callback_svc(void *vrqstp)
set_freezable();
while (!kthread_should_stop()) {
+ if (try_to_freeze())
+ continue;
+
prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE);
spin_lock_bh(&serv->sv_cb_lock);
if (!list_empty(&serv->sv_cb_list)) {
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 2960512792c2..a13d26ede254 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -500,7 +500,7 @@ __be32 nfs4_callback_recallany(struct cb_recallanyargs *args, void *dummy,
&args->craa_type_mask))
pnfs_recall_all_layouts(cps->clp);
if (flags)
- nfs_expire_all_delegation_types(cps->clp, flags);
+ nfs_expire_unused_delegation_types(cps->clp, flags);
out:
dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
return status;
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 84d8eae203a7..c513b0cc835f 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -593,6 +593,8 @@ int nfs_create_rpc_client(struct nfs_client *clp,
args.flags |= RPC_CLNT_CREATE_DISCRTRY;
if (test_bit(NFS_CS_NORESVPORT, &clp->cl_flags))
args.flags |= RPC_CLNT_CREATE_NONPRIVPORT;
+ if (test_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags))
+ args.flags |= RPC_CLNT_CREATE_INFINITE_SLOTS;
if (!IS_ERR(clp->cl_rpcclient))
return 0;
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 6390a4b5fee7..57db3244f4d9 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -64,17 +64,15 @@ int nfs4_have_delegation(struct inode *inode, fmode_t flags)
return ret;
}
-static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_state *state)
+static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid)
{
struct inode *inode = state->inode;
struct file_lock *fl;
int status = 0;
if (inode->i_flock == NULL)
- return 0;
-
- if (inode->i_flock == NULL)
goto out;
+
/* Protect inode->i_flock using the file locks lock */
lock_flocks();
for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) {
@@ -83,7 +81,7 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_
if (nfs_file_open_context(fl->fl_file) != ctx)
continue;
unlock_flocks();
- status = nfs4_lock_delegation_recall(state, fl);
+ status = nfs4_lock_delegation_recall(fl, state, stateid);
if (status < 0)
goto out;
lock_flocks();
@@ -120,7 +118,7 @@ again:
seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
err = nfs4_open_delegation_recall(ctx, state, stateid);
if (!err)
- err = nfs_delegation_claim_locks(ctx, state);
+ err = nfs_delegation_claim_locks(ctx, state, stateid);
if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
err = -EAGAIN;
mutex_unlock(&sp->so_delegreturn_mutex);
@@ -389,6 +387,24 @@ out:
return err;
}
+static bool nfs_delegation_need_return(struct nfs_delegation *delegation)
+{
+ bool ret = false;
+
+ if (test_and_clear_bit(NFS_DELEGATION_RETURN, &delegation->flags))
+ ret = true;
+ if (test_and_clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags) && !ret) {
+ struct inode *inode;
+
+ spin_lock(&delegation->lock);
+ inode = delegation->inode;
+ if (inode && list_empty(&NFS_I(inode)->open_files))
+ ret = true;
+ spin_unlock(&delegation->lock);
+ }
+ return ret;
+}
+
/**
* nfs_client_return_marked_delegations - return previously marked delegations
* @clp: nfs_client to process
@@ -411,8 +427,7 @@ restart:
list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
list_for_each_entry_rcu(delegation, &server->delegations,
super_list) {
- if (!test_and_clear_bit(NFS_DELEGATION_RETURN,
- &delegation->flags))
+ if (!nfs_delegation_need_return(delegation))
continue;
inode = nfs_delegation_grab_inode(delegation);
if (inode == NULL)
@@ -471,6 +486,13 @@ int nfs4_inode_return_delegation(struct inode *inode)
return err;
}
+static void nfs_mark_return_if_closed_delegation(struct nfs_server *server,
+ struct nfs_delegation *delegation)
+{
+ set_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags);
+ set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state);
+}
+
static void nfs_mark_return_delegation(struct nfs_server *server,
struct nfs_delegation *delegation)
{
@@ -478,6 +500,45 @@ static void nfs_mark_return_delegation(struct nfs_server *server,
set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state);
}
+static bool nfs_server_mark_return_all_delegations(struct nfs_server *server)
+{
+ struct nfs_delegation *delegation;
+ bool ret = false;
+
+ list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
+ nfs_mark_return_delegation(server, delegation);
+ ret = true;
+ }
+ return ret;
+}
+
+static void nfs_client_mark_return_all_delegations(struct nfs_client *clp)
+{
+ struct nfs_server *server;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
+ nfs_server_mark_return_all_delegations(server);
+ rcu_read_unlock();
+}
+
+static void nfs_delegation_run_state_manager(struct nfs_client *clp)
+{
+ if (test_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state))
+ nfs4_schedule_state_manager(clp);
+}
+
+/**
+ * nfs_expire_all_delegations
+ * @clp: client to process
+ *
+ */
+void nfs_expire_all_delegations(struct nfs_client *clp)
+{
+ nfs_client_mark_return_all_delegations(clp);
+ nfs_delegation_run_state_manager(clp);
+}
+
/**
* nfs_super_return_all_delegations - return delegations for one superblock
* @sb: sb to process
@@ -486,24 +547,22 @@ static void nfs_mark_return_delegation(struct nfs_server *server,
void nfs_server_return_all_delegations(struct nfs_server *server)
{
struct nfs_client *clp = server->nfs_client;
- struct nfs_delegation *delegation;
+ bool need_wait;
if (clp == NULL)
return;
rcu_read_lock();
- list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
- spin_lock(&delegation->lock);
- set_bit(NFS_DELEGATION_RETURN, &delegation->flags);
- spin_unlock(&delegation->lock);
- }
+ need_wait = nfs_server_mark_return_all_delegations(server);
rcu_read_unlock();
- if (nfs_client_return_marked_delegations(clp) != 0)
+ if (need_wait) {
nfs4_schedule_state_manager(clp);
+ nfs4_wait_clnt_recover(clp);
+ }
}
-static void nfs_mark_return_all_delegation_types(struct nfs_server *server,
+static void nfs_mark_return_unused_delegation_types(struct nfs_server *server,
fmode_t flags)
{
struct nfs_delegation *delegation;
@@ -512,27 +571,21 @@ static void nfs_mark_return_all_delegation_types(struct nfs_server *server,
if ((delegation->type == (FMODE_READ|FMODE_WRITE)) && !(flags & FMODE_WRITE))
continue;
if (delegation->type & flags)
- nfs_mark_return_delegation(server, delegation);
+ nfs_mark_return_if_closed_delegation(server, delegation);
}
}
-static void nfs_client_mark_return_all_delegation_types(struct nfs_client *clp,
+static void nfs_client_mark_return_unused_delegation_types(struct nfs_client *clp,
fmode_t flags)
{
struct nfs_server *server;
rcu_read_lock();
list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
- nfs_mark_return_all_delegation_types(server, flags);
+ nfs_mark_return_unused_delegation_types(server, flags);
rcu_read_unlock();
}
-static void nfs_delegation_run_state_manager(struct nfs_client *clp)
-{
- if (test_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state))
- nfs4_schedule_state_manager(clp);
-}
-
void nfs_remove_bad_delegation(struct inode *inode)
{
struct nfs_delegation *delegation;
@@ -546,27 +599,17 @@ void nfs_remove_bad_delegation(struct inode *inode)
EXPORT_SYMBOL_GPL(nfs_remove_bad_delegation);
/**
- * nfs_expire_all_delegation_types
+ * nfs_expire_unused_delegation_types
* @clp: client to process
* @flags: delegation types to expire
*
*/
-void nfs_expire_all_delegation_types(struct nfs_client *clp, fmode_t flags)
+void nfs_expire_unused_delegation_types(struct nfs_client *clp, fmode_t flags)
{
- nfs_client_mark_return_all_delegation_types(clp, flags);
+ nfs_client_mark_return_unused_delegation_types(clp, flags);
nfs_delegation_run_state_manager(clp);
}
-/**
- * nfs_expire_all_delegations
- * @clp: client to process
- *
- */
-void nfs_expire_all_delegations(struct nfs_client *clp)
-{
- nfs_expire_all_delegation_types(clp, FMODE_READ|FMODE_WRITE);
-}
-
static void nfs_mark_return_unreferenced_delegations(struct nfs_server *server)
{
struct nfs_delegation *delegation;
@@ -574,7 +617,7 @@ static void nfs_mark_return_unreferenced_delegations(struct nfs_server *server)
list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
if (test_and_clear_bit(NFS_DELEGATION_REFERENCED, &delegation->flags))
continue;
- nfs_mark_return_delegation(server, delegation);
+ nfs_mark_return_if_closed_delegation(server, delegation);
}
}
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index d54d4fca6793..9a79c7a99d6d 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -28,6 +28,7 @@ struct nfs_delegation {
enum {
NFS_DELEGATION_NEED_RECLAIM = 0,
NFS_DELEGATION_RETURN,
+ NFS_DELEGATION_RETURN_IF_CLOSED,
NFS_DELEGATION_REFERENCED,
NFS_DELEGATION_RETURNING,
};
@@ -41,7 +42,7 @@ void nfs_inode_return_delegation_noreclaim(struct inode *inode);
struct inode *nfs_delegation_find_inode(struct nfs_client *clp, const struct nfs_fh *fhandle);
void nfs_server_return_all_delegations(struct nfs_server *);
void nfs_expire_all_delegations(struct nfs_client *clp);
-void nfs_expire_all_delegation_types(struct nfs_client *clp, fmode_t flags);
+void nfs_expire_unused_delegation_types(struct nfs_client *clp, fmode_t flags);
void nfs_expire_unreferenced_delegations(struct nfs_client *clp);
int nfs_client_return_marked_delegations(struct nfs_client *clp);
int nfs_delegations_present(struct nfs_client *clp);
@@ -53,7 +54,7 @@ void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
/* NFSv4 delegation-related procedures */
int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync);
int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid);
-int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl);
+int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid);
bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, fmode_t flags);
void nfs_mark_delegation_referenced(struct nfs_delegation *delegation);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index f23f455be42b..e093e73178b7 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1486,6 +1486,8 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags)
goto no_open;
if (d_mountpoint(dentry))
goto no_open;
+ if (NFS_SB(dentry->d_sb)->caps & NFS_CAP_ATOMIC_OPEN_V1)
+ goto no_open;
inode = dentry->d_inode;
parent = dget_parent(dentry);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 29f4a48a0ee6..a87a44f84113 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -744,6 +744,7 @@ static int
do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
{
struct inode *inode = filp->f_mapping->host;
+ struct nfs_lock_context *l_ctx;
int status;
/*
@@ -752,6 +753,14 @@ do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
*/
nfs_sync_mapping(filp->f_mapping);
+ l_ctx = nfs_get_lock_context(nfs_file_open_context(filp));
+ if (!IS_ERR(l_ctx)) {
+ status = nfs_iocounter_wait(&l_ctx->io_count);
+ nfs_put_lock_context(l_ctx);
+ if (status < 0)
+ return status;
+ }
+
/* NOTE: special case
* If we're signalled while cleaning up locks on process exit, we
* still need to complete the unlock.
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 1f941674b089..c1c7a9d78722 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -561,20 +561,22 @@ static void nfs_init_lock_context(struct nfs_lock_context *l_ctx)
l_ctx->lockowner.l_owner = current->files;
l_ctx->lockowner.l_pid = current->tgid;
INIT_LIST_HEAD(&l_ctx->list);
+ nfs_iocounter_init(&l_ctx->io_count);
}
static struct nfs_lock_context *__nfs_find_lock_context(struct nfs_open_context *ctx)
{
- struct nfs_lock_context *pos;
+ struct nfs_lock_context *head = &ctx->lock_context;
+ struct nfs_lock_context *pos = head;
- list_for_each_entry(pos, &ctx->lock_context.list, list) {
+ do {
if (pos->lockowner.l_owner != current->files)
continue;
if (pos->lockowner.l_pid != current->tgid)
continue;
atomic_inc(&pos->count);
return pos;
- }
+ } while ((pos = list_entry(pos->list.next, typeof(*pos), list)) != head);
return NULL;
}
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 541c9ebdbc5a..91e59a39fc08 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -229,6 +229,13 @@ extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
struct nfs_pgio_header *hdr,
void (*release)(struct nfs_pgio_header *hdr));
void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos);
+int nfs_iocounter_wait(struct nfs_io_counter *c);
+
+static inline void nfs_iocounter_init(struct nfs_io_counter *c)
+{
+ c->flags = 0;
+ atomic_set(&c->io_count, 0);
+}
/* nfs2xdr.c */
extern struct rpc_procinfo nfs_procedures[];
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 944c9a5c1039..553a83cc4106 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -36,6 +36,7 @@ enum nfs4_client_state {
struct nfs4_minor_version_ops {
u32 minor_version;
+ unsigned init_caps;
int (*call_sync)(struct rpc_clnt *clnt,
struct nfs_server *server,
@@ -143,12 +144,14 @@ struct nfs4_lock_state {
enum {
LK_STATE_IN_USE,
NFS_DELEGATED_STATE, /* Current stateid is delegation */
+ NFS_OPEN_STATE, /* OPEN stateid is set */
NFS_O_RDONLY_STATE, /* OPEN stateid has read-only state */
NFS_O_WRONLY_STATE, /* OPEN stateid has write-only state */
NFS_O_RDWR_STATE, /* OPEN stateid has read/write state */
NFS_STATE_RECLAIM_REBOOT, /* OPEN stateid server rebooted */
NFS_STATE_RECLAIM_NOGRACE, /* OPEN stateid needs to recover state */
NFS_STATE_POSIX_LOCKS, /* Posix locks are supported */
+ NFS_STATE_RECOVERY_FAILED, /* OPEN stateid state recovery failed */
};
struct nfs4_state {
@@ -233,6 +236,10 @@ extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, struct qstr
extern int nfs4_proc_secinfo(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *);
extern int nfs4_release_lockowner(struct nfs4_lock_state *);
extern const struct xattr_handler *nfs4_xattr_handlers[];
+extern int nfs4_set_rw_stateid(nfs4_stateid *stateid,
+ const struct nfs_open_context *ctx,
+ const struct nfs_lock_context *l_ctx,
+ fmode_t fmode);
#if defined(CONFIG_NFS_V4_1)
static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *server)
@@ -347,13 +354,13 @@ extern int nfs4_wait_clnt_recover(struct nfs_client *clp);
extern int nfs4_client_recover_expired_lease(struct nfs_client *clp);
extern void nfs4_schedule_state_manager(struct nfs_client *);
extern void nfs4_schedule_path_down_recovery(struct nfs_client *clp);
-extern void nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *);
+extern int nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs4_state *);
extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags);
extern void nfs41_handle_server_scope(struct nfs_client *,
struct nfs41_server_scope **);
extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp);
extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl);
-extern void nfs4_select_rw_stateid(nfs4_stateid *, struct nfs4_state *,
+extern int nfs4_select_rw_stateid(nfs4_stateid *, struct nfs4_state *,
fmode_t, const struct nfs_lockowner *);
extern struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_mask);
@@ -412,6 +419,11 @@ static inline bool nfs4_stateid_match(const nfs4_stateid *dst, const nfs4_statei
return memcmp(dst, src, sizeof(*dst)) == 0;
}
+static inline bool nfs4_valid_open_stateid(const struct nfs4_state *state)
+{
+ return test_bit(NFS_STATE_RECOVERY_FAILED, &state->flags) == 0;
+}
+
#else
#define nfs4_close_state(a, b) do { } while (0)
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index ac4fc9a8fdbc..947b0c908aa9 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -198,8 +198,12 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
/* Check NFS protocol revision and initialize RPC op vector */
clp->rpc_ops = &nfs_v4_clientops;
+ if (clp->cl_minorversion != 0)
+ __set_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags);
__set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
- error = nfs_create_rpc_client(clp, timeparms, authflavour);
+ error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_GSS_KRB5I);
+ if (error == -EINVAL)
+ error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_NULL);
if (error < 0)
goto error;
@@ -300,7 +304,7 @@ int nfs40_walk_client_list(struct nfs_client *new,
struct rpc_cred *cred)
{
struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id);
- struct nfs_client *pos, *n, *prev = NULL;
+ struct nfs_client *pos, *prev = NULL;
struct nfs4_setclientid_res clid = {
.clientid = new->cl_clientid,
.confirm = new->cl_confirm,
@@ -308,10 +312,23 @@ int nfs40_walk_client_list(struct nfs_client *new,
int status = -NFS4ERR_STALE_CLIENTID;
spin_lock(&nn->nfs_client_lock);
- list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) {
+ list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
/* If "pos" isn't marked ready, we can't trust the
* remaining fields in "pos" */
- if (pos->cl_cons_state < NFS_CS_READY)
+ if (pos->cl_cons_state > NFS_CS_READY) {
+ atomic_inc(&pos->cl_count);
+ spin_unlock(&nn->nfs_client_lock);
+
+ if (prev)
+ nfs_put_client(prev);
+ prev = pos;
+
+ status = nfs_wait_client_init_complete(pos);
+ spin_lock(&nn->nfs_client_lock);
+ if (status < 0)
+ continue;
+ }
+ if (pos->cl_cons_state != NFS_CS_READY)
continue;
if (pos->rpc_ops != new->rpc_ops)
@@ -423,16 +440,16 @@ int nfs41_walk_client_list(struct nfs_client *new,
struct rpc_cred *cred)
{
struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id);
- struct nfs_client *pos, *n, *prev = NULL;
+ struct nfs_client *pos, *prev = NULL;
int status = -NFS4ERR_STALE_CLIENTID;
spin_lock(&nn->nfs_client_lock);
- list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) {
+ list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
/* If "pos" isn't marked ready, we can't trust the
* remaining fields in "pos", especially the client
* ID and serverowner fields. Wait for CREATE_SESSION
* to finish. */
- if (pos->cl_cons_state < NFS_CS_READY) {
+ if (pos->cl_cons_state > NFS_CS_READY) {
atomic_inc(&pos->cl_count);
spin_unlock(&nn->nfs_client_lock);
@@ -440,18 +457,17 @@ int nfs41_walk_client_list(struct nfs_client *new,
nfs_put_client(prev);
prev = pos;
- nfs4_schedule_lease_recovery(pos);
status = nfs_wait_client_init_complete(pos);
- if (status < 0) {
- nfs_put_client(pos);
- spin_lock(&nn->nfs_client_lock);
- continue;
+ if (status == 0) {
+ nfs4_schedule_lease_recovery(pos);
+ status = nfs4_wait_clnt_recover(pos);
}
- status = pos->cl_cons_state;
spin_lock(&nn->nfs_client_lock);
if (status < 0)
continue;
}
+ if (pos->cl_cons_state != NFS_CS_READY)
+ continue;
if (pos->rpc_ops != new->rpc_ops)
continue;
@@ -469,17 +485,18 @@ int nfs41_walk_client_list(struct nfs_client *new,
continue;
atomic_inc(&pos->cl_count);
- spin_unlock(&nn->nfs_client_lock);
+ *result = pos;
+ status = 0;
dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
__func__, pos, atomic_read(&pos->cl_count));
-
- *result = pos;
- return 0;
+ break;
}
/* No matching nfs_client found. */
spin_unlock(&nn->nfs_client_lock);
dprintk("NFS: <-- %s status = %d\n", __func__, status);
+ if (prev)
+ nfs_put_client(prev);
return status;
}
#endif /* CONFIG_NFS_V4_1 */
@@ -717,6 +734,19 @@ static int nfs4_server_common_setup(struct nfs_server *server,
if (error < 0)
goto out;
+ /* Set the basic capabilities */
+ server->caps |= server->nfs_client->cl_mvops->init_caps;
+ if (server->flags & NFS_MOUNT_NORDIRPLUS)
+ server->caps &= ~NFS_CAP_READDIRPLUS;
+ /*
+ * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
+ * authentication.
+ */
+ if (nfs4_disable_idmapping &&
+ server->client->cl_auth->au_flavor == RPC_AUTH_UNIX)
+ server->caps |= NFS_CAP_UIDGID_NOMAP;
+
+
/* Probe the root fh to retrieve its FSID and filehandle */
error = nfs4_get_rootfh(server, mntfh);
if (error < 0)
@@ -760,9 +790,6 @@ static int nfs4_init_server(struct nfs_server *server,
/* Initialise the client representation from the mount data */
server->flags = data->flags;
- server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR|NFS_CAP_POSIX_LOCK;
- if (!(data->flags & NFS_MOUNT_NORDIRPLUS))
- server->caps |= NFS_CAP_READDIRPLUS;
server->options = data->options;
/* Get a client record */
@@ -779,13 +806,6 @@ static int nfs4_init_server(struct nfs_server *server,
if (error < 0)
goto error;
- /*
- * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
- * authentication.
- */
- if (nfs4_disable_idmapping && data->auth_flavors[0] == RPC_AUTH_UNIX)
- server->caps |= NFS_CAP_UIDGID_NOMAP;
-
if (data->rsize)
server->rsize = nfs_block_size(data->rsize, NULL);
if (data->wsize)
@@ -863,7 +883,6 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
/* Initialise the client representation from the parent server */
nfs_server_copy_userdata(server, parent_server);
- server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR;
/* Get a client representation.
* Note: NFSv4 always uses TCP, */
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 4fb234d3aefb..22d10623f5ee 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -158,11 +158,14 @@ static int filelayout_async_handle_error(struct rpc_task *task,
case -NFS4ERR_OPENMODE:
if (state == NULL)
break;
- nfs4_schedule_stateid_recovery(mds_server, state);
+ if (nfs4_schedule_stateid_recovery(mds_server, state) < 0)
+ goto out_bad_stateid;
goto wait_on_recovery;
case -NFS4ERR_EXPIRED:
- if (state != NULL)
- nfs4_schedule_stateid_recovery(mds_server, state);
+ if (state != NULL) {
+ if (nfs4_schedule_stateid_recovery(mds_server, state) < 0)
+ goto out_bad_stateid;
+ }
nfs4_schedule_lease_recovery(mds_client);
goto wait_on_recovery;
/* DS session errors */
@@ -226,6 +229,9 @@ reset:
out:
task->tk_status = 0;
return -EAGAIN;
+out_bad_stateid:
+ task->tk_status = -EIO;
+ return 0;
wait_on_recovery:
rpc_sleep_on(&mds_client->cl_rpcwaitq, task, NULL);
if (test_bit(NFS4CLNT_MANAGER_RUNNING, &mds_client->cl_state) == 0)
@@ -299,6 +305,10 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data)
{
struct nfs_read_data *rdata = data;
+ if (unlikely(test_bit(NFS_CONTEXT_BAD, &rdata->args.context->flags))) {
+ rpc_exit(task, -EIO);
+ return;
+ }
if (filelayout_reset_to_mds(rdata->header->lseg)) {
dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid);
filelayout_reset_read(rdata);
@@ -307,10 +317,13 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data)
}
rdata->read_done_cb = filelayout_read_done_cb;
- nfs41_setup_sequence(rdata->ds_clp->cl_session,
+ if (nfs41_setup_sequence(rdata->ds_clp->cl_session,
&rdata->args.seq_args,
&rdata->res.seq_res,
- task);
+ task))
+ return;
+ nfs4_set_rw_stateid(&rdata->args.stateid, rdata->args.context,
+ rdata->args.lock_context, FMODE_READ);
}
static void filelayout_read_call_done(struct rpc_task *task, void *data)
@@ -401,16 +414,23 @@ static void filelayout_write_prepare(struct rpc_task *task, void *data)
{
struct nfs_write_data *wdata = data;
+ if (unlikely(test_bit(NFS_CONTEXT_BAD, &wdata->args.context->flags))) {
+ rpc_exit(task, -EIO);
+ return;
+ }
if (filelayout_reset_to_mds(wdata->header->lseg)) {
dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid);
filelayout_reset_write(wdata);
rpc_exit(task, 0);
return;
}
- nfs41_setup_sequence(wdata->ds_clp->cl_session,
+ if (nfs41_setup_sequence(wdata->ds_clp->cl_session,
&wdata->args.seq_args,
&wdata->res.seq_res,
- task);
+ task))
+ return;
+ nfs4_set_rw_stateid(&wdata->args.stateid, wdata->args.context,
+ wdata->args.lock_context, FMODE_WRITE);
}
static void filelayout_write_call_done(struct rpc_task *task, void *data)
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 0dd766079e1c..cdb0b41a4810 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -134,33 +134,38 @@ static size_t nfs_parse_server_name(char *string, size_t len,
return ret;
}
+/**
+ * nfs_find_best_sec - Find a security mechanism supported locally
+ * @flavors: List of security tuples returned by SECINFO procedure
+ *
+ * Return the pseudoflavor of the first security mechanism in
+ * "flavors" that is locally supported. Return RPC_AUTH_UNIX if
+ * no matching flavor is found in the array. The "flavors" array
+ * is searched in the order returned from the server, per RFC 3530
+ * recommendation.
+ */
rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors)
{
- struct gss_api_mech *mech;
- struct xdr_netobj oid;
- int i;
- rpc_authflavor_t pseudoflavor = RPC_AUTH_UNIX;
+ rpc_authflavor_t pseudoflavor;
+ struct nfs4_secinfo4 *secinfo;
+ unsigned int i;
for (i = 0; i < flavors->num_flavors; i++) {
- struct nfs4_secinfo_flavor *flavor;
- flavor = &flavors->flavors[i];
-
- if (flavor->flavor == RPC_AUTH_NULL || flavor->flavor == RPC_AUTH_UNIX) {
- pseudoflavor = flavor->flavor;
- break;
- } else if (flavor->flavor == RPC_AUTH_GSS) {
- oid.len = flavor->gss.sec_oid4.len;
- oid.data = flavor->gss.sec_oid4.data;
- mech = gss_mech_get_by_OID(&oid);
- if (!mech)
- continue;
- pseudoflavor = gss_svc_to_pseudoflavor(mech, flavor->gss.service);
- gss_mech_put(mech);
+ secinfo = &flavors->flavors[i];
+
+ switch (secinfo->flavor) {
+ case RPC_AUTH_NULL:
+ case RPC_AUTH_UNIX:
+ case RPC_AUTH_GSS:
+ pseudoflavor = rpcauth_get_pseudoflavor(secinfo->flavor,
+ &secinfo->flavor_info);
+ if (pseudoflavor != RPC_AUTH_MAXFLAVOR)
+ return pseudoflavor;
break;
}
}
- return pseudoflavor;
+ return RPC_AUTH_UNIX;
}
static rpc_authflavor_t nfs4_negotiate_security(struct inode *inode, struct qstr *name)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 26431cf62ddb..9da4bd55eb30 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -107,6 +107,8 @@ static int nfs4_map_errors(int err)
return -EPROTONOSUPPORT;
case -NFS4ERR_ACCESS:
return -EACCES;
+ case -NFS4ERR_FILE_OPEN:
+ return -EBUSY;
default:
dprintk("%s could not handle NFSv4 error %d\n",
__func__, -err);
@@ -295,19 +297,30 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
}
if (state == NULL)
break;
- nfs4_schedule_stateid_recovery(server, state);
+ ret = nfs4_schedule_stateid_recovery(server, state);
+ if (ret < 0)
+ break;
goto wait_on_recovery;
case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_BAD_STATEID:
+ if (inode != NULL && nfs4_have_delegation(inode, FMODE_READ)) {
+ nfs_remove_bad_delegation(inode);
+ exception->retry = 1;
+ break;
+ }
if (state == NULL)
break;
- nfs_remove_bad_delegation(state->inode);
- nfs4_schedule_stateid_recovery(server, state);
+ ret = nfs4_schedule_stateid_recovery(server, state);
+ if (ret < 0)
+ break;
goto wait_on_recovery;
case -NFS4ERR_EXPIRED:
- if (state != NULL)
- nfs4_schedule_stateid_recovery(server, state);
+ if (state != NULL) {
+ ret = nfs4_schedule_stateid_recovery(server, state);
+ if (ret < 0)
+ break;
+ }
case -NFS4ERR_STALE_STATEID:
case -NFS4ERR_STALE_CLIENTID:
nfs4_schedule_lease_recovery(clp);
@@ -756,10 +769,40 @@ struct nfs4_opendata {
struct iattr attrs;
unsigned long timestamp;
unsigned int rpc_done : 1;
+ unsigned int is_recover : 1;
int rpc_status;
int cancelled;
};
+static bool nfs4_clear_cap_atomic_open_v1(struct nfs_server *server,
+ int err, struct nfs4_exception *exception)
+{
+ if (err != -EINVAL)
+ return false;
+ if (!(server->caps & NFS_CAP_ATOMIC_OPEN_V1))
+ return false;
+ server->caps &= ~NFS_CAP_ATOMIC_OPEN_V1;
+ exception->retry = 1;
+ return true;
+}
+
+static enum open_claim_type4
+nfs4_map_atomic_open_claim(struct nfs_server *server,
+ enum open_claim_type4 claim)
+{
+ if (server->caps & NFS_CAP_ATOMIC_OPEN_V1)
+ return claim;
+ switch (claim) {
+ default:
+ return claim;
+ case NFS4_OPEN_CLAIM_FH:
+ return NFS4_OPEN_CLAIM_NULL;
+ case NFS4_OPEN_CLAIM_DELEG_CUR_FH:
+ return NFS4_OPEN_CLAIM_DELEGATE_CUR;
+ case NFS4_OPEN_CLAIM_DELEG_PREV_FH:
+ return NFS4_OPEN_CLAIM_DELEGATE_PREV;
+ }
+}
static void nfs4_init_opendata_res(struct nfs4_opendata *p)
{
@@ -775,6 +818,7 @@ static void nfs4_init_opendata_res(struct nfs4_opendata *p)
static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
struct nfs4_state_owner *sp, fmode_t fmode, int flags,
const struct iattr *attrs,
+ enum open_claim_type4 claim,
gfp_t gfp_mask)
{
struct dentry *parent = dget_parent(dentry);
@@ -793,7 +837,6 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
p->dir = parent;
p->owner = sp;
atomic_inc(&sp->so_count);
- p->o_arg.fh = NFS_FH(dir);
p->o_arg.open_flags = flags;
p->o_arg.fmode = fmode & (FMODE_READ|FMODE_WRITE);
/* don't put an ACCESS op in OPEN compound if O_EXCL, because ACCESS
@@ -811,7 +854,19 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
p->o_arg.server = server;
p->o_arg.bitmask = server->attr_bitmask;
p->o_arg.open_bitmap = &nfs4_fattr_bitmap[0];
- p->o_arg.claim = NFS4_OPEN_CLAIM_NULL;
+ p->o_arg.claim = nfs4_map_atomic_open_claim(server, claim);
+ switch (p->o_arg.claim) {
+ case NFS4_OPEN_CLAIM_NULL:
+ case NFS4_OPEN_CLAIM_DELEGATE_CUR:
+ case NFS4_OPEN_CLAIM_DELEGATE_PREV:
+ p->o_arg.fh = NFS_FH(dir);
+ break;
+ case NFS4_OPEN_CLAIM_PREVIOUS:
+ case NFS4_OPEN_CLAIM_FH:
+ case NFS4_OPEN_CLAIM_DELEG_CUR_FH:
+ case NFS4_OPEN_CLAIM_DELEG_PREV_FH:
+ p->o_arg.fh = NFS_FH(dentry->d_inode);
+ }
if (attrs != NULL && attrs->ia_valid != 0) {
__be32 verf[2];
@@ -924,6 +979,7 @@ static void nfs_set_open_stateid_locked(struct nfs4_state *state, nfs4_stateid *
if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0)
nfs4_stateid_copy(&state->stateid, stateid);
nfs4_stateid_copy(&state->open_stateid, stateid);
+ set_bit(NFS_OPEN_STATE, &state->flags);
switch (fmode) {
case FMODE_READ:
set_bit(NFS_O_RDONLY_STATE, &state->flags);
@@ -1046,9 +1102,12 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
/* Save the delegation */
nfs4_stateid_copy(&stateid, &delegation->stateid);
rcu_read_unlock();
- ret = nfs_may_open(state->inode, state->owner->so_cred, open_mode);
- if (ret != 0)
- goto out;
+ nfs_release_seqid(opendata->o_arg.seqid);
+ if (!opendata->is_recover) {
+ ret = nfs_may_open(state->inode, state->owner->so_cred, open_mode);
+ if (ret != 0)
+ goto out;
+ }
ret = -EAGAIN;
/* Try to update the stateid using the delegation */
@@ -1193,11 +1252,13 @@ static struct nfs_open_context *nfs4_state_find_open_context(struct nfs4_state *
return ERR_PTR(-ENOENT);
}
-static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context *ctx, struct nfs4_state *state)
+static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context *ctx,
+ struct nfs4_state *state, enum open_claim_type4 claim)
{
struct nfs4_opendata *opendata;
- opendata = nfs4_opendata_alloc(ctx->dentry, state->owner, 0, 0, NULL, GFP_NOFS);
+ opendata = nfs4_opendata_alloc(ctx->dentry, state->owner, 0, 0,
+ NULL, claim, GFP_NOFS);
if (opendata == NULL)
return ERR_PTR(-ENOMEM);
opendata->state = state;
@@ -1233,6 +1294,7 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *
/* memory barrier prior to reading state->n_* */
clear_bit(NFS_DELEGATED_STATE, &state->flags);
+ clear_bit(NFS_OPEN_STATE, &state->flags);
smp_rmb();
if (state->n_rdwr != 0) {
clear_bit(NFS_O_RDWR_STATE, &state->flags);
@@ -1283,11 +1345,10 @@ static int _nfs4_do_open_reclaim(struct nfs_open_context *ctx, struct nfs4_state
fmode_t delegation_type = 0;
int status;
- opendata = nfs4_open_recoverdata_alloc(ctx, state);
+ opendata = nfs4_open_recoverdata_alloc(ctx, state,
+ NFS4_OPEN_CLAIM_PREVIOUS);
if (IS_ERR(opendata))
return PTR_ERR(opendata);
- opendata->o_arg.claim = NFS4_OPEN_CLAIM_PREVIOUS;
- opendata->o_arg.fh = NFS_FH(state->inode);
rcu_read_lock();
delegation = rcu_dereference(NFS_I(state->inode)->delegation);
if (delegation != NULL && test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags) != 0)
@@ -1306,6 +1367,8 @@ static int nfs4_do_open_reclaim(struct nfs_open_context *ctx, struct nfs4_state
int err;
do {
err = _nfs4_do_open_reclaim(ctx, state);
+ if (nfs4_clear_cap_atomic_open_v1(server, err, &exception))
+ continue;
if (err != -NFS4ERR_DELAY)
break;
nfs4_handle_exception(server, err, &exception);
@@ -1320,71 +1383,72 @@ static int nfs4_open_reclaim(struct nfs4_state_owner *sp, struct nfs4_state *sta
ctx = nfs4_state_find_open_context(state);
if (IS_ERR(ctx))
- return PTR_ERR(ctx);
+ return -EAGAIN;
ret = nfs4_do_open_reclaim(ctx, state);
put_nfs_open_context(ctx);
return ret;
}
-static int _nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid)
+static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct nfs4_state *state, const nfs4_stateid *stateid, int err)
{
- struct nfs4_opendata *opendata;
- int ret;
-
- opendata = nfs4_open_recoverdata_alloc(ctx, state);
- if (IS_ERR(opendata))
- return PTR_ERR(opendata);
- opendata->o_arg.claim = NFS4_OPEN_CLAIM_DELEGATE_CUR;
- nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid);
- ret = nfs4_open_recover(opendata, state);
- nfs4_opendata_put(opendata);
- return ret;
+ switch (err) {
+ default:
+ printk(KERN_ERR "NFS: %s: unhandled error "
+ "%d.\n", __func__, err);
+ case 0:
+ case -ENOENT:
+ case -ESTALE:
+ break;
+ case -NFS4ERR_BADSESSION:
+ case -NFS4ERR_BADSLOT:
+ case -NFS4ERR_BAD_HIGH_SLOT:
+ case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+ case -NFS4ERR_DEADSESSION:
+ set_bit(NFS_DELEGATED_STATE, &state->flags);
+ nfs4_schedule_session_recovery(server->nfs_client->cl_session, err);
+ return -EAGAIN;
+ case -NFS4ERR_STALE_CLIENTID:
+ case -NFS4ERR_STALE_STATEID:
+ set_bit(NFS_DELEGATED_STATE, &state->flags);
+ case -NFS4ERR_EXPIRED:
+ /* Don't recall a delegation if it was lost */
+ nfs4_schedule_lease_recovery(server->nfs_client);
+ return -EAGAIN;
+ case -NFS4ERR_DELEG_REVOKED:
+ case -NFS4ERR_ADMIN_REVOKED:
+ case -NFS4ERR_BAD_STATEID:
+ case -NFS4ERR_OPENMODE:
+ nfs_inode_find_state_and_recover(state->inode,
+ stateid);
+ nfs4_schedule_stateid_recovery(server, state);
+ return 0;
+ case -NFS4ERR_DELAY:
+ case -NFS4ERR_GRACE:
+ set_bit(NFS_DELEGATED_STATE, &state->flags);
+ ssleep(1);
+ return -EAGAIN;
+ case -ENOMEM:
+ case -NFS4ERR_DENIED:
+ /* kill_proc(fl->fl_pid, SIGLOST, 1); */
+ return 0;
+ }
+ return err;
}
int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid)
{
- struct nfs4_exception exception = { };
struct nfs_server *server = NFS_SERVER(state->inode);
+ struct nfs4_opendata *opendata;
int err;
- do {
- err = _nfs4_open_delegation_recall(ctx, state, stateid);
- switch (err) {
- case 0:
- case -ENOENT:
- case -ESTALE:
- goto out;
- case -NFS4ERR_BADSESSION:
- case -NFS4ERR_BADSLOT:
- case -NFS4ERR_BAD_HIGH_SLOT:
- case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
- case -NFS4ERR_DEADSESSION:
- set_bit(NFS_DELEGATED_STATE, &state->flags);
- nfs4_schedule_session_recovery(server->nfs_client->cl_session, err);
- err = -EAGAIN;
- goto out;
- case -NFS4ERR_STALE_CLIENTID:
- case -NFS4ERR_STALE_STATEID:
- set_bit(NFS_DELEGATED_STATE, &state->flags);
- case -NFS4ERR_EXPIRED:
- /* Don't recall a delegation if it was lost */
- nfs4_schedule_lease_recovery(server->nfs_client);
- err = -EAGAIN;
- goto out;
- case -NFS4ERR_DELEG_REVOKED:
- case -NFS4ERR_ADMIN_REVOKED:
- case -NFS4ERR_BAD_STATEID:
- nfs_inode_find_state_and_recover(state->inode,
- stateid);
- nfs4_schedule_stateid_recovery(server, state);
- case -ENOMEM:
- err = 0;
- goto out;
- }
- set_bit(NFS_DELEGATED_STATE, &state->flags);
- err = nfs4_handle_exception(server, err, &exception);
- } while (exception.retry);
-out:
- return err;
+
+ opendata = nfs4_open_recoverdata_alloc(ctx, state,
+ NFS4_OPEN_CLAIM_DELEG_CUR_FH);
+ if (IS_ERR(opendata))
+ return PTR_ERR(opendata);
+ nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid);
+ err = nfs4_open_recover(opendata, state);
+ nfs4_opendata_put(opendata);
+ return nfs4_handle_delegation_recall_error(server, state, stateid, err);
}
static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata)
@@ -1467,6 +1531,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
{
struct nfs4_opendata *data = calldata;
struct nfs4_state_owner *sp = data->owner;
+ struct nfs_client *clp = sp->so_server->nfs_client;
if (nfs_wait_on_sequence(data->o_arg.seqid, task) != 0)
goto out_wait;
@@ -1482,15 +1547,20 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
rcu_read_lock();
delegation = rcu_dereference(NFS_I(data->state->inode)->delegation);
if (data->o_arg.claim != NFS4_OPEN_CLAIM_DELEGATE_CUR &&
+ data->o_arg.claim != NFS4_OPEN_CLAIM_DELEG_CUR_FH &&
can_open_delegated(delegation, data->o_arg.fmode))
goto unlock_no_action;
rcu_read_unlock();
}
/* Update client id. */
- data->o_arg.clientid = sp->so_server->nfs_client->cl_clientid;
- if (data->o_arg.claim == NFS4_OPEN_CLAIM_PREVIOUS) {
- task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_NOATTR];
+ data->o_arg.clientid = clp->cl_clientid;
+ switch (data->o_arg.claim) {
+ case NFS4_OPEN_CLAIM_PREVIOUS:
+ case NFS4_OPEN_CLAIM_DELEG_CUR_FH:
+ case NFS4_OPEN_CLAIM_DELEG_PREV_FH:
data->o_arg.open_bitmap = &nfs4_open_noattr_bitmap[0];
+ case NFS4_OPEN_CLAIM_FH:
+ task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_NOATTR];
nfs_copy_fh(&data->o_res.fh, data->o_arg.fh);
}
data->timestamp = jiffies;
@@ -1499,6 +1569,16 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
&data->o_res.seq_res,
task) != 0)
nfs_release_seqid(data->o_arg.seqid);
+
+ /* Set the create mode (note dependency on the session type) */
+ data->o_arg.createmode = NFS4_CREATE_UNCHECKED;
+ if (data->o_arg.open_flags & O_EXCL) {
+ data->o_arg.createmode = NFS4_CREATE_EXCLUSIVE;
+ if (nfs4_has_persistent_session(clp))
+ data->o_arg.createmode = NFS4_CREATE_GUARDED;
+ else if (clp->cl_mvops->minor_version > 0)
+ data->o_arg.createmode = NFS4_CREATE_EXCLUSIVE4_1;
+ }
return;
unlock_no_action:
rcu_read_unlock();
@@ -1594,8 +1674,11 @@ static int nfs4_run_open_task(struct nfs4_opendata *data, int isrecover)
data->rpc_done = 0;
data->rpc_status = 0;
data->cancelled = 0;
- if (isrecover)
+ data->is_recover = 0;
+ if (isrecover) {
nfs4_set_sequence_privileged(&o_arg->seq_args);
+ data->is_recover = 1;
+ }
task = rpc_run_task(&task_setup_data);
if (IS_ERR(task))
return PTR_ERR(task);
@@ -1720,7 +1803,8 @@ static int _nfs4_open_expired(struct nfs_open_context *ctx, struct nfs4_state *s
struct nfs4_opendata *opendata;
int ret;
- opendata = nfs4_open_recoverdata_alloc(ctx, state);
+ opendata = nfs4_open_recoverdata_alloc(ctx, state,
+ NFS4_OPEN_CLAIM_FH);
if (IS_ERR(opendata))
return PTR_ERR(opendata);
ret = nfs4_open_recover(opendata, state);
@@ -1738,6 +1822,8 @@ static int nfs4_do_open_expired(struct nfs_open_context *ctx, struct nfs4_state
do {
err = _nfs4_open_expired(ctx, state);
+ if (nfs4_clear_cap_atomic_open_v1(server, err, &exception))
+ continue;
switch (err) {
default:
goto out;
@@ -1758,7 +1844,7 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta
ctx = nfs4_state_find_open_context(state);
if (IS_ERR(ctx))
- return PTR_ERR(ctx);
+ return -EAGAIN;
ret = nfs4_do_open_expired(ctx, state);
put_nfs_open_context(ctx);
return ret;
@@ -1820,6 +1906,7 @@ static int nfs41_check_open_stateid(struct nfs4_state *state)
clear_bit(NFS_O_RDONLY_STATE, &state->flags);
clear_bit(NFS_O_WRONLY_STATE, &state->flags);
clear_bit(NFS_O_RDWR_STATE, &state->flags);
+ clear_bit(NFS_OPEN_STATE, &state->flags);
}
return status;
}
@@ -1880,10 +1967,8 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
if (ret != 0)
goto out;
- if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) {
+ if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
nfs4_schedule_stateid_recovery(server, state);
- nfs4_wait_clnt_recover(server->nfs_client);
- }
*res = state;
out:
return ret;
@@ -1905,6 +1990,7 @@ static int _nfs4_do_open(struct inode *dir,
struct nfs4_state *state = NULL;
struct nfs_server *server = NFS_SERVER(dir);
struct nfs4_opendata *opendata;
+ enum open_claim_type4 claim = NFS4_OPEN_CLAIM_NULL;
int status;
/* Protect against reboot recovery conflicts */
@@ -1920,7 +2006,10 @@ static int _nfs4_do_open(struct inode *dir,
if (dentry->d_inode != NULL)
nfs4_return_incompatible_delegation(dentry->d_inode, fmode);
status = -ENOMEM;
- opendata = nfs4_opendata_alloc(dentry, sp, fmode, flags, sattr, GFP_KERNEL);
+ if (dentry->d_inode)
+ claim = NFS4_OPEN_CLAIM_FH;
+ opendata = nfs4_opendata_alloc(dentry, sp, fmode, flags, sattr,
+ claim, GFP_KERNEL);
if (opendata == NULL)
goto err_put_state_owner;
@@ -1937,7 +2026,8 @@ static int _nfs4_do_open(struct inode *dir,
if (status != 0)
goto err_opendata_put;
- if (opendata->o_arg.open_flags & O_EXCL) {
+ if ((opendata->o_arg.open_flags & O_EXCL) &&
+ (opendata->o_arg.createmode != NFS4_CREATE_GUARDED)) {
nfs4_exclusive_attrset(opendata, sattr);
nfs_fattr_init(opendata->o_res.f_attr);
@@ -1978,6 +2068,7 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir,
struct rpc_cred *cred,
struct nfs4_threshold **ctx_th)
{
+ struct nfs_server *server = NFS_SERVER(dir);
struct nfs4_exception exception = { };
struct nfs4_state *res;
int status;
@@ -2021,7 +2112,9 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir,
exception.retry = 1;
continue;
}
- res = ERR_PTR(nfs4_handle_exception(NFS_SERVER(dir),
+ if (nfs4_clear_cap_atomic_open_v1(server, status, &exception))
+ continue;
+ res = ERR_PTR(nfs4_handle_exception(server,
status, &exception));
} while (exception.retry);
return res;
@@ -2049,20 +2142,25 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
.rpc_cred = cred,
};
unsigned long timestamp = jiffies;
+ fmode_t fmode;
+ bool truncate;
int status;
nfs_fattr_init(fattr);
- if (state != NULL) {
+ /* Servers should only apply open mode checks for file size changes */
+ truncate = (sattr->ia_valid & ATTR_SIZE) ? true : false;
+ fmode = truncate ? FMODE_WRITE : FMODE_READ;
+
+ if (nfs4_copy_delegation_stateid(&arg.stateid, inode, fmode)) {
+ /* Use that stateid */
+ } else if (truncate && state != NULL && nfs4_valid_open_stateid(state)) {
struct nfs_lockowner lockowner = {
.l_owner = current->files,
.l_pid = current->tgid,
};
nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
&lockowner);
- } else if (nfs4_copy_delegation_stateid(&arg.stateid, inode,
- FMODE_WRITE)) {
- /* Use that stateid */
} else
nfs4_stateid_copy(&arg.stateid, &zero_stateid);
@@ -2086,6 +2184,13 @@ static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
err = _nfs4_do_setattr(inode, cred, fattr, sattr, state);
switch (err) {
case -NFS4ERR_OPENMODE:
+ if (!(sattr->ia_valid & ATTR_SIZE)) {
+ pr_warn_once("NFSv4: server %s is incorrectly "
+ "applying open mode checks to "
+ "a SETATTR that is not "
+ "changing file size.\n",
+ server->nfs_client->cl_hostname);
+ }
if (state && !(state->state & FMODE_WRITE)) {
err = -EBADF;
if (sattr->ia_valid & ATTR_OPEN)
@@ -2129,11 +2234,19 @@ static void nfs4_close_clear_stateid_flags(struct nfs4_state *state,
fmode_t fmode)
{
spin_lock(&state->owner->so_lock);
- if (!(fmode & FMODE_READ))
+ clear_bit(NFS_O_RDWR_STATE, &state->flags);
+ switch (fmode & (FMODE_READ|FMODE_WRITE)) {
+ case FMODE_WRITE:
clear_bit(NFS_O_RDONLY_STATE, &state->flags);
- if (!(fmode & FMODE_WRITE))
+ break;
+ case FMODE_READ:
clear_bit(NFS_O_WRONLY_STATE, &state->flags);
- clear_bit(NFS_O_RDWR_STATE, &state->flags);
+ break;
+ case 0:
+ clear_bit(NFS_O_RDONLY_STATE, &state->flags);
+ clear_bit(NFS_O_WRONLY_STATE, &state->flags);
+ clear_bit(NFS_OPEN_STATE, &state->flags);
+ }
spin_unlock(&state->owner->so_lock);
}
@@ -2201,6 +2314,8 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
calldata->arg.fmode &= ~FMODE_WRITE;
}
}
+ if (!nfs4_valid_open_stateid(state))
+ call_close = 0;
spin_unlock(&state->owner->so_lock);
if (!call_close) {
@@ -2211,8 +2326,10 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
if (calldata->arg.fmode == 0) {
task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CLOSE];
if (calldata->roc &&
- pnfs_roc_drain(inode, &calldata->roc_barrier, task))
+ pnfs_roc_drain(inode, &calldata->roc_barrier, task)) {
+ nfs_release_seqid(calldata->arg.seqid);
goto out_wait;
+ }
}
nfs_fattr_init(calldata->res.fattr);
@@ -2443,7 +2560,7 @@ static int nfs4_lookup_root_sec(struct nfs_server *server, struct nfs_fh *fhandl
auth = rpcauth_create(flavor, server->client);
if (IS_ERR(auth)) {
- ret = -EIO;
+ ret = -EACCES;
goto out;
}
ret = nfs4_lookup_root(server, fhandle, info);
@@ -2451,27 +2568,36 @@ out:
return ret;
}
+/*
+ * Retry pseudoroot lookup with various security flavors. We do this when:
+ *
+ * NFSv4.0: the PUTROOTFH operation returns NFS4ERR_WRONGSEC
+ * NFSv4.1: the server does not support the SECINFO_NO_NAME operation
+ *
+ * Returns zero on success, or a negative NFS4ERR value, or a
+ * negative errno value.
+ */
static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
struct nfs_fsinfo *info)
{
- int i, len, status = 0;
- rpc_authflavor_t flav_array[NFS_MAX_SECFLAVORS];
-
- len = rpcauth_list_flavors(flav_array, ARRAY_SIZE(flav_array));
- if (len < 0)
- return len;
-
- for (i = 0; i < len; i++) {
- /* AUTH_UNIX is the default flavor if none was specified,
- * thus has already been tried. */
- if (flav_array[i] == RPC_AUTH_UNIX)
- continue;
+ /* Per 3530bis 15.33.5 */
+ static const rpc_authflavor_t flav_array[] = {
+ RPC_AUTH_GSS_KRB5P,
+ RPC_AUTH_GSS_KRB5I,
+ RPC_AUTH_GSS_KRB5,
+ RPC_AUTH_UNIX, /* courtesy */
+ RPC_AUTH_NULL,
+ };
+ int status = -EPERM;
+ size_t i;
+ for (i = 0; i < ARRAY_SIZE(flav_array); i++) {
status = nfs4_lookup_root_sec(server, fhandle, info, flav_array[i]);
if (status == -NFS4ERR_WRONGSEC || status == -EACCES)
continue;
break;
}
+
/*
* -EACCESS could mean that the user doesn't have correct permissions
* to access the mount. It could also mean that we tried to mount
@@ -2484,24 +2610,36 @@ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
return status;
}
-/*
- * get the file handle for the "/" directory on the server
+static int nfs4_do_find_root_sec(struct nfs_server *server,
+ struct nfs_fh *fhandle, struct nfs_fsinfo *info)
+{
+ int mv = server->nfs_client->cl_minorversion;
+ return nfs_v4_minor_ops[mv]->find_root_sec(server, fhandle, info);
+}
+
+/**
+ * nfs4_proc_get_rootfh - get file handle for server's pseudoroot
+ * @server: initialized nfs_server handle
+ * @fhandle: we fill in the pseudo-fs root file handle
+ * @info: we fill in an FSINFO struct
+ *
+ * Returns zero on success, or a negative errno.
*/
int nfs4_proc_get_rootfh(struct nfs_server *server, struct nfs_fh *fhandle,
struct nfs_fsinfo *info)
{
- int minor_version = server->nfs_client->cl_minorversion;
- int status = nfs4_lookup_root(server, fhandle, info);
- if ((status == -NFS4ERR_WRONGSEC) && !(server->flags & NFS_MOUNT_SECFLAVOUR))
- /*
- * A status of -NFS4ERR_WRONGSEC will be mapped to -EPERM
- * by nfs4_map_errors() as this function exits.
- */
- status = nfs_v4_minor_ops[minor_version]->find_root_sec(server, fhandle, info);
+ int status;
+
+ status = nfs4_lookup_root(server, fhandle, info);
+ if ((status == -NFS4ERR_WRONGSEC) &&
+ !(server->flags & NFS_MOUNT_SECFLAVOUR))
+ status = nfs4_do_find_root_sec(server, fhandle, info);
+
if (status == 0)
status = nfs4_server_capabilities(server, fhandle);
if (status == 0)
status = nfs4_do_fsinfo(server, fhandle, info);
+
return nfs4_map_errors(status);
}
@@ -3380,12 +3518,21 @@ static int _nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle,
static int nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *fsinfo)
{
struct nfs4_exception exception = { };
+ unsigned long now = jiffies;
int err;
do {
- err = nfs4_handle_exception(server,
- _nfs4_do_fsinfo(server, fhandle, fsinfo),
- &exception);
+ err = _nfs4_do_fsinfo(server, fhandle, fsinfo);
+ if (err == 0) {
+ struct nfs_client *clp = server->nfs_client;
+
+ spin_lock(&clp->cl_lock);
+ clp->cl_lease_time = fsinfo->lease_time * HZ;
+ clp->cl_last_renewal = now;
+ spin_unlock(&clp->cl_lock);
+ break;
+ }
+ err = nfs4_handle_exception(server, err, &exception);
} while (exception.retry);
return err;
}
@@ -3445,6 +3592,46 @@ static int nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
return err;
}
+int nfs4_set_rw_stateid(nfs4_stateid *stateid,
+ const struct nfs_open_context *ctx,
+ const struct nfs_lock_context *l_ctx,
+ fmode_t fmode)
+{
+ const struct nfs_lockowner *lockowner = NULL;
+
+ if (l_ctx != NULL)
+ lockowner = &l_ctx->lockowner;
+ return nfs4_select_rw_stateid(stateid, ctx->state, fmode, lockowner);
+}
+EXPORT_SYMBOL_GPL(nfs4_set_rw_stateid);
+
+static bool nfs4_stateid_is_current(nfs4_stateid *stateid,
+ const struct nfs_open_context *ctx,
+ const struct nfs_lock_context *l_ctx,
+ fmode_t fmode)
+{
+ nfs4_stateid current_stateid;
+
+ if (nfs4_set_rw_stateid(&current_stateid, ctx, l_ctx, fmode))
+ return false;
+ return nfs4_stateid_match(stateid, &current_stateid);
+}
+
+static bool nfs4_error_stateid_expired(int err)
+{
+ switch (err) {
+ case -NFS4ERR_DELEG_REVOKED:
+ case -NFS4ERR_ADMIN_REVOKED:
+ case -NFS4ERR_BAD_STATEID:
+ case -NFS4ERR_STALE_STATEID:
+ case -NFS4ERR_OLD_STATEID:
+ case -NFS4ERR_OPENMODE:
+ case -NFS4ERR_EXPIRED:
+ return true;
+ }
+ return false;
+}
+
void __nfs4_read_done_cb(struct nfs_read_data *data)
{
nfs_invalidate_atime(data->header->inode);
@@ -3465,6 +3652,20 @@ static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data)
return 0;
}
+static bool nfs4_read_stateid_changed(struct rpc_task *task,
+ struct nfs_readargs *args)
+{
+
+ if (!nfs4_error_stateid_expired(task->tk_status) ||
+ nfs4_stateid_is_current(&args->stateid,
+ args->context,
+ args->lock_context,
+ FMODE_READ))
+ return false;
+ rpc_restart_call_prepare(task);
+ return true;
+}
+
static int nfs4_read_done(struct rpc_task *task, struct nfs_read_data *data)
{
@@ -3472,7 +3673,8 @@ static int nfs4_read_done(struct rpc_task *task, struct nfs_read_data *data)
if (!nfs4_sequence_done(task, &data->res.seq_res))
return -EAGAIN;
-
+ if (nfs4_read_stateid_changed(task, &data->args))
+ return -EAGAIN;
return data->read_done_cb ? data->read_done_cb(task, data) :
nfs4_read_done_cb(task, data);
}
@@ -3487,10 +3689,13 @@ static void nfs4_proc_read_setup(struct nfs_read_data *data, struct rpc_message
static void nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
{
- nfs4_setup_sequence(NFS_SERVER(data->header->inode),
+ if (nfs4_setup_sequence(NFS_SERVER(data->header->inode),
&data->args.seq_args,
&data->res.seq_res,
- task);
+ task))
+ return;
+ nfs4_set_rw_stateid(&data->args.stateid, data->args.context,
+ data->args.lock_context, FMODE_READ);
}
static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data)
@@ -3508,10 +3713,26 @@ static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data
return 0;
}
+static bool nfs4_write_stateid_changed(struct rpc_task *task,
+ struct nfs_writeargs *args)
+{
+
+ if (!nfs4_error_stateid_expired(task->tk_status) ||
+ nfs4_stateid_is_current(&args->stateid,
+ args->context,
+ args->lock_context,
+ FMODE_WRITE))
+ return false;
+ rpc_restart_call_prepare(task);
+ return true;
+}
+
static int nfs4_write_done(struct rpc_task *task, struct nfs_write_data *data)
{
if (!nfs4_sequence_done(task, &data->res.seq_res))
return -EAGAIN;
+ if (nfs4_write_stateid_changed(task, &data->args))
+ return -EAGAIN;
return data->write_done_cb ? data->write_done_cb(task, data) :
nfs4_write_done_cb(task, data);
}
@@ -3551,10 +3772,13 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag
static void nfs4_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
{
- nfs4_setup_sequence(NFS_SERVER(data->header->inode),
+ if (nfs4_setup_sequence(NFS_SERVER(data->header->inode),
&data->args.seq_args,
&data->res.seq_res,
- task);
+ task))
+ return;
+ nfs4_set_rw_stateid(&data->args.stateid, data->args.context,
+ data->args.lock_context, FMODE_WRITE);
}
static void nfs4_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data)
@@ -3656,7 +3880,7 @@ static int nfs4_proc_async_renew(struct nfs_client *clp, struct rpc_cred *cred,
return -ENOMEM;
data->client = clp;
data->timestamp = jiffies;
- return rpc_call_async(clp->cl_rpcclient, &msg, RPC_TASK_SOFT,
+ return rpc_call_async(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT,
&nfs4_renew_ops, data);
}
@@ -3670,7 +3894,7 @@ static int nfs4_proc_renew(struct nfs_client *clp, struct rpc_cred *cred)
unsigned long now = jiffies;
int status;
- status = rpc_call_sync(clp->cl_rpcclient, &msg, 0);
+ status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
if (status < 0)
return status;
do_renew_lease(clp, now);
@@ -3980,11 +4204,14 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
case -NFS4ERR_OPENMODE:
if (state == NULL)
break;
- nfs4_schedule_stateid_recovery(server, state);
+ if (nfs4_schedule_stateid_recovery(server, state) < 0)
+ goto stateid_invalid;
goto wait_on_recovery;
case -NFS4ERR_EXPIRED:
- if (state != NULL)
- nfs4_schedule_stateid_recovery(server, state);
+ if (state != NULL) {
+ if (nfs4_schedule_stateid_recovery(server, state) < 0)
+ goto stateid_invalid;
+ }
case -NFS4ERR_STALE_STATEID:
case -NFS4ERR_STALE_CLIENTID:
nfs4_schedule_lease_recovery(clp);
@@ -4016,6 +4243,9 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
}
task->tk_status = nfs4_map_errors(task->tk_status);
return 0;
+stateid_invalid:
+ task->tk_status = -EIO;
+ return 0;
wait_on_recovery:
rpc_sleep_on(&clp->cl_rpcwaitq, task, NULL);
if (test_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) == 0)
@@ -4143,27 +4373,17 @@ int nfs4_proc_setclientid_confirm(struct nfs_client *clp,
struct nfs4_setclientid_res *arg,
struct rpc_cred *cred)
{
- struct nfs_fsinfo fsinfo;
struct rpc_message msg = {
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SETCLIENTID_CONFIRM],
.rpc_argp = arg,
- .rpc_resp = &fsinfo,
.rpc_cred = cred,
};
- unsigned long now;
int status;
dprintk("NFS call setclientid_confirm auth=%s, (client ID %llx)\n",
clp->cl_rpcclient->cl_auth->au_ops->au_name,
clp->cl_clientid);
- now = jiffies;
status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
- if (status == 0) {
- spin_lock(&clp->cl_lock);
- clp->cl_lease_time = fsinfo.lease_time * HZ;
- clp->cl_last_renewal = now;
- spin_unlock(&clp->cl_lock);
- }
dprintk("NFS reply setclientid_confirm: %d\n", status);
return status;
}
@@ -4627,17 +4847,23 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata)
if (nfs_wait_on_sequence(data->arg.open_seqid, task) != 0) {
goto out_release_lock_seqid;
}
- data->arg.open_stateid = &state->stateid;
+ data->arg.open_stateid = &state->open_stateid;
data->arg.new_lock_owner = 1;
data->res.open_seqid = data->arg.open_seqid;
} else
data->arg.new_lock_owner = 0;
+ if (!nfs4_valid_open_stateid(state)) {
+ data->rpc_status = -EBADF;
+ task->tk_action = NULL;
+ goto out_release_open_seqid;
+ }
data->timestamp = jiffies;
if (nfs4_setup_sequence(data->server,
&data->arg.seq_args,
&data->res.seq_res,
task) == 0)
return;
+out_release_open_seqid:
nfs_release_seqid(data->arg.open_seqid);
out_release_lock_seqid:
nfs_release_seqid(data->arg.lock_seqid);
@@ -4983,58 +5209,16 @@ nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request)
return status;
}
-int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
+int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid)
{
struct nfs_server *server = NFS_SERVER(state->inode);
- struct nfs4_exception exception = { };
int err;
err = nfs4_set_lock_state(state, fl);
if (err != 0)
- goto out;
- do {
- err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW);
- switch (err) {
- default:
- printk(KERN_ERR "NFS: %s: unhandled error "
- "%d.\n", __func__, err);
- case 0:
- case -ESTALE:
- goto out;
- case -NFS4ERR_STALE_CLIENTID:
- case -NFS4ERR_STALE_STATEID:
- set_bit(NFS_DELEGATED_STATE, &state->flags);
- case -NFS4ERR_EXPIRED:
- nfs4_schedule_lease_recovery(server->nfs_client);
- err = -EAGAIN;
- goto out;
- case -NFS4ERR_BADSESSION:
- case -NFS4ERR_BADSLOT:
- case -NFS4ERR_BAD_HIGH_SLOT:
- case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
- case -NFS4ERR_DEADSESSION:
- set_bit(NFS_DELEGATED_STATE, &state->flags);
- nfs4_schedule_session_recovery(server->nfs_client->cl_session, err);
- err = -EAGAIN;
- goto out;
- case -NFS4ERR_DELEG_REVOKED:
- case -NFS4ERR_ADMIN_REVOKED:
- case -NFS4ERR_BAD_STATEID:
- case -NFS4ERR_OPENMODE:
- nfs4_schedule_stateid_recovery(server, state);
- err = 0;
- goto out;
- case -ENOMEM:
- case -NFS4ERR_DENIED:
- /* kill_proc(fl->fl_pid, SIGLOST, 1); */
- err = 0;
- goto out;
- }
- set_bit(NFS_DELEGATED_STATE, &state->flags);
- err = nfs4_handle_exception(server, err, &exception);
- } while (exception.retry);
-out:
- return err;
+ return err;
+ err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW);
+ return nfs4_handle_delegation_recall_error(server, state, stateid, err);
}
struct nfs_release_lockowner_data {
@@ -5848,7 +6032,7 @@ static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp,
.rpc_client = clp->cl_rpcclient,
.rpc_message = &msg,
.callback_ops = &nfs41_sequence_ops,
- .flags = RPC_TASK_ASYNC | RPC_TASK_SOFT,
+ .flags = RPC_TASK_ASYNC | RPC_TASK_TIMEOUT,
};
if (!atomic_inc_not_zero(&clp->cl_count))
@@ -6725,6 +6909,10 @@ static const struct nfs4_state_maintenance_ops nfs41_state_renewal_ops = {
static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = {
.minor_version = 0,
+ .init_caps = NFS_CAP_READDIRPLUS
+ | NFS_CAP_ATOMIC_OPEN
+ | NFS_CAP_CHANGE_ATTR
+ | NFS_CAP_POSIX_LOCK,
.call_sync = _nfs4_call_sync,
.match_stateid = nfs4_match_stateid,
.find_root_sec = nfs4_find_root_sec,
@@ -6736,6 +6924,12 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = {
#if defined(CONFIG_NFS_V4_1)
static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
.minor_version = 1,
+ .init_caps = NFS_CAP_READDIRPLUS
+ | NFS_CAP_ATOMIC_OPEN
+ | NFS_CAP_CHANGE_ATTR
+ | NFS_CAP_POSIX_LOCK
+ | NFS_CAP_STATEID_NFSV41
+ | NFS_CAP_ATOMIC_OPEN_V1,
.call_sync = nfs4_call_sync_sequence,
.match_stateid = nfs41_match_stateid,
.find_root_sec = nfs41_find_root_sec,
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 6ace365c6334..0b32f9483b7a 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -154,18 +154,6 @@ struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp)
return cred;
}
-static void nfs4_clear_machine_cred(struct nfs_client *clp)
-{
- struct rpc_cred *cred;
-
- spin_lock(&clp->cl_lock);
- cred = clp->cl_machine_cred;
- clp->cl_machine_cred = NULL;
- spin_unlock(&clp->cl_lock);
- if (cred != NULL)
- put_rpccred(cred);
-}
-
static struct rpc_cred *
nfs4_get_renew_cred_server_locked(struct nfs_server *server)
{
@@ -699,6 +687,8 @@ __nfs4_find_state_byowner(struct inode *inode, struct nfs4_state_owner *owner)
list_for_each_entry(state, &nfsi->open_states, inode_states) {
if (state->owner != owner)
continue;
+ if (!nfs4_valid_open_stateid(state))
+ continue;
if (atomic_inc_not_zero(&state->count))
return state;
}
@@ -987,13 +977,14 @@ int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl)
return 0;
}
-static bool nfs4_copy_lock_stateid(nfs4_stateid *dst, struct nfs4_state *state,
+static int nfs4_copy_lock_stateid(nfs4_stateid *dst,
+ struct nfs4_state *state,
const struct nfs_lockowner *lockowner)
{
struct nfs4_lock_state *lsp;
fl_owner_t fl_owner;
pid_t fl_pid;
- bool ret = false;
+ int ret = -ENOENT;
if (lockowner == NULL)
@@ -1008,7 +999,10 @@ static bool nfs4_copy_lock_stateid(nfs4_stateid *dst, struct nfs4_state *state,
lsp = __nfs4_find_lock_state(state, fl_owner, fl_pid, NFS4_ANY_LOCK_TYPE);
if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) {
nfs4_stateid_copy(dst, &lsp->ls_stateid);
- ret = true;
+ ret = 0;
+ smp_rmb();
+ if (!list_empty(&lsp->ls_seqid.list))
+ ret = -EWOULDBLOCK;
}
spin_unlock(&state->state_lock);
nfs4_put_lock_state(lsp);
@@ -1016,28 +1010,44 @@ out:
return ret;
}
-static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
+static int nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
{
+ const nfs4_stateid *src;
+ int ret;
int seq;
do {
+ src = &zero_stateid;
seq = read_seqbegin(&state->seqlock);
- nfs4_stateid_copy(dst, &state->stateid);
+ if (test_bit(NFS_OPEN_STATE, &state->flags))
+ src = &state->open_stateid;
+ nfs4_stateid_copy(dst, src);
+ ret = 0;
+ smp_rmb();
+ if (!list_empty(&state->owner->so_seqid.list))
+ ret = -EWOULDBLOCK;
} while (read_seqretry(&state->seqlock, seq));
+ return ret;
}
/*
* Byte-range lock aware utility to initialize the stateid of read/write
* requests.
*/
-void nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state,
+int nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state,
fmode_t fmode, const struct nfs_lockowner *lockowner)
{
+ int ret = 0;
if (nfs4_copy_delegation_stateid(dst, state->inode, fmode))
- return;
- if (nfs4_copy_lock_stateid(dst, state, lockowner))
- return;
- nfs4_copy_open_stateid(dst, state);
+ goto out;
+ ret = nfs4_copy_lock_stateid(dst, state, lockowner);
+ if (ret != -ENOENT)
+ goto out;
+ ret = nfs4_copy_open_stateid(dst, state);
+out:
+ if (nfs_server_capable(state->inode, NFS_CAP_STATEID_NFSV41))
+ dst->seqid = 0;
+ return ret;
}
struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_mask)
@@ -1286,14 +1296,17 @@ static int nfs4_state_mark_reclaim_nograce(struct nfs_client *clp, struct nfs4_s
return 1;
}
-void nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4_state *state)
+int nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4_state *state)
{
struct nfs_client *clp = server->nfs_client;
+ if (!nfs4_valid_open_stateid(state))
+ return -EBADF;
nfs4_state_mark_reclaim_nograce(clp, state);
dprintk("%s: scheduling stateid recovery for server %s\n", __func__,
clp->cl_hostname);
nfs4_schedule_state_manager(clp);
+ return 0;
}
EXPORT_SYMBOL_GPL(nfs4_schedule_stateid_recovery);
@@ -1323,6 +1336,27 @@ void nfs_inode_find_state_and_recover(struct inode *inode,
nfs4_schedule_state_manager(clp);
}
+static void nfs4_state_mark_open_context_bad(struct nfs4_state *state)
+{
+ struct inode *inode = state->inode;
+ struct nfs_inode *nfsi = NFS_I(inode);
+ struct nfs_open_context *ctx;
+
+ spin_lock(&inode->i_lock);
+ list_for_each_entry(ctx, &nfsi->open_files, list) {
+ if (ctx->state != state)
+ continue;
+ set_bit(NFS_CONTEXT_BAD, &ctx->flags);
+ }
+ spin_unlock(&inode->i_lock);
+}
+
+static void nfs4_state_mark_recovery_failed(struct nfs4_state *state, int error)
+{
+ set_bit(NFS_STATE_RECOVERY_FAILED, &state->flags);
+ nfs4_state_mark_open_context_bad(state);
+}
+
static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_recovery_ops *ops)
{
@@ -1398,6 +1432,8 @@ restart:
list_for_each_entry(state, &sp->so_states, open_states) {
if (!test_and_clear_bit(ops->state_flag_bit, &state->flags))
continue;
+ if (!nfs4_valid_open_stateid(state))
+ continue;
if (state->state == 0)
continue;
atomic_inc(&state->count);
@@ -1430,11 +1466,10 @@ restart:
* Open state on this file cannot be recovered
* All we can do is revert to using the zero stateid.
*/
- memset(&state->stateid, 0,
- sizeof(state->stateid));
- /* Mark the file as being 'closed' */
- state->state = 0;
+ nfs4_state_mark_recovery_failed(state, status);
break;
+ case -EAGAIN:
+ ssleep(1);
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_STALE_STATEID:
case -NFS4ERR_BAD_STATEID:
@@ -1696,6 +1731,10 @@ static int nfs4_check_lease(struct nfs_client *clp)
}
status = ops->renew_lease(clp, cred);
put_rpccred(cred);
+ if (status == -ETIMEDOUT) {
+ set_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
+ return 0;
+ }
out:
return nfs4_recovery_handle_error(clp, status);
}
@@ -1725,10 +1764,6 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
return -EPERM;
case -EACCES:
- if (clp->cl_machine_cred == NULL)
- return -EACCES;
- /* Handle case where the user hasn't set up machine creds */
- nfs4_clear_machine_cred(clp);
case -NFS4ERR_DELAY:
case -ETIMEDOUT:
case -EAGAIN:
@@ -1823,31 +1858,18 @@ int nfs4_discover_server_trunking(struct nfs_client *clp,
{
const struct nfs4_state_recovery_ops *ops =
clp->cl_mvops->reboot_recovery_ops;
- rpc_authflavor_t *flavors, flav, save;
struct rpc_clnt *clnt;
struct rpc_cred *cred;
- int i, len, status;
+ int i, status;
dprintk("NFS: %s: testing '%s'\n", __func__, clp->cl_hostname);
- len = NFS_MAX_SECFLAVORS;
- flavors = kcalloc(len, sizeof(*flavors), GFP_KERNEL);
- if (flavors == NULL) {
- status = -ENOMEM;
- goto out;
- }
- len = rpcauth_list_flavors(flavors, len);
- if (len < 0) {
- status = len;
- goto out_free;
- }
clnt = clp->cl_rpcclient;
- save = clnt->cl_auth->au_flavor;
i = 0;
mutex_lock(&nfs_clid_init_mutex);
- status = -ENOENT;
again:
+ status = -ENOENT;
cred = ops->get_clid_cred(clp);
if (cred == NULL)
goto out_unlock;
@@ -1857,12 +1879,6 @@ again:
switch (status) {
case 0:
break;
-
- case -EACCES:
- if (clp->cl_machine_cred == NULL)
- break;
- /* Handle case where the user hasn't set up machine creds */
- nfs4_clear_machine_cred(clp);
case -NFS4ERR_DELAY:
case -ETIMEDOUT:
case -EAGAIN:
@@ -1871,22 +1887,23 @@ again:
dprintk("NFS: %s after status %d, retrying\n",
__func__, status);
goto again;
-
+ case -EACCES:
+ if (i++)
+ break;
case -NFS4ERR_CLID_INUSE:
case -NFS4ERR_WRONGSEC:
- status = -EPERM;
- if (i >= len)
- break;
-
- flav = flavors[i++];
- if (flav == save)
- flav = flavors[i++];
- clnt = rpc_clone_client_set_auth(clnt, flav);
+ clnt = rpc_clone_client_set_auth(clnt, RPC_AUTH_UNIX);
if (IS_ERR(clnt)) {
status = PTR_ERR(clnt);
break;
}
- clp->cl_rpcclient = clnt;
+ /* Note: this is safe because we haven't yet marked the
+ * client as ready, so we are the only user of
+ * clp->cl_rpcclient
+ */
+ clnt = xchg(&clp->cl_rpcclient, clnt);
+ rpc_shutdown_client(clnt);
+ clnt = clp->cl_rpcclient;
goto again;
case -NFS4ERR_MINOR_VERS_MISMATCH:
@@ -1897,13 +1914,15 @@ again:
case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery
* in nfs4_exchange_id */
status = -EKEYEXPIRED;
+ break;
+ default:
+ pr_warn("NFS: %s unhandled error %d. Exiting with error EIO\n",
+ __func__, status);
+ status = -EIO;
}
out_unlock:
mutex_unlock(&nfs_clid_init_mutex);
-out_free:
- kfree(flavors);
-out:
dprintk("NFS: %s: status = %d\n", __func__, status);
return status;
}
diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c
index 569b166cc050..a5e1a3026d48 100644
--- a/fs/nfs/nfs4super.c
+++ b/fs/nfs/nfs4super.c
@@ -252,6 +252,8 @@ struct dentry *nfs4_try_mount(int flags, const char *dev_name,
dfprintk(MOUNT, "--> nfs4_try_mount()\n");
+ if (data->auth_flavors[0] == RPC_AUTH_MAXFLAVOR)
+ data->auth_flavors[0] = RPC_AUTH_UNIX;
export_path = data->nfs_server.export_path;
data->nfs_server.export_path = "/";
root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, mount_info,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index e3edda554ac7..3c79c5878c6d 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -530,14 +530,10 @@ static int nfs4_stat_to_errno(int);
decode_setclientid_maxsz)
#define NFS4_enc_setclientid_confirm_sz \
(compound_encode_hdr_maxsz + \
- encode_setclientid_confirm_maxsz + \
- encode_putrootfh_maxsz + \
- encode_fsinfo_maxsz)
+ encode_setclientid_confirm_maxsz)
#define NFS4_dec_setclientid_confirm_sz \
(compound_decode_hdr_maxsz + \
- decode_setclientid_confirm_maxsz + \
- decode_putrootfh_maxsz + \
- decode_fsinfo_maxsz)
+ decode_setclientid_confirm_maxsz)
#define NFS4_enc_lock_sz (compound_encode_hdr_maxsz + \
encode_sequence_maxsz + \
encode_putfh_maxsz + \
@@ -1058,8 +1054,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const
if (iap->ia_valid & ATTR_ATIME_SET) {
bmval1 |= FATTR4_WORD1_TIME_ACCESS_SET;
*p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME);
- *p++ = cpu_to_be32(0);
- *p++ = cpu_to_be32(iap->ia_atime.tv_sec);
+ p = xdr_encode_hyper(p, (s64)iap->ia_atime.tv_sec);
*p++ = cpu_to_be32(iap->ia_atime.tv_nsec);
}
else if (iap->ia_valid & ATTR_ATIME) {
@@ -1069,8 +1064,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const
if (iap->ia_valid & ATTR_MTIME_SET) {
bmval1 |= FATTR4_WORD1_TIME_MODIFY_SET;
*p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME);
- *p++ = cpu_to_be32(0);
- *p++ = cpu_to_be32(iap->ia_mtime.tv_sec);
+ p = xdr_encode_hyper(p, (s64)iap->ia_mtime.tv_sec);
*p++ = cpu_to_be32(iap->ia_mtime.tv_nsec);
}
else if (iap->ia_valid & ATTR_MTIME) {
@@ -1366,33 +1360,28 @@ static inline void encode_openhdr(struct xdr_stream *xdr, const struct nfs_opena
static inline void encode_createmode(struct xdr_stream *xdr, const struct nfs_openargs *arg)
{
+ struct iattr dummy;
__be32 *p;
- struct nfs_client *clp;
p = reserve_space(xdr, 4);
- switch(arg->open_flags & O_EXCL) {
- case 0:
+ switch(arg->createmode) {
+ case NFS4_CREATE_UNCHECKED:
*p = cpu_to_be32(NFS4_CREATE_UNCHECKED);
encode_attrs(xdr, arg->u.attrs, arg->server);
break;
- default:
- clp = arg->server->nfs_client;
- if (clp->cl_mvops->minor_version > 0) {
- if (nfs4_has_persistent_session(clp)) {
- *p = cpu_to_be32(NFS4_CREATE_GUARDED);
- encode_attrs(xdr, arg->u.attrs, arg->server);
- } else {
- struct iattr dummy;
-
- *p = cpu_to_be32(NFS4_CREATE_EXCLUSIVE4_1);
- encode_nfs4_verifier(xdr, &arg->u.verifier);
- dummy.ia_valid = 0;
- encode_attrs(xdr, &dummy, arg->server);
- }
- } else {
- *p = cpu_to_be32(NFS4_CREATE_EXCLUSIVE);
- encode_nfs4_verifier(xdr, &arg->u.verifier);
- }
+ case NFS4_CREATE_GUARDED:
+ *p = cpu_to_be32(NFS4_CREATE_GUARDED);
+ encode_attrs(xdr, arg->u.attrs, arg->server);
+ break;
+ case NFS4_CREATE_EXCLUSIVE:
+ *p = cpu_to_be32(NFS4_CREATE_EXCLUSIVE);
+ encode_nfs4_verifier(xdr, &arg->u.verifier);
+ break;
+ case NFS4_CREATE_EXCLUSIVE4_1:
+ *p = cpu_to_be32(NFS4_CREATE_EXCLUSIVE4_1);
+ encode_nfs4_verifier(xdr, &arg->u.verifier);
+ dummy.ia_valid = 0;
+ encode_attrs(xdr, &dummy, arg->server);
}
}
@@ -1459,6 +1448,23 @@ static inline void encode_claim_delegate_cur(struct xdr_stream *xdr, const struc
encode_string(xdr, name->len, name->name);
}
+static inline void encode_claim_fh(struct xdr_stream *xdr)
+{
+ __be32 *p;
+
+ p = reserve_space(xdr, 4);
+ *p = cpu_to_be32(NFS4_OPEN_CLAIM_FH);
+}
+
+static inline void encode_claim_delegate_cur_fh(struct xdr_stream *xdr, const nfs4_stateid *stateid)
+{
+ __be32 *p;
+
+ p = reserve_space(xdr, 4);
+ *p = cpu_to_be32(NFS4_OPEN_CLAIM_DELEG_CUR_FH);
+ encode_nfs4_stateid(xdr, stateid);
+}
+
static void encode_open(struct xdr_stream *xdr, const struct nfs_openargs *arg, struct compound_hdr *hdr)
{
encode_op_hdr(xdr, OP_OPEN, decode_open_maxsz, hdr);
@@ -1474,6 +1480,12 @@ static void encode_open(struct xdr_stream *xdr, const struct nfs_openargs *arg,
case NFS4_OPEN_CLAIM_DELEGATE_CUR:
encode_claim_delegate_cur(xdr, arg->name, &arg->u.delegation);
break;
+ case NFS4_OPEN_CLAIM_FH:
+ encode_claim_fh(xdr);
+ break;
+ case NFS4_OPEN_CLAIM_DELEG_CUR_FH:
+ encode_claim_delegate_cur_fh(xdr, &arg->u.delegation);
+ break;
default:
BUG();
}
@@ -1506,35 +1518,12 @@ static void encode_putrootfh(struct xdr_stream *xdr, struct compound_hdr *hdr)
encode_op_hdr(xdr, OP_PUTROOTFH, decode_putrootfh_maxsz, hdr);
}
-static void encode_open_stateid(struct xdr_stream *xdr,
- const struct nfs_open_context *ctx,
- const struct nfs_lock_context *l_ctx,
- fmode_t fmode,
- int zero_seqid)
-{
- nfs4_stateid stateid;
-
- if (ctx->state != NULL) {
- const struct nfs_lockowner *lockowner = NULL;
-
- if (l_ctx != NULL)
- lockowner = &l_ctx->lockowner;
- nfs4_select_rw_stateid(&stateid, ctx->state,
- fmode, lockowner);
- if (zero_seqid)
- stateid.seqid = 0;
- encode_nfs4_stateid(xdr, &stateid);
- } else
- encode_nfs4_stateid(xdr, &zero_stateid);
-}
-
static void encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args, struct compound_hdr *hdr)
{
__be32 *p;
encode_op_hdr(xdr, OP_READ, decode_read_maxsz, hdr);
- encode_open_stateid(xdr, args->context, args->lock_context,
- FMODE_READ, hdr->minorversion);
+ encode_nfs4_stateid(xdr, &args->stateid);
p = reserve_space(xdr, 12);
p = xdr_encode_hyper(p, args->offset);
@@ -1670,8 +1659,7 @@ static void encode_write(struct xdr_stream *xdr, const struct nfs_writeargs *arg
__be32 *p;
encode_op_hdr(xdr, OP_WRITE, decode_write_maxsz, hdr);
- encode_open_stateid(xdr, args->context, args->lock_context,
- FMODE_WRITE, hdr->minorversion);
+ encode_nfs4_stateid(xdr, &args->stateid);
p = reserve_space(xdr, 16);
p = xdr_encode_hyper(p, args->offset);
@@ -2609,12 +2597,9 @@ static void nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req,
struct compound_hdr hdr = {
.nops = 0,
};
- const u32 lease_bitmap[3] = { FATTR4_WORD0_LEASE_TIME };
encode_compound_hdr(xdr, req, &hdr);
encode_setclientid_confirm(xdr, arg, &hdr);
- encode_putrootfh(xdr, &hdr);
- encode_fsinfo(xdr, lease_bitmap, &hdr);
encode_nops(&hdr);
}
@@ -3497,8 +3482,11 @@ static int decode_pathname(struct xdr_stream *xdr, struct nfs4_pathname *path)
if (n == 0)
goto root_path;
dprintk("pathname4: ");
- path->ncomponents = 0;
- while (path->ncomponents < n) {
+ if (n > NFS4_PATHNAME_MAXCOMPONENTS) {
+ dprintk("cannot parse %d components in path\n", n);
+ goto out_eio;
+ }
+ for (path->ncomponents = 0; path->ncomponents < n; path->ncomponents++) {
struct nfs4_string *component = &path->components[path->ncomponents];
status = decode_opaque_inline(xdr, &component->len, &component->data);
if (unlikely(status != 0))
@@ -3507,12 +3495,6 @@ static int decode_pathname(struct xdr_stream *xdr, struct nfs4_pathname *path)
pr_cont("%s%.*s ",
(path->ncomponents != n ? "/ " : ""),
component->len, component->data);
- if (path->ncomponents < NFS4_PATHNAME_MAXCOMPONENTS)
- path->ncomponents++;
- else {
- dprintk("cannot parse %d components in path\n", n);
- goto out_eio;
- }
}
out:
return status;
@@ -3557,27 +3539,23 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st
n = be32_to_cpup(p);
if (n <= 0)
goto out_eio;
- res->nlocations = 0;
- while (res->nlocations < n) {
+ for (res->nlocations = 0; res->nlocations < n; res->nlocations++) {
u32 m;
- struct nfs4_fs_location *loc = &res->locations[res->nlocations];
+ struct nfs4_fs_location *loc;
+ if (res->nlocations == NFS4_FS_LOCATIONS_MAXENTRIES)
+ break;
+ loc = &res->locations[res->nlocations];
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
goto out_overflow;
m = be32_to_cpup(p);
- loc->nservers = 0;
dprintk("%s: servers:\n", __func__);
- while (loc->nservers < m) {
- struct nfs4_string *server = &loc->servers[loc->nservers];
- status = decode_opaque_inline(xdr, &server->len, &server->data);
- if (unlikely(status != 0))
- goto out_eio;
- dprintk("%s ", server->data);
- if (loc->nservers < NFS4_FS_LOCATION_MAXSERVERS)
- loc->nservers++;
- else {
+ for (loc->nservers = 0; loc->nservers < m; loc->nservers++) {
+ struct nfs4_string *server;
+
+ if (loc->nservers == NFS4_FS_LOCATION_MAXSERVERS) {
unsigned int i;
dprintk("%s: using first %u of %u servers "
"returned for location %u\n",
@@ -3591,13 +3569,17 @@ static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, st
if (unlikely(status != 0))
goto out_eio;
}
+ break;
}
+ server = &loc->servers[loc->nservers];
+ status = decode_opaque_inline(xdr, &server->len, &server->data);
+ if (unlikely(status != 0))
+ goto out_eio;
+ dprintk("%s ", server->data);
}
status = decode_pathname(xdr, &loc->rootpath);
if (unlikely(status != 0))
goto out_eio;
- if (res->nlocations < NFS4_FS_LOCATIONS_MAXENTRIES)
- res->nlocations++;
}
if (res->nlocations != 0)
status = NFS_ATTR_FATTR_V4_LOCATIONS;
@@ -5209,27 +5191,30 @@ static int decode_delegreturn(struct xdr_stream *xdr)
return decode_op_hdr(xdr, OP_DELEGRETURN);
}
-static int decode_secinfo_gss(struct xdr_stream *xdr, struct nfs4_secinfo_flavor *flavor)
+static int decode_secinfo_gss(struct xdr_stream *xdr,
+ struct nfs4_secinfo4 *flavor)
{
+ u32 oid_len;
__be32 *p;
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
goto out_overflow;
- flavor->gss.sec_oid4.len = be32_to_cpup(p);
- if (flavor->gss.sec_oid4.len > GSS_OID_MAX_LEN)
+ oid_len = be32_to_cpup(p);
+ if (oid_len > GSS_OID_MAX_LEN)
goto out_err;
- p = xdr_inline_decode(xdr, flavor->gss.sec_oid4.len);
+ p = xdr_inline_decode(xdr, oid_len);
if (unlikely(!p))
goto out_overflow;
- memcpy(flavor->gss.sec_oid4.data, p, flavor->gss.sec_oid4.len);
+ memcpy(flavor->flavor_info.oid.data, p, oid_len);
+ flavor->flavor_info.oid.len = oid_len;
p = xdr_inline_decode(xdr, 8);
if (unlikely(!p))
goto out_overflow;
- flavor->gss.qop4 = be32_to_cpup(p++);
- flavor->gss.service = be32_to_cpup(p);
+ flavor->flavor_info.qop = be32_to_cpup(p++);
+ flavor->flavor_info.service = be32_to_cpup(p);
return 0;
@@ -5242,10 +5227,10 @@ out_err:
static int decode_secinfo_common(struct xdr_stream *xdr, struct nfs4_secinfo_res *res)
{
- struct nfs4_secinfo_flavor *sec_flavor;
+ struct nfs4_secinfo4 *sec_flavor;
+ unsigned int i, num_flavors;
int status;
__be32 *p;
- int i, num_flavors;
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
@@ -6648,8 +6633,7 @@ static int nfs4_xdr_dec_setclientid(struct rpc_rqst *req,
* Decode SETCLIENTID_CONFIRM response
*/
static int nfs4_xdr_dec_setclientid_confirm(struct rpc_rqst *req,
- struct xdr_stream *xdr,
- struct nfs_fsinfo *fsinfo)
+ struct xdr_stream *xdr)
{
struct compound_hdr hdr;
int status;
@@ -6657,10 +6641,6 @@ static int nfs4_xdr_dec_setclientid_confirm(struct rpc_rqst *req,
status = decode_compound_hdr(xdr, &hdr);
if (!status)
status = decode_setclientid_confirm(xdr);
- if (!status)
- status = decode_putrootfh(xdr);
- if (!status)
- status = decode_fsinfo(xdr, fsinfo);
return status;
}
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index 88f9611a945c..5457745dd4f1 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -234,7 +234,7 @@ static int __alloc_objio_seg(unsigned numdevs, gfp_t gfp_flags,
lseg = kzalloc(lseg_size, gfp_flags);
if (unlikely(!lseg)) {
- dprintk("%s: Faild allocation numdevs=%d size=%zd\n", __func__,
+ dprintk("%s: Failed allocation numdevs=%d size=%zd\n", __func__,
numdevs, lseg_size);
return -ENOMEM;
}
diff --git a/fs/nfs/objlayout/objlayout.h b/fs/nfs/objlayout/objlayout.h
index 880ba086be94..87aa1dec6120 100644
--- a/fs/nfs/objlayout/objlayout.h
+++ b/fs/nfs/objlayout/objlayout.h
@@ -114,7 +114,7 @@ extern int objio_alloc_lseg(struct pnfs_layout_segment **outp,
gfp_t gfp_flags);
extern void objio_free_lseg(struct pnfs_layout_segment *lseg);
-/* objio_free_result will free these @oir structs recieved from
+/* objio_free_result will free these @oir structs received from
* objlayout_{read,write}_done
*/
extern void objio_free_result(struct objlayout_io_res *oir);
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index e56e846e9d2d..29cfb7ade121 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -84,6 +84,55 @@ nfs_page_free(struct nfs_page *p)
kmem_cache_free(nfs_page_cachep, p);
}
+static void
+nfs_iocounter_inc(struct nfs_io_counter *c)
+{
+ atomic_inc(&c->io_count);
+}
+
+static void
+nfs_iocounter_dec(struct nfs_io_counter *c)
+{
+ if (atomic_dec_and_test(&c->io_count)) {
+ clear_bit(NFS_IO_INPROGRESS, &c->flags);
+ smp_mb__after_clear_bit();
+ wake_up_bit(&c->flags, NFS_IO_INPROGRESS);
+ }
+}
+
+static int
+__nfs_iocounter_wait(struct nfs_io_counter *c)
+{
+ wait_queue_head_t *wq = bit_waitqueue(&c->flags, NFS_IO_INPROGRESS);
+ DEFINE_WAIT_BIT(q, &c->flags, NFS_IO_INPROGRESS);
+ int ret = 0;
+
+ do {
+ prepare_to_wait(wq, &q.wait, TASK_KILLABLE);
+ set_bit(NFS_IO_INPROGRESS, &c->flags);
+ if (atomic_read(&c->io_count) == 0)
+ break;
+ ret = nfs_wait_bit_killable(&c->flags);
+ } while (atomic_read(&c->io_count) != 0);
+ finish_wait(wq, &q.wait);
+ return ret;
+}
+
+/**
+ * nfs_iocounter_wait - wait for i/o to complete
+ * @c: nfs_io_counter to use
+ *
+ * returns -ERESTARTSYS if interrupted by a fatal signal.
+ * Otherwise returns 0 once the io_count hits 0.
+ */
+int
+nfs_iocounter_wait(struct nfs_io_counter *c)
+{
+ if (atomic_read(&c->io_count) == 0)
+ return 0;
+ return __nfs_iocounter_wait(c);
+}
+
/**
* nfs_create_request - Create an NFS read/write request.
* @ctx: open context to use
@@ -104,6 +153,8 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode,
struct nfs_page *req;
struct nfs_lock_context *l_ctx;
+ if (test_bit(NFS_CONTEXT_BAD, &ctx->flags))
+ return ERR_PTR(-EBADF);
/* try to allocate the request struct */
req = nfs_page_alloc();
if (req == NULL)
@@ -116,6 +167,7 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode,
return ERR_CAST(l_ctx);
}
req->wb_lock_context = l_ctx;
+ nfs_iocounter_inc(&l_ctx->io_count);
/* Initialize the request struct. Initially, we assume a
* long write-back delay. This will be adjusted in
@@ -175,6 +227,7 @@ static void nfs_clear_request(struct nfs_page *req)
req->wb_page = NULL;
}
if (l_ctx != NULL) {
+ nfs_iocounter_dec(&l_ctx->io_count);
nfs_put_lock_context(l_ctx);
req->wb_lock_context = NULL;
}
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 4bdffe0ba025..c5bd758e5637 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -718,6 +718,8 @@ pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
spin_lock(&lo->plh_inode->i_lock);
if (pnfs_layoutgets_blocked(lo, 1)) {
status = -EAGAIN;
+ } else if (!nfs4_valid_open_stateid(open_state)) {
+ status = -EBADF;
} else if (list_empty(&lo->plh_segs)) {
int seq;
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index a5e5d9899d56..70a26c651f09 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -514,6 +514,8 @@ void nfs_read_prepare(struct rpc_task *task, void *calldata)
{
struct nfs_read_data *data = calldata;
NFS_PROTO(data->header->inode)->read_rpc_prepare(task, data);
+ if (unlikely(test_bit(NFS_CONTEXT_BAD, &data->args.context->flags)))
+ rpc_exit(task, -EIO);
}
static const struct rpc_call_ops nfs_read_common_ops = {
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 2f8a29db0f1b..eb494f6a4c6b 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -920,7 +920,7 @@ static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(void)
data->mount_server.port = NFS_UNSPEC_PORT;
data->nfs_server.port = NFS_UNSPEC_PORT;
data->nfs_server.protocol = XPRT_TRANSPORT_TCP;
- data->auth_flavors[0] = RPC_AUTH_UNIX;
+ data->auth_flavors[0] = RPC_AUTH_MAXFLAVOR;
data->auth_flavor_len = 1;
data->minorversion = 0;
data->need_mount = true;
@@ -1608,49 +1608,57 @@ out_security_failure:
}
/*
- * Match the requested auth flavors with the list returned by
- * the server. Returns zero and sets the mount's authentication
- * flavor on success; returns -EACCES if server does not support
- * the requested flavor.
+ * Select a security flavor for this mount. The selected flavor
+ * is planted in args->auth_flavors[0].
*/
-static int nfs_walk_authlist(struct nfs_parsed_mount_data *args,
- struct nfs_mount_request *request)
+static void nfs_select_flavor(struct nfs_parsed_mount_data *args,
+ struct nfs_mount_request *request)
{
- unsigned int i, j, server_authlist_len = *(request->auth_flav_len);
+ unsigned int i, count = *(request->auth_flav_len);
+ rpc_authflavor_t flavor;
+
+ if (args->auth_flavors[0] != RPC_AUTH_MAXFLAVOR)
+ goto out;
+
+ /*
+ * The NFSv2 MNT operation does not return a flavor list.
+ */
+ if (args->mount_server.version != NFS_MNT3_VERSION)
+ goto out_default;
/*
* Certain releases of Linux's mountd return an empty
- * flavor list. To prevent behavioral regression with
- * these servers (ie. rejecting mounts that used to
- * succeed), revert to pre-2.6.32 behavior (no checking)
- * if the returned flavor list is empty.
+ * flavor list in some cases.
*/
- if (server_authlist_len == 0)
- return 0;
+ if (count == 0)
+ goto out_default;
/*
- * We avoid sophisticated negotiating here, as there are
- * plenty of cases where we can get it wrong, providing
- * either too little or too much security.
- *
* RFC 2623, section 2.7 suggests we SHOULD prefer the
* flavor listed first. However, some servers list
- * AUTH_NULL first. Our caller plants AUTH_SYS, the
- * preferred default, in args->auth_flavors[0] if user
- * didn't specify sec= mount option.
+ * AUTH_NULL first. Avoid ever choosing AUTH_NULL.
*/
- for (i = 0; i < args->auth_flavor_len; i++)
- for (j = 0; j < server_authlist_len; j++)
- if (args->auth_flavors[i] == request->auth_flavs[j]) {
- dfprintk(MOUNT, "NFS: using auth flavor %d\n",
- request->auth_flavs[j]);
- args->auth_flavors[0] = request->auth_flavs[j];
- return 0;
- }
+ for (i = 0; i < count; i++) {
+ struct rpcsec_gss_info info;
+
+ flavor = request->auth_flavs[i];
+ switch (flavor) {
+ case RPC_AUTH_UNIX:
+ goto out_set;
+ case RPC_AUTH_NULL:
+ continue;
+ default:
+ if (rpcauth_get_gssinfo(flavor, &info) == 0)
+ goto out_set;
+ }
+ }
- dfprintk(MOUNT, "NFS: server does not support requested auth flavor\n");
- nfs_umount(request);
- return -EACCES;
+out_default:
+ flavor = RPC_AUTH_UNIX;
+out_set:
+ args->auth_flavors[0] = flavor;
+out:
+ dfprintk(MOUNT, "NFS: using auth flavor %d\n", args->auth_flavors[0]);
}
/*
@@ -1713,12 +1721,8 @@ static int nfs_request_mount(struct nfs_parsed_mount_data *args,
return status;
}
- /*
- * MNTv1 (NFSv2) does not support auth flavor negotiation.
- */
- if (args->mount_server.version != NFS_MNT3_VERSION)
- return 0;
- return nfs_walk_authlist(args, &request);
+ nfs_select_flavor(args, &request);
+ return 0;
}
struct dentry *nfs_try_mount(int flags, const char *dev_name,
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index c483cc50b82e..a2c7c28049d5 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1251,6 +1251,8 @@ void nfs_write_prepare(struct rpc_task *task, void *calldata)
{
struct nfs_write_data *data = calldata;
NFS_PROTO(data->header->inode)->write_rpc_prepare(task, data);
+ if (unlikely(test_bit(NFS_CONTEXT_BAD, &data->args.context->flags)))
+ rpc_exit(task, -EIO);
}
void nfs_commit_prepare(struct rpc_task *task, void *calldata)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 2e27430b9070..417c84877742 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -234,7 +234,6 @@ static struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct
kmem_cache *slab)
{
struct idr *stateids = &cl->cl_stateids;
- static int min_stateid = 0;
struct nfs4_stid *stid;
int new_id;
@@ -242,7 +241,7 @@ kmem_cache *slab)
if (!stid)
return NULL;
- new_id = idr_alloc(stateids, stid, min_stateid, 0, GFP_KERNEL);
+ new_id = idr_alloc_cyclic(stateids, stid, 0, 0, GFP_KERNEL);
if (new_id < 0)
goto out_free;
stid->sc_client = cl;
@@ -261,10 +260,6 @@ kmem_cache *slab)
* amount of time until an id is reused, by ensuring they always
* "increase" (mod INT_MAX):
*/
-
- min_stateid = new_id+1;
- if (min_stateid == INT_MAX)
- min_stateid = 0;
return stid;
out_free:
kfree(stid);
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index a2720071f282..2502951714b1 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3138,10 +3138,9 @@ nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
static __be32
nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp,
- __be32 nfserr,struct svc_export *exp)
+ __be32 nfserr, struct svc_export *exp)
{
- int i = 0;
- u32 nflavs;
+ u32 i, nflavs;
struct exp_flavor_info *flavs;
struct exp_flavor_info def_flavs[2];
__be32 *p;
@@ -3172,30 +3171,29 @@ nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp,
WRITE32(nflavs);
ADJUST_ARGS();
for (i = 0; i < nflavs; i++) {
- u32 flav = flavs[i].pseudoflavor;
- struct gss_api_mech *gm = gss_mech_get_by_pseudoflavor(flav);
+ struct rpcsec_gss_info info;
- if (gm) {
+ if (rpcauth_get_gssinfo(flavs[i].pseudoflavor, &info) == 0) {
RESERVE_SPACE(4);
WRITE32(RPC_AUTH_GSS);
ADJUST_ARGS();
- RESERVE_SPACE(4 + gm->gm_oid.len);
- WRITE32(gm->gm_oid.len);
- WRITEMEM(gm->gm_oid.data, gm->gm_oid.len);
+ RESERVE_SPACE(4 + info.oid.len);
+ WRITE32(info.oid.len);
+ WRITEMEM(info.oid.data, info.oid.len);
ADJUST_ARGS();
RESERVE_SPACE(4);
- WRITE32(0); /* qop */
+ WRITE32(info.qop);
ADJUST_ARGS();
RESERVE_SPACE(4);
- WRITE32(gss_pseudoflavor_to_service(gm, flav));
+ WRITE32(info.service);
ADJUST_ARGS();
- gss_mech_put(gm);
} else {
RESERVE_SPACE(4);
- WRITE32(flav);
+ WRITE32(flavs[i].pseudoflavor);
ADJUST_ARGS();
}
}
+
out:
if (exp)
exp_put(exp);
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index e0f7c1241a6a..8562bd3af947 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -359,7 +359,6 @@ static int inotify_find_inode(const char __user *dirname, struct path *path, uns
}
static int inotify_add_to_idr(struct idr *idr, spinlock_t *idr_lock,
- int *last_wd,
struct inotify_inode_mark *i_mark)
{
int ret;
@@ -367,11 +366,10 @@ static int inotify_add_to_idr(struct idr *idr, spinlock_t *idr_lock,
idr_preload(GFP_KERNEL);
spin_lock(idr_lock);
- ret = idr_alloc(idr, i_mark, *last_wd + 1, 0, GFP_NOWAIT);
+ ret = idr_alloc_cyclic(idr, i_mark, 1, 0, GFP_NOWAIT);
if (ret >= 0) {
/* we added the mark to the idr, take a reference */
i_mark->wd = ret;
- *last_wd = i_mark->wd;
fsnotify_get_mark(&i_mark->fsn_mark);
}
@@ -638,8 +636,7 @@ static int inotify_new_watch(struct fsnotify_group *group,
if (atomic_read(&group->inotify_data.user->inotify_watches) >= inotify_max_user_watches)
goto out_err;
- ret = inotify_add_to_idr(idr, idr_lock, &group->inotify_data.last_wd,
- tmp_i_mark);
+ ret = inotify_add_to_idr(idr, idr_lock, tmp_i_mark);
if (ret)
goto out_err;
@@ -697,7 +694,6 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events)
spin_lock_init(&group->inotify_data.idr_lock);
idr_init(&group->inotify_data.idr);
- group->inotify_data.last_wd = 0;
group->inotify_data.user = get_current_user();
if (atomic_inc_return(&group->inotify_data.user->inotify_devs) >
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index eeac97bb3bfa..b3fdd1a323d6 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1498,10 +1498,8 @@ leave:
dlm_put(dlm);
if (ret < 0) {
- if (buf)
- kfree(buf);
- if (item)
- kfree(item);
+ kfree(buf);
+ kfree(item);
mlog_errno(ret);
}
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 752f0b26221d..0c60ef2d8056 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -101,13 +101,6 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags,
if (!S_ISDIR(inode->i_mode))
flags &= ~OCFS2_DIRSYNC_FL;
- handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
- if (IS_ERR(handle)) {
- status = PTR_ERR(handle);
- mlog_errno(status);
- goto bail_unlock;
- }
-
oldflags = ocfs2_inode->ip_attr;
flags = flags & mask;
flags |= oldflags & ~mask;
@@ -120,7 +113,14 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags,
if ((oldflags & OCFS2_IMMUTABLE_FL) || ((flags ^ oldflags) &
(OCFS2_APPEND_FL | OCFS2_IMMUTABLE_FL))) {
if (!capable(CAP_LINUX_IMMUTABLE))
- goto bail_commit;
+ goto bail_unlock;
+ }
+
+ handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
+ if (IS_ERR(handle)) {
+ status = PTR_ERR(handle);
+ mlog_errno(status);
+ goto bail_unlock;
}
ocfs2_inode->ip_attr = flags;
@@ -130,8 +130,8 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags,
if (status < 0)
mlog_errno(status);
-bail_commit:
ocfs2_commit_trans(osb, handle);
+
bail_unlock:
ocfs2_inode_unlock(inode, 1);
bail:
@@ -706,8 +706,10 @@ int ocfs2_info_handle_freefrag(struct inode *inode,
o2info_set_request_filled(&oiff->iff_req);
- if (o2info_to_user(*oiff, req))
+ if (o2info_to_user(*oiff, req)) {
+ status = -EFAULT;
goto bail;
+ }
status = 0;
bail:
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index 9f8dcadd9a50..f1fc172175b6 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -471,7 +471,7 @@ static int ocfs2_validate_and_adjust_move_goal(struct inode *inode,
int ret, goal_bit = 0;
struct buffer_head *gd_bh = NULL;
- struct ocfs2_group_desc *bg = NULL;
+ struct ocfs2_group_desc *bg;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
int c_to_b = 1 << (osb->s_clustersize_bits -
inode->i_sb->s_blocksize_bits);
@@ -482,13 +482,6 @@ static int ocfs2_validate_and_adjust_move_goal(struct inode *inode,
range->me_goal = ocfs2_block_to_cluster_start(inode->i_sb,
range->me_goal);
/*
- * moving goal is not allowd to start with a group desc blok(#0 blk)
- * let's compromise to the latter cluster.
- */
- if (range->me_goal == le64_to_cpu(bg->bg_blkno))
- range->me_goal += c_to_b;
-
- /*
* validate goal sits within global_bitmap, and return the victim
* group desc
*/
@@ -502,6 +495,13 @@ static int ocfs2_validate_and_adjust_move_goal(struct inode *inode,
bg = (struct ocfs2_group_desc *)gd_bh->b_data;
/*
+ * moving goal is not allowd to start with a group desc blok(#0 blk)
+ * let's compromise to the latter cluster.
+ */
+ if (range->me_goal == le64_to_cpu(bg->bg_blkno))
+ range->me_goal += c_to_b;
+
+ /*
* movement is not gonna cross two groups.
*/
if ((le16_to_cpu(bg->bg_bits) - goal_bit) * osb->s_clustersize <
@@ -1057,42 +1057,40 @@ int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp)
struct inode *inode = file_inode(filp);
struct ocfs2_move_extents range;
- struct ocfs2_move_extents_context *context = NULL;
+ struct ocfs2_move_extents_context *context;
+
+ if (!argp)
+ return -EINVAL;
status = mnt_want_write_file(filp);
if (status)
return status;
if ((!S_ISREG(inode->i_mode)) || !(filp->f_mode & FMODE_WRITE))
- goto out;
+ goto out_drop;
if (inode->i_flags & (S_IMMUTABLE|S_APPEND)) {
status = -EPERM;
- goto out;
+ goto out_drop;
}
context = kzalloc(sizeof(struct ocfs2_move_extents_context), GFP_NOFS);
if (!context) {
status = -ENOMEM;
mlog_errno(status);
- goto out;
+ goto out_drop;
}
context->inode = inode;
context->file = filp;
- if (argp) {
- if (copy_from_user(&range, argp, sizeof(range))) {
- status = -EFAULT;
- goto out;
- }
- } else {
- status = -EINVAL;
- goto out;
+ if (copy_from_user(&range, argp, sizeof(range))) {
+ status = -EFAULT;
+ goto out_free;
}
if (range.me_start > i_size_read(inode))
- goto out;
+ goto out_free;
if (range.me_start + range.me_len > i_size_read(inode))
range.me_len = i_size_read(inode) - range.me_start;
@@ -1124,25 +1122,24 @@ int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp)
status = ocfs2_validate_and_adjust_move_goal(inode, &range);
if (status)
- goto out;
+ goto out_copy;
}
status = ocfs2_move_extents(context);
if (status)
mlog_errno(status);
-out:
+out_copy:
/*
* movement/defragmentation may end up being partially completed,
* that's the reason why we need to return userspace the finished
* length and new_offset even if failure happens somewhere.
*/
- if (argp) {
- if (copy_to_user(argp, &range, sizeof(range)))
- status = -EFAULT;
- }
+ if (copy_to_user(argp, &range, sizeof(range)))
+ status = -EFAULT;
+out_free:
kfree(context);
-
+out_drop:
mnt_drop_write_file(filp);
return status;
diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index 712f24db9600..ab30716584f5 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -5,7 +5,7 @@
obj-y += proc.o
proc-y := nommu.o task_nommu.o
-proc-$(CONFIG_MMU) := mmu.o task_mmu.o
+proc-$(CONFIG_MMU) := task_mmu.o
proc-y += inode.o root.o base.o generic.o array.o \
fd.o
diff --git a/fs/proc/array.c b/fs/proc/array.c
index f7ed9ee46eb9..cbd0f1b324b9 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -143,6 +143,7 @@ static const char * const task_state_array[] = {
"x (dead)", /* 64 */
"K (wakekill)", /* 128 */
"W (waking)", /* 256 */
+ "P (parked)", /* 512 */
};
static inline const char *get_task_state(struct task_struct *tsk)
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 69078c7cef1f..a19308604145 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -86,6 +86,7 @@
#include <linux/fs_struct.h>
#include <linux/slab.h>
#include <linux/flex_array.h>
+#include <linux/posix-timers.h>
#ifdef CONFIG_HARDWALL
#include <asm/hardwall.h>
#endif
@@ -2013,6 +2014,102 @@ static const struct file_operations proc_map_files_operations = {
.llseek = default_llseek,
};
+struct timers_private {
+ struct pid *pid;
+ struct task_struct *task;
+ struct sighand_struct *sighand;
+ struct pid_namespace *ns;
+ unsigned long flags;
+};
+
+static void *timers_start(struct seq_file *m, loff_t *pos)
+{
+ struct timers_private *tp = m->private;
+
+ tp->task = get_pid_task(tp->pid, PIDTYPE_PID);
+ if (!tp->task)
+ return ERR_PTR(-ESRCH);
+
+ tp->sighand = lock_task_sighand(tp->task, &tp->flags);
+ if (!tp->sighand)
+ return ERR_PTR(-ESRCH);
+
+ return seq_list_start(&tp->task->signal->posix_timers, *pos);
+}
+
+static void *timers_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ struct timers_private *tp = m->private;
+ return seq_list_next(v, &tp->task->signal->posix_timers, pos);
+}
+
+static void timers_stop(struct seq_file *m, void *v)
+{
+ struct timers_private *tp = m->private;
+
+ if (tp->sighand) {
+ unlock_task_sighand(tp->task, &tp->flags);
+ tp->sighand = NULL;
+ }
+
+ if (tp->task) {
+ put_task_struct(tp->task);
+ tp->task = NULL;
+ }
+}
+
+static int show_timer(struct seq_file *m, void *v)
+{
+ struct k_itimer *timer;
+ struct timers_private *tp = m->private;
+ int notify;
+ static char *nstr[] = {
+ [SIGEV_SIGNAL] = "signal",
+ [SIGEV_NONE] = "none",
+ [SIGEV_THREAD] = "thread",
+ };
+
+ timer = list_entry((struct list_head *)v, struct k_itimer, list);
+ notify = timer->it_sigev_notify;
+
+ seq_printf(m, "ID: %d\n", timer->it_id);
+ seq_printf(m, "signal: %d/%p\n", timer->sigq->info.si_signo,
+ timer->sigq->info.si_value.sival_ptr);
+ seq_printf(m, "notify: %s/%s.%d\n",
+ nstr[notify & ~SIGEV_THREAD_ID],
+ (notify & SIGEV_THREAD_ID) ? "tid" : "pid",
+ pid_nr_ns(timer->it_pid, tp->ns));
+
+ return 0;
+}
+
+static const struct seq_operations proc_timers_seq_ops = {
+ .start = timers_start,
+ .next = timers_next,
+ .stop = timers_stop,
+ .show = show_timer,
+};
+
+static int proc_timers_open(struct inode *inode, struct file *file)
+{
+ struct timers_private *tp;
+
+ tp = __seq_open_private(file, &proc_timers_seq_ops,
+ sizeof(struct timers_private));
+ if (!tp)
+ return -ENOMEM;
+
+ tp->pid = proc_pid(inode);
+ tp->ns = inode->i_sb->s_fs_info;
+ return 0;
+}
+
+static const struct file_operations proc_timers_operations = {
+ .open = proc_timers_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release_private,
+};
#endif /* CONFIG_CHECKPOINT_RESTORE */
static struct dentry *proc_pident_instantiate(struct inode *dir,
@@ -2583,6 +2680,9 @@ static const struct pid_entry tgid_base_stuff[] = {
REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations),
REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
#endif
+#ifdef CONFIG_CHECKPOINT_RESTORE
+ REG("timers", S_IRUGO, proc_timers_operations),
+#endif
};
static int proc_tgid_base_readdir(struct file * filp,
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 4b3b3ffb52f1..21e1a8f1659d 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -755,37 +755,8 @@ void pde_put(struct proc_dir_entry *pde)
free_proc_entry(pde);
}
-/*
- * Remove a /proc entry and free it if it's not currently in use.
- */
-void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
+static void entry_rundown(struct proc_dir_entry *de)
{
- struct proc_dir_entry **p;
- struct proc_dir_entry *de = NULL;
- const char *fn = name;
- unsigned int len;
-
- spin_lock(&proc_subdir_lock);
- if (__xlate_proc_name(name, &parent, &fn) != 0) {
- spin_unlock(&proc_subdir_lock);
- return;
- }
- len = strlen(fn);
-
- for (p = &parent->subdir; *p; p=&(*p)->next ) {
- if (proc_match(len, fn, *p)) {
- de = *p;
- *p = de->next;
- de->next = NULL;
- break;
- }
- }
- spin_unlock(&proc_subdir_lock);
- if (!de) {
- WARN(1, "name '%s'\n", name);
- return;
- }
-
spin_lock(&de->pde_unload_lock);
/*
* Stop accepting new callers into module. If you're
@@ -817,6 +788,40 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
spin_lock(&de->pde_unload_lock);
}
spin_unlock(&de->pde_unload_lock);
+}
+
+/*
+ * Remove a /proc entry and free it if it's not currently in use.
+ */
+void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
+{
+ struct proc_dir_entry **p;
+ struct proc_dir_entry *de = NULL;
+ const char *fn = name;
+ unsigned int len;
+
+ spin_lock(&proc_subdir_lock);
+ if (__xlate_proc_name(name, &parent, &fn) != 0) {
+ spin_unlock(&proc_subdir_lock);
+ return;
+ }
+ len = strlen(fn);
+
+ for (p = &parent->subdir; *p; p=&(*p)->next ) {
+ if (proc_match(len, fn, *p)) {
+ de = *p;
+ *p = de->next;
+ de->next = NULL;
+ break;
+ }
+ }
+ spin_unlock(&proc_subdir_lock);
+ if (!de) {
+ WARN(1, "name '%s'\n", name);
+ return;
+ }
+
+ entry_rundown(de);
if (S_ISDIR(de->mode))
parent->nlink--;
@@ -827,3 +832,57 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
pde_put(de);
}
EXPORT_SYMBOL(remove_proc_entry);
+
+int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
+{
+ struct proc_dir_entry **p;
+ struct proc_dir_entry *root = NULL, *de, *next;
+ const char *fn = name;
+ unsigned int len;
+
+ spin_lock(&proc_subdir_lock);
+ if (__xlate_proc_name(name, &parent, &fn) != 0) {
+ spin_unlock(&proc_subdir_lock);
+ return -ENOENT;
+ }
+ len = strlen(fn);
+
+ for (p = &parent->subdir; *p; p=&(*p)->next ) {
+ if (proc_match(len, fn, *p)) {
+ root = *p;
+ *p = root->next;
+ root->next = NULL;
+ break;
+ }
+ }
+ if (!root) {
+ spin_unlock(&proc_subdir_lock);
+ return -ENOENT;
+ }
+ de = root;
+ while (1) {
+ next = de->subdir;
+ if (next) {
+ de->subdir = next->next;
+ next->next = NULL;
+ de = next;
+ continue;
+ }
+ spin_unlock(&proc_subdir_lock);
+
+ entry_rundown(de);
+ next = de->parent;
+ if (S_ISDIR(de->mode))
+ next->nlink--;
+ de->nlink = 0;
+ if (de == root)
+ break;
+ pde_put(de);
+
+ spin_lock(&proc_subdir_lock);
+ de = next;
+ }
+ pde_put(root);
+ return 0;
+}
+EXPORT_SYMBOL(remove_proc_subtree);
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 85ff3a4598b3..75710357a517 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -30,24 +30,6 @@ extern int proc_net_init(void);
static inline int proc_net_init(void) { return 0; }
#endif
-struct vmalloc_info {
- unsigned long used;
- unsigned long largest_chunk;
-};
-
-#ifdef CONFIG_MMU
-#define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START)
-extern void get_vmalloc_info(struct vmalloc_info *vmi);
-#else
-
-#define VMALLOC_TOTAL 0UL
-#define get_vmalloc_info(vmi) \
-do { \
- (vmi)->used = 0; \
- (vmi)->largest_chunk = 0; \
-} while(0)
-#endif
-
extern int proc_tid_stat(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task);
extern int proc_tgid_stat(struct seq_file *m, struct pid_namespace *ns,
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index eda6f017f272..f6a13f489e30 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -15,6 +15,7 @@
#include <linux/capability.h>
#include <linux/elf.h>
#include <linux/elfcore.h>
+#include <linux/notifier.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>
#include <linux/printk.h>
@@ -564,7 +565,6 @@ static const struct file_operations proc_kcore_operations = {
.llseek = default_llseek,
};
-#ifdef CONFIG_MEMORY_HOTPLUG
/* just remember that we have to update kcore */
static int __meminit kcore_callback(struct notifier_block *self,
unsigned long action, void *arg)
@@ -578,8 +578,11 @@ static int __meminit kcore_callback(struct notifier_block *self,
}
return NOTIFY_OK;
}
-#endif
+static struct notifier_block kcore_callback_nb __meminitdata = {
+ .notifier_call = kcore_callback,
+ .priority = 0,
+};
static struct kcore_list kcore_vmalloc;
@@ -631,7 +634,7 @@ static int __init proc_kcore_init(void)
add_modules_range();
/* Store direct-map area from physical memory map */
kcore_update_ram();
- hotplug_memory_notifier(kcore_callback, 0);
+ register_hotmemory_notifier(&kcore_callback_nb);
return 0;
}
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 1efaaa19c4f3..5aa847a603c0 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -11,6 +11,7 @@
#include <linux/swap.h>
#include <linux/vmstat.h>
#include <linux/atomic.h>
+#include <linux/vmalloc.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include "internal.h"
diff --git a/fs/proc/mmu.c b/fs/proc/mmu.c
deleted file mode 100644
index 8ae221dfd010..000000000000
--- a/fs/proc/mmu.c
+++ /dev/null
@@ -1,60 +0,0 @@
-/* mmu.c: mmu memory info files
- *
- * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-#include <linux/spinlock.h>
-#include <linux/vmalloc.h>
-#include <linux/highmem.h>
-#include <asm/pgtable.h>
-#include "internal.h"
-
-void get_vmalloc_info(struct vmalloc_info *vmi)
-{
- struct vm_struct *vma;
- unsigned long free_area_size;
- unsigned long prev_end;
-
- vmi->used = 0;
-
- if (!vmlist) {
- vmi->largest_chunk = VMALLOC_TOTAL;
- }
- else {
- vmi->largest_chunk = 0;
-
- prev_end = VMALLOC_START;
-
- read_lock(&vmlist_lock);
-
- for (vma = vmlist; vma; vma = vma->next) {
- unsigned long addr = (unsigned long) vma->addr;
-
- /*
- * Some archs keep another range for modules in vmlist
- */
- if (addr < VMALLOC_START)
- continue;
- if (addr >= VMALLOC_END)
- break;
-
- vmi->used += vma->size;
-
- free_area_size = addr - prev_end;
- if (vmi->largest_chunk < free_area_size)
- vmi->largest_chunk = free_area_size;
-
- prev_end = vma->size + addr;
- }
-
- if (VMALLOC_END - prev_end > vmi->largest_chunk)
- vmi->largest_chunk = VMALLOC_END - prev_end;
-
- read_unlock(&vmlist_lock);
- }
-}
diff --git a/fs/read_write.c b/fs/read_write.c
index e6ddc8dceb96..7a648911246b 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -128,7 +128,7 @@ EXPORT_SYMBOL(generic_file_llseek_size);
*
* This is a generic implemenation of ->llseek useable for all normal local
* filesystems. It just updates the file offset to the value specified by
- * @offset and @whence under i_mutex.
+ * @offset and @whence.
*/
loff_t generic_file_llseek(struct file *file, loff_t offset, int whence)
{
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index e14512678c9b..e8e0e71b29d5 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -165,21 +165,8 @@ struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd)
if (unlikely(!sd))
return NULL;
- while (1) {
- int v, t;
-
- v = atomic_read(&sd->s_active);
- if (unlikely(v < 0))
- return NULL;
-
- t = atomic_cmpxchg(&sd->s_active, v, v + 1);
- if (likely(t == v))
- break;
- if (t < 0)
- return NULL;
-
- cpu_relax();
- }
+ if (!atomic_inc_unless_negative(&sd->s_active))
+ return NULL;
if (likely(!ignore_lockdep(sd)))
rwsem_acquire_read(&sd->dep_map, 0, 1, _RET_IP_);
@@ -281,6 +268,10 @@ void release_sysfs_dirent(struct sysfs_dirent * sd)
*/
parent_sd = sd->s_parent;
+ WARN(!(sd->s_flags & SYSFS_FLAG_REMOVED),
+ "sysfs: free using entry: %s/%s\n",
+ parent_sd ? parent_sd->s_name : "", sd->s_name);
+
if (sysfs_type(sd) == SYSFS_KOBJ_LINK)
sysfs_put(sd->s_symlink.target_sd);
if (sysfs_type(sd) & SYSFS_COPY_NAME)
@@ -399,7 +390,7 @@ struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type)
sd->s_name = name;
sd->s_mode = mode;
- sd->s_flags = type;
+ sd->s_flags = type | SYSFS_FLAG_REMOVED;
return sd;
@@ -479,6 +470,9 @@ int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME;
}
+ /* Mark the entry added into directory tree */
+ sd->s_flags &= ~SYSFS_FLAG_REMOVED;
+
return 0;
}
@@ -1012,6 +1006,7 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
enum kobj_ns_type type;
const void *ns;
ino_t ino;
+ loff_t off;
type = sysfs_ns_type(parent_sd);
ns = sysfs_info(dentry->d_sb)->ns[type];
@@ -1034,6 +1029,7 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
return 0;
}
mutex_lock(&sysfs_mutex);
+ off = filp->f_pos;
for (pos = sysfs_dir_pos(ns, parent_sd, filp->f_pos, pos);
pos;
pos = sysfs_dir_next_pos(ns, parent_sd, filp->f_pos, pos)) {
@@ -1045,19 +1041,24 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
len = strlen(name);
ino = pos->s_ino;
type = dt_type(pos);
- filp->f_pos = pos->s_hash;
+ off = filp->f_pos = pos->s_hash;
filp->private_data = sysfs_get(pos);
mutex_unlock(&sysfs_mutex);
- ret = filldir(dirent, name, len, filp->f_pos, ino, type);
+ ret = filldir(dirent, name, len, off, ino, type);
mutex_lock(&sysfs_mutex);
if (ret < 0)
break;
}
mutex_unlock(&sysfs_mutex);
- if ((filp->f_pos > 1) && !pos) { /* EOF */
- filp->f_pos = INT_MAX;
+
+ /* don't reference last entry if its refcount is dropped */
+ if (!pos) {
filp->private_data = NULL;
+
+ /* EOF and not changed as 0 or 1 in read/write path */
+ if (off == filp->f_pos && off > 1)
+ filp->f_pos = INT_MAX;
}
return 0;
}
diff --git a/fs/ufs/util.c b/fs/ufs/util.c
index 95425b59ce0a..b6c2f94e041e 100644
--- a/fs/ufs/util.c
+++ b/fs/ufs/util.c
@@ -26,8 +26,7 @@ struct ufs_buffer_head * _ubh_bread_ (struct ufs_sb_private_info * uspi,
count = size >> uspi->s_fshift;
if (count > UFS_MAXFRAG)
return NULL;
- ubh = (struct ufs_buffer_head *)
- kmalloc (sizeof (struct ufs_buffer_head), GFP_NOFS);
+ ubh = kmalloc (sizeof (struct ufs_buffer_head), GFP_NOFS);
if (!ubh)
return NULL;
ubh->fragment = fragment;