summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/bio-integrity.c5
-rw-r--r--fs/file.c56
-rw-r--r--fs/file_table.c1
-rw-r--r--fs/fs-writeback.c33
-rw-r--r--fs/hfsplus/catalog.c41
-rw-r--r--fs/hfsplus/hfsplus_fs.h1
-rw-r--r--fs/hfsplus/hfsplus_raw.h6
-rw-r--r--fs/hfsplus/inode.c9
-rw-r--r--fs/hfsplus/options.c2
-rw-r--r--fs/kernfs/mount.c8
-rw-r--r--fs/namei.c2
-rw-r--r--fs/nfs/delegation.c11
-rw-r--r--fs/nfs/nfs4filelayout.c10
-rw-r--r--fs/nfs/nfs4proc.c24
-rw-r--r--fs/nfs/nfs4state.c14
-rw-r--r--fs/notify/dnotify/dnotify.c2
-rw-r--r--fs/notify/fanotify/fanotify.c8
-rw-r--r--fs/notify/fanotify/fanotify_user.c13
-rw-r--r--fs/notify/fsnotify.c2
-rw-r--r--fs/notify/group.c8
-rw-r--r--fs/notify/inotify/inotify.h2
-rw-r--r--fs/notify/inotify/inotify_fsnotify.c3
-rw-r--r--fs/notify/inotify/inotify_user.c14
-rw-r--r--fs/notify/notification.c20
-rw-r--r--fs/ocfs2/file.c8
-rw-r--r--fs/ocfs2/quota_global.c27
-rw-r--r--fs/ocfs2/quota_local.c4
-rw-r--r--fs/open.c4
-rw-r--r--fs/proc/base.c1
-rw-r--r--fs/proc/page.c5
-rw-r--r--fs/quota/dquot.c14
-rw-r--r--fs/read_write.c40
-rw-r--r--fs/sync.c15
-rw-r--r--fs/sysfs/mount.c5
-rw-r--r--fs/udf/file.c14
-rw-r--r--fs/udf/inode.c1
-rw-r--r--fs/xfs/xfs_iops.c16
-rw-r--r--fs/xfs/xfs_log_cil.c19
-rw-r--r--fs/xfs/xfs_mount.c24
-rw-r--r--fs/xfs/xfs_sb.c10
-rw-r--r--fs/xfs/xfs_super.c2
41 files changed, 339 insertions, 165 deletions
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index 0129b78a6908..4f70f383132c 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -458,11 +458,10 @@ static int bio_integrity_verify(struct bio *bio)
struct blk_integrity_exchg bix;
struct bio_vec *bv;
sector_t sector = bio->bi_integrity->bip_iter.bi_sector;
- unsigned int sectors, total, ret;
+ unsigned int sectors, ret = 0;
void *prot_buf = bio->bi_integrity->bip_buf;
int i;
- ret = total = 0;
bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
bix.sector_size = bi->sector_size;
@@ -484,8 +483,6 @@ static int bio_integrity_verify(struct bio *bio)
sectors = bv->bv_len / bi->sector_size;
sector += sectors;
prot_buf += sectors * bi->tuple_size;
- total += sectors * bi->tuple_size;
- BUG_ON(total > bio->bi_integrity->bip_iter.bi_size);
kunmap_atomic(kaddr);
}
diff --git a/fs/file.c b/fs/file.c
index db25c2bdfe46..60a45e9f5323 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -683,35 +683,65 @@ EXPORT_SYMBOL(fget_raw);
* The fput_needed flag returned by fget_light should be passed to the
* corresponding fput_light.
*/
-struct file *__fget_light(unsigned int fd, fmode_t mask, int *fput_needed)
+static unsigned long __fget_light(unsigned int fd, fmode_t mask)
{
struct files_struct *files = current->files;
struct file *file;
- *fput_needed = 0;
if (atomic_read(&files->count) == 1) {
file = __fcheck_files(files, fd);
- if (file && (file->f_mode & mask))
- file = NULL;
+ if (!file || unlikely(file->f_mode & mask))
+ return 0;
+ return (unsigned long)file;
} else {
file = __fget(fd, mask);
- if (file)
- *fput_needed = 1;
+ if (!file)
+ return 0;
+ return FDPUT_FPUT | (unsigned long)file;
}
-
- return file;
}
-struct file *fget_light(unsigned int fd, int *fput_needed)
+unsigned long __fdget(unsigned int fd)
{
- return __fget_light(fd, FMODE_PATH, fput_needed);
+ return __fget_light(fd, FMODE_PATH);
}
-EXPORT_SYMBOL(fget_light);
+EXPORT_SYMBOL(__fdget);
-struct file *fget_raw_light(unsigned int fd, int *fput_needed)
+unsigned long __fdget_raw(unsigned int fd)
{
- return __fget_light(fd, 0, fput_needed);
+ return __fget_light(fd, 0);
+}
+
+unsigned long __fdget_pos(unsigned int fd)
+{
+ struct files_struct *files = current->files;
+ struct file *file;
+ unsigned long v;
+
+ if (atomic_read(&files->count) == 1) {
+ file = __fcheck_files(files, fd);
+ v = 0;
+ } else {
+ file = __fget(fd, 0);
+ v = FDPUT_FPUT;
+ }
+ if (!file)
+ return 0;
+
+ if (file->f_mode & FMODE_ATOMIC_POS) {
+ if (file_count(file) > 1) {
+ v |= FDPUT_POS_UNLOCK;
+ mutex_lock(&file->f_pos_lock);
+ }
+ }
+ return v | (unsigned long)file;
}
+/*
+ * We only lock f_pos if we have threads or if the file might be
+ * shared with another process. In both cases we'll have an elevated
+ * file count (done either by fdget() or by fork()).
+ */
+
void set_close_on_exec(unsigned int fd, int flag)
{
struct files_struct *files = current->files;
diff --git a/fs/file_table.c b/fs/file_table.c
index 5fff9030be34..5b24008ea4f6 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -135,6 +135,7 @@ struct file *get_empty_filp(void)
atomic_long_set(&f->f_count, 1);
rwlock_init(&f->f_owner.lock);
spin_lock_init(&f->f_lock);
+ mutex_init(&f->f_pos_lock);
eventpoll_init_file(f);
/* f->f_version: 0 */
return f;
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e0259a163f98..d754e3cf99a8 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -40,18 +40,13 @@
struct wb_writeback_work {
long nr_pages;
struct super_block *sb;
- /*
- * Write only inodes dirtied before this time. Don't forget to set
- * older_than_this_is_set when you set this.
- */
- unsigned long older_than_this;
+ unsigned long *older_than_this;
enum writeback_sync_modes sync_mode;
unsigned int tagged_writepages:1;
unsigned int for_kupdate:1;
unsigned int range_cyclic:1;
unsigned int for_background:1;
unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */
- unsigned int older_than_this_is_set:1;
enum wb_reason reason; /* why was writeback initiated? */
struct list_head list; /* pending work list */
@@ -252,10 +247,10 @@ static int move_expired_inodes(struct list_head *delaying_queue,
int do_sb_sort = 0;
int moved = 0;
- WARN_ON_ONCE(!work->older_than_this_is_set);
while (!list_empty(delaying_queue)) {
inode = wb_inode(delaying_queue->prev);
- if (inode_dirtied_after(inode, work->older_than_this))
+ if (work->older_than_this &&
+ inode_dirtied_after(inode, *work->older_than_this))
break;
list_move(&inode->i_wb_list, &tmp);
moved++;
@@ -742,8 +737,6 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
.sync_mode = WB_SYNC_NONE,
.range_cyclic = 1,
.reason = reason,
- .older_than_this = jiffies,
- .older_than_this_is_set = 1,
};
spin_lock(&wb->list_lock);
@@ -802,13 +795,12 @@ static long wb_writeback(struct bdi_writeback *wb,
{
unsigned long wb_start = jiffies;
long nr_pages = work->nr_pages;
+ unsigned long oldest_jif;
struct inode *inode;
long progress;
- if (!work->older_than_this_is_set) {
- work->older_than_this = jiffies;
- work->older_than_this_is_set = 1;
- }
+ oldest_jif = jiffies;
+ work->older_than_this = &oldest_jif;
spin_lock(&wb->list_lock);
for (;;) {
@@ -842,10 +834,10 @@ static long wb_writeback(struct bdi_writeback *wb,
* safe.
*/
if (work->for_kupdate) {
- work->older_than_this = jiffies -
+ oldest_jif = jiffies -
msecs_to_jiffies(dirty_expire_interval * 10);
} else if (work->for_background)
- work->older_than_this = jiffies;
+ oldest_jif = jiffies;
trace_writeback_start(wb->bdi, work);
if (list_empty(&wb->b_io))
@@ -1357,21 +1349,18 @@ EXPORT_SYMBOL(try_to_writeback_inodes_sb);
/**
* sync_inodes_sb - sync sb inode pages
- * @sb: the superblock
- * @older_than_this: timestamp
+ * @sb: the superblock
*
* This function writes and waits on any dirty inode belonging to this
- * superblock that has been dirtied before given timestamp.
+ * super_block.
*/
-void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this)
+void sync_inodes_sb(struct super_block *sb)
{
DECLARE_COMPLETION_ONSTACK(done);
struct wb_writeback_work work = {
.sb = sb,
.sync_mode = WB_SYNC_ALL,
.nr_pages = LONG_MAX,
- .older_than_this = older_than_this,
- .older_than_this_is_set = 1,
.range_cyclic = 0,
.done = &done,
.reason = WB_REASON_SYNC,
diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c
index 968ce411db53..32602c667b4a 100644
--- a/fs/hfsplus/catalog.c
+++ b/fs/hfsplus/catalog.c
@@ -103,6 +103,8 @@ static int hfsplus_cat_build_record(hfsplus_cat_entry *entry,
folder = &entry->folder;
memset(folder, 0, sizeof(*folder));
folder->type = cpu_to_be16(HFSPLUS_FOLDER);
+ if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags))
+ folder->flags |= cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT);
folder->id = cpu_to_be32(inode->i_ino);
HFSPLUS_I(inode)->create_date =
folder->create_date =
@@ -203,6 +205,36 @@ int hfsplus_find_cat(struct super_block *sb, u32 cnid,
return hfs_brec_find(fd, hfs_find_rec_by_key);
}
+static void hfsplus_subfolders_inc(struct inode *dir)
+{
+ struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
+
+ if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) {
+ /*
+ * Increment subfolder count. Note, the value is only meaningful
+ * for folders with HFSPLUS_HAS_FOLDER_COUNT flag set.
+ */
+ HFSPLUS_I(dir)->subfolders++;
+ }
+}
+
+static void hfsplus_subfolders_dec(struct inode *dir)
+{
+ struct hfsplus_sb_info *sbi = HFSPLUS_SB(dir->i_sb);
+
+ if (test_bit(HFSPLUS_SB_HFSX, &sbi->flags)) {
+ /*
+ * Decrement subfolder count. Note, the value is only meaningful
+ * for folders with HFSPLUS_HAS_FOLDER_COUNT flag set.
+ *
+ * Check for zero. Some subfolders may have been created
+ * by an implementation ignorant of this counter.
+ */
+ if (HFSPLUS_I(dir)->subfolders)
+ HFSPLUS_I(dir)->subfolders--;
+ }
+}
+
int hfsplus_create_cat(u32 cnid, struct inode *dir,
struct qstr *str, struct inode *inode)
{
@@ -247,6 +279,8 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir,
goto err1;
dir->i_size++;
+ if (S_ISDIR(inode->i_mode))
+ hfsplus_subfolders_inc(dir);
dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY);
@@ -336,6 +370,8 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
goto out;
dir->i_size--;
+ if (type == HFSPLUS_FOLDER)
+ hfsplus_subfolders_dec(dir);
dir->i_mtime = dir->i_ctime = CURRENT_TIME_SEC;
hfsplus_mark_inode_dirty(dir, HFSPLUS_I_CAT_DIRTY);
@@ -380,6 +416,7 @@ int hfsplus_rename_cat(u32 cnid,
hfs_bnode_read(src_fd.bnode, &entry, src_fd.entryoffset,
src_fd.entrylength);
+ type = be16_to_cpu(entry.type);
/* create new dir entry with the data from the old entry */
hfsplus_cat_build_key(sb, dst_fd.search_key, dst_dir->i_ino, dst_name);
@@ -394,6 +431,8 @@ int hfsplus_rename_cat(u32 cnid,
if (err)
goto out;
dst_dir->i_size++;
+ if (type == HFSPLUS_FOLDER)
+ hfsplus_subfolders_inc(dst_dir);
dst_dir->i_mtime = dst_dir->i_ctime = CURRENT_TIME_SEC;
/* finally remove the old entry */
@@ -405,6 +444,8 @@ int hfsplus_rename_cat(u32 cnid,
if (err)
goto out;
src_dir->i_size--;
+ if (type == HFSPLUS_FOLDER)
+ hfsplus_subfolders_dec(src_dir);
src_dir->i_mtime = src_dir->i_ctime = CURRENT_TIME_SEC;
/* remove old thread entry */
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 08846425b67f..62d571eb69ba 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -242,6 +242,7 @@ struct hfsplus_inode_info {
*/
sector_t fs_blocks;
u8 userflags; /* BSD user file flags */
+ u32 subfolders; /* Subfolder count (HFSX only) */
struct list_head open_dir_list;
loff_t phys_size;
diff --git a/fs/hfsplus/hfsplus_raw.h b/fs/hfsplus/hfsplus_raw.h
index 8ffb3a8ffe75..5a126828d85e 100644
--- a/fs/hfsplus/hfsplus_raw.h
+++ b/fs/hfsplus/hfsplus_raw.h
@@ -261,7 +261,7 @@ struct hfsplus_cat_folder {
struct DInfo user_info;
struct DXInfo finder_info;
__be32 text_encoding;
- u32 reserved;
+ __be32 subfolders; /* Subfolder count in HFSX. Reserved in HFS+. */
} __packed;
/* HFS file info (stolen from hfs.h) */
@@ -301,11 +301,13 @@ struct hfsplus_cat_file {
struct hfsplus_fork_raw rsrc_fork;
} __packed;
-/* File attribute bits */
+/* File and folder flag bits */
#define HFSPLUS_FILE_LOCKED 0x0001
#define HFSPLUS_FILE_THREAD_EXISTS 0x0002
#define HFSPLUS_XATTR_EXISTS 0x0004
#define HFSPLUS_ACL_EXISTS 0x0008
+#define HFSPLUS_HAS_FOLDER_COUNT 0x0010 /* Folder has subfolder count
+ * (HFSX only) */
/* HFS+ catalog thread (part of a cat_entry) */
struct hfsplus_cat_thread {
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index fa929f325f87..a4f45bd88a63 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -375,6 +375,7 @@ struct inode *hfsplus_new_inode(struct super_block *sb, umode_t mode)
hip->extent_state = 0;
hip->flags = 0;
hip->userflags = 0;
+ hip->subfolders = 0;
memset(hip->first_extents, 0, sizeof(hfsplus_extent_rec));
memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec));
hip->alloc_blocks = 0;
@@ -494,6 +495,10 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd)
inode->i_ctime = hfsp_mt2ut(folder->attribute_mod_date);
HFSPLUS_I(inode)->create_date = folder->create_date;
HFSPLUS_I(inode)->fs_blocks = 0;
+ if (folder->flags & cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT)) {
+ HFSPLUS_I(inode)->subfolders =
+ be32_to_cpu(folder->subfolders);
+ }
inode->i_op = &hfsplus_dir_inode_operations;
inode->i_fop = &hfsplus_dir_operations;
} else if (type == HFSPLUS_FILE) {
@@ -566,6 +571,10 @@ int hfsplus_cat_write_inode(struct inode *inode)
folder->content_mod_date = hfsp_ut2mt(inode->i_mtime);
folder->attribute_mod_date = hfsp_ut2mt(inode->i_ctime);
folder->valence = cpu_to_be32(inode->i_size - 2);
+ if (folder->flags & cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT)) {
+ folder->subfolders =
+ cpu_to_be32(HFSPLUS_I(inode)->subfolders);
+ }
hfs_bnode_write(fd.bnode, &entry, fd.entryoffset,
sizeof(struct hfsplus_cat_folder));
} else if (HFSPLUS_IS_RSRC(inode)) {
diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c
index 968eab5bc1f5..68537e8b7a09 100644
--- a/fs/hfsplus/options.c
+++ b/fs/hfsplus/options.c
@@ -75,7 +75,7 @@ int hfsplus_parse_options_remount(char *input, int *force)
int token;
if (!input)
- return 0;
+ return 1;
while ((p = strsep(&input, ",")) != NULL) {
if (!*p)
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 0d6ce895a9ee..0f4152defe7b 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -94,6 +94,7 @@ const void *kernfs_super_ns(struct super_block *sb)
* @fs_type: file_system_type of the fs being mounted
* @flags: mount flags specified for the mount
* @root: kernfs_root of the hierarchy being mounted
+ * @new_sb_created: tell the caller if we allocated a new superblock
* @ns: optional namespace tag of the mount
*
* This is to be called from each kernfs user's file_system_type->mount()
@@ -104,7 +105,8 @@ const void *kernfs_super_ns(struct super_block *sb)
* The return value can be passed to the vfs layer verbatim.
*/
struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
- struct kernfs_root *root, const void *ns)
+ struct kernfs_root *root, bool *new_sb_created,
+ const void *ns)
{
struct super_block *sb;
struct kernfs_super_info *info;
@@ -122,6 +124,10 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
kfree(info);
if (IS_ERR(sb))
return ERR_CAST(sb);
+
+ if (new_sb_created)
+ *new_sb_created = !sb->s_root;
+
if (!sb->s_root) {
error = kernfs_fill_super(sb);
if (error) {
diff --git a/fs/namei.c b/fs/namei.c
index 385f7817bfcc..2f730ef9b4b3 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1884,7 +1884,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
nd->path = f.file->f_path;
if (flags & LOOKUP_RCU) {
- if (f.need_put)
+ if (f.flags & FDPUT_FPUT)
*fp = f.file;
nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
rcu_read_lock();
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index ef792f29f831..5d8ccecf5f5c 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -659,16 +659,19 @@ int nfs_async_inode_return_delegation(struct inode *inode,
rcu_read_lock();
delegation = rcu_dereference(NFS_I(inode)->delegation);
+ if (delegation == NULL)
+ goto out_enoent;
- if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) {
- rcu_read_unlock();
- return -ENOENT;
- }
+ if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid))
+ goto out_enoent;
nfs_mark_return_delegation(server, delegation);
rcu_read_unlock();
nfs_delegation_run_state_manager(clp);
return 0;
+out_enoent:
+ rcu_read_unlock();
+ return -ENOENT;
}
static struct inode *
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 12c8132ad408..b9a35c05b60f 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -324,8 +324,9 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data)
&rdata->res.seq_res,
task))
return;
- nfs4_set_rw_stateid(&rdata->args.stateid, rdata->args.context,
- rdata->args.lock_context, FMODE_READ);
+ if (nfs4_set_rw_stateid(&rdata->args.stateid, rdata->args.context,
+ rdata->args.lock_context, FMODE_READ) == -EIO)
+ rpc_exit(task, -EIO); /* lost lock, terminate I/O */
}
static void filelayout_read_call_done(struct rpc_task *task, void *data)
@@ -435,8 +436,9 @@ static void filelayout_write_prepare(struct rpc_task *task, void *data)
&wdata->res.seq_res,
task))
return;
- nfs4_set_rw_stateid(&wdata->args.stateid, wdata->args.context,
- wdata->args.lock_context, FMODE_WRITE);
+ if (nfs4_set_rw_stateid(&wdata->args.stateid, wdata->args.context,
+ wdata->args.lock_context, FMODE_WRITE) == -EIO)
+ rpc_exit(task, -EIO); /* lost lock, terminate I/O */
}
static void filelayout_write_call_done(struct rpc_task *task, void *data)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 2da6a698b8f7..450bfedbe2f4 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2398,13 +2398,16 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
if (nfs4_copy_delegation_stateid(&arg.stateid, inode, fmode)) {
/* Use that stateid */
- } else if (truncate && state != NULL && nfs4_valid_open_stateid(state)) {
+ } else if (truncate && state != NULL) {
struct nfs_lockowner lockowner = {
.l_owner = current->files,
.l_pid = current->tgid,
};
- nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
- &lockowner);
+ if (!nfs4_valid_open_stateid(state))
+ return -EBADF;
+ if (nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
+ &lockowner) == -EIO)
+ return -EBADF;
} else
nfs4_stateid_copy(&arg.stateid, &zero_stateid);
@@ -4011,8 +4014,9 @@ static bool nfs4_stateid_is_current(nfs4_stateid *stateid,
{
nfs4_stateid current_stateid;
- if (nfs4_set_rw_stateid(&current_stateid, ctx, l_ctx, fmode))
- return false;
+ /* If the current stateid represents a lost lock, then exit */
+ if (nfs4_set_rw_stateid(&current_stateid, ctx, l_ctx, fmode) == -EIO)
+ return true;
return nfs4_stateid_match(stateid, &current_stateid);
}
@@ -5828,8 +5832,7 @@ struct nfs_release_lockowner_data {
struct nfs4_lock_state *lsp;
struct nfs_server *server;
struct nfs_release_lockowner_args args;
- struct nfs4_sequence_args seq_args;
- struct nfs4_sequence_res seq_res;
+ struct nfs_release_lockowner_res res;
unsigned long timestamp;
};
@@ -5837,7 +5840,7 @@ static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata
{
struct nfs_release_lockowner_data *data = calldata;
nfs40_setup_sequence(data->server,
- &data->seq_args, &data->seq_res, task);
+ &data->args.seq_args, &data->res.seq_res, task);
data->timestamp = jiffies;
}
@@ -5846,7 +5849,7 @@ static void nfs4_release_lockowner_done(struct rpc_task *task, void *calldata)
struct nfs_release_lockowner_data *data = calldata;
struct nfs_server *server = data->server;
- nfs40_sequence_done(task, &data->seq_res);
+ nfs40_sequence_done(task, &data->res.seq_res);
switch (task->tk_status) {
case 0:
@@ -5887,7 +5890,6 @@ static int nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_st
data = kmalloc(sizeof(*data), GFP_NOFS);
if (!data)
return -ENOMEM;
- nfs4_init_sequence(&data->seq_args, &data->seq_res, 0);
data->lsp = lsp;
data->server = server;
data->args.lock_owner.clientid = server->nfs_client->cl_clientid;
@@ -5895,6 +5897,8 @@ static int nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_st
data->args.lock_owner.s_dev = server->s_dev;
msg.rpc_argp = &data->args;
+ msg.rpc_resp = &data->res;
+ nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0);
rpc_call_async(server->client, &msg, 0, &nfs4_release_lockowner_ops, data);
return 0;
}
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index e1a47217c05e..0deb32105ccf 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -974,9 +974,6 @@ static int nfs4_copy_lock_stateid(nfs4_stateid *dst,
else if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) {
nfs4_stateid_copy(dst, &lsp->ls_stateid);
ret = 0;
- smp_rmb();
- if (!list_empty(&lsp->ls_seqid.list))
- ret = -EWOULDBLOCK;
}
spin_unlock(&state->state_lock);
nfs4_put_lock_state(lsp);
@@ -984,10 +981,9 @@ out:
return ret;
}
-static int nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
+static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
{
const nfs4_stateid *src;
- int ret;
int seq;
do {
@@ -996,12 +992,7 @@ static int nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
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;
}
/*
@@ -1026,7 +1017,8 @@ int nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state,
* choose to use.
*/
goto out;
- ret = nfs4_copy_open_stateid(dst, state);
+ nfs4_copy_open_stateid(dst, state);
+ ret = 0;
out:
if (nfs_server_capable(state->inode, NFS_CAP_STATEID_NFSV41))
dst->seqid = 0;
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 0b9ff4395e6a..abc8cbcfe90e 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -86,7 +86,7 @@ static int dnotify_handle_event(struct fsnotify_group *group,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, void *data, int data_type,
- const unsigned char *file_name)
+ const unsigned char *file_name, u32 cookie)
{
struct dnotify_mark *dn_mark;
struct dnotify_struct *dn;
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 0e792f5e3147..dc638f786d5c 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -147,7 +147,7 @@ static int fanotify_handle_event(struct fsnotify_group *group,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *fanotify_mark,
u32 mask, void *data, int data_type,
- const unsigned char *file_name)
+ const unsigned char *file_name, u32 cookie)
{
int ret = 0;
struct fanotify_event_info *event;
@@ -192,10 +192,12 @@ static int fanotify_handle_event(struct fsnotify_group *group,
ret = fsnotify_add_notify_event(group, fsn_event, fanotify_merge);
if (ret) {
- BUG_ON(mask & FAN_ALL_PERM_EVENTS);
+ /* Permission events shouldn't be merged */
+ BUG_ON(ret == 1 && mask & FAN_ALL_PERM_EVENTS);
/* Our event wasn't used in the end. Free it. */
fsnotify_destroy_event(group, fsn_event);
- ret = 0;
+
+ return 0;
}
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index b6175fa11bf8..287a22c04149 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -698,6 +698,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
struct fsnotify_group *group;
int f_flags, fd;
struct user_struct *user;
+ struct fanotify_event_info *oevent;
pr_debug("%s: flags=%d event_f_flags=%d\n",
__func__, flags, event_f_flags);
@@ -730,8 +731,20 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
group->fanotify_data.user = user;
atomic_inc(&user->fanotify_listeners);
+ oevent = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL);
+ if (unlikely(!oevent)) {
+ fd = -ENOMEM;
+ goto out_destroy_group;
+ }
+ group->overflow_event = &oevent->fse;
+ fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW);
+ oevent->tgid = get_pid(task_tgid(current));
+ oevent->path.mnt = NULL;
+ oevent->path.dentry = NULL;
+
group->fanotify_data.f_flags = event_f_flags;
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+ oevent->response = 0;
mutex_init(&group->fanotify_data.access_mutex);
init_waitqueue_head(&group->fanotify_data.access_waitq);
INIT_LIST_HEAD(&group->fanotify_data.access_list);
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 1d4e1ea2f37c..9d3e9c50066a 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -179,7 +179,7 @@ static int send_to_group(struct inode *to_tell,
return group->ops->handle_event(group, to_tell, inode_mark,
vfsmount_mark, mask, data, data_is,
- file_name);
+ file_name, cookie);
}
/*
diff --git a/fs/notify/group.c b/fs/notify/group.c
index ee674fe2cec7..ad1995980456 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -55,6 +55,13 @@ void fsnotify_destroy_group(struct fsnotify_group *group)
/* clear the notification queue of all events */
fsnotify_flush_notify(group);
+ /*
+ * Destroy overflow event (we cannot use fsnotify_destroy_event() as
+ * that deliberately ignores overflow events.
+ */
+ if (group->overflow_event)
+ group->ops->free_event(group->overflow_event);
+
fsnotify_put_group(group);
}
@@ -99,7 +106,6 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops)
INIT_LIST_HEAD(&group->marks_list);
group->ops = ops;
- fsnotify_init_event(&group->overflow_event, NULL, FS_Q_OVERFLOW);
return group;
}
diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h
index 485eef3f4407..ed855ef6f077 100644
--- a/fs/notify/inotify/inotify.h
+++ b/fs/notify/inotify/inotify.h
@@ -27,6 +27,6 @@ extern int inotify_handle_event(struct fsnotify_group *group,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, void *data, int data_type,
- const unsigned char *file_name);
+ const unsigned char *file_name, u32 cookie);
extern const struct fsnotify_ops inotify_fsnotify_ops;
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index d5ee56348bb8..43ab1e1a07a2 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -67,7 +67,7 @@ int inotify_handle_event(struct fsnotify_group *group,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, void *data, int data_type,
- const unsigned char *file_name)
+ const unsigned char *file_name, u32 cookie)
{
struct inotify_inode_mark *i_mark;
struct inotify_event_info *event;
@@ -103,6 +103,7 @@ int inotify_handle_event(struct fsnotify_group *group,
fsn_event = &event->fse;
fsnotify_init_event(fsn_event, inode, mask);
event->wd = i_mark->wd;
+ event->sync_cookie = cookie;
event->name_len = len;
if (len)
strcpy(event->name, file_name);
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 497395c8274b..78a2ca3966c3 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -495,7 +495,7 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
/* Queue ignore event for the watch */
inotify_handle_event(group, NULL, fsn_mark, NULL, FS_IN_IGNORED,
- NULL, FSNOTIFY_EVENT_NONE, NULL);
+ NULL, FSNOTIFY_EVENT_NONE, NULL, 0);
i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
/* remove this mark from the idr */
@@ -633,11 +633,23 @@ static int inotify_update_watch(struct fsnotify_group *group, struct inode *inod
static struct fsnotify_group *inotify_new_group(unsigned int max_events)
{
struct fsnotify_group *group;
+ struct inotify_event_info *oevent;
group = fsnotify_alloc_group(&inotify_fsnotify_ops);
if (IS_ERR(group))
return group;
+ oevent = kmalloc(sizeof(struct inotify_event_info), GFP_KERNEL);
+ if (unlikely(!oevent)) {
+ fsnotify_destroy_group(group);
+ return ERR_PTR(-ENOMEM);
+ }
+ group->overflow_event = &oevent->fse;
+ fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW);
+ oevent->wd = -1;
+ oevent->sync_cookie = 0;
+ oevent->name_len = 0;
+
group->max_events = max_events;
spin_lock_init(&group->inotify_data.idr_lock);
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index 18b3c4427dca..1e58402171a5 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -80,7 +80,8 @@ void fsnotify_destroy_event(struct fsnotify_group *group,
/*
* Add an event to the group notification queue. The group can later pull this
* event off the queue to deal with. The function returns 0 if the event was
- * added to the queue, 1 if the event was merged with some other queued event.
+ * added to the queue, 1 if the event was merged with some other queued event,
+ * 2 if the queue of events has overflown.
*/
int fsnotify_add_notify_event(struct fsnotify_group *group,
struct fsnotify_event *event,
@@ -95,10 +96,14 @@ int fsnotify_add_notify_event(struct fsnotify_group *group,
mutex_lock(&group->notification_mutex);
if (group->q_len >= group->max_events) {
+ ret = 2;
/* Queue overflow event only if it isn't already queued */
- if (list_empty(&group->overflow_event.list))
- event = &group->overflow_event;
- ret = 1;
+ if (!list_empty(&group->overflow_event->list)) {
+ mutex_unlock(&group->notification_mutex);
+ return ret;
+ }
+ event = group->overflow_event;
+ goto queue;
}
if (!list_empty(list) && merge) {
@@ -109,6 +114,7 @@ int fsnotify_add_notify_event(struct fsnotify_group *group,
}
}
+queue:
group->q_len++;
list_add_tail(&event->list, list);
mutex_unlock(&group->notification_mutex);
@@ -132,7 +138,11 @@ struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group *group
event = list_first_entry(&group->notification_list,
struct fsnotify_event, list);
- list_del(&event->list);
+ /*
+ * We need to init list head for the case of overflow event so that
+ * check in fsnotify_add_notify_events() works
+ */
+ list_del_init(&event->list);
group->q_len--;
return event;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 8450262bcf2a..51632c40e896 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2393,8 +2393,8 @@ out_dio:
if (((file->f_flags & O_DSYNC) && !direct_io) || IS_SYNC(inode) ||
((file->f_flags & O_DIRECT) && !direct_io)) {
- ret = filemap_fdatawrite_range(file->f_mapping, pos,
- pos + count - 1);
+ ret = filemap_fdatawrite_range(file->f_mapping, *ppos,
+ *ppos + count - 1);
if (ret < 0)
written = ret;
@@ -2407,8 +2407,8 @@ out_dio:
}
if (!ret)
- ret = filemap_fdatawait_range(file->f_mapping, pos,
- pos + count - 1);
+ ret = filemap_fdatawait_range(file->f_mapping, *ppos,
+ *ppos + count - 1);
}
/*
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index aaa50611ec66..d7b5108789e2 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -717,6 +717,12 @@ static int ocfs2_release_dquot(struct dquot *dquot)
*/
if (status < 0)
mlog_errno(status);
+ /*
+ * Clear dq_off so that we search for the structure in quota file next
+ * time we acquire it. The structure might be deleted and reallocated
+ * elsewhere by another node while our dquot structure is on freelist.
+ */
+ dquot->dq_off = 0;
clear_bit(DQ_ACTIVE_B, &dquot->dq_flags);
out_trans:
ocfs2_commit_trans(osb, handle);
@@ -756,16 +762,17 @@ static int ocfs2_acquire_dquot(struct dquot *dquot)
status = ocfs2_lock_global_qf(info, 1);
if (status < 0)
goto out;
- if (!test_bit(DQ_READ_B, &dquot->dq_flags)) {
- status = ocfs2_qinfo_lock(info, 0);
- if (status < 0)
- goto out_dq;
- status = qtree_read_dquot(&info->dqi_gi, dquot);
- ocfs2_qinfo_unlock(info, 0);
- if (status < 0)
- goto out_dq;
- }
- set_bit(DQ_READ_B, &dquot->dq_flags);
+ status = ocfs2_qinfo_lock(info, 0);
+ if (status < 0)
+ goto out_dq;
+ /*
+ * We always want to read dquot structure from disk because we don't
+ * know what happened with it while it was on freelist.
+ */
+ status = qtree_read_dquot(&info->dqi_gi, dquot);
+ ocfs2_qinfo_unlock(info, 0);
+ if (status < 0)
+ goto out_dq;
OCFS2_DQUOT(dquot)->dq_use_count++;
OCFS2_DQUOT(dquot)->dq_origspace = dquot->dq_dqb.dqb_curspace;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 2e4344be3b96..2001862bf2b1 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -1303,10 +1303,6 @@ int ocfs2_local_release_dquot(handle_t *handle, struct dquot *dquot)
ocfs2_journal_dirty(handle, od->dq_chunk->qc_headerbh);
out:
- /* Clear the read bit so that next time someone uses this
- * dquot he reads fresh info from disk and allocates local
- * dquot structure */
- clear_bit(DQ_READ_B, &dquot->dq_flags);
return status;
}
diff --git a/fs/open.c b/fs/open.c
index 4b3e1edf2fe4..b9ed8b25c108 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -705,6 +705,10 @@ static int do_dentry_open(struct file *f,
return 0;
}
+ /* POSIX.1-2008/SUSv4 Section XSI 2.9.7 */
+ if (S_ISREG(inode->i_mode))
+ f->f_mode |= FMODE_ATOMIC_POS;
+
f->f_op = fops_get(inode->i_fop);
if (unlikely(WARN_ON(!f->f_op))) {
error = -ENODEV;
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 51507065263b..b9760628e1fd 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1824,6 +1824,7 @@ static int proc_map_files_get_link(struct dentry *dentry, struct path *path)
if (rc)
goto out_mmput;
+ rc = -ENOENT;
down_read(&mm->mmap_sem);
vma = find_exact_vma(mm, vm_start, vm_end);
if (vma && vma->vm_file) {
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 02174a610315..e647c55275d9 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -121,9 +121,8 @@ u64 stable_page_flags(struct page *page)
* just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon
* to make sure a given page is a thp, not a non-huge compound page.
*/
- else if (PageTransCompound(page) &&
- (PageLRU(compound_trans_head(page)) ||
- PageAnon(compound_trans_head(page))))
+ else if (PageTransCompound(page) && (PageLRU(compound_head(page)) ||
+ PageAnon(compound_head(page))))
u |= 1 << KPF_THP;
/*
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 831d49a4111f..cfc8dcc16043 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -581,9 +581,17 @@ int dquot_scan_active(struct super_block *sb,
dqstats_inc(DQST_LOOKUPS);
dqput(old_dquot);
old_dquot = dquot;
- ret = fn(dquot, priv);
- if (ret < 0)
- goto out;
+ /*
+ * ->release_dquot() can be racing with us. Our reference
+ * protects us from new calls to it so just wait for any
+ * outstanding call and recheck the DQ_ACTIVE_B after that.
+ */
+ wait_on_dquot(dquot);
+ if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
+ ret = fn(dquot, priv);
+ if (ret < 0)
+ goto out;
+ }
spin_lock(&dq_list_lock);
/* We are safe to continue now because our dquot could not
* be moved out of the inuse list while we hold the reference */
diff --git a/fs/read_write.c b/fs/read_write.c
index edc5746a902a..54e19b9392dc 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -264,10 +264,22 @@ loff_t vfs_llseek(struct file *file, loff_t offset, int whence)
}
EXPORT_SYMBOL(vfs_llseek);
+static inline struct fd fdget_pos(int fd)
+{
+ return __to_fd(__fdget_pos(fd));
+}
+
+static inline void fdput_pos(struct fd f)
+{
+ if (f.flags & FDPUT_POS_UNLOCK)
+ mutex_unlock(&f.file->f_pos_lock);
+ fdput(f);
+}
+
SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence)
{
off_t retval;
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
if (!f.file)
return -EBADF;
@@ -278,7 +290,7 @@ SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence)
if (res != (loff_t)retval)
retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */
}
- fdput(f);
+ fdput_pos(f);
return retval;
}
@@ -498,7 +510,7 @@ static inline void file_pos_write(struct file *file, loff_t pos)
SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
@@ -506,7 +518,7 @@ SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
ret = vfs_read(f.file, buf, count, &pos);
if (ret >= 0)
file_pos_write(f.file, pos);
- fdput(f);
+ fdput_pos(f);
}
return ret;
}
@@ -514,7 +526,7 @@ SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count)
SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
size_t, count)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
@@ -522,7 +534,7 @@ SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf,
ret = vfs_write(f.file, buf, count, &pos);
if (ret >= 0)
file_pos_write(f.file, pos);
- fdput(f);
+ fdput_pos(f);
}
return ret;
@@ -797,7 +809,7 @@ EXPORT_SYMBOL(vfs_writev);
SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
unsigned long, vlen)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
@@ -805,7 +817,7 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
ret = vfs_readv(f.file, vec, vlen, &pos);
if (ret >= 0)
file_pos_write(f.file, pos);
- fdput(f);
+ fdput_pos(f);
}
if (ret > 0)
@@ -817,7 +829,7 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
unsigned long, vlen)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
@@ -825,7 +837,7 @@ SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
ret = vfs_writev(f.file, vec, vlen, &pos);
if (ret >= 0)
file_pos_write(f.file, pos);
- fdput(f);
+ fdput_pos(f);
}
if (ret > 0)
@@ -968,7 +980,7 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
const struct compat_iovec __user *,vec,
compat_ulong_t, vlen)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
ssize_t ret;
loff_t pos;
@@ -978,7 +990,7 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
ret = compat_readv(f.file, vec, vlen, &pos);
if (ret >= 0)
f.file->f_pos = pos;
- fdput(f);
+ fdput_pos(f);
return ret;
}
@@ -1035,7 +1047,7 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
const struct compat_iovec __user *, vec,
compat_ulong_t, vlen)
{
- struct fd f = fdget(fd);
+ struct fd f = fdget_pos(fd);
ssize_t ret;
loff_t pos;
@@ -1045,7 +1057,7 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
ret = compat_writev(f.file, vec, vlen, &pos);
if (ret >= 0)
f.file->f_pos = pos;
- fdput(f);
+ fdput_pos(f);
return ret;
}
diff --git a/fs/sync.c b/fs/sync.c
index e8ba024a055b..b28d1dd10e8b 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -27,11 +27,10 @@
* wait == 1 case since in that case write_inode() functions do
* sync_dirty_buffer() and thus effectively write one block at a time.
*/
-static int __sync_filesystem(struct super_block *sb, int wait,
- unsigned long start)
+static int __sync_filesystem(struct super_block *sb, int wait)
{
if (wait)
- sync_inodes_sb(sb, start);
+ sync_inodes_sb(sb);
else
writeback_inodes_sb(sb, WB_REASON_SYNC);
@@ -48,7 +47,6 @@ static int __sync_filesystem(struct super_block *sb, int wait,
int sync_filesystem(struct super_block *sb)
{
int ret;
- unsigned long start = jiffies;
/*
* We need to be protected against the filesystem going from
@@ -62,17 +60,17 @@ int sync_filesystem(struct super_block *sb)
if (sb->s_flags & MS_RDONLY)
return 0;
- ret = __sync_filesystem(sb, 0, start);
+ ret = __sync_filesystem(sb, 0);
if (ret < 0)
return ret;
- return __sync_filesystem(sb, 1, start);
+ return __sync_filesystem(sb, 1);
}
EXPORT_SYMBOL_GPL(sync_filesystem);
static void sync_inodes_one_sb(struct super_block *sb, void *arg)
{
if (!(sb->s_flags & MS_RDONLY))
- sync_inodes_sb(sb, *((unsigned long *)arg));
+ sync_inodes_sb(sb);
}
static void sync_fs_one_sb(struct super_block *sb, void *arg)
@@ -104,10 +102,9 @@ static void fdatawait_one_bdev(struct block_device *bdev, void *arg)
SYSCALL_DEFINE0(sync)
{
int nowait = 0, wait = 1;
- unsigned long start = jiffies;
wakeup_flusher_threads(0, WB_REASON_SYNC);
- iterate_supers(sync_inodes_one_sb, &start);
+ iterate_supers(sync_inodes_one_sb, NULL);
iterate_supers(sync_fs_one_sb, &nowait);
iterate_supers(sync_fs_one_sb, &wait);
iterate_bdevs(fdatawrite_one_bdev, NULL);
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 6211230814fd..3eaf5c6622eb 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -27,6 +27,7 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
{
struct dentry *root;
void *ns;
+ bool new_sb;
if (!(flags & MS_KERNMOUNT)) {
if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
@@ -37,8 +38,8 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
}
ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
- root = kernfs_mount_ns(fs_type, flags, sysfs_root, ns);
- if (IS_ERR(root))
+ root = kernfs_mount_ns(fs_type, flags, sysfs_root, &new_sb, ns);
+ if (IS_ERR(root) || !new_sb)
kobj_ns_drop(KOBJ_NS_TYPE_NET, ns);
return root;
}
diff --git a/fs/udf/file.c b/fs/udf/file.c
index c02a27a19c6d..1037637957c7 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -144,6 +144,7 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
size_t count = iocb->ki_nbytes;
struct udf_inode_info *iinfo = UDF_I(inode);
+ mutex_lock(&inode->i_mutex);
down_write(&iinfo->i_data_sem);
if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) {
if (file->f_flags & O_APPEND)
@@ -156,6 +157,7 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
pos + count)) {
err = udf_expand_file_adinicb(inode);
if (err) {
+ mutex_unlock(&inode->i_mutex);
udf_debug("udf_expand_adinicb: err=%d\n", err);
return err;
}
@@ -169,9 +171,17 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
} else
up_write(&iinfo->i_data_sem);
- retval = generic_file_aio_write(iocb, iov, nr_segs, ppos);
- if (retval > 0)
+ retval = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+ mutex_unlock(&inode->i_mutex);
+
+ if (retval > 0) {
+ ssize_t err;
+
mark_inode_dirty(inode);
+ err = generic_write_sync(file, iocb->ki_pos - retval, retval);
+ if (err < 0)
+ retval = err;
+ }
return retval;
}
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 062b7925bca0..982ce05c87ed 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -265,6 +265,7 @@ int udf_expand_file_adinicb(struct inode *inode)
.nr_to_write = 1,
};
+ WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex));
if (!iinfo->i_lenAlloc) {
if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD))
iinfo->i_alloc_type = ICBTAG_FLAG_AD_SHORT;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index f35d5c953ff9..9ddfb8190ca1 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -705,7 +705,6 @@ xfs_setattr_size(
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
- int mask = iattr->ia_valid;
xfs_off_t oldsize, newsize;
struct xfs_trans *tp;
int error;
@@ -726,8 +725,8 @@ xfs_setattr_size(
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(S_ISREG(ip->i_d.di_mode));
- ASSERT((mask & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
- ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
+ ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
+ ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
oldsize = inode->i_size;
newsize = iattr->ia_size;
@@ -736,7 +735,7 @@ xfs_setattr_size(
* Short circuit the truncate case for zero length files.
*/
if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
- if (!(mask & (ATTR_CTIME|ATTR_MTIME)))
+ if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME)))
return 0;
/*
@@ -824,10 +823,11 @@ xfs_setattr_size(
* these flags set. For all other operations the VFS set these flags
* explicitly if it wants a timestamp update.
*/
- if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME)))) {
+ if (newsize != oldsize &&
+ !(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
iattr->ia_ctime = iattr->ia_mtime =
current_fs_time(inode->i_sb);
- mask |= ATTR_CTIME | ATTR_MTIME;
+ iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
}
/*
@@ -863,9 +863,9 @@ xfs_setattr_size(
xfs_inode_clear_eofblocks_tag(ip);
}
- if (mask & ATTR_MODE)
+ if (iattr->ia_valid & ATTR_MODE)
xfs_setattr_mode(ip, iattr);
- if (mask & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
+ if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
xfs_setattr_time(ip, iattr);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index cdebd832c3db..4ef6fdbced78 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -205,16 +205,25 @@ xlog_cil_insert_format_items(
/*
* We 64-bit align the length of each iovec so that the start
* of the next one is naturally aligned. We'll need to
- * account for that slack space here.
+ * account for that slack space here. Then round nbytes up
+ * to 64-bit alignment so that the initial buffer alignment is
+ * easy to calculate and verify.
*/
nbytes += niovecs * sizeof(uint64_t);
+ nbytes = round_up(nbytes, sizeof(uint64_t));
/* grab the old item if it exists for reservation accounting */
old_lv = lip->li_lv;
- /* calc buffer size */
- buf_size = sizeof(struct xfs_log_vec) + nbytes +
- niovecs * sizeof(struct xfs_log_iovec);
+ /*
+ * The data buffer needs to start 64-bit aligned, so round up
+ * that space to ensure we can align it appropriately and not
+ * overrun the buffer.
+ */
+ buf_size = nbytes +
+ round_up((sizeof(struct xfs_log_vec) +
+ niovecs * sizeof(struct xfs_log_iovec)),
+ sizeof(uint64_t));
/* compare to existing item size */
if (lip->li_lv && buf_size <= lip->li_lv->lv_size) {
@@ -251,6 +260,8 @@ xlog_cil_insert_format_items(
/* The allocated data region lies beyond the iovec region */
lv->lv_buf_len = 0;
lv->lv_buf = (char *)lv + buf_size - nbytes;
+ ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t)));
+
lip->li_ops->iop_format(lip, lv);
insert:
ASSERT(lv->lv_buf_len <= nbytes);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 02df7b408a26..f96c05669a9e 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -282,22 +282,29 @@ xfs_readsb(
struct xfs_sb *sbp = &mp->m_sb;
int error;
int loud = !(flags & XFS_MFSI_QUIET);
+ const struct xfs_buf_ops *buf_ops;
ASSERT(mp->m_sb_bp == NULL);
ASSERT(mp->m_ddev_targp != NULL);
/*
+ * For the initial read, we must guess at the sector
+ * size based on the block device. It's enough to
+ * get the sb_sectsize out of the superblock and
+ * then reread with the proper length.
+ * We don't verify it yet, because it may not be complete.
+ */
+ sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
+ buf_ops = NULL;
+
+ /*
* Allocate a (locked) buffer to hold the superblock.
* This will be kept around at all times to optimize
* access to the superblock.
*/
- sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
-
reread:
bp = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
- BTOBB(sector_size), 0,
- loud ? &xfs_sb_buf_ops
- : &xfs_sb_quiet_buf_ops);
+ BTOBB(sector_size), 0, buf_ops);
if (!bp) {
if (loud)
xfs_warn(mp, "SB buffer read failed");
@@ -328,12 +335,13 @@ reread:
}
/*
- * If device sector size is smaller than the superblock size,
- * re-read the superblock so the buffer is correctly sized.
+ * Re-read the superblock so the buffer is correctly sized,
+ * and properly verified.
*/
- if (sector_size < sbp->sb_sectsize) {
+ if (buf_ops == NULL) {
xfs_buf_relse(bp);
sector_size = sbp->sb_sectsize;
+ buf_ops = loud ? &xfs_sb_buf_ops : &xfs_sb_quiet_buf_ops;
goto reread;
}
diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c
index b7c9aea77f8f..1e116794bb66 100644
--- a/fs/xfs/xfs_sb.c
+++ b/fs/xfs/xfs_sb.c
@@ -295,8 +295,7 @@ xfs_mount_validate_sb(
sbp->sb_dblocks == 0 ||
sbp->sb_dblocks > XFS_MAX_DBLOCKS(sbp) ||
sbp->sb_dblocks < XFS_MIN_DBLOCKS(sbp))) {
- XFS_CORRUPTION_ERROR("SB sanity check failed",
- XFS_ERRLEVEL_LOW, mp, sbp);
+ xfs_notice(mp, "SB sanity check failed");
return XFS_ERROR(EFSCORRUPTED);
}
@@ -611,10 +610,10 @@ xfs_sb_read_verify(
XFS_SB_VERSION_5) ||
dsb->sb_crc != 0)) {
- if (!xfs_verify_cksum(bp->b_addr, be16_to_cpu(dsb->sb_sectsize),
+ if (!xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
offsetof(struct xfs_sb, sb_crc))) {
/* Only fail bad secondaries on a known V5 filesystem */
- if (bp->b_bn != XFS_SB_DADDR &&
+ if (bp->b_bn == XFS_SB_DADDR ||
xfs_sb_version_hascrc(&mp->m_sb)) {
error = EFSCORRUPTED;
goto out_error;
@@ -625,7 +624,7 @@ xfs_sb_read_verify(
out_error:
if (error) {
- if (error != EWRONGFS)
+ if (error == EFSCORRUPTED)
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW,
mp, bp->b_addr);
xfs_buf_ioerror(bp, error);
@@ -644,7 +643,6 @@ xfs_sb_quiet_read_verify(
{
struct xfs_dsb *dsb = XFS_BUF_TO_SBP(bp);
-
if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC)) {
/* XFS filesystem, verify noisily! */
xfs_sb_read_verify(bp);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index f317488263dd..d971f4932b5d 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -913,7 +913,7 @@ xfs_flush_inodes(
struct super_block *sb = mp->m_super;
if (down_read_trylock(&sb->s_umount)) {
- sync_inodes_sb(sb, jiffies);
+ sync_inodes_sb(sb);
up_read(&sb->s_umount);
}
}