Fix sys_sync() and cleanup code (version 3)
Subsystems (2)
Jan Kara
maintainercover Fix sys_sync() and cleanup code (version 3)
Hi,
this is a next version of the patches. I've modified comments a bit
and mainly fixed a return value of __fsync_super() (forgot to commit the fix before). Thanks to Trond and Christoph for useful comments.
Honza
Jan Kara
maintainerPATCH 1/4 vfs: Fix sys_sync() and fsync_super() reliability (version 3)
So far, do_sync() called:
sync_inodes(0);
sync_supers();
sync_filesystems(0);
sync_filesystems(1);
sync_inodes(1);
This ordering makes it kind of hard for filesystems as sync_inodes(0) need not submit all the IO (for example it skips inodes with I_SYNC set) so e.g. forcing transaction to disk in ->sync_fs() is not really enough. Therefore sys_sync has not been completely reliable on some filesystems (ext3, ext4, reiserfs, ocfs2 and others are hit by this) when racing e.g. with background writeback. A similar problem hits also other filesystems (e.g. ext2) because of write_supers() being called before the sync_inodes(1).
Change the ordering of calls in do_sync() - this requires a new function sync_blkdevs() to preserve the property that block devices are always synced after write_super() / sync_fs() call.
The same issue is fixed in __fsync_super() function used on umount / remount read-only.
--- fs/super.c | 27 ++++++++++++++++++++++++++- fs/sync.c | 3 ++- include/linux/fs.h | 2 ++ 3 files changed, 30 insertions(+), 2 deletions(-)
fs/super.c +26 -1
@@ -267,6 +267,7 @@ void __fsync_super(struct super_block *sb) {sync_inodes_sb (sb,0 );vfs_dq_sync (sb); +sync_inodes_sb (sb,1 );lock_super (sb);if (sb->s_dirt && sb->s_op->write_super) sb->s_op->write_super (sb);
@@ -274,7 +275,6 @@ void __fsync_super(struct super_block *sb)if (sb->s_op->sync_fs) sb->s_op->sync_fs (sb,1 );sync_blockdev (sb->s_bdev); -sync_inodes_sb (sb,1 ); }/*
@@ -502,6 +502,31 @@ restart:mutex_unlock (&mutex); } +/* +* Sync all block devices underlying some superblock +*/ +void sync_blockdevs (void ) +{ +struct super_block *sb; + +spin_lock (&sb_lock); +restart: +list_for_each_entry (sb, &super_blocks, s_list) { +if (!sb->s_bdev) +continue ; + sb->s_count++; +spin_unlock (&sb_lock); +down_read (&sb->s_umount); +if (sb->s_root) +sync_blockdev (sb->s_bdev); +up_read (&sb->s_umount); +spin_lock (&sb_lock); +if (__put_super_and_need_restart (sb)) + goto restart; + } +spin_unlock (&sb_lock); +} +/** * get_super - get the superblock of a device * @bdev: device to get the superblock for
fs/sync.c +2 -1
@@ -26,10 +26,11 @@ static void do_sync(unsigned long wait)wakeup_pdflush (0 );sync_inodes (0 );/* All mappings, inodes and their blockdevs */ vfs_dq_sync (NULL ); +sync_inodes (wait);/* Mappings, inodes and blockdevs, again. */ sync_supers ();/* Write the superblocks */ sync_filesystems (0 );/* Start syncing the filesystems */ sync_filesystems (wait);/* Waitingly sync the filesystems */ -sync_inodes (wait);/* Mappings, inodes and blockdevs, again. */ +sync_blockdevs ();if (!wait)printk ("Emergency Sync complete\n" );if (unlikely (laptop_mode))
include/linux/fs.h +2 -0
@@ -1942,6 +1942,7 @@ extern void bdput(struct block_device *);extern struct block_device *open_by_devnum (dev_t ,fmode_t );extern void invalidate_bdev (struct block_device *);extern int sync_blockdev (struct block_device *bdev); +extern void sync_blockdevs (void );extern struct super_block *freeze_bdev (struct block_device *);extern void emergency_thaw_all (void );extern int thaw_bdev (struct block_device *bdev,struct super_block *sb);
@@ -1951,6 +1952,7 @@ extern int fsync_no_super(struct block_device *);#else static inline void bd_forget (struct inode *inode) {}static inline int sync_blockdev (struct block_device *bdev) {return 0 ; } +static inline void sync_blockdevs (void ) { }static inline void invalidate_bdev (struct block_device *bdev) {}static inline struct super_block *freeze_bdev (struct block_device *sb)
Signature · 1 line
1.6.0.2
Jan Kara
maintainerPATCH 2/4 vfs: Call ->sync_fs() even if s_dirt is 0 (version 3)
In reply to Jan Karasync_filesystems() has a condition that if wait == 0 and s_dirt == 0, then ->sync_fs() isn't called. This does not really make much sence since s_dirt is generally used by a filesystem to mean that ->write_super() needs to be called. But ->sync_fs() does different things. I even suspect that some filesystems (btrfs?) sets s_dirt just to fool this logic.
--- fs/super.c | 2 +- 1 files changed, 1 insertions(+), 1 deletions(-)
fs/super.c +1 -1
@@ -490,7 +490,7 @@ restart:spin_unlock (&sb_lock);down_read (&sb->s_umount);async_synchronize_full_domain (&sb->s_async_list); -if (sb->s_root && (wait || sb->s_dirt)) +if (sb->s_root) sb->s_op->sync_fs (sb, wait);up_read (&sb->s_umount);/* restart only when sb is no longer on the list */
Signature · 1 line
1.6.0.2
Jan Kara
maintainerPATCH 3/4 vfs: Make __fsync_super() a static function (version 3)
In reply to Jan Kara__fsync_super() does the same thing as fsync_super(). So change the only caller to use fsync_super() and make __fsync_super() static. This removes unnecessarily duplicated call to sync_blockdev() and prepares ground for the changes to __fsync_super() in the following patches.
--- fs/block_dev.c | 2 +- fs/super.c | 5 ++--- include/linux/fs.h | 1 - 3 files changed, 3 insertions(+), 5 deletions(-)
fs/block_dev.c +1 -1
@@ -240,7 +240,7 @@ struct super_block *freeze_bdev(struct block_device *bdev) sb->s_frozen =SB_FREEZE_WRITE ;smp_wmb (); -__fsync_super (sb); +fsync_super (sb); sb->s_frozen =SB_FREEZE_TRANS ;smp_wmb ();
fs/super.c +2 -3
@@ -263,7 +263,7 @@ EXPORT_SYMBOL(unlock_super);* device. Takes the superblock lock. Requires a second blkdev * flush by the caller to complete the operation. */ -void __fsync_super (struct super_block *sb) +static int __fsync_super (struct super_block *sb) {sync_inodes_sb (sb,0 );vfs_dq_sync (sb);
@@ -284,8 +284,7 @@ void __fsync_super(struct super_block *sb)*/ int fsync_super (struct super_block *sb) { -__fsync_super (sb); -return sync_blockdev (sb->s_bdev); +return __fsync_super (sb); }EXPORT_SYMBOL_GPL (fsync_super);
include/linux/fs.h +0 -1
@@ -2084,7 +2084,6 @@ extern int filemap_fdatawrite_range(struct address_space *mapping,extern int vfs_fsync (struct file *file,struct dentry *dentry,int datasync);extern void sync_supers (void );extern void sync_filesystems (int wait); -extern void __fsync_super (struct super_block *sb);extern void emergency_sync (void );extern void emergency_remount (void ); extern int do_remount_sb(struct super_block *sb, int flags,
Signature · 1 line
1.6.0.2
Re: [PATCH 3/4] vfs: Make __fsync_super() a static function (version 3)
Quoted 30 lines · Jan Kara
__fsync_super()does the same thing asfsync_super(). So change the only caller to usefsync_super()and make__fsync_super()static. This removes unnecessarily duplicated call tosync_blockdev()and prepares ground for the changes to__fsync_super()in the following patches.Signed-off-by Jan Kara <[email protected]>--- fs/block_dev.c | 2 +- fs/super.c | 5 ++--- include/linux/fs.h | 1 - 3 files changed, 3 insertions(+), 5 deletions(-)fs/block_dev.c +1
-1@@ -240,7 +240,7 @@ struct super_block *freeze_bdev(struct block_device *bdev) sb->s_frozen =SB_FREEZE_WRITE ;smp_wmb (); -__fsync_super (sb); +fsync_super (sb); sb->s_frozen =SB_FREEZE_TRANS ;smp_wmb ();fs/super.c +0
-0
fs/super.c EXPORT_SYMBOL(unlock_super); · line 269
Quoted 8 lines
fs/super.c +1
-1@@ -263,7 +263,7 @@ EXPORT_SYMBOL(unlock_super);* device. Takes the superblock lock. Requires a second blkdev * flush by the caller to complete the operation. */ -void __fsync_super (struct super_block *sb) +static int __fsync_super (struct super_block *sb) {sync_inodes_sb (sb,0 );vfs_dq_sync (sb);
Still missing the return value here :-)
Quoted 22 lines
fs/super.c +1
-2@@ -284,8 +284,7 @@ void __fsync_super(struct super_block *sb)*/ int fsync_super (struct super_block *sb) { -__fsync_super (sb); -return sync_blockdev (sb->s_bdev); +return __fsync_super (sb); }EXPORT_SYMBOL_GPL (fsync_super);include/linux/fs.h +0
-1@@ -2084,7 +2084,6 @@ extern int filemap_fdatawrite_range(struct address_space *mapping,extern int vfs_fsync (struct file *file,struct dentry *dentry,int datasync);extern void sync_supers (void );extern void sync_filesystems (int wait); -extern void __fsync_super (struct super_block *sb);extern void emergency_sync (void );extern void emergency_remount (void ); extern int do_remount_sb(struct super_block *sb, int flags,
Jan Kara
maintainerRe: [PATCH 3/4] vfs: Make __fsync_super() a static function (version 3)
Quoted 33 lines · Trond Myklebust
Quoted 32 lines · Jan Kara
__fsync_super()does the same thing asfsync_super(). So change the only caller to usefsync_super()and make__fsync_super()static. This removes unnecessarily duplicated call tosync_blockdev()and prepares ground for the changes to__fsync_super()in the following patches.Signed-off-by Jan Kara <[email protected]>--- fs/block_dev.c | 2 +- fs/super.c | 5 ++--- include/linux/fs.h | 1 - 3 files changed, 3 insertions(+), 5 deletions(-)fs/block_dev.c +1
-1@@ -240,7 +240,7 @@ struct super_block *freeze_bdev(struct block_device *bdev) sb->s_frozen =SB_FREEZE_WRITE ;smp_wmb (); -__fsync_super (sb); +fsync_super (sb); sb->s_frozen =SB_FREEZE_TRANS ;smp_wmb ();fs/super.c +0
-0@@ -263,7 +263,7 @@ EXPORT_SYMBOL(unlock_super);* device. Takes the superblock lock. Requires a second blkdev * flush by the caller to complete the operation.
Quoted 8 lines
fs/super.c EXPORT_SYMBOL(unlock_super); · line 269
Quoted 6 lines
fs/super.c +1
-1*/ -void __fsync_super (struct super_block *sb) +static int __fsync_super (struct super_block *sb) {sync_inodes_sb (sb,0 );vfs_dq_sync (sb);Still missing the return value here :-)
Ah, OK, but it's fixed in the last patch. I'll fix it in this one as well
for next time. Thanks.
Honza
Signature · 2 lines
Jan Kara <[email protected]> SUSE Labs, CR
Jan Kara
maintainerPATCH 4/4 vfs: Make sys_sync() use fsync_super() (version 3)
In reply to Jan KaraIt is unnecessarily fragile to have two places (fsync_super() and do_sync()) doing data integrity sync of the filesystem. Alter __fsync_super() to accommodate needs of both callers and use it. So after this patch __fsync_super() is the only place where we gather all the calls needed to properly send all data on a filesystem to disk.
Nice bonus is that we get a complete livelock avoidance and write_supers() is now only used for periodic writeback of superblocks.
--- fs/block_dev.c | 15 ++++++--- fs/fs-writeback.c | 49 ------------------------------- fs/super.c | 70 +++++++++++++++------------------------------ fs/sync.c | 31 ++++++------------- include/linux/fs.h | 4 +- include/linux/writeback.h | 1 - 6 files changed, 45 insertions(+), 125 deletions(-)
fs/block_dev.c +10 -5
@@ -175,17 +175,22 @@ blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, iov, offset, nr_segs, blkdev_get_blocks, NULL); } +int __sync_blockdev (struct block_device *bdev,int wait) +{ +if (!bdev) +return 0 ; +if (!wait) +return filemap_flush (bdev->bd_inode->i_mapping); +return filemap_write_and_wait (bdev->bd_inode->i_mapping); +} +/* * Write out and wait upon all the dirty data associated with a block * device via its mapping. Does not take the superblock lock. */ int sync_blockdev (struct block_device *bdev) { -int ret =0 ; - -if (bdev) - ret =filemap_write_and_wait (bdev->bd_inode->i_mapping); -return ret; +return __sync_blockdev (bdev,1 ); }EXPORT_SYMBOL (sync_blockdev);
fs/fs-writeback.c +0 -49
55 lines not on this page · raw message
fs/super.c +23 -47
129 lines not on this page · raw message
fs/sync.c +10 -21
@@ -17,35 +17,24 @@#define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \ SYNC_FILE_RANGE_WAIT_AFTER) -/* -* sync everything. Start out by waking pdflush, because that writes back -* all queues in parallel. -*/ -static void do_sync (unsigned long wait) +SYSCALL_DEFINE0 (sync) { -wakeup_pdflush (0 ); -sync_inodes (0 );/* All mappings, inodes and their blockdevs */ -vfs_dq_sync (NULL ); -sync_inodes (wait);/* Mappings, inodes and blockdevs, again. */ -sync_supers ();/* Write the superblocks */ -sync_filesystems (0 );/* Start syncing the filesystems */ -sync_filesystems (wait);/* Waitingly sync the filesystems */ -sync_blockdevs (); -if (!wait) -printk ("Emergency Sync complete\n" ); +sync_filesystems (0 ); +sync_filesystems (1 );if (unlikely (laptop_mode))laptop_sync_completion (); -} - -SYSCALL_DEFINE0 (sync) -{ -do_sync (1 );return 0 ; }static void do_sync_work (struct work_struct *work) { -do_sync (0 ); +/* +* Sync twice to reduce the possibility we skipped some inodes / pages +* because they were temporarily locked +*/ +sync_filesystems (0 ); +sync_filesystems (0 ); +printk ("Emergency Sync complete\n" );kfree (work); }
include/linux/fs.h +2 -2
@@ -1321,7 +1321,7 @@ struct super_block {struct rw_semaphore s_umount;struct mutex s_lock;int s_count; -int s_need_sync_fs; +int s_need_sync;atomic_t s_active;#ifdef CONFIG_SECURITY void *s_security;
@@ -1942,7 +1942,7 @@ extern void bdput(struct block_device *);extern struct block_device *open_by_devnum (dev_t ,fmode_t );extern void invalidate_bdev (struct block_device *);extern int sync_blockdev (struct block_device *bdev); -extern void sync_blockdevs (void ); +extern int __sync_blockdev (struct block_device *bdev,int wait);extern struct super_block *freeze_bdev (struct block_device *);extern void emergency_thaw_all (void );extern int thaw_bdev (struct block_device *bdev,struct super_block *sb);
include/linux/writeback.h +0 -1
@@ -79,7 +79,6 @@ struct writeback_control {void writeback_inodes (struct writeback_control *wbc);int inode_wait (void *);void sync_inodes_sb (struct super_block *,int wait); -void sync_inodes (int wait);/* writeback.h requires fs.h; it, too, is not included from here. */ static inline void wait_on_inode (struct inode *inode)
Signature · 1 line
1.6.0.2
Quoted 5 lines · Jan Kara
Hi,
this is a next version of the patches. I've modified comments a bit
and mainly fixed a return value of__fsync_super()(forgot to commit the fix before). Thanks to Trond and Christoph for useful comments.
FYI this (or rather the previous one) seems to do fine running xfsqa.
Any chance you could move sync_filesystems to fs/sync.c? It fits in there much better. Same is probably true for (__)fsync_super, which could also use a better name..
Jan Kara
maintainerQuoted 3 lines · Christoph Hellwig
Any chance you could move
sync_filesystemstofs/sync.c? It fits in there much better. Same is probably true for (__)fsync_super, which could also use a better name..
OK, I've moved the syncing code to sync.c and renamed fsync_super() tosync_filesystem() which better describes what it does I think.
Honza
Signature · 2 lines
Jan Kara <[email protected]> SUSE Labs, CR