Commit c4be0c1d authored by Takashi Sato's avatar Takashi Sato Committed by Linus Torvalds
Browse files

filesystem freeze: add error handling of write_super_lockfs/unlockfs 



Currently, ext3 in mainline Linux doesn't have the freeze feature which
suspends write requests.  So, we cannot take a backup which keeps the
filesystem's consistency with the storage device's features (snapshot and
replication) while it is mounted.

In many case, a commercial filesystem (e.g.  VxFS) has the freeze feature
and it would be used to get the consistent backup.

If Linux's standard filesystem ext3 has the freeze feature, we can do it
without a commercial filesystem.

So I have implemented the ioctls of the freeze feature.
I think we can take the consistent backup with the following steps.
1. Freeze the filesystem with the freeze ioctl.
2. Separate the replication volume or create the snapshot
   with the storage device's feature.
3. Unfreeze the filesystem with the unfreeze ioctl.
4. Take the backup from the separated replication volume
   or the snapshot.

This patch:

VFS:
Changed the type of write_super_lockfs and unlockfs from "void"
to "int" so that they can return an error.
Rename write_super_lockfs and unlockfs of the super block operation
freeze_fs and unfreeze_fs to avoid a confusion.

ext3, ext4, xfs, gfs2, jfs:
Changed the type of write_super_lockfs and unlockfs from "void"
to "int" so that write_super_lockfs returns an error if needed,
and unlockfs always returns 0.

reiserfs:
Changed the type of write_super_lockfs and unlockfs from "void"
to "int" so that they always return 0 (success) to keep a current behavior.

Signed-off-by: default avatarTakashi Sato <t-sato@yk.jp.nec.com>
Signed-off-by: default avatarMasayuki Hamaguchi <m-hamaguchi@ys.jp.nec.com>
Cc: <xfs-masters@oss.sgi.com>
Cc: <linux-ext4@vger.kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dave Kleikamp <shaggy@austin.ibm.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Alasdair G Kergon <agk@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 69347a23

Documentation/filesystems/Locking

+4 −4
Original line number Original line Diff line number Diff line
@@ -97,8 +97,8 @@ prototypes: 
	void (*put_super) (struct super_block *);

	void (*put_super) (struct super_block *);

	void (*write_super) (struct super_block *);

	void (*write_super) (struct super_block *);

	int (*sync_fs)(struct super_block *sb, int wait);

	int (*sync_fs)(struct super_block *sb, int wait);

	void (*write_super_lockfs) (struct super_block *);

	int (*freeze_fs) (struct super_block *);

	void (*unlockfs) (struct super_block *);

	int (*unfreeze_fs) (struct super_block *);

	int (*statfs) (struct dentry *, struct kstatfs *);

	int (*statfs) (struct dentry *, struct kstatfs *);

	int (*remount_fs) (struct super_block *, int *, char *);

	int (*remount_fs) (struct super_block *, int *, char *);

	void (*clear_inode) (struct inode *);

	void (*clear_inode) (struct inode *);
@@ -119,8 +119,8 @@ delete_inode: no 
put_super:		yes	yes	no

put_super:		yes	yes	no

write_super:		no	yes	read

write_super:		no	yes	read

sync_fs:		no	no	read

sync_fs:		no	no	read

write_super_lockfs:	?

freeze_fs:		?

unlockfs:		?

unfreeze_fs:		?

statfs:			no	no	no

statfs:			no	no	no

remount_fs:		yes	yes	maybe		(see below)

remount_fs:		yes	yes	maybe		(see below)

clear_inode:		no

clear_inode:		no

Documentation/filesystems/vfs.txt

+4 −4
Original line number Original line Diff line number Diff line
@@ -210,8 +210,8 @@ struct super_operations { 
        void (*put_super) (struct super_block *);

        void (*put_super) (struct super_block *);

        void (*write_super) (struct super_block *);

        void (*write_super) (struct super_block *);

        int (*sync_fs)(struct super_block *sb, int wait);

        int (*sync_fs)(struct super_block *sb, int wait);

        void (*write_super_lockfs) (struct super_block *);

        int (*freeze_fs) (struct super_block *);

        void (*unlockfs) (struct super_block *);

        int (*unfreeze_fs) (struct super_block *);

        int (*statfs) (struct dentry *, struct kstatfs *);

        int (*statfs) (struct dentry *, struct kstatfs *);

        int (*remount_fs) (struct super_block *, int *, char *);

        int (*remount_fs) (struct super_block *, int *, char *);

        void (*clear_inode) (struct inode *);

        void (*clear_inode) (struct inode *);
@@ -270,11 +270,11 @@ or bottom half). 
  	a superblock. The second parameter indicates whether the method

  	a superblock. The second parameter indicates whether the method

	should wait until the write out has been completed. Optional.

	should wait until the write out has been completed. Optional.





  write_super_lockfs: called when VFS is locking a filesystem and

  freeze_fs: called when VFS is locking a filesystem and

  	forcing it into a consistent state.  This method is currently

  	forcing it into a consistent state.  This method is currently

  	used by the Logical Volume Manager (LVM).

  	used by the Logical Volume Manager (LVM).





  unlockfs: called when VFS is unlocking a filesystem and making it writable

  unfreeze_fs: called when VFS is unlocking a filesystem and making it writable

  	again.

  	again.





  statfs: called when the VFS needs to get filesystem statistics. This

  statfs: called when the VFS needs to get filesystem statistics. This

fs/buffer.c

+4 −4
Original line number Original line Diff line number Diff line
@@ -221,8 +221,8 @@ struct super_block *freeze_bdev(struct block_device *bdev) 




		sync_blockdev(sb->s_bdev);

		sync_blockdev(sb->s_bdev);





		if (sb->s_op->write_super_lockfs)

		if (sb->s_op->freeze_fs)

			sb->s_op->write_super_lockfs(sb);

			sb->s_op->freeze_fs(sb);

	}

	}





	sync_blockdev(bdev);

	sync_blockdev(bdev);
@@ -242,8 +242,8 @@ void thaw_bdev(struct block_device *bdev, struct super_block *sb) 
	if (sb) {

	if (sb) {

		BUG_ON(sb->s_bdev != bdev);

		BUG_ON(sb->s_bdev != bdev);





		if (sb->s_op->unlockfs)

		if (sb->s_op->unfreeze_fs)

			sb->s_op->unlockfs(sb);

			sb->s_op->unfreeze_fs(sb);

		sb->s_frozen = SB_UNFROZEN;

		sb->s_frozen = SB_UNFROZEN;

		smp_wmb();

		smp_wmb();

		wake_up(&sb->s_wait_unfrozen);

		wake_up(&sb->s_wait_unfrozen);

fs/ext3/super.c

+29 −16
Original line number Original line Diff line number Diff line
@@ -48,7 +48,7 @@ static int ext3_load_journal(struct super_block *, struct ext3_super_block *, 
			     unsigned long journal_devnum);

			     unsigned long journal_devnum);

static int ext3_create_journal(struct super_block *, struct ext3_super_block *,

static int ext3_create_journal(struct super_block *, struct ext3_super_block *,

			       unsigned int);

			       unsigned int);

static void ext3_commit_super (struct super_block * sb,

static int ext3_commit_super(struct super_block *sb,

			       struct ext3_super_block *es,

			       struct ext3_super_block *es,

			       int sync);

			       int sync);

static void ext3_mark_recovery_complete(struct super_block * sb,

static void ext3_mark_recovery_complete(struct super_block * sb,
@@ -60,9 +60,9 @@ static const char *ext3_decode_error(struct super_block * sb, int errno, 
				     char nbuf[16]);

				     char nbuf[16]);

static int ext3_remount (struct super_block * sb, int * flags, char * data);

static int ext3_remount (struct super_block * sb, int * flags, char * data);

static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf);

static int ext3_statfs (struct dentry * dentry, struct kstatfs * buf);

static void ext3_unlockfs(struct super_block *sb);

static int ext3_unfreeze(struct super_block *sb);

static void ext3_write_super (struct super_block * sb);

static void ext3_write_super (struct super_block * sb);

static void ext3_write_super_lockfs(struct super_block *sb);

static int ext3_freeze(struct super_block *sb);





/*

/*

 * Wrappers for journal_start/end.

 * Wrappers for journal_start/end.
@@ -759,8 +759,8 @@ static const struct super_operations ext3_sops = { 
	.put_super	= ext3_put_super,

	.put_super	= ext3_put_super,

	.write_super	= ext3_write_super,

	.write_super	= ext3_write_super,

	.sync_fs	= ext3_sync_fs,

	.sync_fs	= ext3_sync_fs,

	.write_super_lockfs = ext3_write_super_lockfs,

	.freeze_fs	= ext3_freeze,

	.unlockfs	= ext3_unlockfs,

	.unfreeze_fs	= ext3_unfreeze,

	.statfs		= ext3_statfs,

	.statfs		= ext3_statfs,

	.remount_fs	= ext3_remount,

	.remount_fs	= ext3_remount,

	.clear_inode	= ext3_clear_inode,

	.clear_inode	= ext3_clear_inode,
@@ -2311,21 +2311,23 @@ static int ext3_create_journal(struct super_block * sb, 
	return 0;

	return 0;

}

}





static void ext3_commit_super (struct super_block * sb,

static int ext3_commit_super(struct super_block *sb,

			       struct ext3_super_block *es,

			       struct ext3_super_block *es,

			       int sync)

			       int sync)

{

{

	struct buffer_head *sbh = EXT3_SB(sb)->s_sbh;

	struct buffer_head *sbh = EXT3_SB(sb)->s_sbh;

	int error = 0;





	if (!sbh)

	if (!sbh)

		return;

		return error;

	es->s_wtime = cpu_to_le32(get_seconds());

	es->s_wtime = cpu_to_le32(get_seconds());

	es->s_free_blocks_count = cpu_to_le32(ext3_count_free_blocks(sb));

	es->s_free_blocks_count = cpu_to_le32(ext3_count_free_blocks(sb));

	es->s_free_inodes_count = cpu_to_le32(ext3_count_free_inodes(sb));

	es->s_free_inodes_count = cpu_to_le32(ext3_count_free_inodes(sb));

	BUFFER_TRACE(sbh, "marking dirty");

	BUFFER_TRACE(sbh, "marking dirty");

	mark_buffer_dirty(sbh);

	mark_buffer_dirty(sbh);

	if (sync)

	if (sync)

		sync_dirty_buffer(sbh);

		error = sync_dirty_buffer(sbh);

	return error;

}

}
@@ -2439,12 +2441,14 @@ static int ext3_sync_fs(struct super_block *sb, int wait) 
 * LVM calls this function before a (read-only) snapshot is created.  This

 * LVM calls this function before a (read-only) snapshot is created.  This

 * gives us a chance to flush the journal completely and mark the fs clean.

 * gives us a chance to flush the journal completely and mark the fs clean.

 */

 */

static void ext3_write_super_lockfs(struct super_block *sb)

static int ext3_freeze(struct super_block *sb)

{

{

	int error = 0;

	journal_t *journal;

	sb->s_dirt = 0;

	sb->s_dirt = 0;





	if (!(sb->s_flags & MS_RDONLY)) {

	if (!(sb->s_flags & MS_RDONLY)) {

		journal_t *journal = EXT3_SB(sb)->s_journal;

		journal = EXT3_SB(sb)->s_journal;





		/* Now we set up the journal barrier. */

		/* Now we set up the journal barrier. */

		journal_lock_updates(journal);

		journal_lock_updates(journal);
@@ -2453,20 +2457,28 @@ static void ext3_write_super_lockfs(struct super_block *sb) 
		 * We don't want to clear needs_recovery flag when we failed

		 * We don't want to clear needs_recovery flag when we failed

		 * to flush the journal.

		 * to flush the journal.

		 */

		 */

		if (journal_flush(journal) < 0)

		error = journal_flush(journal);

			return;

		if (error < 0)

			goto out;





		/* Journal blocked and flushed, clear needs_recovery flag. */

		/* Journal blocked and flushed, clear needs_recovery flag. */

		EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);

		EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);

		ext3_commit_super(sb, EXT3_SB(sb)->s_es, 1);

		error = ext3_commit_super(sb, EXT3_SB(sb)->s_es, 1);

		if (error)

			goto out;

	}

	}

	return 0;



out:

	journal_unlock_updates(journal);

	return error;

}

}





/*

/*

 * Called by LVM after the snapshot is done.  We need to reset the RECOVER

 * Called by LVM after the snapshot is done.  We need to reset the RECOVER

 * flag here, even though the filesystem is not technically dirty yet.

 * flag here, even though the filesystem is not technically dirty yet.

 */

 */

static void ext3_unlockfs(struct super_block *sb)

static int ext3_unfreeze(struct super_block *sb)

{

{

	if (!(sb->s_flags & MS_RDONLY)) {

	if (!(sb->s_flags & MS_RDONLY)) {

		lock_super(sb);

		lock_super(sb);
@@ -2476,6 +2488,7 @@ static void ext3_unlockfs(struct super_block *sb) 
		unlock_super(sb);

		unlock_super(sb);

		journal_unlock_updates(EXT3_SB(sb)->s_journal);

		journal_unlock_updates(EXT3_SB(sb)->s_journal);

	}

	}

	return 0;

}

}





static int ext3_remount (struct super_block * sb, int * flags, char * data)

static int ext3_remount (struct super_block * sb, int * flags, char * data)

fs/ext4/super.c

+31 −14
Original line number Original line Diff line number Diff line
@@ -51,7 +51,7 @@ struct proc_dir_entry *ext4_proc_root; 




static int ext4_load_journal(struct super_block *, struct ext4_super_block *,

static int ext4_load_journal(struct super_block *, struct ext4_super_block *,

			     unsigned long journal_devnum);

			     unsigned long journal_devnum);

static void ext4_commit_super(struct super_block *sb,

static int ext4_commit_super(struct super_block *sb,

			      struct ext4_super_block *es, int sync);

			      struct ext4_super_block *es, int sync);

static void ext4_mark_recovery_complete(struct super_block *sb,

static void ext4_mark_recovery_complete(struct super_block *sb,

					struct ext4_super_block *es);

					struct ext4_super_block *es);
@@ -62,9 +62,9 @@ static const char *ext4_decode_error(struct super_block *sb, int errno, 
				     char nbuf[16]);

				     char nbuf[16]);

static int ext4_remount(struct super_block *sb, int *flags, char *data);

static int ext4_remount(struct super_block *sb, int *flags, char *data);

static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf);

static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf);

static void ext4_unlockfs(struct super_block *sb);

static int ext4_unfreeze(struct super_block *sb);

static void ext4_write_super(struct super_block *sb);

static void ext4_write_super(struct super_block *sb);

static void ext4_write_super_lockfs(struct super_block *sb);

static int ext4_freeze(struct super_block *sb);









ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,

ext4_fsblk_t ext4_block_bitmap(struct super_block *sb,
@@ -978,8 +978,8 @@ static const struct super_operations ext4_sops = { 
	.put_super	= ext4_put_super,

	.put_super	= ext4_put_super,

	.write_super	= ext4_write_super,

	.write_super	= ext4_write_super,

	.sync_fs	= ext4_sync_fs,

	.sync_fs	= ext4_sync_fs,

	.write_super_lockfs = ext4_write_super_lockfs,

	.freeze_fs	= ext4_freeze,

	.unlockfs	= ext4_unlockfs,

	.unfreeze_fs	= ext4_unfreeze,

	.statfs		= ext4_statfs,

	.statfs		= ext4_statfs,

	.remount_fs	= ext4_remount,

	.remount_fs	= ext4_remount,

	.clear_inode	= ext4_clear_inode,

	.clear_inode	= ext4_clear_inode,
@@ -2888,13 +2888,14 @@ static int ext4_load_journal(struct super_block *sb, 
	return 0;

	return 0;

}

}





static void ext4_commit_super(struct super_block *sb,

static int ext4_commit_super(struct super_block *sb,

			      struct ext4_super_block *es, int sync)

			      struct ext4_super_block *es, int sync)

{

{

	struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;

	struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;

	int error = 0;





	if (!sbh)

	if (!sbh)

		return;

		return error;

	if (buffer_write_io_error(sbh)) {

	if (buffer_write_io_error(sbh)) {

		/*

		/*

		 * Oh, dear.  A previous attempt to write the

		 * Oh, dear.  A previous attempt to write the
@@ -2918,14 +2919,19 @@ static void ext4_commit_super(struct super_block *sb, 
	BUFFER_TRACE(sbh, "marking dirty");

	BUFFER_TRACE(sbh, "marking dirty");

	mark_buffer_dirty(sbh);

	mark_buffer_dirty(sbh);

	if (sync) {

	if (sync) {

		sync_dirty_buffer(sbh);

		error = sync_dirty_buffer(sbh);

		if (buffer_write_io_error(sbh)) {

		if (error)

			return error;



		error = buffer_write_io_error(sbh);

		if (error) {

			printk(KERN_ERR "EXT4-fs: I/O error while writing "

			printk(KERN_ERR "EXT4-fs: I/O error while writing "

			       "superblock for %s.\n", sb->s_id);

			       "superblock for %s.\n", sb->s_id);

			clear_buffer_write_io_error(sbh);

			clear_buffer_write_io_error(sbh);

			set_buffer_uptodate(sbh);

			set_buffer_uptodate(sbh);

		}

		}

	}

	}

	return error;

}

}
@@ -3058,12 +3064,14 @@ static int ext4_sync_fs(struct super_block *sb, int wait) 
 * LVM calls this function before a (read-only) snapshot is created.  This

 * LVM calls this function before a (read-only) snapshot is created.  This

 * gives us a chance to flush the journal completely and mark the fs clean.

 * gives us a chance to flush the journal completely and mark the fs clean.

 */

 */

static void ext4_write_super_lockfs(struct super_block *sb)

static int ext4_freeze(struct super_block *sb)

{

{

	int error = 0;

	journal_t *journal;

	sb->s_dirt = 0;

	sb->s_dirt = 0;





	if (!(sb->s_flags & MS_RDONLY)) {

	if (!(sb->s_flags & MS_RDONLY)) {

		journal_t *journal = EXT4_SB(sb)->s_journal;

		journal = EXT4_SB(sb)->s_journal;





		if (journal) {

		if (journal) {

			/* Now we set up the journal barrier. */

			/* Now we set up the journal barrier. */
@@ -3073,21 +3081,29 @@ static void ext4_write_super_lockfs(struct super_block *sb) 
			 * We don't want to clear needs_recovery flag when we

			 * We don't want to clear needs_recovery flag when we

			 * failed to flush the journal.

			 * failed to flush the journal.

			 */

			 */

			if (jbd2_journal_flush(journal) < 0)

			error = jbd2_journal_flush(journal);

				return;

			if (error < 0)

				goto out;

		}

		}





		/* Journal blocked and flushed, clear needs_recovery flag. */

		/* Journal blocked and flushed, clear needs_recovery flag. */

		EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);

		EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);

		ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1);

		ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1);

		error = ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1);

		if (error)

			goto out;

	}

	}

	return 0;

out:

	jbd2_journal_unlock_updates(journal);

	return error;

}

}





/*

/*

 * Called by LVM after the snapshot is done.  We need to reset the RECOVER

 * Called by LVM after the snapshot is done.  We need to reset the RECOVER

 * flag here, even though the filesystem is not technically dirty yet.

 * flag here, even though the filesystem is not technically dirty yet.

 */

 */

static void ext4_unlockfs(struct super_block *sb)

static int ext4_unfreeze(struct super_block *sb)

{

{

	if (EXT4_SB(sb)->s_journal && !(sb->s_flags & MS_RDONLY)) {

	if (EXT4_SB(sb)->s_journal && !(sb->s_flags & MS_RDONLY)) {

		lock_super(sb);

		lock_super(sb);
@@ -3097,6 +3113,7 @@ static void ext4_unlockfs(struct super_block *sb) 
		unlock_super(sb);

		unlock_super(sb);

		jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);

		jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);

	}

	}

	return 0;

}

}





static int ext4_remount(struct super_block *sb, int *flags, char *data)

static int ext4_remount(struct super_block *sb, int *flags, char *data)

CRA Git | Maintained and supported by SUSTech CRA and CCSE