From 5a3e5cb8e08bd876e2542c1451c9a93dab1b0e39 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 27 Apr 2009 16:43:48 +0200 Subject: vfs: Fix sys_sync() and fsync_super() reliability (version 4) 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_blockdevs() 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. [AV: build fixes] Signed-off-by: Jan Kara Signed-off-by: Al Viro --- fs/super.c | 29 ++++++++++++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) (limited to 'fs/super.c') diff --git a/fs/super.c b/fs/super.c index 3d9f117dd2a..18d159dc1e4 100644 --- a/fs/super.c +++ b/fs/super.c @@ -293,6 +293,7 @@ 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); @@ -300,7 +301,6 @@ 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); } /* @@ -522,6 +522,33 @@ restart: mutex_unlock(&mutex); } +#ifdef CONFIG_BLOCK +/* + * 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); +} +#endif + /** * get_super - get the superblock of a device * @bdev: device to get the superblock for -- cgit v1.2.3