UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

Btrfs: remove unnecessary locking of cleaner_mutex to avoid deadlock 

After commmit e44163e177 ("btrfs: explictly delete unused block groups
in close_ctree and ro-remount"), added in the 4.3 merge window, we have
calls to btrfs_delete_unused_bgs() while holding the cleaner_mutex.
This can cause a deadlock with a concurrent block group relocation (when
a filesystem balance or shrink operation is in progress for example)
because btrfs_delete_unused_bgs() locks delete_unused_bgs_mutex and the
relocation path locks first delete_unused_bgs_mutex and then it locks
cleaner_mutex, resulting in a classic ABBA deadlock:

         CPU 0                                        CPU 1

lock fs_info->cleaner_mutex

                                           __btrfs_balance() || btrfs_shrink_device()
                                             lock fs_info->delete_unused_bgs_mutex
                                             btrfs_relocate_chunk()
                                               btrfs_relocate_block_group()
                                                 lock fs_info->cleaner_mutex
btrfs_delete_unused_bgs()
  lock fs_info->delete_unused_bgs_mutex

Fix this by not taking the cleaner_mutex before calling
btrfs_delete_unused_bgs() because it's no longer needed after
commit 67c5e7d464 ("Btrfs: fix race between balance and unused block
group deletion"). The mutex fs_info->delete_unused_bgs_mutex, the
spinlock fs_info->unused_bgs_lock and a block group's spinlock are
enough to get correct serialization between tasks running relocation
and unused block group deletion (as well as between multiple tasks
concurrently calling btrfs_delete_unused_bgs()).

This issue was discussed (in the mailing list) during the review of
the patch titled "btrfs: explictly delete unused block groups in
close_ctree and ro-remount" and it was agreed that acquiring the
cleaner mutex had to be dropped after the patch titled
"Btrfs: fix race between balance and unused block group deletion"
got merged (both patches were submitted at about the same time, but
one landed in kernel 4.2 and the other in the 4.3 merge window).

Signed-off-by: Filipe Manana <fdmanana@suse.com>
This commit is contained in:
Filipe Manana 2015-09-10 10:36:06 +01:00
parent 6af3e3adca
commit 85e0a0f21a
2 changed files with 0 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
fs/btrfs/disk-io.c
View File

@ -3762,9 +3762,7 @@ void close_ctree(struct btrfs_root *root)
* block groups queued for removal, the deletion will be
* skipped when we quit the cleaner thread.
*/
mutex_lock(&root->fs_info->cleaner_mutex);
btrfs_delete_unused_bgs(root->fs_info);
mutex_unlock(&root->fs_info->cleaner_mutex);
ret = btrfs_commit_super(root);
if (ret)

2
fs/btrfs/super.c
View File

@ -1658,9 +1658,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
* groups on disk until we're mounted read-write again
* unless we clean them up here.
*/
mutex_lock(&root->fs_info->cleaner_mutex);
btrfs_delete_unused_bgs(fs_info);
mutex_unlock(&root->fs_info->cleaner_mutex);
btrfs_dev_replace_suspend_for_unmount(fs_info);
btrfs_scrub_cancel(fs_info);