diff options
author | Filipe Manana <fdmanana@suse.com> | 2015-11-27 12:16:16 +0000 |
---|---|---|
committer | Filipe Manana <fdmanana@suse.com> | 2015-12-10 11:22:38 +0000 |
commit | 348a0013d54acec35c22958480af054b97b5e4fe (patch) | |
tree | ff187ba3c2f0b4658f695fce69a8f121ae1be549 /fs | |
parent | dba72cb30b6a4811038128c8a98b268d18ca60fe (diff) | |
download | linux-348a0013d54acec35c22958480af054b97b5e4fe.tar.bz2 |
Btrfs: fix unprotected list move from unused_bgs to deleted_bgs list
As of my previous change titled "Btrfs: fix scrub preventing unused block
groups from being deleted", the following warning at
extent-tree.c:btrfs_delete_unused_bgs() can be hit when we mount the a
filesysten with "-o discard":
10263 void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
10264 {
(...)
10405 if (trimming) {
10406 WARN_ON(!list_empty(&block_group->bg_list));
10407 spin_lock(&trans->transaction->deleted_bgs_lock);
10408 list_move(&block_group->bg_list,
10409 &trans->transaction->deleted_bgs);
10410 spin_unlock(&trans->transaction->deleted_bgs_lock);
10411 btrfs_get_block_group(block_group);
10412 }
(...)
This happens because scrub can now add back the block group to the list of
unused block groups (fs_info->unused_bgs). This is dangerous because we
are moving the block group from the unused block groups list to the list
of deleted block groups without holding the lock that protects the source
list (fs_info->unused_bgs_lock).
The following diagram illustrates how this happens:
CPU 1 CPU 2
cleaner_kthread()
btrfs_delete_unused_bgs()
sees bg X in list
fs_info->unused_bgs
deletes bg X from list
fs_info->unused_bgs
scrub_enumerate_chunks()
searches device tree using
its commit root
finds device extent for
block group X
gets block group X from the tree
fs_info->block_group_cache_tree
(via btrfs_lookup_block_group())
sets bg X to RO (again)
scrub_chunk(bg X)
sets bg X back to RW mode
adds bg X to the list
fs_info->unused_bgs again,
since it's still unused and
currently not in that list
sets bg X to RO mode
btrfs_remove_chunk(bg X)
--> discard is enabled and bg X
is in the fs_info->unused_bgs
list again so the warning is
triggered
--> we move it from that list into
the transaction's delete_bgs
list, but we can have another
task currently manipulating
the first list (fs_info->unused_bgs)
Fix this by using the same lock (fs_info->unused_bgs_lock) to protect both
the list of unused block groups and the list of deleted block groups. This
makes it safe and there's not much worry for more lock contention, as this
lock is seldom used and only the cleaner kthread adds elements to the list
of deleted block groups. The warning goes away too, as this was previously
an impossible case (and would have been better a BUG_ON/ASSERT) but it's
not impossible anymore.
Reproduced with fstest btrfs/073 (using MOUNT_OPTIONS="-o discard").
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Diffstat (limited to 'fs')
-rw-r--r-- | fs/btrfs/extent-tree.c | 10 | ||||
-rw-r--r-- | fs/btrfs/transaction.c | 1 | ||||
-rw-r--r-- | fs/btrfs/transaction.h | 2 |
3 files changed, 8 insertions, 5 deletions
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 4b89680a1923..c4661db2b72a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -10480,11 +10480,15 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) * until transaction commit to do the actual discard. */ if (trimming) { - WARN_ON(!list_empty(&block_group->bg_list)); - spin_lock(&trans->transaction->deleted_bgs_lock); + spin_lock(&fs_info->unused_bgs_lock); + /* + * A concurrent scrub might have added us to the list + * fs_info->unused_bgs, so use a list_move operation + * to add the block group to the deleted_bgs list. + */ list_move(&block_group->bg_list, &trans->transaction->deleted_bgs); - spin_unlock(&trans->transaction->deleted_bgs_lock); + spin_unlock(&fs_info->unused_bgs_lock); btrfs_get_block_group(block_group); } end_trans: diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 3367a3c6f214..be8eae80ff65 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -274,7 +274,6 @@ loop: cur_trans->num_dirty_bgs = 0; spin_lock_init(&cur_trans->dirty_bgs_lock); INIT_LIST_HEAD(&cur_trans->deleted_bgs); - spin_lock_init(&cur_trans->deleted_bgs_lock); spin_lock_init(&cur_trans->dropped_roots_lock); list_add_tail(&cur_trans->list, &fs_info->trans_list); extent_io_tree_init(&cur_trans->dirty_pages, diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 0da21ca9b3fb..64c8221b6165 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -77,8 +77,8 @@ struct btrfs_transaction { */ struct mutex cache_write_mutex; spinlock_t dirty_bgs_lock; + /* Protected by spin lock fs_info->unused_bgs_lock. */ struct list_head deleted_bgs; - spinlock_t deleted_bgs_lock; spinlock_t dropped_roots_lock; struct btrfs_delayed_ref_root delayed_refs; int aborted; |