diff options
| -rw-r--r-- | fs/btrfs/transaction.c | 15 | ||||
| -rw-r--r-- | fs/btrfs/volumes.c | 9 |
2 files changed, 22 insertions, 2 deletions
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index d1f1da6820fb..682b463a7633 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -2009,7 +2009,20 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err) if (current->journal_info == trans) current->journal_info = NULL; - btrfs_scrub_cancel(fs_info); + + /* + * If relocation is running, we can't cancel scrub because that will + * result in a deadlock. Before relocating a block group, relocation + * pauses scrub, then starts and commits a transaction before unpausing + * scrub. If the transaction commit is being done by the relocation + * task or triggered by another task and the relocation task is waiting + * for the commit, and we end up here due to an error in the commit + * path, then calling btrfs_scrub_cancel() will deadlock, as we are + * asking for scrub to stop while having it asked to be paused higher + * above in relocation code. + */ + if (!test_bit(BTRFS_FS_RELOC_RUNNING, &fs_info->flags)) + btrfs_scrub_cancel(fs_info); kmem_cache_free(btrfs_trans_handle_cachep, trans); } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index f02b8cbd6ec4..6a2b6042845c 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3286,8 +3286,15 @@ int btrfs_relocate_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset) btrfs_scrub_pause(fs_info); ret = btrfs_relocate_block_group(fs_info, chunk_offset); btrfs_scrub_continue(fs_info); - if (ret) + if (ret) { + /* + * If we had a transaction abort, stop all running scrubs. + * See transaction.c:cleanup_transaction() why we do it here. + */ + if (BTRFS_FS_ERROR(fs_info)) + btrfs_scrub_cancel(fs_info); return ret; + } block_group = btrfs_lookup_block_group(fs_info, chunk_offset); if (!block_group) |