@@ -2686,10 +2686,23 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
wait_event(sctx->list_wait,
atomic_read(&sctx->bios_in_flight) == 0);
- atomic_set(&sctx->wr_ctx.flush_all_writes, 0);
+ atomic_inc(&fs_info->scrubs_paused);
+ wake_up(&fs_info->scrub_pause_wait);
+
+ /*
+ * must be called before we decrease @scrub_paused.
+ * make sure we don't block transaction commit while
+ * we are waiting pending workers finished.
+ */
wait_event(sctx->list_wait,
atomic_read(&sctx->workers_pending) == 0);
- scrub_blocked_if_needed(fs_info);
+ atomic_set(&sctx->wr_ctx.flush_all_writes, 0);
+
+ mutex_lock(&fs_info->scrub_lock);
+ __scrub_blocked_if_needed(fs_info);
+ atomic_dec(&fs_info->scrubs_paused);
+ mutex_unlock(&fs_info->scrub_lock);
+ wake_up(&fs_info->scrub_pause_wait);
btrfs_put_block_group(cache);
if (ret)
commit cb7ab02156e4 cause a following deadlock found by xfstests,btrfs/011: Thread1 is commiting transaction which is blocked at btrfs_scrub_pause(). Thread2 is calling btrfs_file_aio_write() which has held inode's @i_mutex and commit transaction(blocked because Thread1 is committing transaction). Thread3 is copy_nocow_page worker which will also try to hold inode @i_mutex, so thread3 will wait Thread1 finished. Thread4 is waiting pending workers finished which will wait Thread3 finished. So the problem is like this: Thread1--->Thread4--->Thread3--->Thread2---->Thread1 Deadlock happens! we fix it by letting Thread1 go firstly, which means we won't block transaction commit while we are waiting pending workers finished. Reported-by: Qu Wenruo <quwenruo@cn.fujitsu.com> Signed-off-by: Wang Shilong <wangsl.fnst@cn.fujitsu.com> --- fs/btrfs/scrub.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-)