Merge tag 'for-5.5-rc8-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fix from David Sterba:
 "Here's a last minute fix for a regression introduced in this
  development cycle.

  There's a small chance of a silent corruption when device replace and
  NOCOW data writes happen at the same time in one block group. Metadata
  or COW data writes are unaffected.

  The extra fixup patch is there to silence an unnecessary warning"

* tag 'for-5.5-rc8-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: dev-replace: remove warning for unknown return codes when finished
  btrfs: scrub: Require mandatory block group RO for dev-replace

2 files changed, 29 insertions, 9 deletions

diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index f639dde2a679..ba4d8f375b3c 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -500,11 +500,8 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
 			      &dev_replace->scrub_progress, 0, 1);
 
 	ret = btrfs_dev_replace_finishing(fs_info, ret);
-	if (ret == -EINPROGRESS) {
+	if (ret == -EINPROGRESS)
 		ret = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS;
-	} else if (ret != -ECANCELED) {
-		WARN_ON(ret);
-	}
 
 	return ret;
 
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 21de630b0730..fd266a2d15ec 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3577,17 +3577,27 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		 * This can easily boost the amount of SYSTEM chunks if cleaner
 		 * thread can't be triggered fast enough, and use up all space
 		 * of btrfs_super_block::sys_chunk_array
+		 *
+		 * While for dev replace, we need to try our best to mark block
+		 * group RO, to prevent race between:
+		 * - Write duplication
+		 *   Contains latest data
+		 * - Scrub copy
+		 *   Contains data from commit tree
+		 *
+		 * If target block group is not marked RO, nocow writes can
+		 * be overwritten by scrub copy, causing data corruption.
+		 * So for dev-replace, it's not allowed to continue if a block
+		 * group is not RO.
 		 */
-		ret = btrfs_inc_block_group_ro(cache, false);
-		scrub_pause_off(fs_info);
-
+		ret = btrfs_inc_block_group_ro(cache, sctx->is_dev_replace);
 		if (ret == 0) {
 			ro_set = 1;
-		} else if (ret == -ENOSPC) {
+		} else if (ret == -ENOSPC && !sctx->is_dev_replace) {
 			/*
 			 * btrfs_inc_block_group_ro return -ENOSPC when it
 			 * failed in creating new chunk for metadata.
-			 * It is not a problem for scrub/replace, because
+			 * It is not a problem for scrub, because
 			 * metadata are always cowed, and our scrub paused
 			 * commit_transactions.
 			 */
@@ -3596,9 +3606,22 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 			btrfs_warn(fs_info,
 				   "failed setting block group ro: %d", ret);
 			btrfs_put_block_group(cache);
+			scrub_pause_off(fs_info);
 			break;
 		}
 
+		/*
+		 * Now the target block is marked RO, wait for nocow writes to
+		 * finish before dev-replace.
+		 * COW is fine, as COW never overwrites extents in commit tree.
+		 */
+		if (sctx->is_dev_replace) {
+			btrfs_wait_nocow_writers(cache);
+			btrfs_wait_ordered_roots(fs_info, U64_MAX, cache->start,
+					cache->length);
+		}
+
+		scrub_pause_off(fs_info);
 		down_write(&dev_replace->rwsem);
 		dev_replace->cursor_right = found_key.offset + length;
 		dev_replace->cursor_left = found_key.offset;