Merge tag 'v5.6-rc3' into sched/core, to pick up fixes and dependent patches

Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 34 insertions, 6 deletions

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 21de630b0730..61b37c56a7fb 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -8,6 +8,7 @@
 #include <linux/sched/mm.h>
 #include <crypto/hash.h>
 #include "ctree.h"
+#include "discard.h"
 #include "volumes.h"
 #include "disk-io.h"
 #include "ordered-data.h"
@@ -3577,17 +3578,27 @@ 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 +3607,22 @@ 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;
@@ -3659,7 +3683,11 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		if (!cache->removed && !cache->ro && cache->reserved == 0 &&
 		    cache->used == 0) {
 			spin_unlock(&cache->lock);
-			btrfs_mark_bg_unused(cache);
+			if (btrfs_test_opt(fs_info, DISCARD_ASYNC))
+				btrfs_discard_queue_work(&fs_info->discard_ctl,
+							 cache);
+			else
+				btrfs_mark_bg_unused(cache);
 		} else {
 			spin_unlock(&cache->lock);
 		}