1 files changed, 39 insertions, 9 deletions

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 4423d8b716a5..7eef79ece5b3 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -34,6 +34,19 @@ int btrfs_should_fragment_free_space(const struct btrfs_block_group *block_group
 }
 #endif
 
+static inline bool has_unwritten_metadata(struct btrfs_block_group *block_group)
+{
+	/* The meta_write_pointer is available only on the zoned setup. */
+	if (!btrfs_is_zoned(block_group->fs_info))
+		return false;
+
+	if (block_group->flags & BTRFS_BLOCK_GROUP_DATA)
+		return false;
+
+	return block_group->start + block_group->alloc_offset >
+		block_group->meta_write_pointer;
+}
+
 /*
  * Return target flags in extended format or 0 if restripe for this chunk_type
  * is not in progress
@@ -1249,6 +1262,15 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 		goto out;
 
 	spin_lock(&block_group->lock);
+	/*
+	 * Hitting this WARN means we removed a block group with an unwritten
+	 * region. It will cause "unable to find chunk map for logical" errors.
+	 */
+	if (WARN_ON(has_unwritten_metadata(block_group)))
+		btrfs_warn(fs_info,
+			   "block group %llu is removed before metadata write out",
+			   block_group->start);
+
 	set_bit(BLOCK_GROUP_FLAG_REMOVED, &block_group->runtime_flags);
 
 	/*
@@ -1567,8 +1589,9 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		 * needing to allocate extents from the block group.
 		 */
 		used = btrfs_space_info_used(space_info, true);
-		if (space_info->total_bytes - block_group->length < used &&
-		    block_group->zone_unusable < block_group->length) {
+		if ((space_info->total_bytes - block_group->length < used &&
+		     block_group->zone_unusable < block_group->length) ||
+		    has_unwritten_metadata(block_group)) {
 			/*
 			 * Add a reference for the list, compensate for the ref
 			 * drop under the "next" label for the
@@ -1891,6 +1914,17 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 			up_write(&space_info->groups_sem);
 			goto next;
 		}
+
+		/*
+		 * Cache the zone_unusable value before turning the block group
+		 * to read only. As soon as the block group is read only it's
+		 * zone_unusable value gets moved to the block group's read-only
+		 * bytes and isn't available for calculations anymore. We also
+		 * cache it before unlocking the block group, to prevent races
+		 * (reports from KCSAN and such tools) with tasks updating it.
+		 */
+		zone_unusable = bg->zone_unusable;
+
 		spin_unlock(&bg->lock);
 		spin_unlock(&space_info->lock);
 
@@ -1907,13 +1941,6 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 			goto next;
 		}
 
-		/*
-		 * Cache the zone_unusable value before turning the block group
-		 * to read only. As soon as the blog group is read only it's
-		 * zone_unusable value gets moved to the block group's read-only
-		 * bytes and isn't available for calculations anymore.
-		 */
-		zone_unusable = bg->zone_unusable;
 		ret = inc_block_group_ro(bg, 0);
 		up_write(&space_info->groups_sem);
 		if (ret < 0)
@@ -2776,8 +2803,11 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
 		/* Already aborted the transaction if it failed. */
 next:
 		btrfs_dec_delayed_refs_rsv_bg_inserts(fs_info);
+
+		spin_lock(&fs_info->unused_bgs_lock);
 		list_del_init(&block_group->bg_list);
 		clear_bit(BLOCK_GROUP_FLAG_NEW, &block_group->runtime_flags);
+		spin_unlock(&fs_info->unused_bgs_lock);
 
 		/*
 		 * If the block group is still unused, add it to the list of