1 files changed, 48 insertions, 38 deletions

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 5b0cb04b2b93..9bf282d2453c 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
@@ -832,8 +845,8 @@ out:
 
 static inline void btrfs_free_excluded_extents(const struct btrfs_block_group *bg)
 {
-	btrfs_clear_extent_bits(&bg->fs_info->excluded_extents, bg->start,
-				bg->start + bg->length - 1, EXTENT_DIRTY);
+	btrfs_clear_extent_bit(&bg->fs_info->excluded_extents, bg->start,
+			       bg->start + bg->length - 1, EXTENT_DIRTY, NULL);
 }
 
 static noinline void caching_thread(struct btrfs_work *work)
@@ -877,7 +890,7 @@ static noinline void caching_thread(struct btrfs_work *work)
 	 */
 	if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) &&
 	    !(test_bit(BTRFS_FS_FREE_SPACE_TREE_UNTRUSTED, &fs_info->flags)))
-		ret = load_free_space_tree(caching_ctl);
+		ret = btrfs_load_free_space_tree(caching_ctl);
 	else
 		ret = load_extent_tree_free(caching_ctl);
 done:
@@ -1235,7 +1248,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	 * another task to attempt to create another block group with the same
 	 * item key (and failing with -EEXIST and a transaction abort).
 	 */
-	ret = remove_block_group_free_space(trans, block_group);
+	ret = btrfs_remove_block_group_free_space(trans, block_group);
 	if (ret)
 		goto out;
 
@@ -1244,6 +1257,15 @@ 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);
 
 	/*
@@ -1403,7 +1425,7 @@ out:
 	if (ret == -ENOSPC && btrfs_test_opt(cache->fs_info, ENOSPC_DEBUG)) {
 		btrfs_info(cache->fs_info,
 			"unable to make block group %llu ro", cache->start);
-		btrfs_dump_space_info(cache->fs_info, cache->space_info, 0, 0);
+		btrfs_dump_space_info(cache->fs_info, cache->space_info, 0, false);
 	}
 	return ret;
 }
@@ -1436,14 +1458,14 @@ static bool clean_pinned_extents(struct btrfs_trans_handle *trans,
 	 */
 	mutex_lock(&fs_info->unused_bg_unpin_mutex);
 	if (prev_trans) {
-		ret = btrfs_clear_extent_bits(&prev_trans->pinned_extents, start, end,
-					      EXTENT_DIRTY);
+		ret = btrfs_clear_extent_bit(&prev_trans->pinned_extents, start, end,
+					     EXTENT_DIRTY, NULL);
 		if (ret)
 			goto out;
 	}
 
-	ret = btrfs_clear_extent_bits(&trans->transaction->pinned_extents, start, end,
-				      EXTENT_DIRTY);
+	ret = btrfs_clear_extent_bit(&trans->transaction->pinned_extents, start, end,
+				     EXTENT_DIRTY, NULL);
 out:
 	mutex_unlock(&fs_info->unused_bg_unpin_mutex);
 	if (prev_trans)
@@ -1586,8 +1608,9 @@ 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
@@ -1616,8 +1639,10 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		ret = btrfs_zone_finish(block_group);
 		if (ret < 0) {
 			btrfs_dec_block_group_ro(block_group);
-			if (ret == -EAGAIN)
+			if (ret == -EAGAIN) {
+				btrfs_link_bg_list(block_group, &retry_list);
 				ret = 0;
+			}
 			goto next;
 		}
 
@@ -1843,7 +1868,6 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 	 */
 	list_sort(NULL, &fs_info->reclaim_bgs, reclaim_bgs_cmp);
 	while (!list_empty(&fs_info->reclaim_bgs)) {
-		u64 zone_unusable;
 		u64 used;
 		u64 reserved;
 		int ret = 0;
@@ -1910,16 +1934,6 @@ 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 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);
 
@@ -1963,14 +1977,8 @@ void btrfs_reclaim_bgs_work(struct work_struct *work)
 		reserved = bg->reserved;
 		spin_unlock(&bg->lock);
 
-		btrfs_info(fs_info,
-	"reclaiming chunk %llu with %llu%% used %llu%% reserved %llu%% unusable",
-				bg->start,
-				div64_u64(used * 100, bg->length),
-				div64_u64(reserved * 100, bg->length),
-				div64_u64(zone_unusable * 100, bg->length));
 		trace_btrfs_reclaim_block_group(bg);
-		ret = btrfs_relocate_chunk(fs_info, bg->start);
+		ret = btrfs_relocate_chunk(fs_info, bg->start, false);
 		if (ret) {
 			btrfs_dec_block_group_ro(bg);
 			btrfs_err(fs_info, "error relocating chunk %llu",
@@ -2372,7 +2380,7 @@ static int read_one_block_group(struct btrfs_fs_info *info,
 	cache->global_root_id = btrfs_stack_block_group_chunk_objectid(bgi);
 	cache->space_info = btrfs_find_space_info(info, cache->flags);
 
-	set_free_space_tree_thresholds(cache);
+	btrfs_set_free_space_tree_thresholds(cache);
 
 	if (need_clear) {
 		/*
@@ -2791,7 +2799,7 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
 					 block_group->length);
 		if (ret)
 			btrfs_abort_transaction(trans, ret);
-		add_block_group_free_space(trans, block_group);
+		btrfs_add_block_group_free_space(trans, block_group);
 
 		/*
 		 * If we restriped during balance, we may have added a new raid
@@ -2889,7 +2897,7 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran
 	set_bit(BLOCK_GROUP_FLAG_NEW, &cache->runtime_flags);
 
 	cache->length = size;
-	set_free_space_tree_thresholds(cache);
+	btrfs_set_free_space_tree_thresholds(cache);
 	cache->flags = type;
 	cache->cached = BTRFS_CACHE_FINISHED;
 	cache->global_root_id = calculate_global_root_id(fs_info, cache->start);
@@ -3636,9 +3644,11 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans)
 				wait_event(cur_trans->writer_wait,
 				   atomic_read(&cur_trans->num_writers) == 1);
 				ret = update_block_group_item(trans, path, cache);
-			}
-			if (ret)
+				if (ret)
+					btrfs_abort_transaction(trans, ret);
+			} else if (ret) {
 				btrfs_abort_transaction(trans, ret);
+			}
 		}
 
 		/* If its not on the io list, we need to put the block group */
@@ -4298,7 +4308,7 @@ static void reserve_chunk_space(struct btrfs_trans_handle *trans,
 	if (left < bytes && btrfs_test_opt(fs_info, ENOSPC_DEBUG)) {
 		btrfs_info(fs_info, "left=%llu, need=%llu, flags=%llu",
 			   left, bytes, type);
-		btrfs_dump_space_info(fs_info, info, 0, 0);
+		btrfs_dump_space_info(fs_info, info, 0, false);
 	}
 
 	if (left < bytes) {
@@ -4443,7 +4453,7 @@ static void check_removing_space_info(struct btrfs_space_info *space_info)
 	 * indicates a real bug if this happens.
 	 */
 	if (WARN_ON(space_info->bytes_pinned > 0 || space_info->bytes_may_use > 0))
-		btrfs_dump_space_info(info, space_info, 0, 0);
+		btrfs_dump_space_info(info, space_info, 0, false);
 
 	/*
 	 * If there was a failure to cleanup a log tree, very likely due to an
@@ -4454,7 +4464,7 @@ static void check_removing_space_info(struct btrfs_space_info *space_info)
 	if (!(space_info->flags & BTRFS_BLOCK_GROUP_METADATA) ||
 	    !BTRFS_FS_LOG_CLEANUP_ERROR(info)) {
 		if (WARN_ON(space_info->bytes_reserved > 0))
-			btrfs_dump_space_info(info, space_info, 0, 0);
+			btrfs_dump_space_info(info, space_info, 0, false);
 	}
 
 	WARN_ON(space_info->reclaim_size > 0);