Merge tag 'for-5.14-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs zoned mode fixes from David Sterba:

 - fix deadlock when allocating system chunk

 - fix wrong mutex unlock on an error path

 - fix extent map splitting for append operation

 - update and fix message reporting unusable chunk space

 - don't block when background zone reclaim runs with balance in
   parallel

* tag 'for-5.14-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: zoned: fix wrong mutex unlock on failure to allocate log root tree
  btrfs: don't block if we can't acquire the reclaim lock
  btrfs: properly split extent_map for REQ_OP_ZONE_APPEND
  btrfs: rework chunk allocation to avoid exhaustion of the system chunk array
  btrfs: fix deadlock with concurrent chunk allocations involving system chunks
  btrfs: zoned: print unusable percentage when reclaiming block groups
  btrfs: zoned: fix types for u64 division in btrfs_reclaim_bgs_work

fs/btrfs/block-group.h

@@ -97,6 +97,7 @@ struct btrfs_block_group {
 	unsigned int removed:1;
 	unsigned int to_copy:1;
 	unsigned int relocating_repair:1;
+	unsigned int chunk_item_inserted:1;
 
 	int disk_cache_state;
 
@@ -268,8 +269,9 @@ void btrfs_reclaim_bgs_work(struct work_struct *work);
 void btrfs_reclaim_bgs(struct btrfs_fs_info *fs_info);
 void btrfs_mark_bg_to_reclaim(struct btrfs_block_group *bg);
 int btrfs_read_block_groups(struct btrfs_fs_info *info);
-int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
-			   u64 type, u64 chunk_offset, u64 size);
+struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *trans,
+						 u64 bytes_used, u64 type,
+						 u64 chunk_offset, u64 size);
 void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans);
 int btrfs_inc_block_group_ro(struct btrfs_block_group *cache,
 			     bool do_chunk_alloc);

fs/btrfs/ctree.c

@@ -364,49 +364,6 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
-static struct extent_buffer *alloc_tree_block_no_bg_flush(
-					  struct btrfs_trans_handle *trans,
-					  struct btrfs_root *root,
-					  u64 parent_start,
-					  const struct btrfs_disk_key *disk_key,
-					  int level,
-					  u64 hint,
-					  u64 empty_size,
-					  enum btrfs_lock_nesting nest)
-{
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct extent_buffer *ret;
-
-	/*
-	 * If we are COWing a node/leaf from the extent, chunk, device or free
-	 * space trees, make sure that we do not finish block group creation of
-	 * pending block groups. We do this to avoid a deadlock.
-	 * COWing can result in allocation of a new chunk, and flushing pending
-	 * block groups (btrfs_create_pending_block_groups()) can be triggered
-	 * when finishing allocation of a new chunk. Creation of a pending block
-	 * group modifies the extent, chunk, device and free space trees,
-	 * therefore we could deadlock with ourselves since we are holding a
-	 * lock on an extent buffer that btrfs_create_pending_block_groups() may
-	 * try to COW later.
-	 * For similar reasons, we also need to delay flushing pending block
-	 * groups when splitting a leaf or node, from one of those trees, since
-	 * we are holding a write lock on it and its parent or when inserting a
-	 * new root node for one of those trees.
-	 */
-	if (root == fs_info->extent_root ||
-	    root == fs_info->chunk_root ||
-	    root == fs_info->dev_root ||
-	    root == fs_info->free_space_root)
-		trans->can_flush_pending_bgs = false;
-
-	ret = btrfs_alloc_tree_block(trans, root, parent_start,
-				     root->root_key.objectid, disk_key, level,
-				     hint, empty_size, nest);
-	trans->can_flush_pending_bgs = true;
-
-	return ret;
-}
-
 /*
  * does the dirty work in cow of a single block.  The parent block (if
  * supplied) is updated to point to the new cow copy.  The new buffer is marked
@@ -455,8 +412,9 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 	if ((root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) && parent)
 		parent_start = parent->start;
 
-	cow = alloc_tree_block_no_bg_flush(trans, root, parent_start, &disk_key,
-					   level, search_start, empty_size, nest);
+	cow = btrfs_alloc_tree_block(trans, root, parent_start,
+				     root->root_key.objectid, &disk_key, level,
+				     search_start, empty_size, nest);
 	if (IS_ERR(cow))
 		return PTR_ERR(cow);
 
@@ -2458,8 +2416,8 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
 	else
 		btrfs_node_key(lower, &lower_key, 0);
 
-	c = alloc_tree_block_no_bg_flush(trans, root, 0, &lower_key, level,
-					 root->node->start, 0,
+	c = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
+				   &lower_key, level, root->node->start, 0,
 				   BTRFS_NESTING_NEW_ROOT);
 	if (IS_ERR(c))
 		return PTR_ERR(c);
@@ -2589,8 +2547,9 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 	mid = (c_nritems + 1) / 2;
 	btrfs_node_key(c, &disk_key, mid);
 
-	split = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, level,
-					     c->start, 0, BTRFS_NESTING_SPLIT);
+	split = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
+				       &disk_key, level, c->start, 0,
+				       BTRFS_NESTING_SPLIT);
 	if (IS_ERR(split))
 		return PTR_ERR(split);
 
@@ -3381,9 +3340,9 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans,
 	 * BTRFS_NESTING_SPLIT_THE_SPLITTENING if we need to, but for now just
 	 * use BTRFS_NESTING_NEW_ROOT.
 	 */
-	right = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, 0,
-					     l->start, 0, num_doubles ?
-					     BTRFS_NESTING_NEW_ROOT :
+	right = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
+				       &disk_key, 0, l->start, 0,
+				       num_doubles ? BTRFS_NESTING_NEW_ROOT :
 				       BTRFS_NESTING_SPLIT);
 	if (IS_ERR(right))
 		return PTR_ERR(right);

fs/btrfs/inode.c

@@ -2271,13 +2271,127 @@ static blk_status_t btrfs_submit_bio_start(struct inode *inode, struct bio *bio,
 	return btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0);
 }
 
+/*
+ * Split an extent_map at [start, start + len]
+ *
+ * This function is intended to be used only for extract_ordered_extent().
+ */
+static int split_zoned_em(struct btrfs_inode *inode, u64 start, u64 len,
+			  u64 pre, u64 post)
+{
+	struct extent_map_tree *em_tree = &inode->extent_tree;
+	struct extent_map *em;
+	struct extent_map *split_pre = NULL;
+	struct extent_map *split_mid = NULL;
+	struct extent_map *split_post = NULL;
+	int ret = 0;
+	int modified;
+	unsigned long flags;
+
+	/* Sanity check */
+	if (pre == 0 && post == 0)
+		return 0;
+
+	split_pre = alloc_extent_map();
+	if (pre)
+		split_mid = alloc_extent_map();
+	if (post)
+		split_post = alloc_extent_map();
+	if (!split_pre || (pre && !split_mid) || (post && !split_post)) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ASSERT(pre + post < len);
+
+	lock_extent(&inode->io_tree, start, start + len - 1);
+	write_lock(&em_tree->lock);
+	em = lookup_extent_mapping(em_tree, start, len);
+	if (!em) {
+		ret = -EIO;
+		goto out_unlock;
+	}
+
+	ASSERT(em->len == len);
+	ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags));
+	ASSERT(em->block_start < EXTENT_MAP_LAST_BYTE);
+
+	flags = em->flags;
+	clear_bit(EXTENT_FLAG_PINNED, &em->flags);
+	clear_bit(EXTENT_FLAG_LOGGING, &flags);
+	modified = !list_empty(&em->list);
+
+	/* First, replace the em with a new extent_map starting from * em->start */
+	split_pre->start = em->start;
+	split_pre->len = (pre ? pre : em->len - post);
+	split_pre->orig_start = split_pre->start;
+	split_pre->block_start = em->block_start;
+	split_pre->block_len = split_pre->len;
+	split_pre->orig_block_len = split_pre->block_len;
+	split_pre->ram_bytes = split_pre->len;
+	split_pre->flags = flags;
+	split_pre->compress_type = em->compress_type;
+	split_pre->generation = em->generation;
+
+	replace_extent_mapping(em_tree, em, split_pre, modified);
+
+	/*
+	 * Now we only have an extent_map at:
+	 *     [em->start, em->start + pre] if pre != 0
+	 *     [em->start, em->start + em->len - post] if pre == 0
+	 */
+
+	if (pre) {
+		/* Insert the middle extent_map */
+		split_mid->start = em->start + pre;
+		split_mid->len = em->len - pre - post;
+		split_mid->orig_start = split_mid->start;
+		split_mid->block_start = em->block_start + pre;
+		split_mid->block_len = split_mid->len;
+		split_mid->orig_block_len = split_mid->block_len;
+		split_mid->ram_bytes = split_mid->len;
+		split_mid->flags = flags;
+		split_mid->compress_type = em->compress_type;
+		split_mid->generation = em->generation;
+		add_extent_mapping(em_tree, split_mid, modified);
+	}
+
+	if (post) {
+		split_post->start = em->start + em->len - post;
+		split_post->len = post;
+		split_post->orig_start = split_post->start;
+		split_post->block_start = em->block_start + em->len - post;
+		split_post->block_len = split_post->len;
+		split_post->orig_block_len = split_post->block_len;
+		split_post->ram_bytes = split_post->len;
+		split_post->flags = flags;
+		split_post->compress_type = em->compress_type;
+		split_post->generation = em->generation;
+		add_extent_mapping(em_tree, split_post, modified);
+	}
+
+	/* Once for us */
+	free_extent_map(em);
+	/* Once for the tree */
+	free_extent_map(em);
+
+out_unlock:
+	write_unlock(&em_tree->lock);
+	unlock_extent(&inode->io_tree, start, start + len - 1);
+out:
+	free_extent_map(split_pre);
+	free_extent_map(split_mid);
+	free_extent_map(split_post);
+
+	return ret;
+}
+
 static blk_status_t extract_ordered_extent(struct btrfs_inode *inode,
 					   struct bio *bio, loff_t file_offset)
 {
 	struct btrfs_ordered_extent *ordered;
-	struct extent_map *em = NULL, *em_new = NULL;
-	struct extent_map_tree *em_tree = &inode->extent_tree;
 	u64 start = (u64)bio->bi_iter.bi_sector << SECTOR_SHIFT;
+	u64 file_len;
 	u64 len = bio->bi_iter.bi_size;
 	u64 end = start + len;
 	u64 ordered_end;
@@ -2317,41 +2431,16 @@ static blk_status_t extract_ordered_extent(struct btrfs_inode *inode,
 		goto out;
 	}
 
+	file_len = ordered->num_bytes;
 	pre = start - ordered->disk_bytenr;
 	post = ordered_end - end;
 
 	ret = btrfs_split_ordered_extent(ordered, pre, post);
 	if (ret)
 		goto out;
-
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, ordered->file_offset, len);
-	if (!em) {
-		read_unlock(&em_tree->lock);
-		ret = -EIO;
-		goto out;
-	}
-	read_unlock(&em_tree->lock);
-
-	ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags));
-	/*
-	 * We cannot reuse em_new here but have to create a new one, as
-	 * unpin_extent_cache() expects the start of the extent map to be the
-	 * logical offset of the file, which does not hold true anymore after
-	 * splitting.
-	 */
-	em_new = create_io_em(inode, em->start + pre, len,
-			      em->start + pre, em->block_start + pre, len,
-			      len, len, BTRFS_COMPRESS_NONE,
-			      BTRFS_ORDERED_REGULAR);
-	if (IS_ERR(em_new)) {
-		ret = PTR_ERR(em_new);
-		goto out;
-	}
-	free_extent_map(em_new);
+	ret = split_zoned_em(inode, file_offset, file_len, pre, post);
 
 out:
-	free_extent_map(em);
 	btrfs_put_ordered_extent(ordered);
 
 	return errno_to_blk_status(ret);

fs/btrfs/transaction.c

@@ -254,23 +254,21 @@ static inline int extwriter_counter_read(struct btrfs_transaction *trans)
 }
 
 /*
- * To be called after all the new block groups attached to the transaction
- * handle have been created (btrfs_create_pending_block_groups()).
+ * To be called after doing the chunk btree updates right after allocating a new
+ * chunk (after btrfs_chunk_alloc_add_chunk_item() is called), when removing a
+ * chunk after all chunk btree updates and after finishing the second phase of
+ * chunk allocation (btrfs_create_pending_block_groups()) in case some block
+ * group had its chunk item insertion delayed to the second phase.
  */
 void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_transaction *cur_trans = trans->transaction;
 
 	if (!trans->chunk_bytes_reserved)
 		return;
 
-	WARN_ON_ONCE(!list_empty(&trans->new_bgs));
-
 	btrfs_block_rsv_release(fs_info, &fs_info->chunk_block_rsv,
 				trans->chunk_bytes_reserved, NULL);
-	atomic64_sub(trans->chunk_bytes_reserved, &cur_trans->chunk_bytes_reserved);
-	cond_wake_up(&cur_trans->chunk_reserve_wait);
 	trans->chunk_bytes_reserved = 0;
 }
 
@@ -386,8 +384,6 @@ static noinline int join_transaction(struct btrfs_fs_info *fs_info,
 	spin_lock_init(&cur_trans->dropped_roots_lock);
 	INIT_LIST_HEAD(&cur_trans->releasing_ebs);
 	spin_lock_init(&cur_trans->releasing_ebs_lock);
-	atomic64_set(&cur_trans->chunk_bytes_reserved, 0);
-	init_waitqueue_head(&cur_trans->chunk_reserve_wait);
 	list_add_tail(&cur_trans->list, &fs_info->trans_list);
 	extent_io_tree_init(fs_info, &cur_trans->dirty_pages,
 			IO_TREE_TRANS_DIRTY_PAGES, fs_info->btree_inode);
@@ -701,7 +697,6 @@ start_transaction(struct btrfs_root *root, unsigned int num_items,
 	h->fs_info = root->fs_info;
 
 	h->type = type;
-	h->can_flush_pending_bgs = true;
 	INIT_LIST_HEAD(&h->new_bgs);
 
 	smp_mb();

fs/btrfs/transaction.h

@@ -96,13 +96,6 @@ struct btrfs_transaction {
 
 	spinlock_t releasing_ebs_lock;
 	struct list_head releasing_ebs;
-
-	/*
-	 * The number of bytes currently reserved, by all transaction handles
-	 * attached to this transaction, for metadata extents of the chunk tree.
-	 */
-	atomic64_t chunk_bytes_reserved;
-	wait_queue_head_t chunk_reserve_wait;
 };
 
 #define __TRANS_FREEZABLE	(1U << 0)
@@ -139,7 +132,7 @@ struct btrfs_trans_handle {
 	short aborted;
 	bool adding_csums;
 	bool allocating_chunk;
-	bool can_flush_pending_bgs;
+	bool removing_chunk;
 	bool reloc_reserved;
 	bool in_fsync;
 	struct btrfs_root *root;

fs/btrfs/tree-log.c

@@ -3173,7 +3173,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 		if (!log_root_tree->node) {
 			ret = btrfs_alloc_log_tree_node(trans, log_root_tree);
 			if (ret) {
-				mutex_unlock(&fs_info->tree_log_mutex);
+				mutex_unlock(&fs_info->tree_root->log_mutex);
 				goto out;
 			}
 		}

fs/btrfs/volumes.h

@@ -450,7 +450,8 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *map,
 			  struct btrfs_io_geometry *io_geom);
 int btrfs_read_sys_array(struct btrfs_fs_info *fs_info);
 int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info);
-int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type);
+struct btrfs_block_group *btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
+					    u64 type);
 void btrfs_mapping_tree_free(struct extent_map_tree *tree);
 blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 			   int mirror_num);
@@ -509,6 +510,8 @@ unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info,
 				    u64 logical);
 int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
 			     u64 chunk_offset, u64 chunk_size);
+int btrfs_chunk_alloc_add_chunk_item(struct btrfs_trans_handle *trans,
+				     struct btrfs_block_group *bg);
 int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset);
 struct extent_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
 				       u64 logical, u64 length);