Merge tag 'for-6.4-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:

 - fix backward leaf iteration which could possibly return the same key

 - fix assertion when device add and balance race for exclusive
   operation

 - fix regression when freeing device, state tree would leak after
   device replace

 - fix attempt to clear space cache v1 when block-group-tree is enabled

 - fix potential i_size corruption when encoded write races with send v2
   and enabled no-holes (the race is hard to hit though, the window is a
   few instructions wide)

 - fix wrong bitmap API use when checking empty zones, parameters were
   swapped but not causing a bug due to other code

 - prevent potential qgroup leak if subvolume create does not commit
   transaction (which is pending in the development queue)

 - error handling and reporting:
     - abort transaction when sibling keys check fails for leaves
     - print extent buffers when sibling keys check fails

* tag 'for-6.4-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: don't free qgroup space unless specified
  btrfs: fix encoded write i_size corruption with no-holes
  btrfs: zoned: fix wrong use of bitops API in btrfs_ensure_empty_zones
  btrfs: properly reject clear_cache and v1 cache for block-group-tree
  btrfs: print extent buffers when sibling keys check fails
  btrfs: abort transaction when sibling keys check fails for leaves
  btrfs: fix leak of source device allocation state after device replace
  btrfs: fix assertion of exclop condition when starting balance
  btrfs: fix btrfs_prev_leaf() to not return the same key twice

Author: torvalds

fs/btrfs/block-rsv.c

@@ -124,7 +124,8 @@ static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
 	} else {
 		num_bytes = 0;
 	}
-	if (block_rsv->qgroup_rsv_reserved >= block_rsv->qgroup_rsv_size) {
+	if (qgroup_to_release_ret &&
+	    block_rsv->qgroup_rsv_reserved >= block_rsv->qgroup_rsv_size) {
 		qgroup_to_release = block_rsv->qgroup_rsv_reserved -
 				    block_rsv->qgroup_rsv_size;
 		block_rsv->qgroup_rsv_reserved = block_rsv->qgroup_rsv_size;

fs/btrfs/ctree.c

@@ -2627,6 +2627,10 @@ static bool check_sibling_keys(struct extent_buffer *left,
 	}
 
 	if (btrfs_comp_cpu_keys(&left_last, &right_first) >= 0) {
+		btrfs_crit(left->fs_info, "left extent buffer:");
+		btrfs_print_tree(left, false);
+		btrfs_crit(left->fs_info, "right extent buffer:");
+		btrfs_print_tree(right, false);
 		btrfs_crit(left->fs_info,
 "bad key order, sibling blocks, left last (%llu %u %llu) right first (%llu %u %llu)",
 			   left_last.objectid, left_last.type,
@@ -3215,6 +3219,7 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root
 
 	if (check_sibling_keys(left, right)) {
 		ret = -EUCLEAN;
+		btrfs_abort_transaction(trans, ret);
 		btrfs_tree_unlock(right);
 		free_extent_buffer(right);
 		return ret;
@@ -3433,6 +3438,7 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root
 
 	if (check_sibling_keys(left, right)) {
 		ret = -EUCLEAN;
+		btrfs_abort_transaction(trans, ret);
 		goto out;
 	}
 	return __push_leaf_left(trans, path, min_data_size, empty, left,
@@ -4478,10 +4484,12 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path)
 {
 	struct btrfs_key key;
+	struct btrfs_key orig_key;
 	struct btrfs_disk_key found_key;
 	int ret;
 
 	btrfs_item_key_to_cpu(path->nodes[0], &key, 0);
+	orig_key = key;
 
 	if (key.offset > 0) {
 		key.offset--;
@@ -4498,8 +4506,36 @@ int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path)
 
 	btrfs_release_path(path);
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
-	if (ret < 0)
+	if (ret <= 0)
 		return ret;
+
+	/*
+	 * Previous key not found. Even if we were at slot 0 of the leaf we had
+	 * before releasing the path and calling btrfs_search_slot(), we now may
+	 * be in a slot pointing to the same original key - this can happen if
+	 * after we released the path, one of more items were moved from a
+	 * sibling leaf into the front of the leaf we had due to an insertion
+	 * (see push_leaf_right()).
+	 * If we hit this case and our slot is > 0 and just decrement the slot
+	 * so that the caller does not process the same key again, which may or
+	 * may not break the caller, depending on its logic.
+	 */
+	if (path->slots[0] < btrfs_header_nritems(path->nodes[0])) {
+		btrfs_item_key(path->nodes[0], &found_key, path->slots[0]);
+		ret = comp_keys(&found_key, &orig_key);
+		if (ret == 0) {
+			if (path->slots[0] > 0) {
+				path->slots[0]--;
+				return 0;
+			}
+			/*
+			 * At slot 0, same key as before, it means orig_key is
+			 * the lowest, leftmost, key in the tree. We're done.
+			 */
+			return 1;
+		}
+	}
+
 	btrfs_item_key(path->nodes[0], &found_key, 0);
 	ret = comp_keys(&found_key, &key);
 	/*

fs/btrfs/file-item.c

@@ -52,20 +52,21 @@ void btrfs_inode_safe_disk_i_size_write(struct btrfs_inode *inode, u64 new_i_siz
 	u64 start, end, i_size;
 	int ret;
 
+	spin_lock(&inode->lock);
 	i_size = new_i_size ?: i_size_read(&inode->vfs_inode);
 	if (btrfs_fs_incompat(fs_info, NO_HOLES)) {
 		inode->disk_i_size = i_size;
-		return;
+		goto out_unlock;
 	}
 
-	spin_lock(&inode->lock);
 	ret = find_contiguous_extent_bit(&inode->file_extent_tree, 0, &start,
 					 &end, EXTENT_DIRTY);
 	if (!ret && start == 0)
 		i_size = min(i_size, end + 1);
 	else
 		i_size = 0;
 	inode->disk_i_size = i_size;
+out_unlock:
 	spin_unlock(&inode->lock);
 }
 

fs/btrfs/ioctl.c

@@ -454,7 +454,9 @@ void btrfs_exclop_balance(struct btrfs_fs_info *fs_info,
 	case BTRFS_EXCLOP_BALANCE_PAUSED:
 		spin_lock(&fs_info->super_lock);
 		ASSERT(fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE ||
-		       fs_info->exclusive_operation == BTRFS_EXCLOP_DEV_ADD);
+		       fs_info->exclusive_operation == BTRFS_EXCLOP_DEV_ADD ||
+		       fs_info->exclusive_operation == BTRFS_EXCLOP_NONE ||
+		       fs_info->exclusive_operation == BTRFS_EXCLOP_BALANCE_PAUSED);
 		fs_info->exclusive_operation = BTRFS_EXCLOP_BALANCE_PAUSED;
 		spin_unlock(&fs_info->super_lock);
 		break;

fs/btrfs/super.c

@@ -826,7 +826,12 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 	    !btrfs_test_opt(info, CLEAR_CACHE)) {
 		btrfs_err(info, "cannot disable free space tree");
 		ret = -EINVAL;
-
+	}
+	if (btrfs_fs_compat_ro(info, BLOCK_GROUP_TREE) &&
+	    (btrfs_test_opt(info, CLEAR_CACHE) ||
+	     !btrfs_test_opt(info, FREE_SPACE_TREE))) {
+		btrfs_err(info, "cannot disable free space tree with block-group-tree feature");
+		ret = -EINVAL;
 	}
 	if (!ret)
 		ret = btrfs_check_mountopts_zoned(info);

fs/btrfs/volumes.c

@@ -395,6 +395,7 @@ void btrfs_free_device(struct btrfs_device *device)
 {
 	WARN_ON(!list_empty(&device->post_commit_list));
 	rcu_string_free(device->name);
+	extent_io_tree_release(&device->alloc_state);
 	btrfs_destroy_dev_zone_info(device);
 	kfree(device);
 }

fs/btrfs/zoned.c

@@ -1168,12 +1168,12 @@ int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size)
 		return -ERANGE;
 
 	/* All the zones are conventional */
-	if (find_next_bit(zinfo->seq_zones, begin, end) == end)
+	if (find_next_bit(zinfo->seq_zones, end, begin) == end)
 		return 0;
 
 	/* All the zones are sequential and empty */
-	if (find_next_zero_bit(zinfo->seq_zones, begin, end) == end &&
-	    find_next_zero_bit(zinfo->empty_zones, begin, end) == end)
+	if (find_next_zero_bit(zinfo->seq_zones, end, begin) == end &&
+	    find_next_zero_bit(zinfo->empty_zones, end, begin) == end)
 		return 0;
 
 	for (pos = start; pos < start + size; pos += zinfo->zone_size) {