btrfs: automatically remove the subvolume qgroup

Currently if we fully clean a subvolume (not only delete its directory,
but fully clean all it's related data and root item), the associated
qgroup would not be removed.

We have "btrfs qgroup clear-stale" to handle such 0 level qgroups.

Change the behavior to automatically removie the qgroup of a fully
cleaned subvolume when possible:

- Full qgroup but still consistent
  We can and should remove the qgroup.
  The qgroup numbers should be 0, without any rsv.

- Full qgroup but inconsistent
  Can happen with drop_subtree_threshold feature (skip accounting
  and mark qgroup inconsistent).

  We can and should remove the qgroup.
  Higher level qgroup numbers will be incorrect, but since qgroup
  is already inconsistent, it should not be a problem.

- Squota mode
  This is the special case, we can only drop the qgroup if its numbers
  are all 0.

  This would be handled by can_delete_qgroup(), so we only need to check
  the return value and ignore the -EBUSY error.

Link: https://bugzilla.suse.com/show_bug.cgi?id=1222847
Reviewed-by: Boris Burkov <[email protected]>
Signed-off-by: Qu Wenruo <[email protected]>
Reviewed-by: David Sterba <[email protected]>
Signed-off-by: David Sterba <[email protected]>

fs/btrfs/extent-tree.c

@@ -5833,6 +5833,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
 	struct btrfs_root_item *root_item = &root->root_item;
 	struct walk_control *wc;
 	struct btrfs_key key;
+	const u64 rootid = btrfs_root_id(root);
 	int err = 0;
 	int ret;
 	int level;
@@ -6063,6 +6064,13 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc)
 	kfree(wc);
 	btrfs_free_path(path);
 out:
+	if (!err && root_dropped) {
+		ret = btrfs_qgroup_cleanup_dropped_subvolume(fs_info, rootid);
+		if (ret < 0)
+			btrfs_warn_rl(fs_info,
+				      "failed to cleanup qgroup 0/%llu: %d",
+				      rootid, ret);
+	}
 	/*
 	 * We were an unfinished drop root, check to see if there are any
 	 * pending, and if not clear and wake up any waiters.

fs/btrfs/qgroup.c

@@ -1889,6 +1889,41 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 	return ret;
 }
 
+int btrfs_qgroup_cleanup_dropped_subvolume(struct btrfs_fs_info *fs_info, u64 subvolid)
+{
+	struct btrfs_trans_handle *trans;
+	int ret;
+
+	if (!is_fstree(subvolid) || !btrfs_qgroup_enabled(fs_info) || !fs_info->quota_root)
+		return 0;
+
+	/*
+	 * Commit current transaction to make sure all the rfer/excl numbers
+	 * get updated.
+	 */
+	trans = btrfs_start_transaction(fs_info->quota_root, 0);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
+
+	ret = btrfs_commit_transaction(trans);
+	if (ret < 0)
+		return ret;
+
+	/* Start new trans to delete the qgroup info and limit items. */
+	trans = btrfs_start_transaction(fs_info->quota_root, 2);
+	if (IS_ERR(trans))
+		return PTR_ERR(trans);
+	ret = btrfs_remove_qgroup(trans, subvolid);
+	btrfs_end_transaction(trans);
+	/*
+	 * It's squota and the subvolume still has numbers needed for future
+	 * accounting, in this case we can not delete it.  Just skip it.
+	 */
+	if (ret == -EBUSY)
+		ret = 0;
+	return ret;
+}
+
 int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid,
 		       struct btrfs_qgroup_limit *limit)
 {

fs/btrfs/qgroup.h

@@ -327,6 +327,7 @@ int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
 			      u64 dst);
 int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid);
 int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid);
+int btrfs_qgroup_cleanup_dropped_subvolume(struct btrfs_fs_info *fs_info, u64 subvolid);
 int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid,
 		       struct btrfs_qgroup_limit *limit);
 int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info);