btrfs: qgroup: simple quota auto hierarchy for nested subvolumes

Consider the following sequence:

- enable quotas
- create subvol S id 256 at dir outer/
- create a qgroup 1/100
- add 0/256 (S's auto qgroup) to 1/100
- create subvol T id 257 at dir outer/inner/

With full qgroups, there is no relationship between 0/257 and either of
0/256 or 1/100. There is an inherit feature that the creator of inner/
can use to specify it ought to be in 1/100.

Simple quotas are targeted at container isolation, where such automatic
inheritance for not necessarily trusted/controlled nested subvol
creation would be quite helpful. Therefore, add a new default behavior
for simple quotas: when you create a nested subvol, automatically
inherit as parents any parents of the qgroup of the subvol the new inode
is going in.

In our example, 257/0 would also be under 1/100, allowing easy control
of a total quota over an arbitrary hierarchy of subvolumes.

I think this _might_ be a generally useful behavior, so it could be
interesting to put it behind a new inheritance flag that simple quotas
always use while traditional quotas let the user specify, but this is a
minimally intrusive change to start.

Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>

4 files changed, 67 insertions, 12 deletions

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 58189d99a22c..6603b6fff93f 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -652,7 +652,7 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
 	/* Tree log can't currently deal with an inode which is a new root. */
 	btrfs_set_log_full_commit(trans);
 
-	ret = btrfs_qgroup_inherit(trans, 0, objectid, inherit);
+	ret = btrfs_qgroup_inherit(trans, 0, objectid, root->root_key.objectid, inherit);
 	if (ret)
 		goto out;
 
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 4c70417f13b0..5b3ad2f15039 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1549,8 +1549,7 @@ out:
 	return ret;
 }
 
-int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
-			      u64 dst)
+int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, u64 dst)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_qgroup *parent;
@@ -3018,6 +3017,47 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans)
 	return ret;
 }
 
+static int qgroup_auto_inherit(struct btrfs_fs_info *fs_info,
+			       u64 inode_rootid,
+			       struct btrfs_qgroup_inherit **inherit)
+{
+	int i = 0;
+	u64 num_qgroups = 0;
+	struct btrfs_qgroup *inode_qg;
+	struct btrfs_qgroup_list *qg_list;
+	struct btrfs_qgroup_inherit *res;
+	size_t struct_sz;
+	u64 *qgids;
+
+	if (*inherit)
+		return -EEXIST;
+
+	inode_qg = find_qgroup_rb(fs_info, inode_rootid);
+	if (!inode_qg)
+		return -ENOENT;
+
+	num_qgroups = list_count_nodes(&inode_qg->groups);
+
+	if (!num_qgroups)
+		return 0;
+
+	struct_sz = struct_size(res, qgroups, num_qgroups);
+	if (struct_sz == SIZE_MAX)
+		return -ERANGE;
+
+	res = kzalloc(struct_sz, GFP_NOFS);
+	if (!res)
+		return -ENOMEM;
+	res->num_qgroups = num_qgroups;
+	qgids = res->qgroups;
+
+	list_for_each_entry(qg_list, &inode_qg->groups, next_group)
+		qgids[i] = qg_list->group->qgroupid;
+
+	*inherit = res;
+	return 0;
+}
+
 /*
  * Copy the accounting information between qgroups. This is necessary
  * when a snapshot or a subvolume is created. Throwing an error will
@@ -3025,7 +3065,8 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans)
  * when a readonly fs is a reasonable outcome.
  */
 int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
-			 u64 objectid, struct btrfs_qgroup_inherit *inherit)
+			 u64 objectid, u64 inode_rootid,
+			 struct btrfs_qgroup_inherit *inherit)
 {
 	int ret = 0;
 	int i;
@@ -3037,6 +3078,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 	struct btrfs_qgroup *dstgroup;
 	struct btrfs_qgroup *prealloc;
 	struct btrfs_qgroup_list **qlist_prealloc = NULL;
+	bool free_inherit = false;
 	bool need_rescan = false;
 	u32 level_size = 0;
 	u64 nums;
@@ -3073,6 +3115,13 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 		goto out;
 	}
 
+	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE && !inherit) {
+		ret = qgroup_auto_inherit(fs_info, inode_rootid, &inherit);
+		if (ret)
+			goto out;
+		free_inherit = true;
+	}
+
 	if (inherit) {
 		i_qgroups = (u64 *)(inherit + 1);
 		nums = inherit->num_qgroups + 2 * inherit->num_ref_copies +
@@ -3256,6 +3305,8 @@ out:
 			kfree(qlist_prealloc[i]);
 		kfree(qlist_prealloc);
 	}
+	if (free_inherit)
+		kfree(inherit);
 	kfree(prealloc);
 	return ret;
 }
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 1e0eb04ef96c..9858244eef20 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -312,8 +312,7 @@ int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info);
 void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info);
 int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
 				     bool interruptible);
-int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
-			      u64 dst);
+int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, u64 dst);
 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);
@@ -343,7 +342,8 @@ int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans);
 int btrfs_run_qgroups(struct btrfs_trans_handle *trans);
 int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
-			 u64 objectid, struct btrfs_qgroup_inherit *inherit);
+			 u64 objectid, u64 inode_rootid,
+			 struct btrfs_qgroup_inherit *inherit);
 void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
 			       u64 ref_root, u64 num_bytes,
 			       enum btrfs_qgroup_rsv_type type);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 6c24d00c3612..b87b00884e47 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1620,8 +1620,8 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
 	int ret;
 
 	/*
-	 * Save some performance in the case that full qgroups are not enabled.
-	 * If this check races with the ioctl, rescan will kick in anyway.
+	 * Save some performance in the case that qgroups are not enabled. If
+	 * this check races with the ioctl, rescan will kick in anyway.
 	 */
 	if (!btrfs_qgroup_full_accounting(fs_info))
 		return 0;
@@ -1662,7 +1662,7 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
 
 	/* Now qgroup are all updated, we can inherit it to new qgroups */
 	ret = btrfs_qgroup_inherit(trans, src->root_key.objectid, dst_objectid,
-				   inherit);
+				   parent->root_key.objectid, inherit);
 	if (ret < 0)
 		goto out;
 
@@ -1929,8 +1929,12 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	 * To co-operate with that hack, we do hack again.
 	 * Or snapshot will be greatly slowed down by a subtree qgroup rescan
 	 */
-	ret = qgroup_account_snapshot(trans, root, parent_root,
-				      pending->inherit, objectid);
+	if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_FULL)
+		ret = qgroup_account_snapshot(trans, root, parent_root,
+					      pending->inherit, objectid);
+	else if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE)
+		ret = btrfs_qgroup_inherit(trans, root->root_key.objectid, objectid,
+					   parent_root->root_key.objectid, pending->inherit);
 	if (ret < 0)
 		goto fail;