btrfs: qgroup: fix qgroup prealloc rsv leak in subvolume operations

Create subvolume, create snapshot and delete subvolume all use
btrfs_subvolume_reserve_metadata() to reserve metadata for the changes
done to the parent subvolume's fs tree, which cannot be mediated in the
normal way via start_transaction. When quota groups (squota or qgroups)
are enabled, this reserves qgroup metadata of type PREALLOC. Once the
operation is associated to a transaction, we convert PREALLOC to
PERTRANS, which gets cleared in bulk at the end of the transaction.

However, the error paths of these three operations were not implementing
this lifecycle correctly. They unconditionally converted the PREALLOC to
PERTRANS in a generic cleanup step regardless of errors or whether the
operation was fully associated to a transaction or not. This resulted in
error paths occasionally converting this rsv to PERTRANS without calling
record_root_in_trans successfully, which meant that unless that root got
recorded in the transaction by some other thread, the end of the
transaction would not free that root's PERTRANS, leaking it. Ultimately,
this resulted in hitting a WARN in CONFIG_BTRFS_DEBUG builds at unmount
for the leaked reservation.

The fix is to ensure that every qgroup PREALLOC reservation observes the
following properties:

1. any failure before record_root_in_trans is called successfully
   results in freeing the PREALLOC reservation.
2. after record_root_in_trans, we convert to PERTRANS, and now the
   transaction owns freeing the reservation.

This patch enforces those properties on the three operations. Without
it, generic/269 with squotas enabled at mkfs time would fail in ~5-10
runs on my system. With this patch, it ran successfully 1000 times in a
row.

Fixes: e85fde5162bf ("btrfs: qgroup: fix qgroup meta rsv leak for subvolume operations")
CC: stable@vger.kernel.org # 6.1+
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 28 insertions, 9 deletions

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 38459a89b27c..5a507237c4fa 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -613,6 +613,7 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
 	int ret;
 	dev_t anon_dev;
 	u64 objectid;
+	u64 qgroup_reserved = 0;
 
 	root_item = kzalloc(sizeof(*root_item), GFP_KERNEL);
 	if (!root_item)
@@ -650,13 +651,18 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
 					       trans_num_items, false);
 	if (ret)
 		goto out_new_inode_args;
+	qgroup_reserved = block_rsv.qgroup_rsv_reserved;
 
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
-		btrfs_subvolume_release_metadata(root, &block_rsv);
-		goto out_new_inode_args;
+		goto out_release_rsv;
 	}
+	ret = btrfs_record_root_in_trans(trans, BTRFS_I(dir)->root);
+	if (ret)
+		goto out;
+	btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
+	qgroup_reserved = 0;
 	trans->block_rsv = &block_rsv;
 	trans->bytes_reserved = block_rsv.size;
 	/* Tree log can't currently deal with an inode which is a new root. */
@@ -767,9 +773,11 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
 out:
 	trans->block_rsv = NULL;
 	trans->bytes_reserved = 0;
-	btrfs_subvolume_release_metadata(root, &block_rsv);
-
 	btrfs_end_transaction(trans);
+out_release_rsv:
+	btrfs_block_rsv_release(fs_info, &block_rsv, (u64)-1, NULL);
+	if (qgroup_reserved)
+		btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved);
 out_new_inode_args:
 	btrfs_new_inode_args_destroy(&new_inode_args);
 out_inode:
@@ -791,6 +799,8 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	struct btrfs_pending_snapshot *pending_snapshot;
 	unsigned int trans_num_items;
 	struct btrfs_trans_handle *trans;
+	struct btrfs_block_rsv *block_rsv;
+	u64 qgroup_reserved = 0;
 	int ret;
 
 	/* We do not support snapshotting right now. */
@@ -827,19 +837,19 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 		goto free_pending;
 	}
 
-	btrfs_init_block_rsv(&pending_snapshot->block_rsv,
-			     BTRFS_BLOCK_RSV_TEMP);
+	block_rsv = &pending_snapshot->block_rsv;
+	btrfs_init_block_rsv(block_rsv, BTRFS_BLOCK_RSV_TEMP);
 	/*
 	 * 1 to add dir item
 	 * 1 to add dir index
 	 * 1 to update parent inode item
 	 */
 	trans_num_items = create_subvol_num_items(inherit) + 3;
-	ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root,
-					       &pending_snapshot->block_rsv,
+	ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root, block_rsv,
 					       trans_num_items, false);
 	if (ret)
 		goto free_pending;
+	qgroup_reserved = block_rsv->qgroup_rsv_reserved;
 
 	pending_snapshot->dentry = dentry;
 	pending_snapshot->root = root;
@@ -852,6 +862,13 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 		ret = PTR_ERR(trans);
 		goto fail;
 	}
+	ret = btrfs_record_root_in_trans(trans, BTRFS_I(dir)->root);
+	if (ret) {
+		btrfs_end_transaction(trans);
+		goto fail;
+	}
+	btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
+	qgroup_reserved = 0;
 
 	trans->pending_snapshot = pending_snapshot;
 
@@ -881,7 +898,9 @@ fail:
 	if (ret && pending_snapshot->snap)
 		pending_snapshot->snap->anon_dev = 0;
 	btrfs_put_root(pending_snapshot->snap);
-	btrfs_subvolume_release_metadata(root, &pending_snapshot->block_rsv);
+	btrfs_block_rsv_release(fs_info, block_rsv, (u64)-1, NULL);
+	if (qgroup_reserved)
+		btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved);
 free_pending:
 	if (pending_snapshot->anon_dev)
 		free_anon_bdev(pending_snapshot->anon_dev);