Commit 4e8cb33d authored by Boris Burkov's avatar Boris Burkov Committed by Ye Bin
Browse files

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

mainline inclusion
from mainline-v6.9-rc4
commit 74e97958121aa1f5854da6effba70143f051b0cd
category: bugfix
bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9QR71
CVE: CVE-2024-35956

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=74e97958121aa1f5854da6effba70143f051b0cd



--------------------------------

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: e85fde51 ("btrfs: qgroup: fix qgroup meta rsv leak for subvolume operations")
CC: stable@vger.kernel.org # 6.1+
Reviewed-by: default avatarQu Wenruo <wqu@suse.com>
Signed-off-by: default avatarBoris Burkov <boris@bur.io>
Signed-off-by: default avatarDavid Sterba <dsterba@suse.com>
Conflicts:
	fs/btrfs/ctree.h
	fs/btrfs/ioctl.c
	fs/btrfs/inode.c
	fs/btrfs/root-tree.h
[fix context diff]
Signed-off-by: default avatarYe Bin <yebin10@huawei.com>
parent 80be2ec5
Loading
Loading
Loading
Loading
+0 −2
Original line number Diff line number Diff line
@@ -2667,8 +2667,6 @@ enum btrfs_flush_state {
int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
				     struct btrfs_block_rsv *rsv,
				     int nitems, bool use_global_rsv);
void btrfs_subvolume_release_metadata(struct btrfs_root *root,
				      struct btrfs_block_rsv *rsv);
void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes);

int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes);
+12 −1
Original line number Diff line number Diff line
@@ -4021,6 +4021,7 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry)
	struct btrfs_block_rsv block_rsv;
	u64 root_flags;
	int ret;
	u64 qgroup_reserved = 0;
	int err;

	/*
@@ -4063,12 +4064,20 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry)
	err = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true);
	if (err)
		goto out_up_write;
	qgroup_reserved = block_rsv.qgroup_rsv_reserved;

	trans = btrfs_start_transaction(root, 0);
	if (IS_ERR(trans)) {
		err = PTR_ERR(trans);
		goto out_release;
	}
	ret = btrfs_record_root_in_trans(trans, root);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto out_end_trans;
	}
	btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
	qgroup_reserved = 0;
	trans->block_rsv = &block_rsv;
	trans->bytes_reserved = block_rsv.size;

@@ -4129,7 +4138,9 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry)
		err = ret;
	inode->i_flags |= S_DEAD;
out_release:
	btrfs_subvolume_release_metadata(root, &block_rsv);
	btrfs_block_rsv_release(fs_info, &block_rsv, (u64)-1, NULL);
	if (qgroup_reserved)
		btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved);
out_up_write:
	up_write(&fs_info->subvol_sem);
	if (err) {
+28 −8
Original line number Diff line number Diff line
@@ -594,6 +594,7 @@ static noinline int create_subvol(struct inode *dir,
	int err;
	dev_t anon_dev;
	u64 objectid;
	u64 qgroup_reserved = 0;
	u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID;
	u64 index = 0;

@@ -626,13 +627,18 @@ static noinline int create_subvol(struct inode *dir,
	ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 8, false);
	if (ret)
		goto out_anon_dev;
	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_anon_dev;
		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;

@@ -765,7 +771,6 @@ static noinline int create_subvol(struct inode *dir,
out:
	trans->block_rsv = NULL;
	trans->bytes_reserved = 0;
	btrfs_subvolume_release_metadata(root, &block_rsv);

	err = btrfs_commit_transaction(trans);
	if (err && !ret)
@@ -777,6 +782,10 @@ static noinline int create_subvol(struct inode *dir,
			return PTR_ERR(inode);
		d_instantiate(dentry, inode);
	}
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_anon_dev:
	if (anon_dev)
		free_anon_bdev(anon_dev);
@@ -793,6 +802,8 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
	struct inode *inode;
	struct btrfs_pending_snapshot *pending_snapshot;
	struct btrfs_trans_handle *trans;
	struct btrfs_block_rsv *block_rsv;
	u64 qgroup_reserved = 0;
	int ret;

	if (btrfs_root_refs(&root->root_item) == 0)
@@ -822,8 +833,8 @@ 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 - parent dir inode
	 * 2 - dir entries
@@ -833,10 +844,10 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
	 * 1 - UUID item
	 */
	ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root,
					&pending_snapshot->block_rsv, 8,
					false);
					       block_rsv, 8, false);
	if (ret)
		goto free_pending;
	qgroup_reserved = block_rsv->qgroup_rsv_reserved;

	pending_snapshot->dentry = dentry;
	pending_snapshot->root = root;
@@ -849,6 +860,13 @@ 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;

	spin_lock(&fs_info->trans_lock);
	list_add(&pending_snapshot->list,
@@ -881,7 +899,9 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
	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);
+0 −10
Original line number Diff line number Diff line
@@ -521,13 +521,3 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
	}
	return ret;
}

void btrfs_subvolume_release_metadata(struct btrfs_root *root,
				      struct btrfs_block_rsv *rsv)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	u64 qgroup_to_release;

	btrfs_block_rsv_release(fs_info, rsv, (u64)-1, &qgroup_to_release);
	btrfs_qgroup_convert_reserved_meta(root, qgroup_to_release);
}