6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Boris Burkov boris@bur.io
commit 74e97958121aa1f5854da6effba70143f051b0cd upstream.
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 [Xiangyu: BP to fix CVE-2024-35956, due to 6.1 btrfs_subvolume_release_metadata() defined in ctree.h, modified the header file name from root-tree.h to ctree.h] Signed-off-by: Xiangyu Chen xiangyu.chen@windriver.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/ctree.h | 2 -- fs/btrfs/inode.c | 13 ++++++++++++- fs/btrfs/ioctl.c | 36 ++++++++++++++++++++++++++++-------- fs/btrfs/root-tree.c | 10 ---------- 4 files changed, 40 insertions(+), 21 deletions(-)
--- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2987,8 +2987,6 @@ 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, --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4707,6 +4707,7 @@ int btrfs_delete_subvolume(struct inode struct btrfs_trans_handle *trans; struct btrfs_block_rsv block_rsv; u64 root_flags; + u64 qgroup_reserved = 0; int ret;
down_write(&fs_info->subvol_sem); @@ -4751,12 +4752,20 @@ int btrfs_delete_subvolume(struct inode ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true); if (ret) goto out_undead; + qgroup_reserved = block_rsv.qgroup_rsv_reserved;
trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = 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;
@@ -4815,7 +4824,9 @@ out_end_trans: ret = btrfs_end_transaction(trans); 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_undead: if (ret) { spin_lock(&dest->root_item_lock); --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -592,6 +592,7 @@ static noinline int create_subvol(struct int ret; dev_t anon_dev; u64 objectid; + u64 qgroup_reserved = 0;
root_item = kzalloc(sizeof(*root_item), GFP_KERNEL); if (!root_item) @@ -629,13 +630,18 @@ static noinline int create_subvol(struct 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;
@@ -744,12 +750,15 @@ static noinline int create_subvol(struct out: trans->block_rsv = NULL; trans->bytes_reserved = 0; - btrfs_subvolume_release_metadata(root, &block_rsv);
if (ret) btrfs_end_transaction(trans); else ret = btrfs_commit_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: @@ -771,6 +780,8 @@ static int create_snapshot(struct btrfs_ 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. */ @@ -807,19 +818,19 @@ static int create_snapshot(struct btrfs_ 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; @@ -832,6 +843,13 @@ static int create_snapshot(struct btrfs_ 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;
@@ -861,7 +879,9 @@ 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); --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -532,13 +532,3 @@ int btrfs_subvolume_reserve_metadata(str } 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); -}