[PATCH v3] btrfs: qgroup: fix sleep from invalid context bug in update_qgroup_limit_item()

[PATCH v3] btrfs: qgroup: fix sleep from invalid context bug in update_qgroup_limit_item()

[ChenXiaoSong]

Syzkaller reported BUG as follows:

  BUG: sleeping function called from invalid context at
       include/linux/sched/mm.h:274
  Call Trace:
   <TASK>
   dump_stack_lvl+0xcd/0x134
   __might_resched.cold+0x222/0x26b
   kmem_cache_alloc+0x2e7/0x3c0
   update_qgroup_limit_item+0xe1/0x390
   btrfs_qgroup_inherit+0x147b/0x1ee0
   create_subvol+0x4eb/0x1710
   btrfs_mksubvol+0xfe5/0x13f0
   __btrfs_ioctl_snap_create+0x2b0/0x430
   btrfs_ioctl_snap_create_v2+0x25a/0x520
   btrfs_ioctl+0x2a1c/0x5ce0
   __x64_sys_ioctl+0x193/0x200
   do_syscall_64+0x35/0x80

Fix this by delaying the limit item updates until unlock the spin lock.

Signed-off-by: ChenXiaoSong <chenxiaosong2@huawei.com>
---
 fs/btrfs/qgroup.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 9334c3157c22..0071b2be6785 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2860,6 +2860,8 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 	bool need_rescan = false;
 	u32 level_size = 0;
 	u64 nums;
+	bool update_limit = false;
+	int err;
 
 	/*
 	 * There are only two callers of this function.
@@ -2950,15 +2952,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 		dstgroup->max_excl = inherit->lim.max_excl;
 		dstgroup->rsv_rfer = inherit->lim.rsv_rfer;
 		dstgroup->rsv_excl = inherit->lim.rsv_excl;
-
-		ret = update_qgroup_limit_item(trans, dstgroup);
-		if (ret) {
-			qgroup_mark_inconsistent(fs_info);
-			btrfs_info(fs_info,
-				   "unable to update quota limit for %llu",
-				   dstgroup->qgroupid);
-			goto unlock;
-		}
+		update_limit = true;
 	}
 
 	if (srcid) {
@@ -2985,6 +2979,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 		dstgroup->max_excl = srcgroup->max_excl;
 		dstgroup->rsv_rfer = srcgroup->rsv_rfer;
 		dstgroup->rsv_excl = srcgroup->rsv_excl;
+		update_limit = true;
 
 		qgroup_dirty(fs_info, dstgroup);
 		qgroup_dirty(fs_info, srcgroup);
@@ -3053,6 +3048,16 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 
 unlock:
 	spin_unlock(&fs_info->qgroup_lock);
+	if (update_limit) {
+		err = update_qgroup_limit_item(trans, dstgroup);
+		if (err) {
+			ret = err;
+			qgroup_mark_inconsistent(fs_info);
+			btrfs_info(fs_info,
+				   "unable to update quota limit for %llu",
+				   dstgroup->qgroupid);
+		}
+	}
 	if (!ret)
 		ret = btrfs_sysfs_add_one_qgroup(fs_info, dstgroup);
 out:
-- 
2.31.1

Re: [PATCH v3] btrfs: qgroup: fix sleep from invalid context bug in update_qgroup_limit_item()

[ChenXiaoSong]

Please ignore this v3 patch, I will try to send a new version patch 
according to Qu Wenruo's suggestions: 
https://lore.kernel.org/all/df7ede88-86a2-1c6d-0343-c97a851b9bdf@gmx.com/

在 2022/11/11 17:20, ChenXiaoSong 写道:
> Syzkaller reported BUG as follows:
> 
>    BUG: sleeping function called from invalid context at
>         include/linux/sched/mm.h:274
>    Call Trace:
>     <TASK>
>     dump_stack_lvl+0xcd/0x134
>     __might_resched.cold+0x222/0x26b
>     kmem_cache_alloc+0x2e7/0x3c0
>     update_qgroup_limit_item+0xe1/0x390
>     btrfs_qgroup_inherit+0x147b/0x1ee0
>     create_subvol+0x4eb/0x1710
>     btrfs_mksubvol+0xfe5/0x13f0
>     __btrfs_ioctl_snap_create+0x2b0/0x430
>     btrfs_ioctl_snap_create_v2+0x25a/0x520
>     btrfs_ioctl+0x2a1c/0x5ce0
>     __x64_sys_ioctl+0x193/0x200
>     do_syscall_64+0x35/0x80
> 
> Fix this by delaying the limit item updates until unlock the spin lock.
> 
> Signed-off-by: ChenXiaoSong <chenxiaosong2@huawei.com>
> ---
>   fs/btrfs/qgroup.c | 23 ++++++++++++++---------
>   1 file changed, 14 insertions(+), 9 deletions(-)
> 
> diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
> index 9334c3157c22..0071b2be6785 100644
> --- a/fs/btrfs/qgroup.c
> +++ b/fs/btrfs/qgroup.c
> @@ -2860,6 +2860,8 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
>   	bool need_rescan = false;
>   	u32 level_size = 0;
>   	u64 nums;
> +	bool update_limit = false;
> +	int err;
>   
>   	/*
>   	 * There are only two callers of this function.
> @@ -2950,15 +2952,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
>   		dstgroup->max_excl = inherit->lim.max_excl;
>   		dstgroup->rsv_rfer = inherit->lim.rsv_rfer;
>   		dstgroup->rsv_excl = inherit->lim.rsv_excl;
> -
> -		ret = update_qgroup_limit_item(trans, dstgroup);
> -		if (ret) {
> -			qgroup_mark_inconsistent(fs_info);
> -			btrfs_info(fs_info,
> -				   "unable to update quota limit for %llu",
> -				   dstgroup->qgroupid);
> -			goto unlock;
> -		}
> +		update_limit = true;
>   	}
>   
>   	if (srcid) {
> @@ -2985,6 +2979,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
>   		dstgroup->max_excl = srcgroup->max_excl;
>   		dstgroup->rsv_rfer = srcgroup->rsv_rfer;
>   		dstgroup->rsv_excl = srcgroup->rsv_excl;
> +		update_limit = true;
>   
>   		qgroup_dirty(fs_info, dstgroup);
>   		qgroup_dirty(fs_info, srcgroup);
> @@ -3053,6 +3048,16 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
>   
>   unlock:
>   	spin_unlock(&fs_info->qgroup_lock);
> +	if (update_limit) {
> +		err = update_qgroup_limit_item(trans, dstgroup);
> +		if (err) {
> +			ret = err;
> +			qgroup_mark_inconsistent(fs_info);
> +			btrfs_info(fs_info,
> +				   "unable to update quota limit for %llu",
> +				   dstgroup->qgroupid);
> +		}
> +	}
>   	if (!ret)
>   		ret = btrfs_sysfs_add_one_qgroup(fs_info, dstgroup);
>   out:
>