[PATCH v3] xfs: don't hold buffer locks across sync transaction commit in xfs_sync_sb_buf

[PATCH v3] xfs: don't hold buffer locks across sync transaction commit in xfs_sync_sb_buf

[Yun Zhou]

xfs_sync_sb_buf() holds sb/rtsb buffer locks across a synchronous
xfs_trans_commit(), which flushes the CIL push workqueue internally.
If shutdown occurs during the CIL push, xfs_buf_item_unpin() needs to
lock these buffers to fail them, causing a deadlock:

  setlabel:          holds buf lock -> flush_workqueue(xfs-cil)
  CIL push worker:   xfs_buf_item_unpin -> xfs_buf_lock(same buf)

Remove the xfs_trans_bhold() calls so that commit releases the buffer
locks normally.  After the sync commit, re-acquire the buffers via
mp->m_sb_bp / mp->m_rtsb_bp for the on-disk writeback.

Fixes: f7664b31975b ("xfs: implement online get/set fs label")
Reported-by: syzbot+837bcd54843dd6262f2f@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=837bcd54843dd6262f2f
Cc: stable@vger.kernel.org
Signed-off-by: Yun Zhou <yun.zhou@windriver.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
v3:
 - Drop xfs_buf_hold/xfs_buf_relse, use lock/unlock directly (Christoph).

v2:
 - Remove the bp variable and pass xfs_trans_getsb(tp) directly to
   xfs_log_rtsb() to fix compilation warnings when CONFIG_XFS_RT=n.
 - Convert xfs_log_rtsb() stub from macro to inline function to avoid
   the need for (void) casting (Christoph).
---
 fs/xfs/libxfs/xfs_rtgroup.h |  6 +++++-
 fs/xfs/libxfs/xfs_sb.c      | 37 +++++++++++++++++--------------------
 2 files changed, 22 insertions(+), 21 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
index c0b9f9f2c413..fca2eb74908c 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.h
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -359,7 +359,11 @@ static inline int xfs_initialize_rtgroups(struct xfs_mount *mp,
 # define xfs_rtgroup_unlock(rtg, gf)		((void)0)
 # define xfs_rtgroup_trans_join(tp, rtg, gf)	((void)0)
 # define xfs_update_rtsb(bp, sb_bp)	((void)0)
-# define xfs_log_rtsb(tp, sb_bp)	(NULL)
+static inline struct xfs_buf *xfs_log_rtsb(struct xfs_trans *tp,
+		const struct xfs_buf *sb_bp)
+{
+	return NULL;
+}
 # define xfs_rtgroup_get_geometry(rtg, rgeo)	(-EOPNOTSUPP)
 #endif /* CONFIG_XFS_RT */
 
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 47322adb7690..2664728f2d8f 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -1470,36 +1470,33 @@ xfs_sync_sb_buf(
 	bool			update_rtsb)
 {
 	struct xfs_trans	*tp;
-	struct xfs_buf		*bp;
-	struct xfs_buf		*rtsb_bp = NULL;
 	int			error;
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0, 0, &tp);
 	if (error)
 		return error;
 
-	bp = xfs_trans_getsb(tp);
 	xfs_log_sb(tp);
-	xfs_trans_bhold(tp, bp);
-	if (update_rtsb) {
-		rtsb_bp = xfs_log_rtsb(tp, bp);
-		if (rtsb_bp)
-			xfs_trans_bhold(tp, rtsb_bp);
-	}
+	if (update_rtsb)
+		xfs_log_rtsb(tp, xfs_trans_getsb(tp));
 	xfs_trans_set_sync(tp);
 	error = xfs_trans_commit(tp);
 	if (error)
-		goto out;
-	/*
-	 * write out the sb buffer to get the changes to disk
-	 */
-	error = xfs_bwrite(bp);
-	if (!error && rtsb_bp)
-		error = xfs_bwrite(rtsb_bp);
-out:
-	if (rtsb_bp)
-		xfs_buf_relse(rtsb_bp);
-	xfs_buf_relse(bp);
+		return error;
+
+	/* Re-acquire and write the sb and rtsb to disk. */
+	xfs_buf_lock(mp->m_sb_bp);
+	error = xfs_bwrite(mp->m_sb_bp);
+	xfs_buf_unlock(mp->m_sb_bp);
+	if (error)
+		return error;
+
+	if (update_rtsb && mp->m_rtsb_bp) {
+		xfs_buf_lock(mp->m_rtsb_bp);
+		error = xfs_bwrite(mp->m_rtsb_bp);
+		xfs_buf_unlock(mp->m_rtsb_bp);
+	}
+
 	return error;
 }
 
-- 
2.43.0

Re: [PATCH v3] xfs: don't hold buffer locks across sync transaction commit in xfs_sync_sb_buf

[Carlos Maiolino]

On Fri, 31 Jul 2026 11:10:10 +0800, Yun Zhou wrote:
> xfs_sync_sb_buf() holds sb/rtsb buffer locks across a synchronous
> xfs_trans_commit(), which flushes the CIL push workqueue internally.
> If shutdown occurs during the CIL push, xfs_buf_item_unpin() needs to
> lock these buffers to fail them, causing a deadlock:
> 
>   setlabel:          holds buf lock -> flush_workqueue(xfs-cil)
>   CIL push worker:   xfs_buf_item_unpin -> xfs_buf_lock(same buf)
> 
> [...]

Applied to for-next, thanks!

[1/1] xfs: don't hold buffer locks across sync transaction commit in xfs_sync_sb_buf
      commit: 41a28c865d1d5843f8cb9e0af17a8f4d9e2961ff

Best regards,
-- 
Carlos Maiolino <cem@kernel.org>

Re: [PATCH v3] xfs: don't hold buffer locks across sync transaction commit in xfs_sync_sb_buf

[Darrick J. Wong]

On Fri, Jul 31, 2026 at 11:10:10AM +0800, Yun Zhou wrote:
> xfs_sync_sb_buf() holds sb/rtsb buffer locks across a synchronous
> xfs_trans_commit(), which flushes the CIL push workqueue internally.
> If shutdown occurs during the CIL push, xfs_buf_item_unpin() needs to
> lock these buffers to fail them, causing a deadlock:
> 
>   setlabel:          holds buf lock -> flush_workqueue(xfs-cil)
>   CIL push worker:   xfs_buf_item_unpin -> xfs_buf_lock(same buf)
> 
> Remove the xfs_trans_bhold() calls so that commit releases the buffer
> locks normally.  After the sync commit, re-acquire the buffers via
> mp->m_sb_bp / mp->m_rtsb_bp for the on-disk writeback.
> 
> Fixes: f7664b31975b ("xfs: implement online get/set fs label")
> Reported-by: syzbot+837bcd54843dd6262f2f@syzkaller.appspotmail.com
> Closes: https://syzkaller.appspot.com/bug?extid=837bcd54843dd6262f2f
> Cc: stable@vger.kernel.org
> Signed-off-by: Yun Zhou <yun.zhou@windriver.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> ---
> v3:
>  - Drop xfs_buf_hold/xfs_buf_relse, use lock/unlock directly (Christoph).
> 
> v2:
>  - Remove the bp variable and pass xfs_trans_getsb(tp) directly to
>    xfs_log_rtsb() to fix compilation warnings when CONFIG_XFS_RT=n.
>  - Convert xfs_log_rtsb() stub from macro to inline function to avoid
>    the need for (void) casting (Christoph).
> ---
>  fs/xfs/libxfs/xfs_rtgroup.h |  6 +++++-
>  fs/xfs/libxfs/xfs_sb.c      | 37 +++++++++++++++++--------------------
>  2 files changed, 22 insertions(+), 21 deletions(-)
> 
> diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
> index c0b9f9f2c413..fca2eb74908c 100644
> --- a/fs/xfs/libxfs/xfs_rtgroup.h
> +++ b/fs/xfs/libxfs/xfs_rtgroup.h
> @@ -359,7 +359,11 @@ static inline int xfs_initialize_rtgroups(struct xfs_mount *mp,
>  # define xfs_rtgroup_unlock(rtg, gf)		((void)0)
>  # define xfs_rtgroup_trans_join(tp, rtg, gf)	((void)0)
>  # define xfs_update_rtsb(bp, sb_bp)	((void)0)
> -# define xfs_log_rtsb(tp, sb_bp)	(NULL)
> +static inline struct xfs_buf *xfs_log_rtsb(struct xfs_trans *tp,
> +		const struct xfs_buf *sb_bp)
> +{
> +	return NULL;
> +}
>  # define xfs_rtgroup_get_geometry(rtg, rgeo)	(-EOPNOTSUPP)
>  #endif /* CONFIG_XFS_RT */
>  
> diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
> index 47322adb7690..2664728f2d8f 100644
> --- a/fs/xfs/libxfs/xfs_sb.c
> +++ b/fs/xfs/libxfs/xfs_sb.c
> @@ -1470,36 +1470,33 @@ xfs_sync_sb_buf(
>  	bool			update_rtsb)
>  {
>  	struct xfs_trans	*tp;
> -	struct xfs_buf		*bp;
> -	struct xfs_buf		*rtsb_bp = NULL;
>  	int			error;
>  
>  	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_sb, 0, 0, 0, &tp);
>  	if (error)
>  		return error;
>  
> -	bp = xfs_trans_getsb(tp);
>  	xfs_log_sb(tp);
> -	xfs_trans_bhold(tp, bp);
> -	if (update_rtsb) {
> -		rtsb_bp = xfs_log_rtsb(tp, bp);
> -		if (rtsb_bp)
> -			xfs_trans_bhold(tp, rtsb_bp);
> -	}
> +	if (update_rtsb)
> +		xfs_log_rtsb(tp, xfs_trans_getsb(tp));
>  	xfs_trans_set_sync(tp);
>  	error = xfs_trans_commit(tp);
>  	if (error)
> -		goto out;
> -	/*
> -	 * write out the sb buffer to get the changes to disk
> -	 */
> -	error = xfs_bwrite(bp);
> -	if (!error && rtsb_bp)
> -		error = xfs_bwrite(rtsb_bp);
> -out:
> -	if (rtsb_bp)
> -		xfs_buf_relse(rtsb_bp);
> -	xfs_buf_relse(bp);
> +		return error;
> +
> +	/* Re-acquire and write the sb and rtsb to disk. */
> +	xfs_buf_lock(mp->m_sb_bp);

FYI, this causes porting problems to xfsprogs' libxfs because userspace
doesn't have m_sb_bp or m_rtsb_bp pointers in struct xfs_mount.  It's
not a big deal to add them, but if anyone ever wants to call
xfs_sync_sb_buf then we're going to have to figure out when to populate
those pointers.

--D

> +	error = xfs_bwrite(mp->m_sb_bp);
> +	xfs_buf_unlock(mp->m_sb_bp);
> +	if (error)
> +		return error;
> +
> +	if (update_rtsb && mp->m_rtsb_bp) {
> +		xfs_buf_lock(mp->m_rtsb_bp);
> +		error = xfs_bwrite(mp->m_rtsb_bp);
> +		xfs_buf_unlock(mp->m_rtsb_bp);
> +	}
> +
>  	return error;
>  }
>  
> -- 
> 2.43.0
> 
>