diff mbox series

[01/36] libxfs: fix repair deadlock due to failed inode flushes.

Message ID 155259742930.31886.16675099707553706623.stgit@magnolia (mailing list archive)
State Accepted, archived
Headers show
Series xfsprogs-5.0: fix various problems | expand

Commit Message

Darrick J. Wong March 14, 2019, 9:03 p.m. UTC
From: Dave Chinner <dchinner@redhat.com>

If inode_item_done() fails to flush an inode after we've grabbed a
reference to the underlying buffer during a transaction commit, we
fail to put the buffer and hence leak it. We then deadlock on the
next lookup ofthe inode buffer as it is still locked and no-one owns
it.

To fix it, put the buffer on error so that it gets unlocked and
can be recovered appropriately in a later phase of repair.

Reported-by: Arkadiusz Miskiewicz <arekm@maven.pl>
Fixes: d15188a1ec14 ("xfs: rework the inline directory verifiers")
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 libxfs/trans.c |   17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

Comments

Allison Henderson March 15, 2019, 10:01 p.m. UTC | #1
Looks good.

Reviewed-by: Allison Henderson <allison.henderson@oracle.com>

On 3/14/19 2:03 PM, Darrick J. Wong wrote:
> From: Dave Chinner <dchinner@redhat.com>
> 
> If inode_item_done() fails to flush an inode after we've grabbed a
> reference to the underlying buffer during a transaction commit, we
> fail to put the buffer and hence leak it. We then deadlock on the
> next lookup ofthe inode buffer as it is still locked and no-one owns
> it.
> 
> To fix it, put the buffer on error so that it gets unlocked and
> can be recovered appropriately in a later phase of repair.
> 
> Reported-by: Arkadiusz Miskiewicz <arekm@maven.pl>
> Fixes: d15188a1ec14 ("xfs: rework the inline directory verifiers")
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
> ---
>   libxfs/trans.c |   17 +++++++++++++----
>   1 file changed, 13 insertions(+), 4 deletions(-)
> 
> 
> diff --git a/libxfs/trans.c b/libxfs/trans.c
> index 46ff8b4a..10a35dd4 100644
> --- a/libxfs/trans.c
> +++ b/libxfs/trans.c
> @@ -824,8 +824,10 @@ _("Transaction block reservation exceeded! %u > %u\n"),
>   
>   /*
>    * Transaction commital code follows (i.e. write to disk in libxfs)
> + *
> + * XXX (dgc): should failure to flush the inode (e.g. due to uncorrected
> + * corruption) result in transaction commit failure w/ EFSCORRUPTED?
>    */
> -
>   static void
>   inode_item_done(
>   	xfs_inode_log_item_t	*iip)
> @@ -856,17 +858,24 @@ inode_item_done(
>   		return;
>   	}
>   
> +	/*
> +	 * Flush the inode and disassociate it from the transaction regardless
> +	 * of whether the flush succeed or not. If we fail the flush, make sure
> +	 * we still release the buffer reference we currently hold.
> +	 */
>   	bp->b_log_item = iip;
>   	error = libxfs_iflush_int(ip, bp);
> +	ip->i_transp = NULL;	/* disassociate from transaction */
> +	bp->b_log_item = NULL;	/* remove log item */
> +	bp->b_transp = NULL;	/* remove xact ptr */
> +
>   	if (error) {
>   		fprintf(stderr, _("%s: warning - iflush_int failed (%d)\n"),
>   			progname, error);
> +		libxfs_putbuf(bp);
>   		return;
>   	}
>   
> -	ip->i_transp = NULL;	/* disassociate from transaction */
> -	bp->b_log_item = NULL;	/* remove log item */
> -	bp->b_transp = NULL;	/* remove xact ptr */
>   	libxfs_writebuf(bp, 0);
>   #ifdef XACT_DEBUG
>   	fprintf(stderr, "flushing dirty inode %llu, buffer %p\n",
>
diff mbox series

Patch

diff --git a/libxfs/trans.c b/libxfs/trans.c
index 46ff8b4a..10a35dd4 100644
--- a/libxfs/trans.c
+++ b/libxfs/trans.c
@@ -824,8 +824,10 @@  _("Transaction block reservation exceeded! %u > %u\n"),
 
 /*
  * Transaction commital code follows (i.e. write to disk in libxfs)
+ *
+ * XXX (dgc): should failure to flush the inode (e.g. due to uncorrected
+ * corruption) result in transaction commit failure w/ EFSCORRUPTED?
  */
-
 static void
 inode_item_done(
 	xfs_inode_log_item_t	*iip)
@@ -856,17 +858,24 @@  inode_item_done(
 		return;
 	}
 
+	/*
+	 * Flush the inode and disassociate it from the transaction regardless
+	 * of whether the flush succeed or not. If we fail the flush, make sure
+	 * we still release the buffer reference we currently hold.
+	 */
 	bp->b_log_item = iip;
 	error = libxfs_iflush_int(ip, bp);
+	ip->i_transp = NULL;	/* disassociate from transaction */
+	bp->b_log_item = NULL;	/* remove log item */
+	bp->b_transp = NULL;	/* remove xact ptr */
+
 	if (error) {
 		fprintf(stderr, _("%s: warning - iflush_int failed (%d)\n"),
 			progname, error);
+		libxfs_putbuf(bp);
 		return;
 	}
 
-	ip->i_transp = NULL;	/* disassociate from transaction */
-	bp->b_log_item = NULL;	/* remove log item */
-	bp->b_transp = NULL;	/* remove xact ptr */
 	libxfs_writebuf(bp, 0);
 #ifdef XACT_DEBUG
 	fprintf(stderr, "flushing dirty inode %llu, buffer %p\n",