* [PATCH block#for-2.6.31] block: fix a possible oops on elv_abort_queue()
@ 2009-06-01 23:42 Kiyoshi Ueda
2009-06-02 6:43 ` Jens Axboe
0 siblings, 1 reply; 2+ messages in thread
From: Kiyoshi Ueda @ 2009-06-01 23:42 UTC (permalink / raw)
To: Jens Axboe; +Cc: linux-kernel, Jun'ichi Nomura, k-ueda
Hi Jens,
I found one more mis-conversion to the 'request is always dequeued
when completing' model in elv_abort_queue() during code inspection.
Although I haven't hit any problem caused by this mis-conversion yet
and just done compile/boot test, please apply if you have no problem.
Request must be dequeued when it completes.
However, elv_abort_queue() completes requests without dequeueing.
This will cause oops in the __blk_end_request_all().
This patch fixes the oops.
Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com>
Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
Cc: Jens Axboe <jens.axboe@oracle.com>
---
block/elevator.c | 5 +++++
1 file changed, 5 insertions(+)
Index: linux-2.6-block/block/elevator.c
===================================================================
--- linux-2.6-block.orig/block/elevator.c
+++ linux-2.6-block/block/elevator.c
@@ -813,6 +813,11 @@ void elv_abort_queue(struct request_queu
rq = list_entry_rq(q->queue_head.next);
rq->cmd_flags |= REQ_QUIET;
trace_block_rq_abort(q, rq);
+ /*
+ * Mark this request as started so we don't trigger
+ * any debug logic in the end I/O path.
+ */
+ blk_start_request(rq);
__blk_end_request_all(rq, -EIO);
}
}
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: [PATCH block#for-2.6.31] block: fix a possible oops on elv_abort_queue()
2009-06-01 23:42 [PATCH block#for-2.6.31] block: fix a possible oops on elv_abort_queue() Kiyoshi Ueda
@ 2009-06-02 6:43 ` Jens Axboe
0 siblings, 0 replies; 2+ messages in thread
From: Jens Axboe @ 2009-06-02 6:43 UTC (permalink / raw)
To: Kiyoshi Ueda; +Cc: linux-kernel, Jun'ichi Nomura
On Tue, Jun 02 2009, Kiyoshi Ueda wrote:
> Hi Jens,
>
> I found one more mis-conversion to the 'request is always dequeued
> when completing' model in elv_abort_queue() during code inspection.
> Although I haven't hit any problem caused by this mis-conversion yet
> and just done compile/boot test, please apply if you have no problem.
>
>
> Request must be dequeued when it completes.
> However, elv_abort_queue() completes requests without dequeueing.
> This will cause oops in the __blk_end_request_all().
> This patch fixes the oops.
Thanks, applied!
> Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com>
> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com>
> Cc: Jens Axboe <jens.axboe@oracle.com>
> ---
> block/elevator.c | 5 +++++
> 1 file changed, 5 insertions(+)
>
> Index: linux-2.6-block/block/elevator.c
> ===================================================================
> --- linux-2.6-block.orig/block/elevator.c
> +++ linux-2.6-block/block/elevator.c
> @@ -813,6 +813,11 @@ void elv_abort_queue(struct request_queu
> rq = list_entry_rq(q->queue_head.next);
> rq->cmd_flags |= REQ_QUIET;
> trace_block_rq_abort(q, rq);
> + /*
> + * Mark this request as started so we don't trigger
> + * any debug logic in the end I/O path.
> + */
> + blk_start_request(rq);
> __blk_end_request_all(rq, -EIO);
> }
> }
--
Jens Axboe
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2009-06-02 6:43 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2009-06-01 23:42 [PATCH block#for-2.6.31] block: fix a possible oops on elv_abort_queue() Kiyoshi Ueda
2009-06-02 6:43 ` Jens Axboe
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox