Messages in this thread | | | Date | Tue, 2 Jun 2009 08:43:07 +0200 | From | Jens Axboe <> | Subject | Re: [PATCH block#for-2.6.31] block: fix a possible oops on elv_abort_queue() |
| |
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
| |