block: fix a possible oops on elv_abort_queue()
PATCH 1/1 block: fix a possible oops on elv_abort_queue()
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.
--- block/elevator.c | 5 +++++ 1 file changed, 5 insertions(+)
block/elevator.c +5 -0
@@ -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
AppliedQuoted 8 lines · Kiyoshi 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.
Quoted 4 lines
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!
Quoted 23 lines
Signed-off-by Kiyoshi Ueda <[email protected]>Signed-off-by Jun'ichi Nomura <[email protected]>Cc Jens Axboe <[email protected]>--- block/elevator.c | 5 +++++ 1 file changed, 5 insertions(+)Index:
linux-2.6-block/block/elevator.c
===================================================================block/elevator.c +5
-0@@ -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 ); } }
Signature · 1 line
Jens Axboe