cfq-iosched: fix race in cfq_set_request()

We need to hold the queue lock over the reference increment,
it's not atomic anymore.

Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
This commit is contained in:
Jens Axboe 2011-03-07 08:59:06 +01:00
parent da52777000
commit 93803e0140

View File

@ -3675,12 +3675,11 @@ new_queue:
cfqq->allocated[rw]++;
spin_unlock_irqrestore(q->queue_lock, flags);
cfqq->ref++;
rq->elevator_private[0] = cic;
rq->elevator_private[1] = cfqq;
rq->elevator_private[2] = cfq_ref_get_cfqg(cfqq->cfqg);
spin_unlock_irqrestore(q->queue_lock, flags);
return 0;
queue_fail: