NVMe: Use a retryable error code on reset

A negative status has the "do not retry" bit set, which makes it not
retryable.  Use a fake status that can potentially be retried on reset.

An aborted command's status is overridden by the timeout handler so
that it won't be retried, which is necessary to keep initialization from
getting into a reset loop.

Signed-off-by: Keith Busch <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>
This commit is contained in:
Keith Busch 2016-01-04 09:10:56 -07:00 • committed by Jens Axboe
commit 1d49c38c48

View file

@ -1017,7 +1017,7 @@ static void nvme_cancel_queue_ios(struct request *req, void *data, bool reserved
dev_warn(nvmeq->q_dmadev,
"Cancelling I/O %d QID %d\n", req->tag, nvmeq->qid);
status = NVME_SC_CANCELLED;
status = NVME_SC_ABORT_REQ;
if (blk_queue_dying(req->q))
status |= NVME_SC_DNR;
blk_mq_complete_request(req, status);