From: Christoph Hellwig <hch@lst.de>
Date: Thu, 2 Nov 2017 21:28:51 +0300
Subject: nvme: move the dying queue check from cancel to completion
Patch-mainline: v4.15-rc1
Git-commit: e54b064cb24c8268252336ccdd6523e08c0dcbde
References: FATE#323952, FATE#322506
With multipath we don't want a hard DNR bit on a request that is cancelled
by a controller reset, but instead want to be able to retry it on another
patch. To archive this don't always set the DNR bit when the queue is
dying in nvme_cancel_request, but defer that decision to
nvme_req_needs_retry. Note that it applies to any command there and not
just cancelled commands, but one the queue is dying that is the right
thing to do anyway.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Acked-by: Johannes Thumshirn <jthumshirn@suse.de>
---
drivers/nvme/host/core.c | 9 +++------
1 file changed, 3 insertions(+), 6 deletions(-)
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -172,6 +172,8 @@ static inline bool nvme_req_needs_retry(
return false;
if (nvme_req(req)->retries >= nvme_max_retries)
return false;
+ if (blk_queue_dying(req->q))
+ return false;
return true;
}
@@ -189,18 +191,13 @@ EXPORT_SYMBOL_GPL(nvme_complete_rq);
void nvme_cancel_request(struct request *req, void *data, bool reserved)
{
- int status;
-
if (!blk_mq_request_started(req))
return;
dev_dbg_ratelimited(((struct nvme_ctrl *) data)->device,
"Cancelling I/O %d", req->tag);
- status = NVME_SC_ABORT_REQ;
- if (blk_queue_dying(req->q))
- status |= NVME_SC_DNR;
- nvme_req(req)->status = status;
+ nvme_req(req)->status = NVME_SC_ABORT_REQ;
blk_mq_complete_request(req);
}