[PATCH] nvme-multipath: do not reset controller on unknown status

[Hannes Reinecke <hare@suse.de>]

We're seeing occasional controller resets during straight I/O,
but only when multipath is active.
The problem here is the nvme-multipath will reset the controller
on every unknown status, which really is an odd behaviour, seeing
that the host already received a perfectly good status; it's just
that it's not smart enough to understand it.
And resetting wouldn't help at all; the error status will continue
to be received.
So we should rather pass up any unknown error to the generic
routines and let them deal with this situation.

Signed-off-by: Hannes Reinecke <hare@suse.de>
Cc: John Managhini <john.meneghini@netapp.com>
---
 drivers/nvme/host/core.c      |  4 ++--
 drivers/nvme/host/multipath.c | 18 ++++++++++--------
 drivers/nvme/host/nvme.h      |  2 +-
 3 files changed, 13 insertions(+), 11 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 5dc32b72e7fa..edb081781ae7 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -293,8 +293,8 @@ void nvme_complete_rq(struct request *req)
 	if (unlikely(status != BLK_STS_OK && nvme_req_needs_retry(req))) {
 		if ((req->cmd_flags & REQ_NVME_MPATH) &&
 		    blk_path_error(status)) {
-			nvme_failover_req(req);
-			return;
+			if (nvme_failover_req(req))
+				return;
 		}
 
 		if (!blk_queue_dying(req->q)) {
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 797c18337d96..71e8acae78eb 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -64,16 +64,16 @@ void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 	}
 }
 
-void nvme_failover_req(struct request *req)
+bool nvme_failover_req(struct request *req)
 {
 	struct nvme_ns *ns = req->q->queuedata;
 	u16 status = nvme_req(req)->status;
 	unsigned long flags;
+	bool handled = false;
 
 	spin_lock_irqsave(&ns->head->requeue_lock, flags);
 	blk_steal_bios(&ns->head->requeue_list, req);
 	spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
-	blk_mq_end_request(req, 0);
 
 	switch (status & 0x7ff) {
 	case NVME_SC_ANA_TRANSITION:
@@ -88,11 +88,13 @@ void nvme_failover_req(struct request *req)
 		 * mark the the path as pending and kick of a re-read of the ANA
 		 * log page ASAP.
 		 */
+		blk_mq_end_request(req, 0);
 		nvme_mpath_clear_current_path(ns);
 		if (ns->ctrl->ana_log_buf) {
 			set_bit(NVME_NS_ANA_PENDING, &ns->flags);
 			queue_work(nvme_wq, &ns->ctrl->ana_work);
 		}
+		handled = true;
 		break;
 	case NVME_SC_HOST_PATH_ERROR:
 	case NVME_SC_HOST_ABORTED_CMD:
@@ -100,18 +102,18 @@ void nvme_failover_req(struct request *req)
 		 * Temporary transport disruption in talking to the controller.
 		 * Try to send on a new path.
 		 */
+		blk_mq_end_request(req, 0);
 		nvme_mpath_clear_current_path(ns);
+		handled = true;
 		break;
 	default:
-		/*
-		 * Reset the controller for any non-ANA error as we don't know
-		 * what caused the error.
-		 */
-		nvme_reset_ctrl(ns->ctrl);
+		/* Delegate to common error handling */
 		break;
 	}
 
-	kblockd_schedule_work(&ns->head->requeue_work);
+	if (handled)
+		kblockd_schedule_work(&ns->head->requeue_work);
+	return handled;
 }
 
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 1024fec7914c..7e28084f71af 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -550,7 +550,7 @@ void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys);
 void nvme_mpath_start_freeze(struct nvme_subsystem *subsys);
 void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 			struct nvme_ctrl *ctrl, int *flags);
-void nvme_failover_req(struct request *req);
+bool nvme_failover_req(struct request *req);
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
 int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head);
 void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id);
-- 
2.16.4


_______________________________________________
linux-nvme mailing list
linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme