From: John Meneghini johnm@netapp.com
[ Upstream commit 764e9332098c0e60251386a507fe46ac91276120 ]
The nvme multipath error handling defaults to controller reset if the error is unknown. There are, however, no existing nvme status codes that indicate a reset should be used, and resetting causes unnecessary disruption to the rest of IO.
Change nvme's error handling to first check if failover should happen. If not, let the normal error handling take over rather than reset the controller.
Based-on-a-patch-by: Christoph Hellwig hch@lst.de Reviewed-by: Hannes Reinecke hare@suse.de Signed-off-by: John Meneghini johnm@netapp.com Signed-off-by: Keith Busch kbusch@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/core.c | 5 +---- drivers/nvme/host/multipath.c | 21 +++++++++------------ drivers/nvme/host/nvme.h | 5 +++-- 3 files changed, 13 insertions(+), 18 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 0d60f2f8f3eec..4b182ac15687e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -255,11 +255,8 @@ void nvme_complete_rq(struct request *req) trace_nvme_complete_rq(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); + if ((req->cmd_flags & REQ_NVME_MPATH) && nvme_failover_req(req)) return; - }
if (!blk_queue_dying(req->q)) { nvme_req(req)->retries++; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 2e63c1106030b..e71075338ff5c 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -73,17 +73,12 @@ 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;
- 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: case NVME_SC_ANA_INACCESSIBLE: @@ -111,15 +106,17 @@ void nvme_failover_req(struct request *req) nvme_mpath_clear_current_path(ns); break; default: - /* - * Reset the controller for any non-ANA error as we don't know - * what caused the error. - */ - nvme_reset_ctrl(ns->ctrl); - break; + /* This was a non-ANA error so follow the normal error path. */ + return 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); + kblockd_schedule_work(&ns->head->requeue_work); + return true; }
void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl) diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index cc4273f119894..31c1496f938fb 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -477,7 +477,7 @@ 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); @@ -521,8 +521,9 @@ static inline void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns, sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance); }
-static inline void nvme_failover_req(struct request *req) +static inline bool nvme_failover_req(struct request *req) { + return false; } static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl) {