[dm-devel] nvme: update failover handling to work with REQ_FAILFAST_TRANSPORT

[Mike Snitzer]

BZ: 1948690
Upstream Status: RHEL-only

Signed-off-by: Mike Snitzer <snitzer at redhat.com>

rhel-8.git commit f8fb6ea1226e2abc525c88da13b346118d548eea
Author: Mike Snitzer <snitzer at redhat.com>
Date:   Tue Aug 25 21:52:46 2020 -0400

    [nvme] nvme: update failover handling to work with REQ_FAILFAST_TRANSPORT
    
    Message-id: <20200825215248.2291-9-snitzer at redhat.com>
    Patchwork-id: 325177
    Patchwork-instance: patchwork
    O-Subject: [RHEL8.3 PATCH 08/10] nvme: update failover handling to work with REQ_FAILFAST_TRANSPORT
    Bugzilla: 1843515
    RH-Acked-by: David Milburn <dmilburn at redhat.com>
    RH-Acked-by: Gopal Tiwari <gtiwari at redhat.com>
    RH-Acked-by: Ewan Milne <emilne at redhat.com>
    
    BZ: 1843515
    Upstream Status: RHEL-only
    
    If REQ_FAILFAST_TRANSPORT is set it means the driver should not retry
    IO that completed with transport errors.  REQ_FAILFAST_TRANSPORT is
    set by multipathing software (e.g. dm-multipath) before it issues IO.
    Update NVMe to prepare for failover of requests marked with either
    REQ_NVME_MPATH or REQ_FAILFAST_TRANSPORT.  This allows such requests
    to be given a disposition of FAILOVER.
    
    Introduce nvme_end_req_with_failover() for use in nvme_complete_rq()
    if REQ_NVME_MPATH isn't set.  nvme_end_req_with_failover() ensures
    request is completed with a retryable IO error when appropriate.
    __nvme_end_req() was factored out for use by both nvme_end_req() and
    nvme_end_req_with_failover().
    
    Signed-off-by: Mike Snitzer <snitzer at redhat.com>
    Signed-off-by: Frantisek Hrbata <fhrbata at redhat.com>

---
 drivers/nvme/host/core.c |   33 ++++++++++++++++++++++++++++-----
 1 file changed, 28 insertions(+), 5 deletions(-)

Index: linux-rhel9/drivers/nvme/host/core.c
===================================================================
--- linux-rhel9.orig/drivers/nvme/host/core.c
+++ linux-rhel9/drivers/nvme/host/core.c
@@ -311,7 +311,7 @@ static inline enum nvme_disposition nvme
 	    nvme_req(req)->retries >= nvme_max_retries)
 		return COMPLETE;
 
-	if (req->cmd_flags & REQ_NVME_MPATH) {
+	if (req->cmd_flags & (REQ_NVME_MPATH | REQ_FAILFAST_TRANSPORT)) {
 		if (nvme_is_path_error(nvme_req(req)->status) ||
 		    blk_queue_dying(req->q))
 			return FAILOVER;
@@ -323,10 +323,8 @@ static inline enum nvme_disposition nvme
 	return RETRY;
 }
 
-static inline void nvme_end_req(struct request *req)
+static inline void __nvme_end_req(struct request *req, blk_status_t status)
 {
-	blk_status_t status = nvme_error_status(nvme_req(req)->status);
-
 	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
 	    req_op(req) == REQ_OP_ZONE_APPEND)
 		req->__sector = nvme_lba_to_sect(req->q->queuedata,
@@ -336,6 +334,28 @@ static inline void nvme_end_req(struct r
 	blk_mq_end_request(req, status);
 }
 
+static inline void nvme_end_req(struct request *req)
+{
+	__nvme_end_req(req, nvme_error_status(nvme_req(req)->status));
+}
+
+static inline void nvme_end_req_with_failover(struct request *req)
+{
+	u16 nvme_status = nvme_req(req)->status;
+	blk_status_t status = nvme_error_status(nvme_status);
+
+	if (unlikely(nvme_status & NVME_SC_DNR))
+		goto out;
+
+	if (!blk_path_error(status)) {
+		pr_debug("Request meant for failover but blk_status_t (errno=%d) was not retryable.\n",
+			 blk_status_to_errno(status));
+		status = BLK_STS_IOERR;
+	}
+out:
+	__nvme_end_req(req, status);
+}
+
 void nvme_complete_rq(struct request *req)
 {
 	trace_nvme_complete_rq(req);
@@ -352,7 +372,10 @@ void nvme_complete_rq(struct request *re
 		nvme_retry_req(req);
 		return;
 	case FAILOVER:
-		nvme_failover_req(req);
+		if (req->cmd_flags & REQ_NVME_MPATH)
+			nvme_failover_req(req);
+		else
+			nvme_end_req_with_failover(req);
 		return;
 	}
 }