[dm-devel] [PATCH v2 3/4] nvme: introduce FAILUP handling for REQ_FAILFAST_TRANSPORT

[Mike Snitzer]

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 allow failover of requests marked with either
REQ_NVME_MPATH or REQ_FAILFAST_TRANSPORT. This allows such requests
to be given a disposition of either FAILOVER or FAILUP respectively.
FAILUP handling ensures a retryable error is returned up from NVMe.

Introduce nvme_failup_req() for use in nvme_complete_rq() if
nvme_decide_disposition() returns FAILUP. nvme_failup_req() ensures
the 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_failup_req().

Signed-off-by: Mike Snitzer <snitzer at redhat.com>
---
 drivers/nvme/host/core.c | 31 ++++++++++++++++++++++++++-----
 1 file changed, 26 insertions(+), 5 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 4134cf3c7e48..10375197dd53 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -299,6 +299,7 @@ enum nvme_disposition {
 	COMPLETE,
 	RETRY,
 	FAILOVER,
+	FAILUP,
 };
 
 static inline enum nvme_disposition nvme_decide_disposition(struct request *req)
@@ -318,10 +319,11 @@ static inline enum nvme_disposition nvme_decide_disposition(struct request *req)
 	    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;
+			return (req->cmd_flags & REQ_NVME_MPATH) ?
+				FAILOVER : FAILUP;
 	} else {
 		if (blk_queue_dying(req->q))
 			return COMPLETE;
@@ -330,10 +332,8 @@ static inline enum nvme_disposition nvme_decide_disposition(struct request *req)
 	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,
@@ -343,6 +343,24 @@ static inline void nvme_end_req(struct request *req)
 	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 void nvme_failup_req(struct request *req)
+{
+	blk_status_t status = nvme_error_status(nvme_req(req)->status);
+
+	if (WARN_ON_ONCE(!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;
+	}
+
+	__nvme_end_req(req, status);
+}
+
 void nvme_complete_rq(struct request *req)
 {
 	trace_nvme_complete_rq(req);
@@ -361,6 +379,9 @@ void nvme_complete_rq(struct request *req)
 	case FAILOVER:
 		nvme_failover_req(req);
 		return;
+	case FAILUP:
+		nvme_failup_req(req);
+		return;
 	}
 }
 EXPORT_SYMBOL_GPL(nvme_complete_rq);
-- 
2.15.0