nvme-multipath: support io stats on the mpath device

Our mpath stack device is just a shim that selects a bottom namespace
and submits the bio to it without any fancy splitting. This also means
that we don't clone the bio or have any context to the bio beyond
submission. However it really sucks that we don't see the mpath device
io stats.

Given that the mpath device can't do that without adding some context
to it, we let the bottom device do it on its behalf (somewhat similar
to the approach taken in nvme_trace_bio_complete).

When the IO starts, we account the request for multipath IO stats using
REQ_NVME_MPATH_IO_STATS nvme_request flag to avoid queue io stats disable
in the middle of the request.

Signed-off-by: Sagi Grimberg <[email protected]>
Signed-off-by: Christoph Hellwig <[email protected]>
Reviewed-by: Keith Busch <[email protected]>

Author: sagigrimberg

drivers/nvme/host/core.c

@@ -384,6 +384,8 @@ static inline void nvme_end_req(struct request *req)
 		nvme_log_error(req);
 	nvme_end_req_zoned(req);
 	nvme_trace_bio_complete(req);
+	if (req->cmd_flags & REQ_NVME_MPATH)
+		nvme_mpath_end_request(req);
 	blk_mq_end_request(req, status);
 }
 

drivers/nvme/host/multipath.c

@@ -114,6 +114,31 @@ void nvme_failover_req(struct request *req)
 	kblockd_schedule_work(&ns->head->requeue_work);
 }
 
+void nvme_mpath_start_request(struct request *rq)
+{
+	struct nvme_ns *ns = rq->q->queuedata;
+	struct gendisk *disk = ns->head->disk;
+
+	if (!blk_queue_io_stat(disk->queue) || blk_rq_is_passthrough(rq))
+		return;
+
+	nvme_req(rq)->flags |= NVME_MPATH_IO_STATS;
+	nvme_req(rq)->start_time = bdev_start_io_acct(disk->part0,
+					blk_rq_bytes(rq) >> SECTOR_SHIFT,
+					req_op(rq), jiffies);
+}
+EXPORT_SYMBOL_GPL(nvme_mpath_start_request);
+
+void nvme_mpath_end_request(struct request *rq)
+{
+	struct nvme_ns *ns = rq->q->queuedata;
+
+	if (!(nvme_req(rq)->flags & NVME_MPATH_IO_STATS))
+		return;
+	bdev_end_io_acct(ns->head->disk->part0, req_op(rq),
+		nvme_req(rq)->start_time);
+}
+
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
@@ -503,6 +528,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, head->disk->queue);
 	blk_queue_flag_set(QUEUE_FLAG_NOWAIT, head->disk->queue);
+	blk_queue_flag_set(QUEUE_FLAG_IO_STAT, head->disk->queue);
 	/*
 	 * This assumes all controllers that refer to a namespace either
 	 * support poll queues or not.  That is not a strict guarantee,

drivers/nvme/host/nvme.h

@@ -162,6 +162,9 @@ struct nvme_request {
 	u8			retries;
 	u8			flags;
 	u16			status;
+#ifdef CONFIG_NVME_MULTIPATH
+	unsigned long		start_time;
+#endif
 	struct nvme_ctrl	*ctrl;
 };
 
@@ -173,6 +176,7 @@ struct nvme_request {
 enum {
 	NVME_REQ_CANCELLED		= (1 << 0),
 	NVME_REQ_USERCMD		= (1 << 1),
+	NVME_MPATH_IO_STATS		= (1 << 2),
 };
 
 static inline struct nvme_request *nvme_req(struct request *req)
@@ -882,6 +886,8 @@ bool nvme_mpath_clear_current_path(struct nvme_ns *ns);
 void nvme_mpath_revalidate_paths(struct nvme_ns *ns);
 void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl);
 void nvme_mpath_shutdown_disk(struct nvme_ns_head *head);
+void nvme_mpath_start_request(struct request *rq);
+void nvme_mpath_end_request(struct request *rq);
 
 static inline void nvme_trace_bio_complete(struct request *req)
 {
@@ -967,6 +973,12 @@ static inline void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
 static inline void nvme_mpath_default_iopolicy(struct nvme_subsystem *subsys)
 {
 }
+static inline void nvme_mpath_start_request(struct request *rq)
+{
+}
+static inline void nvme_mpath_end_request(struct request *rq)
+{
+}
 #endif /* CONFIG_NVME_MULTIPATH */
 
 int nvme_revalidate_zones(struct nvme_ns *ns);
@@ -1014,6 +1026,8 @@ static inline void nvme_hwmon_exit(struct nvme_ctrl *ctrl)
 
 static inline void nvme_start_request(struct request *rq)
 {
+	if (rq->cmd_flags & REQ_NVME_MPATH)
+		nvme_mpath_start_request(rq);
 	blk_mq_start_request(rq);
 }