scsi: blk-mq: Return budget token from .get_budget callback

SCSI uses a global atomic variable to track queue depth for each
LUN/request queue.

This doesn't scale well when there are lots of CPU cores and the disk is
very fast. It has been observed that IOPS is affected a lot by tracking
queue depth via sdev->device_busy in the I/O path.

Return budget token from .get_budget callback. The budget token can be
passed to driver so that we can replace the atomic variable with
sbitmap_queue and alleviate the scaling problems that way.

Link: https://lore.kernel.org/r/20210122023317.687987-9-ming.lei@redhat.com
Cc: Omar Sandoval <osandov@fb.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Sumanesh Samanta <sumanesh.samanta@broadcom.com>
Cc: Ewan D. Milne <emilne@redhat.com>
Tested-by: Sumanesh Samanta <sumanesh.samanta@broadcom.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 3616453..9ce64bc 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -187,17 +187,34 @@ unsigned int blk_mq_in_flight(struct request_queue *q,
 void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part,
 		unsigned int inflight[2]);
 
-static inline void blk_mq_put_dispatch_budget(struct request_queue *q)
+static inline void blk_mq_put_dispatch_budget(struct request_queue *q,
+					      int budget_token)
 {
 	if (q->mq_ops->put_budget)
-		q->mq_ops->put_budget(q);
+		q->mq_ops->put_budget(q, budget_token);
 }
 
-static inline bool blk_mq_get_dispatch_budget(struct request_queue *q)
+static inline int blk_mq_get_dispatch_budget(struct request_queue *q)
 {
 	if (q->mq_ops->get_budget)
 		return q->mq_ops->get_budget(q);
-	return true;
+	return 0;
+}
+
+static inline void blk_mq_set_rq_budget_token(struct request *rq, int token)
+{
+	if (token < 0)
+		return;
+
+	if (rq->q->mq_ops->set_rq_budget_token)
+		rq->q->mq_ops->set_rq_budget_token(rq, token);
+}
+
+static inline int blk_mq_get_rq_budget_token(struct request *rq)
+{
+	if (rq->q->mq_ops->get_rq_budget_token)
+		return rq->q->mq_ops->get_rq_budget_token(rq);
+	return -1;
 }
 
 static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx)