blk-mq, elevator: Count requests per hctx to improve performance

High CPU utilization on "native_queued_spin_lock_slowpath" due to lock
contention is possible for mq-deadline and bfq IO schedulers
when nr_hw_queues is more than one.

It is because kblockd work queue can submit IO from all online CPUs
(through blk_mq_run_hw_queues()) even though only one hctx has pending
commands.

The elevator callback .has_work for mq-deadline and bfq scheduler considers
pending work if there are any IOs on request queue but it does not account
hctx context.

Add a per-hctx 'elevator_queued' count to the hctx to avoid triggering
the elevator even though there are no requests queued.

[jpg: Relocated atomic_dec() in dd_dispatch_request(), update commit message per Kashyap]
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: John Garry <john.garry@huawei.com>
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/bfq-iosched.c

@@ -4640,6 +4640,9 @@ static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
 {
 	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
 
+	if (!atomic_read(&hctx->elevator_queued))
+		return false;
+
 	/*
 	 * Avoiding lock: a race on bfqd->busy_queues should cause at
 	 * most a call to dispatch for nothing
@@ -5554,6 +5557,7 @@ static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
 		rq = list_first_entry(list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 		bfq_insert_request(hctx, rq, at_head);
+		atomic_inc(&hctx->elevator_queued);
 	}
 }
 
@@ -5933,6 +5937,7 @@ static void bfq_finish_requeue_request(struct request *rq)
 
 		bfq_completed_request(bfqq, bfqd);
 		bfq_finish_requeue_request_body(bfqq);
+		atomic_dec(&rq->mq_hctx->elevator_queued);
 
 		spin_unlock_irqrestore(&bfqd->lock, flags);
 	} else {

block/blk-mq.c

@@ -2660,6 +2660,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set,
 		goto free_hctx;
 
 	atomic_set(&hctx->nr_active, 0);
+	atomic_set(&hctx->elevator_queued, 0);
 	if (node == NUMA_NO_NODE)
 		node = set->numa_node;
 	hctx->numa_node = node;

block/mq-deadline.c

@@ -386,6 +386,8 @@ static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	spin_lock(&dd->lock);
 	rq = __dd_dispatch_request(dd);
 	spin_unlock(&dd->lock);
+	if (rq)
+		atomic_dec(&rq->mq_hctx->elevator_queued);
 
 	return rq;
 }
@@ -533,6 +535,7 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
 		rq = list_first_entry(list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 		dd_insert_request(hctx, rq, at_head);
+		atomic_inc(&hctx->elevator_queued);
 	}
 	spin_unlock(&dd->lock);
 }
@@ -579,6 +582,9 @@ static bool dd_has_work(struct blk_mq_hw_ctx *hctx)
 {
 	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
 
+	if (!atomic_read(&hctx->elevator_queued))
+		return false;
+
 	return !list_empty_careful(&dd->dispatch) ||
 		!list_empty_careful(&dd->fifo_list[0]) ||
 		!list_empty_careful(&dd->fifo_list[1]);

include/linux/blk-mq.h

@@ -139,6 +139,10 @@ struct blk_mq_hw_ctx {
 	 * shared across request queues.
 	 */
 	atomic_t		nr_active;
+	/**
+	 * @elevator_queued: Number of queued requests on hctx.
+	 */
+	atomic_t                elevator_queued;
 
 	/** @cpuhp_online: List to store request if CPU is going to die */
 	struct hlist_node	cpuhp_online;