elevator: factor elevator lock out of dispatch_request method

Currently, both mq-deadline and bfq have global spin lock that will be
grabbed inside elevator methods like dispatch_request, insert_requests,
and bio_merge. And the global lock is the main reason mq-deadline and
bfq can't scale very well.

For dispatch_request method, current behavior is dispatching one request at
a time. In the case of multiple dispatching contexts, this behavior will
cause huge lock contention and messing up the requests dispatching
order. And folloiwng patches will support requests batch dispatching to
fix thoses problems.

While dispatching request, blk_mq_get_disatpch_budget() and
blk_mq_get_driver_tag() must be called, and they are not ready to be
called inside elevator methods, hence introduce a new method like
dispatch_requests is not possible.

In conclusion, this patch factor the global lock out of dispatch_request
method, and following patches will support request batch dispatch by
calling the methods multiple time while holding the lock.

Signed-off-by: Yu Kuai <[email protected]>

Author: YuKuai-huawei

block/bfq-iosched.c

@@ -5307,8 +5307,6 @@ static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	struct bfq_queue *in_serv_queue;
 	bool waiting_rq, idle_timer_disabled = false;
 
-	spin_lock_irq(bfqd->lock);
-
 	in_serv_queue = bfqd->in_service_queue;
 	waiting_rq = in_serv_queue && bfq_bfqq_wait_request(in_serv_queue);
 
@@ -5318,7 +5316,6 @@ static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
 			waiting_rq && !bfq_bfqq_wait_request(in_serv_queue);
 	}
 
-	spin_unlock_irq(bfqd->lock);
 	bfq_update_dispatch_stats(hctx->queue, rq,
 			idle_timer_disabled ? in_serv_queue : NULL,
 				idle_timer_disabled);

block/blk-mq-sched.c

@@ -98,6 +98,7 @@ static int __blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
 		max_dispatch = hctx->queue->nr_requests;
 
 	do {
+		bool sq_sched = blk_queue_sq_sched(q);
 		struct request *rq;
 		int budget_token;
 
@@ -113,7 +114,12 @@ static int __blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
 		if (budget_token < 0)
 			break;
 
+		if (sq_sched)
+			spin_lock_irq(&e->lock);
 		rq = e->type->ops.dispatch_request(hctx);
+		if (sq_sched)
+			spin_unlock_irq(&e->lock);
+
 		if (!rq) {
 			blk_mq_put_dispatch_budget(q, budget_token);
 			/*

block/mq-deadline.c

@@ -466,10 +466,9 @@ static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 	struct request *rq;
 	enum dd_prio prio;
 
-	spin_lock(dd->lock);
 	rq = dd_dispatch_prio_aged_requests(dd, now);
 	if (rq)
-		goto unlock;
+		return rq;
 
 	/*
 	 * Next, dispatch requests in priority order. Ignore lower priority
@@ -481,8 +480,6 @@ static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
 			break;
 	}
 
-unlock:
-	spin_unlock(dd->lock);
 	return rq;
 }