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

mainline inclusion
from mainline-5.12-rc1
commit 5ac83c64
category: perf
bugzilla: https://gitee.com/openeuler/kernel/issues/I4SW26
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=5ac83c644f5fb924f0b2c09102ab82fc788f8411

-------------------------------------------------

This reverts commit b445547e.

Since both mq-deadline and BFQ completely ignore hctx they are passed to
their dispatch function and dispatch whatever request they deem fit
checking whether any request for a particular hctx is queued is just
pointless since we'll very likely get a request from a different hctx
anyway. In the following commit we'll deal with lock contention in these
IO schedulers in presence of multiple HW queues in a different way.
Signed-off-by: NJan Kara <jack@suse.cz>
Reviewed-by: NMing Lei <ming.lei@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Conflicts:
	block/bfq-iosched.c
Signed-off-by: NBaokun Li <libaokun1@huawei.com>
Reviewed-by: NHou Tao <houtao1@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>

block/bfq-iosched.c

@@ -4651,9 +4651,6 @@ 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
@@ -5570,7 +5567,6 @@ 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);
 	}
 }
 
@@ -5935,7 +5931,6 @@ static void bfq_finish_requeue_request(struct request *rq)
 			bfq_update_inject_limit(bfqd, bfqq);
 
 		bfq_completed_request(bfqq, bfqd);
-		atomic_dec(&rq->mq_hctx->elevator_queued);
 	}
 	bfq_finish_requeue_request_body(bfqq);
 	spin_unlock_irqrestore(&bfqd->lock, flags);

block/blk-mq.c

@@ -2748,7 +2748,6 @@ 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

@@ -386,8 +386,6 @@ 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;
 }
@@ -539,7 +537,6 @@ 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);
 }
@@ -586,9 +583,6 @@ 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

@@ -141,10 +141,6 @@ 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;