blk-mq: Record nr_active_requests per queue for when using shared sbitmap

The per-hctx nr_active value can no longer be used to fairly assign a share
of tag depth per request queue for when using a shared sbitmap, as it does
not consider that the tags are shared tags over all hctx's.

For this case, record the nr_active_requests per request_queue, and make
the judgement based on that value.

Co-developed-with: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Tested-by: Don Brace<don.brace@microsemi.com> #SCSI resv cmds patches used
Tested-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-core.c

@@ -543,6 +543,8 @@ struct request_queue *blk_alloc_queue(int node_id)
 	q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
 	q->node = node_id;
 
+	atomic_set(&q->nr_active_requests_shared_sbitmap, 0);
+
 	timer_setup(&q->backing_dev_info->laptop_mode_wb_timer,
 		    laptop_mode_timer_fn, 0);
 	timer_setup(&q->timeout, blk_rq_timed_out_timer, 0);

block/blk-mq.c

@@ -519,7 +519,7 @@ void blk_mq_free_request(struct request *rq)
 
 	ctx->rq_completed[rq_is_sync(rq)]++;
 	if (rq->rq_flags & RQF_MQ_INFLIGHT)
-		atomic_dec(&hctx->nr_active);
+		__blk_mq_dec_active_requests(hctx);
 
 	if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
 		laptop_io_completion(q->backing_dev_info);
@@ -1127,7 +1127,7 @@ static bool blk_mq_get_driver_tag(struct request *rq)
 	if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) &&
 			!(rq->rq_flags & RQF_MQ_INFLIGHT)) {
 		rq->rq_flags |= RQF_MQ_INFLIGHT;
-		atomic_inc(&hctx->nr_active);
+		__blk_mq_inc_active_requests(hctx);
 	}
 	hctx->tags->rqs[rq->tag] = rq;
 	return true;

block/blk-mq.h

@@ -199,6 +199,28 @@ static inline bool blk_mq_get_dispatch_budget(struct request_queue *q)
 	return true;
 }
 
+static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx)
+{
+	if (blk_mq_is_sbitmap_shared(hctx->flags))
+		atomic_inc(&hctx->queue->nr_active_requests_shared_sbitmap);
+	else
+		atomic_inc(&hctx->nr_active);
+}
+
+static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx)
+{
+	if (blk_mq_is_sbitmap_shared(hctx->flags))
+		atomic_dec(&hctx->queue->nr_active_requests_shared_sbitmap);
+	else
+		atomic_dec(&hctx->nr_active);
+}
+
+static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx)
+{
+	if (blk_mq_is_sbitmap_shared(hctx->flags))
+		return atomic_read(&hctx->queue->nr_active_requests_shared_sbitmap);
+	return atomic_read(&hctx->nr_active);
+}
 static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
 					   struct request *rq)
 {
@@ -207,7 +229,7 @@ static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
 
 	if (rq->rq_flags & RQF_MQ_INFLIGHT) {
 		rq->rq_flags &= ~RQF_MQ_INFLIGHT;
-		atomic_dec(&hctx->nr_active);
+		__blk_mq_dec_active_requests(hctx);
 	}
 }
 
@@ -287,7 +309,7 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx,
 	 * Allow at least some tags
 	 */
 	depth = max((bt->sb.depth + users - 1) / users, 4U);
-	return atomic_read(&hctx->nr_active) < depth;
+	return __blk_mq_active_requests(hctx) < depth;
 }
 
 

include/linux/blkdev.h

@@ -485,6 +485,8 @@ struct request_queue {
 	struct timer_list	timeout;
 	struct work_struct	timeout_work;
 
+	atomic_t		nr_active_requests_shared_sbitmap;
+
 	struct list_head	icq_list;
 #ifdef CONFIG_BLK_CGROUP
 	DECLARE_BITMAP		(blkcg_pols, BLKCG_MAX_POLS);