blk-mq: introduce .get_budget and .put_budget in blk_mq_ops

For SCSI devices, there is often a per-request-queue depth, which needs
to be respected before queuing one request.

Currently blk-mq always dequeues the request first, then calls
.queue_rq() to dispatch the request to lld. One obvious issue with this
approach is that I/O merging may not be successful, because when the
per-request-queue depth can't be respected, .queue_rq() has to return
BLK_STS_RESOURCE, and then this request has to stay in hctx->dispatch
list. This means it never gets a chance to be merged with other IO.

This patch introduces .get_budget and .put_budget callback in blk_mq_ops,
then we can try to get reserved budget first before dequeuing request.
If the budget for queueing I/O can't be satisfied, we don't need to
dequeue request at all. Hence the request can be left in the IO
scheduler queue, for more merging opportunities.

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-mq-sched.c

@@ -89,31 +89,57 @@ static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
 	return false;
 }
 
-static void blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
+/* return true if hctx need to run again */
+static bool blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx)
 {
 	struct request_queue *q = hctx->queue;
 	struct elevator_queue *e = q->elevator;
 	LIST_HEAD(rq_list);
 
 	do {
-		struct request *rq = e->type->ops.mq.dispatch_request(hctx);
+		struct request *rq;
+		blk_status_t ret;
 
-		if (!rq)
+		if (e->type->ops.mq.has_work &&
+				!e->type->ops.mq.has_work(hctx))
 			break;
+
+		ret = blk_mq_get_dispatch_budget(hctx);
+		if (ret == BLK_STS_RESOURCE)
+			return true;
+
+		rq = e->type->ops.mq.dispatch_request(hctx);
+		if (!rq) {
+			blk_mq_put_dispatch_budget(hctx);
+			break;
+		} else if (ret != BLK_STS_OK) {
+			blk_mq_end_request(rq, ret);
+			continue;
+		}
+
+		/*
+		 * Now this rq owns the budget which has to be released
+		 * if this rq won't be queued to driver via .queue_rq()
+		 * in blk_mq_dispatch_rq_list().
+		 */
 		list_add(&rq->queuelist, &rq_list);
-	} while (blk_mq_dispatch_rq_list(q, &rq_list));
+	} while (blk_mq_dispatch_rq_list(q, &rq_list, true));
+
+	return false;
 }
 
-void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
+/* return true if hw queue need to be run again */
+bool blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 {
 	struct request_queue *q = hctx->queue;
 	struct elevator_queue *e = q->elevator;
 	const bool has_sched_dispatch = e && e->type->ops.mq.dispatch_request;
 	LIST_HEAD(rq_list);
+	bool run_queue = false;
 
 	/* RCU or SRCU read lock is needed before checking quiesced flag */
 	if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)))
-		return;
+		return false;
 
 	hctx->run++;
 
@@ -143,14 +169,23 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	 */
 	if (!list_empty(&rq_list)) {
 		blk_mq_sched_mark_restart_hctx(hctx);
-		if (blk_mq_dispatch_rq_list(q, &rq_list) && has_sched_dispatch)
+		if (blk_mq_dispatch_rq_list(q, &rq_list, false) &&
-			blk_mq_do_dispatch_sched(hctx);
+				has_sched_dispatch)
+			run_queue = blk_mq_do_dispatch_sched(hctx);
 	} else if (has_sched_dispatch) {
-		blk_mq_do_dispatch_sched(hctx);
+		run_queue = blk_mq_do_dispatch_sched(hctx);
 	} else {
 		blk_mq_flush_busy_ctxs(hctx, &rq_list);
-		blk_mq_dispatch_rq_list(q, &rq_list);
+		blk_mq_dispatch_rq_list(q, &rq_list, false);
 	}
+
+	if (run_queue && !blk_mq_sched_needs_restart(hctx) &&
+			!test_bit(BLK_MQ_S_TAG_WAITING, &hctx->state)) {
+		blk_mq_sched_mark_restart_hctx(hctx);
+		return true;
+	}
+
+	return false;
 }
 
 bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,

block/blk-mq-sched.h

@@ -22,7 +22,7 @@ void blk_mq_sched_insert_requests(struct request_queue *q,
 				  struct blk_mq_ctx *ctx,
 				  struct list_head *list, bool run_queue_async);
 
-void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
+bool blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
 
 int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e);
 void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e);

block/blk-mq.c

@@ -1048,7 +1048,8 @@ static bool blk_mq_dispatch_wait_add(struct blk_mq_hw_ctx *hctx)
 	return true;
 }
 
-bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
+bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
+		bool got_budget)
 {
 	struct blk_mq_hw_ctx *hctx;
 	struct request *rq;
@@ -1057,6 +1058,8 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
 	if (list_empty(list))
 		return false;
 
+	WARN_ON(!list_is_singular(list) && got_budget);
+
 	/*
 	 * Now process all the entries, sending them to the driver.
 	 */
@@ -1074,16 +1077,30 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
 			 * The initial allocation attempt failed, so we need to
 			 * rerun the hardware queue when a tag is freed.
 			 */
-			if (!blk_mq_dispatch_wait_add(hctx))
+			if (!blk_mq_dispatch_wait_add(hctx)) {
+				if (got_budget)
+					blk_mq_put_dispatch_budget(hctx);
 				break;
+			}
 
 			/*
 			 * It's possible that a tag was freed in the window
 			 * between the allocation failure and adding the
 			 * hardware queue to the wait queue.
 			 */
-			if (!blk_mq_get_driver_tag(rq, &hctx, false))
+			if (!blk_mq_get_driver_tag(rq, &hctx, false)) {
+				if (got_budget)
+					blk_mq_put_dispatch_budget(hctx);
 				break;
+			}
+		}
+
+		if (!got_budget) {
+			ret = blk_mq_get_dispatch_budget(hctx);
+			if (ret == BLK_STS_RESOURCE)
+				break;
+			if (ret != BLK_STS_OK)
+				goto fail_rq;
 		}
 
 		list_del_init(&rq->queuelist);
@@ -1111,6 +1128,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
 			break;
 		}
 
+ fail_rq:
 		if (unlikely(ret != BLK_STS_OK)) {
 			errors++;
 			blk_mq_end_request(rq, BLK_STS_IOERR);
@@ -1169,6 +1187,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
 static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 {
 	int srcu_idx;
+	bool run_queue;
 
 	/*
 	 * We should be running this queue from one of the CPUs that
@@ -1185,15 +1204,18 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 
 	if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
 		rcu_read_lock();
-		blk_mq_sched_dispatch_requests(hctx);
+		run_queue = blk_mq_sched_dispatch_requests(hctx);
 		rcu_read_unlock();
 	} else {
 		might_sleep();
 
 		srcu_idx = srcu_read_lock(hctx->queue_rq_srcu);
-		blk_mq_sched_dispatch_requests(hctx);
+		run_queue = blk_mq_sched_dispatch_requests(hctx);
 		srcu_read_unlock(hctx->queue_rq_srcu, srcu_idx);
 	}
+
+	if (run_queue)
+		blk_mq_run_hw_queue(hctx, true);
 }
 
 /*
@@ -1582,6 +1604,13 @@ static void __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 	if (!blk_mq_get_driver_tag(rq, NULL, false))
 		goto insert;
 
+	ret = blk_mq_get_dispatch_budget(hctx);
+	if (ret == BLK_STS_RESOURCE) {
+		blk_mq_put_driver_tag(rq);
+		goto insert;
+	} else if (ret != BLK_STS_OK)
+		goto fail_rq;
+
 	new_cookie = request_to_qc_t(hctx, rq);
 
 	/*
@@ -1598,6 +1627,7 @@ static void __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 		__blk_mq_requeue_request(rq);
 		goto insert;
 	default:
+ fail_rq:
 		*cookie = BLK_QC_T_NONE;
 		blk_mq_end_request(rq, ret);
 		return;
@@ -2582,6 +2612,9 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (!set->ops->queue_rq)
 		return -EINVAL;
 
+	if (!set->ops->get_budget ^ !set->ops->put_budget)
+		return -EINVAL;
+
 	if (set->queue_depth > BLK_MQ_MAX_DEPTH) {
 		pr_info("blk-mq: reduced tag depth to %u\n",
 			BLK_MQ_MAX_DEPTH);

block/blk-mq.h

@@ -30,7 +30,7 @@ void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_free_queue(struct request_queue *q);
 int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
 void blk_mq_wake_waiters(struct request_queue *q);
-bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *);
+bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *, bool);
 void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
 bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx);
 bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
@@ -137,4 +137,22 @@ static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx)
 void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part,
 			unsigned int inflight[2]);
 
+static inline void blk_mq_put_dispatch_budget(struct blk_mq_hw_ctx *hctx)
+{
+	struct request_queue *q = hctx->queue;
+
+	if (q->mq_ops->put_budget)
+		q->mq_ops->put_budget(hctx);
+}
+
+static inline blk_status_t blk_mq_get_dispatch_budget(
+		struct blk_mq_hw_ctx *hctx)
+{
+	struct request_queue *q = hctx->queue;
+
+	if (q->mq_ops->get_budget)
+		return q->mq_ops->get_budget(hctx);
+	return BLK_STS_OK;
+}
+
 #endif

include/linux/blk-mq.h

@@ -90,6 +90,8 @@ struct blk_mq_queue_data {
 
 typedef blk_status_t (queue_rq_fn)(struct blk_mq_hw_ctx *,
 		const struct blk_mq_queue_data *);
+typedef blk_status_t (get_budget_fn)(struct blk_mq_hw_ctx *);
+typedef void (put_budget_fn)(struct blk_mq_hw_ctx *);
 typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool);
 typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int);
 typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int);
@@ -111,6 +113,15 @@ struct blk_mq_ops {
 	 */
 	queue_rq_fn		*queue_rq;
 
+	/*
+	 * Reserve budget before queue request, once .queue_rq is
+	 * run, it is driver's responsibility to release the
+	 * reserved budget. Also we have to handle failure case
+	 * of .get_budget for avoiding I/O deadlock.
+	 */
+	get_budget_fn		*get_budget;
+	put_budget_fn		*put_budget;
+
 	/*
 	 * Called on request timeout
 	 */