blk-mq: add a new queue sysfs attribute async_depth

Add a new field async_depth to request_queue and related APIs, this is
currently not used, following patches will convert elevators to use
this instead of internal async_depth.

Signed-off-by: Yu Kuai <yukuai@fnnas.com>
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-core.c

@@ -463,6 +463,7 @@ struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id)
 	fs_reclaim_release(GFP_KERNEL);
 
 	q->nr_requests = BLKDEV_DEFAULT_RQ;
+	q->async_depth = BLKDEV_DEFAULT_RQ;
 
 	return q;
 

block/blk-mq.c

@@ -4662,6 +4662,7 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	spin_lock_init(&q->requeue_lock);
 
 	q->nr_requests = set->queue_depth;
+	q->async_depth = set->queue_depth;
 
 	blk_mq_init_cpu_queues(q, set->nr_hw_queues);
 	blk_mq_map_swqueue(q);
@@ -5028,6 +5029,11 @@ struct elevator_tags *blk_mq_update_nr_requests(struct request_queue *q,
 		q->elevator->et = et;
 	}
 
+	/*
+	 * Preserve relative value, both nr and async_depth are at most 16 bit
+	 * value, no need to worry about overflow.
+	 */
+	q->async_depth = max(q->async_depth * nr / q->nr_requests, 1);
 	q->nr_requests = nr;
 	if (q->elevator && q->elevator->type->ops.depth_updated)
 		q->elevator->type->ops.depth_updated(q);

block/blk-sysfs.c

@@ -127,6 +127,46 @@ unlock:
 	return ret;
 }
 
+static ssize_t queue_async_depth_show(struct gendisk *disk, char *page)
+{
+	guard(mutex)(&disk->queue->elevator_lock);
+
+	return queue_var_show(disk->queue->async_depth, page);
+}
+
+static ssize_t
+queue_async_depth_store(struct gendisk *disk, const char *page, size_t count)
+{
+	struct request_queue *q = disk->queue;
+	unsigned int memflags;
+	unsigned long nr;
+	int ret;
+
+	if (!queue_is_mq(q))
+		return -EINVAL;
+
+	ret = queue_var_store(&nr, page, count);
+	if (ret < 0)
+		return ret;
+
+	if (nr == 0)
+		return -EINVAL;
+
+	memflags = blk_mq_freeze_queue(q);
+	scoped_guard(mutex, &q->elevator_lock) {
+		if (q->elevator) {
+			q->async_depth = min(q->nr_requests, nr);
+			if (q->elevator->type->ops.depth_updated)
+				q->elevator->type->ops.depth_updated(q);
+		} else {
+			ret = -EINVAL;
+		}
+	}
+	blk_mq_unfreeze_queue(q, memflags);
+
+	return ret;
+}
+
 static ssize_t queue_ra_show(struct gendisk *disk, char *page)
 {
 	ssize_t ret;
@@ -532,6 +572,7 @@ static struct queue_sysfs_entry _prefix##_entry = {	\
 }
 
 QUEUE_RW_ENTRY(queue_requests, "nr_requests");
+QUEUE_RW_ENTRY(queue_async_depth, "async_depth");
 QUEUE_RW_ENTRY(queue_ra, "read_ahead_kb");
 QUEUE_LIM_RW_ENTRY(queue_max_sectors, "max_sectors_kb");
 QUEUE_LIM_RO_ENTRY(queue_max_hw_sectors, "max_hw_sectors_kb");
@@ -719,6 +760,7 @@ static struct attribute *blk_mq_queue_attrs[] = {
 	 */
 	&elv_iosched_entry.attr,
 	&queue_requests_entry.attr,
+	&queue_async_depth_entry.attr,
 #ifdef CONFIG_BLK_WBT
 	&queue_wb_lat_entry.attr,
 #endif

block/elevator.c

@@ -589,6 +589,7 @@ static int elevator_switch(struct request_queue *q, struct elv_change_ctx *ctx)
 		blk_queue_flag_clear(QUEUE_FLAG_SQ_SCHED, q);
 		q->elevator = NULL;
 		q->nr_requests = q->tag_set->queue_depth;
+		q->async_depth = q->tag_set->queue_depth;
 	}
 	blk_add_trace_msg(q, "elv switch: %s", ctx->name);
 

include/linux/blkdev.h

@@ -551,6 +551,7 @@ struct request_queue {
 	 * queue settings
 	 */
 	unsigned int		nr_requests;	/* Max # of requests */
+	unsigned int		async_depth;	/* Max # of async requests */
 
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 	struct blk_crypto_profile *crypto_profile;