blk-mq: move the srcu_struct used for quiescing to the tagset

All I/O submissions have fairly similar latencies, and a tagset-wide
quiesce is a fairly common operation.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Chao Leng <lengchao@huawei.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://lore.kernel.org/r/20221101150050.3510-12-hch@lst.de
[axboe: fix whitespace]
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 25 insertions, 8 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index a03abadfe4c6..bee728dac9cd 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -261,8 +261,8 @@ EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait);
  */
 void blk_mq_wait_quiesce_done(struct request_queue *q)
 {
-	if (blk_queue_has_srcu(q))
-		synchronize_srcu(q->srcu);
+	if (q->tag_set->flags & BLK_MQ_F_BLOCKING)
+		synchronize_srcu(q->tag_set->srcu);
 	else
 		synchronize_rcu();
 }
@@ -4003,7 +4003,7 @@ static struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set,
 	struct request_queue *q;
 	int ret;
 
-	q = blk_alloc_queue(set->numa_node, set->flags & BLK_MQ_F_BLOCKING);
+	q = blk_alloc_queue(set->numa_node);
 	if (!q)
 		return ERR_PTR(-ENOMEM);
 	q->queuedata = queuedata;
@@ -4168,9 +4168,6 @@ static void blk_mq_update_poll_flag(struct request_queue *q)
 int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 		struct request_queue *q)
 {
-	WARN_ON_ONCE(blk_queue_has_srcu(q) !=
-			!!(set->flags & BLK_MQ_F_BLOCKING));
-
 	/* mark the queue as mq asap */
 	q->mq_ops = set->ops;
 
@@ -4429,8 +4426,18 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (set->nr_maps == 1 && set->nr_hw_queues > nr_cpu_ids)
 		set->nr_hw_queues = nr_cpu_ids;
 
-	if (blk_mq_alloc_tag_set_tags(set, set->nr_hw_queues) < 0)
-		return -ENOMEM;
+	if (set->flags & BLK_MQ_F_BLOCKING) {
+		set->srcu = kmalloc(sizeof(*set->srcu), GFP_KERNEL);
+		if (!set->srcu)
+			return -ENOMEM;
+		ret = init_srcu_struct(set->srcu);
+		if (ret)
+			goto out_free_srcu;
+	}
+
+	ret = blk_mq_alloc_tag_set_tags(set, set->nr_hw_queues);
+	if (ret)
+		goto out_cleanup_srcu;
 
 	ret = -ENOMEM;
 	for (i = 0; i < set->nr_maps; i++) {
@@ -4460,6 +4467,12 @@ out_free_mq_map:
 	}
 	kfree(set->tags);
 	set->tags = NULL;
+out_cleanup_srcu:
+	if (set->flags & BLK_MQ_F_BLOCKING)
+		cleanup_srcu_struct(set->srcu);
+out_free_srcu:
+	if (set->flags & BLK_MQ_F_BLOCKING)
+		kfree(set->srcu);
 	return ret;
 }
 EXPORT_SYMBOL(blk_mq_alloc_tag_set);
@@ -4499,6 +4512,10 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 
 	kfree(set->tags);
 	set->tags = NULL;
+	if (set->flags & BLK_MQ_F_BLOCKING) {
+		cleanup_srcu_struct(set->srcu);
+		kfree(set->srcu);
+	}
 }
 EXPORT_SYMBOL(blk_mq_free_tag_set);