blk-mq: sync the update nr_hw_queues with blk_mq_queue_tag_busy_iter

For blk-mq, part_in_flight/rw will invoke blk_mq_in_flight/rw to
account the inflight requests. It will access the queue_hw_ctx and
nr_hw_queues w/o any protection. When updating nr_hw_queues and
blk_mq_in_flight/rw occur concurrently, panic comes up.

Before update nr_hw_queues, the q will be frozen. So we could use
q_usage_counter to avoid the race. percpu_ref_is_zero is used here
so that we will not miss any in-flight request. The access to
nr_hw_queues and queue_hw_ctx in blk_mq_queue_tag_busy_iter are
under rcu critical section, __blk_mq_update_nr_hw_queues could use
synchronize_rcu to ensure the zeroed q_usage_counter to be globally
visible.

Signed-off-by: Jianchao Wang <jianchao.w.wang@oracle.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/blk-mq-tag.c

@@ -320,6 +320,18 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
+	/*
+	 * __blk_mq_update_nr_hw_queues will update the nr_hw_queues and
+	 * queue_hw_ctx after freeze the queue. So we could use q_usage_counter
+	 * to avoid race with it. __blk_mq_update_nr_hw_queues will users
+	 * synchronize_rcu to ensure all of the users go out of the critical
+	 * section below and see zeroed q_usage_counter.
+	 */
+	rcu_read_lock();
+	if (percpu_ref_is_zero(&q->q_usage_counter)) {
+		rcu_read_unlock();
+		return;
+	}
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		struct blk_mq_tags *tags = hctx->tags;
@@ -335,7 +347,7 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 			bt_for_each(hctx, &tags->breserved_tags, fn, priv, true);
 		bt_for_each(hctx, &tags->bitmap_tags, fn, priv, false);
 	}
-
+	rcu_read_unlock();
 }
 
 static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth,

block/blk-mq.c

@@ -2976,6 +2976,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
 		blk_mq_freeze_queue(q);
+	/*
+	 * Sync with blk_mq_queue_tag_busy_iter.
+	 */
+	synchronize_rcu();
 	/*
 	 * Switch IO scheduler to 'none', cleaning up the data associated
 	 * with the previous scheduler. We will switch back once we are done