block/null_blk: add queue_rqs() support

Add batched mq_ops.queue_rqs() support in null_blk for testing. The
implementation is much easy since null_blk doesn't have commit_rqs().

We simply handle each request one by one, if errors are encountered,
leave them in the passed in list and return back.

There is about 3.6% improvement in IOPS of fio/t/io_uring on null_blk
with hw_queue_depth=256 on my test VM, from 1.09M to 1.13M.

Signed-off-by: Chengming Zhou <[e-mail]>
Reviewed-by: Ming Lei <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Jens Axboe <[e-mail]>

drivers/block/null_blk/main.c

···
 	return null_handle_cmd(cmd, sector, nr_sectors, req_op(rq));
 }
 
+static void null_queue_rqs(struct request **rqlist)
+{
+	struct request *requeue_list = NULL;
+	struct request **requeue_lastp = &requeue_list;
+	struct blk_mq_queue_data bd = { };
+	blk_status_t ret;
+
+	do {
+		struct request *rq = rq_list_pop(rqlist);
+
+		bd.rq = rq;
+		ret = null_queue_rq(rq->mq_hctx, &bd);
+		if (ret != BLK_STS_OK)
+			rq_list_add_tail(&requeue_lastp, rq);
+	} while (!rq_list_empty(*rqlist));
+
+	*rqlist = requeue_list;
+}
+
 static void cleanup_queue(struct nullb_queue *nq)
 {
 	bitmap_free(nq->tag_map);
···
 
 static const struct blk_mq_ops null_mq_ops = {
 	.queue_rq       = null_queue_rq,
+	.queue_rqs	= null_queue_rqs,
 	.complete	= null_complete_rq,
 	.timeout	= null_timeout_rq,
 	.poll		= null_poll,