virtio-blk: support completion batching for the IRQ path

This patch adds completion batching to the IRQ path. It reuses batch
completion code of virtblk_poll(). It collects requests to io_comp_batch
and processes them all at once. It can boost up the performance by 2%.

To validate the performance improvement and stabilty, I did fio test with
4 vCPU VM and 12 vCPU VM respectively. Both VMs have 8GB ram and the same
number of HW queues as vCPU.
The fio cammad is as follows and I ran the fio 5 times and got IOPS average.
(io_uring, randread, direct=1, bs=512, iodepth=64 numjobs=2,4)

Test result shows about 2% improvement.

           4 vcpu VM       |   numjobs=2   |   numjobs=4
      -----------------------------------------------------------
        fio without patch  |  367.2K IOPS  |   397.6K IOPS
      -----------------------------------------------------------
        fio with patch     |  372.8K IOPS  |   407.7K IOPS

           12 vcpu VM      |   numjobs=2   |   numjobs=4
      -----------------------------------------------------------
        fio without patch  |  363.6K IOPS  |   374.8K IOPS
      -----------------------------------------------------------
        fio with patch     |  373.8K IOPS  |   385.3K IOPS
Signed-off-by: Suwan Kim <suwan.kim027@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Message-Id: <20221221145456.281218-3-suwan.kim027@gmail.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

drivers/block/virtio_blk.c

@@ -334,33 +334,63 @@ static inline void virtblk_request_done(struct request *req)
 	blk_mq_end_request(req, status);
 }
 
+static void virtblk_complete_batch(struct io_comp_batch *iob)
+{
+	struct request *req;
+
+	rq_list_for_each(&iob->req_list, req) {
+		virtblk_unmap_data(req, blk_mq_rq_to_pdu(req));
+		virtblk_cleanup_cmd(req);
+	}
+	blk_mq_end_request_batch(iob);
+}
+
+static int virtblk_handle_req(struct virtio_blk_vq *vq,
+			      struct io_comp_batch *iob)
+{
+	struct virtblk_req *vbr;
+	int req_done = 0;
+	unsigned int len;
+
+	while ((vbr = virtqueue_get_buf(vq->vq, &len)) != NULL) {
+		struct request *req = blk_mq_rq_from_pdu(vbr);
+
+		if (likely(!blk_should_fake_timeout(req->q)) &&
+		    !blk_mq_complete_request_remote(req) &&
+		    !blk_mq_add_to_batch(req, iob, vbr->status,
+					 virtblk_complete_batch))
+			virtblk_request_done(req);
+		req_done++;
+	}
+
+	return req_done;
+}
+
 static void virtblk_done(struct virtqueue *vq)
 {
 	struct virtio_blk *vblk = vq->vdev->priv;
-	bool req_done = false;
-	int qid = vq->index;
-	struct virtblk_req *vbr;
+	struct virtio_blk_vq *vblk_vq = &vblk->vqs[vq->index];
+	int req_done = 0;
 	unsigned long flags;
-	unsigned int len;
+	DEFINE_IO_COMP_BATCH(iob);
 
-	spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
+	spin_lock_irqsave(&vblk_vq->lock, flags);
 	do {
 		virtqueue_disable_cb(vq);
-		while ((vbr = virtqueue_get_buf(vblk->vqs[qid].vq, &len)) != NULL) {
-			struct request *req = blk_mq_rq_from_pdu(vbr);
+		req_done += virtblk_handle_req(vblk_vq, &iob);
 
-			if (likely(!blk_should_fake_timeout(req->q)))
-				blk_mq_complete_request(req);
-			req_done = true;
-		}
 		if (unlikely(virtqueue_is_broken(vq)))
 			break;
 	} while (!virtqueue_enable_cb(vq));
 
-	/* In case queue is stopped waiting for more buffers. */
-	if (req_done)
+	if (req_done) {
+		if (!rq_list_empty(iob.req_list))
+			iob.complete(&iob);
+
+		/* In case queue is stopped waiting for more buffers. */
 		blk_mq_start_stopped_hw_queues(vblk->disk->queue, true);
-	spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
+	}
+	spin_unlock_irqrestore(&vblk_vq->lock, flags);
 }
 
 static void virtio_commit_rqs(struct blk_mq_hw_ctx *hctx)
@@ -1176,37 +1206,15 @@ static void virtblk_map_queues(struct blk_mq_tag_set *set)
 	}
 }
 
-static void virtblk_complete_batch(struct io_comp_batch *iob)
-{
-	struct request *req;
-
-	rq_list_for_each(&iob->req_list, req) {
-		virtblk_unmap_data(req, blk_mq_rq_to_pdu(req));
-		virtblk_cleanup_cmd(req);
-	}
-	blk_mq_end_request_batch(iob);
-}
-
 static int virtblk_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 {
 	struct virtio_blk *vblk = hctx->queue->queuedata;
 	struct virtio_blk_vq *vq = get_virtio_blk_vq(hctx);
-	struct virtblk_req *vbr;
 	unsigned long flags;
-	unsigned int len;
 	int found = 0;
 
 	spin_lock_irqsave(&vq->lock, flags);
-
-	while ((vbr = virtqueue_get_buf(vq->vq, &len)) != NULL) {
-		struct request *req = blk_mq_rq_from_pdu(vbr);
-
-		found++;
-		if (!blk_mq_complete_request_remote(req) &&
-		    !blk_mq_add_to_batch(req, iob, vbr->status,
-						virtblk_complete_batch))
-			virtblk_request_done(req);
-	}
+	found = virtblk_handle_req(vq, iob);
 
 	if (found)
 		blk_mq_start_stopped_hw_queues(vblk->disk->queue, true);