virtio-blk: support mq_ops->queue_rqs()

This patch supports mq_ops->queue_rqs() hook. It has an advantage of
batch submission to virtio-blk driver. It also helps polling I/O because
polling uses batched completion of block layer. Batch submission in
queue_rqs() can boost polling performance.

In queue_rqs(), it iterates plug->mq_list, collects requests that
belong to same HW queue until it encounters a request from other
HW queue or sees the end of the list.
Then, virtio-blk adds requests into virtqueue and kicks virtqueue
to submit requests.

If there is an error, it inserts error request to requeue_list and
passes it to ordinary block layer path.

For verification, I did fio test.
(io_uring, randread, direct=1, bs=4K, iodepth=64 numjobs=N)
I set 4 vcpu and 2 virtio-blk queues for VM and run fio test 5 times.
It shows about 2% improvement.

                                 |   numjobs=2   |   numjobs=4
      -----------------------------------------------------------
        fio without queue_rqs()  |   291K IOPS   |   238K IOPS
      -----------------------------------------------------------
        fio with queue_rqs()     |   295K IOPS   |   243K IOPS

For polling I/O performance, I also did fio test as below.
(io_uring, hipri, randread, direct=1, bs=512, iodepth=64 numjobs=4)
I set 4 vcpu and 2 poll queues for VM.
It shows about 2% improvement in polling I/O.

                                      |   IOPS   |  avg latency
      -----------------------------------------------------------
        fio poll without queue_rqs()  |   424K   |   613.05 usec
      -----------------------------------------------------------
        fio poll with queue_rqs()     |   435K   |   601.01 usec
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Suwan Kim <suwan.kim027@gmail.com>
Message-Id: <20220406153207.163134-3-suwan.kim027@gmail.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>

drivers/block/virtio_blk.c

@@ -101,8 +101,7 @@ static inline blk_status_t virtblk_result(struct virtblk_req *vbr)
 	}
 }
 
-static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr,
-		struct scatterlist *data_sg, bool have_data)
+static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr)
 {
 	struct scatterlist hdr, status, *sgs[3];
 	unsigned int num_out = 0, num_in = 0;
@@ -110,11 +109,11 @@ static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr,
 	sg_init_one(&hdr, &vbr->out_hdr, sizeof(vbr->out_hdr));
 	sgs[num_out++] = &hdr;
 
-	if (have_data) {
+	if (vbr->sg_table.nents) {
 		if (vbr->out_hdr.type & cpu_to_virtio32(vq->vdev, VIRTIO_BLK_T_OUT))
-			sgs[num_out++] = data_sg;
+			sgs[num_out++] = vbr->sg_table.sgl;
 		else
-			sgs[num_out + num_in++] = data_sg;
+			sgs[num_out + num_in++] = vbr->sg_table.sgl;
 	}
 
 	sg_init_one(&status, &vbr->status, sizeof(vbr->status));
@@ -304,6 +303,28 @@ static void virtio_commit_rqs(struct blk_mq_hw_ctx *hctx)
 		virtqueue_notify(vq->vq);
 }
 
+static blk_status_t virtblk_prep_rq(struct blk_mq_hw_ctx *hctx,
+					struct virtio_blk *vblk,
+					struct request *req,
+					struct virtblk_req *vbr)
+{
+	blk_status_t status;
+
+	status = virtblk_setup_cmd(vblk->vdev, req, vbr);
+	if (unlikely(status))
+		return status;
+
+	blk_mq_start_request(req);
+
+	vbr->sg_table.nents = virtblk_map_data(hctx, req, vbr);
+	if (unlikely(vbr->sg_table.nents < 0)) {
+		virtblk_cleanup_cmd(req);
+		return BLK_STS_RESOURCE;
+	}
+
+	return BLK_STS_OK;
+}
+
 static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 			   const struct blk_mq_queue_data *bd)
 {
@@ -311,26 +332,17 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct request *req = bd->rq;
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
 	unsigned long flags;
-	int num;
 	int qid = hctx->queue_num;
 	bool notify = false;
 	blk_status_t status;
 	int err;
 
-	status = virtblk_setup_cmd(vblk->vdev, req, vbr);
+	status = virtblk_prep_rq(hctx, vblk, req, vbr);
 	if (unlikely(status))
 		return status;
 
-	blk_mq_start_request(req);
-
-	num = virtblk_map_data(hctx, req, vbr);
-	if (unlikely(num < 0)) {
-		virtblk_cleanup_cmd(req);
-		return BLK_STS_RESOURCE;
-	}
-
 	spin_lock_irqsave(&vblk->vqs[qid].lock, flags);
-	err = virtblk_add_req(vblk->vqs[qid].vq, vbr, vbr->sg_table.sgl, num);
+	err = virtblk_add_req(vblk->vqs[qid].vq, vbr);
 	if (err) {
 		virtqueue_kick(vblk->vqs[qid].vq);
 		/* Don't stop the queue if -ENOMEM: we may have failed to
@@ -360,6 +372,75 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return BLK_STS_OK;
 }
 
+static bool virtblk_prep_rq_batch(struct request *req)
+{
+	struct virtio_blk *vblk = req->mq_hctx->queue->queuedata;
+	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+
+	req->mq_hctx->tags->rqs[req->tag] = req;
+
+	return virtblk_prep_rq(req->mq_hctx, vblk, req, vbr) == BLK_STS_OK;
+}
+
+static bool virtblk_add_req_batch(struct virtio_blk_vq *vq,
+					struct request **rqlist,
+					struct request **requeue_list)
+{
+	unsigned long flags;
+	int err;
+	bool kick;
+
+	spin_lock_irqsave(&vq->lock, flags);
+
+	while (!rq_list_empty(*rqlist)) {
+		struct request *req = rq_list_pop(rqlist);
+		struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
+
+		err = virtblk_add_req(vq->vq, vbr);
+		if (err) {
+			virtblk_unmap_data(req, vbr);
+			virtblk_cleanup_cmd(req);
+			rq_list_add(requeue_list, req);
+		}
+	}
+
+	kick = virtqueue_kick_prepare(vq->vq);
+	spin_unlock_irqrestore(&vq->lock, flags);
+
+	return kick;
+}
+
+static void virtio_queue_rqs(struct request **rqlist)
+{
+	struct request *req, *next, *prev = NULL;
+	struct request *requeue_list = NULL;
+
+	rq_list_for_each_safe(rqlist, req, next) {
+		struct virtio_blk_vq *vq = req->mq_hctx->driver_data;
+		bool kick;
+
+		if (!virtblk_prep_rq_batch(req)) {
+			rq_list_move(rqlist, &requeue_list, req, prev);
+			req = prev;
+			if (!req)
+				continue;
+		}
+
+		if (!next || req->mq_hctx != next->mq_hctx) {
+			req->rq_next = NULL;
+			kick = virtblk_add_req_batch(vq, rqlist, &requeue_list);
+			if (kick)
+				virtqueue_notify(vq->vq);
+
+			*rqlist = next;
+			prev = NULL;
+		} else
+			prev = req;
+	}
+
+	*rqlist = requeue_list;
+}
+
 /* return id (s/n) string for *disk to *id_str
  */
 static int virtblk_get_id(struct gendisk *disk, char *id_str)
@@ -794,6 +875,7 @@ static int virtblk_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 
 static const struct blk_mq_ops virtio_mq_ops = {
 	.queue_rq	= virtio_queue_rq,
+	.queue_rqs	= virtio_queue_rqs,
 	.commit_rqs	= virtio_commit_rqs,
 	.init_hctx	= virtblk_init_hctx,
 	.complete	= virtblk_request_done,