virtio-net: support dim profile fine-tuning

Virtio-net has different types of back-end device implementations.
In order to effectively optimize the dim library's gains for different
device implementations, let's use the new interface params to
initialize and query dim results from a customized profile list.
Signed-off-by: Heng Qi <hengqi@linux.alibaba.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240621101353.107425-6-hengqi@linux.alibaba.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/virtio_net.c

@@ -2469,6 +2469,13 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
 	return err;
 }
 
+static void virtnet_cancel_dim(struct virtnet_info *vi, struct dim *dim)
+{
+	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL))
+		return;
+	net_dim_work_cancel(dim);
+}
+
 static int virtnet_open(struct net_device *dev)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
@@ -2495,7 +2502,7 @@ static int virtnet_open(struct net_device *dev)
 
 	for (i--; i >= 0; i--) {
 		virtnet_disable_queue_pair(vi, i);
-		cancel_work_sync(&vi->rq[i].dim.work);
+		virtnet_cancel_dim(vi, &vi->rq[i].dim);
 	}
 
 	return err;
@@ -2671,7 +2678,7 @@ static int virtnet_rx_resize(struct virtnet_info *vi,
 
 	if (running) {
 		napi_disable(&rq->napi);
-		cancel_work_sync(&rq->dim.work);
+		virtnet_cancel_dim(vi, &rq->dim);
 	}
 
 	err = virtqueue_resize(rq->vq, ring_num, virtnet_rq_unmap_free_buf);
@@ -2932,7 +2939,7 @@ static int virtnet_close(struct net_device *dev)
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		virtnet_disable_queue_pair(vi, i);
-		cancel_work_sync(&vi->rq[i].dim.work);
+		virtnet_cancel_dim(vi, &vi->rq[i].dim);
 	}
 
 	return 0;
@@ -4458,7 +4465,7 @@ static void virtnet_rx_dim_work(struct work_struct *work)
 	if (!rq->dim_enabled)
 		goto out;
 
-	update_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
+	update_moder = net_dim_get_rx_irq_moder(dev, dim);
 	if (update_moder.usec != rq->intr_coal.max_usecs ||
 	    update_moder.pkts != rq->intr_coal.max_packets) {
 		err = virtnet_send_rx_ctrl_coal_vq_cmd(vi, qnum,
@@ -5158,6 +5165,36 @@ static void virtnet_tx_timeout(struct net_device *dev, unsigned int txqueue)
 		   jiffies_to_usecs(jiffies - READ_ONCE(txq->trans_start)));
 }
 
+static int virtnet_init_irq_moder(struct virtnet_info *vi)
+{
+	u8 profile_flags = 0, coal_flags = 0;
+	int ret, i;
+
+	profile_flags |= DIM_PROFILE_RX;
+	coal_flags |= DIM_COALESCE_USEC | DIM_COALESCE_PKTS;
+	ret = net_dim_init_irq_moder(vi->dev, profile_flags, coal_flags,
+				     DIM_CQ_PERIOD_MODE_START_FROM_EQE,
+				     0, virtnet_rx_dim_work, NULL);
+
+	if (ret)
+		return ret;
+
+	for (i = 0; i < vi->max_queue_pairs; i++)
+		net_dim_setting(vi->dev, &vi->rq[i].dim, false);
+
+	return 0;
+}
+
+static void virtnet_free_irq_moder(struct virtnet_info *vi)
+{
+	if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL))
+		return;
+
+	rtnl_lock();
+	net_dim_free_irq_moder(vi->dev);
+	rtnl_unlock();
+}
+
 static const struct net_device_ops virtnet_netdev = {
 	.ndo_open            = virtnet_open,
 	.ndo_stop   	     = virtnet_close,
@@ -5437,9 +5474,6 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
 					 virtnet_poll_tx,
 					 napi_tx ? napi_weight : 0);
 
-		INIT_WORK(&vi->rq[i].dim.work, virtnet_rx_dim_work);
-		vi->rq[i].dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
-
 		sg_init_table(vi->rq[i].sg, ARRAY_SIZE(vi->rq[i].sg));
 		ewma_pkt_len_init(&vi->rq[i].mrg_avg_pkt_len);
 		sg_init_table(vi->sq[i].sg, ARRAY_SIZE(vi->sq[i].sg));
@@ -5868,6 +5902,10 @@ static int virtnet_probe(struct virtio_device *vdev)
 		for (i = 0; i < vi->max_queue_pairs; i++)
 			if (vi->sq[i].napi.weight)
 				vi->sq[i].intr_coal.max_packets = 1;
+
+		err = virtnet_init_irq_moder(vi);
+		if (err)
+			goto free;
 	}
 
 #ifdef CONFIG_SYSFS
@@ -6019,6 +6057,8 @@ static void virtnet_remove(struct virtio_device *vdev)
 	disable_rx_mode_work(vi);
 	flush_work(&vi->rx_mode_work);
 
+	virtnet_free_irq_moder(vi);
+
 	unregister_netdev(vi->dev);
 
 	net_failover_destroy(vi->failover);