[PATCH net-next] virtio-net: switch to use XPS to choose txq

[Jason Wang]

We used to use a percpu structure vq_index to record the cpu to queue
mapping, this is suboptimal since it duplicates the work of XPS and
loses all other XPS functionality such as allowing use to configure
their own transmission steering strategy.

So this patch switches to use XPS and suggest a default mapping when
the number of cpus is equal to the number of queues. With XPS support,
there's no need for keeping per-cpu vq_index and .ndo_select_queue(),
so they were removed also.

Cc: Rusty Russell <rusty@xxxxxxxxxxxxxxx>
Cc: Michael S. Tsirkin <mst@xxxxxxxxxx>
Signed-off-by: Jason Wang <jasowang@xxxxxxxxxx>
---
 drivers/net/virtio_net.c |   55 +++++++--------------------------------------
 1 files changed, 9 insertions(+), 46 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index defec2b..4102c1b 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -127,9 +127,6 @@ struct virtnet_info {
 	/* Does the affinity hint is set for virtqueues? */
 	bool affinity_hint_set;
 
-	/* Per-cpu variable to show the mapping from CPU to virtqueue */
-	int __percpu *vq_index;
-
 	/* CPU hot plug notifier */
 	struct notifier_block nb;
 };
@@ -1063,7 +1060,6 @@ static int virtnet_vlan_rx_kill_vid(struct net_device *dev,
 static void virtnet_clean_affinity(struct virtnet_info *vi, long hcpu)
 {
 	int i;
-	int cpu;
 
 	if (vi->affinity_hint_set) {
 		for (i = 0; i < vi->max_queue_pairs; i++) {
@@ -1073,20 +1069,11 @@ static void virtnet_clean_affinity(struct virtnet_info *vi, long hcpu)
 
 		vi->affinity_hint_set = false;
 	}
-
-	i = 0;
-	for_each_online_cpu(cpu) {
-		if (cpu == hcpu) {
-			*per_cpu_ptr(vi->vq_index, cpu) = -1;
-		} else {
-			*per_cpu_ptr(vi->vq_index, cpu) =
-				++i % vi->curr_queue_pairs;
-		}
-	}
 }
 
 static void virtnet_set_affinity(struct virtnet_info *vi)
 {
+	cpumask_var_t cpumask;
 	int i;
 	int cpu;
 
@@ -1100,15 +1087,21 @@ static void virtnet_set_affinity(struct virtnet_info *vi)
 		return;
 	}
 
+	if (!alloc_cpumask_var(&cpumask, GFP_KERNEL))
+		return;
+
 	i = 0;
 	for_each_online_cpu(cpu) {
 		virtqueue_set_affinity(vi->rq[i].vq, cpu);
 		virtqueue_set_affinity(vi->sq[i].vq, cpu);
-		*per_cpu_ptr(vi->vq_index, cpu) = i;
+		cpumask_clear(cpumask);
+		cpumask_set_cpu(cpu, cpumask);
+		netif_set_xps_queue(vi->dev, cpumask, i);
 		i++;
 	}
 
 	vi->affinity_hint_set = true;
+	free_cpumask_var(cpumask);
 }
 
 static int virtnet_cpu_callback(struct notifier_block *nfb,
@@ -1217,28 +1210,6 @@ static int virtnet_change_mtu(struct net_device *dev, int new_mtu)
 	return 0;
 }
 
-/* To avoid contending a lock hold by a vcpu who would exit to host, select the
- * txq based on the processor id.
- */
-static u16 virtnet_select_queue(struct net_device *dev, struct sk_buff *skb)
-{
-	int txq;
-	struct virtnet_info *vi = netdev_priv(dev);
-
-	if (skb_rx_queue_recorded(skb)) {
-		txq = skb_get_rx_queue(skb);
-	} else {
-		txq = *__this_cpu_ptr(vi->vq_index);
-		if (txq == -1)
-			txq = 0;
-	}
-
-	while (unlikely(txq >= dev->real_num_tx_queues))
-		txq -= dev->real_num_tx_queues;
-
-	return txq;
-}
-
 static const struct net_device_ops virtnet_netdev = {
 	.ndo_open            = virtnet_open,
 	.ndo_stop   	     = virtnet_close,
@@ -1250,7 +1221,6 @@ static const struct net_device_ops virtnet_netdev = {
 	.ndo_get_stats64     = virtnet_stats,
 	.ndo_vlan_rx_add_vid = virtnet_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid = virtnet_vlan_rx_kill_vid,
-	.ndo_select_queue     = virtnet_select_queue,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = virtnet_netpoll,
 #endif
@@ -1559,10 +1529,6 @@ static int virtnet_probe(struct virtio_device *vdev)
 	if (vi->stats == NULL)
 		goto free;
 
-	vi->vq_index = alloc_percpu(int);
-	if (vi->vq_index == NULL)
-		goto free_stats;
-
 	mutex_init(&vi->config_lock);
 	vi->config_enable = true;
 	INIT_WORK(&vi->config_work, virtnet_config_changed_work);
@@ -1589,7 +1555,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 	/* Allocate/initialize the rx/tx queues, and invoke find_vqs */
 	err = init_vqs(vi);
 	if (err)
-		goto free_index;
+		goto free_stats;
 
 	netif_set_real_num_tx_queues(dev, 1);
 	netif_set_real_num_rx_queues(dev, 1);
@@ -1640,8 +1606,6 @@ free_recv_bufs:
 free_vqs:
 	cancel_delayed_work_sync(&vi->refill);
 	virtnet_del_vqs(vi);
-free_index:
-	free_percpu(vi->vq_index);
 free_stats:
 	free_percpu(vi->stats);
 free:
@@ -1678,7 +1642,6 @@ static void virtnet_remove(struct virtio_device *vdev)
 
 	flush_work(&vi->config_work);
 
-	free_percpu(vi->vq_index);
 	free_percpu(vi->stats);
 	free_netdev(vi->dev);
 }
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/