vxlan: GRO support at tunnel layer

Add calls to gro_cells infrastructure to do GRO when receiving on a tunnel.

Testing:

Ran 200 netperf TCP_STREAM instance

  - With fix (GRO enabled on VXLAN interface)

    Verify GRO is happening.

    9084 MBps tput
    3.44% CPU utilization

  - Without fix (GRO disabled on VXLAN interface)

    Verified no GRO is happening.

    9084 MBps tput
    5.54% CPU utilization
Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/vxlan.c

@@ -1208,7 +1208,7 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb,
 	stats->rx_bytes += skb->len;
 	u64_stats_update_end(&stats->syncp);
 
-	netif_rx(skb);
+	gro_cells_receive(&vxlan->gro_cells, skb);
 
 	return;
 drop:
@@ -2446,6 +2446,8 @@ static void vxlan_setup(struct net_device *dev)
 
 	vxlan->dev = dev;
 
+	gro_cells_init(&vxlan->gro_cells, dev);
+
 	for (h = 0; h < FDB_HASH_SIZE; ++h)
 		INIT_HLIST_HEAD(&vxlan->fdb_head[h]);
 }
@@ -2885,6 +2887,7 @@ static void vxlan_dellink(struct net_device *dev, struct list_head *head)
 		hlist_del_rcu(&vxlan->hlist);
 	spin_unlock(&vn->sock_lock);
 
+	gro_cells_destroy(&vxlan->gro_cells);
 	list_del(&vxlan->next);
 	unregister_netdevice_queue(dev, head);
 }
@@ -3093,9 +3096,11 @@ static void __net_exit vxlan_exit_net(struct net *net)
 		/* If vxlan->dev is in the same netns, it has already been added
 		 * to the list by the previous loop.
 		 */
-		if (!net_eq(dev_net(vxlan->dev), net))
+		if (!net_eq(dev_net(vxlan->dev), net)) {
+			gro_cells_destroy(&vxlan->gro_cells);
 			unregister_netdevice_queue(vxlan->dev, &list);
 		}
+	}
 
 	unregister_netdevice_many(&list);
 	rtnl_unlock();

include/net/vxlan.h

@@ -161,6 +161,7 @@ struct vxlan_dev {
 	struct timer_list age_timer;
 	spinlock_t	  hash_lock;
 	unsigned int	  addrcnt;
+	struct gro_cells  gro_cells;
 
 	struct vxlan_config	cfg;