tun: switch to use skb array for tx

We used to queue tx packets in sk_receive_queue, this is less
efficient since it requires spinlocks to synchronize between producer
and consumer.

This patch tries to address this by:

- switch from sk_receive_queue to a skb_array, and resize it when
  tx_queue_len was changed.
- introduce a new proto_ops peek_len which was used for peeking the
  skb length.
- implement a tun version of peek_len for vhost_net to use and convert
  vhost_net to use peek_len if possible.

Pktgen test shows about 15.3% improvement on guest receiving pps for small
buffers:

Before: ~1300000pps
After : ~1500000pps

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/vhost/net.c

@@ -481,10 +481,14 @@ out:
 
 static int peek_head_len(struct sock *sk)
 {
+	struct socket *sock = sk->sk_socket;
 	struct sk_buff *head;
 	int len = 0;
 	unsigned long flags;
 
+	if (sock->ops->peek_len)
+		return sock->ops->peek_len(sock);
+
 	spin_lock_irqsave(&sk->sk_receive_queue.lock, flags);
 	head = skb_peek(&sk->sk_receive_queue);
 	if (likely(head)) {
@@ -497,6 +501,16 @@ static int peek_head_len(struct sock *sk)
 	return len;
 }
 
+static int sk_has_rx_data(struct sock *sk)
+{
+	struct socket *sock = sk->sk_socket;
+
+	if (sock->ops->peek_len)
+		return sock->ops->peek_len(sock);
+
+	return skb_queue_empty(&sk->sk_receive_queue);
+}
+
 static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 {
 	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
@@ -513,7 +527,7 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 		endtime = busy_clock() + vq->busyloop_timeout;
 
 		while (vhost_can_busy_poll(&net->dev, endtime) &&
-		       skb_queue_empty(&sk->sk_receive_queue) &&
+		       !sk_has_rx_data(sk) &&
 		       vhost_vq_avail_empty(&net->dev, vq))
 			cpu_relax_lowlatency();