tuntap: XDP_TX can use native XDP

Now we have ndo_xdp_xmit, switch to use it instead of the slow generic
XDP TX routine. XDP_TX on TAP gets ~20% improvements from ~1.5Mpps to
~1.8Mpps on 2.60GHz Core(TM) i7-5600U.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/tun.c

@@ -1613,7 +1613,6 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	unsigned int delta = 0;
 	char *buf;
 	size_t copied;
-	bool xdp_xmit = false;
 	int err, pad = TUN_RX_PAD;
 
 	rcu_read_lock();
@@ -1671,8 +1670,14 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 			preempt_enable();
 			return NULL;
 		case XDP_TX:
-			xdp_xmit = true;
-			/* fall through */
+			get_page(alloc_frag->page);
+			alloc_frag->offset += buflen;
+			if (tun_xdp_xmit(tun->dev, &xdp))
+				goto err_redirect;
+			tun_xdp_flush(tun->dev);
+			rcu_read_unlock();
+			preempt_enable();
+			return NULL;
 		case XDP_PASS:
 			delta = orig_data - xdp.data;
 			break;
@@ -1699,14 +1704,6 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	get_page(alloc_frag->page);
 	alloc_frag->offset += buflen;
 
-	if (xdp_xmit) {
-		skb->dev = tun->dev;
-		generic_xdp_tx(skb, xdp_prog);
-		rcu_read_unlock();
-		preempt_enable();
-		return NULL;
-	}
-
 	rcu_read_unlock();
 	preempt_enable();