net/ipv4: add dst cache support for gre lwtunnels

In case of UDP traffic with datagram length below MTU this
gives about 4% performance increase
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Suggested-and-Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/ipv4/ip_gre.c

@@ -540,9 +540,16 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto err_free_skb;
 
 	key = &tun_info->key;
+	rt = !skb->mark ? dst_cache_get_ip4(&tun_info->dst_cache, &fl.saddr) :
+			 NULL;
+	if (!rt) {
 		rt = gre_get_rt(skb, dev, &fl, key);
 		if (IS_ERR(rt))
 				goto err_free_skb;
+		if (!skb->mark)
+			dst_cache_set_ip4(&tun_info->dst_cache, &rt->dst,
+					  fl.saddr);
+	}
 
 	tunnel_hlen = ip_gre_calc_hlen(key->tun_flags);