tcp/dccp: do not touch listener sk_refcnt under synflood

When a SYNFLOOD targets a non SO_REUSEPORT listener, multiple
cpus contend on sk->sk_refcnt and sk->sk_wmem_alloc changes.

By letting listeners use SOCK_RCU_FREE infrastructure,
we can relax TCP_LISTEN lookup rules and avoid touching sk_refcnt

Note that we still use SLAB_DESTROY_BY_RCU rules for other sockets,
only listeners are impacted by this change.

Peak performance under SYNFLOOD is increased by ~33% :

On my test machine, I could process 3.2 Mpps instead of 2.4 Mpps

Most consuming functions are now skb_set_owner_w() and sock_wfree()
contending on sk->sk_wmem_alloc when cooking SYNACK and freeing them.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 28332bd..b87beca 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -66,13 +66,15 @@
 					  const __be16 sport,
 					  const struct in6_addr *daddr,
 					  const u16 hnum,
-					  const int dif)
+					  const int dif,
+					  bool *refcounted)
 {
 	struct sock *sk = __inet6_lookup_established(net, hashinfo, saddr,
 						sport, daddr, hnum, dif);
+	*refcounted = true;
 	if (sk)
 		return sk;
-
+	*refcounted = false;
 	return inet6_lookup_listener(net, hashinfo, skb, doff, saddr, sport,
 				     daddr, hnum, dif);
 }
@@ -81,17 +83,19 @@
 					      struct sk_buff *skb, int doff,
 					      const __be16 sport,
 					      const __be16 dport,
-					      int iif)
+					      int iif,
+					      bool *refcounted)
 {
 	struct sock *sk = skb_steal_sock(skb);
 
+	*refcounted = true;
 	if (sk)
 		return sk;
 
 	return __inet6_lookup(dev_net(skb_dst(skb)->dev), hashinfo, skb,
 			      doff, &ipv6_hdr(skb)->saddr, sport,
 			      &ipv6_hdr(skb)->daddr, ntohs(dport),
-			      iif);
+			      iif, refcounted);
 }
 
 struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,