1 files changed, 40 insertions, 13 deletions

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 4a3e65626e8b..56030d45823a 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -291,11 +291,7 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
 					  struct udp_table *udptable)
 {
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
-	struct sock *sk;
 
-	sk = skb_steal_sock(skb);
-	if (unlikely(sk))
-		return sk;
 	return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
 				 &iph->daddr, dport, inet6_iif(skb),
 				 udptable, skb);
@@ -332,6 +328,15 @@ struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be
 EXPORT_SYMBOL_GPL(udp6_lib_lookup);
 #endif
 
+/* do not use the scratch area len for jumbogram: their length execeeds the
+ * scratch area space; note that the IP6CB flags is still in the first
+ * cacheline, so checking for jumbograms is cheap
+ */
+static int udp6_skb_len(struct sk_buff *skb)
+{
+	return unlikely(inet6_is_jumbogram(skb)) ? skb->len : udp_skb_len(skb);
+}
+
 /*
  *	This should be easy, if there is something there we
  *	return it, otherwise we block.
@@ -357,12 +362,13 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
 
 try_again:
-	peeking = off = sk_peek_offset(sk, flags);
+	peeking = flags & MSG_PEEK;
+	off = sk_peek_offset(sk, flags);
 	skb = __skb_recv_udp(sk, flags, noblock, &peeked, &off, &err);
 	if (!skb)
 		return err;
 
-	ulen = udp_skb_len(skb);
+	ulen = udp6_skb_len(skb);
 	copied = len;
 	if (copied > ulen - off)
 		copied = ulen - off;
@@ -569,8 +575,7 @@ static __inline__ void udpv6_err(struct sk_buff *skb,
 static struct static_key udpv6_encap_needed __read_mostly;
 void udpv6_encap_enable(void)
 {
-	if (!static_key_enabled(&udpv6_encap_needed))
-		static_key_slow_inc(&udpv6_encap_needed);
+	static_key_enable(&udpv6_encap_needed);
 }
 EXPORT_SYMBOL(udpv6_encap_enable);
 
@@ -762,6 +767,15 @@ start_lookup:
 	return 0;
 }
 
+static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
+{
+	if (udp_sk_rx_dst_set(sk, dst)) {
+		const struct rt6_info *rt = (const struct rt6_info *)dst;
+
+		inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt);
+	}
+}
+
 int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		   int proto)
 {
@@ -804,6 +818,24 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (udp6_csum_init(skb, uh, proto))
 		goto csum_error;
 
+	/* Check if the socket is already available, e.g. due to early demux */
+	sk = skb_steal_sock(skb);
+	if (sk) {
+		struct dst_entry *dst = skb_dst(skb);
+		int ret;
+
+		if (unlikely(sk->sk_rx_dst != dst))
+			udp6_sk_rx_dst_set(sk, dst);
+
+		ret = udpv6_queue_rcv_skb(sk, skb);
+		sock_put(sk);
+
+		/* a return value > 0 means to resubmit the input */
+		if (ret > 0)
+			return ret;
+		return 0;
+	}
+
 	/*
 	 *	Multicast receive code
 	 */
@@ -812,11 +844,6 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 				saddr, daddr, udptable, proto);
 
 	/* Unicast */
-
-	/*
-	 * check socket cache ... must talk to Alan about his plans
-	 * for sock caches... i'll skip this for now.
-	 */
 	sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
 	if (sk) {
 		int ret;