net: ipv6: fix TCP early demux

IPv6 needs a cookie in dst_check() call.

We need to add rx_dst_cookie and provide a family independent
sk_rx_dst_set(sk, skb) method to properly support IPv6 TCP early demux.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 39 insertions, 7 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2fd2bc9e3c6..85308b90df8 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5392,6 +5392,8 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 {
         struct tcp_sock *tp = tcp_sk(sk);
 
+        if (unlikely(sk->sk_rx_dst == NULL))
+                inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb);
         /*
          *      Header prediction.
          *      The code loosely follows the one in the famous
@@ -5605,7 +5607,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
         tcp_set_state(sk, TCP_ESTABLISHED);
 
         if (skb != NULL) {
-                inet_sk_rx_dst_set(sk, skb);
+                icsk->icsk_af_ops->sk_rx_dst_set(sk, skb);
                 security_inet_conn_established(sk, skb);
         }
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 42b2a6a7309..272241f16fc 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1627,9 +1627,6 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
                                 sk->sk_rx_dst = NULL;
                         }
                 }
-                if (unlikely(sk->sk_rx_dst == NULL))
-                        inet_sk_rx_dst_set(sk, skb);
-
                 if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len)) {
                         rsk = sk;
                         goto reset;
@@ -1872,10 +1869,20 @@ static struct timewait_sock_ops tcp_timewait_sock_ops = {
         .twsk_destructor= tcp_twsk_destructor,
 };
 
+static void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
+{
+        struct dst_entry *dst = skb_dst(skb);
+
+        dst_hold(dst);
+        sk->sk_rx_dst = dst;
+        inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+}
+
 const struct inet_connection_sock_af_ops ipv4_specific = {
         .queue_xmit        = ip_queue_xmit,
         .send_check        = tcp_v4_send_check,
         .rebuild_header    = inet_sk_rebuild_header,
+        .sk_rx_dst_set     = inet_sk_rx_dst_set,
         .conn_request      = tcp_v4_conn_request,
         .syn_recv_sock     = tcp_v4_syn_recv_sock,
         .net_header_len    = sizeof(struct iphdr),
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 232a90c3ec8..d9c9dcef2de 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -387,7 +387,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
                 struct tcp_sock *oldtp = tcp_sk(sk);
                 struct tcp_cookie_values *oldcvp = oldtp->cookie_values;
 
-                inet_sk_rx_dst_set(newsk, skb);
+                newicsk->icsk_af_ops->sk_rx_dst_set(newsk, skb);
 
                 /* TCP Cookie Transactions require space for the cookie pair,
                  * as it differs for each connection.  There is no need to
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index c66b90f71c9..5a439e9a4c0 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1447,7 +1447,17 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
                 opt_skb = skb_clone(skb, sk_gfp_atomic(sk, GFP_ATOMIC));
 
         if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
+                struct dst_entry *dst = sk->sk_rx_dst;
+
                 sock_rps_save_rxhash(sk, skb);
+                if (dst) {
+                        if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
+                            dst->ops->check(dst, np->rx_dst_cookie) == NULL) {
+                                dst_release(dst);
+                                sk->sk_rx_dst = NULL;
+                        }
+                }
+
                 if (tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len))
                         goto reset;
                 if (opt_skb)
@@ -1705,9 +1715,9 @@ static void tcp_v6_early_demux(struct sk_buff *skb)
                         struct dst_entry *dst = sk->sk_rx_dst;
                         struct inet_sock *icsk = inet_sk(sk);
                         if (dst)
-                                dst = dst_check(dst, 0);
+                                dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie);
                         if (dst &&
-                            icsk->rx_dst_ifindex == inet6_iif(skb))
+                            icsk->rx_dst_ifindex == skb->skb_iif)
                                 skb_dst_set_noref(skb, dst);
                 }
         }
@@ -1719,10 +1729,23 @@ static struct timewait_sock_ops tcp6_timewait_sock_ops = {
         .twsk_destructor= tcp_twsk_destructor,
 };
 
+static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
+{
+        struct dst_entry *dst = skb_dst(skb);
+        const struct rt6_info *rt = (const struct rt6_info *)dst;
+
+        dst_hold(dst);
+        sk->sk_rx_dst = dst;
+        inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
+        if (rt->rt6i_node)
+                inet6_sk(sk)->rx_dst_cookie = rt->rt6i_node->fn_sernum;
+}
+
 static const struct inet_connection_sock_af_ops ipv6_specific = {
         .queue_xmit        = inet6_csk_xmit,
         .send_check        = tcp_v6_send_check,
         .rebuild_header    = inet6_sk_rebuild_header,
+        .sk_rx_dst_set     = inet6_sk_rx_dst_set,
         .conn_request      = tcp_v6_conn_request,
         .syn_recv_sock     = tcp_v6_syn_recv_sock,
         .net_header_len    = sizeof(struct ipv6hdr),