netfilter: socket: Lookup orig tuple for IPv6 SNAT

commit 932b32ffd7604fb00b5c57e239a3cc4d901ccf6e upstream.

nf_sk_lookup_slow_v4 does the conntrack lookup for IPv4 packets to
restore the original 5-tuple in case of SNAT, to be able to find the
right socket (if any). Then socket_match() can correctly check whether
the socket was transparent.

However, the IPv6 counterpart (nf_sk_lookup_slow_v6) lacks this
conntrack lookup, making xt_socket fail to match on the socket when the
packet was SNATed. Add the same logic to nf_sk_lookup_slow_v6.

IPv6 SNAT is used in Kubernetes clusters for pod-to-world packets, as
pods' addresses are in the fd00::/8 ULA subnet and need to be replaced
with the node's external address. Cilium leverages Envoy to enforce L7
policies, and Envoy uses transparent sockets. Cilium inserts an iptables
prerouting rule that matches on `-m socket --transparent` and redirects
the packets to localhost, but it fails to match SNATed IPv6 packets due
to that missing conntrack lookup.

Closes: https://github.com/cilium/cilium/issues/37932
Fixes: eb31628e37a0 ("netfilter: nf_tables: Add support for IPv6 NAT")
Signed-off-by: Maxim Mikityanskiy <maxim@isovalent.com>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/net/ipv6/netfilter/nf_socket_ipv6.c b/net/ipv6/netfilter/nf_socket_ipv6.c
index aa5bb8789ba0b44f075ae6a8992132062762b8fa..697b9e60e24ed2ca5d0cb68a3a876ac7e9336ed8 100644 (file)
--- a/net/ipv6/netfilter/nf_socket_ipv6.c
+++ b/net/ipv6/netfilter/nf_socket_ipv6.c
@@ -103,6 +103,10 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb,
        struct sk_buff *data_skb = NULL;
        int doff = 0;
        int thoff = 0, tproto;
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+       enum ip_conntrack_info ctinfo;
+       struct nf_conn const *ct;
+#endif
 
        tproto = ipv6_find_hdr(skb, &thoff, -1, NULL, NULL);
        if (tproto < 0) {
@@ -136,6 +140,25 @@ struct sock *nf_sk_lookup_slow_v6(struct net *net, const struct sk_buff *skb,
                return NULL;
        }
 
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+       /* Do the lookup with the original socket address in
+        * case this is a reply packet of an established
+        * SNAT-ted connection.
+        */
+       ct = nf_ct_get(skb, &ctinfo);
+       if (ct &&
+           ((tproto != IPPROTO_ICMPV6 &&
+             ctinfo == IP_CT_ESTABLISHED_REPLY) ||
+            (tproto == IPPROTO_ICMPV6 &&
+             ctinfo == IP_CT_RELATED_REPLY)) &&
+           (ct->status & IPS_SRC_NAT_DONE)) {
+               daddr = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in6;
+               dport = (tproto == IPPROTO_TCP) ?
+                       ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port :
+                       ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port;
+       }
+#endif
+
        return nf_socket_get_sock_v6(net, data_skb, doff, tproto, saddr, daddr,
                                     sport, dport, indev);
 }