netfilter: af_info: add 'strict' parameter to limit lookup to .oif

ipv6 fib lookup can set RT6_LOOKUP_F_IFACE flag to restrict search
to an interface, but this flag cannot be set via struct flowi.

Also, it cannot be set via ip6_route_output: this function uses the
passed sock struct to determine if this flag is required
(by testing for nonzero sk_bound_dev_if).

Work around this by passing in an artificial struct sk in case
'strict' argument is true.

This is required to replace the rt6_lookup call in xt_addrtype.c with
nf_afinfo->route().

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Patrick McHardy <kaber@trash.net>

5 files changed, 17 insertions, 9 deletions

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 20ed4528e850..7fa95df60146 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -271,7 +271,7 @@ struct nf_afinfo {
                                             unsigned int len,
                                             u_int8_t protocol);
         int             (*route)(struct net *net, struct dst_entry **dst,
-                                 struct flowi *fl);
+                                 struct flowi *fl, bool strict);
         void            (*saveroute)(const struct sk_buff *skb,
                                      struct nf_queue_entry *entry);
         int             (*reroute)(struct sk_buff *skb,
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index f1035f056503..4614babdc45f 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -222,7 +222,7 @@ static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook,
 }
 
 static int nf_ip_route(struct net *net, struct dst_entry **dst,
-                       struct flowi *fl)
+                       struct flowi *fl, bool strict __always_unused)
 {
         struct rtable *rt = ip_route_output_key(net, &fl->u.ip4);
         if (IS_ERR(rt))
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index e008b9b4a779..28bc1f644b7b 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -91,9 +91,17 @@ static int nf_ip6_reroute(struct sk_buff *skb,
 }
 
 static int nf_ip6_route(struct net *net, struct dst_entry **dst,
-                        struct flowi *fl)
+                        struct flowi *fl, bool strict)
 {
-        *dst = ip6_route_output(net, NULL, &fl->u.ip6);
+        static const struct ipv6_pinfo fake_pinfo;
+        static const struct inet_sock fake_sk = {
+                /* makes ip6_route_output set RT6_LOOKUP_F_IFACE: */
+                .sk.sk_bound_dev_if = 1,
+                .pinet6 = (struct ipv6_pinfo *) &fake_pinfo,
+        };
+        const void *sk = strict ? &fake_sk : NULL;
+
+        *dst = ip6_route_output(net, sk, &fl->u.ip6);
         return (*dst)->error;
 }
 
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index 39a453895b4d..18b2ce5c8ced 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -732,9 +732,9 @@ static int callforward_do_filter(const union nf_inet_addr *src,
                 memset(&fl2, 0, sizeof(fl2));
                 fl2.daddr = dst->ip;
                 if (!afinfo->route(&init_net, (struct dst_entry **)&rt1,
-                                   flowi4_to_flowi(&fl1))) {
+                                   flowi4_to_flowi(&fl1), false)) {
                         if (!afinfo->route(&init_net, (struct dst_entry **)&rt2,
-                                           flowi4_to_flowi(&fl2))) {
+                                           flowi4_to_flowi(&fl2), false)) {
                                 if (rt1->rt_gateway == rt2->rt_gateway &&
                                     rt1->dst.dev  == rt2->dst.dev)
                                         ret = 1;
@@ -756,9 +756,9 @@ static int callforward_do_filter(const union nf_inet_addr *src,
                 memset(&fl2, 0, sizeof(fl2));
                 ipv6_addr_copy(&fl2.daddr, &dst->in6);
                 if (!afinfo->route(&init_net, (struct dst_entry **)&rt1,
-                                   flowi6_to_flowi(&fl1))) {
+                                   flowi6_to_flowi(&fl1), false)) {
                         if (!afinfo->route(&init_net, (struct dst_entry **)&rt2,
-                                           flowi6_to_flowi(&fl2))) {
+                                           flowi6_to_flowi(&fl2), false)) {
                                 if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway,
                                             sizeof(rt1->rt6i_gateway)) &&
                                     rt1->dst.dev == rt2->dst.dev)
diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c
index 8690125e3b18..9e63b43faeed 100644
--- a/net/netfilter/xt_TCPMSS.c
+++ b/net/netfilter/xt_TCPMSS.c
@@ -166,7 +166,7 @@ static u_int32_t tcpmss_reverse_mtu(const struct sk_buff *skb,
         rcu_read_lock();
         ai = nf_get_afinfo(family);
         if (ai != NULL)
-                ai->route(&init_net, (struct dst_entry **)&rt, &fl);
+                ai->route(&init_net, (struct dst_entry **)&rt, &fl, false);
         rcu_read_unlock();
 
         if (rt != NULL) {