netfilter: add nf_ipv6_ops hook to fix xt_addrtype with IPv6

Quoting https://bugzilla.netfilter.org/show_bug.cgi?id=812:

[ ip6tables -m addrtype ]
When I tried to use in the nat/PREROUTING it messes up the
routing cache even if the rule didn't matched at all.
[..]
If I remove the --limit-iface-in from the non-working scenario, so just
use the -m addrtype --dst-type LOCAL it works!

This happens when LOCAL type matching is requested with --limit-iface-in,
and the default ipv6 route is via the interface the packet we test
arrived on.

Because xt_addrtype uses ip6_route_output, the ipv6 routing implementation
creates an unwanted cached entry, and the packet won't make it to the
real/expected destination.

Silently ignoring --limit-iface-in makes the routing work but it breaks
rule matching (--dst-type LOCAL with limit-iface-in is supposed to only
match if the dst address is configured on the incoming interface;
without --limit-iface-in it will match if the address is reachable
via lo).

The test should call ipv6_chk_addr() instead. However, this would add
a link-time dependency on ipv6.

There are two possible solutions:

1) Revert the commit that moved ipt_addrtype to xt_addrtype,
and put ipv6 specific code into ip6t_addrtype.
2) add new "nf_ipv6_ops" struct to register pointers to ipv6 functions.

While the former might seem preferable, Pablo pointed out that there
are more xt modules with link-time dependeny issues regarding ipv6,
so lets go for 2).

Signed-off-by: Florian Westphal <[e-mail]>
Signed-off-by: Pablo Neira Ayuso <[e-mail]>

include/linux/netfilter_ipv6.h

···
 
 extern int ipv6_netfilter_init(void);
 extern void ipv6_netfilter_fini(void);
+
+/*
+ * Hook functions for ipv6 to allow xt_* modules to be built-in even
+ * if IPv6 is a module.
+ */
+struct nf_ipv6_ops {
+	int (*chk_addr)(struct net *net, const struct in6_addr *addr,
+			const struct net_device *dev, int strict);
+};
+
+extern const struct nf_ipv6_ops __rcu *nf_ipv6_ops;
+static inline const struct nf_ipv6_ops *nf_get_ipv6_ops(void)
+{
+	return rcu_dereference(nf_ipv6_ops);
+}
+
 #else /* CONFIG_NETFILTER */
 static inline int ipv6_netfilter_init(void) { return 0; }
 static inline void ipv6_netfilter_fini(void) { return; }

include/net/addrconf.h

···
 
 extern int			ipv6_chk_addr(struct net *net,
 					      const struct in6_addr *addr,
-					      struct net_device *dev,
+					      const struct net_device *dev,
 					      int strict);
 
 #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)

net/ipv6/addrconf.c

···
 }
 
 int ipv6_chk_addr(struct net *net, const struct in6_addr *addr,
-		  struct net_device *dev, int strict)
+		  const struct net_device *dev, int strict)
 {
 	struct inet6_ifaddr *ifp;
 	unsigned int hash = inet6_addr_hash(addr);

net/ipv6/netfilter.c

···
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv6.h>
 #include <linux/export.h>
+#include <net/addrconf.h>
 #include <net/dst.h>
 #include <net/ipv6.h>
 #include <net/ip6_route.h>
···
 	return csum;
 };
 
+static const struct nf_ipv6_ops ipv6ops = {
+	.chk_addr	= ipv6_chk_addr,
+};
+
 static const struct nf_afinfo nf_ip6_afinfo = {
 	.family			= AF_INET6,
 	.checksum		= nf_ip6_checksum,
···
 
 int __init ipv6_netfilter_init(void)
 {
+	RCU_INIT_POINTER(nf_ipv6_ops, &ipv6ops);
 	return nf_register_afinfo(&nf_ip6_afinfo);
 }
 
···
  */
 void ipv6_netfilter_fini(void)
 {
+	RCU_INIT_POINTER(nf_ipv6_ops, NULL);
 	nf_unregister_afinfo(&nf_ip6_afinfo);
 }

net/netfilter/core.c

···
 
 const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly;
 EXPORT_SYMBOL(nf_afinfo);
+const struct nf_ipv6_ops __rcu *nf_ipv6_ops __read_mostly;
+EXPORT_SYMBOL_GPL(nf_ipv6_ops);
 
 int nf_register_afinfo(const struct nf_afinfo *afinfo)
 {

net/netfilter/xt_addrtype.c

···
 #include <net/ip6_fib.h>
 #endif
 
+#include <linux/netfilter_ipv6.h>
 #include <linux/netfilter/xt_addrtype.h>
 #include <linux/netfilter/x_tables.h>
 
···
 
 #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 static u32 match_lookup_rt6(struct net *net, const struct net_device *dev,
-			    const struct in6_addr *addr)
+			    const struct in6_addr *addr, u16 mask)
 {
 	const struct nf_afinfo *afinfo;
 	struct flowi6 flow;
 	struct rt6_info *rt;
-	u32 ret;
+	u32 ret = 0;
 	int route_err;
 
 	memset(&flow, 0, sizeof(flow));
···
 	rcu_read_lock();
 
 	afinfo = nf_get_afinfo(NFPROTO_IPV6);
-	if (afinfo != NULL)
-		route_err = afinfo->route(net, (struct dst_entry **)&rt,
-					flowi6_to_flowi(&flow), !!dev);
-	else
-		route_err = 1;
+	if (afinfo != NULL) {
+		const struct nf_ipv6_ops *v6ops;
 
+		if (dev && (mask & XT_ADDRTYPE_LOCAL)) {
+			v6ops = nf_get_ipv6_ops();
+			if (v6ops && v6ops->chk_addr(net, addr, dev, true))
+				ret = XT_ADDRTYPE_LOCAL;
+		}
+		route_err = afinfo->route(net, (struct dst_entry **)&rt,
+					  flowi6_to_flowi(&flow), false);
+	} else {
+		route_err = 1;
+	}
 	rcu_read_unlock();
 
 	if (route_err)
···
 
 	if (rt->rt6i_flags & RTF_REJECT)
 		ret = XT_ADDRTYPE_UNREACHABLE;
-	else
-		ret = 0;
 
-	if (rt->rt6i_flags & RTF_LOCAL)
+	if (dev == NULL && rt->rt6i_flags & RTF_LOCAL)
 		ret |= XT_ADDRTYPE_LOCAL;
 	if (rt->rt6i_flags & RTF_ANYCAST)
 		ret |= XT_ADDRTYPE_ANYCAST;
-
 
 	dst_release(&rt->dst);
 	return ret;
···
 
 	if ((XT_ADDRTYPE_LOCAL | XT_ADDRTYPE_ANYCAST |
 	     XT_ADDRTYPE_UNREACHABLE) & mask)
-		return !!(mask & match_lookup_rt6(net, dev, addr));
+		return !!(mask & match_lookup_rt6(net, dev, addr, mask));
 	return true;
 }