ipv4: Allow ipv6 gateway with ipv4 routes

Add support for RTA_VIA and allow an IPv6 nexthop for v4 routes:
   $ ip ro add 172.16.1.0/24 via inet6 2001:db8::1 dev eth0
   $ ip ro ls
   ...
   172.16.1.0/24 via inet6 2001:db8::1 dev eth0

For convenience and simplicity, userspace can use RTA_VIA to specify
AF_INET or AF_INET6 gateway.

The common fib_nexthop_info dump function compares the gateway address
family to the nh_common family to know if the gateway should be encoded
as RTA_VIA or RTA_GATEWAY.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 121 insertions, 8 deletions

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index f99a2ec32505..310060e67790 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -665,10 +665,55 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = {
 	[RTA_DPORT]		= { .type = NLA_U16 },
 };
 
+int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla,
+		    struct netlink_ext_ack *extack)
+{
+	struct rtvia *via;
+	int alen;
+
+	if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr)) {
+		NL_SET_ERR_MSG(extack, "Invalid attribute length for RTA_VIA");
+		return -EINVAL;
+	}
+
+	via = nla_data(nla);
+	alen = nla_len(nla) - offsetof(struct rtvia, rtvia_addr);
+
+	switch (via->rtvia_family) {
+	case AF_INET:
+		if (alen != sizeof(__be32)) {
+			NL_SET_ERR_MSG(extack, "Invalid IPv4 address in RTA_VIA");
+			return -EINVAL;
+		}
+		cfg->fc_gw_family = AF_INET;
+		cfg->fc_gw4 = *((__be32 *)via->rtvia_addr);
+		break;
+	case AF_INET6:
+#ifdef CONFIG_IPV6
+		if (alen != sizeof(struct in6_addr)) {
+			NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_VIA");
+			return -EINVAL;
+		}
+		cfg->fc_gw_family = AF_INET6;
+		cfg->fc_gw6 = *((struct in6_addr *)via->rtvia_addr);
+#else
+		NL_SET_ERR_MSG(extack, "IPv6 support not enabled in kernel");
+		return -EINVAL;
+#endif
+		break;
+	default:
+		NL_SET_ERR_MSG(extack, "Unsupported address family in RTA_VIA");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 			     struct nlmsghdr *nlh, struct fib_config *cfg,
 			     struct netlink_ext_ack *extack)
 {
+	bool has_gw = false, has_via = false;
 	struct nlattr *attr;
 	int err, remaining;
 	struct rtmsg *rtm;
@@ -709,13 +754,16 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 			cfg->fc_oif = nla_get_u32(attr);
 			break;
 		case RTA_GATEWAY:
+			has_gw = true;
 			cfg->fc_gw_family = AF_INET;
 			cfg->fc_gw4 = nla_get_be32(attr);
 			break;
 		case RTA_VIA:
-			NL_SET_ERR_MSG(extack, "IPv4 does not support RTA_VIA attribute");
-			err = -EINVAL;
-			goto errout;
+			has_via = true;
+			err = fib_gw_from_via(cfg, attr, extack);
+			if (err)
+				goto errout;
+			break;
 		case RTA_PRIORITY:
 			cfg->fc_priority = nla_get_u32(attr);
 			break;
@@ -754,6 +802,12 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 		}
 	}
 
+	if (has_gw && has_via) {
+		NL_SET_ERR_MSG(extack,
+			       "Nexthop configuration can not contain both GATEWAY and VIA");
+		goto errout;
+	}
+
 	return 0;
 errout:
 	return err;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 4a968e24507b..017273885eee 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -606,12 +606,22 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
 
 		attrlen = rtnh_attrlen(rtnh);
 		if (attrlen > 0) {
-			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
+			struct nlattr *nla, *nlav, *attrs = rtnh_attrs(rtnh);
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
+			nlav = nla_find(attrs, attrlen, RTA_VIA);
+			if (nla && nlav) {
+				NL_SET_ERR_MSG(extack,
+					       "Nexthop configuration can not contain both GATEWAY and VIA");
+				return -EINVAL;
+			}
 			if (nla) {
 				fib_cfg.fc_gw_family = AF_INET;
 				fib_cfg.fc_gw4 = nla_get_in_addr(nla);
+			} else if (nlav) {
+				ret = fib_gw_from_via(&fib_cfg, nlav, extack);
+				if (ret)
+					goto errout;
 			}
 
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
@@ -792,11 +802,43 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
 
 		attrlen = rtnh_attrlen(rtnh);
 		if (attrlen > 0) {
-			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
+			struct nlattr *nla, *nlav, *attrs = rtnh_attrs(rtnh);
 
 			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
-			if (nla && nla_get_in_addr(nla) != nh->fib_nh_gw4)
-				return 1;
+			nlav = nla_find(attrs, attrlen, RTA_VIA);
+			if (nla && nlav) {
+				NL_SET_ERR_MSG(extack,
+					       "Nexthop configuration can not contain both GATEWAY and VIA");
+				return -EINVAL;
+			}
+
+			if (nla) {
+				if (nh->fib_nh_gw_family != AF_INET ||
+				    nla_get_in_addr(nla) != nh->fib_nh_gw4)
+					return 1;
+			} else if (nlav) {
+				struct fib_config cfg2;
+				int err;
+
+				err = fib_gw_from_via(&cfg2, nlav, extack);
+				if (err)
+					return err;
+
+				switch (nh->fib_nh_gw_family) {
+				case AF_INET:
+					if (cfg2.fc_gw_family != AF_INET ||
+					    cfg2.fc_gw4 != nh->fib_nh_gw4)
+						return 1;
+					break;
+				case AF_INET6:
+					if (cfg2.fc_gw_family != AF_INET6 ||
+					    ipv6_addr_cmp(&cfg2.fc_gw6,
+							  &nh->fib_nh_gw6))
+						return 1;
+					break;
+				}
+			}
+
 #ifdef CONFIG_IP_ROUTE_CLASSID
 			nla = nla_find(attrs, attrlen, RTA_FLOW);
 			if (nla && nla_get_u32(nla) != nh->nh_tclassid)
@@ -1429,8 +1471,25 @@ int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc,
 			goto nla_put_failure;
 		break;
 	case AF_INET6:
-		if (nla_put_in6_addr(skb, RTA_GATEWAY, &nhc->nhc_gw.ipv6) < 0)
+		/* if gateway family does not match nexthop family
+		 * gateway is encoded as RTA_VIA
+		 */
+		if (nhc->nhc_gw_family != nhc->nhc_family) {
+			int alen = sizeof(struct in6_addr);
+			struct nlattr *nla;
+			struct rtvia *via;
+
+			nla = nla_reserve(skb, RTA_VIA, alen + 2);
+			if (!nla)
+				goto nla_put_failure;
+
+			via = nla_data(nla);
+			via->rtvia_family = AF_INET6;
+			memcpy(via->rtvia_addr, &nhc->nhc_gw.ipv6, alen);
+		} else if (nla_put_in6_addr(skb, RTA_GATEWAY,
+					    &nhc->nhc_gw.ipv6) < 0) {
 			goto nla_put_failure;
+		}
 		break;
 	}