ip_tunnel: Allow policy-based routing through tunnels

This feature allows the administrator to set an fwmark for
packets traversing a tunnel.  This allows the use of independent
routing tables for tunneled packets without the use of iptables.

There is no concept of per-packet routing decisions through IPv4
tunnels, so this implementation does not need to work with
per-packet route lookups as the v6 implementation may
(with IP6_TNL_F_USE_ORIG_FWMARK).

Further, since the v4 tunnel ioctls share datastructures
(which can not be trivially modified) with the kernel's internal
tunnel configuration structures, the mark attribute must be stored
in the tunnel structure itself and passed as a parameter when
creating or changing tunnel attributes.

Signed-off-by: Craig Gallek <kraig@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 24 insertions, 13 deletions

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 99853c6..61e5902 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -881,11 +881,12 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 			goto tx_error;
 	}
 
-	rt = ip_route_output_ports(tunnel->net, &fl4, NULL,
-				   dst, tiph->saddr,
-				   0, 0,
-				   IPPROTO_IPV6, RT_TOS(tos),
-				   tunnel->parms.link);
+	flowi4_init_output(&fl4, tunnel->parms.link, tunnel->fwmark,
+			   RT_TOS(tos), RT_SCOPE_UNIVERSE, IPPROTO_IPV6,
+			   0, dst, tiph->saddr, 0, 0,
+			   sock_net_uid(tunnel->net, NULL));
+	rt = ip_route_output_flow(tunnel->net, &fl4, NULL);
+
 	if (IS_ERR(rt)) {
 		dev->stats.tx_carrier_errors++;
 		goto tx_error_icmp;
@@ -1071,7 +1072,8 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
 	}
 }
 
-static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p)
+static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p,
+				__u32 fwmark)
 {
 	struct net *net = t->net;
 	struct sit_net *sitn = net_generic(net, sit_net_id);
@@ -1085,8 +1087,9 @@ static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm *p)
 	ipip6_tunnel_link(sitn, t);
 	t->parms.iph.ttl = p->iph.ttl;
 	t->parms.iph.tos = p->iph.tos;
-	if (t->parms.link != p->link) {
+	if (t->parms.link != p->link || t->fwmark != fwmark) {
 		t->parms.link = p->link;
+		t->fwmark = fwmark;
 		ipip6_tunnel_bind_dev(t->dev);
 	}
 	dst_cache_reset(&t->dst_cache);
@@ -1220,7 +1223,7 @@ ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 				t = netdev_priv(dev);
 			}
 
-			ipip6_tunnel_update(t, &p);
+			ipip6_tunnel_update(t, &p, t->fwmark);
 		}
 
 		if (t) {
@@ -1418,7 +1421,8 @@ static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[])
 }
 
 static void ipip6_netlink_parms(struct nlattr *data[],
-				struct ip_tunnel_parm *parms)
+				struct ip_tunnel_parm *parms,
+				__u32 *fwmark)
 {
 	memset(parms, 0, sizeof(*parms));
 
@@ -1457,6 +1461,8 @@ static void ipip6_netlink_parms(struct nlattr *data[],
 	if (data[IFLA_IPTUN_PROTO])
 		parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]);
 
+	if (data[IFLA_IPTUN_FWMARK])
+		*fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]);
 }
 
 /* This function returns true when ENCAP attributes are present in the nl msg */
@@ -1549,7 +1555,7 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev,
 			return err;
 	}
 
-	ipip6_netlink_parms(data, &nt->parms);
+	ipip6_netlink_parms(data, &nt->parms, &nt->fwmark);
 
 	if (ipip6_tunnel_locate(net, &nt->parms, 0))
 		return -EEXIST;
@@ -1577,6 +1583,7 @@ static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[],
 #ifdef CONFIG_IPV6_SIT_6RD
 	struct ip_tunnel_6rd ip6rd;
 #endif
+	__u32 fwmark = t->fwmark;
 	int err;
 
 	if (dev == sitn->fb_tunnel_dev)
@@ -1588,7 +1595,7 @@ static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[],
 			return err;
 	}
 
-	ipip6_netlink_parms(data, &p);
+	ipip6_netlink_parms(data, &p, &fwmark);
 
 	if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) ||
 	    (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr))
@@ -1602,7 +1609,7 @@ static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[],
 	} else
 		t = netdev_priv(dev);
 
-	ipip6_tunnel_update(t, &p);
+	ipip6_tunnel_update(t, &p, fwmark);
 
 #ifdef CONFIG_IPV6_SIT_6RD
 	if (ipip6_netlink_6rd_parms(data, &ip6rd))
@@ -1649,6 +1656,8 @@ static size_t ipip6_get_size(const struct net_device *dev)
 		nla_total_size(2) +
 		/* IFLA_IPTUN_ENCAP_DPORT */
 		nla_total_size(2) +
+		/* IFLA_IPTUN_FWMARK */
+		nla_total_size(4) +
 		0;
 }
 
@@ -1665,7 +1674,8 @@ static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_IPTUN_PMTUDISC,
 		       !!(parm->iph.frag_off & htons(IP_DF))) ||
 	    nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) ||
-	    nla_put_be16(skb, IFLA_IPTUN_FLAGS, parm->i_flags))
+	    nla_put_be16(skb, IFLA_IPTUN_FLAGS, parm->i_flags) ||
+	    nla_put_u32(skb, IFLA_IPTUN_FWMARK, tunnel->fwmark))
 		goto nla_put_failure;
 
 #ifdef CONFIG_IPV6_SIT_6RD
@@ -1715,6 +1725,7 @@ static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = {
 	[IFLA_IPTUN_ENCAP_FLAGS]	= { .type = NLA_U16 },
 	[IFLA_IPTUN_ENCAP_SPORT]	= { .type = NLA_U16 },
 	[IFLA_IPTUN_ENCAP_DPORT]	= { .type = NLA_U16 },
+	[IFLA_IPTUN_FWMARK]		= { .type = NLA_U32 },
 };
 
 static void ipip6_dellink(struct net_device *dev, struct list_head *head)