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, 17 insertions, 7 deletions

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index c9c1cb635d9a..e90c80a548ad 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -829,7 +829,8 @@ out:
 static int ipgre_netlink_parms(struct net_device *dev,
 				struct nlattr *data[],
 				struct nlattr *tb[],
-				struct ip_tunnel_parm *parms)
+				struct ip_tunnel_parm *parms,
+				__u32 *fwmark)
 {
 	struct ip_tunnel *t = netdev_priv(dev);
 
@@ -886,6 +887,9 @@ static int ipgre_netlink_parms(struct net_device *dev,
 		t->ignore_df = !!nla_get_u8(data[IFLA_GRE_IGNORE_DF]);
 	}
 
+	if (data[IFLA_GRE_FWMARK])
+		*fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]);
+
 	return 0;
 }
 
@@ -957,6 +961,7 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev,
 {
 	struct ip_tunnel_parm p;
 	struct ip_tunnel_encap ipencap;
+	__u32 fwmark = 0;
 	int err;
 
 	if (ipgre_netlink_encap_parms(data, &ipencap)) {
@@ -967,31 +972,32 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev,
 			return err;
 	}
 
-	err = ipgre_netlink_parms(dev, data, tb, &p);
+	err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark);
 	if (err < 0)
 		return err;
-	return ip_tunnel_newlink(dev, tb, &p);
+	return ip_tunnel_newlink(dev, tb, &p, fwmark);
 }
 
 static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
 			    struct nlattr *data[])
 {
+	struct ip_tunnel *t = netdev_priv(dev);
 	struct ip_tunnel_parm p;
 	struct ip_tunnel_encap ipencap;
+	__u32 fwmark = t->fwmark;
 	int err;
 
 	if (ipgre_netlink_encap_parms(data, &ipencap)) {
-		struct ip_tunnel *t = netdev_priv(dev);
 		err = ip_tunnel_encap_setup(t, &ipencap);
 
 		if (err < 0)
 			return err;
 	}
 
-	err = ipgre_netlink_parms(dev, data, tb, &p);
+	err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark);
 	if (err < 0)
 		return err;
-	return ip_tunnel_changelink(dev, tb, &p);
+	return ip_tunnel_changelink(dev, tb, &p, fwmark);
 }
 
 static size_t ipgre_get_size(const struct net_device *dev)
@@ -1029,6 +1035,8 @@ static size_t ipgre_get_size(const struct net_device *dev)
 		nla_total_size(0) +
 		/* IFLA_GRE_IGNORE_DF */
 		nla_total_size(1) +
+		/* IFLA_GRE_FWMARK */
+		nla_total_size(4) +
 		0;
 }
 
@@ -1049,7 +1057,8 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_u8(skb, IFLA_GRE_TTL, p->iph.ttl) ||
 	    nla_put_u8(skb, IFLA_GRE_TOS, p->iph.tos) ||
 	    nla_put_u8(skb, IFLA_GRE_PMTUDISC,
-		       !!(p->iph.frag_off & htons(IP_DF))))
+		       !!(p->iph.frag_off & htons(IP_DF))) ||
+	    nla_put_u32(skb, IFLA_GRE_FWMARK, t->fwmark))
 		goto nla_put_failure;
 
 	if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE,
@@ -1093,6 +1102,7 @@ static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = {
 	[IFLA_GRE_ENCAP_DPORT]	= { .type = NLA_U16 },
 	[IFLA_GRE_COLLECT_METADATA]	= { .type = NLA_FLAG },
 	[IFLA_GRE_IGNORE_DF]	= { .type = NLA_U8 },
+	[IFLA_GRE_FWMARK]	= { .type = NLA_U32 },
 };
 
 static struct rtnl_link_ops ipgre_link_ops __read_mostly = {