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, 10 deletions

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 823abaef006b..b878ecbc0608 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -293,7 +293,8 @@ failed:
 static inline void init_tunnel_flow(struct flowi4 *fl4,
 				    int proto,
 				    __be32 daddr, __be32 saddr,
-				    __be32 key, __u8 tos, int oif)
+				    __be32 key, __u8 tos, int oif,
+				    __u32 mark)
 {
 	memset(fl4, 0, sizeof(*fl4));
 	fl4->flowi4_oif = oif;
@@ -302,6 +303,7 @@ static inline void init_tunnel_flow(struct flowi4 *fl4,
 	fl4->flowi4_tos = tos;
 	fl4->flowi4_proto = proto;
 	fl4->fl4_gre_key = key;
+	fl4->flowi4_mark = mark;
 }
 
 static int ip_tunnel_bind_dev(struct net_device *dev)
@@ -322,7 +324,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 
 		init_tunnel_flow(&fl4, iph->protocol, iph->daddr,
 				 iph->saddr, tunnel->parms.o_key,
-				 RT_TOS(iph->tos), tunnel->parms.link);
+				 RT_TOS(iph->tos), tunnel->parms.link,
+				 tunnel->fwmark);
 		rt = ip_route_output_key(tunnel->net, &fl4);
 
 		if (!IS_ERR(rt)) {
@@ -578,7 +581,7 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto)
 			tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
 	}
 	init_tunnel_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, 0,
-			 RT_TOS(tos), tunnel->parms.link);
+			 RT_TOS(tos), tunnel->parms.link, tunnel->fwmark);
 	if (tunnel->encap.type != TUNNEL_ENCAP_NONE)
 		goto tx_error;
 	rt = ip_route_output_key(tunnel->net, &fl4);
@@ -707,7 +710,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	}
 
 	init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
-			 tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link);
+			 tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link,
+			 tunnel->fwmark);
 
 	if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0)
 		goto tx_error;
@@ -795,7 +799,8 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn,
 			     struct ip_tunnel *t,
 			     struct net_device *dev,
 			     struct ip_tunnel_parm *p,
-			     bool set_mtu)
+			     bool set_mtu,
+			     __u32 fwmark)
 {
 	ip_tunnel_del(itn, t);
 	t->parms.iph.saddr = p->iph.saddr;
@@ -812,10 +817,11 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn,
 	t->parms.iph.tos = p->iph.tos;
 	t->parms.iph.frag_off = p->iph.frag_off;
 
-	if (t->parms.link != p->link) {
+	if (t->parms.link != p->link || t->fwmark != fwmark) {
 		int mtu;
 
 		t->parms.link = p->link;
+		t->fwmark = fwmark;
 		mtu = ip_tunnel_bind_dev(dev);
 		if (set_mtu)
 			dev->mtu = mtu;
@@ -893,7 +899,7 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd)
 
 		if (t) {
 			err = 0;
-			ip_tunnel_update(itn, t, dev, p, true);
+			ip_tunnel_update(itn, t, dev, p, true, 0);
 		} else {
 			err = -ENOENT;
 		}
@@ -1066,7 +1072,7 @@ void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops)
 EXPORT_SYMBOL_GPL(ip_tunnel_delete_net);
 
 int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
-		      struct ip_tunnel_parm *p)
+		      struct ip_tunnel_parm *p, __u32 fwmark)
 {
 	struct ip_tunnel *nt;
 	struct net *net = dev_net(dev);
@@ -1087,6 +1093,7 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
 
 	nt->net = net;
 	nt->parms = *p;
+	nt->fwmark = fwmark;
 	err = register_netdevice(dev);
 	if (err)
 		goto out;
@@ -1105,7 +1112,7 @@ out:
 EXPORT_SYMBOL_GPL(ip_tunnel_newlink);
 
 int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
-			 struct ip_tunnel_parm *p)
+			 struct ip_tunnel_parm *p, __u32 fwmark)
 {
 	struct ip_tunnel *t;
 	struct ip_tunnel *tunnel = netdev_priv(dev);
@@ -1137,7 +1144,7 @@ int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
 		}
 	}
 
-	ip_tunnel_update(itn, t, dev, p, !tb[IFLA_MTU]);
+	ip_tunnel_update(itn, t, dev, p, !tb[IFLA_MTU], fwmark);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_changelink);