ipv6 sit: 6rd (IPv6 Rapid Deployment) Support.

IPv6 Rapid Deployment (6rd; draft-ietf-softwire-ipv6-6rd) builds upon
mechanisms of 6to4 (RFC3056) to enable a service provider to rapidly
deploy IPv6 unicast service to IPv4 sites to which it provides
customer premise equipment.  Like 6to4, it utilizes stateless IPv6 in
IPv4 encapsulation in order to transit IPv4-only network
infrastructure.  Unlike 6to4, a 6rd service provider uses an IPv6
prefix of its own in place of the fixed 6to4 prefix.

With this option enabled, the SIT driver offers 6rd functionality by
providing additional ioctl API to configure the IPv6 Prefix for in
stead of static 2002::/16 for 6to4.

Original patch was done by Alexandre Cassen <acassen@freebox.fr>
based on old Internet-Draft.

Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 135 insertions, 8 deletions

diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index ead6c7a42f4..f5619982745 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -170,6 +170,25 @@ config IPV6_SIT
 
 	  Saying M here will produce a module called sit. If unsure, say Y.
 
+config IPV6_SIT_6RD
+	bool "IPv6: IPv6 Rapid Development (6RD) (EXPERIMENTAL)"
+	depends on IPV6_SIT && EXPERIMENTAL
+	default n
+	---help---
+	  IPv6 Rapid Deployment (6rd; draft-ietf-softwire-ipv6-6rd) builds upon
+	  mechanisms of 6to4 (RFC3056) to enable a service provider to rapidly
+	  deploy IPv6 unicast service to IPv4 sites to which it provides
+	  customer premise equipment.  Like 6to4, it utilizes stateless IPv6 in
+	  IPv4 encapsulation in order to transit IPv4-only network
+	  infrastructure.  Unlike 6to4, a 6rd service provider uses an IPv6
+	  prefix of its own in place of the fixed 6to4 prefix.
+
+	  With this option enabled, the SIT driver offers 6rd functionality by
+	  providing additional ioctl API to configure the IPv6 Prefix for in
+	  stead of static 2002::/16 for 6to4.
+
+	  If unsure, say N.
+
 config IPV6_NDISC_NODETYPE
 	bool
 
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 99da272951d..6955654262a 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -161,6 +161,21 @@ static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t)
 	write_unlock_bh(&ipip6_lock);
 }
 
+static void ipip6_tunnel_clone_6rd(struct ip_tunnel *t, struct sit_net *sitn)
+{
+#ifdef CONFIG_IPV6_SIT_6RD
+	if (t->dev == sitn->fb_tunnel_dev) {
+		ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0);
+		t->ip6rd.relay_prefix = 0;
+		t->ip6rd.prefixlen = 16;
+		t->ip6rd.relay_prefixlen = 0;
+	} else {
+		struct ip_tunnel *t0 = netdev_priv(sitn->fb_tunnel_dev);
+		memcpy(&t->ip6rd, &t0->ip6rd, sizeof(t->ip6rd));
+	}
+#endif
+}
+
 static struct ip_tunnel * ipip6_tunnel_locate(struct net *net,
 		struct ip_tunnel_parm *parms, int create)
 {
@@ -213,6 +228,8 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net,
 
 	dev_hold(dev);
 
+	ipip6_tunnel_clone_6rd(t, sitn);
+
 	ipip6_tunnel_link(sitn, nt);
 	return nt;
 
@@ -532,17 +549,41 @@ out:
 	return 0;
 }
 
-/* Returns the embedded IPv4 address if the IPv6 address
-   comes from 6to4 (RFC 3056) addr space */
-
-static inline __be32 try_6to4(struct in6_addr *v6dst)
+/*
+ * Returns the embedded IPv4 address if the IPv6 address
+ * comes from 6rd / 6to4 (RFC 3056) addr space.
+ */
+static inline
+__be32 try_6rd(struct in6_addr *v6dst, struct ip_tunnel *tunnel)
 {
 	__be32 dst = 0;
 
+#ifdef CONFIG_IPV6_SIT_6RD
+	if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix,
+			      tunnel->ip6rd.prefixlen)) {
+		unsigned pbw0, pbi0;
+		int pbi1;
+		u32 d;
+
+		pbw0 = tunnel->ip6rd.prefixlen >> 5;
+		pbi0 = tunnel->ip6rd.prefixlen & 0x1f;
+
+		d = (ntohl(tunnel->ip6rd.prefix.s6_addr32[pbw0]) << pbi0) >>
+		    tunnel->ip6rd.relay_prefixlen;
+
+		pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen;
+		if (pbi1 > 0)
+			d |= ntohl(tunnel->ip6rd.prefix.s6_addr32[pbw0 + 1]) >>
+			     (32 - pbi1);
+
+		dst = tunnel->ip6rd.relay_prefix | htonl(d);
+	}
+#else
 	if (v6dst->s6_addr16[0] == htons(0x2002)) {
 		/* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */
 		memcpy(&dst, &v6dst->s6_addr16[1], 4);
 	}
+#endif
 	return dst;
 }
 
@@ -596,7 +637,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	}
 
 	if (!dst)
-		dst = try_6to4(&iph6->daddr);
+		dst = try_6rd(&iph6->daddr, tunnel);
 
 	if (!dst) {
 		struct neighbour *neigh = NULL;
@@ -786,9 +827,15 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 	struct ip_tunnel *t;
 	struct net *net = dev_net(dev);
 	struct sit_net *sitn = net_generic(net, sit_net_id);
+#ifdef CONFIG_IPV6_SIT_6RD
+	struct ip_tunnel_6rd ip6rd;
+#endif
 
 	switch (cmd) {
 	case SIOCGETTUNNEL:
+#ifdef CONFIG_IPV6_SIT_6RD
+	case SIOCGET6RD:
+#endif
 		t = NULL;
 		if (dev == sitn->fb_tunnel_dev) {
 			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
@@ -799,9 +846,25 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 		}
 		if (t == NULL)
 			t = netdev_priv(dev);
-		memcpy(&p, &t->parms, sizeof(p));
-		if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
-			err = -EFAULT;
+
+		err = -EFAULT;
+		if (cmd == SIOCGETTUNNEL) {
+			memcpy(&p, &t->parms, sizeof(p));
+			if (copy_to_user(ifr->ifr_ifru.ifru_data, &p,
+					 sizeof(p)))
+				goto done;
+#ifdef CONFIG_IPV6_SIT_6RD
+		} else {
+			ipv6_addr_copy(&ip6rd.prefix, &t->ip6rd.prefix);
+			ip6rd.relay_prefix = t->ip6rd.relay_prefix;
+			ip6rd.prefixlen = t->ip6rd.prefixlen;
+			ip6rd.relay_prefixlen = t->ip6rd.relay_prefixlen;
+			if (copy_to_user(ifr->ifr_ifru.ifru_data, &ip6rd,
+					 sizeof(ip6rd)))
+				goto done;
+#endif
+		}
+		err = 0;
 		break;
 
 	case SIOCADDTUNNEL:
@@ -922,6 +985,51 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 		netdev_state_change(dev);
 		break;
 
+#ifdef CONFIG_IPV6_SIT_6RD
+	case SIOCADD6RD:
+	case SIOCCHG6RD:
+	case SIOCDEL6RD:
+		err = -EPERM;
+		if (!capable(CAP_NET_ADMIN))
+			goto done;
+
+		err = -EFAULT;
+		if (copy_from_user(&ip6rd, ifr->ifr_ifru.ifru_data,
+				   sizeof(ip6rd)))
+			goto done;
+
+		t = netdev_priv(dev);
+
+		if (cmd != SIOCDEL6RD) {
+			struct in6_addr prefix;
+			__be32 relay_prefix;
+
+			err = -EINVAL;
+			if (ip6rd.relay_prefixlen > 32 ||
+			    ip6rd.prefixlen + (32 - ip6rd.relay_prefixlen) > 64)
+				goto done;
+
+			ipv6_addr_prefix(&prefix, &ip6rd.prefix,
+					 ip6rd.prefixlen);
+			if (!ipv6_addr_equal(&prefix, &ip6rd.prefix))
+				goto done;
+			relay_prefix = ip6rd.relay_prefix &
+				       htonl(0xffffffffUL <<
+					     (32 - ip6rd.relay_prefixlen));
+			if (relay_prefix != ip6rd.relay_prefix)
+				goto done;
+
+			ipv6_addr_copy(&t->ip6rd.prefix, &prefix);
+			t->ip6rd.relay_prefix = relay_prefix;
+			t->ip6rd.prefixlen = ip6rd.prefixlen;
+			t->ip6rd.relay_prefixlen = ip6rd.relay_prefixlen;
+		} else
+			ipip6_tunnel_clone_6rd(t, sitn);
+
+		err = 0;
+		break;
+#endif
+
 	default:
 		err = -EINVAL;
 	}