[PATCH/RFC net-next 0/4] net: support MPLS in IPv4 and UDP

[PATCH/RFC net-next 0/4] net: support MPLS in IPv4 and UDP

[Simon Horman]

This short series provides support for MPLS in IPv4 (RFC4023), and by
virtue of FOU, MPLS in UDP (RFC7510).

The changes are as follows:
1. Teach tunnel4.c about AF_MPLS, it already understands AF_INET and
   AF_INET6
2. Enhance IPIP and SIT to handle MPLS. Both already handle IPv4.
   SIT also already handles IPv6.
3. Trivially enhance MPLS to allow routes over SIT and IPIP tunnels.

A corresponding iproute2 patchset will also be posted.

Simon Horman (4):
  tunnels: support MPLS over IPv4 tunnels
  sit: support MPLS over IPv4
  ipip: support MPLS over IPv4
  mpls: allow routes on ipip and sit devices

 net/ipv4/ipip.c    | 137 ++++++++++++++++++++++++++++++++++++++++++++++-------
 net/ipv4/tunnel4.c |  77 ++++++++++++++++++++++++++----
 net/ipv6/sit.c     |  93 +++++++++++++++++++++++++++++-------
 net/mpls/af_mpls.c |   6 ++-
 4 files changed, 269 insertions(+), 44 deletions(-)

-- 
2.7.0.rc3.207.g0ac5344

[PATCH/RFC net-next 1/4] tunnels: support MPLS over IPv4 tunnels

[Simon Horman]

Extend tunnel support to MPLS over IPv4.  The implementation extends the
existing differentiation between IPIP and IPv6 over IPv4 to also cover MPLS
over IPv4.

Signed-off-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Dinan Gunawardena <dinan.gunawardena@netronome.com>
---
 net/ipv4/tunnel4.c | 77 +++++++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 67 insertions(+), 10 deletions(-)

diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c
index 0d0171830620..45cd4253583a 100644
--- a/net/ipv4/tunnel4.c
+++ b/net/ipv4/tunnel4.c
@@ -6,6 +6,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/mpls.h>
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
@@ -16,11 +17,14 @@
 
 static struct xfrm_tunnel __rcu *tunnel4_handlers __read_mostly;
 static struct xfrm_tunnel __rcu *tunnel64_handlers __read_mostly;
+static struct xfrm_tunnel __rcu *tunnelmpls4_handlers __read_mostly;
 static DEFINE_MUTEX(tunnel4_mutex);
 
 static inline struct xfrm_tunnel __rcu **fam_handlers(unsigned short family)
 {
-	return (family == AF_INET) ? &tunnel4_handlers : &tunnel64_handlers;
+	return (family == AF_INET) ? &tunnel4_handlers :
+		(family == AF_INET6) ? &tunnel64_handlers :
+		&tunnelmpls4_handlers;
 }
 
 int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family)
@@ -125,6 +129,26 @@ drop:
 }
 #endif
 
+#if IS_ENABLED(CONFIG_MPLS)
+static int tunnelmpls4_rcv(struct sk_buff *skb)
+{
+	struct xfrm_tunnel *handler;
+
+	if (!pskb_may_pull(skb, sizeof(struct mpls_label)))
+		goto drop;
+
+	for_each_tunnel_rcu(tunnelmpls4_handlers, handler)
+		if (!handler->handler(skb))
+			return 0;
+
+	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
+
+drop:
+	kfree_skb(skb);
+	return 0;
+}
+#endif
+
 static void tunnel4_err(struct sk_buff *skb, u32 info)
 {
 	struct xfrm_tunnel *handler;
@@ -145,6 +169,17 @@ static void tunnel64_err(struct sk_buff *skb, u32 info)
 }
 #endif
 
+#if IS_ENABLED(CONFIG_MPLS)
+static void tunnelmpls4_err(struct sk_buff *skb, u32 info)
+{
+	struct xfrm_tunnel *handler;
+
+	for_each_tunnel_rcu(tunnelmpls4_handlers, handler)
+		if (!handler->err_handler(skb, info))
+			break;
+}
+#endif
+
 static const struct net_protocol tunnel4_protocol = {
 	.handler	=	tunnel4_rcv,
 	.err_handler	=	tunnel4_err,
@@ -161,24 +196,46 @@ static const struct net_protocol tunnel64_protocol = {
 };
 #endif
 
+#if IS_ENABLED(CONFIG_MPLS)
+static const struct net_protocol tunnelmpls4_protocol = {
+	.handler	=	tunnelmpls4_rcv,
+	.err_handler	=	tunnelmpls4_err,
+	.no_policy	=	1,
+	.netns_ok	=	1,
+};
+#endif
+
 static int __init tunnel4_init(void)
 {
-	if (inet_add_protocol(&tunnel4_protocol, IPPROTO_IPIP)) {
-		pr_err("%s: can't add protocol\n", __func__);
-		return -EAGAIN;
-	}
+	if (inet_add_protocol(&tunnel4_protocol, IPPROTO_IPIP))
+		goto err_ipip;
 #if IS_ENABLED(CONFIG_IPV6)
-	if (inet_add_protocol(&tunnel64_protocol, IPPROTO_IPV6)) {
-		pr_err("tunnel64 init: can't add protocol\n");
-		inet_del_protocol(&tunnel4_protocol, IPPROTO_IPIP);
-		return -EAGAIN;
-	}
+	if (inet_add_protocol(&tunnel64_protocol, IPPROTO_IPV6))
+		goto err_ipv6;
+#endif
+#if IS_ENABLED(CONFIG_MPLS)
+	if (inet_add_protocol(&tunnelmpls4_protocol, IPPROTO_MPLS))
+		goto err_mpls;
 #endif
 	return 0;
+
+#if IS_ENABLED(CONFIG_IPV6)
+err_mpls:
+	inet_del_protocol(&tunnel4_protocol, IPPROTO_IPV6);
+#endif
+err_ipv6:
+	inet_del_protocol(&tunnel4_protocol, IPPROTO_IPIP);
+err_ipip:
+	pr_err("%s: can't add protocol\n", __func__);
+	return -EAGAIN;
 }
 
 static void __exit tunnel4_fini(void)
 {
+#if IS_ENABLED(CONFIG_MPLS)
+	if (inet_del_protocol(&tunnelmpls4_protocol, IPPROTO_MPLS))
+		pr_err("tunnelmpls4 close: can't remove protocol\n");
+#endif
 #if IS_ENABLED(CONFIG_IPV6)
 	if (inet_del_protocol(&tunnel64_protocol, IPPROTO_IPV6))
 		pr_err("tunnel64 close: can't remove protocol\n");
-- 
2.7.0.rc3.207.g0ac5344

[PATCH/RFC net-next 2/4] sit: support MPLS over IPv4

[Simon Horman]

Extend the SIT driver to support MPLS over IPv4. This implementation
extends existing support for IPv6 over IPv4 and IPv4 over IPv4.

Signed-off-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Dinan Gunawardena <dinan.gunawardena@netronome.com>
---
 net/ipv6/sit.c | 93 ++++++++++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 77 insertions(+), 16 deletions(-)

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 917a5cd4b8fc..5d96a09102c7 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -688,12 +688,19 @@ out:
 	return 0;
 }
 
-static const struct tnl_ptk_info tpi = {
+static const struct tnl_ptk_info ipip_tpi = {
 	/* no tunnel info required for ipip. */
 	.proto = htons(ETH_P_IP),
 };
 
-static int ipip_rcv(struct sk_buff *skb)
+#if IS_ENABLED(CONFIG_MPLS)
+static const struct tnl_ptk_info mplsip_tpi = {
+	/* no tunnel info required for mplsip. */
+	.proto = htons(ETH_P_MPLS_UC),
+};
+#endif
+
+static int sit_tunnel_rcv(struct sk_buff *skb, u8 ipproto)
 {
 	const struct iphdr *iph;
 	struct ip_tunnel *tunnel;
@@ -702,15 +709,23 @@ static int ipip_rcv(struct sk_buff *skb)
 	tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
 				     iph->saddr, iph->daddr);
 	if (tunnel) {
-		if (tunnel->parms.iph.protocol != IPPROTO_IPIP &&
+		const struct tnl_ptk_info *tpi;
+
+		if (tunnel->parms.iph.protocol != ipproto &&
 		    tunnel->parms.iph.protocol != 0)
 			goto drop;
 
 		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
 			goto drop;
-		if (iptunnel_pull_header(skb, 0, tpi.proto, false))
+#if IS_ENABLED(CONFIG_MPLS)
+		if (ipproto == IPPROTO_MPLS)
+			tpi = &mplsip_tpi;
+		else
+#endif
+			tpi = &ipip_tpi;
+		if (iptunnel_pull_header(skb, 0, tpi->proto, false))
 			goto drop;
-		return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, log_ecn_error);
+		return ip_tunnel_rcv(tunnel, skb, tpi, NULL, log_ecn_error);
 	}
 
 	return 1;
@@ -720,6 +735,18 @@ drop:
 	return 0;
 }
 
+static int ipip_rcv(struct sk_buff *skb)
+{
+	return sit_tunnel_rcv(skb, IPPROTO_IPIP);
+}
+
+#if IS_ENABLED(CONFIG_MPLS)
+static int mplsip_rcv(struct sk_buff *skb)
+{
+	return sit_tunnel_rcv(skb, IPPROTO_MPLS);
+}
+#endif
+
 /*
  * If the IPv6 address comes from 6rd / 6to4 (RFC 3056) addr space this function
  * stores the embedded IPv4 address in v4dst and returns true.
@@ -958,7 +985,8 @@ tx_error:
 	return NETDEV_TX_OK;
 }
 
-static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t sit_tunnel_xmit__(struct sk_buff *skb,
+				     struct net_device *dev, u8 ipproto)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	const struct iphdr  *tiph = &tunnel->parms.iph;
@@ -966,9 +994,9 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4))
 		goto tx_error;
 
-	skb_set_inner_ipproto(skb, IPPROTO_IPIP);
+	skb_set_inner_ipproto(skb, ipproto);
 
-	ip_tunnel_xmit(skb, dev, tiph, IPPROTO_IPIP);
+	ip_tunnel_xmit(skb, dev, tiph, ipproto);
 	return NETDEV_TX_OK;
 tx_error:
 	kfree_skb(skb);
@@ -981,11 +1009,16 @@ static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb,
 {
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
-		ipip_tunnel_xmit(skb, dev);
+		sit_tunnel_xmit__(skb, dev, IPPROTO_IPIP);
 		break;
 	case htons(ETH_P_IPV6):
 		ipip6_tunnel_xmit(skb, dev);
 		break;
+#if IS_ENABLED(CONFIG_MPLS)
+	case htons(ETH_P_MPLS_UC):
+		sit_tunnel_xmit__(skb, dev, IPPROTO_MPLS);
+		break;
+#endif
 	default:
 		goto tx_err;
 	}
@@ -1093,6 +1126,16 @@ static int ipip6_tunnel_update_6rd(struct ip_tunnel *t,
 }
 #endif
 
+bool ipip6_valid_ip_proto(u8 ipproto)
+{
+	return ipproto == IPPROTO_IPV6 ||
+		ipproto != IPPROTO_IPIP ||
+#if IS_ENABLED(CONFIG_MPLS)
+		ipproto == IPPROTO_MPLS ||
+#endif
+		ipproto == 0;
+}
+
 static int
 ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
@@ -1152,9 +1195,7 @@ ipip6_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			goto done;
 
 		err = -EINVAL;
-		if (p.iph.protocol != IPPROTO_IPV6 &&
-		    p.iph.protocol != IPPROTO_IPIP &&
-		    p.iph.protocol != 0)
+		if (!ipip6_valid_ip_proto(p.iph.protocol))
 			goto done;
 		if (p.iph.version != 4 ||
 		    p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
@@ -1379,9 +1420,7 @@ static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[])
 		return 0;
 
 	proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);
-	if (proto != IPPROTO_IPV6 &&
-	    proto != IPPROTO_IPIP &&
-	    proto != 0)
+	if (!ipip6_valid_ip_proto(proto))
 		return -EINVAL;
 
 	return 0;
@@ -1723,6 +1762,14 @@ static struct xfrm_tunnel ipip_handler __read_mostly = {
 	.priority	=	2,
 };
 
+#if IS_ENABLED(CONFIG_MPLS)
+static struct xfrm_tunnel mplsip_handler __read_mostly = {
+	.handler	=	mplsip_rcv,
+	.err_handler	=	ipip6_err,
+	.priority	=	2,
+};
+#endif
+
 static void __net_exit sit_destroy_tunnels(struct net *net,
 					   struct list_head *head)
 {
@@ -1818,6 +1865,9 @@ static void __exit sit_cleanup(void)
 	rtnl_link_unregister(&sit_link_ops);
 	xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
 	xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
+#if IS_ENABLED(CONFIG_MPLS)
+	xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS);
+#endif
 
 	unregister_pernet_device(&sit_net_ops);
 	rcu_barrier(); /* Wait for completion of call_rcu()'s */
@@ -1827,7 +1877,7 @@ static int __init sit_init(void)
 {
 	int err;
 
-	pr_info("IPv6 over IPv4 tunneling driver\n");
+	pr_info("IPv6, IPv4 and MPLS over IPv4 tunneling driver\n");
 
 	err = register_pernet_device(&sit_net_ops);
 	if (err < 0)
@@ -1842,6 +1892,13 @@ static int __init sit_init(void)
 		pr_info("%s: can't register ip4ip4\n", __func__);
 		goto xfrm_tunnel4_failed;
 	}
+#if IS_ENABLED(CONFIG_MPLS)
+	err = xfrm4_tunnel_register(&mplsip_handler, AF_MPLS);
+	if (err < 0) {
+		pr_info("%s: can't register mplsip\n", __func__);
+		goto xfrm_tunnel_mpls_failed;
+	}
+#endif
 	err = rtnl_link_register(&sit_link_ops);
 	if (err < 0)
 		goto rtnl_link_failed;
@@ -1850,6 +1907,10 @@ out:
 	return err;
 
 rtnl_link_failed:
+#if IS_ENABLED(CONFIG_MPLS)
+	xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS);
+xfrm_tunnel_mpls_failed:
+#endif
 	xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
 xfrm_tunnel4_failed:
 	xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
-- 
2.7.0.rc3.207.g0ac5344

[PATCH/RFC net-next 3/4] ipip: support MPLS over IPv4

[Simon Horman]

Extend the IPIP driver to support MPLS over IPv4. The implementation is an
extension of existing support for IPv4 over IPv4 and is based of multiple
inner-protocol support for the SIT driver.

Signed-off-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Dinan Gunawardena <dinan.gunawardena@netronome.com>
---
 net/ipv4/ipip.c | 137 +++++++++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 121 insertions(+), 16 deletions(-)

diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 978370132f29..4ae3f8e6c6cc 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -148,14 +148,14 @@ static int ipip_err(struct sk_buff *skb, u32 info)
 
 	if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
 		ipv4_update_pmtu(skb, dev_net(skb->dev), info,
-				 t->parms.link, 0, IPPROTO_IPIP, 0);
+				 t->parms.link, 0, iph->protocol, 0);
 		err = 0;
 		goto out;
 	}
 
 	if (type == ICMP_REDIRECT) {
 		ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
-			      IPPROTO_IPIP, 0);
+			      iph->protocol, 0);
 		err = 0;
 		goto out;
 	}
@@ -177,12 +177,19 @@ out:
 	return err;
 }
 
-static const struct tnl_ptk_info tpi = {
+static const struct tnl_ptk_info ipip_tpi = {
 	/* no tunnel info required for ipip. */
 	.proto = htons(ETH_P_IP),
 };
 
-static int ipip_rcv(struct sk_buff *skb)
+#if IS_ENABLED(CONFIG_MPLS)
+static const struct tnl_ptk_info mplsip_tpi = {
+	/* no tunnel info required for mplsip. */
+	.proto = htons(ETH_P_MPLS_UC),
+};
+#endif
+
+static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto)
 {
 	struct net *net = dev_net(skb->dev);
 	struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
@@ -193,11 +200,23 @@ static int ipip_rcv(struct sk_buff *skb)
 	tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
 			iph->saddr, iph->daddr, 0);
 	if (tunnel) {
+		const struct tnl_ptk_info *tpi;
+
+		if (tunnel->parms.iph.protocol != ipproto &&
+		    tunnel->parms.iph.protocol != 0)
+			goto drop;
+
 		if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
 			goto drop;
-		if (iptunnel_pull_header(skb, 0, tpi.proto, false))
+#if IS_ENABLED(CONFIG_MPLS)
+		if (ipproto == IPPROTO_MPLS)
+			tpi = &mplsip_tpi;
+		else
+#endif
+			tpi = &ipip_tpi;
+		if (iptunnel_pull_header(skb, 0, tpi->proto, false))
 			goto drop;
-		return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, log_ecn_error);
+		return ip_tunnel_rcv(tunnel, skb, tpi, NULL, log_ecn_error);
 	}
 
 	return -1;
@@ -207,24 +226,51 @@ drop:
 	return 0;
 }
 
+static int ipip_rcv(struct sk_buff *skb)
+{
+	return ipip_tunnel_rcv(skb, IPPROTO_IPIP);
+}
+
+#if IS_ENABLED(CONFIG_MPLS)
+static int mplsip_rcv(struct sk_buff *skb)
+{
+	return ipip_tunnel_rcv(skb, IPPROTO_MPLS);
+}
+#endif
+
 /*
  *	This function assumes it is being called from dev_queue_xmit()
  *	and that skb is filled properly by that function.
  */
-static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb,
+				    struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	const struct iphdr  *tiph = &tunnel->parms.iph;
+	u8 ipproto;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		ipproto = IPPROTO_IPIP;
+		break;
+#if IS_ENABLED(CONFIG_MPLS)
+	case htons(ETH_P_MPLS_UC):
+		ipproto = IPPROTO_MPLS;
+		break;
+#endif
+	default:
+		goto tx_error;
+	}
 
-	if (unlikely(skb->protocol != htons(ETH_P_IP)))
+	if (tiph->protocol != ipproto && tiph->protocol != 0)
 		goto tx_error;
 
 	if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4))
 		goto tx_error;
 
-	skb_set_inner_ipproto(skb, IPPROTO_IPIP);
+	skb_set_inner_ipproto(skb, ipproto);
 
-	ip_tunnel_xmit(skb, dev, tiph, tiph->protocol);
+	ip_tunnel_xmit(skb, dev, tiph, ipproto);
 	return NETDEV_TX_OK;
 
 tx_error:
@@ -234,6 +280,20 @@ tx_error:
 	return NETDEV_TX_OK;
 }
 
+static bool ipip_tunnel_ioctl_verify_protocol(u8 ipproto)
+{
+	switch (ipproto) {
+	case 0:
+	case IPPROTO_IPIP:
+#if IS_ENABLED(CONFIG_MPLS)
+	case IPPROTO_MPLS:
+#endif
+		return true;
+	}
+
+	return false;
+}
+
 static int
 ipip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
@@ -244,7 +304,8 @@ ipip_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 		return -EFAULT;
 
 	if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) {
-		if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP ||
+		if (p.iph.version != 4 ||
+		    !ipip_tunnel_ioctl_verify_protocol(p.iph.protocol) ||
 		    p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
 			return -EINVAL;
 	}
@@ -301,10 +362,23 @@ static int ipip_tunnel_init(struct net_device *dev)
 
 	tunnel->tun_hlen = 0;
 	tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen;
-	tunnel->parms.iph.protocol = IPPROTO_IPIP;
 	return ip_tunnel_init(dev);
 }
 
+static int ipip_tunnel_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+	u8 proto;
+
+	if (!data || !data[IFLA_IPTUN_PROTO])
+		return 0;
+
+	proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);
+	if (proto != IPPROTO_IPIP && proto != IPPROTO_MPLS && proto != 0)
+		return -EINVAL;
+
+	return 0;
+}
+
 static void ipip_netlink_parms(struct nlattr *data[],
 			       struct ip_tunnel_parm *parms)
 {
@@ -335,6 +409,9 @@ static void ipip_netlink_parms(struct nlattr *data[],
 	if (data[IFLA_IPTUN_TOS])
 		parms->iph.tos = nla_get_u8(data[IFLA_IPTUN_TOS]);
 
+	if (data[IFLA_IPTUN_PROTO])
+		parms->iph.protocol = nla_get_u8(data[IFLA_IPTUN_PROTO]);
+
 	if (!data[IFLA_IPTUN_PMTUDISC] || nla_get_u8(data[IFLA_IPTUN_PMTUDISC]))
 		parms->iph.frag_off = htons(IP_DF);
 }
@@ -427,6 +504,8 @@ static size_t ipip_get_size(const struct net_device *dev)
 		nla_total_size(1) +
 		/* IFLA_IPTUN_TOS */
 		nla_total_size(1) +
+		/* IFLA_IPTUN_PROTO */
+		nla_total_size(1) +
 		/* IFLA_IPTUN_PMTUDISC */
 		nla_total_size(1) +
 		/* IFLA_IPTUN_ENCAP_TYPE */
@@ -450,6 +529,7 @@ static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_in_addr(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) ||
 	    nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) ||
 	    nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) ||
+	    nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) ||
 	    nla_put_u8(skb, IFLA_IPTUN_PMTUDISC,
 		       !!(parm->iph.frag_off & htons(IP_DF))))
 		goto nla_put_failure;
@@ -476,6 +556,7 @@ static const struct nla_policy ipip_policy[IFLA_IPTUN_MAX + 1] = {
 	[IFLA_IPTUN_REMOTE]		= { .type = NLA_U32 },
 	[IFLA_IPTUN_TTL]		= { .type = NLA_U8 },
 	[IFLA_IPTUN_TOS]		= { .type = NLA_U8 },
+	[IFLA_IPTUN_PROTO]		= { .type = NLA_U8 },
 	[IFLA_IPTUN_PMTUDISC]		= { .type = NLA_U8 },
 	[IFLA_IPTUN_ENCAP_TYPE]		= { .type = NLA_U16 },
 	[IFLA_IPTUN_ENCAP_FLAGS]	= { .type = NLA_U16 },
@@ -489,6 +570,7 @@ static struct rtnl_link_ops ipip_link_ops __read_mostly = {
 	.policy		= ipip_policy,
 	.priv_size	= sizeof(struct ip_tunnel),
 	.setup		= ipip_tunnel_setup,
+	.validate	= ipip_tunnel_validate,
 	.newlink	= ipip_newlink,
 	.changelink	= ipip_changelink,
 	.dellink	= ip_tunnel_dellink,
@@ -503,6 +585,14 @@ static struct xfrm_tunnel ipip_handler __read_mostly = {
 	.priority	=	1,
 };
 
+#if IS_ENABLED(CONFIG_MPLS)
+static struct xfrm_tunnel mplsip_handler __read_mostly = {
+	.handler	=	mplsip_rcv,
+	.err_handler	=	ipip_err,
+	.priority	=	1,
+};
+#endif
+
 static int __net_init ipip_init_net(struct net *net)
 {
 	return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0");
@@ -525,7 +615,7 @@ static int __init ipip_init(void)
 {
 	int err;
 
-	pr_info("ipip: IPv4 over IPv4 tunneling driver\n");
+	pr_info("ipip: IPv4 and MPLS over IPv4 tunneling driver\n");
 
 	err = register_pernet_device(&ipip_net_ops);
 	if (err < 0)
@@ -533,8 +623,15 @@ static int __init ipip_init(void)
 	err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
 	if (err < 0) {
 		pr_info("%s: can't register tunnel\n", __func__);
-		goto xfrm_tunnel_failed;
+		goto xfrm_tunnel_ipip_failed;
+	}
+#if IS_ENABLED(CONFIG_MPLS)
+	err = xfrm4_tunnel_register(&mplsip_handler, AF_MPLS);
+	if (err < 0) {
+		pr_info("%s: can't register tunnel\n", __func__);
+		goto xfrm_tunnel_mplsip_failed;
 	}
+#endif
 	err = rtnl_link_register(&ipip_link_ops);
 	if (err < 0)
 		goto rtnl_link_failed;
@@ -543,8 +640,13 @@ out:
 	return err;
 
 rtnl_link_failed:
+#if IS_ENABLED(CONFIG_MPLS)
+	xfrm4_tunnel_deregister(&mplsip_handler, AF_INET);
+xfrm_tunnel_mplsip_failed:
+
+#endif
 	xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
-xfrm_tunnel_failed:
+xfrm_tunnel_ipip_failed:
 	unregister_pernet_device(&ipip_net_ops);
 	goto out;
 }
@@ -554,7 +656,10 @@ static void __exit ipip_fini(void)
 	rtnl_link_unregister(&ipip_link_ops);
 	if (xfrm4_tunnel_deregister(&ipip_handler, AF_INET))
 		pr_info("%s: can't deregister tunnel\n", __func__);
-
+#if IS_ENABLED(CONFIG_MPLS)
+	if (xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS))
+		pr_info("%s: can't deregister tunnel\n", __func__);
+#endif
 	unregister_pernet_device(&ipip_net_ops);
 }
 
-- 
2.7.0.rc3.207.g0ac5344

[PATCH/RFC net-next 4/4] mpls: allow routes on ipip and sit devices

[Simon Horman]

Allow MPLS routes on IPIP and SIT devices now that they
support forwarding MPLS packets.

Signed-off-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Dinan Gunawardena <dinan.gunawardena@netronome.com>
---
 net/mpls/af_mpls.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index e9beaa58573c..5c161e7759b5 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1009,10 +1009,12 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 	unsigned int flags;
 
 	if (event == NETDEV_REGISTER) {
-		/* For now just support Ethernet and IPGRE devices */
+		/* For now just support Ethernet, IPGRE, SIT and IPIP devices */
 		if (dev->type == ARPHRD_ETHER ||
 		    dev->type == ARPHRD_LOOPBACK ||
-		    dev->type == ARPHRD_IPGRE) {
+		    dev->type == ARPHRD_IPGRE ||
+		    dev->type == ARPHRD_SIT ||
+		    dev->type == ARPHRD_TUNNEL) {
 			mdev = mpls_add_dev(dev);
 			if (IS_ERR(mdev))
 				return notifier_from_errno(PTR_ERR(mdev));
-- 
2.7.0.rc3.207.g0ac5344

Re: [PATCH/RFC net-next 0/4] net: support MPLS in IPv4 and UDP

[Tom Herbert]

On Wed, Jul 6, 2016 at 11:22 AM, Simon Horman
<simon.horman@netronome.com> wrote:
> This short series provides support for MPLS in IPv4 (RFC4023), and by
> virtue of FOU, MPLS in UDP (RFC7510).
>
> The changes are as follows:
> 1. Teach tunnel4.c about AF_MPLS, it already understands AF_INET and
>    AF_INET6
> 2. Enhance IPIP and SIT to handle MPLS. Both already handle IPv4.
>    SIT also already handles IPv6.
> 3. Trivially enhance MPLS to allow routes over SIT and IPIP tunnels.
>

HI Siomon,

Thanks for these patches! Can provide the commands for testing this?

Tom

> A corresponding iproute2 patchset will also be posted.
>
> Simon Horman (4):
>   tunnels: support MPLS over IPv4 tunnels
>   sit: support MPLS over IPv4
>   ipip: support MPLS over IPv4
>   mpls: allow routes on ipip and sit devices
>
>  net/ipv4/ipip.c    | 137 ++++++++++++++++++++++++++++++++++++++++++++++-------
>  net/ipv4/tunnel4.c |  77 ++++++++++++++++++++++++++----
>  net/ipv6/sit.c     |  93 +++++++++++++++++++++++++++++-------
>  net/mpls/af_mpls.c |   6 ++-
>  4 files changed, 269 insertions(+), 44 deletions(-)
>
> --
> 2.7.0.rc3.207.g0ac5344
>

Re: [PATCH/RFC net-next 2/4] sit: support MPLS over IPv4

[David Miller]

From: Simon Horman <simon.horman@netronome.com>
Date: Wed,  6 Jul 2016 20:22:33 +0200

>  
> +bool ipip6_valid_ip_proto(u8 ipproto)
> +{
> +	return ipproto == IPPROTO_IPV6 ||
> +		ipproto != IPPROTO_IPIP ||
> +#if IS_ENABLED(CONFIG_MPLS)
> +		ipproto == IPPROTO_MPLS ||
> +#endif
> +		ipproto == 0;
> +}

This returns true any time ipproto is not equal to IPPROTO_IPIP,
which is probably not what you intended here.

Re: [PATCH/RFC net-next 0/4] net: support MPLS in IPv4 and UDP

[David Miller]

From: Simon Horman <simon.horman@netronome.com>
Date: Wed,  6 Jul 2016 20:22:31 +0200

> This short series provides support for MPLS in IPv4 (RFC4023), and by
> virtue of FOU, MPLS in UDP (RFC7510).
> 
> The changes are as follows:
> 1. Teach tunnel4.c about AF_MPLS, it already understands AF_INET and
>    AF_INET6
> 2. Enhance IPIP and SIT to handle MPLS. Both already handle IPv4.
>    SIT also already handles IPv6.
> 3. Trivially enhance MPLS to allow routes over SIT and IPIP tunnels.
> 
> A corresponding iproute2 patchset will also be posted.

Other than the protocol value test logic problem in patch #2, this looks
fine to me.

Re: [PATCH/RFC net-next 2/4] sit: support MPLS over IPv4

[Simon Horman]

On Wed, Jul 06, 2016 at 10:10:59PM -0700, David Miller wrote:
> From: Simon Horman <simon.horman@netronome.com>
> Date: Wed,  6 Jul 2016 20:22:33 +0200
> 
> >  
> > +bool ipip6_valid_ip_proto(u8 ipproto)
> > +{
> > +	return ipproto == IPPROTO_IPV6 ||
> > +		ipproto != IPPROTO_IPIP ||
> > +#if IS_ENABLED(CONFIG_MPLS)
> > +		ipproto == IPPROTO_MPLS ||
> > +#endif
> > +		ipproto == 0;
> > +}
> 
> This returns true any time ipproto is not equal to IPPROTO_IPIP,
> which is probably not what you intended here.

Thanks, I will fix that.

Re: [PATCH/RFC net-next 0/4] net: support MPLS in IPv4 and UDP

[Simon Horman]

On Wed, Jul 06, 2016 at 09:44:13PM -0700, Tom Herbert wrote:
> On Wed, Jul 6, 2016 at 11:22 AM, Simon Horman
> <simon.horman@netronome.com> wrote:
> > This short series provides support for MPLS in IPv4 (RFC4023), and by
> > virtue of FOU, MPLS in UDP (RFC7510).
> >
> > The changes are as follows:
> > 1. Teach tunnel4.c about AF_MPLS, it already understands AF_INET and
> >    AF_INET6
> > 2. Enhance IPIP and SIT to handle MPLS. Both already handle IPv4.
> >    SIT also already handles IPv6.
> > 3. Trivially enhance MPLS to allow routes over SIT and IPIP tunnels.
> >
> 
> HI Siomon,
> 
> Thanks for these patches! Can provide the commands for testing this?

Sure, will do.