ipv6: sr: add support for SRH encapsulation and injection with lwtunnels

This patch creates a new type of interfaceless lightweight tunnel (SEG6),
enabling the encapsulation and injection of SRH within locally emitted
packets and forwarded packets.

>From a configuration viewpoint, a seg6 tunnel would be configured as follows:

  ip -6 ro ad fc00::1/128 encap seg6 mode encap segs fc42::1,fc42::2,fc42::3 dev eth0

Any packet whose destination address is fc00::1 would thus be encapsulated
within an outer IPv6 header containing the SRH with three segments, and would
actually be routed to the first segment of the list. If `mode inline' was
specified instead of `mode encap', then the SRH would be directly inserted
after the IPv6 header without outer encapsulation.

The inline mode is only available if CONFIG_IPV6_SEG6_INLINE is enabled. This
feature was made configurable because direct header insertion may break
several mechanisms such as PMTUD or IPSec AH.

Signed-off-by: David Lebrun <david.lebrun@uclouvain.be>
Signed-off-by: David S. Miller <davem@davemloft.net>

Author: David Lebrun

include/linux/seg6_iptunnel.h

@@ -0,0 +1,6 @@
+#ifndef _LINUX_SEG6_IPTUNNEL_H
+#define _LINUX_SEG6_IPTUNNEL_H
+
+#include <uapi/linux/seg6_iptunnel.h>
+
+#endif

include/net/seg6.h

@@ -16,6 +16,8 @@
 
 #include <linux/net.h>
 #include <linux/ipv6.h>
+#include <net/lwtunnel.h>
+#include <linux/seg6.h>
 
 static inline void update_csum_diff4(struct sk_buff *skb, __be32 from,
 				     __be32 to)
@@ -48,5 +50,9 @@ static inline struct seg6_pernet_data *seg6_pernet(struct net *net)
 
 extern int seg6_init(void);
 extern void seg6_exit(void);
+extern int seg6_iptunnel_init(void);
+extern void seg6_iptunnel_exit(void);
+
+extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len);
 
 #endif

include/uapi/linux/lwtunnel.h

@@ -9,6 +9,7 @@ enum lwtunnel_encap_types {
 	LWTUNNEL_ENCAP_IP,
 	LWTUNNEL_ENCAP_ILA,
 	LWTUNNEL_ENCAP_IP6,
+	LWTUNNEL_ENCAP_SEG6,
 	__LWTUNNEL_ENCAP_MAX,
 };
 

include/uapi/linux/seg6_iptunnel.h

@@ -0,0 +1,44 @@
+/*
+ *  SR-IPv6 implementation
+ *
+ *  Author:
+ *  David Lebrun <david.lebrun@uclouvain.be>
+ *
+ *
+ *  This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _UAPI_LINUX_SEG6_IPTUNNEL_H
+#define _UAPI_LINUX_SEG6_IPTUNNEL_H
+
+enum {
+	SEG6_IPTUNNEL_UNSPEC,
+	SEG6_IPTUNNEL_SRH,
+	__SEG6_IPTUNNEL_MAX,
+};
+#define SEG6_IPTUNNEL_MAX (__SEG6_IPTUNNEL_MAX - 1)
+
+struct seg6_iptunnel_encap {
+	int mode;
+	struct ipv6_sr_hdr srh[0];
+};
+
+#define SEG6_IPTUN_ENCAP_SIZE(x) ((sizeof(*x)) + (((x)->srh->hdrlen + 1) << 3))
+
+enum {
+	SEG6_IPTUN_MODE_INLINE,
+	SEG6_IPTUN_MODE_ENCAP,
+};
+
+static inline size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo)
+{
+	int encap = (tuninfo->mode == SEG6_IPTUN_MODE_ENCAP);
+
+	return ((tuninfo->srh->hdrlen + 1) << 3) +
+	       (encap * sizeof(struct ipv6hdr));
+}
+
+#endif

net/core/lwtunnel.c

@@ -39,6 +39,8 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type)
 		return "MPLS";
 	case LWTUNNEL_ENCAP_ILA:
 		return "ILA";
+	case LWTUNNEL_ENCAP_SEG6:
+		return "SEG6";
 	case LWTUNNEL_ENCAP_IP6:
 	case LWTUNNEL_ENCAP_IP:
 	case LWTUNNEL_ENCAP_NONE:

net/ipv6/Kconfig

@@ -289,4 +289,16 @@ config IPV6_PIMSM_V2
 	  Support for IPv6 PIM multicast routing protocol PIM-SMv2.
 	  If unsure, say N.
 
+config IPV6_SEG6_INLINE
+	bool "IPv6: direct Segment Routing Header insertion "
+	depends on IPV6
+	---help---
+	  Support for direct insertion of the Segment Routing Header,
+	  also known as inline mode. Be aware that direct insertion of
+	  extension headers (as opposed to encapsulation) may break
+	  multiple mechanisms such as PMTUD or IPSec AH. Use this feature
+	  only if you know exactly what you are doing.
+
+	  If unsure, say N.
+
 endif # IPV6

net/ipv6/Makefile

@@ -9,7 +9,7 @@ ipv6-objs :=	af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \
 		route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \
 		raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \
 		exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o \
-		udp_offload.o seg6.o
+		udp_offload.o seg6.o seg6_iptunnel.o
 
 ipv6-offload :=	ip6_offload.o tcpv6_offload.o exthdrs_offload.o
 

net/ipv6/seg6.c

@@ -26,6 +26,43 @@
 #include <linux/seg6.h>
 #include <linux/seg6_genl.h>
 
+bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len)
+{
+	int trailing;
+	unsigned int tlv_offset;
+
+	if (srh->type != IPV6_SRCRT_TYPE_4)
+		return false;
+
+	if (((srh->hdrlen + 1) << 3) != len)
+		return false;
+
+	if (srh->segments_left != srh->first_segment)
+		return false;
+
+	tlv_offset = sizeof(*srh) + ((srh->first_segment + 1) << 4);
+
+	trailing = len - tlv_offset;
+	if (trailing < 0)
+		return false;
+
+	while (trailing) {
+		struct sr6_tlv *tlv;
+		unsigned int tlv_len;
+
+		tlv = (struct sr6_tlv *)((unsigned char *)srh + tlv_offset);
+		tlv_len = sizeof(*tlv) + tlv->len;
+
+		trailing -= tlv_len;
+		if (trailing < 0)
+			return false;
+
+		tlv_offset += tlv_len;
+	}
+
+	return true;
+}
+
 static struct genl_family seg6_genl_family;
 
 static const struct nla_policy seg6_genl_policy[SEG6_ATTR_MAX + 1] = {
@@ -198,17 +235,24 @@ int __init seg6_init(void)
 	if (err)
 		goto out_unregister_genl;
 
+	err = seg6_iptunnel_init();
+	if (err)
+		goto out_unregister_pernet;
+
 	pr_info("Segment Routing with IPv6\n");
 
 out:
 	return err;
+out_unregister_pernet:
+	unregister_pernet_subsys(&ip6_segments_ops);
 out_unregister_genl:
 	genl_unregister_family(&seg6_genl_family);
 	goto out;
 }
 
 void seg6_exit(void)
 {
+	seg6_iptunnel_exit();
 	unregister_pernet_subsys(&ip6_segments_ops);
 	genl_unregister_family(&seg6_genl_family);
 }