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>

4 files changed, 467 insertions, 1 deletions

diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 2343e4f2e0bf..1123a001d729 100644
--- a/net/ipv6/Kconfig
+++ b/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
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index c92010d62afc..59ee92fb3689 100644
--- a/net/ipv6/Makefile
+++ b/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
 
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index e246b0ba12ac..9c78053e67e0 100644
--- a/net/ipv6/seg6.c
+++ b/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] = {
@@ -198,10 +235,16 @@ 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;
@@ -209,6 +252,7 @@ out_unregister_genl:
 
 void seg6_exit(void)
 {
+	seg6_iptunnel_exit();
 	unregister_pernet_subsys(&ip6_segments_ops);
 	genl_unregister_family(&seg6_genl_family);
 }
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
new file mode 100644
index 000000000000..39762b2fa7a2
--- /dev/null
+++ b/net/ipv6/seg6_iptunnel.c
@@ -0,0 +1,410 @@
+/*
+ *  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.
+ */
+
+#include <linux/types.h>
+#include <linux/skbuff.h>
+#include <linux/net.h>
+#include <linux/module.h>
+#include <net/ip.h>
+#include <net/lwtunnel.h>
+#include <net/netevent.h>
+#include <net/netns/generic.h>
+#include <net/ip6_fib.h>
+#include <net/route.h>
+#include <net/seg6.h>
+#include <linux/seg6.h>
+#include <linux/seg6_iptunnel.h>
+#include <net/addrconf.h>
+#include <net/ip6_route.h>
+#ifdef CONFIG_DST_CACHE
+#include <net/dst_cache.h>
+#endif
+
+struct seg6_lwt {
+#ifdef CONFIG_DST_CACHE
+	struct dst_cache cache;
+#endif
+	struct seg6_iptunnel_encap tuninfo[0];
+};
+
+static inline struct seg6_lwt *seg6_lwt_lwtunnel(struct lwtunnel_state *lwt)
+{
+	return (struct seg6_lwt *)lwt->data;
+}
+
+static inline struct seg6_iptunnel_encap *
+seg6_encap_lwtunnel(struct lwtunnel_state *lwt)
+{
+	return seg6_lwt_lwtunnel(lwt)->tuninfo;
+}
+
+static const struct nla_policy seg6_iptunnel_policy[SEG6_IPTUNNEL_MAX + 1] = {
+	[SEG6_IPTUNNEL_SRH]	= { .type = NLA_BINARY },
+};
+
+int nla_put_srh(struct sk_buff *skb, int attrtype,
+		struct seg6_iptunnel_encap *tuninfo)
+{
+	struct seg6_iptunnel_encap *data;
+	struct nlattr *nla;
+	int len;
+
+	len = SEG6_IPTUN_ENCAP_SIZE(tuninfo);
+
+	nla = nla_reserve(skb, attrtype, len);
+	if (!nla)
+		return -EMSGSIZE;
+
+	data = nla_data(nla);
+	memcpy(data, tuninfo, len);
+
+	return 0;
+}
+
+static void set_tun_src(struct net *net, struct net_device *dev,
+			struct in6_addr *daddr, struct in6_addr *saddr)
+{
+	struct seg6_pernet_data *sdata = seg6_pernet(net);
+	struct in6_addr *tun_src;
+
+	rcu_read_lock();
+
+	tun_src = rcu_dereference(sdata->tun_src);
+
+	if (!ipv6_addr_any(tun_src)) {
+		memcpy(saddr, tun_src, sizeof(struct in6_addr));
+	} else {
+		ipv6_dev_get_saddr(net, dev, daddr, IPV6_PREFER_SRC_PUBLIC,
+				   saddr);
+	}
+
+	rcu_read_unlock();
+}
+
+/* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */
+static int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
+{
+	struct net *net = dev_net(skb_dst(skb)->dev);
+	struct ipv6hdr *hdr, *inner_hdr;
+	struct ipv6_sr_hdr *isrh;
+	int hdrlen, tot_len, err;
+
+	hdrlen = (osrh->hdrlen + 1) << 3;
+	tot_len = hdrlen + sizeof(*hdr);
+
+	err = pskb_expand_head(skb, tot_len, 0, GFP_ATOMIC);
+	if (unlikely(err))
+		return err;
+
+	inner_hdr = ipv6_hdr(skb);
+
+	skb_push(skb, tot_len);
+	skb_reset_network_header(skb);
+	skb_mac_header_rebuild(skb);
+	hdr = ipv6_hdr(skb);
+
+	/* inherit tc, flowlabel and hlim
+	 * hlim will be decremented in ip6_forward() afterwards and
+	 * decapsulation will overwrite inner hlim with outer hlim
+	 */
+	ip6_flow_hdr(hdr, ip6_tclass(ip6_flowinfo(inner_hdr)),
+		     ip6_flowlabel(inner_hdr));
+	hdr->hop_limit = inner_hdr->hop_limit;
+	hdr->nexthdr = NEXTHDR_ROUTING;
+
+	isrh = (void *)hdr + sizeof(*hdr);
+	memcpy(isrh, osrh, hdrlen);
+
+	isrh->nexthdr = NEXTHDR_IPV6;
+
+	hdr->daddr = isrh->segments[isrh->first_segment];
+	set_tun_src(net, skb->dev, &hdr->daddr, &hdr->saddr);
+
+	skb_postpush_rcsum(skb, hdr, tot_len);
+
+	return 0;
+}
+
+/* insert an SRH within an IPv6 packet, just after the IPv6 header */
+#ifdef CONFIG_IPV6_SEG6_INLINE
+static int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
+{
+	struct ipv6hdr *hdr, *oldhdr;
+	struct ipv6_sr_hdr *isrh;
+	int hdrlen, err;
+
+	hdrlen = (osrh->hdrlen + 1) << 3;
+
+	err = pskb_expand_head(skb, hdrlen, 0, GFP_ATOMIC);
+	if (unlikely(err))
+		return err;
+
+	oldhdr = ipv6_hdr(skb);
+
+	skb_pull(skb, sizeof(struct ipv6hdr));
+	skb_postpull_rcsum(skb, skb_network_header(skb),
+			   sizeof(struct ipv6hdr));
+
+	skb_push(skb, sizeof(struct ipv6hdr) + hdrlen);
+	skb_reset_network_header(skb);
+	skb_mac_header_rebuild(skb);
+
+	hdr = ipv6_hdr(skb);
+
+	memmove(hdr, oldhdr, sizeof(*hdr));
+
+	isrh = (void *)hdr + sizeof(*hdr);
+	memcpy(isrh, osrh, hdrlen);
+
+	isrh->nexthdr = hdr->nexthdr;
+	hdr->nexthdr = NEXTHDR_ROUTING;
+
+	isrh->segments[0] = hdr->daddr;
+	hdr->daddr = isrh->segments[isrh->first_segment];
+
+	skb_postpush_rcsum(skb, hdr, sizeof(struct ipv6hdr) + hdrlen);
+
+	return 0;
+}
+#endif
+
+static int seg6_do_srh(struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct seg6_iptunnel_encap *tinfo;
+	int err = 0;
+
+	tinfo = seg6_encap_lwtunnel(dst->lwtstate);
+
+	if (likely(!skb->encapsulation)) {
+		skb_reset_inner_headers(skb);
+		skb->encapsulation = 1;
+	}
+
+	switch (tinfo->mode) {
+#ifdef CONFIG_IPV6_SEG6_INLINE
+	case SEG6_IPTUN_MODE_INLINE:
+		err = seg6_do_srh_inline(skb, tinfo->srh);
+		skb_reset_inner_headers(skb);
+		break;
+#endif
+	case SEG6_IPTUN_MODE_ENCAP:
+		err = seg6_do_srh_encap(skb, tinfo->srh);
+		break;
+	}
+
+	if (err)
+		return err;
+
+	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
+	skb_set_transport_header(skb, sizeof(struct ipv6hdr));
+
+	skb_set_inner_protocol(skb, skb->protocol);
+
+	return 0;
+}
+
+int seg6_input(struct sk_buff *skb)
+{
+	int err;
+
+	err = seg6_do_srh(skb);
+	if (unlikely(err)) {
+		kfree_skb(skb);
+		return err;
+	}
+
+	skb_dst_drop(skb);
+	ip6_route_input(skb);
+
+	return dst_input(skb);
+}
+
+int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	struct dst_entry *orig_dst = skb_dst(skb);
+	struct dst_entry *dst = NULL;
+	struct seg6_lwt *slwt;
+	int err = -EINVAL;
+
+	err = seg6_do_srh(skb);
+	if (unlikely(err))
+		goto drop;
+
+	slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
+
+#ifdef CONFIG_DST_CACHE
+	dst = dst_cache_get(&slwt->cache);
+#endif
+
+	if (unlikely(!dst)) {
+		struct ipv6hdr *hdr = ipv6_hdr(skb);
+		struct flowi6 fl6;
+
+		fl6.daddr = hdr->daddr;
+		fl6.saddr = hdr->saddr;
+		fl6.flowlabel = ip6_flowinfo(hdr);
+		fl6.flowi6_mark = skb->mark;
+		fl6.flowi6_proto = hdr->nexthdr;
+
+		dst = ip6_route_output(net, NULL, &fl6);
+		if (dst->error) {
+			err = dst->error;
+			dst_release(dst);
+			goto drop;
+		}
+
+#ifdef CONFIG_DST_CACHE
+		dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr);
+#endif
+	}
+
+	skb_dst_drop(skb);
+	skb_dst_set(skb, dst);
+
+	return dst_output(net, sk, skb);
+drop:
+	kfree_skb(skb);
+	return err;
+}
+
+static int seg6_build_state(struct net_device *dev, struct nlattr *nla,
+			    unsigned int family, const void *cfg,
+			    struct lwtunnel_state **ts)
+{
+	struct nlattr *tb[SEG6_IPTUNNEL_MAX + 1];
+	struct seg6_iptunnel_encap *tuninfo;
+	struct lwtunnel_state *newts;
+	int tuninfo_len, min_size;
+	struct seg6_lwt *slwt;
+	int err;
+
+	err = nla_parse_nested(tb, SEG6_IPTUNNEL_MAX, nla,
+			       seg6_iptunnel_policy);
+
+	if (err < 0)
+		return err;
+
+	if (!tb[SEG6_IPTUNNEL_SRH])
+		return -EINVAL;
+
+	tuninfo = nla_data(tb[SEG6_IPTUNNEL_SRH]);
+	tuninfo_len = nla_len(tb[SEG6_IPTUNNEL_SRH]);
+
+	/* tuninfo must contain at least the iptunnel encap structure,
+	 * the SRH and one segment
+	 */
+	min_size = sizeof(*tuninfo) + sizeof(struct ipv6_sr_hdr) +
+		   sizeof(struct in6_addr);
+	if (tuninfo_len < min_size)
+		return -EINVAL;
+
+	switch (tuninfo->mode) {
+#ifdef CONFIG_IPV6_SEG6_INLINE
+	case SEG6_IPTUN_MODE_INLINE:
+		break;
+#endif
+	case SEG6_IPTUN_MODE_ENCAP:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* verify that SRH is consistent */
+	if (!seg6_validate_srh(tuninfo->srh, tuninfo_len - sizeof(*tuninfo)))
+		return -EINVAL;
+
+	newts = lwtunnel_state_alloc(tuninfo_len + sizeof(*slwt));
+	if (!newts)
+		return -ENOMEM;
+
+	slwt = seg6_lwt_lwtunnel(newts);
+
+#ifdef CONFIG_DST_CACHE
+	err = dst_cache_init(&slwt->cache, GFP_KERNEL);
+	if (err) {
+		kfree(newts);
+		return err;
+	}
+#endif
+
+	memcpy(&slwt->tuninfo, tuninfo, tuninfo_len);
+
+	newts->type = LWTUNNEL_ENCAP_SEG6;
+	newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT |
+			LWTUNNEL_STATE_INPUT_REDIRECT;
+	newts->headroom = seg6_lwt_headroom(tuninfo);
+
+	*ts = newts;
+
+	return 0;
+}
+
+#ifdef CONFIG_DST_CACHE
+static void seg6_destroy_state(struct lwtunnel_state *lwt)
+{
+	dst_cache_destroy(&seg6_lwt_lwtunnel(lwt)->cache);
+}
+#endif
+
+static int seg6_fill_encap_info(struct sk_buff *skb,
+				struct lwtunnel_state *lwtstate)
+{
+	struct seg6_iptunnel_encap *tuninfo = seg6_encap_lwtunnel(lwtstate);
+
+	if (nla_put_srh(skb, SEG6_IPTUNNEL_SRH, tuninfo))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int seg6_encap_nlsize(struct lwtunnel_state *lwtstate)
+{
+	struct seg6_iptunnel_encap *tuninfo = seg6_encap_lwtunnel(lwtstate);
+
+	return nla_total_size(SEG6_IPTUN_ENCAP_SIZE(tuninfo));
+}
+
+static int seg6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
+{
+	struct seg6_iptunnel_encap *a_hdr = seg6_encap_lwtunnel(a);
+	struct seg6_iptunnel_encap *b_hdr = seg6_encap_lwtunnel(b);
+	int len = SEG6_IPTUN_ENCAP_SIZE(a_hdr);
+
+	if (len != SEG6_IPTUN_ENCAP_SIZE(b_hdr))
+		return 1;
+
+	return memcmp(a_hdr, b_hdr, len);
+}
+
+static const struct lwtunnel_encap_ops seg6_iptun_ops = {
+	.build_state = seg6_build_state,
+#ifdef CONFIG_DST_CACHE
+	.destroy_state = seg6_destroy_state,
+#endif
+	.output = seg6_output,
+	.input = seg6_input,
+	.fill_encap = seg6_fill_encap_info,
+	.get_encap_size = seg6_encap_nlsize,
+	.cmp_encap = seg6_encap_cmp,
+};
+
+int __init seg6_iptunnel_init(void)
+{
+	return lwtunnel_encap_add_ops(&seg6_iptun_ops, LWTUNNEL_ENCAP_SEG6);
+}
+
+void seg6_iptunnel_exit(void)
+{
+	lwtunnel_encap_del_ops(&seg6_iptun_ops, LWTUNNEL_ENCAP_SEG6);
+}