* [PATCH RFC net-next v5 1/2] seg6: add support for the SRv6 End.MAP behavior
2026-10-02 12:31 [PATCH RFC net-next v5 0/2] seg6: add support for the SRv6 End.MAP behavior Yuya Kusakabe
@ 2026-10-02 12:31 ` Yuya Kusakabe
2026-10-02 12:31 ` [PATCH RFC net-next v5 2/2] selftests: seg6: add selftest for " Yuya Kusakabe
1 sibling, 0 replies; 3+ messages in thread
From: Yuya Kusakabe @ 2026-10-02 12:31 UTC (permalink / raw)
To: Andrea Mayer, Andrea Mayer, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, David Ahern,
Ido Schimmel, Shuah Khan
Cc: Justin Iurman, Florian Westphal, Fernando Fernandez Mancera,
linux-kernel, netdev, linux-kselftest, Yuya Kusakabe
SRv6 End.MAP is defined in RFC 9433 [1].
The SRv6 End.MAP is an SRv6 endpoint that replaces the IPv6
destination address with the configured mapped SID and forwards the
packet via the IPv6 FIB without consuming the SRH.
The SRv6 End.MAP Linux implementation is the first behavior of the
SRv6 Mobile User Plane and introduces a dedicated
LWTUNNEL_ENCAP_SEG6_MOBILE encap type, a CONFIG_IPV6_SEG6_MOBILE
build option and a net/ipv6/seg6_mobile.c file that hosts the
action dispatch table. The user-space ABI lives in
include/uapi/linux/seg6_mobile.h under a SEG6_MOBILE_* namespace,
kept separate from SEG6_LOCAL_* so that attributes whose semantics
differ between behaviors do not overload the same UAPI table.
The SRv6 End.MAP behavior can be instantiated using a command
similar to the following:
$ ip -6 route add 2001:db8:f::/64 encap seg6mobile action End.MAP \
mapped_sid 2001:db8:2::e dev eth0
We introduce the "seg6mobile" extension in iproute2 in a following
patch.
[1] https://www.rfc-editor.org/rfc/rfc9433.html
Assisted-by: LLM
Signed-off-by: Yuya Kusakabe <yuya.kusakabe@gmail.com>
---
include/net/seg6.h | 8 +
include/uapi/linux/lwtunnel.h | 1 +
include/uapi/linux/seg6_mobile.h | 61 ++++
net/core/lwtunnel.c | 2 +
net/ipv6/Kconfig | 10 +
net/ipv6/Makefile | 1 +
net/ipv6/seg6.c | 7 +
net/ipv6/seg6_mobile.c | 723 +++++++++++++++++++++++++++++++++++++++
8 files changed, 813 insertions(+)
diff --git a/include/net/seg6.h b/include/net/seg6.h
index 82b3fbbcbb93..789e9bcc4773 100644
--- a/include/net/seg6.h
+++ b/include/net/seg6.h
@@ -64,6 +64,14 @@ static inline int seg6_local_init(void) { return 0; }
static inline void seg6_local_exit(void) {}
#endif
+#ifdef CONFIG_IPV6_SEG6_MOBILE
+extern int seg6_mobile_init(void);
+extern void seg6_mobile_exit(void);
+#else
+static inline int seg6_mobile_init(void) { return 0; }
+static inline void seg6_mobile_exit(void) {}
+#endif
+
extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced);
extern struct ipv6_sr_hdr *seg6_get_srh(struct sk_buff *skb, int flags);
extern void seg6_icmp_srh(struct sk_buff *skb, struct inet6_skb_parm *opt);
diff --git a/include/uapi/linux/lwtunnel.h b/include/uapi/linux/lwtunnel.h
index 229655ef792f..6e48f79c548e 100644
--- a/include/uapi/linux/lwtunnel.h
+++ b/include/uapi/linux/lwtunnel.h
@@ -16,6 +16,7 @@ enum lwtunnel_encap_types {
LWTUNNEL_ENCAP_RPL,
LWTUNNEL_ENCAP_IOAM6,
LWTUNNEL_ENCAP_XFRM,
+ LWTUNNEL_ENCAP_SEG6_MOBILE,
__LWTUNNEL_ENCAP_MAX,
};
diff --git a/include/uapi/linux/seg6_mobile.h b/include/uapi/linux/seg6_mobile.h
new file mode 100644
index 000000000000..068ab91b2873
--- /dev/null
+++ b/include/uapi/linux/seg6_mobile.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * SRv6 Mobile User Plane implementation
+ *
+ * Author:
+ * Yuya Kusakabe <yuya.kusakabe@gmail.com>
+ */
+#ifndef _UAPI_LINUX_SEG6_MOBILE_H
+#define _UAPI_LINUX_SEG6_MOBILE_H
+
+enum {
+ SEG6_MOBILE_UNSPEC,
+ SEG6_MOBILE_ACTION,
+ SEG6_MOBILE_MAPPED_SID,
+ SEG6_MOBILE_COUNTERS,
+ __SEG6_MOBILE_MAX,
+};
+
+#define SEG6_MOBILE_MAX (__SEG6_MOBILE_MAX - 1)
+
+enum {
+ SEG6_MOBILE_ACTION_UNSPEC = 0,
+ /* swap IPv6 DA with the mapped SID, leave SRH untouched */
+ SEG6_MOBILE_ACTION_END_MAP = 1,
+
+ __SEG6_MOBILE_ACTION_MAX,
+};
+
+#define SEG6_MOBILE_ACTION_MAX (__SEG6_MOBILE_ACTION_MAX - 1)
+
+/* SRv6 Mobile Behavior counters are encoded as netlink attributes
+ * guaranteeing the correct alignment.
+ * Each counter is identified by a different attribute type (i.e.
+ * SEG6_MOBILE_CNT_PACKETS).
+ *
+ * - SEG6_MOBILE_CNT_PACKETS: identifies a counter that counts the number
+ * of packets that have been CORRECTLY processed by an SRv6 Behavior
+ * instance (i.e., packets that generate errors or are dropped are NOT
+ * counted).
+ *
+ * - SEG6_MOBILE_CNT_BYTES: identifies a counter that counts the total
+ * amount of traffic in bytes of all packets that have been CORRECTLY
+ * processed by an SRv6 Behavior instance (i.e., packets that generate
+ * errors or are dropped are NOT counted).
+ *
+ * - SEG6_MOBILE_CNT_ERRORS: identifies a counter that counts the number
+ * of packets that have NOT been properly processed by an SRv6 Behavior
+ * instance (i.e., packets that generate errors or are dropped).
+ */
+enum {
+ SEG6_MOBILE_CNT_UNSPEC,
+ SEG6_MOBILE_CNT_PACKETS,
+ SEG6_MOBILE_CNT_BYTES,
+ SEG6_MOBILE_CNT_ERRORS,
+ SEG6_MOBILE_CNT_PAD, /* pad for 64 bits values */
+ __SEG6_MOBILE_CNT_MAX,
+};
+
+#define SEG6_MOBILE_CNT_MAX (__SEG6_MOBILE_CNT_MAX - 1)
+
+#endif /* _UAPI_LINUX_SEG6_MOBILE_H */
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index b01a395d9a96..4476293ccb37 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -53,6 +53,8 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type)
case LWTUNNEL_ENCAP_XFRM:
/* module autoload not supported for encap type */
return NULL;
+ case LWTUNNEL_ENCAP_SEG6_MOBILE:
+ return "SEG6MOBILE";
case LWTUNNEL_ENCAP_IP6:
case LWTUNNEL_ENCAP_IP:
case LWTUNNEL_ENCAP_NONE:
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index c3806c6ac96f..e094b835a118 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -314,6 +314,16 @@ config IPV6_SEG6_BPF
depends on IPV6_SEG6_LWTUNNEL
depends on IPV6 = y
+config IPV6_SEG6_MOBILE
+ bool "IPv6: SRv6 Mobile User Plane (RFC 9433) behaviors"
+ depends on IPV6_SEG6_LWTUNNEL
+ help
+ Support for the SRv6 Mobile User Plane behaviors defined by
+ RFC 9433, exposed via the LWTUNNEL_ENCAP_SEG6_MOBILE lightweight
+ tunnel encapsulation.
+
+ If unsure, say N.
+
config IPV6_RPL_LWTUNNEL
bool "IPv6: RPL Source Routing Header support"
depends on IPV6
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index cf5e01f83ce3..95961f180439 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -24,6 +24,7 @@ ipv6-$(CONFIG_SYN_COOKIES) += syncookies.o
ipv6-$(CONFIG_NETLABEL) += calipso.o
ipv6-$(CONFIG_IPV6_SEG6_LWTUNNEL) += seg6_iptunnel.o seg6_local.o
ipv6-$(CONFIG_IPV6_SEG6_HMAC) += seg6_hmac.o
+ipv6-$(CONFIG_IPV6_SEG6_MOBILE) += seg6_mobile.o
ipv6-$(CONFIG_IPV6_RPL_LWTUNNEL) += rpl_iptunnel.o
ipv6-$(CONFIG_IPV6_IOAM6_LWTUNNEL) += ioam6_iptunnel.o
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index 8c2b156c227a..c7f71174b6d0 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -525,10 +525,16 @@ int __init seg6_init(void)
if (err)
goto out_unregister_iptun;
+ err = seg6_mobile_init();
+ if (err)
+ goto out_unregister_local;
+
pr_info("Segment Routing with IPv6\n");
out:
return err;
+out_unregister_local:
+ seg6_local_exit();
out_unregister_iptun:
seg6_iptunnel_exit();
out_unregister_genl:
@@ -540,6 +546,7 @@ int __init seg6_init(void)
void seg6_exit(void)
{
+ seg6_mobile_exit();
seg6_local_exit();
seg6_iptunnel_exit();
genl_unregister_family(&seg6_genl_family);
diff --git a/net/ipv6/seg6_mobile.c b/net/ipv6/seg6_mobile.c
new file mode 100644
index 000000000000..8a228f44d1e2
--- /dev/null
+++ b/net/ipv6/seg6_mobile.c
@@ -0,0 +1,723 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * SRv6 Mobile User Plane implementation
+ *
+ * Author:
+ * Yuya Kusakabe <yuya.kusakabe@gmail.com>
+ */
+
+#include <linux/icmpv6.h>
+#include <linux/in6.h>
+#include <linux/ipv6.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/tcp.h>
+#include <linux/types.h>
+#include <linux/udp.h>
+#include <net/checksum.h>
+#include <net/ipv6.h>
+#include <net/lwtunnel.h>
+#include <net/seg6.h>
+#ifdef CONFIG_IPV6_SEG6_HMAC
+#include <net/seg6_hmac.h>
+#endif
+#include <uapi/linux/seg6_mobile.h>
+
+#define SEG6_MOBILE_F_ATTR(i) BIT(i)
+#define SEG6_F_MOBILE_COUNTERS SEG6_MOBILE_F_ATTR(SEG6_MOBILE_COUNTERS)
+
+struct seg6_mobile_lwt;
+
+struct seg6_mobile_action_desc {
+ int action;
+ unsigned long attrs;
+ unsigned long optattrs;
+ int (*input)(struct sk_buff *skb, struct seg6_mobile_lwt *slwt);
+};
+
+struct seg6_mobile_action_param {
+ int (*parse)(struct nlattr **attrs, struct seg6_mobile_lwt *slwt,
+ struct netlink_ext_ack *extack);
+ int (*put)(struct sk_buff *skb, struct seg6_mobile_lwt *slwt);
+ int (*cmp)(struct seg6_mobile_lwt *a, struct seg6_mobile_lwt *b);
+
+ /* optional destroy() callback to release resources acquired in
+ * the corresponding parse() function.
+ */
+ void (*destroy)(struct seg6_mobile_lwt *slwt);
+};
+
+struct pcpu_seg6_mobile_counters {
+ u64_stats_t packets;
+ u64_stats_t bytes;
+ u64_stats_t errors;
+
+ struct u64_stats_sync syncp;
+};
+
+/* User-space aggregate format for the per-CPU counters. Kept private
+ * to the kernel; userspace receives the values through SEG6_MOBILE_CNT_*
+ * nested netlink attributes.
+ */
+struct seg6_mobile_counters {
+ __u64 packets;
+ __u64 bytes;
+ __u64 errors;
+};
+
+#define seg6_mobile_alloc_pcpu_counters(__gfp) \
+ __netdev_alloc_pcpu_stats(struct pcpu_seg6_mobile_counters, \
+ ((__gfp) | __GFP_ZERO))
+
+struct seg6_mobile_lwt {
+ int action;
+ struct in6_addr mapped_sid;
+ const struct seg6_mobile_action_desc *desc;
+ struct pcpu_seg6_mobile_counters __percpu *pcpu_counters;
+
+ /* required attrs are tracked by desc->attrs; optional attrs that
+ * the user actually configured are tracked here so that fill_encap
+ * / cmp / destroy can iterate only over what was parsed.
+ */
+ unsigned long parsed_optattrs;
+};
+
+static struct seg6_mobile_lwt *seg6_mobile_lwtunnel(struct lwtunnel_state *lwt)
+{
+ return (struct seg6_mobile_lwt *)lwt->data;
+}
+
+/* ABSENT is told apart from MALFORMED so that a behavior which accepts
+ * SRH-less packets still drops a malformed SRH
+ */
+enum seg6_mobile_srh_state {
+ SEG6_MOBILE_SRH_ABSENT,
+ SEG6_MOBILE_SRH_PRESENT,
+ SEG6_MOBILE_SRH_MALFORMED,
+};
+
+static struct ipv6_sr_hdr *
+seg6_mobile_get_and_validate_srh(struct sk_buff *skb,
+ enum seg6_mobile_srh_state *state)
+{
+ struct ipv6_rt_hdr _rh, *rh;
+ struct ipv6_sr_hdr *srh;
+ unsigned int srhoff = 0;
+ int hdr_proto;
+ int flags = 0;
+
+ srh = seg6_get_srh(skb, 0);
+ if (srh) {
+#ifdef CONFIG_IPV6_SEG6_HMAC
+ if (!seg6_hmac_validate_skb(skb, srh)) {
+ *state = SEG6_MOBILE_SRH_MALFORMED;
+ return NULL;
+ }
+#endif
+ *state = SEG6_MOBILE_SRH_PRESENT;
+ return srh;
+ }
+
+ hdr_proto = ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, &flags);
+ if (hdr_proto == -ENOENT) {
+ *state = SEG6_MOBILE_SRH_ABSENT;
+ return NULL;
+ }
+
+ /* RFC 8200 Section 4.4: an unrecognized Routing Type with Segments
+ * Left 0 is ignored
+ */
+ rh = hdr_proto == IPPROTO_ROUTING ?
+ skb_header_pointer(skb, srhoff, sizeof(_rh), &_rh) : NULL;
+ if (rh && rh->type != IPV6_SRCRT_TYPE_4 && !rh->segments_left)
+ *state = SEG6_MOBILE_SRH_ABSENT;
+ else
+ *state = SEG6_MOBILE_SRH_MALFORMED;
+ return NULL;
+}
+
+static int seg6_mobile_l4_csum_hlen(u8 nexthdr)
+{
+ switch (nexthdr) {
+ case IPPROTO_TCP:
+ return sizeof(struct tcphdr);
+ case IPPROTO_UDP:
+ return sizeof(struct udphdr);
+ case IPPROTO_ICMPV6:
+ return sizeof(struct icmp6hdr);
+ }
+ return 0;
+}
+
+static __sum16 *seg6_mobile_l4_csum(struct sk_buff *skb, int l4_off,
+ u8 nexthdr)
+{
+ switch (nexthdr) {
+ case IPPROTO_TCP:
+ return &((struct tcphdr *)(skb->data + l4_off))->check;
+ case IPPROTO_UDP: {
+ struct udphdr *uh = (struct udphdr *)(skb->data + l4_off);
+
+ /* zero UDPv6 checksum on a non-offloaded skb means "none" */
+ if (!uh->check && skb->ip_summed != CHECKSUM_PARTIAL)
+ return NULL;
+ return &uh->check;
+ }
+ case IPPROTO_ICMPV6:
+ return &((struct icmp6hdr *)(skb->data + l4_off))->icmp6_cksum;
+ }
+ return NULL;
+}
+
+/* rewrite DA; the L4 checksum follows only when the receiver will verify
+ * it against the new DA, i.e. no SRH is left for it to process
+ */
+static enum skb_drop_reason
+seg6_mobile_advance_da(struct sk_buff *skb, const struct in6_addr *nh,
+ bool srh_present)
+{
+ int l4_off = 0, l4_hlen = 0;
+ unsigned int nonext_off = 0;
+ struct in6_addr old_da;
+ struct ipv6hdr *ip6h;
+ __be16 frag_off;
+ u8 nexthdr = 0;
+ __sum16 *csum;
+ int write_len;
+
+ if (!pskb_may_pull(skb, sizeof(*ip6h)))
+ return SKB_DROP_REASON_NOT_SPECIFIED;
+
+ ip6h = ipv6_hdr(skb);
+ write_len = sizeof(*ip6h);
+
+ if (!srh_present) {
+ nexthdr = ip6h->nexthdr;
+ l4_off = ipv6_skip_exthdr(skb, sizeof(*ip6h), &nexthdr,
+ &frag_off);
+ /* a chain ending in No Next Header has no L4 checksum */
+ if (l4_off < 0 &&
+ ipv6_find_hdr(skb, &nonext_off, NEXTHDR_NONE, NULL,
+ NULL) != NEXTHDR_NONE)
+ return SKB_DROP_REASON_NOT_SPECIFIED;
+
+ /* only the first fragment carries the L4 header; frag_off
+ * is the raw field, M flag included
+ */
+ if (l4_off >= 0 && !(frag_off & htons(IP6_OFFSET)))
+ l4_hlen = seg6_mobile_l4_csum_hlen(nexthdr);
+ if (l4_hlen)
+ write_len = l4_off + l4_hlen;
+ }
+
+ if (skb_ensure_writable(skb, write_len))
+ return SKB_DROP_REASON_NOMEM;
+
+ /* skb_ensure_writable() may change skb pointers; evaluate ip6h again */
+ ip6h = ipv6_hdr(skb);
+ old_da = ip6h->daddr;
+
+ csum = l4_hlen ? seg6_mobile_l4_csum(skb, l4_off, nexthdr) : NULL;
+ if (csum) {
+ inet_proto_csum_replace16(csum, skb, old_da.s6_addr32,
+ nh->s6_addr32, true);
+ if (nexthdr == IPPROTO_UDP && !*csum)
+ *csum = CSUM_MANGLED_0;
+ } else if (skb->ip_summed == CHECKSUM_COMPLETE) {
+ /* no L4 patch, so skb->csum must track the DA change itself */
+ update_csum_diff16(skb, old_da.s6_addr32, (__be32 *)nh);
+ }
+
+ ip6h->daddr = *nh;
+ skb_clear_hash(skb);
+
+ return SKB_NOT_DROPPED_YET;
+}
+
+static int seg6_mobile_forward(struct sk_buff *skb)
+{
+ seg6_lookup_nexthop(skb, NULL, 0);
+ return dst_input(skb);
+}
+
+/* replace DA with the mapped SID and forward, leaving the SRH untouched */
+static int input_action_end_map(struct sk_buff *skb,
+ struct seg6_mobile_lwt *slwt)
+{
+ enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
+ enum seg6_mobile_srh_state srh_state;
+ struct ipv6_sr_hdr *srh;
+
+ srh = seg6_mobile_get_and_validate_srh(skb, &srh_state);
+ if (srh_state == SEG6_MOBILE_SRH_MALFORMED)
+ goto drop;
+
+ /* SL == 0: SRH spent, L4 is verified against the new DA */
+ reason = seg6_mobile_advance_da(skb, &slwt->mapped_sid,
+ srh && srh->segments_left);
+ if (reason)
+ goto drop;
+
+ return seg6_mobile_forward(skb);
+
+drop:
+ kfree_skb_reason(skb, reason);
+ return -EINVAL;
+}
+
+static int parse_nla_mapped_sid(struct nlattr **attrs,
+ struct seg6_mobile_lwt *slwt,
+ struct netlink_ext_ack *extack)
+{
+ memcpy(&slwt->mapped_sid, nla_data(attrs[SEG6_MOBILE_MAPPED_SID]),
+ sizeof(struct in6_addr));
+
+ return 0;
+}
+
+static int put_nla_mapped_sid(struct sk_buff *skb, struct seg6_mobile_lwt *slwt)
+{
+ if (nla_put_in6_addr(skb, SEG6_MOBILE_MAPPED_SID, &slwt->mapped_sid))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+static int cmp_nla_mapped_sid(struct seg6_mobile_lwt *a,
+ struct seg6_mobile_lwt *b)
+{
+ return memcmp(&a->mapped_sid, &b->mapped_sid, sizeof(struct in6_addr));
+}
+
+static const struct
+nla_policy seg6_mobile_counters_policy[SEG6_MOBILE_CNT_MAX + 1] = {
+ [SEG6_MOBILE_CNT_PACKETS] = { .type = NLA_U64 },
+ [SEG6_MOBILE_CNT_BYTES] = { .type = NLA_U64 },
+ [SEG6_MOBILE_CNT_ERRORS] = { .type = NLA_U64 },
+};
+
+static int parse_nla_counters(struct nlattr **attrs,
+ struct seg6_mobile_lwt *slwt,
+ struct netlink_ext_ack *extack)
+{
+ struct pcpu_seg6_mobile_counters __percpu *pcounters;
+ struct nlattr *tb[SEG6_MOBILE_CNT_MAX + 1];
+ int ret;
+
+ ret = nla_parse_nested(tb, SEG6_MOBILE_CNT_MAX,
+ attrs[SEG6_MOBILE_COUNTERS],
+ seg6_mobile_counters_policy, extack);
+ if (ret < 0)
+ return ret;
+
+ /* basic support for SRv6 Behavior counters requires at least:
+ * packets, bytes and errors.
+ */
+ if (!tb[SEG6_MOBILE_CNT_PACKETS] || !tb[SEG6_MOBILE_CNT_BYTES] ||
+ !tb[SEG6_MOBILE_CNT_ERRORS])
+ return -EINVAL;
+
+ /* counters are always zero initialized */
+ pcounters = seg6_mobile_alloc_pcpu_counters(GFP_KERNEL);
+ if (!pcounters)
+ return -ENOMEM;
+
+ slwt->pcpu_counters = pcounters;
+
+ return 0;
+}
+
+static int seg6_mobile_fill_nla_counters(struct sk_buff *skb,
+ struct seg6_mobile_counters *counters)
+{
+ if (nla_put_u64_64bit(skb, SEG6_MOBILE_CNT_PACKETS, counters->packets,
+ SEG6_MOBILE_CNT_PAD))
+ return -EMSGSIZE;
+
+ if (nla_put_u64_64bit(skb, SEG6_MOBILE_CNT_BYTES, counters->bytes,
+ SEG6_MOBILE_CNT_PAD))
+ return -EMSGSIZE;
+
+ if (nla_put_u64_64bit(skb, SEG6_MOBILE_CNT_ERRORS, counters->errors,
+ SEG6_MOBILE_CNT_PAD))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+static int put_nla_counters(struct sk_buff *skb, struct seg6_mobile_lwt *slwt)
+{
+ struct seg6_mobile_counters counters = { 0, 0, 0 };
+ struct nlattr *nest;
+ int rc, i;
+
+ nest = nla_nest_start(skb, SEG6_MOBILE_COUNTERS);
+ if (!nest)
+ return -EMSGSIZE;
+
+ for_each_possible_cpu(i) {
+ struct pcpu_seg6_mobile_counters *pcounters;
+ u64 packets, bytes, errors;
+ unsigned int start;
+
+ pcounters = per_cpu_ptr(slwt->pcpu_counters, i);
+ do {
+ start = u64_stats_fetch_begin(&pcounters->syncp);
+
+ packets = u64_stats_read(&pcounters->packets);
+ bytes = u64_stats_read(&pcounters->bytes);
+ errors = u64_stats_read(&pcounters->errors);
+
+ } while (u64_stats_fetch_retry(&pcounters->syncp, start));
+
+ counters.packets += packets;
+ counters.bytes += bytes;
+ counters.errors += errors;
+ }
+
+ rc = seg6_mobile_fill_nla_counters(skb, &counters);
+ if (rc < 0) {
+ nla_nest_cancel(skb, nest);
+ return rc;
+ }
+
+ return nla_nest_end(skb, nest);
+}
+
+static int cmp_nla_counters(struct seg6_mobile_lwt *a,
+ struct seg6_mobile_lwt *b)
+{
+ /* tunnels with counters enabled and disabled are different. */
+ return (!!((unsigned long)a->pcpu_counters)) ^
+ (!!((unsigned long)b->pcpu_counters));
+}
+
+static void destroy_attr_counters(struct seg6_mobile_lwt *slwt)
+{
+ free_percpu(slwt->pcpu_counters);
+}
+
+static const struct seg6_mobile_action_desc seg6_mobile_action_table[] = {
+ {
+ .action = SEG6_MOBILE_ACTION_END_MAP,
+ .attrs = SEG6_MOBILE_F_ATTR(SEG6_MOBILE_MAPPED_SID),
+ .optattrs = SEG6_F_MOBILE_COUNTERS,
+ .input = input_action_end_map,
+ },
+};
+
+static const struct seg6_mobile_action_param
+seg6_mobile_action_params[SEG6_MOBILE_MAX + 1] = {
+ [SEG6_MOBILE_MAPPED_SID] = {
+ .parse = parse_nla_mapped_sid,
+ .put = put_nla_mapped_sid,
+ .cmp = cmp_nla_mapped_sid,
+ },
+ [SEG6_MOBILE_COUNTERS] = {
+ .parse = parse_nla_counters,
+ .put = put_nla_counters,
+ .cmp = cmp_nla_counters,
+ .destroy = destroy_attr_counters,
+ },
+};
+
+static const struct nla_policy
+seg6_mobile_policy[SEG6_MOBILE_MAX + 1] = {
+ [SEG6_MOBILE_ACTION] = { .type = NLA_U32 },
+ [SEG6_MOBILE_MAPPED_SID] =
+ NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
+ [SEG6_MOBILE_COUNTERS] = { .type = NLA_NESTED },
+};
+
+static const struct seg6_mobile_action_desc *
+seg6_mobile_get_action_desc(int action)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(seg6_mobile_action_table); i++) {
+ if (seg6_mobile_action_table[i].action == action)
+ return &seg6_mobile_action_table[i];
+ }
+
+ return NULL;
+}
+
+/* call the destroy() callback (if available) for each set attribute in
+ * @parsed_attrs, starting from the first attribute up to the @max_parsed
+ * (excluded) attribute.
+ */
+static void __destroy_attrs(unsigned long parsed_attrs, int max_parsed,
+ struct seg6_mobile_lwt *slwt)
+{
+ const struct seg6_mobile_action_param *param;
+ int i;
+
+ for (i = SEG6_MOBILE_ACTION + 1; i < max_parsed; i++) {
+ if (!(parsed_attrs & SEG6_MOBILE_F_ATTR(i)))
+ continue;
+
+ param = &seg6_mobile_action_params[i];
+ if (param->destroy)
+ param->destroy(slwt);
+ }
+}
+
+static void destroy_attrs(struct seg6_mobile_lwt *slwt)
+{
+ unsigned long attrs = slwt->desc->attrs | slwt->parsed_optattrs;
+
+ __destroy_attrs(attrs, SEG6_MOBILE_MAX + 1, slwt);
+}
+
+static int seg6_mobile_parse_attrs(struct nlattr **attrs,
+ struct seg6_mobile_lwt *slwt,
+ struct netlink_ext_ack *extack)
+{
+ const struct seg6_mobile_action_param *param;
+ const struct seg6_mobile_action_desc *desc;
+ unsigned long parsed_optattrs = 0;
+ int i, err;
+
+ desc = slwt->desc;
+
+ if (WARN_ON_ONCE(desc->attrs & desc->optattrs))
+ return -EINVAL;
+
+ for (i = SEG6_MOBILE_ACTION + 1; i <= SEG6_MOBILE_MAX; i++) {
+ bool required = desc->attrs & SEG6_MOBILE_F_ATTR(i);
+ bool optional = desc->optattrs & SEG6_MOBILE_F_ATTR(i);
+
+ if (!required && !optional)
+ continue;
+
+ if (required && !attrs[i]) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "missing required attribute");
+ err = -EINVAL;
+ goto err;
+ }
+
+ if (!attrs[i])
+ continue;
+
+ param = &seg6_mobile_action_params[i];
+ err = param->parse(attrs, slwt, extack);
+ if (err < 0)
+ goto err;
+
+ if (optional)
+ parsed_optattrs |= SEG6_MOBILE_F_ATTR(i);
+ }
+
+ slwt->parsed_optattrs = parsed_optattrs;
+
+ return 0;
+
+err:
+ __destroy_attrs(desc->attrs | parsed_optattrs, i, slwt);
+ return err;
+}
+
+static bool seg6_mobile_counters_enabled(struct seg6_mobile_lwt *slwt)
+{
+ return slwt->parsed_optattrs & SEG6_F_MOBILE_COUNTERS;
+}
+
+static void seg6_mobile_update_counters(struct seg6_mobile_lwt *slwt,
+ unsigned int len, int err)
+{
+ struct pcpu_seg6_mobile_counters *pcounters;
+
+ pcounters = this_cpu_ptr(slwt->pcpu_counters);
+ u64_stats_update_begin(&pcounters->syncp);
+
+ if (likely(!err)) {
+ u64_stats_inc(&pcounters->packets);
+ u64_stats_add(&pcounters->bytes, len);
+ } else {
+ u64_stats_inc(&pcounters->errors);
+ }
+
+ u64_stats_update_end(&pcounters->syncp);
+}
+
+static int seg6_mobile_input(struct sk_buff *skb)
+{
+ struct dst_entry *orig_dst = skb_dst(skb);
+ struct seg6_mobile_lwt *slwt;
+ unsigned int len = skb->len;
+ int rc;
+
+ if (skb->protocol != htons(ETH_P_IPV6)) {
+ kfree_skb(skb);
+ return -EINVAL;
+ }
+
+ slwt = seg6_mobile_lwtunnel(orig_dst->lwtstate);
+
+ rc = slwt->desc->input(skb, slwt);
+
+ if (seg6_mobile_counters_enabled(slwt))
+ seg6_mobile_update_counters(slwt, len, rc);
+
+ return rc;
+}
+
+static int seg6_mobile_build_state(struct net *net, struct nlattr *nla,
+ unsigned int family, const void *cfg,
+ struct lwtunnel_state **ts,
+ struct netlink_ext_ack *extack)
+{
+ const struct seg6_mobile_action_desc *desc;
+ struct nlattr *tb[SEG6_MOBILE_MAX + 1];
+ struct lwtunnel_state *newts;
+ struct seg6_mobile_lwt *slwt;
+ int err;
+
+ if (family != AF_INET6)
+ return -EINVAL;
+
+ err = nla_parse_nested(tb, SEG6_MOBILE_MAX, nla,
+ seg6_mobile_policy, extack);
+ if (err < 0)
+ return err;
+
+ if (!tb[SEG6_MOBILE_ACTION]) {
+ NL_SET_ERR_MSG_MOD(extack, "missing SEG6_MOBILE_ACTION");
+ return -EINVAL;
+ }
+
+ desc = seg6_mobile_get_action_desc(nla_get_u32(tb[SEG6_MOBILE_ACTION]));
+ if (!desc) {
+ NL_SET_ERR_MSG_MOD(extack, "unknown SRv6 Mobile action");
+ return -EOPNOTSUPP;
+ }
+
+ newts = lwtunnel_state_alloc(sizeof(*slwt));
+ if (!newts)
+ return -ENOMEM;
+
+ slwt = seg6_mobile_lwtunnel(newts);
+ slwt->action = desc->action;
+ slwt->desc = desc;
+
+ err = seg6_mobile_parse_attrs(tb, slwt, extack);
+ if (err < 0) {
+ kfree(newts);
+ return err;
+ }
+
+ newts->type = LWTUNNEL_ENCAP_SEG6_MOBILE;
+ newts->flags = LWTUNNEL_STATE_INPUT_REDIRECT;
+
+ *ts = newts;
+
+ return 0;
+}
+
+static void seg6_mobile_destroy_state(struct lwtunnel_state *lwt)
+{
+ destroy_attrs(seg6_mobile_lwtunnel(lwt));
+}
+
+static int seg6_mobile_fill_encap(struct sk_buff *skb,
+ struct lwtunnel_state *lwt)
+{
+ struct seg6_mobile_lwt *slwt = seg6_mobile_lwtunnel(lwt);
+ const struct seg6_mobile_action_param *param;
+ unsigned long attrs;
+ int i, err;
+
+ if (nla_put_u32(skb, SEG6_MOBILE_ACTION, slwt->action))
+ return -EMSGSIZE;
+
+ attrs = slwt->desc->attrs | slwt->parsed_optattrs;
+ for (i = SEG6_MOBILE_ACTION + 1; i <= SEG6_MOBILE_MAX; i++) {
+ if (!(attrs & SEG6_MOBILE_F_ATTR(i)))
+ continue;
+
+ param = &seg6_mobile_action_params[i];
+ err = param->put(skb, slwt);
+ if (err < 0)
+ return err;
+ }
+
+ return 0;
+}
+
+static int seg6_mobile_get_encap_size(struct lwtunnel_state *lwt)
+{
+ struct seg6_mobile_lwt *slwt = seg6_mobile_lwtunnel(lwt);
+ unsigned long attrs;
+ int nlsize;
+
+ nlsize = nla_total_size(sizeof(u32)); /* SEG6_MOBILE_ACTION */
+
+ attrs = slwt->desc->attrs | slwt->parsed_optattrs;
+ if (attrs & SEG6_MOBILE_F_ATTR(SEG6_MOBILE_MAPPED_SID))
+ nlsize += nla_total_size(sizeof(struct in6_addr));
+
+ if (attrs & SEG6_F_MOBILE_COUNTERS)
+ nlsize += nla_total_size(0) + /* nest SEG6_MOBILE_COUNTERS */
+ /* SEG6_MOBILE_CNT_PACKETS */
+ nla_total_size_64bit(sizeof(__u64)) +
+ /* SEG6_MOBILE_CNT_BYTES */
+ nla_total_size_64bit(sizeof(__u64)) +
+ /* SEG6_MOBILE_CNT_ERRORS */
+ nla_total_size_64bit(sizeof(__u64));
+
+ return nlsize;
+}
+
+static int seg6_mobile_cmp_encap(struct lwtunnel_state *a,
+ struct lwtunnel_state *b)
+{
+ struct seg6_mobile_lwt *slwt_a = seg6_mobile_lwtunnel(a);
+ struct seg6_mobile_lwt *slwt_b = seg6_mobile_lwtunnel(b);
+ const struct seg6_mobile_action_param *param;
+ unsigned long attrs_a, attrs_b;
+ int i;
+
+ if (slwt_a->action != slwt_b->action)
+ return 1;
+
+ attrs_a = slwt_a->desc->attrs | slwt_a->parsed_optattrs;
+ attrs_b = slwt_b->desc->attrs | slwt_b->parsed_optattrs;
+
+ if (attrs_a != attrs_b)
+ return 1;
+
+ for (i = SEG6_MOBILE_ACTION + 1; i <= SEG6_MOBILE_MAX; i++) {
+ if (!(attrs_a & SEG6_MOBILE_F_ATTR(i)))
+ continue;
+
+ param = &seg6_mobile_action_params[i];
+ if (param->cmp(slwt_a, slwt_b))
+ return 1;
+ }
+
+ return 0;
+}
+
+static const struct lwtunnel_encap_ops seg6_mobile_ops = {
+ .build_state = seg6_mobile_build_state,
+ .destroy_state = seg6_mobile_destroy_state,
+ .input = seg6_mobile_input,
+ .fill_encap = seg6_mobile_fill_encap,
+ .get_encap_size = seg6_mobile_get_encap_size,
+ .cmp_encap = seg6_mobile_cmp_encap,
+ .owner = THIS_MODULE,
+};
+
+int __init seg6_mobile_init(void)
+{
+ BUILD_BUG_ON(SEG6_MOBILE_MAX + 1 > BITS_PER_TYPE(unsigned long));
+
+ return lwtunnel_encap_add_ops(&seg6_mobile_ops,
+ LWTUNNEL_ENCAP_SEG6_MOBILE);
+}
+
+void seg6_mobile_exit(void)
+{
+ lwtunnel_encap_del_ops(&seg6_mobile_ops, LWTUNNEL_ENCAP_SEG6_MOBILE);
+}
--
2.50.1
^ permalink raw reply [flat|nested] 3+ messages in thread* [PATCH RFC net-next v5 2/2] selftests: seg6: add selftest for End.MAP behavior
2026-10-02 12:31 [PATCH RFC net-next v5 0/2] seg6: add support for the SRv6 End.MAP behavior Yuya Kusakabe
2026-10-02 12:31 ` [PATCH RFC net-next v5 1/2] " Yuya Kusakabe
@ 2026-10-02 12:31 ` Yuya Kusakabe
1 sibling, 0 replies; 3+ messages in thread
From: Yuya Kusakabe @ 2026-10-02 12:31 UTC (permalink / raw)
To: Andrea Mayer, Andrea Mayer, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, Simon Horman, David Ahern,
Ido Schimmel, Shuah Khan
Cc: Justin Iurman, Florian Westphal, Fernando Fernandez Mancera,
linux-kernel, netdev, linux-kselftest, Yuya Kusakabe
This selftest is designed for testing the SRv6 End.MAP behavior. It
instantiates three network namespaces interconnected through veth
pairs, with the middle one running End.MAP; the topology and the
cases are described in the script header.
The correct execution of the behavior is verified through ICMPv6 echo
reachability with and without an SRH, asserting that the receiver
counts no transport checksum errors, and through the route's own
error counter for the packets End.MAP must drop. A small C helper,
srv6_mobile_send, crafts the routing headers the standard tools
cannot produce.
Assisted-by: LLM
Signed-off-by: Yuya Kusakabe <yuya.kusakabe@gmail.com>
---
tools/testing/selftests/net/.gitignore | 1 +
tools/testing/selftests/net/Makefile | 2 +
tools/testing/selftests/net/config | 1 +
tools/testing/selftests/net/srv6_end_map_test.sh | 456 +++++++++++++++++++++++
tools/testing/selftests/net/srv6_mobile_send.c | 283 ++++++++++++++
5 files changed, 743 insertions(+)
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index c9f46031ac73..9afff0d83dde 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -42,6 +42,7 @@ socket
so_incoming_cpu
so_netns_cookie
so_rcv_listener
+srv6_mobile_send
stress_reuseport_listen
tap
tcp_fastopen_backup_key
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index d4ca82fec0b4..377bb91e178c 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -97,6 +97,7 @@ TEST_PROGS := \
srv6_end_dx4_netfilter_test.sh \
srv6_end_dx6_netfilter_test.sh \
srv6_end_flavors_test.sh \
+ srv6_end_map_test.sh \
srv6_end_next_csid_l3vpn_test.sh \
srv6_end_x_next_csid_l3vpn_test.sh \
srv6_hencap_red_l3vpn_test.sh \
@@ -166,6 +167,7 @@ TEST_GEN_FILES := \
so_netns_cookie \
so_rcv_listener \
socket \
+ srv6_mobile_send \
stress_reuseport_listen \
tcp_fastopen_backup_key \
tcp_inq \
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 737e7e6327b3..abdc585a325e 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -49,6 +49,7 @@ CONFIG_IPV6_ROUTE_INFO=y
CONFIG_IPV6_ROUTER_PREF=y
CONFIG_IPV6_RPL_LWTUNNEL=y
CONFIG_IPV6_SEG6_LWTUNNEL=y
+CONFIG_IPV6_SEG6_MOBILE=y
CONFIG_IPV6_SIT=y
CONFIG_IPV6_VTI=y
CONFIG_IPVLAN=m
diff --git a/tools/testing/selftests/net/srv6_end_map_test.sh b/tools/testing/selftests/net/srv6_end_map_test.sh
new file mode 100755
index 000000000000..4c6360795456
--- /dev/null
+++ b/tools/testing/selftests/net/srv6_end_map_test.sh
@@ -0,0 +1,456 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# author: Yuya Kusakabe <yuya.kusakabe@gmail.com>
+
+# Selftest for the SRv6 End.MAP behavior (RFC 9433).
+#
+# +------+ 2001:db8:1::/64 +------+ 2001:db8:2::/64 +------+
+# | rt-1 | --------------------- | rt-2 | --------------------- | rt-3 |
+# +------+ veth1 +------+ veth2 +------+
+# (End.MAP)
+#
+# rt-2 holds the End.MAP route for 2001:db8:f::/64 that replaces the
+# IPv6 destination with 2001:db8:3::3 (an address on rt-3's loopback,
+# also used as the final SRv6 segment in the H.Encaps scenario).
+#
+# The original destination 2001:db8:f::1 and the replacement
+# 2001:db8:3::3 have different 16-bit word sums, so any regression in
+# the transport-checksum diff update would corrupt the ICMPv6
+# checksum and bump Icmp6InCsumErrors -- the forwarding cases assert
+# that the counter does not move.
+#
+# Ten cases are exercised:
+#
+# 1. SRH absent -- plain ICMPv6 echo to the End.MAP SID.
+# 2. SRH present -- the destination is reached through an
+# H.Encaps wrapper that carries an SRH with
+# two segments; End.MAP must leave the SRH
+# structurally intact.
+# 3. SRH inline -- the destination is reached through an
+# H.Insert wrapper that inserts an SRH whose
+# first hop is the End.MAP SID; End.MAP must
+# NOT patch the L4 checksum, because the
+# receiver's SRv6 processing restores the
+# destination from segments[0] before the
+# ICMPv6 handler verifies it.
+# 4. RH not an SRH, Segments Left 0
+# -- a C helper sends an echo whose Routing Header
+# is type 0 rather than 4; RFC 8200 has an
+# unrecognized Routing Type with Segments Left 0
+# ignored, so End.MAP must forward it as if no
+# SRH were present and the receiver must accept
+# the echo.
+# 5. RH not an SRH, Segments Left 1
+# -- the same Routing Header with Segments Left 1;
+# End.MAP must drop it. The behavior's own
+# errors counter binds the assertion to the drop.
+# 6. SRH malformed -- the helper sends an SRH whose Last Entry
+# exceeds its length; End.MAP must drop it.
+# 7. SRH exhausted -- the helper sends a valid SRH with Segments
+# Left 0, so the IPv6 DA already is the final
+# destination; End.MAP must patch the L4
+# checksum as in the SRH-absent case and the
+# receiver must accept the echo.
+# 8. Fragmented -- an oversized echo without an SRH is fragmented
+# by rt-1; only the first fragment carries the
+# ICMPv6 header, and End.MAP must patch its
+# checksum so the reassembled echo verifies at
+# rt-3.
+# 9. Hop Limit -- an echo whose Hop Limit is 1 on arrival at
+# the End.MAP node must yield an ICMPv6 Time
+# Exceeded from that node, confirming Hop Limit
+# handling is delegated to the ip6_forward path.
+# 10. No Next Header -- the helper sends a bare IPv6 header whose Next
+# Header is 59; there is no L4 checksum to patch,
+# and End.MAP must forward it. The behavior's
+# packets counter binds the assertion.
+
+source lib.sh
+
+readonly PING_TIMEOUT_SEC=4
+readonly COUNTER_TIMEOUT_SEC=2
+readonly END_MAP_PREFIX="2001:db8:f::/64"
+readonly END_MAP_SID="2001:db8:f::1"
+readonly RT3_SID="2001:db8:3::3"
+HELPER_DIR=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)
+readonly HELPER_DIR
+readonly HELPER="${HELPER_DIR}/srv6_mobile_send"
+
+ret=0
+nsuccess=0
+nfail=0
+
+PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
+
+log_test()
+{
+ local rc=$1
+ local expected=$2
+ local msg="$3"
+
+ if [ "${rc}" -eq "${expected}" ]; then
+ nsuccess=$((nsuccess + 1))
+ printf "\n TEST: %-60s [ OK ]\n" "${msg}"
+ else
+ ret=1
+ nfail=$((nfail + 1))
+ printf "\n TEST: %-60s [FAIL]\n" "${msg}"
+ if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+ echo
+ echo "hit enter to continue, 'q' to quit"
+ read -r a
+ [ "$a" = "q" ] && exit 1
+ fi
+ fi
+}
+
+print_log_test_results()
+{
+ printf "\nTests passed: %3d\n" "${nsuccess}"
+ printf "Tests failed: %3d\n" "${nfail}"
+}
+
+cleanup()
+{
+ cleanup_all_ns
+}
+
+trap cleanup EXIT
+
+check_dependencies()
+{
+ if [ "$(id -u)" -ne 0 ]; then
+ echo "SKIP: need root privileges"
+ exit "${ksft_skip}"
+ fi
+
+ for cmd in ip ping nstat sysctl ethtool; do
+ if ! command -v "$cmd" >/dev/null; then
+ echo "SKIP: ${cmd} is required"
+ exit "${ksft_skip}"
+ fi
+ done
+
+ if [ ! -x "${HELPER}" ]; then
+ echo "SKIP: ${HELPER} not built"
+ exit "${ksft_skip}"
+ fi
+
+ if ! ip route help 2>&1 | grep -qF "seg6mobile"; then
+ echo "SKIP: iproute2 lacks seg6mobile support"
+ exit "${ksft_skip}"
+ fi
+
+ if ! ip route help 2>&1 | grep -qF "End.MAP"; then
+ echo "SKIP: iproute2 lacks End.MAP action"
+ exit "${ksft_skip}"
+ fi
+}
+
+setup()
+{
+ setup_ns rt1 rt2 rt3
+
+ # shellcheck disable=SC2154 # variables assigned by setup_ns
+ for ns in "$rt1" "$rt2" "$rt3"; do
+ ip -n "$ns" link set lo up
+ done
+
+ ip link add veth1 netns "$rt1" \
+ type veth peer name veth1-rt2 netns "$rt2"
+ ip link add veth2 netns "$rt2" \
+ type veth peer name veth2-rt3 netns "$rt3"
+
+ ip -n "$rt1" addr add 2001:db8:1::1/64 dev veth1 nodad
+ ip -n "$rt2" addr add 2001:db8:1::2/64 dev veth1-rt2 nodad
+ ip -n "$rt2" addr add 2001:db8:2::1/64 dev veth2 nodad
+ ip -n "$rt3" addr add 2001:db8:2::2/64 dev veth2-rt3 nodad
+ # rt-3 also owns the End.MAP replacement SID / SRH endpoint.
+ ip -n "$rt3" addr add "$RT3_SID/128" dev lo nodad
+
+ ip -n "$rt1" link set veth1 up
+ ip -n "$rt2" link set veth1-rt2 up
+ ip -n "$rt2" link set veth2 up
+ ip -n "$rt3" link set veth2-rt3 up
+
+ ip netns exec "$rt2" sysctl -wq net.ipv6.conf.all.forwarding=1
+
+ # rt-3 must accept SRv6 packets so ipv6_srh_rcv lets the
+ # extension header chain through to local delivery.
+ ip netns exec "$rt3" sysctl -wq net.ipv6.conf.all.seg6_enabled=1
+ ip netns exec "$rt3" \
+ sysctl -wq net.ipv6.conf.veth2-rt3.seg6_enabled=1
+ ip netns exec "$rt3" sysctl -wq net.ipv6.conf.lo.seg6_enabled=1
+
+ # Disable HW checksum offload so the kernel software checksum
+ # path runs unconditionally and any csum bug surfaces.
+ ip netns exec "$rt1" ethtool -K veth1 tx off rx off
+ ip netns exec "$rt2" ethtool -K veth1-rt2 tx off rx off
+ ip netns exec "$rt2" ethtool -K veth2 tx off rx off
+ ip netns exec "$rt3" ethtool -K veth2-rt3 tx off rx off
+
+ # rt-1: route the End.MAP locator into rt-2.
+ ip -n "$rt1" -6 route add "$END_MAP_PREFIX" via 2001:db8:1::2
+
+ # rt-1: a separate H.Encaps route for the SRH-present scenario,
+ # wrapping the inner ICMPv6 echo in an outer IPv6+SRH carrying
+ # [End.MAP_SID, RT3_SID].
+ ip -n "$rt1" -6 route add "$RT3_SID/128" via 2001:db8:1::2 \
+ encap seg6 mode encap \
+ segs "$END_MAP_SID","$RT3_SID" \
+ dev veth1
+
+ # rt-2: End.MAP -- swap DA from the End.MAP SID to RT3_SID
+ # (an address on rt-3) and forward via the IPv6 FIB. "count"
+ # enables the per-behavior counters the drop tests read.
+ ip -n "$rt2" -6 route add "$END_MAP_PREFIX" \
+ encap seg6mobile action End.MAP mapped_sid "$RT3_SID" count \
+ dev veth2
+
+ # rt-2: reach RT3_SID (on rt-3's loopback) through the
+ # directly connected neighbour 2001:db8:2::2.
+ ip -n "$rt2" -6 route add "$RT3_SID/128" via 2001:db8:2::2
+
+ # rt-3: return route for the ICMPv6 echo reply.
+ ip -n "$rt3" -6 route add 2001:db8:1::/64 via 2001:db8:2::1
+}
+
+read_nstat_counter()
+{
+ local ns=$1
+ local name=$2
+
+ # nstat -az reports a counter that has never incremented as 0,
+ # which is what we rely on for a clean before/after delta.
+ ip netns exec "$ns" nstat -az "$name" \
+ | awk -v n="$name" '$1 == n {print $2}'
+}
+
+read_route_counter()
+{
+ local name=$1
+
+ ip -n "$rt2" -j -s -6 route show "$END_MAP_PREFIX" \
+ | grep -oE "\"${name}\":[0-9]+" | grep -oE '[0-9]+'
+}
+
+read_route_errors()
+{
+ # The End.MAP route carries "count", so its errors counter
+ # increments once for every packet the behavior drops. Reading it
+ # binds the negative test to the drop itself rather than to any
+ # unrelated loss on the path to rt-3.
+ read_route_counter errors
+}
+
+test_srh_absent()
+{
+ local before after rc=0
+
+ before=$(read_nstat_counter "$rt3" Icmp6InCsumErrors)
+
+ if ! ip netns exec "$rt1" \
+ ping -6 -c 1 -W "$PING_TIMEOUT_SEC" "$END_MAP_SID" \
+ >/dev/null 2>&1; then
+ rc=1
+ fi
+
+ if [ "$rc" -eq 0 ]; then
+ after=$(read_nstat_counter "$rt3" Icmp6InCsumErrors)
+ [ "$before" != "$after" ] && rc=1
+ fi
+
+ log_test "$rc" 0 "End.MAP forwards an ICMPv6 echo without an SRH"
+}
+
+test_srh_present()
+{
+ local before after rc=0
+
+ before=$(read_nstat_counter "$rt3" Icmp6InCsumErrors)
+
+ if ! ip netns exec "$rt1" \
+ ping -6 -c 1 -W "$PING_TIMEOUT_SEC" "$RT3_SID" \
+ >/dev/null 2>&1; then
+ rc=1
+ fi
+
+ if [ "$rc" -eq 0 ]; then
+ after=$(read_nstat_counter "$rt3" Icmp6InCsumErrors)
+ [ "$before" != "$after" ] && rc=1
+ fi
+
+ log_test "$rc" 0 "End.MAP preserves an SRH carried by H.Encaps"
+}
+
+test_srh_inline()
+{
+ local before after rc=0
+
+ ip -n "$rt1" -6 route add 2001:db8:2::2/128 via 2001:db8:1::2 \
+ encap seg6 mode inline segs "$END_MAP_SID" \
+ dev veth1
+
+ before=$(read_nstat_counter "$rt3" Icmp6InCsumErrors)
+
+ if ! ip netns exec "$rt1" \
+ ping -6 -c 1 -W "$PING_TIMEOUT_SEC" 2001:db8:2::2 \
+ >/dev/null 2>&1; then
+ rc=1
+ fi
+
+ if [ "$rc" -eq 0 ]; then
+ after=$(read_nstat_counter "$rt3" Icmp6InCsumErrors)
+ [ "$before" != "$after" ] && rc=1
+ fi
+
+ log_test "$rc" 0 "End.MAP preserves L4 csum across mode inline SRH"
+}
+
+# The drop happens on rt-2's receive path, asynchronously to the
+# sender, so wait for the errors counter instead of sampling it.
+expect_end_map_drop()
+{
+ local before rc=0
+
+ before=$(read_route_errors)
+
+ ip netns exec "$rt1" "$HELPER" -m end-map "$@" \
+ -s 2001:db8:1::1 -d "$END_MAP_SID" >/dev/null 2>&1
+
+ slowwait "$COUNTER_TIMEOUT_SEC" until_counter_is ">= $((before + 1))" \
+ read_route_errors >/dev/null || rc=1
+ [ "$(read_route_errors)" -eq "$((before + 1))" ] || rc=1
+
+ echo "$rc"
+}
+
+# Sends a helper-crafted echo through End.MAP and waits for rt-3 to
+# accept it with a valid transport checksum.
+expect_end_map_echo()
+{
+ local before_echos before_csum rc=0
+
+ before_echos=$(read_nstat_counter "$rt3" Icmp6InEchos)
+ before_csum=$(read_nstat_counter "$rt3" Icmp6InCsumErrors)
+
+ ip netns exec "$rt1" "$HELPER" -m end-map "$@" \
+ -s 2001:db8:1::1 -d "$END_MAP_SID" >/dev/null 2>&1
+
+ slowwait "$COUNTER_TIMEOUT_SEC" \
+ until_counter_is ">= $((before_echos + 1))" \
+ read_nstat_counter "$rt3" Icmp6InEchos >/dev/null || rc=1
+ [ "$(read_nstat_counter "$rt3" Icmp6InCsumErrors)" -eq \
+ "$before_csum" ] || rc=1
+
+ echo "$rc"
+}
+
+test_rh_not_srh()
+{
+ local rc
+
+ rc=$(expect_end_map_echo --rh-type 0)
+ log_test "$rc" 0 "End.MAP ignores a non-SRH RH with Segments Left 0"
+}
+
+test_rh_not_srh_segleft()
+{
+ local rc
+
+ rc=$(expect_end_map_drop --rh-type 0 --segleft 1)
+ log_test "$rc" 0 "End.MAP drops a non-SRH RH with Segments Left 1"
+}
+
+test_srh_malformed()
+{
+ local rc
+
+ rc=$(expect_end_map_drop --bad-srh)
+ log_test "$rc" 0 "End.MAP drops a malformed SRH"
+}
+
+test_srh_exhausted()
+{
+ local rc
+
+ rc=$(expect_end_map_echo)
+ log_test "$rc" 0 "End.MAP patches the L4 csum of an exhausted SRH"
+}
+
+test_fragmented()
+{
+ local before after rc=0
+
+ before=$(read_nstat_counter "$rt3" Icmp6InCsumErrors)
+
+ if ! ip netns exec "$rt1" \
+ ping -6 -c 1 -s 2000 -M dont -W "$PING_TIMEOUT_SEC" \
+ "$END_MAP_SID" >/dev/null 2>&1; then
+ rc=1
+ fi
+
+ if [ "$rc" -eq 0 ]; then
+ after=$(read_nstat_counter "$rt3" Icmp6InCsumErrors)
+ [ "$before" != "$after" ] && rc=1
+ fi
+
+ log_test "$rc" 0 "End.MAP patches the L4 csum of a fragmented echo"
+}
+
+test_hoplimit_expiry()
+{
+ local before after rc=0
+
+ before=$(read_nstat_counter "$rt2" Icmp6OutTimeExcds)
+
+ ip netns exec "$rt1" \
+ ping -6 -c 1 -t 1 -W "$PING_TIMEOUT_SEC" "$END_MAP_SID" \
+ >/dev/null 2>&1
+
+ after=$(read_nstat_counter "$rt2" Icmp6OutTimeExcds)
+ [ "$((after - before))" -eq 1 ] || rc=1
+
+ log_test "$rc" 0 "End.MAP delegates Hop Limit expiry to ip6_forward"
+}
+
+test_no_next_header()
+{
+ local before_pkts before_errs rc=0
+
+ before_pkts=$(read_route_counter packets)
+ before_errs=$(read_route_errors)
+
+ ip netns exec "$rt1" "$HELPER" -m end-map --no-next-header \
+ -s 2001:db8:1::1 -d "$END_MAP_SID" >/dev/null 2>&1
+
+ slowwait "$COUNTER_TIMEOUT_SEC" \
+ until_counter_is ">= $((before_pkts + 1))" \
+ read_route_counter packets >/dev/null || rc=1
+ [ "$(read_route_errors)" -eq "$before_errs" ] || rc=1
+
+ log_test "$rc" 0 "End.MAP forwards a packet with No Next Header"
+}
+
+main()
+{
+ check_dependencies
+ setup
+
+ test_srh_absent
+ test_srh_present
+ test_srh_inline
+ test_rh_not_srh
+ test_rh_not_srh_segleft
+ test_srh_malformed
+ test_srh_exhausted
+ test_fragmented
+ test_hoplimit_expiry
+ test_no_next_header
+
+ print_log_test_results
+ exit "${ret}"
+}
+
+main "$@"
diff --git a/tools/testing/selftests/net/srv6_mobile_send.c b/tools/testing/selftests/net/srv6_mobile_send.c
new file mode 100644
index 000000000000..3ee95e09f4ed
--- /dev/null
+++ b/tools/testing/selftests/net/srv6_mobile_send.c
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Author: Yuya Kusakabe (yuya.kusakabe@gmail.com)
+ *
+ * Helper for SRv6 Mobile (RFC 9433) selftests.
+ *
+ * Usage:
+ * srv6_mobile_send -m end-map -s <src> -d <dst> [--rh-type N]
+ * [--segleft N] [--bad-srh] [--no-next-header]
+ */
+
+#include <arpa/inet.h>
+#include <assert.h>
+#include <errno.h>
+#include <getopt.h>
+#include <netinet/in.h>
+#include <netinet/ip6.h>
+#include <netinet/icmp6.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+/* RFC 8200 Routing header common fields are 4 bytes; an additional
+ * 4 bytes of type-specific data follow (the Reserved field for the
+ * deprecated type 0, or first_segment/flags/tag for SRH type 4). The
+ * segment list then runs in 16-byte units, giving a total of 24 bytes
+ * for one segment -- which is what ip6r_len = 2 advertises.
+ */
+struct srh_one_seg {
+ struct ip6_rthdr rthdr;
+ uint32_t type_data;
+ struct in6_addr segment;
+};
+
+/* Built as a struct so the headers are written through typed, aligned
+ * members rather than casts of a byte array; static_assert keeps it
+ * exactly the on-wire layout.
+ */
+struct end_map_frame {
+ struct ip6_hdr ip6;
+ struct srh_one_seg srh;
+ struct icmp6_hdr icmp6;
+};
+
+static_assert(sizeof(struct end_map_frame) ==
+ sizeof(struct ip6_hdr) + sizeof(struct srh_one_seg) +
+ sizeof(struct icmp6_hdr),
+ "end_map_frame must not contain padding");
+
+enum mode {
+ MODE_NONE,
+ MODE_END_MAP,
+};
+
+struct cfg {
+ enum mode mode;
+ struct in6_addr src6;
+ struct in6_addr dst6;
+ uint8_t rh_type;
+ uint8_t segleft;
+ bool bad_srh;
+ bool no_next_header;
+};
+
+static void usage(const char *bin)
+{
+ fprintf(stderr,
+ "Usage: %s -m <mode> -s <src> -d <dst> [opts]\n"
+ "\n"
+ "Modes:\n"
+ " end-map Send IPv6 + SRH + ICMPv6 echo for End.MAP testing\n"
+ "\n"
+ "Mode end-map options:\n"
+ " --rh-type <n> Routing Header type (default 4, the SRH)\n"
+ " --segleft <n> Routing Header Segments Left (default 0)\n"
+ " --bad-srh emit an SRH whose Last Entry exceeds its length (drop test)\n"
+ " --no-next-header send a bare IPv6 header with Next Header 59\n"
+ "\n"
+ "Exit: 0 sent, 1 failure, 3 invalid arguments.\n",
+ bin);
+}
+
+static int parse_u32(const char *s, uint32_t *out)
+{
+ unsigned long v;
+ char *end;
+
+ errno = 0;
+ v = strtoul(s, &end, 0);
+ if (errno || !*s || *end || v > 0xffffffffUL)
+ return -1;
+ *out = (uint32_t)v;
+ return 0;
+}
+
+static int parse_u8(const char *s, uint8_t *out)
+{
+ uint32_t v;
+
+ if (parse_u32(s, &v) || v > 0xff)
+ return -1;
+ *out = (uint8_t)v;
+ return 0;
+}
+
+static enum mode parse_mode(const char *s)
+{
+ if (!strcmp(s, "end-map"))
+ return MODE_END_MAP;
+ return MODE_NONE;
+}
+
+static int parse_args(int argc, char **argv, struct cfg *cfg)
+{
+ enum { OPT_RH_TYPE = 256, OPT_SEGLEFT, OPT_BAD_SRH, OPT_NO_NEXT_HEADER };
+ static const struct option longopts[] = {
+ { "rh-type", required_argument, NULL, OPT_RH_TYPE },
+ { "segleft", required_argument, NULL, OPT_SEGLEFT },
+ { "bad-srh", no_argument, NULL, OPT_BAD_SRH },
+ { "no-next-header", no_argument, NULL, OPT_NO_NEXT_HEADER },
+ { NULL, 0, NULL, 0 },
+ };
+ int c;
+
+ cfg->rh_type = 4; /* RFC 8754: the SRH is Routing Header type 4 */
+ while ((c = getopt_long(argc, argv, "m:s:d:", longopts, NULL))
+ != -1) {
+ switch (c) {
+ case 'm':
+ cfg->mode = parse_mode(optarg);
+ break;
+ case 's':
+ if (inet_pton(AF_INET6, optarg, &cfg->src6) != 1)
+ return -1;
+ break;
+ case 'd':
+ if (inet_pton(AF_INET6, optarg, &cfg->dst6) != 1)
+ return -1;
+ break;
+ case OPT_RH_TYPE:
+ if (parse_u8(optarg, &cfg->rh_type))
+ return -1;
+ break;
+ case OPT_SEGLEFT:
+ if (parse_u8(optarg, &cfg->segleft))
+ return -1;
+ break;
+ case OPT_BAD_SRH:
+ cfg->bad_srh = true;
+ break;
+ case OPT_NO_NEXT_HEADER:
+ cfg->no_next_header = true;
+ break;
+ default:
+ return -1;
+ }
+ }
+ if (cfg->mode == MODE_NONE)
+ return -1;
+ return 0;
+}
+
+static uint16_t csum_fold(uint32_t sum)
+{
+ while (sum >> 16)
+ sum = (sum & 0xffff) + (sum >> 16);
+ return ~sum;
+}
+
+static uint32_t csum_partial(const void *buf, size_t len, uint32_t sum)
+{
+ const uint8_t *p = buf;
+ uint16_t word;
+
+ while (len > 1) {
+ memcpy(&word, p, sizeof(word));
+ sum += word;
+ p += sizeof(word);
+ len -= sizeof(word);
+ }
+ if (len)
+ sum += *p;
+ return sum;
+}
+
+static uint16_t pseudo_csum(const struct in6_addr *src,
+ const struct in6_addr *dst,
+ uint32_t plen, uint8_t nexthdr,
+ const void *payload, size_t len)
+{
+ uint32_t nh = htonl(nexthdr);
+ uint32_t pl = htonl(plen);
+ uint32_t sum;
+
+ sum = csum_partial(src, sizeof(*src), 0);
+ sum = csum_partial(dst, sizeof(*dst), sum);
+ sum = csum_partial(&pl, sizeof(pl), sum);
+ sum = csum_partial(&nh, sizeof(nh), sum);
+ sum = csum_partial(payload, len, sum);
+ return csum_fold(sum);
+}
+
+static int send_end_map(const struct cfg *cfg)
+{
+ struct sockaddr_in6 dst_addr = { .sin6_family = AF_INET6 };
+ struct end_map_frame frame = {};
+ size_t len = sizeof(frame);
+ ssize_t res;
+ int fd;
+
+ frame.ip6.ip6_flow = htonl(6u << 28);
+ frame.ip6.ip6_plen = htons(sizeof(frame.srh) + sizeof(frame.icmp6));
+ frame.ip6.ip6_nxt = IPPROTO_ROUTING;
+ frame.ip6.ip6_hops = 64;
+ frame.ip6.ip6_src = cfg->src6;
+ frame.ip6.ip6_dst = cfg->dst6;
+
+ frame.srh.rthdr.ip6r_nxt = IPPROTO_ICMPV6;
+ frame.srh.rthdr.ip6r_len = 2; /* (1 + ip6r_len) * 8 = 24 */
+ frame.srh.rthdr.ip6r_type = cfg->rh_type;
+ frame.srh.rthdr.ip6r_segleft = cfg->segleft;
+ /* SRH Last Entry is the high byte of the type-specific word. A
+ * single segment makes it 0; --bad-srh claims a second segment the
+ * header has no room for, which seg6_validate_srh() rejects.
+ */
+ frame.srh.type_data = htonl((uint32_t)(cfg->bad_srh ? 1 : 0) << 24);
+ frame.srh.segment = frame.ip6.ip6_dst;
+
+ frame.icmp6.icmp6_type = ICMP6_ECHO_REQUEST;
+ frame.icmp6.icmp6_code = 0;
+ frame.icmp6.icmp6_dataun.icmp6_un_data16[0] = htons(0x1234);
+ frame.icmp6.icmp6_dataun.icmp6_un_data16[1] = htons(1);
+ frame.icmp6.icmp6_cksum = pseudo_csum(&frame.ip6.ip6_src,
+ &frame.ip6.ip6_dst,
+ sizeof(frame.icmp6),
+ IPPROTO_ICMPV6, &frame.icmp6,
+ sizeof(frame.icmp6));
+
+ if (cfg->no_next_header) {
+ frame.ip6.ip6_nxt = IPPROTO_NONE;
+ frame.ip6.ip6_plen = 0;
+ len = sizeof(frame.ip6);
+ }
+
+ fd = socket(AF_INET6, SOCK_RAW, IPPROTO_RAW);
+ if (fd < 0) {
+ perror("socket");
+ return 1;
+ }
+ dst_addr.sin6_addr = frame.ip6.ip6_dst;
+
+ res = sendto(fd, &frame, len, 0,
+ (struct sockaddr *)&dst_addr, sizeof(dst_addr));
+ close(fd);
+ if (res != (ssize_t)len) {
+ perror("sendto");
+ return 1;
+ }
+ return 0;
+}
+
+int main(int argc, char **argv)
+{
+ struct cfg cfg = {};
+
+ if (parse_args(argc, argv, &cfg)) {
+ usage(argv[0]);
+ return 3;
+ }
+
+ switch (cfg.mode) {
+ case MODE_END_MAP:
+ return send_end_map(&cfg);
+ default:
+ usage(argv[0]);
+ return 3;
+ }
+}
--
2.50.1
^ permalink raw reply [flat|nested] 3+ messages in thread