Merge branch 'ipv6-ioam'

Justin Iurman says:

====================
Support for the IOAM Pre-allocated Trace with IPv6

v5:
 - Refine types, min/max and default values for new sysctls
 - Introduce a "_wide" sysctl for each "ioam6_id" sysctl
 - Add more validation on headers before processing data
 - RCU for sc <> ns pointers + appropriate accessors
 - Generic Netlink policies are now per op, not per family anymore
 - Address other comments/remarks from Jakub (thanks again)
 - Revert "__packed" to "__attribute__((packed))" for uapi headers
 - Add tests to cover the functionality added, as requested by David Ahern

v4:
 - Address warnings from checkpatch (ignore errors related to unnamed bitfields
   in the first patch)
 - Use of hweight32 (thanks Jakub)
 - Remove inline keyword from static functions in C files and let the compiler
   decide what to do (thanks Jakub)

v3:
 - Fix warning "unused label 'out_unregister_genl'" by adding conditional macro
 - Fix lwtunnel output redirect bug: dst cache useless in this case, use
   orig_output instead

v2:
 - Fix warning with static for __ioam6_fill_trace_data
 - Fix sparse warning with __force when casting __be64 to __be32
 - Fix unchecked dereference when removing IOAM namespaces or schemas
 - exthdrs.c: Don't drop by default (now: ignore) to match the act bits "00"
 - Add control plane support for the inline insertion (lwtunnel)
 - Provide uapi structures
 - Use __net_timestamp if skb->tstamp is empty
 - Add note about the temporary IANA allocation
 - Remove support for "removable" TLVs
 - Remove support for virtual/anonymous tunnel decapsulation

In-situ Operations, Administration, and Maintenance (IOAM) records
operational and telemetry information in a packet while it traverses
a path between two points in an IOAM domain. It is defined in
draft-ietf-ippm-ioam-data [1]. IOAM data fields can be encapsulated
into a variety of protocols. The IPv6 encapsulation is defined in
draft-ietf-ippm-ioam-ipv6-options [2], via extension headers. IOAM
can be used to complement OAM mechanisms based on e.g. ICMP or other
types of probe packets.

This patchset implements support for the Pre-allocated Trace, carried
by a Hop-by-Hop. Therefore, a new IPv6 Hop-by-Hop TLV option is
introduced, see IANA [3]. The three other IOAM options are not included
in this patchset (Incremental Trace, Proof-of-Transit and Edge-to-Edge).
The main idea behind the IOAM Pre-allocated Trace is that a node
pre-allocates some room in packets for IOAM data. Then, each IOAM node
on the path will insert its data. There exist several interesting use-
cases, e.g. Fast failure detection/isolation or Smart service selection.
Another killer use-case is what we have called Cross-Layer Telemetry,
see the demo video on its repository [4], that aims to make the entire
stack (L2/L3 -> L7) visible for distributed tracing tools (e.g. Jaeger),
instead of the current L5 -> L7 limited view. So, basically, this is a
nice feature for the Linux Kernel.

This patchset also provides support for the control plane part, but only for the
inline insertion (host-to-host use case), through lightweight tunnels. Indeed,
for in-transit traffic, the solution is to have an IPv6-in-IPv6 encapsulation,
which brings some difficulties and still requires a little bit of work and
discussion (ie anonymous tunnel decapsulation and multi egress resolution).

- Patch 1: IPv6 IOAM headers definition
- Patch 2: Data plane support for Pre-allocated Trace
- Patch 3: IOAM Generic Netlink API
- Patch 4: Support for IOAM injection with lwtunnels
- Patch 5: Documentation for new IOAM sysctls
- Patch 6: Test for the IOAM insertion with IPv6

  [1] https://tools.ietf.org/html/draft-ietf-ippm-ioam-data
  [2] https://tools.ietf.org/html/draft-ietf-ippm-ioam-ipv6-options
  [3] https://www.iana.org/assignments/ipv6-parameters/ipv6-parameters.xhtml#ipv6-parameters-2
  [4] https://github.com/iurmanj/cross-layer-telemetry
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/ioam6-sysctl.rst

+.. SPDX-License-Identifier: GPL-2.0
+
+=====================
+IOAM6 Sysfs variables
+=====================
+
+
+/proc/sys/net/conf/<iface>/ioam6_* variables:
+=============================================
+
+ioam6_enabled - BOOL
+        Accept (= enabled) or ignore (= disabled) IPv6 IOAM options on ingress
+        for this interface.
+
+        * 0 - disabled (default)
+        * 1 - enabled
+
+ioam6_id - SHORT INTEGER
+        Define the IOAM id of this interface.
+
+        Default is ~0.
+
+ioam6_id_wide - INTEGER
+        Define the wide IOAM id of this interface.
+
+        Default is ~0.

Documentation/networking/ip-sysctl.rst

@@ -1926,6 +1926,23 @@ fib_notify_on_flag_change - INTEGER
         - 1 - Emit notifications.
         - 2 - Emit notifications only for RTM_F_OFFLOAD_FAILED flag change.
 
+ioam6_id - INTEGER
+        Define the IOAM id of this node. Uses only 24 bits out of 32 in total.
+
+        Min: 0
+        Max: 0xFFFFFF
+
+        Default: 0xFFFFFF
+
+ioam6_id_wide - LONG INTEGER
+        Define the wide IOAM id of this node. Uses only 56 bits out of 64 in
+        total. Can be different from ioam6_id.
+
+        Min: 0
+        Max: 0xFFFFFFFFFFFFFF
+
+        Default: 0xFFFFFFFFFFFFFF
+
 IPv6 Fragmentation:
 
 ip6frag_high_thresh - INTEGER

include/linux/ioam6.h

+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ *  IPv6 IOAM
+ *
+ *  Author:
+ *  Justin Iurman <justin.iurman@uliege.be>
+ */
+#ifndef _LINUX_IOAM6_H
+#define _LINUX_IOAM6_H
+
+#include <uapi/linux/ioam6.h>
+
+#endif /* _LINUX_IOAM6_H */

include/linux/ioam6_genl.h

+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ *  IPv6 IOAM Generic Netlink API
+ *
+ *  Author:
+ *  Justin Iurman <justin.iurman@uliege.be>
+ */
+#ifndef _LINUX_IOAM6_GENL_H
+#define _LINUX_IOAM6_GENL_H
+
+#include <uapi/linux/ioam6_genl.h>
+
+#endif /* _LINUX_IOAM6_GENL_H */

include/linux/ioam6_iptunnel.h

+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ *  IPv6 IOAM Lightweight Tunnel API
+ *
+ *  Author:
+ *  Justin Iurman <justin.iurman@uliege.be>
+ */
+#ifndef _LINUX_IOAM6_IPTUNNEL_H
+#define _LINUX_IOAM6_IPTUNNEL_H
+
+#include <uapi/linux/ioam6_iptunnel.h>
+
+#endif /* _LINUX_IOAM6_IPTUNNEL_H */

include/linux/ipv6.h

@@ -76,6 +76,9 @@ struct ipv6_devconf {
 	__s32		disable_policy;
 	__s32           ndisc_tclass;
 	__s32		rpl_seg_enabled;
+	__u32		ioam6_id;
+	__u32		ioam6_id_wide;
+	__u8		ioam6_enabled;
 
 	struct ctl_table_header *sysctl_header;
 };

include/net/ioam6.h

+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ *  IPv6 IOAM implementation
+ *
+ *  Author:
+ *  Justin Iurman <justin.iurman@uliege.be>
+ */
+
+#ifndef _NET_IOAM6_H
+#define _NET_IOAM6_H
+
+#include <linux/net.h>
+#include <linux/ipv6.h>
+#include <linux/ioam6.h>
+#include <linux/rhashtable-types.h>
+
+struct ioam6_namespace {
+	struct rhash_head head;
+	struct rcu_head rcu;
+
+	struct ioam6_schema __rcu *schema;
+
+	__be16 id;
+	__be32 data;
+	__be64 data_wide;
+};
+
+struct ioam6_schema {
+	struct rhash_head head;
+	struct rcu_head rcu;
+
+	struct ioam6_namespace __rcu *ns;
+
+	u32 id;
+	int len;
+	__be32 hdr;
+
+	u8 data[0];
+};
+
+struct ioam6_pernet_data {
+	struct mutex lock;
+	struct rhashtable namespaces;
+	struct rhashtable schemas;
+};
+
+static inline struct ioam6_pernet_data *ioam6_pernet(struct net *net)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	return net->ipv6.ioam6_data;
+#else
+	return NULL;
+#endif
+}
+
+struct ioam6_namespace *ioam6_namespace(struct net *net, __be16 id);
+void ioam6_fill_trace_data(struct sk_buff *skb,
+			   struct ioam6_namespace *ns,
+			   struct ioam6_trace_hdr *trace);
+
+int ioam6_init(void);
+void ioam6_exit(void);
+
+int ioam6_iptunnel_init(void);
+void ioam6_iptunnel_exit(void);
+
+#endif /* _NET_IOAM6_H */

include/net/netns/ipv6.h

@@ -51,6 +51,8 @@ struct netns_sysctl_ipv6 {
 	int max_dst_opts_len;
 	int max_hbh_opts_len;
 	int seg6_flowlabel;
+	u32 ioam6_id;
+	u64 ioam6_id_wide;
 	bool skip_notify_on_dev_down;
 	u8 fib_notify_on_flag_change;
 };
@@ -110,6 +112,7 @@ struct netns_ipv6 {
 		spinlock_t	lock;
 		u32		seq;
 	} ip6addrlbl_table;
+	struct ioam6_pernet_data *ioam6_data;
 };
 
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)

include/uapi/linux/in6.h

@@ -145,6 +145,7 @@ struct in6_flowlabel_req {
 #define IPV6_TLV_PADN		1
 #define IPV6_TLV_ROUTERALERT	5
 #define IPV6_TLV_CALIPSO	7	/* RFC 5570 */
+#define IPV6_TLV_IOAM		49	/* TEMPORARY IANA allocation for IOAM */
 #define IPV6_TLV_JUMBO		194
 #define IPV6_TLV_HAO		201	/* home address option */
 

include/uapi/linux/ioam6.h

+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ *  IPv6 IOAM implementation
+ *
+ *  Author:
+ *  Justin Iurman <justin.iurman@uliege.be>
+ */
+
+#ifndef _UAPI_LINUX_IOAM6_H
+#define _UAPI_LINUX_IOAM6_H
+
+#include <asm/byteorder.h>
+#include <linux/types.h>
+
+#define IOAM6_U16_UNAVAILABLE U16_MAX
+#define IOAM6_U32_UNAVAILABLE U32_MAX
+#define IOAM6_U64_UNAVAILABLE U64_MAX
+
+#define IOAM6_DEFAULT_ID (IOAM6_U32_UNAVAILABLE >> 8)
+#define IOAM6_DEFAULT_ID_WIDE (IOAM6_U64_UNAVAILABLE >> 8)
+#define IOAM6_DEFAULT_IF_ID IOAM6_U16_UNAVAILABLE
+#define IOAM6_DEFAULT_IF_ID_WIDE IOAM6_U32_UNAVAILABLE
+
+/*
+ * IPv6 IOAM Option Header
+ */
+struct ioam6_hdr {
+	__u8 opt_type;
+	__u8 opt_len;
+	__u8 :8;				/* reserved */
+#define IOAM6_TYPE_PREALLOC 0
+	__u8 type;
+} __attribute__((packed));
+
+/*
+ * IOAM Trace Header
+ */
+struct ioam6_trace_hdr {
+	__be16	namespace_id;
+
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+
+	__u8	:1,				/* unused */
+		:1,				/* unused */
+		overflow:1,
+		nodelen:5;
+
+	__u8	remlen:7,
+		:1;				/* unused */
+
+	union {
+		__be32 type_be32;
+
+		struct {
+			__u32	bit7:1,
+				bit6:1,
+				bit5:1,
+				bit4:1,
+				bit3:1,
+				bit2:1,
+				bit1:1,
+				bit0:1,
+				bit15:1,	/* unused */
+				bit14:1,	/* unused */
+				bit13:1,	/* unused */
+				bit12:1,	/* unused */
+				bit11:1,
+				bit10:1,
+				bit9:1,
+				bit8:1,
+				bit23:1,	/* reserved */
+				bit22:1,
+				bit21:1,	/* unused */
+				bit20:1,	/* unused */
+				bit19:1,	/* unused */
+				bit18:1,	/* unused */
+				bit17:1,	/* unused */
+				bit16:1,	/* unused */
+				:8;		/* reserved */
+		} type;
+	};
+
+#elif defined(__BIG_ENDIAN_BITFIELD)
+
+	__u8	nodelen:5,
+		overflow:1,
+		:1,				/* unused */
+		:1;				/* unused */
+
+	__u8	:1,				/* unused */
+		remlen:7;
+
+	union {
+		__be32 type_be32;
+
+		struct {
+			__u32	bit0:1,
+				bit1:1,
+				bit2:1,
+				bit3:1,
+				bit4:1,
+				bit5:1,
+				bit6:1,
+				bit7:1,
+				bit8:1,
+				bit9:1,
+				bit10:1,
+				bit11:1,
+				bit12:1,	/* unused */
+				bit13:1,	/* unused */
+				bit14:1,	/* unused */
+				bit15:1,	/* unused */
+				bit16:1,	/* unused */
+				bit17:1,	/* unused */
+				bit18:1,	/* unused */
+				bit19:1,	/* unused */
+				bit20:1,	/* unused */
+				bit21:1,	/* unused */
+				bit22:1,
+				bit23:1,	/* reserved */
+				:8;		/* reserved */
+		} type;
+	};
+
+#else
+#error "Please fix <asm/byteorder.h>"
+#endif
+
+#define IOAM6_TRACE_DATA_SIZE_MAX 244
+	__u8	data[0];
+} __attribute__((packed));
+
+#endif /* _UAPI_LINUX_IOAM6_H */

include/uapi/linux/ioam6_genl.h

+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ *  IPv6 IOAM Generic Netlink API
+ *
+ *  Author:
+ *  Justin Iurman <justin.iurman@uliege.be>
+ */
+
+#ifndef _UAPI_LINUX_IOAM6_GENL_H
+#define _UAPI_LINUX_IOAM6_GENL_H
+
+#define IOAM6_GENL_NAME "IOAM6"
+#define IOAM6_GENL_VERSION 0x1
+
+enum {
+	IOAM6_ATTR_UNSPEC,
+
+	IOAM6_ATTR_NS_ID,	/* u16 */
+	IOAM6_ATTR_NS_DATA,	/* u32 */
+	IOAM6_ATTR_NS_DATA_WIDE,/* u64 */
+
+#define IOAM6_MAX_SCHEMA_DATA_LEN (255 * 4)
+	IOAM6_ATTR_SC_ID,	/* u32 */
+	IOAM6_ATTR_SC_DATA,	/* Binary */
+	IOAM6_ATTR_SC_NONE,	/* Flag */
+
+	IOAM6_ATTR_PAD,
+
+	__IOAM6_ATTR_MAX,
+};
+
+#define IOAM6_ATTR_MAX (__IOAM6_ATTR_MAX - 1)
+
+enum {
+	IOAM6_CMD_UNSPEC,
+
+	IOAM6_CMD_ADD_NAMESPACE,
+	IOAM6_CMD_DEL_NAMESPACE,
+	IOAM6_CMD_DUMP_NAMESPACES,
+
+	IOAM6_CMD_ADD_SCHEMA,
+	IOAM6_CMD_DEL_SCHEMA,
+	IOAM6_CMD_DUMP_SCHEMAS,
+
+	IOAM6_CMD_NS_SET_SCHEMA,
+
+	__IOAM6_CMD_MAX,
+};
+
+#define IOAM6_CMD_MAX (__IOAM6_CMD_MAX - 1)
+
+#endif /* _UAPI_LINUX_IOAM6_GENL_H */

include/uapi/linux/ioam6_iptunnel.h

+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ *  IPv6 IOAM Lightweight Tunnel API
+ *
+ *  Author:
+ *  Justin Iurman <justin.iurman@uliege.be>
+ */
+
+#ifndef _UAPI_LINUX_IOAM6_IPTUNNEL_H
+#define _UAPI_LINUX_IOAM6_IPTUNNEL_H
+
+enum {
+	IOAM6_IPTUNNEL_UNSPEC,
+	IOAM6_IPTUNNEL_TRACE,		/* struct ioam6_trace_hdr */
+	__IOAM6_IPTUNNEL_MAX,
+};
+
+#define IOAM6_IPTUNNEL_MAX (__IOAM6_IPTUNNEL_MAX - 1)
+
+#endif /* _UAPI_LINUX_IOAM6_IPTUNNEL_H */

include/uapi/linux/ipv6.h

@@ -190,6 +190,9 @@ enum {
 	DEVCONF_NDISC_TCLASS,
 	DEVCONF_RPL_SEG_ENABLED,
 	DEVCONF_RA_DEFRTR_METRIC,
+	DEVCONF_IOAM6_ENABLED,
+	DEVCONF_IOAM6_ID,
+	DEVCONF_IOAM6_ID_WIDE,
 	DEVCONF_MAX
 };
 

include/uapi/linux/lwtunnel.h

@@ -14,6 +14,7 @@ enum lwtunnel_encap_types {
 	LWTUNNEL_ENCAP_BPF,
 	LWTUNNEL_ENCAP_SEG6_LOCAL,
 	LWTUNNEL_ENCAP_RPL,
+	LWTUNNEL_ENCAP_IOAM6,
 	__LWTUNNEL_ENCAP_MAX,
 };
 

net/core/lwtunnel.c

@@ -43,6 +43,8 @@ static const char *lwtunnel_encap_str(enum lwtunnel_encap_types encap_type)
 		return "SEG6LOCAL";
 	case LWTUNNEL_ENCAP_RPL:
 		return "RPL";
+	case LWTUNNEL_ENCAP_IOAM6:
+		return "IOAM6";
 	case LWTUNNEL_ENCAP_IP6:
 	case LWTUNNEL_ENCAP_IP:
 	case LWTUNNEL_ENCAP_NONE:

net/ipv6/Kconfig

@@ -328,4 +328,15 @@ config IPV6_RPL_LWTUNNEL
 
 	  If unsure, say N.
 
+config IPV6_IOAM6_LWTUNNEL
+	bool "IPv6: IOAM Pre-allocated Trace insertion support"
+	depends on IPV6
+	select LWTUNNEL
+	help
+	  Support for the inline insertion of IOAM Pre-allocated
+	  Trace Header (only on locally generated packets), using
+	  the lightweight tunnels mechanism.
+
+	  If unsure, say N.
+
 endif # IPV6

net/ipv6/Makefile

@@ -10,7 +10,7 @@ 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 fib6_notifier.o rpl.o
+		udp_offload.o seg6.o fib6_notifier.o rpl.o ioam6.o
 
 ipv6-offload :=	ip6_offload.o tcpv6_offload.o exthdrs_offload.o
 
@@ -27,6 +27,7 @@ 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_RPL_LWTUNNEL) += rpl_iptunnel.o
+ipv6-$(CONFIG_IPV6_IOAM6_LWTUNNEL) += ioam6_iptunnel.o
 
 ipv6-objs += $(ipv6-y)
 

net/ipv6/addrconf.c

@@ -89,12 +89,15 @@
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/export.h>
+#include <linux/ioam6.h>
 
 #define	INFINITY_LIFE_TIME	0xFFFFFFFF
 
 #define IPV6_MAX_STRLEN \
 	sizeof("ffff:ffff:ffff:ffff:ffff:ffff:255.255.255.255")
 
+static u32 ioam6_if_id_max = U16_MAX;
+
 static inline u32 cstamp_delta(unsigned long cstamp)
 {
 	return (cstamp - INITIAL_JIFFIES) * 100UL / HZ;
@@ -237,6 +240,9 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.addr_gen_mode		= IN6_ADDR_GEN_MODE_EUI64,
 	.disable_policy		= 0,
 	.rpl_seg_enabled	= 0,
+	.ioam6_enabled		= 0,
+	.ioam6_id               = IOAM6_DEFAULT_IF_ID,
+	.ioam6_id_wide		= IOAM6_DEFAULT_IF_ID_WIDE,
 };
 
 static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
@@ -293,6 +299,9 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.addr_gen_mode		= IN6_ADDR_GEN_MODE_EUI64,
 	.disable_policy		= 0,
 	.rpl_seg_enabled	= 0,
+	.ioam6_enabled		= 0,
+	.ioam6_id               = IOAM6_DEFAULT_IF_ID,
+	.ioam6_id_wide		= IOAM6_DEFAULT_IF_ID_WIDE,
 };
 
 /* Check if link is ready: is it up and is a valid qdisc available */
@@ -5524,6 +5533,9 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 	array[DEVCONF_DISABLE_POLICY] = cnf->disable_policy;
 	array[DEVCONF_NDISC_TCLASS] = cnf->ndisc_tclass;
 	array[DEVCONF_RPL_SEG_ENABLED] = cnf->rpl_seg_enabled;
+	array[DEVCONF_IOAM6_ENABLED] = cnf->ioam6_enabled;
+	array[DEVCONF_IOAM6_ID] = cnf->ioam6_id;
+	array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide;
 }
 
 static inline size_t inet6_ifla6_size(void)
@@ -6930,6 +6942,31 @@ static const struct ctl_table addrconf_sysctl[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "ioam6_enabled",
+		.data		= &ipv6_devconf.ioam6_enabled,
+		.maxlen		= sizeof(u8),
+		.mode		= 0644,
+		.proc_handler	= proc_dou8vec_minmax,
+		.extra1		= (void *)SYSCTL_ZERO,
+		.extra2		= (void *)SYSCTL_ONE,
+	},
+	{
+		.procname	= "ioam6_id",
+		.data		= &ipv6_devconf.ioam6_id,
+		.maxlen		= sizeof(u32),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec_minmax,
+		.extra1		= (void *)SYSCTL_ZERO,
+		.extra2		= (void *)&ioam6_if_id_max,
+	},
+	{
+		.procname	= "ioam6_id_wide",
+		.data		= &ipv6_devconf.ioam6_id_wide,
+		.maxlen		= sizeof(u32),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec,
+	},
 	{
 		/* sentinel */
 	}

net/ipv6/af_inet6.c

@@ -62,6 +62,7 @@
 #include <net/rpl.h>
 #include <net/compat.h>
 #include <net/xfrm.h>
+#include <net/ioam6.h>
 
 #include <linux/uaccess.h>
 #include <linux/mroute6.h>
@@ -961,6 +962,9 @@ static int __net_init inet6_net_init(struct net *net)
 	net->ipv6.sysctl.fib_notify_on_flag_change = 0;
 	atomic_set(&net->ipv6.fib6_sernum, 1);
 
+	net->ipv6.sysctl.ioam6_id = IOAM6_DEFAULT_ID;
+	net->ipv6.sysctl.ioam6_id_wide = IOAM6_DEFAULT_ID_WIDE;
+
 	err = ipv6_init_mibs(net);
 	if (err)
 		return err;
@@ -1191,6 +1195,10 @@ static int __init inet6_init(void)
 	if (err)
 		goto rpl_fail;
 
+	err = ioam6_init();
+	if (err)
+		goto ioam6_fail;
+
 	err = igmp6_late_init();
 	if (err)
 		goto igmp6_late_err;
@@ -1213,6 +1221,8 @@ static int __init inet6_init(void)
 	igmp6_late_cleanup();
 #endif
 igmp6_late_err:
+	ioam6_exit();
+ioam6_fail:
 	rpl_exit();
 rpl_fail:
 	seg6_exit();

net/ipv6/exthdrs.c

@@ -49,6 +49,9 @@
 #include <net/seg6_hmac.h>
 #endif
 #include <net/rpl.h>
+#include <linux/ioam6.h>
+#include <net/ioam6.h>
+#include <net/dst_metadata.h>
 
 #include <linux/uaccess.h>
 
@@ -928,6 +931,60 @@ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff)
 	return false;
 }
 
+/* IOAM */
+
+static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff)
+{
+	struct ioam6_trace_hdr *trace;
+	struct ioam6_namespace *ns;
+	struct ioam6_hdr *hdr;
+
+	/* Bad alignment (must be 4n-aligned) */
+	if (optoff & 3)
+		goto drop;
+
+	/* Ignore if IOAM is not enabled on ingress */
+	if (!__in6_dev_get(skb->dev)->cnf.ioam6_enabled)
+		goto ignore;
+
+	/* Truncated Option header */
+	hdr = (struct ioam6_hdr *)(skb_network_header(skb) + optoff);
+	if (hdr->opt_len < 2)
+		goto drop;
+
+	switch (hdr->type) {
+	case IOAM6_TYPE_PREALLOC:
+		/* Truncated Pre-allocated Trace header */
+		if (hdr->opt_len < 2 + sizeof(*trace))
+			goto drop;
+
+		/* Malformed Pre-allocated Trace header */
+		trace = (struct ioam6_trace_hdr *)((u8 *)hdr + sizeof(*hdr));
+		if (hdr->opt_len < 2 + sizeof(*trace) + trace->remlen * 4)
+			goto drop;
+
+		/* Ignore if the IOAM namespace is unknown */
+		ns = ioam6_namespace(ipv6_skb_net(skb), trace->namespace_id);
+		if (!ns)
+			goto ignore;
+
+		if (!skb_valid_dst(skb))
+			ip6_route_input(skb);
+
+		ioam6_fill_trace_data(skb, ns, trace);
+		break;
+	default:
+		break;
+	}
+
+ignore:
+	return true;
+
+drop:
+	kfree_skb(skb);
+	return false;
+}
+
 /* Jumbo payload */
 
 static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff)
@@ -999,6 +1056,10 @@ static const struct tlvtype_proc tlvprochopopt_lst[] = {
 		.type	= IPV6_TLV_ROUTERALERT,
 		.func	= ipv6_hop_ra,
 	},
+	{
+		.type	= IPV6_TLV_IOAM,
+		.func	= ipv6_hop_ioam,
+	},
 	{
 		.type	= IPV6_TLV_JUMBO,
 		.func	= ipv6_hop_jumbo,

net/ipv6/ioam6.c

+// SPDX-License-Identifier: GPL-2.0+
+/*
+ *  IPv6 IOAM implementation
+ *
+ *  Author:
+ *  Justin Iurman <justin.iurman@uliege.be>
+ */
+
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/net.h>
+#include <linux/ioam6.h>
+#include <linux/ioam6_genl.h>
+#include <linux/rhashtable.h>
+
+#include <net/addrconf.h>
+#include <net/genetlink.h>
+#include <net/ioam6.h>
+
+static void ioam6_ns_release(struct ioam6_namespace *ns)
+{
+	kfree_rcu(ns, rcu);
+}
+
+static void ioam6_sc_release(struct ioam6_schema *sc)
+{
+	kfree_rcu(sc, rcu);
+}
+
+static void ioam6_free_ns(void *ptr, void *arg)
+{
+	struct ioam6_namespace *ns = (struct ioam6_namespace *)ptr;
+
+	if (ns)
+		ioam6_ns_release(ns);
+}
+
+static void ioam6_free_sc(void *ptr, void *arg)
+{
+	struct ioam6_schema *sc = (struct ioam6_schema *)ptr;
+
+	if (sc)
+		ioam6_sc_release(sc);
+}
+
+static int ioam6_ns_cmpfn(struct rhashtable_compare_arg *arg, const void *obj)
+{
+	const struct ioam6_namespace *ns = obj;
+
+	return (ns->id != *(__be16 *)arg->key);
+}
+
+static int ioam6_sc_cmpfn(struct rhashtable_compare_arg *arg, const void *obj)
+{
+	const struct ioam6_schema *sc = obj;
+
+	return (sc->id != *(u32 *)arg->key);
+}
+
+static const struct rhashtable_params rht_ns_params = {
+	.key_len		= sizeof(__be16),
+	.key_offset		= offsetof(struct ioam6_namespace, id),
+	.head_offset		= offsetof(struct ioam6_namespace, head),
+	.automatic_shrinking	= true,
+	.obj_cmpfn		= ioam6_ns_cmpfn,
+};
+
+static const struct rhashtable_params rht_sc_params = {
+	.key_len		= sizeof(u32),
+	.key_offset		= offsetof(struct ioam6_schema, id),
+	.head_offset		= offsetof(struct ioam6_schema, head),
+	.automatic_shrinking	= true,
+	.obj_cmpfn		= ioam6_sc_cmpfn,
+};
+
+static struct genl_family ioam6_genl_family;
+
+static const struct nla_policy ioam6_genl_policy_addns[] = {
+	[IOAM6_ATTR_NS_ID]	= { .type = NLA_U16 },
+	[IOAM6_ATTR_NS_DATA]	= { .type = NLA_U32 },
+	[IOAM6_ATTR_NS_DATA_WIDE] = { .type = NLA_U64 },
+};
+
+static const struct nla_policy ioam6_genl_policy_delns[] = {
+	[IOAM6_ATTR_NS_ID]	= { .type = NLA_U16 },
+};
+
+static const struct nla_policy ioam6_genl_policy_addsc[] = {
+	[IOAM6_ATTR_SC_ID]	= { .type = NLA_U32 },
+	[IOAM6_ATTR_SC_DATA]	= { .type = NLA_BINARY,
+				    .len = IOAM6_MAX_SCHEMA_DATA_LEN },
+};
+
+static const struct nla_policy ioam6_genl_policy_delsc[] = {
+	[IOAM6_ATTR_SC_ID]	= { .type = NLA_U32 },
+};
+
+static const struct nla_policy ioam6_genl_policy_ns_sc[] = {
+	[IOAM6_ATTR_NS_ID]	= { .type = NLA_U16 },
+	[IOAM6_ATTR_SC_ID]	= { .type = NLA_U32 },
+	[IOAM6_ATTR_SC_NONE]	= { .type = NLA_FLAG },
+};
+
+static int ioam6_genl_addns(struct sk_buff *skb, struct genl_info *info)
+{
+	struct ioam6_pernet_data *nsdata;
+	struct ioam6_namespace *ns;
+	u64 data64;
+	u32 data32;
+	__be16 id;
+	int err;
+
+	if (!info->attrs[IOAM6_ATTR_NS_ID])
+		return -EINVAL;
+
+	id = cpu_to_be16(nla_get_u16(info->attrs[IOAM6_ATTR_NS_ID]));
+	nsdata = ioam6_pernet(genl_info_net(info));
+
+	mutex_lock(&nsdata->lock);
+
+	ns = rhashtable_lookup_fast(&nsdata->namespaces, &id, rht_ns_params);
+	if (ns) {
+		err = -EEXIST;
+		goto out_unlock;
+	}
+
+	ns = kzalloc(sizeof(*ns), GFP_KERNEL);
+	if (!ns) {
+		err = -ENOMEM;
+		goto out_unlock;
+	}
+
+	ns->id = id;
+
+	if (!info->attrs[IOAM6_ATTR_NS_DATA])
+		data32 = IOAM6_U32_UNAVAILABLE;
+	else
+		data32 = nla_get_u32(info->attrs[IOAM6_ATTR_NS_DATA]);
+
+	if (!info->attrs[IOAM6_ATTR_NS_DATA_WIDE])
+		data64 = IOAM6_U64_UNAVAILABLE;
+	else
+		data64 = nla_get_u64(info->attrs[IOAM6_ATTR_NS_DATA_WIDE]);
+
+	ns->data = cpu_to_be32(data32);
+	ns->data_wide = cpu_to_be64(data64);
+
+	err = rhashtable_lookup_insert_fast(&nsdata->namespaces, &ns->head,
+					    rht_ns_params);
+	if (err)
+		kfree(ns);
+
+out_unlock:
+	mutex_unlock(&nsdata->lock);
+	return err;
+}
+
+static int ioam6_genl_delns(struct sk_buff *skb, struct genl_info *info)
+{
+	struct ioam6_pernet_data *nsdata;
+	struct ioam6_namespace *ns;
+	struct ioam6_schema *sc;
+	__be16 id;
+	int err;
+
+	if (!info->attrs[IOAM6_ATTR_NS_ID])
+		return -EINVAL;
+
+	id = cpu_to_be16(nla_get_u16(info->attrs[IOAM6_ATTR_NS_ID]));
+	nsdata = ioam6_pernet(genl_info_net(info));
+
+	mutex_lock(&nsdata->lock);
+
+	ns = rhashtable_lookup_fast(&nsdata->namespaces, &id, rht_ns_params);
+	if (!ns) {
+		err = -ENOENT;
+		goto out_unlock;
+	}
+
+	sc = rcu_dereference_protected(ns->schema,
+				       lockdep_is_held(&nsdata->lock));
+
+	err = rhashtable_remove_fast(&nsdata->namespaces, &ns->head,
+				     rht_ns_params);
+	if (err)
+		goto out_unlock;
+
+	if (sc)
+		rcu_assign_pointer(sc->ns, NULL);
+
+	ioam6_ns_release(ns);
+
+out_unlock:
+	mutex_unlock(&nsdata->lock);
+	return err;
+}
+
+static int __ioam6_genl_dumpns_element(struct ioam6_namespace *ns,
+				       u32 portid,
+				       u32 seq,
+				       u32 flags,
+				       struct sk_buff *skb,
+				       u8 cmd)
+{
+	struct ioam6_schema *sc;
+	u64 data64;
+	u32 data32;
+	void *hdr;
+
+	hdr = genlmsg_put(skb, portid, seq, &ioam6_genl_family, flags, cmd);
+	if (!hdr)
+		return -ENOMEM;
+
+	data32 = be32_to_cpu(ns->data);
+	data64 = be64_to_cpu(ns->data_wide);
+
+	if (nla_put_u16(skb, IOAM6_ATTR_NS_ID, be16_to_cpu(ns->id)) ||
+	    (data32 != IOAM6_U32_UNAVAILABLE &&
+	     nla_put_u32(skb, IOAM6_ATTR_NS_DATA, data32)) ||
+	    (data64 != IOAM6_U64_UNAVAILABLE &&
+	     nla_put_u64_64bit(skb, IOAM6_ATTR_NS_DATA_WIDE,
+			       data64, IOAM6_ATTR_PAD)))
+		goto nla_put_failure;
+
+	rcu_read_lock();
+
+	sc = rcu_dereference(ns->schema);
+	if (sc && nla_put_u32(skb, IOAM6_ATTR_SC_ID, sc->id)) {
+		rcu_read_unlock();
+		goto nla_put_failure;
+	}
+
+	rcu_read_unlock();
+
+	genlmsg_end(skb, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(skb, hdr);
+	return -EMSGSIZE;
+}
+
+static int ioam6_genl_dumpns_start(struct netlink_callback *cb)
+{
+	struct ioam6_pernet_data *nsdata = ioam6_pernet(sock_net(cb->skb->sk));
+	struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0];
+
+	if (!iter) {
+		iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+		if (!iter)
+			return -ENOMEM;
+
+		cb->args[0] = (long)iter;
+	}
+
+	rhashtable_walk_enter(&nsdata->namespaces, iter);
+
+	return 0;
+}
+
+static int ioam6_genl_dumpns_done(struct netlink_callback *cb)
+{
+	struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0];
+
+	rhashtable_walk_exit(iter);
+	kfree(iter);
+
+	return 0;
+}
+
+static int ioam6_genl_dumpns(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct rhashtable_iter *iter;
+	struct ioam6_namespace *ns;
+	int err;
+
+	iter = (struct rhashtable_iter *)cb->args[0];
+	rhashtable_walk_start(iter);
+
+	for (;;) {
+		ns = rhashtable_walk_next(iter);
+
+		if (IS_ERR(ns)) {
+			if (PTR_ERR(ns) == -EAGAIN)
+				continue;
+			err = PTR_ERR(ns);
+			goto done;
+		} else if (!ns) {
+			break;
+		}
+
+		err = __ioam6_genl_dumpns_element(ns,
+						  NETLINK_CB(cb->skb).portid,
+						  cb->nlh->nlmsg_seq,
+						  NLM_F_MULTI,
+						  skb,
+						  IOAM6_CMD_DUMP_NAMESPACES);
+		if (err)
+			goto done;
+	}
+
+	err = skb->len;
+
+done:
+	rhashtable_walk_stop(iter);
+	return err;
+}
+
+static int ioam6_genl_addsc(struct sk_buff *skb, struct genl_info *info)
+{
+	struct ioam6_pernet_data *nsdata;
+	int len, len_aligned, err;
+	struct ioam6_schema *sc;
+	u32 id;
+
+	if (!info->attrs[IOAM6_ATTR_SC_ID] || !info->attrs[IOAM6_ATTR_SC_DATA])
+		return -EINVAL;
+
+	id = nla_get_u32(info->attrs[IOAM6_ATTR_SC_ID]);
+	nsdata = ioam6_pernet(genl_info_net(info));
+
+	mutex_lock(&nsdata->lock);
+
+	sc = rhashtable_lookup_fast(&nsdata->schemas, &id, rht_sc_params);
+	if (sc) {
+		err = -EEXIST;
+		goto out_unlock;
+	}
+
+	len = nla_len(info->attrs[IOAM6_ATTR_SC_DATA]);
+	len_aligned = ALIGN(len, 4);
+
+	sc = kzalloc(sizeof(*sc) + len_aligned, GFP_KERNEL);
+	if (!sc) {
+		err = -ENOMEM;
+		goto out_unlock;
+	}
+
+	sc->id = id;
+	sc->len = len_aligned;
+	sc->hdr = cpu_to_be32(sc->id | ((u8)(sc->len / 4) << 24));
+	nla_memcpy(sc->data, info->attrs[IOAM6_ATTR_SC_DATA], len);
+
+	err = rhashtable_lookup_insert_fast(&nsdata->schemas, &sc->head,
+					    rht_sc_params);
+	if (err)
+		goto free_sc;
+
+out_unlock:
+	mutex_unlock(&nsdata->lock);
+	return err;
+free_sc:
+	kfree(sc);
+	goto out_unlock;
+}
+
+static int ioam6_genl_delsc(struct sk_buff *skb, struct genl_info *info)
+{
+	struct ioam6_pernet_data *nsdata;
+	struct ioam6_namespace *ns;
+	struct ioam6_schema *sc;
+	int err;
+	u32 id;
+
+	if (!info->attrs[IOAM6_ATTR_SC_ID])
+		return -EINVAL;
+
+	id = nla_get_u32(info->attrs[IOAM6_ATTR_SC_ID]);
+	nsdata = ioam6_pernet(genl_info_net(info));
+
+	mutex_lock(&nsdata->lock);
+
+	sc = rhashtable_lookup_fast(&nsdata->schemas, &id, rht_sc_params);
+	if (!sc) {
+		err = -ENOENT;
+		goto out_unlock;
+	}
+
+	ns = rcu_dereference_protected(sc->ns, lockdep_is_held(&nsdata->lock));
+
+	err = rhashtable_remove_fast(&nsdata->schemas, &sc->head,
+				     rht_sc_params);
+	if (err)
+		goto out_unlock;
+
+	if (ns)
+		rcu_assign_pointer(ns->schema, NULL);
+
+	ioam6_sc_release(sc);
+
+out_unlock:
+	mutex_unlock(&nsdata->lock);
+	return err;
+}
+
+static int __ioam6_genl_dumpsc_element(struct ioam6_schema *sc,
+				       u32 portid, u32 seq, u32 flags,
+				       struct sk_buff *skb, u8 cmd)
+{
+	struct ioam6_namespace *ns;
+	void *hdr;
+
+	hdr = genlmsg_put(skb, portid, seq, &ioam6_genl_family, flags, cmd);
+	if (!hdr)
+		return -ENOMEM;
+
+	if (nla_put_u32(skb, IOAM6_ATTR_SC_ID, sc->id) ||
+	    nla_put(skb, IOAM6_ATTR_SC_DATA, sc->len, sc->data))
+		goto nla_put_failure;
+
+	rcu_read_lock();
+
+	ns = rcu_dereference(sc->ns);
+	if (ns && nla_put_u16(skb, IOAM6_ATTR_NS_ID, be16_to_cpu(ns->id))) {
+		rcu_read_unlock();
+		goto nla_put_failure;
+	}
+
+	rcu_read_unlock();
+
+	genlmsg_end(skb, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(skb, hdr);
+	return -EMSGSIZE;
+}
+
+static int ioam6_genl_dumpsc_start(struct netlink_callback *cb)
+{
+	struct ioam6_pernet_data *nsdata = ioam6_pernet(sock_net(cb->skb->sk));
+	struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0];
+
+	if (!iter) {
+		iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+		if (!iter)
+			return -ENOMEM;
+
+		cb->args[0] = (long)iter;
+	}
+
+	rhashtable_walk_enter(&nsdata->schemas, iter);
+
+	return 0;
+}
+
+static int ioam6_genl_dumpsc_done(struct netlink_callback *cb)
+{
+	struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0];
+
+	rhashtable_walk_exit(iter);
+	kfree(iter);
+
+	return 0;
+}
+
+static int ioam6_genl_dumpsc(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct rhashtable_iter *iter;
+	struct ioam6_schema *sc;
+	int err;
+
+	iter = (struct rhashtable_iter *)cb->args[0];
+	rhashtable_walk_start(iter);
+
+	for (;;) {
+		sc = rhashtable_walk_next(iter);
+
+		if (IS_ERR(sc)) {
+			if (PTR_ERR(sc) == -EAGAIN)
+				continue;
+			err = PTR_ERR(sc);
+			goto done;
+		} else if (!sc) {
+			break;
+		}
+
+		err = __ioam6_genl_dumpsc_element(sc,
+						  NETLINK_CB(cb->skb).portid,
+						  cb->nlh->nlmsg_seq,
+						  NLM_F_MULTI,
+						  skb,
+						  IOAM6_CMD_DUMP_SCHEMAS);
+		if (err)
+			goto done;
+	}
+
+	err = skb->len;
+
+done:
+	rhashtable_walk_stop(iter);
+	return err;
+}
+
+static int ioam6_genl_ns_set_schema(struct sk_buff *skb, struct genl_info *info)
+{
+	struct ioam6_namespace *ns, *ns_ref;
+	struct ioam6_schema *sc, *sc_ref;
+	struct ioam6_pernet_data *nsdata;
+	__be16 ns_id;
+	u32 sc_id;
+	int err;
+
+	if (!info->attrs[IOAM6_ATTR_NS_ID] ||
+	    (!info->attrs[IOAM6_ATTR_SC_ID] &&
+	     !info->attrs[IOAM6_ATTR_SC_NONE]))
+		return -EINVAL;
+
+	ns_id = cpu_to_be16(nla_get_u16(info->attrs[IOAM6_ATTR_NS_ID]));
+	nsdata = ioam6_pernet(genl_info_net(info));
+
+	mutex_lock(&nsdata->lock);
+
+	ns = rhashtable_lookup_fast(&nsdata->namespaces, &ns_id, rht_ns_params);
+	if (!ns) {
+		err = -ENOENT;
+		goto out_unlock;
+	}
+
+	if (info->attrs[IOAM6_ATTR_SC_NONE]) {
+		sc = NULL;
+	} else {
+		sc_id = nla_get_u32(info->attrs[IOAM6_ATTR_SC_ID]);
+		sc = rhashtable_lookup_fast(&nsdata->schemas, &sc_id,
+					    rht_sc_params);
+		if (!sc) {
+			err = -ENOENT;
+			goto out_unlock;
+		}
+	}
+
+	sc_ref = rcu_dereference_protected(ns->schema,
+					   lockdep_is_held(&nsdata->lock));
+	if (sc_ref)
+		rcu_assign_pointer(sc_ref->ns, NULL);
+	rcu_assign_pointer(ns->schema, sc);
+
+	if (sc) {
+		ns_ref = rcu_dereference_protected(sc->ns,
+						   lockdep_is_held(&nsdata->lock));
+		if (ns_ref)
+			rcu_assign_pointer(ns_ref->schema, NULL);
+		rcu_assign_pointer(sc->ns, ns);
+	}
+
+	err = 0;
+
+out_unlock:
+	mutex_unlock(&nsdata->lock);
+	return err;
+}
+
+static const struct genl_ops ioam6_genl_ops[] = {
+	{
+		.cmd	= IOAM6_CMD_ADD_NAMESPACE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit	= ioam6_genl_addns,
+		.flags	= GENL_ADMIN_PERM,
+		.policy	= ioam6_genl_policy_addns,
+		.maxattr = ARRAY_SIZE(ioam6_genl_policy_addns) - 1,
+	},
+	{
+		.cmd	= IOAM6_CMD_DEL_NAMESPACE,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit	= ioam6_genl_delns,
+		.flags	= GENL_ADMIN_PERM,
+		.policy	= ioam6_genl_policy_delns,
+		.maxattr = ARRAY_SIZE(ioam6_genl_policy_delns) - 1,
+	},
+	{
+		.cmd	= IOAM6_CMD_DUMP_NAMESPACES,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.start	= ioam6_genl_dumpns_start,
+		.dumpit	= ioam6_genl_dumpns,
+		.done	= ioam6_genl_dumpns_done,
+		.flags	= GENL_ADMIN_PERM,
+	},
+	{
+		.cmd	= IOAM6_CMD_ADD_SCHEMA,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit	= ioam6_genl_addsc,
+		.flags	= GENL_ADMIN_PERM,
+		.policy	= ioam6_genl_policy_addsc,
+		.maxattr = ARRAY_SIZE(ioam6_genl_policy_addsc) - 1,
+	},
+	{
+		.cmd	= IOAM6_CMD_DEL_SCHEMA,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit	= ioam6_genl_delsc,
+		.flags	= GENL_ADMIN_PERM,
+		.policy	= ioam6_genl_policy_delsc,
+		.maxattr = ARRAY_SIZE(ioam6_genl_policy_delsc) - 1,
+	},
+	{
+		.cmd	= IOAM6_CMD_DUMP_SCHEMAS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.start	= ioam6_genl_dumpsc_start,
+		.dumpit	= ioam6_genl_dumpsc,
+		.done	= ioam6_genl_dumpsc_done,
+		.flags	= GENL_ADMIN_PERM,
+	},
+	{
+		.cmd	= IOAM6_CMD_NS_SET_SCHEMA,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit	= ioam6_genl_ns_set_schema,
+		.flags	= GENL_ADMIN_PERM,
+		.policy	= ioam6_genl_policy_ns_sc,
+		.maxattr = ARRAY_SIZE(ioam6_genl_policy_ns_sc) - 1,
+	},
+};
+
+static struct genl_family ioam6_genl_family __ro_after_init = {
+	.name		= IOAM6_GENL_NAME,
+	.version	= IOAM6_GENL_VERSION,
+	.netnsok	= true,
+	.parallel_ops	= true,
+	.ops		= ioam6_genl_ops,
+	.n_ops		= ARRAY_SIZE(ioam6_genl_ops),
+	.module		= THIS_MODULE,
+};
+
+struct ioam6_namespace *ioam6_namespace(struct net *net, __be16 id)
+{
+	struct ioam6_pernet_data *nsdata = ioam6_pernet(net);
+
+	return rhashtable_lookup_fast(&nsdata->namespaces, &id, rht_ns_params);
+}
+
+static void __ioam6_fill_trace_data(struct sk_buff *skb,
+				    struct ioam6_namespace *ns,
+				    struct ioam6_trace_hdr *trace,
+				    struct ioam6_schema *sc,
+				    u8 sclen)
+{
+	struct __kernel_sock_timeval ts;
+	u64 raw64;
+	u32 raw32;
+	u16 raw16;
+	u8 *data;
+	u8 byte;
+
+	data = trace->data + trace->remlen * 4 - trace->nodelen * 4 - sclen * 4;
+
+	/* hop_lim and node_id */
+	if (trace->type.bit0) {
+		byte = ipv6_hdr(skb)->hop_limit;
+		if (skb->dev)
+			byte--;
+
+		raw32 = dev_net(skb_dst(skb)->dev)->ipv6.sysctl.ioam6_id;
+
+		*(__be32 *)data = cpu_to_be32((byte << 24) | raw32);
+		data += sizeof(__be32);
+	}
+
+	/* ingress_if_id and egress_if_id */
+	if (trace->type.bit1) {
+		if (!skb->dev)
+			raw16 = IOAM6_U16_UNAVAILABLE;
+		else
+			raw16 = (__force u16)__in6_dev_get(skb->dev)->cnf.ioam6_id;
+
+		*(__be16 *)data = cpu_to_be16(raw16);
+		data += sizeof(__be16);
+
+		if (skb_dst(skb)->dev->flags & IFF_LOOPBACK)
+			raw16 = IOAM6_U16_UNAVAILABLE;
+		else
+			raw16 = (__force u16)__in6_dev_get(skb_dst(skb)->dev)->cnf.ioam6_id;
+
+		*(__be16 *)data = cpu_to_be16(raw16);
+		data += sizeof(__be16);
+	}
+
+	/* timestamp seconds */
+	if (trace->type.bit2) {
+		if (!skb->dev) {
+			*(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE);
+		} else {
+			if (!skb->tstamp)
+				__net_timestamp(skb);
+
+			skb_get_new_timestamp(skb, &ts);
+			*(__be32 *)data = cpu_to_be32((u32)ts.tv_sec);
+		}
+		data += sizeof(__be32);
+	}
+
+	/* timestamp subseconds */
+	if (trace->type.bit3) {
+		if (!skb->dev) {
+			*(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE);
+		} else {
+			if (!skb->tstamp)
+				__net_timestamp(skb);
+
+			if (!trace->type.bit2)
+				skb_get_new_timestamp(skb, &ts);
+
+			*(__be32 *)data = cpu_to_be32((u32)ts.tv_usec);
+		}
+		data += sizeof(__be32);
+	}
+
+	/* transit delay */
+	if (trace->type.bit4) {
+		*(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE);
+		data += sizeof(__be32);
+	}
+
+	/* namespace data */
+	if (trace->type.bit5) {
+		*(__be32 *)data = ns->data;
+		data += sizeof(__be32);
+	}
+
+	/* queue depth */
+	if (trace->type.bit6) {
+		*(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE);
+		data += sizeof(__be32);
+	}
+
+	/* checksum complement */
+	if (trace->type.bit7) {
+		*(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE);
+		data += sizeof(__be32);
+	}
+
+	/* hop_lim and node_id (wide) */
+	if (trace->type.bit8) {
+		byte = ipv6_hdr(skb)->hop_limit;
+		if (skb->dev)
+			byte--;
+
+		raw64 = dev_net(skb_dst(skb)->dev)->ipv6.sysctl.ioam6_id_wide;
+
+		*(__be64 *)data = cpu_to_be64(((u64)byte << 56) | raw64);
+		data += sizeof(__be64);
+	}
+
+	/* ingress_if_id and egress_if_id (wide) */
+	if (trace->type.bit9) {
+		if (!skb->dev)
+			raw32 = IOAM6_U32_UNAVAILABLE;
+		else
+			raw32 = __in6_dev_get(skb->dev)->cnf.ioam6_id_wide;
+
+		*(__be32 *)data = cpu_to_be32(raw32);
+		data += sizeof(__be32);
+
+		if (skb_dst(skb)->dev->flags & IFF_LOOPBACK)
+			raw32 = IOAM6_U32_UNAVAILABLE;
+		else
+			raw32 = __in6_dev_get(skb_dst(skb)->dev)->cnf.ioam6_id_wide;
+
+		*(__be32 *)data = cpu_to_be32(raw32);
+		data += sizeof(__be32);
+	}
+
+	/* namespace data (wide) */
+	if (trace->type.bit10) {
+		*(__be64 *)data = ns->data_wide;
+		data += sizeof(__be64);
+	}
+
+	/* buffer occupancy */
+	if (trace->type.bit11) {
+		*(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE);
+		data += sizeof(__be32);
+	}
+
+	/* opaque state snapshot */
+	if (trace->type.bit22) {
+		if (!sc) {
+			*(__be32 *)data = cpu_to_be32(IOAM6_U32_UNAVAILABLE >> 8);
+		} else {
+			*(__be32 *)data = sc->hdr;
+			data += sizeof(__be32);
+
+			memcpy(data, sc->data, sc->len);
+		}
+	}
+}
+
+/* called with rcu_read_lock() */
+void ioam6_fill_trace_data(struct sk_buff *skb,
+			   struct ioam6_namespace *ns,
+			   struct ioam6_trace_hdr *trace)
+{
+	struct ioam6_schema *sc;
+	u8 sclen = 0;
+
+	/* Skip if Overflow flag is set OR
+	 * if an unknown type (bit 12-21) is set
+	 */
+	if (trace->overflow ||
+	    trace->type.bit12 | trace->type.bit13 | trace->type.bit14 |
+	    trace->type.bit15 | trace->type.bit16 | trace->type.bit17 |
+	    trace->type.bit18 | trace->type.bit19 | trace->type.bit20 |
+	    trace->type.bit21) {
+		return;
+	}
+
+	/* NodeLen does not include Opaque State Snapshot length. We need to
+	 * take it into account if the corresponding bit is set (bit 22) and
+	 * if the current IOAM namespace has an active schema attached to it
+	 */
+	sc = rcu_dereference(ns->schema);
+	if (trace->type.bit22) {
+		sclen = sizeof_field(struct ioam6_schema, hdr) / 4;
+
+		if (sc)
+			sclen += sc->len / 4;
+	}
+
+	/* If there is no space remaining, we set the Overflow flag and we
+	 * skip without filling the trace
+	 */
+	if (!trace->remlen || trace->remlen < trace->nodelen + sclen) {
+		trace->overflow = 1;
+		return;
+	}
+
+	__ioam6_fill_trace_data(skb, ns, trace, sc, sclen);
+	trace->remlen -= trace->nodelen + sclen;
+}
+
+static int __net_init ioam6_net_init(struct net *net)
+{
+	struct ioam6_pernet_data *nsdata;
+	int err = -ENOMEM;
+
+	nsdata = kzalloc(sizeof(*nsdata), GFP_KERNEL);
+	if (!nsdata)
+		goto out;
+
+	mutex_init(&nsdata->lock);
+	net->ipv6.ioam6_data = nsdata;
+
+	err = rhashtable_init(&nsdata->namespaces, &rht_ns_params);
+	if (err)
+		goto free_nsdata;
+
+	err = rhashtable_init(&nsdata->schemas, &rht_sc_params);
+	if (err)
+		goto free_rht_ns;
+
+out:
+	return err;
+free_rht_ns:
+	rhashtable_destroy(&nsdata->namespaces);
+free_nsdata:
+	kfree(nsdata);
+	net->ipv6.ioam6_data = NULL;
+	goto out;
+}
+
+static void __net_exit ioam6_net_exit(struct net *net)
+{
+	struct ioam6_pernet_data *nsdata = ioam6_pernet(net);
+
+	rhashtable_free_and_destroy(&nsdata->namespaces, ioam6_free_ns, NULL);
+	rhashtable_free_and_destroy(&nsdata->schemas, ioam6_free_sc, NULL);
+
+	kfree(nsdata);
+}
+
+static struct pernet_operations ioam6_net_ops = {
+	.init = ioam6_net_init,
+	.exit = ioam6_net_exit,
+};
+
+int __init ioam6_init(void)
+{
+	int err = register_pernet_subsys(&ioam6_net_ops);
+	if (err)
+		goto out;
+
+	err = genl_register_family(&ioam6_genl_family);
+	if (err)
+		goto out_unregister_pernet_subsys;
+
+#ifdef CONFIG_IPV6_IOAM6_LWTUNNEL
+	err = ioam6_iptunnel_init();
+	if (err)
+		goto out_unregister_genl;
+#endif
+
+	pr_info("In-situ OAM (IOAM) with IPv6\n");
+
+out:
+	return err;
+#ifdef CONFIG_IPV6_IOAM6_LWTUNNEL
+out_unregister_genl:
+	genl_unregister_family(&ioam6_genl_family);
+#endif
+out_unregister_pernet_subsys:
+	unregister_pernet_subsys(&ioam6_net_ops);
+	goto out;
+}
+
+void ioam6_exit(void)
+{
+#ifdef CONFIG_IPV6_IOAM6_LWTUNNEL
+	ioam6_iptunnel_exit();
+#endif
+	genl_unregister_family(&ioam6_genl_family);
+	unregister_pernet_subsys(&ioam6_net_ops);
+}

net/ipv6/ioam6_iptunnel.c

+// SPDX-License-Identifier: GPL-2.0+
+/*
+ *  IPv6 IOAM Lightweight Tunnel implementation
+ *
+ *  Author:
+ *  Justin Iurman <justin.iurman@uliege.be>
+ */
+
+#include <linux/kernel.h>
+#include <linux/skbuff.h>
+#include <linux/net.h>
+#include <linux/netlink.h>
+#include <linux/in6.h>
+#include <linux/ioam6.h>
+#include <linux/ioam6_iptunnel.h>
+#include <net/dst.h>
+#include <net/sock.h>
+#include <net/lwtunnel.h>
+#include <net/ioam6.h>
+
+#define IOAM6_MASK_SHORT_FIELDS 0xff100000
+#define IOAM6_MASK_WIDE_FIELDS 0xe00000
+
+struct ioam6_lwt_encap {
+	struct ipv6_hopopt_hdr	eh;
+	u8			pad[2];	/* 2-octet padding for 4n-alignment */
+	struct ioam6_hdr	ioamh;
+	struct ioam6_trace_hdr	traceh;
+} __packed;
+
+struct ioam6_lwt {
+	struct ioam6_lwt_encap	tuninfo;
+};
+
+static struct ioam6_lwt *ioam6_lwt_state(struct lwtunnel_state *lwt)
+{
+	return (struct ioam6_lwt *)lwt->data;
+}
+
+static struct ioam6_lwt_encap *ioam6_lwt_info(struct lwtunnel_state *lwt)
+{
+	return &ioam6_lwt_state(lwt)->tuninfo;
+}
+
+static struct ioam6_trace_hdr *ioam6_trace(struct lwtunnel_state *lwt)
+{
+	return &(ioam6_lwt_state(lwt)->tuninfo.traceh);
+}
+
+static const struct nla_policy ioam6_iptunnel_policy[IOAM6_IPTUNNEL_MAX + 1] = {
+	[IOAM6_IPTUNNEL_TRACE]	= NLA_POLICY_EXACT_LEN(sizeof(struct ioam6_trace_hdr)),
+};
+
+static int nla_put_ioam6_trace(struct sk_buff *skb, int attrtype,
+			       struct ioam6_trace_hdr *trace)
+{
+	struct ioam6_trace_hdr *data;
+	struct nlattr *nla;
+	int len;
+
+	len = sizeof(*trace);
+
+	nla = nla_reserve(skb, attrtype, len);
+	if (!nla)
+		return -EMSGSIZE;
+
+	data = nla_data(nla);
+	memcpy(data, trace, len);
+
+	return 0;
+}
+
+static bool ioam6_validate_trace_hdr(struct ioam6_trace_hdr *trace)
+{
+	u32 fields;
+
+	if (!trace->type_be32 || !trace->remlen ||
+	    trace->remlen > IOAM6_TRACE_DATA_SIZE_MAX / 4)
+		return false;
+
+	trace->nodelen = 0;
+	fields = be32_to_cpu(trace->type_be32);
+
+	trace->nodelen += hweight32(fields & IOAM6_MASK_SHORT_FIELDS)
+				* (sizeof(__be32) / 4);
+	trace->nodelen += hweight32(fields & IOAM6_MASK_WIDE_FIELDS)
+				* (sizeof(__be64) / 4);
+
+	return true;
+}
+
+static int ioam6_build_state(struct net *net, struct nlattr *nla,
+			     unsigned int family, const void *cfg,
+			     struct lwtunnel_state **ts,
+			     struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[IOAM6_IPTUNNEL_MAX + 1];
+	struct ioam6_lwt_encap *tuninfo;
+	struct ioam6_trace_hdr *trace;
+	struct lwtunnel_state *s;
+	int len_aligned;
+	int len, err;
+
+	if (family != AF_INET6)
+		return -EINVAL;
+
+	err = nla_parse_nested(tb, IOAM6_IPTUNNEL_MAX, nla,
+			       ioam6_iptunnel_policy, extack);
+	if (err < 0)
+		return err;
+
+	if (!tb[IOAM6_IPTUNNEL_TRACE]) {
+		NL_SET_ERR_MSG(extack, "missing trace");
+		return -EINVAL;
+	}
+
+	trace = nla_data(tb[IOAM6_IPTUNNEL_TRACE]);
+	if (!ioam6_validate_trace_hdr(trace)) {
+		NL_SET_ERR_MSG_ATTR(extack, tb[IOAM6_IPTUNNEL_TRACE],
+				    "invalid trace validation");
+		return -EINVAL;
+	}
+
+	len = sizeof(*tuninfo) + trace->remlen * 4;
+	len_aligned = ALIGN(len, 8);
+
+	s = lwtunnel_state_alloc(len_aligned);
+	if (!s)
+		return -ENOMEM;
+
+	tuninfo = ioam6_lwt_info(s);
+	tuninfo->eh.hdrlen = (len_aligned >> 3) - 1;
+	tuninfo->pad[0] = IPV6_TLV_PADN;
+	tuninfo->ioamh.type = IOAM6_TYPE_PREALLOC;
+	tuninfo->ioamh.opt_type = IPV6_TLV_IOAM;
+	tuninfo->ioamh.opt_len = sizeof(tuninfo->ioamh) - 2 + sizeof(*trace)
+					+ trace->remlen * 4;
+
+	memcpy(&tuninfo->traceh, trace, sizeof(*trace));
+
+	len = len_aligned - len;
+	if (len == 1) {
+		tuninfo->traceh.data[trace->remlen * 4] = IPV6_TLV_PAD1;
+	} else if (len > 0) {
+		tuninfo->traceh.data[trace->remlen * 4] = IPV6_TLV_PADN;
+		tuninfo->traceh.data[trace->remlen * 4 + 1] = len - 2;
+	}
+
+	s->type = LWTUNNEL_ENCAP_IOAM6;
+	s->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT;
+
+	*ts = s;
+
+	return 0;
+}
+
+static int ioam6_do_inline(struct sk_buff *skb, struct ioam6_lwt_encap *tuninfo)
+{
+	struct ioam6_trace_hdr *trace;
+	struct ipv6hdr *oldhdr, *hdr;
+	struct ioam6_namespace *ns;
+	int hdrlen, err;
+
+	hdrlen = (tuninfo->eh.hdrlen + 1) << 3;
+
+	err = skb_cow_head(skb, hdrlen + skb->mac_len);
+	if (unlikely(err))
+		return err;
+
+	oldhdr = ipv6_hdr(skb);
+	skb_pull(skb, sizeof(*oldhdr));
+	skb_postpull_rcsum(skb, skb_network_header(skb), sizeof(*oldhdr));
+
+	skb_push(skb, sizeof(*oldhdr) + hdrlen);
+	skb_reset_network_header(skb);
+	skb_mac_header_rebuild(skb);
+
+	hdr = ipv6_hdr(skb);
+	memmove(hdr, oldhdr, sizeof(*oldhdr));
+	tuninfo->eh.nexthdr = hdr->nexthdr;
+
+	skb_set_transport_header(skb, sizeof(*hdr));
+	skb_postpush_rcsum(skb, hdr, sizeof(*hdr) + hdrlen);
+
+	memcpy(skb_transport_header(skb), (u8 *)tuninfo, hdrlen);
+
+	hdr->nexthdr = NEXTHDR_HOP;
+	hdr->payload_len = cpu_to_be16(skb->len - sizeof(*hdr));
+
+	trace = (struct ioam6_trace_hdr *)(skb_transport_header(skb)
+					   + sizeof(struct ipv6_hopopt_hdr) + 2
+					   + sizeof(struct ioam6_hdr));
+
+	ns = ioam6_namespace(dev_net(skb_dst(skb)->dev), trace->namespace_id);
+	if (ns)
+		ioam6_fill_trace_data(skb, ns, trace);
+
+	return 0;
+}
+
+static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	struct lwtunnel_state *lwt = skb_dst(skb)->lwtstate;
+	int err = -EINVAL;
+
+	if (skb->protocol != htons(ETH_P_IPV6))
+		goto drop;
+
+	/* Only for packets we send and
+	 * that do not contain a Hop-by-Hop yet
+	 */
+	if (skb->dev || ipv6_hdr(skb)->nexthdr == NEXTHDR_HOP)
+		goto out;
+
+	err = ioam6_do_inline(skb, ioam6_lwt_info(lwt));
+	if (unlikely(err))
+		goto drop;
+
+	err = skb_cow_head(skb, LL_RESERVED_SPACE(skb_dst(skb)->dev));
+	if (unlikely(err))
+		goto drop;
+
+out:
+	return lwt->orig_output(net, sk, skb);
+
+drop:
+	kfree_skb(skb);
+	return err;
+}
+
+static int ioam6_fill_encap_info(struct sk_buff *skb,
+				 struct lwtunnel_state *lwtstate)
+{
+	struct ioam6_trace_hdr *trace = ioam6_trace(lwtstate);
+
+	if (nla_put_ioam6_trace(skb, IOAM6_IPTUNNEL_TRACE, trace))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int ioam6_encap_nlsize(struct lwtunnel_state *lwtstate)
+{
+	struct ioam6_trace_hdr *trace = ioam6_trace(lwtstate);
+
+	return nla_total_size(sizeof(*trace));
+}
+
+static int ioam6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
+{
+	struct ioam6_trace_hdr *a_hdr = ioam6_trace(a);
+	struct ioam6_trace_hdr *b_hdr = ioam6_trace(b);
+
+	return (a_hdr->namespace_id != b_hdr->namespace_id);
+}
+
+static const struct lwtunnel_encap_ops ioam6_iptun_ops = {
+	.build_state	= ioam6_build_state,
+	.output		= ioam6_output,
+	.fill_encap	= ioam6_fill_encap_info,
+	.get_encap_size	= ioam6_encap_nlsize,
+	.cmp_encap	= ioam6_encap_cmp,
+	.owner		= THIS_MODULE,
+};
+
+int __init ioam6_iptunnel_init(void)
+{
+	return lwtunnel_encap_add_ops(&ioam6_iptun_ops, LWTUNNEL_ENCAP_IOAM6);
+}
+
+void ioam6_iptunnel_exit(void)
+{
+	lwtunnel_encap_del_ops(&ioam6_iptun_ops, LWTUNNEL_ENCAP_IOAM6);
+}

net/ipv6/sysctl_net_ipv6.c

@@ -21,6 +21,7 @@
 #ifdef CONFIG_NETLABEL
 #include <net/calipso.h>
 #endif
+#include <linux/ioam6.h>
 
 static int two = 2;
 static int three = 3;
@@ -28,6 +29,8 @@ static int flowlabel_reflect_max = 0x7;
 static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX;
 static u32 rt6_multipath_hash_fields_all_mask =
 	FIB_MULTIPATH_HASH_FIELD_ALL_MASK;
+static u32 ioam6_id_max = IOAM6_DEFAULT_ID;
+static u64 ioam6_id_wide_max = IOAM6_DEFAULT_ID_WIDE;
 
 static int proc_rt6_multipath_hash_policy(struct ctl_table *table, int write,
 					  void *buffer, size_t *lenp, loff_t *ppos)
@@ -196,6 +199,22 @@ static struct ctl_table ipv6_table_template[] = {
 		.extra1         = SYSCTL_ZERO,
 		.extra2         = &two,
 	},
+	{
+		.procname	= "ioam6_id",
+		.data		= &init_net.ipv6.sysctl.ioam6_id,
+		.maxlen		= sizeof(u32),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec_minmax,
+		.extra2		= &ioam6_id_max,
+	},
+	{
+		.procname	= "ioam6_id_wide",
+		.data		= &init_net.ipv6.sysctl.ioam6_id_wide,
+		.maxlen		= sizeof(u64),
+		.mode		= 0644,
+		.proc_handler	= proc_doulongvec_minmax,
+		.extra2		= &ioam6_id_wide_max,
+	},
 	{ }
 };
 

tools/testing/selftests/net/Makefile

@@ -25,6 +25,7 @@ TEST_PROGS += bareudp.sh
 TEST_PROGS += unicast_extensions.sh
 TEST_PROGS += udpgro_fwd.sh
 TEST_PROGS += veth.sh
+TEST_PROGS += ioam6.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
@@ -36,6 +37,7 @@ TEST_GEN_FILES += fin_ack_lat
 TEST_GEN_FILES += reuseaddr_ports_exhausted
 TEST_GEN_FILES += hwtstamp_config rxtimestamp timestamping txtimestamp
 TEST_GEN_FILES += ipsec
+TEST_GEN_FILES += ioam6_parser
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
 TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
 

tools/testing/selftests/net/config

@@ -42,3 +42,4 @@ CONFIG_NET_CLS_FLOWER=m
 CONFIG_NET_ACT_TUNNEL_KEY=m
 CONFIG_NET_ACT_MIRRED=m
 CONFIG_BAREUDP=m
+CONFIG_IPV6_IOAM6_LWTUNNEL=y

tools/testing/selftests/net/ioam6.sh

+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Author: Justin Iurman <justin.iurman@uliege.be>
+#
+# This test evaluates the IOAM insertion for IPv6 by checking the IOAM data
+# integrity on the receiver.
+#
+# The topology is formed by 3 nodes: Alpha (sender), Beta (router in-between)
+# and Gamma (receiver). An IOAM domain is configured from Alpha to Gamma only,
+# which means not on the reverse path. When Gamma is the destination, Alpha
+# adds an IOAM option (Pre-allocated Trace) inside a Hop-by-hop and fills the
+# trace with its own IOAM data. Beta and Gamma also fill the trace. The IOAM
+# data integrity is checked on Gamma, by comparing with the pre-defined IOAM
+# configuration (see below).
+#
+#     +-------------------+            +-------------------+
+#     |                   |            |                   |
+#     |    alpha netns    |            |    gamma netns    |
+#     |                   |            |                   |
+#     |  +-------------+  |            |  +-------------+  |
+#     |  |    veth0    |  |            |  |    veth0    |  |
+#     |  |  db01::2/64 |  |            |  |  db02::2/64 |  |
+#     |  +-------------+  |            |  +-------------+  |
+#     |         .         |            |         .         |
+#     +-------------------+            +-------------------+
+#               .                                .
+#               .                                .
+#               .                                .
+#     +----------------------------------------------------+
+#     |         .                                .         |
+#     |  +-------------+                  +-------------+  |
+#     |  |    veth0    |                  |    veth1    |  |
+#     |  |  db01::1/64 | ................ |  db02::1/64 |  |
+#     |  +-------------+                  +-------------+  |
+#     |                                                    |
+#     |                      beta netns                    |
+#     |                                                    |
+#     +--------------------------+-------------------------+
+#
+#
+# ~~~~~~~~~~~~~~~~~~~~~~
+# | IOAM configuration |
+# ~~~~~~~~~~~~~~~~~~~~~~
+#
+# Alpha
+# +-----------------------------------------------------------+
+# | Type                | Value                               |
+# +-----------------------------------------------------------+
+# | Node ID             | 1                                   |
+# +-----------------------------------------------------------+
+# | Node Wide ID        | 11111111                            |
+# +-----------------------------------------------------------+
+# | Ingress ID          | 0xffff (default value)              |
+# +-----------------------------------------------------------+
+# | Ingress Wide ID     | 0xffffffff (default value)          |
+# +-----------------------------------------------------------+
+# | Egress ID           | 101                                 |
+# +-----------------------------------------------------------+
+# | Egress Wide ID      | 101101                              |
+# +-----------------------------------------------------------+
+# | Namespace Data      | 0xdeadbee0                          |
+# +-----------------------------------------------------------+
+# | Namespace Wide Data | 0xcafec0caf00dc0de                  |
+# +-----------------------------------------------------------+
+# | Schema ID           | 777                                 |
+# +-----------------------------------------------------------+
+# | Schema Data         | something that will be 4n-aligned   |
+# +-----------------------------------------------------------+
+#
+# Note: When Gamma is the destination, Alpha adds an IOAM Pre-allocated Trace
+#       option inside a Hop-by-hop, where 164 bytes are pre-allocated for the
+#       trace, with 123 as the IOAM-Namespace and with 0xfff00200 as the trace
+#       type (= all available options at this time). As a result, and based on
+#       IOAM configurations here, only both Alpha and Beta should be capable of
+#       inserting their IOAM data while Gamma won't have enough space and will
+#       set the overflow bit.
+#
+# Beta
+# +-----------------------------------------------------------+
+# | Type                | Value                               |
+# +-----------------------------------------------------------+
+# | Node ID             | 2                                   |
+# +-----------------------------------------------------------+
+# | Node Wide ID        | 22222222                            |
+# +-----------------------------------------------------------+
+# | Ingress ID          | 201                                 |
+# +-----------------------------------------------------------+
+# | Ingress Wide ID     | 201201                              |
+# +-----------------------------------------------------------+
+# | Egress ID           | 202                                 |
+# +-----------------------------------------------------------+
+# | Egress Wide ID      | 202202                              |
+# +-----------------------------------------------------------+
+# | Namespace Data      | 0xdeadbee1                          |
+# +-----------------------------------------------------------+
+# | Namespace Wide Data | 0xcafec0caf11dc0de                  |
+# +-----------------------------------------------------------+
+# | Schema ID           | 0xffffff (= None)                   |
+# +-----------------------------------------------------------+
+# | Schema Data         |                                     |
+# +-----------------------------------------------------------+
+#
+# Gamma
+# +-----------------------------------------------------------+
+# | Type                | Value                               |
+# +-----------------------------------------------------------+
+# | Node ID             | 3                                   |
+# +-----------------------------------------------------------+
+# | Node Wide ID        | 33333333                            |
+# +-----------------------------------------------------------+
+# | Ingress ID          | 301                                 |
+# +-----------------------------------------------------------+
+# | Ingress Wide ID     | 301301                              |
+# +-----------------------------------------------------------+
+# | Egress ID           | 0xffff (default value)              |
+# +-----------------------------------------------------------+
+# | Egress Wide ID      | 0xffffffff (default value)          |
+# +-----------------------------------------------------------+
+# | Namespace Data      | 0xdeadbee2                          |
+# +-----------------------------------------------------------+
+# | Namespace Wide Data | 0xcafec0caf22dc0de                  |
+# +-----------------------------------------------------------+
+# | Schema ID           | 0xffffff (= None)                   |
+# +-----------------------------------------------------------+
+# | Schema Data         |                                     |
+# +-----------------------------------------------------------+
+
+#===============================================================================
+#
+# WARNING:
+# Do NOT modify the following configuration unless you know what you're doing.
+#
+IOAM_NAMESPACE=123
+IOAM_TRACE_TYPE=0xfff00200
+IOAM_PREALLOC_DATA_SIZE=164
+
+ALPHA=(
+	1					# ID
+	11111111				# Wide ID
+	0xffff					# Ingress ID
+	0xffffffff				# Ingress Wide ID
+	101					# Egress ID
+	101101					# Egress Wide ID
+	0xdeadbee0				# Namespace Data
+	0xcafec0caf00dc0de			# Namespace Wide Data
+	777					# Schema ID (0xffffff = None)
+	"something that will be 4n-aligned"	# Schema Data
+)
+
+BETA=(
+	2
+	22222222
+	201
+	201201
+	202
+	202202
+	0xdeadbee1
+	0xcafec0caf11dc0de
+	0xffffff
+	""
+)
+
+GAMMA=(
+	3
+	33333333
+	301
+	301301
+	0xffff
+	0xffffffff
+	0xdeadbee2
+	0xcafec0caf22dc0de
+	0xffffff
+	""
+)
+#===============================================================================
+
+if [ "$(id -u)" -ne 0 ]; then
+  echo "SKIP: Need root privileges"
+  exit 1
+fi
+
+if [ ! -x "$(command -v ip)" ]; then
+  echo "SKIP: Could not run test without ip tool"
+  exit 1
+fi
+
+ip ioam &>/dev/null
+if [ $? = 1 ]; then
+  echo "SKIP: ip tool must include IOAM"
+  exit 1
+fi
+
+if [ ! -e /proc/sys/net/ipv6/ioam6_id ]; then
+  echo "SKIP: ioam6 sysctls do not exist"
+  exit 1
+fi
+
+cleanup()
+{
+  ip link del ioam-veth-alpha 2>/dev/null || true
+  ip link del ioam-veth-gamma 2>/dev/null || true
+
+  ip netns del ioam-node-alpha || true
+  ip netns del ioam-node-beta || true
+  ip netns del ioam-node-gamma || true
+}
+
+setup()
+{
+  ip netns add ioam-node-alpha
+  ip netns add ioam-node-beta
+  ip netns add ioam-node-gamma
+
+  ip link add name ioam-veth-alpha type veth peer name ioam-veth-betaL
+  ip link add name ioam-veth-betaR type veth peer name ioam-veth-gamma
+
+  ip link set ioam-veth-alpha netns ioam-node-alpha
+  ip link set ioam-veth-betaL netns ioam-node-beta
+  ip link set ioam-veth-betaR netns ioam-node-beta
+  ip link set ioam-veth-gamma netns ioam-node-gamma
+
+  ip -netns ioam-node-alpha link set ioam-veth-alpha name veth0
+  ip -netns ioam-node-beta link set ioam-veth-betaL name veth0
+  ip -netns ioam-node-beta link set ioam-veth-betaR name veth1
+  ip -netns ioam-node-gamma link set ioam-veth-gamma name veth0
+
+  ip -netns ioam-node-alpha addr add db01::2/64 dev veth0
+  ip -netns ioam-node-alpha link set veth0 up
+  ip -netns ioam-node-alpha link set lo up
+  ip -netns ioam-node-alpha route add default via db01::1
+
+  ip -netns ioam-node-beta addr add db01::1/64 dev veth0
+  ip -netns ioam-node-beta addr add db02::1/64 dev veth1
+  ip -netns ioam-node-beta link set veth0 up
+  ip -netns ioam-node-beta link set veth1 up
+  ip -netns ioam-node-beta link set lo up
+
+  ip -netns ioam-node-gamma addr add db02::2/64 dev veth0
+  ip -netns ioam-node-gamma link set veth0 up
+  ip -netns ioam-node-gamma link set lo up
+  ip -netns ioam-node-gamma route add default via db02::1
+
+  # - IOAM config -
+  ip netns exec ioam-node-alpha sysctl -wq net.ipv6.ioam6_id=${ALPHA[0]}
+  ip netns exec ioam-node-alpha sysctl -wq net.ipv6.ioam6_id_wide=${ALPHA[1]}
+  ip netns exec ioam-node-alpha sysctl -wq net.ipv6.conf.veth0.ioam6_id=${ALPHA[4]}
+  ip netns exec ioam-node-alpha sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${ALPHA[5]}
+  ip -netns ioam-node-alpha ioam namespace add ${IOAM_NAMESPACE} data ${ALPHA[6]} wide ${ALPHA[7]}
+  ip -netns ioam-node-alpha ioam schema add ${ALPHA[8]} "${ALPHA[9]}"
+  ip -netns ioam-node-alpha ioam namespace set ${IOAM_NAMESPACE} schema ${ALPHA[8]}
+  ip -netns ioam-node-alpha route add db02::/64 encap ioam6 trace type ${IOAM_TRACE_TYPE:0:-2} ns ${IOAM_NAMESPACE} size ${IOAM_PREALLOC_DATA_SIZE} via db01::1 dev veth0
+
+  ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.all.forwarding=1
+  ip netns exec ioam-node-beta sysctl -wq net.ipv6.ioam6_id=${BETA[0]}
+  ip netns exec ioam-node-beta sysctl -wq net.ipv6.ioam6_id_wide=${BETA[1]}
+  ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1
+  ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth0.ioam6_id=${BETA[2]}
+  ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${BETA[3]}
+  ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth1.ioam6_id=${BETA[4]}
+  ip netns exec ioam-node-beta sysctl -wq net.ipv6.conf.veth1.ioam6_id_wide=${BETA[5]}
+  ip -netns ioam-node-beta ioam namespace add ${IOAM_NAMESPACE} data ${BETA[6]} wide ${BETA[7]}
+
+  ip netns exec ioam-node-gamma sysctl -wq net.ipv6.ioam6_id=${GAMMA[0]}
+  ip netns exec ioam-node-gamma sysctl -wq net.ipv6.ioam6_id_wide=${GAMMA[1]}
+  ip netns exec ioam-node-gamma sysctl -wq net.ipv6.conf.veth0.ioam6_enabled=1
+  ip netns exec ioam-node-gamma sysctl -wq net.ipv6.conf.veth0.ioam6_id=${GAMMA[2]}
+  ip netns exec ioam-node-gamma sysctl -wq net.ipv6.conf.veth0.ioam6_id_wide=${GAMMA[3]}
+  ip -netns ioam-node-gamma ioam namespace add ${IOAM_NAMESPACE} data ${GAMMA[6]} wide ${GAMMA[7]}
+}
+
+run()
+{
+  echo -n "IOAM test... "
+
+  ip netns exec ioam-node-alpha ping6 -c 5 -W 1 db02::2 &>/dev/null
+  if [ $? != 0 ]; then
+    echo "FAILED"
+    cleanup &>/dev/null
+    exit 0
+  fi
+
+  ip netns exec ioam-node-gamma ./ioam6_parser veth0 2 ${IOAM_NAMESPACE} ${IOAM_TRACE_TYPE} 64 ${ALPHA[0]} ${ALPHA[1]} ${ALPHA[2]} ${ALPHA[3]} ${ALPHA[4]} ${ALPHA[5]} ${ALPHA[6]} ${ALPHA[7]} ${ALPHA[8]} "${ALPHA[9]}" 63 ${BETA[0]} ${BETA[1]} ${BETA[2]} ${BETA[3]} ${BETA[4]} ${BETA[5]} ${BETA[6]} ${BETA[7]} ${BETA[8]} &
+
+  local spid=$!
+  sleep 0.1
+
+  ip netns exec ioam-node-alpha ping6 -c 5 -W 1 db02::2 &>/dev/null
+
+  wait $spid
+  [ $? = 0 ] && echo "PASSED" || echo "FAILED"
+}
+
+cleanup &>/dev/null
+setup
+run
+cleanup &>/dev/null

tools/testing/selftests/net/ioam6_parser.c

+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Author: Justin Iurman (justin.iurman@uliege.be)
+ *
+ * IOAM parser for IPv6, see ioam6.sh for details.
+ */
+#include <asm/byteorder.h>
+#include <linux/const.h>
+#include <linux/if_ether.h>
+#include <linux/ioam6.h>
+#include <linux/ipv6.h>
+#include <sys/socket.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+struct node_args {
+	__u32 id;
+	__u64 wide;
+	__u16 ingr_id;
+	__u16 egr_id;
+	__u32 ingr_wide;
+	__u32 egr_wide;
+	__u32 ns_data;
+	__u64 ns_wide;
+	__u32 sc_id;
+	__u8 hop_limit;
+	__u8 *sc_data; /* NULL when sc_id = 0xffffff (default empty value) */
+};
+
+/* expected args per node, in that order */
+enum {
+	NODE_ARG_HOP_LIMIT,
+	NODE_ARG_ID,
+	NODE_ARG_WIDE,
+	NODE_ARG_INGR_ID,
+	NODE_ARG_INGR_WIDE,
+	NODE_ARG_EGR_ID,
+	NODE_ARG_EGR_WIDE,
+	NODE_ARG_NS_DATA,
+	NODE_ARG_NS_WIDE,
+	NODE_ARG_SC_ID,
+	__NODE_ARG_MAX,
+};
+
+#define NODE_ARGS_SIZE __NODE_ARG_MAX
+
+struct args {
+	__u16 ns_id;
+	__u32 trace_type;
+	__u8 n_node;
+	__u8 *ifname;
+	struct node_args node[0];
+};
+
+/* expected args, in that order */
+enum {
+	ARG_IFNAME,
+	ARG_N_NODE,
+	ARG_NS_ID,
+	ARG_TRACE_TYPE,
+	__ARG_MAX,
+};
+
+#define ARGS_SIZE __ARG_MAX
+
+int check_ioam6_node_data(__u8 **p, struct ioam6_trace_hdr *trace, __u8 hlim,
+			  __u32 id, __u64 wide, __u16 ingr_id, __u32 ingr_wide,
+			  __u16 egr_id, __u32 egr_wide, __u32 ns_data,
+			  __u64 ns_wide, __u32 sc_id, __u8 *sc_data)
+{
+	__u64 raw64;
+	__u32 raw32;
+	__u8 sc_len;
+
+	if (trace->type.bit0) {
+		raw32 = __be32_to_cpu(*((__u32 *)*p));
+		if (hlim != (raw32 >> 24) || id != (raw32 & 0xffffff))
+			return 1;
+		*p += sizeof(__u32);
+	}
+
+	if (trace->type.bit1) {
+		raw32 = __be32_to_cpu(*((__u32 *)*p));
+		if (ingr_id != (raw32 >> 16) || egr_id != (raw32 & 0xffff))
+			return 1;
+		*p += sizeof(__u32);
+	}
+
+	if (trace->type.bit2)
+		*p += sizeof(__u32);
+
+	if (trace->type.bit3)
+		*p += sizeof(__u32);
+
+	if (trace->type.bit4) {
+		if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
+			return 1;
+		*p += sizeof(__u32);
+	}
+
+	if (trace->type.bit5) {
+		if (__be32_to_cpu(*((__u32 *)*p)) != ns_data)
+			return 1;
+		*p += sizeof(__u32);
+	}
+
+	if (trace->type.bit6) {
+		if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
+			return 1;
+		*p += sizeof(__u32);
+	}
+
+	if (trace->type.bit7) {
+		if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
+			return 1;
+		*p += sizeof(__u32);
+	}
+
+	if (trace->type.bit8) {
+		raw64 = __be64_to_cpu(*((__u64 *)*p));
+		if (hlim != (raw64 >> 56) || wide != (raw64 & 0xffffffffffffff))
+			return 1;
+		*p += sizeof(__u64);
+	}
+
+	if (trace->type.bit9) {
+		if (__be32_to_cpu(*((__u32 *)*p)) != ingr_wide)
+			return 1;
+		*p += sizeof(__u32);
+
+		if (__be32_to_cpu(*((__u32 *)*p)) != egr_wide)
+			return 1;
+		*p += sizeof(__u32);
+	}
+
+	if (trace->type.bit10) {
+		if (__be64_to_cpu(*((__u64 *)*p)) != ns_wide)
+			return 1;
+		*p += sizeof(__u64);
+	}
+
+	if (trace->type.bit11) {
+		if (__be32_to_cpu(*((__u32 *)*p)) != 0xffffffff)
+			return 1;
+		*p += sizeof(__u32);
+	}
+
+	if (trace->type.bit22) {
+		raw32 = __be32_to_cpu(*((__u32 *)*p));
+		sc_len = sc_data ? __ALIGN_KERNEL(strlen(sc_data), 4) : 0;
+		if (sc_len != (raw32 >> 24) * 4 || sc_id != (raw32 & 0xffffff))
+			return 1;
+		*p += sizeof(__u32);
+
+		if (sc_data) {
+			if (strncmp(*p, sc_data, strlen(sc_data)))
+				return 1;
+
+			*p += strlen(sc_data);
+			sc_len -= strlen(sc_data);
+
+			while (sc_len--) {
+				if (**p != '\0')
+					return 1;
+				*p += sizeof(__u8);
+			}
+		}
+	}
+
+	return 0;
+}
+
+int check_ioam6_trace(struct ioam6_trace_hdr *trace, struct args *args)
+{
+	__u8 *p;
+	int i;
+
+	if (__be16_to_cpu(trace->namespace_id) != args->ns_id ||
+	    __be32_to_cpu(trace->type_be32) != args->trace_type)
+		return 1;
+
+	p = trace->data + trace->remlen * 4;
+
+	for (i = args->n_node - 1; i >= 0; i--) {
+		if (check_ioam6_node_data(&p, trace,
+					  args->node[i].hop_limit,
+					  args->node[i].id,
+					  args->node[i].wide,
+					  args->node[i].ingr_id,
+					  args->node[i].ingr_wide,
+					  args->node[i].egr_id,
+					  args->node[i].egr_wide,
+					  args->node[i].ns_data,
+					  args->node[i].ns_wide,
+					  args->node[i].sc_id,
+					  args->node[i].sc_data))
+			return 1;
+	}
+
+	return 0;
+}
+
+int parse_node_args(int *argcp, char ***argvp, struct node_args *node)
+{
+	char **argv = *argvp;
+
+	if (*argcp < NODE_ARGS_SIZE)
+		return 1;
+
+	node->hop_limit = strtoul(argv[NODE_ARG_HOP_LIMIT], NULL, 10);
+	if (!node->hop_limit) {
+		node->hop_limit = strtoul(argv[NODE_ARG_HOP_LIMIT], NULL, 16);
+		if (!node->hop_limit)
+			return 1;
+	}
+
+	node->id = strtoul(argv[NODE_ARG_ID], NULL, 10);
+	if (!node->id) {
+		node->id = strtoul(argv[NODE_ARG_ID], NULL, 16);
+		if (!node->id)
+			return 1;
+	}
+
+	node->wide = strtoull(argv[NODE_ARG_WIDE], NULL, 10);
+	if (!node->wide) {
+		node->wide = strtoull(argv[NODE_ARG_WIDE], NULL, 16);
+		if (!node->wide)
+			return 1;
+	}
+
+	node->ingr_id = strtoul(argv[NODE_ARG_INGR_ID], NULL, 10);
+	if (!node->ingr_id) {
+		node->ingr_id = strtoul(argv[NODE_ARG_INGR_ID], NULL, 16);
+		if (!node->ingr_id)
+			return 1;
+	}
+
+	node->ingr_wide = strtoul(argv[NODE_ARG_INGR_WIDE], NULL, 10);
+	if (!node->ingr_wide) {
+		node->ingr_wide = strtoul(argv[NODE_ARG_INGR_WIDE], NULL, 16);
+		if (!node->ingr_wide)
+			return 1;
+	}
+
+	node->egr_id = strtoul(argv[NODE_ARG_EGR_ID], NULL, 10);
+	if (!node->egr_id) {
+		node->egr_id = strtoul(argv[NODE_ARG_EGR_ID], NULL, 16);
+		if (!node->egr_id)
+			return 1;
+	}
+
+	node->egr_wide = strtoul(argv[NODE_ARG_EGR_WIDE], NULL, 10);
+	if (!node->egr_wide) {
+		node->egr_wide = strtoul(argv[NODE_ARG_EGR_WIDE], NULL, 16);
+		if (!node->egr_wide)
+			return 1;
+	}
+
+	node->ns_data = strtoul(argv[NODE_ARG_NS_DATA], NULL, 16);
+	if (!node->ns_data)
+		return 1;
+
+	node->ns_wide = strtoull(argv[NODE_ARG_NS_WIDE], NULL, 16);
+	if (!node->ns_wide)
+		return 1;
+
+	node->sc_id = strtoul(argv[NODE_ARG_SC_ID], NULL, 10);
+	if (!node->sc_id) {
+		node->sc_id = strtoul(argv[NODE_ARG_SC_ID], NULL, 16);
+		if (!node->sc_id)
+			return 1;
+	}
+
+	*argcp -= NODE_ARGS_SIZE;
+	*argvp += NODE_ARGS_SIZE;
+
+	if (node->sc_id != 0xffffff) {
+		if (!*argcp)
+			return 1;
+
+		node->sc_data = argv[NODE_ARG_SC_ID + 1];
+
+		*argcp -= 1;
+		*argvp += 1;
+	}
+
+	return 0;
+}
+
+struct args *parse_args(int argc, char **argv)
+{
+	struct args *args;
+	int n_node, i;
+
+	if (argc < ARGS_SIZE)
+		goto out;
+
+	n_node = strtoul(argv[ARG_N_NODE], NULL, 10);
+	if (!n_node || n_node > 10)
+		goto out;
+
+	args = calloc(1, sizeof(*args) + n_node * sizeof(struct node_args));
+	if (!args)
+		goto out;
+
+	args->ns_id = strtoul(argv[ARG_NS_ID], NULL, 10);
+	if (!args->ns_id)
+		goto free;
+
+	args->trace_type = strtoul(argv[ARG_TRACE_TYPE], NULL, 16);
+	if (!args->trace_type)
+		goto free;
+
+	args->n_node = n_node;
+	args->ifname = argv[ARG_IFNAME];
+
+	argv += ARGS_SIZE;
+	argc -= ARGS_SIZE;
+
+	for (i = 0; i < n_node; i++) {
+		if (parse_node_args(&argc, &argv, &args->node[i]))
+			goto free;
+	}
+
+	if (argc)
+		goto free;
+
+	return args;
+free:
+	free(args);
+out:
+	return NULL;
+}
+
+int main(int argc, char **argv)
+{
+	int ret, fd, pkts, size, hoplen, found;
+	struct ioam6_trace_hdr *ioam6h;
+	struct ioam6_hdr *opt;
+	struct ipv6hdr *ip6h;
+	__u8 buffer[400], *p;
+	struct args *args;
+
+	args = parse_args(argc - 1, argv + 1);
+	if (!args) {
+		ret = 1;
+		goto out;
+	}
+
+	fd = socket(AF_PACKET, SOCK_DGRAM, __cpu_to_be16(ETH_P_IPV6));
+	if (!fd) {
+		ret = 1;
+		goto out;
+	}
+
+	if (setsockopt(fd, SOL_SOCKET, SO_BINDTODEVICE,
+		       args->ifname, strlen(args->ifname))) {
+		ret = 1;
+		goto close;
+	}
+
+	pkts = 0;
+	found = 0;
+	while (pkts < 3 && !found) {
+		size = recv(fd, buffer, sizeof(buffer), 0);
+		ip6h = (struct ipv6hdr *)buffer;
+		pkts++;
+
+		if (ip6h->nexthdr == IPPROTO_HOPOPTS) {
+			p = buffer + sizeof(*ip6h);
+			hoplen = (p[1] + 1) << 3;
+
+			p += sizeof(struct ipv6_hopopt_hdr);
+			while (hoplen > 0) {
+				opt = (struct ioam6_hdr *)p;
+
+				if (opt->opt_type == IPV6_TLV_IOAM &&
+				    opt->type == IOAM6_TYPE_PREALLOC) {
+					found = 1;
+
+					p += sizeof(*opt);
+					ioam6h = (struct ioam6_trace_hdr *)p;
+
+					ret = check_ioam6_trace(ioam6h, args);
+					break;
+				}
+
+				p += opt->opt_len + 2;
+				hoplen -= opt->opt_len + 2;
+			}
+		}
+	}
+
+	if (!found)
+		ret = 1;
+close:
+	close(fd);
+out:
+	free(args);
+	return ret;
+}