[PATCH iproute2 1/3] ip: add support of netconf messages

@@ -8,6 +8,7 @@
 #include <linux/if_link.h>
 #include <linux/if_addr.h>
 #include <linux/neighbour.h>
+#include <linux/netconf.h>
 
 struct rtnl_handle
 {

@@ -0,0 +1,24 @@
+#ifndef _UAPI_LINUX_NETCONF_H_
+#define _UAPI_LINUX_NETCONF_H_
+
+#include <linux/types.h>
+#include <linux/netlink.h>
+
+struct netconfmsg {
+	__u8	ncm_family;
+};
+
+enum {
+	NETCONFA_UNSPEC,
+	NETCONFA_IFINDEX,
+	NETCONFA_FORWARDING,
+	NETCONFA_RP_FILTER,
+	NETCONFA_MC_FORWARDING,
+	__NETCONFA_MAX
+};
+#define NETCONFA_MAX	(__NETCONFA_MAX - 1)
+
+#define NETCONFA_IFINDEX_ALL		-1
+#define NETCONFA_IFINDEX_DEFAULT	-2
+
+#endif /* _UAPI_LINUX_NETCONF_H_ */

@@ -120,6 +120,11 @@ enum {
 	RTM_SETDCB,
 #define RTM_SETDCB RTM_SETDCB
 
+	RTM_NEWNETCONF = 80,
+#define RTM_NEWNETCONF RTM_NEWNETCONF
+	RTM_GETNETCONF = 82,
+#define RTM_GETNETCONF RTM_GETNETCONF
+
 	__RTM_MAX,
 #define RTM_MAX		(((__RTM_MAX + 3) & ~3) - 1)
 };

@@ -585,6 +590,10 @@ enum rtnetlink_groups {
 #define RTNLGRP_PHONET_ROUTE	RTNLGRP_PHONET_ROUTE
 	RTNLGRP_DCB,
 #define RTNLGRP_DCB		RTNLGRP_DCB
+	RTNLGRP_IPV4_NETCONF,
+#define RTNLGRP_IPV4_NETCONF	RTNLGRP_IPV4_NETCONF
+	RTNLGRP_IPV6_NETCONF,
+#define RTNLGRP_IPV6_NETCONF	RTNLGRP_IPV6_NETCONF
 	__RTNLGRP_MAX
 };
 #define RTNLGRP_MAX	(__RTNLGRP_MAX - 1)

@@ -4,7 +4,7 @@ IPOBJ=ip.o ipaddress.o ipaddrlabel.o iproute.o iprule.o ipnetns.o \
     ipxfrm.o xfrm_state.o xfrm_policy.o xfrm_monitor.o \
     iplink_vlan.o link_veth.o link_gre.o iplink_can.o \
     iplink_macvlan.o iplink_macvtap.o ipl2tp.o link_vti.o \
-    iplink_vxlan.o tcp_metrics.o iplink_ipoib.o
+    iplink_vxlan.o tcp_metrics.o iplink_ipoib.o ipnetconf.o
 
 RTMONOBJ=rtmon.o
 

@@ -85,6 +85,7 @@ static const struct cmd {
 	{ "mroute",	do_multiroute },
 	{ "mrule",	do_multirule },
 	{ "netns",	do_netns },
+	{ "netconf",	do_ipnetconf },
 	{ "help",	do_help },
 	{ 0 }
 };

@@ -25,6 +25,8 @@ extern int print_prefix(const struct sockaddr_nl *who,
 			struct nlmsghdr *n, void *arg);
 extern int print_rule(const struct sockaddr_nl *who,
 		      struct nlmsghdr *n, void *arg);
+extern int print_netconf(const struct sockaddr_nl *who,
+			 struct nlmsghdr *n, void *arg);
 extern int do_ipaddr(int argc, char **argv);
 extern int do_ipaddrlabel(int argc, char **argv);
 extern int do_iproute(int argc, char **argv);

@@ -43,6 +45,7 @@ extern int do_netns(int argc, char **argv);
 extern int do_xfrm(int argc, char **argv);
 extern int do_ipl2tp(int argc, char **argv);
 extern int do_tcp_metrics(int argc, char **argv);
+extern int do_ipnetconf(int argc, char **argv);
 
 static inline int rtm_get_table(struct rtmsg *r, struct rtattr **tb)
 {

@@ -85,6 +85,12 @@ int accept_msg(const struct sockaddr_nl *who,
 		print_rule(who, n, arg);
 		return 0;
 	}
+	if (n->nlmsg_type == RTM_NEWNETCONF) {
+		if (prefix_banner)
+			fprintf(fp, "[NETCONF]");
+		print_netconf(who, n, arg);
+		return 0;
+	}
 	if (n->nlmsg_type == 15) {
 		char *tstr;
 		time_t secs = ((__u32*)NLMSG_DATA(n))[0];

@@ -118,6 +124,7 @@ int do_ipmonitor(int argc, char **argv)
 	int lroute=0;
 	int lprefix=0;
 	int lneigh=0;
+	int lnetconf=0;
 
 	rtnl_close(&rth);
 	ipaddr_reset_filter(1);

@@ -143,6 +150,9 @@ int do_ipmonitor(int argc, char **argv)
 		} else if (matches(*argv, "neigh") == 0) {
 			lneigh = 1;
 			groups = 0;
+		} else if (matches(*argv, "netconf") == 0) {
+			lnetconf = 1;
+			groups = 0;
 		} else if (strcmp(*argv, "all") == 0) {
 			groups = ~RTMGRP_TC;
 			prefix_banner=1;

@@ -176,6 +186,12 @@ int do_ipmonitor(int argc, char **argv)
 	if (lneigh) {
 		groups |= nl_mgrp(RTNLGRP_NEIGH);
 	}
+	if (lnetconf) {
+		if (!preferred_family || preferred_family == AF_INET)
+			groups |= nl_mgrp(RTNLGRP_IPV4_NETCONF);
+		if (!preferred_family || preferred_family == AF_INET6)
+			groups |= nl_mgrp(RTNLGRP_IPV6_NETCONF);
+	}
 	if (file) {
 		FILE *fp;
 		fp = fopen(file, "r");

@@ -0,0 +1,183 @@
+/*
+ * ipnetconf.c		"ip netconf".
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ *
+ * Authors:	Nicolas Dichtel, <nicolas.dichtel@6wind.com>
+ *
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <string.h>
+#include <sys/time.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+
+static struct
+{
+	int family;
+	int ifindex;
+} filter;
+
+static void usage(void) __attribute__((noreturn));
+
+static void usage(void)
+{
+	fprintf(stderr, "Usage: ip netconf show [ dev STRING ]\n");
+	exit(-1);
+}
+
+#define NETCONF_RTA(r)	((struct rtattr*)(((char*)(r)) + NLMSG_ALIGN(sizeof(struct netconfmsg))))
+
+int print_netconf(const struct sockaddr_nl *who, struct nlmsghdr *n, void *arg)
+{
+	FILE *fp = (FILE*)arg;
+	struct netconfmsg *ncm = NLMSG_DATA(n);
+	int len = n->nlmsg_len;
+	struct rtattr *tb[NETCONFA_MAX+1];
+
+	if (n->nlmsg_type == NLMSG_ERROR)
+		return -1;
+	if (n->nlmsg_type != RTM_NEWNETCONF) {
+		fprintf(stderr, "Not RTM_NEWNETCONF: %08x %08x %08x\n",
+			n->nlmsg_len, n->nlmsg_type, n->nlmsg_flags);
+
+		return -1;
+	}
+	len -= NLMSG_SPACE(sizeof(*ncm));
+	if (len < 0) {
+		fprintf(stderr, "BUG: wrong nlmsg len %d\n", len);
+		return -1;
+	}
+
+	if (filter.family && filter.family != ncm->ncm_family)
+		return 0;
+
+	parse_rtattr(tb, NETCONFA_MAX, NETCONF_RTA(ncm),
+		     NLMSG_PAYLOAD(n, sizeof(*ncm)));
+
+	switch (ncm->ncm_family) {
+	case AF_INET:
+		fprintf(fp, "ipv4 ");
+		break;
+	case AF_INET6:
+		fprintf(fp, "ipv6 ");
+		break;
+	default:
+		fprintf(fp, "unknown ");
+		break;
+	}
+
+	if (tb[NETCONFA_IFINDEX]) {
+		int *ifindex = (int *)RTA_DATA(tb[NETCONFA_IFINDEX]);
+
+		switch (*ifindex) {
+		case NETCONFA_IFINDEX_ALL:
+			fprintf(fp, "all ");
+			break;
+		case NETCONFA_IFINDEX_DEFAULT:
+			fprintf(fp, "default ");
+			break;
+		default:
+			fprintf(fp, "dev %s ", ll_index_to_name(*ifindex));
+			break;
+		}
+	}
+
+	if (tb[NETCONFA_FORWARDING])
+		fprintf(fp, "forwarding %s ",
+			*(int *)RTA_DATA(tb[NETCONFA_FORWARDING])?"on":"off");
+	if (tb[NETCONFA_RP_FILTER]) {
+		int rp_filter = *(int *)RTA_DATA(tb[NETCONFA_RP_FILTER]);
+
+		if (rp_filter == 0)
+			fprintf(fp, "rp_filter off ");
+		else if (rp_filter == 1)
+			fprintf(fp, "rp_filter strict ");
+		else if (rp_filter == 2)
+			fprintf(fp, "rp_filter loose ");
+		else
+			fprintf(fp, "rp_filter unknown mode ");
+	}
+	if (tb[NETCONFA_MC_FORWARDING])
+		fprintf(fp, "mc_forwarding %d ",
+			*(int *)RTA_DATA(tb[NETCONFA_MC_FORWARDING]));
+
+	fprintf(fp, "\n");
+	fflush(fp);
+	return 0;
+}
+
+void ipnetconf_reset_filter(void)
+{
+	memset(&filter, 0, sizeof(filter));
+}
+
+int do_show(int argc, char **argv)
+{
+	struct {
+		struct nlmsghdr		n;
+		struct netconfmsg	ncm;
+		char			buf[1024];
+	} req;
+
+	ipnetconf_reset_filter();
+	filter.family = preferred_family;
+	if (filter.family == AF_UNSPEC)
+		filter.family = AF_INET;
+	filter.ifindex = NETCONFA_IFINDEX_ALL;
+
+	while (argc > 0) {
+		if (strcmp(*argv, "dev") == 0) {
+			NEXT_ARG();
+			filter.ifindex = ll_name_to_index(*argv);
+			if (filter.ifindex <= 0) {
+				fprintf(stderr, "Device \"%s\" does not exist.\n",
+					*argv);
+				return -1;
+			}
+		}
+		argv++; argc--;
+	}
+
+	ll_init_map(&rth);
+	memset(&req, 0, sizeof(req));
+	req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct netconfmsg));
+	req.n.nlmsg_flags = NLM_F_REQUEST|NLM_F_ACK;
+	req.n.nlmsg_type = RTM_GETNETCONF;
+	req.ncm.ncm_family = filter.family;
+	addattr_l(&req.n, sizeof(req), NETCONFA_IFINDEX, &filter.ifindex,
+		  sizeof(filter.ifindex));
+
+	rtnl_send(&rth, &req.n, req.n.nlmsg_len);
+	rtnl_listen(&rth, print_netconf, stdout);
+
+	return 0;
+}
+
+int do_ipnetconf(int argc, char **argv)
+{
+	if (argc > 0) {
+		if (matches(*argv, "show") == 0 ||
+		    matches(*argv, "lst") == 0 ||
+		    matches(*argv, "list") == 0)
+			return do_show(argc-1, argv+1);
+		if (matches(*argv, "help") == 0)
+			usage();
+	} else
+		return do_show(0, NULL);
+
+	fprintf(stderr, "Command \"%s\" is unknown, try \"ip netconf help\".\n", *argv);
+	exit(-1);
+}

@@ -4,7 +4,8 @@ IPOBJ=ip.o ipaddress.o ipaddrlabel.o iproute.o iprule.o ipnetns.o \
     ipxfrm.o xfrm_state.o xfrm_policy.o xfrm_monitor.o \
     iplink_vlan.o link_veth.o link_gre.o iplink_can.o \
     iplink_macvlan.o iplink_macvtap.o ipl2tp.o link_vti.o \
-    iplink_vxlan.o tcp_metrics.o iplink_ipoib.o ipnetconf.o link_ip6tnl.o
+    iplink_vxlan.o tcp_metrics.o iplink_ipoib.o ipnetconf.o link_ip6tnl.o \
+    link_iptnl.o
 
 RTMONOBJ=rtmon.o
 

@@ -84,7 +84,7 @@ void iplink_usage(void)
 	if (iplink_have_newlink()) {
 		fprintf(stderr, "\n");
 		fprintf(stderr, "TYPE := { vlan | veth | vcan | dummy | ifb | macvlan | can |\n");
-		fprintf(stderr, "          bridge | ipoib | ip6tnl }\n");
+		fprintf(stderr, "          bridge | ipoib | ip6tnl | ipip | sit }\n");
 	}
 	exit(-1);
 }

@@ -0,0 +1,340 @@
+/*
+ * link_iptnl.c	ipip and sit driver module
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ *
+ * Authors:	Nicolas Dichtel <nicolas.dichtel@6wind.com>
+ *
+ */
+
+#include <string.h>
+#include <net/if.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+
+#include <linux/ip.h>
+#include <linux/if_tunnel.h>
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+#include "tunnel.h"
+
+static void usage(int sit) __attribute__((noreturn));
+static void usage(int sit)
+{
+	fprintf(stderr, "Usage: ip link { add | set | change | replace | del } NAME\n");
+	fprintf(stderr, "          type { ipip | sit } [ remote ADDR ] [ local ADDR ]\n");
+	fprintf(stderr, "          [ ttl TTL ] [ tos TOS ] [ [no]pmtudisc ] [ dev PHYS_DEV ]\n");
+	fprintf(stderr, "          [ 6rd-prefix ADDR ] [ 6rd-relay_prefix ADDR ] [ 6rd-reset ]\n");
+	if (sit)
+		fprintf(stderr, "          [ isatap ]\n");
+	fprintf(stderr, "\n");
+	fprintf(stderr, "Where: NAME := STRING\n");
+	fprintf(stderr, "       ADDR := { IP_ADDRESS | any }\n");
+	fprintf(stderr, "       TOS  := { NUMBER | inherit }\n");
+	fprintf(stderr, "       TTL  := { 1..255 | inherit }\n");
+	exit(-1);
+}
+
+static int iptunnel_parse_opt(struct link_util *lu, int argc, char **argv,
+			      struct nlmsghdr *n)
+{
+	struct {
+		struct nlmsghdr n;
+		struct ifinfomsg i;
+		char buf[2048];
+	} req;
+	struct ifinfomsg *ifi = (struct ifinfomsg *)(n + 1);
+	struct rtattr *tb[IFLA_MAX + 1];
+	struct rtattr *linkinfo[IFLA_INFO_MAX+1];
+	struct rtattr *iptuninfo[IFLA_IPTUN_MAX + 1];
+	int len;
+	__u32 link = 0;
+	__u32 laddr = 0;
+	__u32 raddr = 0;
+	__u8 ttl = 0;
+	__u8 tos = 0;
+	__u8 pmtudisc = 1;
+	__u16 iflags = 0;
+	struct in6_addr ip6rdprefix;
+	__u16 ip6rdprefixlen = 0;
+	__u32 ip6rdrelayprefix = 0;
+	__u16 ip6rdrelayprefixlen = 0;
+
+	memset(&ip6rdprefix, 0, sizeof(ip6rdprefix));
+
+	if (!(n->nlmsg_flags & NLM_F_CREATE)) {
+		memset(&req, 0, sizeof(req));
+
+		req.n.nlmsg_len = NLMSG_LENGTH(sizeof(*ifi));
+		req.n.nlmsg_flags = NLM_F_REQUEST;
+		req.n.nlmsg_type = RTM_GETLINK;
+		req.i.ifi_family = preferred_family;
+		req.i.ifi_index = ifi->ifi_index;
+
+		if (rtnl_talk(&rth, &req.n, 0, 0, &req.n) < 0) {
+get_failed:
+			fprintf(stderr,
+				"Failed to get existing tunnel info.\n");
+			return -1;
+		}
+
+		len = req.n.nlmsg_len;
+		len -= NLMSG_LENGTH(sizeof(*ifi));
+		if (len < 0)
+			goto get_failed;
+
+		parse_rtattr(tb, IFLA_MAX, IFLA_RTA(&req.i), len);
+
+		if (!tb[IFLA_LINKINFO])
+			goto get_failed;
+
+		parse_rtattr_nested(linkinfo, IFLA_INFO_MAX, tb[IFLA_LINKINFO]);
+
+		if (!linkinfo[IFLA_INFO_DATA])
+			goto get_failed;
+
+		parse_rtattr_nested(iptuninfo, IFLA_IPTUN_MAX,
+				    linkinfo[IFLA_INFO_DATA]);
+
+		if (iptuninfo[IFLA_IPTUN_LOCAL])
+			laddr = rta_getattr_u32(iptuninfo[IFLA_IPTUN_LOCAL]);
+
+		if (iptuninfo[IFLA_IPTUN_REMOTE])
+			raddr = rta_getattr_u32(iptuninfo[IFLA_IPTUN_REMOTE]);
+
+		if (iptuninfo[IFLA_IPTUN_TTL])
+			ttl = rta_getattr_u8(iptuninfo[IFLA_IPTUN_TTL]);
+
+		if (iptuninfo[IFLA_IPTUN_TOS])
+			tos = rta_getattr_u8(iptuninfo[IFLA_IPTUN_TOS]);
+
+		if (iptuninfo[IFLA_IPTUN_PMTUDISC])
+			pmtudisc =
+				rta_getattr_u8(iptuninfo[IFLA_IPTUN_PMTUDISC]);
+
+		if (iptuninfo[IFLA_IPTUN_FLAGS])
+			iflags = rta_getattr_u16(iptuninfo[IFLA_IPTUN_FLAGS]);
+
+		if (iptuninfo[IFLA_IPTUN_LINK])
+			link = rta_getattr_u32(iptuninfo[IFLA_IPTUN_LINK]);
+
+		if (iptuninfo[IFLA_IPTUN_6RD_PREFIX])
+			memcpy(&ip6rdprefix,
+			       RTA_DATA(iptuninfo[IFLA_IPTUN_6RD_PREFIX]),
+			       sizeof(laddr));
+
+		if (iptuninfo[IFLA_IPTUN_6RD_PREFIXLEN])
+			ip6rdprefixlen =
+				rta_getattr_u16(iptuninfo[IFLA_IPTUN_6RD_PREFIXLEN]);
+
+		if (iptuninfo[IFLA_IPTUN_6RD_RELAY_PREFIX])
+			ip6rdrelayprefix =
+				rta_getattr_u32(iptuninfo[IFLA_IPTUN_6RD_RELAY_PREFIX]);
+
+		if (iptuninfo[IFLA_IPTUN_6RD_RELAY_PREFIXLEN])
+			ip6rdrelayprefixlen =
+				rta_getattr_u16(iptuninfo[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]);
+	}
+
+	while (argc > 0) {
+		if (strcmp(*argv, "remote") == 0) {
+			NEXT_ARG();
+			if (strcmp(*argv, "any"))
+				raddr = get_addr32(*argv);
+			else
+				raddr = 0;
+		} else if (strcmp(*argv, "local") == 0) {
+			NEXT_ARG();
+			if (strcmp(*argv, "any"))
+				laddr = get_addr32(*argv);
+			else
+				laddr = 0;
+		} else if (matches(*argv, "dev") == 0) {
+			NEXT_ARG();
+			link = if_nametoindex(*argv);
+			if (link == 0)
+				invarg("\"dev\" is invalid", *argv);
+		} else if (strcmp(*argv, "ttl") == 0 ||
+			   strcmp(*argv, "hoplimit") == 0) {
+			NEXT_ARG();
+			if (strcmp(*argv, "inherit") != 0) {
+				if (get_u8(&ttl, *argv, 0))
+					invarg("invalid TTL\n", *argv);
+			} else
+				ttl = 0;
+		} else if (strcmp(*argv, "tos") == 0 ||
+			   strcmp(*argv, "tclass") == 0 ||
+			   matches(*argv, "dsfield") == 0) {
+			__u32 uval;
+			NEXT_ARG();
+			if (strcmp(*argv, "inherit") != 0) {
+				if (rtnl_dsfield_a2n(&uval, *argv))
+					invarg("bad TOS value", *argv);
+				tos = uval;
+			} else
+				tos = 1;
+		} else if (strcmp(*argv, "nopmtudisc") == 0) {
+			pmtudisc = 0;
+		} else if (strcmp(*argv, "pmtudisc") == 0) {
+			pmtudisc = 1;
+		} else if (strcmp(lu->id, "sit") == 0 &&
+			   strcmp(*argv, "isatap") == 0) {
+			iflags |= SIT_ISATAP;
+		} else if (strcmp(*argv, "6rd-prefix") == 0) {
+			inet_prefix prefix;
+			NEXT_ARG();
+			if (get_prefix(&prefix, *argv, AF_INET6))
+				invarg("invalid 6rd_prefix\n", *argv);
+			memcpy(&ip6rdprefix, prefix.data, 16);
+			ip6rdprefixlen = prefix.bitlen;
+		} else if (strcmp(*argv, "6rd-relay_prefix") == 0) {
+			inet_prefix prefix;
+			NEXT_ARG();
+			if (get_prefix(&prefix, *argv, AF_INET))
+				invarg("invalid 6rd-relay_prefix\n", *argv);
+			memcpy(&ip6rdrelayprefix, prefix.data, 4);
+			ip6rdrelayprefixlen = prefix.bitlen;
+		} else if (strcmp(*argv, "6rd-reset") == 0) {
+			inet_prefix prefix;
+			get_prefix(&prefix, "2002::", AF_INET6);
+			memcpy(&ip6rdprefix, prefix.data, 16);
+			ip6rdprefixlen = 16;
+			ip6rdrelayprefix = 0;
+			ip6rdrelayprefixlen = 0;
+		} else
+			usage(strcmp(lu->id, "sit") == 0);
+		argc--, argv++;
+	}
+
+	if (ttl && pmtudisc == 0) {
+		fprintf(stderr, "ttl != 0 and noptmudisc are incompatible\n");
+		exit(-1);
+	}
+
+	addattr32(n, 1024, IFLA_IPTUN_LINK, link);
+	addattr32(n, 1024, IFLA_IPTUN_LOCAL, laddr);
+	addattr32(n, 1024, IFLA_IPTUN_REMOTE, raddr);
+	addattr8(n, 1024, IFLA_IPTUN_TTL, ttl);
+	addattr8(n, 1024, IFLA_IPTUN_TOS, tos);
+	addattr8(n, 1024, IFLA_IPTUN_PMTUDISC, pmtudisc);
+	if (strcmp(lu->id, "sit") == 0) {
+		addattr16(n, 1024, IFLA_IPTUN_FLAGS, iflags);
+		if (ip6rdprefixlen) {
+			addattr_l(n, 1024, IFLA_IPTUN_6RD_PREFIX,
+				  &ip6rdprefix, sizeof(ip6rdprefix));
+			addattr16(n, 1024, IFLA_IPTUN_6RD_PREFIXLEN,
+				  ip6rdprefixlen);
+			addattr32(n, 1024, IFLA_IPTUN_6RD_RELAY_PREFIX,
+				  ip6rdrelayprefix);
+			addattr16(n, 1024, IFLA_IPTUN_6RD_RELAY_PREFIXLEN,
+				  ip6rdrelayprefixlen);
+		}
+	}
+
+	return 0;
+}
+
+static void iptunnel_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+	char s1[1024];
+	char s2[64];
+	const char *local = "any";
+	const char *remote = "any";
+
+	if (!tb)
+		return;
+
+	if (tb[IFLA_IPTUN_REMOTE]) {
+		unsigned addr = rta_getattr_u32(tb[IFLA_IPTUN_REMOTE]);
+
+		if (addr)
+			remote = format_host(AF_INET, 4, &addr, s1, sizeof(s1));
+	}
+
+	fprintf(f, "remote %s ", remote);
+
+	if (tb[IFLA_IPTUN_LOCAL]) {
+		unsigned addr = rta_getattr_u32(tb[IFLA_IPTUN_LOCAL]);
+
+		if (addr)
+			local = format_host(AF_INET, 4, &addr, s1, sizeof(s1));
+	}
+
+	fprintf(f, "local %s ", local);
+
+	if (tb[IFLA_IPTUN_LINK] && rta_getattr_u32(tb[IFLA_IPTUN_LINK])) {
+		unsigned link = rta_getattr_u32(tb[IFLA_IPTUN_LINK]);
+		const char *n = if_indextoname(link, s2);
+
+		if (n)
+			fprintf(f, "dev %s ", n);
+		else
+			fprintf(f, "dev %u ", link);
+	}
+
+	if (tb[IFLA_IPTUN_TTL] && rta_getattr_u8(tb[IFLA_IPTUN_TTL]))
+		fprintf(f, "ttl %d ", rta_getattr_u8(tb[IFLA_IPTUN_TTL]));
+	else
+		fprintf(f, "ttl inherit ");
+
+	if (tb[IFLA_IPTUN_TOS] && rta_getattr_u8(tb[IFLA_IPTUN_TOS])) {
+		int tos = rta_getattr_u8(tb[IFLA_IPTUN_TOS]);
+
+		fputs("tos ", f);
+		if (tos == 1)
+			fputs("inherit ", f);
+		else
+			fprintf(f, "0x%x ", tos);
+	}
+
+	if (tb[IFLA_IPTUN_PMTUDISC] && rta_getattr_u8(tb[IFLA_IPTUN_PMTUDISC]))
+		fprintf(f, "pmtudisc ");
+	else
+		fprintf(f, "nopmtudisc ");
+
+	if (tb[IFLA_IPTUN_FLAGS]) {
+	       __u16 iflags = rta_getattr_u16(tb[IFLA_IPTUN_FLAGS]);
+
+	      if (iflags & SIT_ISATAP)
+		      fprintf(f, "isatap ");
+	}
+
+	if (tb[IFLA_IPTUN_6RD_PREFIXLEN] &&
+	    *(__u16 *)RTA_DATA(tb[IFLA_IPTUN_6RD_PREFIXLEN])) {
+		__u16 prefixlen = rta_getattr_u16(tb[IFLA_IPTUN_6RD_PREFIXLEN]);
+		__u16 relayprefixlen =
+			rta_getattr_u16(tb[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]);
+		__u32 relayprefix =
+			rta_getattr_u32(tb[IFLA_IPTUN_6RD_RELAY_PREFIX]);
+
+		printf("6rd-prefix %s/%u ",
+		       inet_ntop(AF_INET6, RTA_DATA(tb[IFLA_IPTUN_6RD_PREFIX]),
+			         s1, sizeof(s1)),
+		       prefixlen);
+		if (relayprefix) {
+			printf("6rd-relay_prefix %s/%u ",
+			       format_host(AF_INET, 4, &relayprefix, s1,
+				           sizeof(s1)),
+			       relayprefixlen);
+		}
+	}
+}
+
+struct link_util ipip_link_util = {
+	.id = "ipip",
+	.maxattr = IFLA_IPTUN_MAX,
+	.parse_opt = iptunnel_parse_opt,
+	.print_opt = iptunnel_print_opt,
+};
+
+struct link_util sit_link_util = {
+	.id = "sit",
+	.maxattr = IFLA_IPTUN_MAX,
+	.parse_opt = iptunnel_parse_opt,
+	.print_opt = iptunnel_print_opt,
+};

@@ -37,6 +37,26 @@ struct ip_tunnel_parm {
 	struct iphdr		iph;
 };
 
+enum {
+	IFLA_IPTUN_UNSPEC,
+	IFLA_IPTUN_LINK,
+	IFLA_IPTUN_LOCAL,
+	IFLA_IPTUN_REMOTE,
+	IFLA_IPTUN_TTL,
+	IFLA_IPTUN_TOS,
+	IFLA_IPTUN_ENCAP_LIMIT,
+	IFLA_IPTUN_FLOWINFO,
+	IFLA_IPTUN_FLAGS,
+	IFLA_IPTUN_PROTO,
+	IFLA_IPTUN_PMTUDISC,
+	IFLA_IPTUN_6RD_PREFIX,
+	IFLA_IPTUN_6RD_RELAY_PREFIX,
+	IFLA_IPTUN_6RD_PREFIXLEN,
+	IFLA_IPTUN_6RD_RELAY_PREFIXLEN,
+	__IFLA_IPTUN_MAX,
+};
+#define IFLA_IPTUN_MAX	(__IFLA_IPTUN_MAX - 1)
+
 /* SIT-mode i_flags */
 #define	SIT_ISATAP	0x0001
 

@@ -4,7 +4,7 @@ IPOBJ=ip.o ipaddress.o ipaddrlabel.o iproute.o iprule.o ipnetns.o \
     ipxfrm.o xfrm_state.o xfrm_policy.o xfrm_monitor.o \
     iplink_vlan.o link_veth.o link_gre.o iplink_can.o \
     iplink_macvlan.o iplink_macvtap.o ipl2tp.o link_vti.o \
-    iplink_vxlan.o tcp_metrics.o iplink_ipoib.o ipnetconf.o
+    iplink_vxlan.o tcp_metrics.o iplink_ipoib.o ipnetconf.o link_ip6tnl.o
 
 RTMONOBJ=rtmon.o
 

@@ -83,7 +83,8 @@ void iplink_usage(void)
 
 	if (iplink_have_newlink()) {
 		fprintf(stderr, "\n");
-		fprintf(stderr, "TYPE := { vlan | veth | vcan | dummy | ifb | macvlan | can | bridge | ipoib }\n");
+		fprintf(stderr, "TYPE := { vlan | veth | vcan | dummy | ifb | macvlan | can |\n");
+		fprintf(stderr, "          bridge | ipoib | ip6tnl }\n");
 	}
 	exit(-1);
 }

@@ -0,0 +1,344 @@
+/*
+ * link_ip6tnl.c	ip6tnl driver module
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ *
+ * Authors:	Nicolas Dichtel <nicolas.dichtel@6wind.com>
+ *
+ */
+
+#include <string.h>
+#include <net/if.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
+
+#include <linux/ip.h>
+#include <linux/if_tunnel.h>
+#include <linux/ip6_tunnel.h>
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+#include "tunnel.h"
+
+#define IP6_FLOWINFO_TCLASS	htonl(0x0FF00000)
+#define IP6_FLOWINFO_FLOWLABEL	htonl(0x000FFFFF)
+
+#define DEFAULT_TNL_HOP_LIMIT	(64)
+
+static void usage(void) __attribute__((noreturn));
+static void usage(void)
+{
+	fprintf(stderr, "Usage: ip link { add | set | change | replace | del } NAME\n");
+	fprintf(stderr, "          type ip6tnl [ remote ADDR ] [ local ADDR ]\n");
+	fprintf(stderr, "          [ dev PHYS_DEV ] [ encaplimit ELIM ]\n");
+	fprintf(stderr ,"          [ hoplimit HLIM ] [ tclass TCLASS ] [ flowlabel FLOWLABEL ]\n");
+	fprintf(stderr, "          [ dscp inherit ] [ fwmark inherit ]\n");
+	fprintf(stderr, "\n");
+	fprintf(stderr, "Where: NAME      := STRING\n");
+	fprintf(stderr, "       ADDR      := IPV6_ADDRESS\n");
+	fprintf(stderr, "       ELIM      := { none | 0..255 }(default=%d)\n",
+		IPV6_DEFAULT_TNL_ENCAP_LIMIT);
+	fprintf(stderr, "       HLIM      := 0..255 (default=%d)\n",
+		DEFAULT_TNL_HOP_LIMIT);
+	fprintf(stderr, "       TCLASS    := { 0x0..0xff | inherit }\n");
+	fprintf(stderr, "       FLOWLABEL := { 0x0..0xfffff | inherit }\n");
+	exit(-1);
+}
+
+static int ip6tunnel_parse_opt(struct link_util *lu, int argc, char **argv,
+			       struct nlmsghdr *n)
+{
+	struct {
+		struct nlmsghdr n;
+		struct ifinfomsg i;
+		char buf[2048];
+	} req;
+	struct ifinfomsg *ifi = (struct ifinfomsg *)(n + 1);
+	struct rtattr *tb[IFLA_MAX + 1];
+	struct rtattr *linkinfo[IFLA_INFO_MAX+1];
+	struct rtattr *iptuninfo[IFLA_IPTUN_MAX + 1];
+	int len;
+	struct in6_addr laddr;
+	struct in6_addr raddr;
+	__u8 hop_limit = DEFAULT_TNL_HOP_LIMIT;
+	__u8 encap_limit = IPV6_DEFAULT_TNL_ENCAP_LIMIT;
+	__u32 flowinfo = 0;
+	__u32 flags = 0;
+	__u32 link = 0;
+	__u8 proto = 0;
+
+	memset(&laddr, 0, sizeof(laddr));
+	memset(&raddr, 0, sizeof(raddr));
+
+	if (!(n->nlmsg_flags & NLM_F_CREATE)) {
+		memset(&req, 0, sizeof(req));
+
+		req.n.nlmsg_len = NLMSG_LENGTH(sizeof(*ifi));
+		req.n.nlmsg_flags = NLM_F_REQUEST;
+		req.n.nlmsg_type = RTM_GETLINK;
+		req.i.ifi_family = preferred_family;
+		req.i.ifi_index = ifi->ifi_index;
+
+		if (rtnl_talk(&rth, &req.n, 0, 0, &req.n) < 0) {
+get_failed:
+			fprintf(stderr,
+				"Failed to get existing tunnel info.\n");
+			return -1;
+		}
+
+		len = req.n.nlmsg_len;
+		len -= NLMSG_LENGTH(sizeof(*ifi));
+		if (len < 0)
+			goto get_failed;
+
+		parse_rtattr(tb, IFLA_MAX, IFLA_RTA(&req.i), len);
+
+		if (!tb[IFLA_LINKINFO])
+			goto get_failed;
+
+		parse_rtattr_nested(linkinfo, IFLA_INFO_MAX, tb[IFLA_LINKINFO]);
+
+		if (!linkinfo[IFLA_INFO_DATA])
+			goto get_failed;
+
+		parse_rtattr_nested(iptuninfo, IFLA_IPTUN_MAX,
+				    linkinfo[IFLA_INFO_DATA]);
+
+		if (iptuninfo[IFLA_IPTUN_LOCAL])
+			memcpy(&laddr, RTA_DATA(iptuninfo[IFLA_IPTUN_LOCAL]),
+			       sizeof(laddr));
+
+		if (iptuninfo[IFLA_IPTUN_REMOTE])
+			memcpy(&raddr, RTA_DATA(iptuninfo[IFLA_IPTUN_REMOTE]),
+			       sizeof(raddr));
+
+		if (iptuninfo[IFLA_IPTUN_TTL])
+			hop_limit = rta_getattr_u8(iptuninfo[IFLA_IPTUN_TTL]);
+
+		if (iptuninfo[IFLA_IPTUN_ENCAP_LIMIT])
+			encap_limit = rta_getattr_u8(iptuninfo[IFLA_IPTUN_ENCAP_LIMIT]);
+
+		if (iptuninfo[IFLA_IPTUN_FLOWINFO])
+			flowinfo = rta_getattr_u32(iptuninfo[IFLA_IPTUN_FLOWINFO]);
+
+		if (iptuninfo[IFLA_IPTUN_FLAGS])
+			flags = rta_getattr_u32(iptuninfo[IFLA_IPTUN_FLAGS]);
+
+		if (iptuninfo[IFLA_IPTUN_LINK])
+			link = rta_getattr_u32(iptuninfo[IFLA_IPTUN_LINK]);
+
+		if (iptuninfo[IFLA_IPTUN_PROTO])
+			proto = rta_getattr_u8(iptuninfo[IFLA_IPTUN_PROTO]);
+	}
+
+	while (argc > 0) {
+		if (matches(*argv, "mode") == 0) {
+			NEXT_ARG();
+			if (strcmp(*argv, "ipv6/ipv6") == 0 ||
+			    strcmp(*argv, "ip6ip6") == 0)
+				proto = IPPROTO_IPV6;
+			else if (strcmp(*argv, "ip/ipv6") == 0 ||
+				 strcmp(*argv, "ipv4/ipv6") == 0 ||
+				 strcmp(*argv, "ipip6") == 0 ||
+				 strcmp(*argv, "ip4ip6") == 0)
+				proto = IPPROTO_IPIP;
+			else if (strcmp(*argv, "any/ipv6") == 0 ||
+				 strcmp(*argv, "any") == 0)
+				proto = 0;
+			else
+				invarg("Cannot guess tunnel mode.", *argv);
+		} else if (strcmp(*argv, "remote") == 0) {
+			inet_prefix addr;
+			NEXT_ARG();
+			get_prefix(&addr, *argv, preferred_family);
+			if (addr.family == AF_UNSPEC)
+				invarg("\"remote\" address family is AF_UNSPEC", *argv);
+			memcpy(&raddr, addr.data, addr.bytelen);
+		} else if (strcmp(*argv, "local") == 0) {
+			inet_prefix addr;
+			NEXT_ARG();
+			get_prefix(&addr, *argv, preferred_family);
+			if (addr.family == AF_UNSPEC)
+				invarg("\"local\" address family is AF_UNSPEC", *argv);
+			memcpy(&laddr, addr.data, addr.bytelen);
+		} else if (matches(*argv, "dev") == 0) {
+			NEXT_ARG();
+			link = if_nametoindex(*argv);
+			if (link == 0)
+				invarg("\"dev\" is invalid", *argv);
+		} else if (strcmp(*argv, "hoplimit") == 0 ||
+			   strcmp(*argv, "ttl") == 0 ||
+			   strcmp(*argv, "hlim") == 0) {
+			__u8 uval;
+			NEXT_ARG();
+			if (get_u8(&uval, *argv, 0))
+				invarg("invalid HLIM", *argv);
+			hop_limit = uval;
+		} else if (matches(*argv, "encaplimit") == 0) {
+			NEXT_ARG();
+			if (strcmp(*argv, "none") == 0) {
+				flags |= IP6_TNL_F_IGN_ENCAP_LIMIT;
+			} else {
+				__u8 uval;
+				if (get_u8(&uval, *argv, 0) < -1)
+					invarg("invalid ELIM", *argv);
+				encap_limit = uval;
+				flags &= ~IP6_TNL_F_IGN_ENCAP_LIMIT;
+			}
+		} else if (strcmp(*argv, "tclass") == 0 ||
+			   strcmp(*argv, "tc") == 0 ||
+			   strcmp(*argv, "tos") == 0 ||
+			   matches(*argv, "dsfield") == 0) {
+			__u8 uval;
+			NEXT_ARG();
+			flowinfo &= ~IP6_FLOWINFO_TCLASS;
+			if (strcmp(*argv, "inherit") == 0)
+				flags |= IP6_TNL_F_USE_ORIG_TCLASS;
+			else {
+				if (get_u8(&uval, *argv, 16))
+					invarg("invalid TClass", *argv);
+				flowinfo |= htonl((__u32)uval << 20) & IP6_FLOWINFO_TCLASS;
+				flags &= ~IP6_TNL_F_USE_ORIG_TCLASS;
+			}
+		} else if (strcmp(*argv, "flowlabel") == 0 ||
+			   strcmp(*argv, "fl") == 0) {
+			__u32 uval;
+			NEXT_ARG();
+			flowinfo &= ~IP6_FLOWINFO_FLOWLABEL;
+			if (strcmp(*argv, "inherit") == 0)
+				flags |= IP6_TNL_F_USE_ORIG_FLOWLABEL;
+			else {
+				if (get_u32(&uval, *argv, 16))
+					invarg("invalid Flowlabel", *argv);
+				if (uval > 0xFFFFF)
+					invarg("invalid Flowlabel", *argv);
+				flowinfo |= htonl(uval) & IP6_FLOWINFO_FLOWLABEL;
+				flags &= ~IP6_TNL_F_USE_ORIG_FLOWLABEL;
+			}
+		} else if (strcmp(*argv, "dscp") == 0) {
+			NEXT_ARG();
+			if (strcmp(*argv, "inherit") != 0)
+				invarg("not inherit", *argv);
+			flags |= IP6_TNL_F_RCV_DSCP_COPY;
+		} else if (strcmp(*argv, "fwmark") == 0) {
+			NEXT_ARG();
+			if (strcmp(*argv, "inherit") != 0)
+				invarg("not inherit", *argv);
+			flags |= IP6_TNL_F_USE_ORIG_FWMARK;
+		} else
+			usage();
+		argc--, argv++;
+	}
+
+	addattr8(n, 1024, IFLA_IPTUN_PROTO, proto);
+	addattr_l(n, 1024, IFLA_IPTUN_LOCAL, &laddr, sizeof(laddr));
+	addattr_l(n, 1024, IFLA_IPTUN_REMOTE, &raddr, sizeof(raddr));
+	addattr8(n, 1024, IFLA_IPTUN_TTL, hop_limit);
+	addattr8(n, 1024, IFLA_IPTUN_ENCAP_LIMIT, encap_limit);
+	addattr32(n, 1024, IFLA_IPTUN_FLOWINFO, flowinfo);
+	addattr32(n, 1024, IFLA_IPTUN_FLAGS, flags);
+	addattr32(n, 1024, IFLA_IPTUN_LINK, link);
+
+	return 0;
+}
+
+static void ip6tunnel_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
+{
+	char s1[256];
+	char s2[64];
+	int flags = 0;
+	__u32 flowinfo = 0;
+
+	if (!tb)
+		return;
+
+	if (tb[IFLA_IPTUN_FLAGS])
+		flags = rta_getattr_u32(tb[IFLA_IPTUN_FLAGS]);
+
+	if (tb[IFLA_IPTUN_FLOWINFO])
+		flowinfo = rta_getattr_u32(tb[IFLA_IPTUN_FLOWINFO]);
+
+	if (tb[IFLA_IPTUN_PROTO]) {
+		switch (rta_getattr_u8(tb[IFLA_IPTUN_PROTO])) {
+		case IPPROTO_IPIP:
+			fprintf(f, "ipip6 ");
+			break;
+		case IPPROTO_IPV6:
+			fprintf(f, "ip6ip6 ");
+			break;
+		case 0:
+			fprintf(f, "any ");
+			break;
+		}
+	}
+
+	if (tb[IFLA_IPTUN_REMOTE]) {
+		fprintf(f, "remote %s ",
+			rt_addr_n2a(AF_INET6,
+				    RTA_PAYLOAD(tb[IFLA_IPTUN_REMOTE]),
+				    RTA_DATA(tb[IFLA_IPTUN_REMOTE]),
+				    s1, sizeof(s1)));
+	}
+
+	if (tb[IFLA_IPTUN_LOCAL]) {
+		fprintf(f, "local %s ",
+			rt_addr_n2a(AF_INET6,
+				    RTA_PAYLOAD(tb[IFLA_IPTUN_LOCAL]),
+				    RTA_DATA(tb[IFLA_IPTUN_LOCAL]),
+				    s1, sizeof(s1)));
+	}
+
+	if (tb[IFLA_IPTUN_LINK] && rta_getattr_u32(tb[IFLA_IPTUN_LINK])) {
+		unsigned link = rta_getattr_u32(tb[IFLA_IPTUN_LINK]);
+		const char *n = if_indextoname(link, s2);
+
+		if (n)
+			fprintf(f, "dev %s ", n);
+		else
+			fprintf(f, "dev %u ", link);
+	}
+
+	if (flags & IP6_TNL_F_IGN_ENCAP_LIMIT)
+		printf("encaplimit none ");
+	else if (tb[IFLA_IPTUN_ENCAP_LIMIT])
+		fprintf(f, "encaplimit %u ",
+			rta_getattr_u8(tb[IFLA_IPTUN_ENCAP_LIMIT]));
+
+	if (tb[IFLA_IPTUN_TTL])
+		fprintf(f, "hoplimit %u ", rta_getattr_u8(tb[IFLA_IPTUN_TTL]));
+
+	if (flags & IP6_TNL_F_USE_ORIG_TCLASS)
+		printf("tclass inherit ");
+	else if (tb[IFLA_IPTUN_FLOWINFO]) {
+		__u32 val = ntohl(flowinfo & IP6_FLOWINFO_TCLASS);
+
+		printf("tclass 0x%02x ", (__u8)(val >> 20));
+	}
+
+	if (flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)
+		printf("flowlabel inherit ");
+	else
+		printf("flowlabel 0x%05x ", ntohl(flowinfo & IP6_FLOWINFO_FLOWLABEL));
+
+	printf("(flowinfo 0x%08x) ", ntohl(flowinfo));
+
+	if (flags & IP6_TNL_F_RCV_DSCP_COPY)
+		printf("dscp inherit ");
+
+	if (flags & IP6_TNL_F_MIP6_DEV)
+		fprintf(f, "mip6 ");
+
+	if (flags & IP6_TNL_F_USE_ORIG_FWMARK)
+		fprintf(f, "fwmark inherit ");
+}
+
+struct link_util ip6tnl_link_util = {
+	.id = "ip6tnl",
+	.maxattr = IFLA_IPTUN_MAX,
+	.parse_opt = ip6tunnel_parse_opt,
+	.print_opt = ip6tunnel_print_opt,
+};