ip: add support of 'ip link type ip6tnl'

This patch allows to manage ip6 tunnels via the interface ip link.
The syntax for parameters is the same that 'ip -6 tunnel'.

It also allows to display tunnels parameters with 'ip -details link' or
'ip -details monitor link'.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>

diff --git a/include/libnetlink.h b/include/libnetlink.h
index 81649afe5a1421af8d54e8313a811e136c0ecd49..4a6b8789fdc2ab1f5548f2078096eed32018744e 100644 (file)
--- a/include/libnetlink.h
+++ b/include/libnetlink.h
@@ -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
 {

diff --git a/ip/Makefile b/ip/Makefile
index 1676f0ff80ce07a89be135069ed7bc747cbb400a..abf54bf714ed57cbe1d5dfcfa647002114c367ff 100644 (file)
--- a/ip/Makefile
+++ b/ip/Makefile
@@ -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 link_ip6tnl.o
 
 RTMONOBJ=rtmon.o
 

diff --git a/ip/ip.c b/ip/ip.c
index e0f7e60951f2fd6b8cc428106c29426133d289da..632d2717b096f66409f4e7fe6f5cf195e16de842 100644 (file)
--- a/ip/ip.c
+++ b/ip/ip.c
@@ -85,6 +85,7 @@ static const struct cmd {
        { "mroute",     do_multiroute },
        { "mrule",      do_multirule },
        { "netns",      do_netns },
+       { "netconf",    do_ipnetconf },
        { "help",       do_help },
        { 0 }
 };

diff --git a/ip/ip_common.h b/ip/ip_common.h
index 2fd66b743a7211148df5e073e3e8db94d63e6dd5..a3946690293b773d41f907c7b46eb4cfdc067b52 100644 (file)
--- a/ip/ip_common.h
+++ b/ip/ip_common.h
@@ -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)
 {

diff --git a/ip/iplink.c b/ip/iplink.c
index 7451aa029b2e8a91ac8d9624826f4350e98438f2..8aac9fc93d441010209fe075505d11e10394a484 100644 (file)
--- a/ip/iplink.c
+++ b/ip/iplink.c
@@ -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);
 }

diff --git a/ip/ipmonitor.c b/ip/ipmonitor.c
index 4b1d469df884d6b356153d3626fb541e3bf7fae6..d87e58f14b37bf48dd2e04b2c22f5e1e8a1d7b6c 100644 (file)
--- a/ip/ipmonitor.c
+++ b/ip/ipmonitor.c
@@ -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");

diff --git a/ip/link_ip6tnl.c b/ip/link_ip6tnl.c
new file mode 100644 (file)
index 0000000..2947364
--- /dev/null
+++ b/ip/link_ip6tnl.c
@@ -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,
+};