traceroute6.c

IPv6环境下的traceroute实现

/*	$KAME: traceroute6.c,v 1.60 2002/08/30 04:01:58 onoe Exp $	*/

/*
 * Copyright (C) 1995, 1996, 1997, and 1998 WIDE Project.
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. Neither the name of the project nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE PROJECT AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE PROJECT OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 */

/*-
 * Copyright (c) 1990, 1993
 *	The Regents of the University of California.  All rights reserved.
 *
 * This code is derived from software contributed to Berkeley by
 * Van Jacobson.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgement:
 *	This product includes software developed by the University of
 *	California, Berkeley and its contributors.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 */

#ifndef lint
static char copyright[] =
"@(#) Copyright (c) 1990, 1993\n\
	The Regents of the University of California.  All rights reserved.\n";
#endif /* not lint */

#ifndef lint
static char sccsid[] = "@(#)traceroute.c	8.1 (Berkeley) 6/6/93";
#endif /* not lint */

/*
 * traceroute host  - trace the route ip packets follow going to "host".
 *
 * Attempt to trace the route an ip packet would follow to some
 * internet host.  We find out intermediate hops by launching probe
 * packets with a small ttl (time to live) then listening for an
 * icmp "time exceeded" reply from a gateway.  We start our probes
 * with a ttl of one and increase by one until we get an icmp "port
 * unreachable" (which means we got to "host") or hit a max (which
 * defaults to 30 hops & can be changed with the -m flag).  Three
 * probes (change with -q flag) are sent at each ttl setting and a
 * line is printed showing the ttl, address of the gateway and
 * round trip time of each probe.  If the probe answers come from
 * different gateways, the address of each responding system will
 * be printed.  If there is no response within a 5 sec. timeout
 * interval (changed with the -w flag), a "*" is printed for that
 * probe.
 *
 * Probe packets are UDP format.  We don't want the destination
 * host to process them so the destination port is set to an
 * unlikely value (if some clod on the destination is using that
 * value, it can be changed with the -p flag).
 *
 * A sample use might be:
 *
 *     [yak 71]% traceroute nis.nsf.net.
 *     traceroute to nis.nsf.net (35.1.1.48), 30 hops max, 56 byte packet
 *      1  helios.ee.lbl.gov (128.3.112.1)  19 ms  19 ms  0 ms
 *      2  lilac-dmc.Berkeley.EDU (128.32.216.1)  39 ms  39 ms  19 ms
 *      3  lilac-dmc.Berkeley.EDU (128.32.216.1)  39 ms  39 ms  19 ms
 *      4  ccngw-ner-cc.Berkeley.EDU (128.32.136.23)  39 ms  40 ms  39 ms
 *      5  ccn-nerif22.Berkeley.EDU (128.32.168.22)  39 ms  39 ms  39 ms
 *      6  128.32.197.4 (128.32.197.4)  40 ms  59 ms  59 ms
 *      7  131.119.2.5 (131.119.2.5)  59 ms  59 ms  59 ms
 *      8  129.140.70.13 (129.140.70.13)  99 ms  99 ms  80 ms
 *      9  129.140.71.6 (129.140.71.6)  139 ms  239 ms  319 ms
 *     10  129.140.81.7 (129.140.81.7)  220 ms  199 ms  199 ms
 *     11  nic.merit.edu (35.1.1.48)  239 ms  239 ms  239 ms
 *
 * Note that lines 2 & 3 are the same.  This is due to a buggy
 * kernel on the 2nd hop system -- lbl-csam.arpa -- that forwards
 * packets with a zero ttl.
 *
 * A more interesting example is:
 *
 *     [yak 72]% traceroute allspice.lcs.mit.edu.
 *     traceroute to allspice.lcs.mit.edu (18.26.0.115), 30 hops max
 *      1  helios.ee.lbl.gov (128.3.112.1)  0 ms  0 ms  0 ms
 *      2  lilac-dmc.Berkeley.EDU (128.32.216.1)  19 ms  19 ms  19 ms
 *      3  lilac-dmc.Berkeley.EDU (128.32.216.1)  39 ms  19 ms  19 ms
 *      4  ccngw-ner-cc.Berkeley.EDU (128.32.136.23)  19 ms  39 ms  39 ms
 *      5  ccn-nerif22.Berkeley.EDU (128.32.168.22)  20 ms  39 ms  39 ms
 *      6  128.32.197.4 (128.32.197.4)  59 ms  119 ms  39 ms
 *      7  131.119.2.5 (131.119.2.5)  59 ms  59 ms  39 ms
 *      8  129.140.70.13 (129.140.70.13)  80 ms  79 ms  99 ms
 *      9  129.140.71.6 (129.140.71.6)  139 ms  139 ms  159 ms
 *     10  129.140.81.7 (129.140.81.7)  199 ms  180 ms  300 ms
 *     11  129.140.72.17 (129.140.72.17)  300 ms  239 ms  239 ms
 *     12  * * *
 *     13  128.121.54.72 (128.121.54.72)  259 ms  499 ms  279 ms
 *     14  * * *
 *     15  * * *
 *     16  * * *
 *     17  * * *
 *     18  ALLSPICE.LCS.MIT.EDU (18.26.0.115)  339 ms  279 ms  279 ms
 *
 * (I start to see why I'm having so much trouble with mail to
 * MIT.)  Note that the gateways 12, 14, 15, 16 & 17 hops away
 * either don't send ICMP "time exceeded" messages or send them
 * with a ttl too small to reach us.  14 - 17 are running the
 * MIT C Gateway code that doesn't send "time exceeded"s.  God
 * only knows what's going on with 12.
 *
 * The silent gateway 12 in the above may be the result of a bug in
 * the 4.[23]BSD network code (and its derivatives):  4.x (x <= 3)
 * sends an unreachable message using whatever ttl remains in the
 * original datagram.  Since, for gateways, the remaining ttl is
 * zero, the icmp "time exceeded" is guaranteed to not make it back
 * to us.  The behavior of this bug is slightly more interesting
 * when it appears on the destination system:
 *
 *      1  helios.ee.lbl.gov (128.3.112.1)  0 ms  0 ms  0 ms
 *      2  lilac-dmc.Berkeley.EDU (128.32.216.1)  39 ms  19 ms  39 ms
 *      3  lilac-dmc.Berkeley.EDU (128.32.216.1)  19 ms  39 ms  19 ms
 *      4  ccngw-ner-cc.Berkeley.EDU (128.32.136.23)  39 ms  40 ms  19 ms
 *      5  ccn-nerif35.Berkeley.EDU (128.32.168.35)  39 ms  39 ms  39 ms
 *      6  csgw.Berkeley.EDU (128.32.133.254)  39 ms  59 ms  39 ms
 *      7  * * *
 *      8  * * *
 *      9  * * *
 *     10  * * *
 *     11  * * *
 *     12  * * *
 *     13  rip.Berkeley.EDU (128.32.131.22)  59 ms !  39 ms !  39 ms !
 *
 * Notice that there are 12 "gateways" (13 is the final
 * destination) and exactly the last half of them are "missing".
 * What's really happening is that rip (a Sun-3 running Sun OS3.5)
 * is using the ttl from our arriving datagram as the ttl in its
 * icmp reply.  So, the reply will time out on the return path
 * (with no notice sent to anyone since icmp's aren't sent for
 * icmp's) until we probe with a ttl that's at least twice the path
 * length.  I.e., rip is really only 7 hops away.  A reply that
 * returns with a ttl of 1 is a clue this problem exists.
 * Traceroute prints a "!" after the time if the ttl is <= 1.
 * Since vendors ship a lot of obsolete (DEC's Ultrix, Sun 3.x) or
 * non-standard (HPUX) software, expect to see this problem
 * frequently and/or take care picking the target host of your
 * probes.
 *
 * Other possible annotations after the time are !H, !N, !P (got a host,
 * network or protocol unreachable, respectively), !S or !F (source
 * route failed or fragmentation needed -- neither of these should
 * ever occur and the associated gateway is busted if you see one).  If
 * almost all the probes result in some kind of unreachable, traceroute
 * will give up and exit.
 *
 * Notes
 * -----
 * This program must be run by root or be setuid.  (I suggest that
 * you *don't* make it setuid -- casual use could result in a lot
 * of unnecessary traffic on our poor, congested nets.)
 *
 * This program requires a kernel mod that does not appear in any
 * system available from Berkeley:  A raw ip socket using proto
 * IPPROTO_RAW must interpret the data sent as an ip datagram (as
 * opposed to data to be wrapped in a ip datagram).  See the README
 * file that came with the source to this program for a description
 * of the mods I made to /sys/netinet/raw_ip.c.  Your mileage may
 * vary.  But, again, ANY 4.x (x < 4) BSD KERNEL WILL HAVE TO BE
 * MODIFIED TO RUN THIS PROGRAM.
 *
 * The udp port usage may appear bizarre (well, ok, it is bizarre).
 * The problem is that an icmp message only contains 8 bytes of
 * data from the original datagram.  8 bytes is the size of a udp
 * header so, if we want to associate replies with the original
 * datagram, the necessary information must be encoded into the
 * udp header (the ip id could be used but there's no way to
 * interlock with the kernel's assignment of ip id's and, anyway,
 * it would have taken a lot more kernel hacking to allow this
 * code to set the ip id).  So, to allow two or more users to
 * use traceroute simultaneously, we use this task's pid as the
 * source port (the high bit is set to move the port number out
 * of the "likely" range).  To keep track of which probe is being
 * replied to (so times and/or hop counts don't get confused by a
 * reply that was delayed in transit), we increment the destination
 * port number before each probe.
 *
 * Don't use this as a coding example.  I was trying to find a
 * routing problem and this code sort-of popped out after 48 hours
 * without sleep.  I was amazed it ever compiled, much less ran.
 *
 * I stole the idea for this program from Steve Deering.  Since
 * the first release, I've learned that had I attended the right
 * IETF working group meetings, I also could have stolen it from Guy
 * Almes or Matt Mathis.  I don't know (or care) who came up with
 * the idea first.  I envy the originators' perspicacity and I'm
 * glad they didn't keep the idea a secret.
 *
 * Tim Seaver, Ken Adelman and C. Philip Wood provided bug fixes and/or
 * enhancements to the original distribution.
 *
 * I've hacked up a round-trip-route version of this that works by
 * sending a loose-source-routed udp datagram through the destination
 * back to yourself.  Unfortunately, SO many gateways botch source
 * routing, the thing is almost worthless.  Maybe one day...
 *
 *  -- Van Jacobson ([e-mail])
 *     Tue Dec 20 03:50:13 PST 1988
 */

#include <sys/param.h>
#include <sys/time.h>
#include <sys/socket.h>
#include <sys/uio.h>
#include <sys/file.h>
#include <sys/ioctl.h>
#include <sys/sysctl.h>

#include <netinet/in.h>

#include <arpa/inet.h>

#include <netdb.h>
#include <stdio.h>
#include <err.h>
#ifdef HAVE_POLL
#include <poll.h>
#endif
#include <errno.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>

#include <netinet/ip6.h>
#include <netinet/icmp6.h>
#include <netinet/udp.h>

#ifdef IPSEC
#include <net/route.h>
#include <netinet6/ipsec.h>
#endif

#define DUMMY_PORT 10010

#define	MAXPACKET	65535	/* max ip packet size */

#ifndef HAVE_GETIPNODEBYNAME
#define getipnodebyname(x, y, z, u)	gethostbyname2((x), (y))
#define freehostent(x)
#endif

/*
 * format of a (udp) probe packet.
 */
struct opacket {
	u_char seq;		/* sequence number of this packet */
	u_char hops;		/* hop limit of the packet */
	struct timeval tv;	/* time packet left */
};
struct tv32 {
	u_int32_t tv32_sec;
	u_int32_t tv32_usec;
};

u_char	packet[512];		/* last inbound (icmp) packet */
struct opacket	*outpacket;	/* last output (udp) packet */

int	main __P((int, char *[]));
int	wait_for_reply __P((int, struct msghdr *));
#ifdef IPSEC
#ifdef IPSEC_POLICY_IPSEC
int	setpolicy __P((int so, char *policy));
#endif
#endif
void	send_probe __P((int, int));
struct udphdr *get_udphdr __P((struct ip6_hdr *, u_char *));
int	get_hoplim __P((struct msghdr *));
double	deltaT __P((struct timeval *, struct timeval *));
char	*pr_type __P((int));
int	packet_ok __P((struct msghdr *, int, int));
void	print __P((struct msghdr *, int));
void	tvsub __P((struct timeval *, struct timeval *));
const char *inetname __P((struct sockaddr *));
void	usage __P((void));

int rcvsock;			/* receive (icmp) socket file descriptor */
int sndsock;			/* send (udp) socket file descriptor */

struct msghdr rcvmhdr;
struct iovec rcviov[2];
int rcvhlim;
struct in6_pktinfo *rcvpktinfo;

struct sockaddr_in6 Src, Dst, Rcv;
int datalen;			/* How much data */
#define	ICMP6ECHOLEN	8
/* XXX: 2064 = 127(max hops in type 0 rthdr) * sizeof(ip6_hdr) + 16(margin) */
char rtbuf[2064];
#ifdef USE_RFC2292BIS
struct ip6_rthdr *rth;
#endif
struct cmsghdr *cmsg;

char *source = 0;
char *hostname;

int nprobes = 3;
int first_hop = 1;
int max_hops = 30;
u_int16_t srcport;
u_int16_t port = 32768+666;	/* start udp dest port # for probe packets */
u_int16_t ident;
int options;			/* socket options */
int verbose;
int waittime = 5;		/* time to wait for response (in seconds) */
int nflag;			/* print addresses numerically */
int useicmp;
int lflag;			/* print both numerical address & hostname */

int
main(argc, argv)
	int argc;
	char *argv[];
{
	struct hostent *hp;
	int error;
	struct addrinfo hints, *res;
	int ch, i, on, probe, seq, hops, rcvcmsglen;
	static u_char *rcvcmsgbuf;
	char hbuf[NI_MAXHOST], src0[NI_MAXHOST];
	char *ep;
	int mib[4] = { CTL_NET, PF_INET6, IPPROTO_IPV6, IPV6CTL_DEFHLIM };
	size_t size = sizeof(max_hops);
	u_long lport;
	int minlen;

	/*
	 * Receive ICMP
	 */
	if ((rcvsock = socket(AF_INET6, SOCK_RAW, IPPROTO_ICMPV6)) < 0) {
		perror("socket(ICMPv6)");
		exit(5);
	}

	/* revoke privs */
	seteuid(getuid());
	setuid(getuid());

	(void) sysctl(mib, sizeof(mib)/sizeof(mib[0]), &max_hops, &size,
	    NULL, 0);

	/* set a minimum set of socket options */
	on = 1;
	/* specify to tell receiving interface */
#ifdef IPV6_RECVPKTINFO
	if (setsockopt(rcvsock, IPPROTO_IPV6, IPV6_RECVPKTINFO, &on,
	    sizeof(on)) < 0)
		err(1, "setsockopt(IPV6_RECVPKTINFO)");
#else  /* old adv. API */
	if (setsockopt(rcvsock, IPPROTO_IPV6, IPV6_PKTINFO, &on,
	    sizeof(on)) < 0)
		err(1, "setsockopt(IPV6_PKTINFO)");
#endif

	/* specify to tell value of hoplimit field of received IP6 hdr */
#ifdef IPV6_RECVHOPLIMIT
	if (setsockopt(rcvsock, IPPROTO_IPV6, IPV6_RECVHOPLIMIT, &on,
	    sizeof(on)) < 0)
		err(1, "setsockopt(IPV6_RECVHOPLIMIT)");
#else  /* old adv. API */
	if (setsockopt(rcvsock, IPPROTO_IPV6, IPV6_HOPLIMIT, &on,
	    sizeof(on)) < 0)
		err(1, "setsockopt(IPV6_HOPLIMIT)");
#endif

	seq = 0;
	
	while ((ch = getopt(argc, argv, "df:g:Ilm:np:q:rs:w:v")) != -1)
		switch (ch) {
		case 'd':
			options |= SO_DEBUG;
			break;
		case 'f':
			ep = NULL;
			first_hop = strtoul(optarg, &ep, 0);
			if (!*argv || *ep) {
				fprintf(stderr,
				    "traceroute6: invalid min hoplimit.\n");
				exit(1);
			}
			if (first_hop > max_hops) {
				fprintf(stderr,
				    "traceroute6: min hoplimit must be <= %d.\n",
				    max_hops);
				exit(1);
			}
			break;
		case 'g':
			hp = getipnodebyname(optarg, AF_INET6, 0, &h_errno);
			if (hp == NULL) {
				fprintf(stderr,
				    "traceroute6: unknown host %s\n", optarg);
				exit(1);
			}
#ifdef USE_RFC2292BIS
			if (rth == NULL) {
				/*
				 * XXX: We can't detect the number of
				 * intermediate nodes yet.
				 */
				if ((rth = inet6_rth_init((void *)rtbuf,
				    sizeof(rtbuf), IPV6_RTHDR_TYPE_0,
				    0)) == NULL) {
					fprintf(stderr,
					    "inet6_rth_init failed.\n");
					exit(1);
				}
			}
			if (inet6_rth_add((void *)rth,
			    (struct in6_addr *)hp->h_addr)) {
				fprintf(stderr,
				    "inet6_rth_add failed for %s\n",