traceroute.pmtu.c

TCP／IP详解

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

#ifndef lint
static char sccsid[] = "@(#)traceroute.c	5.4 (Berkeley) 5/15/90";
#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/types.h>
#include <sys/param.h>
#include <sys/time.h>
#ifdef	_AIX
#include <sys/select.h>
#endif
#include <sys/socket.h>
#include <sys/file.h>
#include <sys/ioctl.h>

#include <netinet/in_systm.h>
#include <netinet/in.h>
#include <netinet/ip.h>
#include <netinet/ip_var.h>
#include <netinet/ip_icmp.h>
#include <netinet/udp.h>
#include <netdb.h>
#include <ctype.h>

#include <stdio.h>
#include <errno.h>
#include <string.h>

#define	MAXPACKET	65535	/* max ip packet size */
#ifndef MAXHOSTNAMELEN
#define MAXHOSTNAMELEN	64
#endif

#ifndef FD_SET
#define NFDBITS         (8*sizeof(fd_set))
#define FD_SETSIZE      NFDBITS
#define FD_SET(n, p)    ((p)->fds_bits[(n)/NFDBITS] |= (1 << ((n) % NFDBITS)))
#define FD_CLR(n, p)    ((p)->fds_bits[(n)/NFDBITS] &= ~(1 << ((n) % NFDBITS)))
#define FD_ISSET(n, p)  ((p)->fds_bits[(n)/NFDBITS] & (1 << ((n) % NFDBITS)))
#define FD_ZERO(p)      bzero((char *)(p), sizeof(*(p)))
#endif

#define Fprintf (void)fprintf
#define Sprintf (void)sprintf
#define Printf (void)printf
extern	int errno;
extern  char *malloc();
extern  char *inet_ntoa();
extern  u_long inet_addr();

/*
 * format of a (udp) probe packet.
 */
struct opacket {
	struct ip ip;
	struct udphdr udp;
	u_char seq;		/* sequence number of this packet */
	u_char ttl;		/* ttl packet left with */
	struct timeval tv;	/* time packet left */
};

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

int s;				/* receive (icmp) socket file descriptor */
int sndsock;			/* send (udp) socket file descriptor */
struct timezone tz;		/* leftover */

struct sockaddr whereto;	/* Who to try to reach */

int datalen;		/* How much data */
int mtus[] = {
	17914,
	 8166,
	 4464,
	 4352,
	 2048,
	 2002,
	 1536,
	 1500,
	 1492,
	 1006,
	  576,
	  552,
	  544,
	  512,
	  508,
	  296,
	   68,
	    0
};
int *mtuptr = &mtus[0];
/* start at 16 Mb token ring, since not all systems like SO_SNDBUF of 65535 */

char *source = 0;
char *hostname;

int nprobes = 3;
int max_ttl = 30;
u_short ident;
u_short port = 32768+666;	/* start udp dest port # for probe packets */
int options;			/* socket options */
int verbose;
int waittime = 5;		/* time to wait for response (in seconds) */
int nflag;			/* print addresses numerically */

	/* some implementations require IP_OPTIONS arg be on 4-byte boundary */
u_char optlist[MAX_IPOPTLEN];

main(argc, argv)
	char *argv[];
{
	extern char *optarg;
	extern int optind;
	struct hostent *hp;
	struct protoent *pe;
	struct sockaddr_in from, *to;
	int ch, i, on, probe, seq, tos, ttl;
 	int lsrr = 0;
 	u_long gw;
 	u_char *oix;
 
	on = 1;
	seq = tos = 0;
	to = (struct sockaddr_in *)&whereto;
	while ((ch = getopt(argc, argv, "dg:G:m:np:q:rs:t:w:v")) != EOF)
		switch(ch) {
		case 'd':
			options |= SO_DEBUG;
			break;
		case 'G':	/* strict */
		case 'g':	/* loose */
					/* can specify multiple times */
			if ((lsrr+1) >=
			    ((MAX_IPOPTLEN-IPOPT_MINOFF)/sizeof(u_long))) {
			  Fprintf(stderr,"No more than %d gateways\n",
			       ((MAX_IPOPTLEN-IPOPT_MINOFF)/sizeof(u_long))-1);
			  exit(1);
			}
			if (lsrr == 0) {	/* first one */
 			  oix = optlist;
 			  bzero(optlist, sizeof(optlist));
			  *oix++ = (ch == 'G') ? IPOPT_SSRR : IPOPT_LSRR;
			  *oix++;	/* fill in total length later */
			  *oix++ = IPOPT_MINOFF; /* ptr to LSRR addresses */
			}
			lsrr++;
				/* first try as dotted-decimal, then as name */
			if ( (gw = inet_addr(optarg)) != 0xffffffff) {
			    bcopy(&gw, oix, sizeof(u_long));
			    Fprintf(stderr, "LSRR to %8x\n", ntohl(gw));
			} else {
			  if ( (hp = gethostbyname(optarg)) != NULL) {
			    bcopy(hp->h_addr, oix, sizeof(u_long));
			    Fprintf(stderr, "LSRR to %8x\n",
					ntohl(*((u_long *)hp->h_addr)));
			  } else {
			    Fprintf(stderr, "Unknown host %s\n",optarg);
			    exit(1);
			  }
			}
			oix += sizeof(u_long);	/* for next IP addr in list */
			break;
		case 'm':
			max_ttl = atoi(optarg);
			if (max_ttl <= 1) {
				Fprintf(stderr,
				    "traceroute: max ttl must be >1.\n");
				exit(1);
			}
			break;
		case 'n':
			nflag++;
			break;
		case 'p':
			port = atoi(optarg);
			if (port < 1) {
				Fprintf(stderr,
				    "traceroute: port must be >0.\n");
				exit(1);
			}
			break;
		case 'q':
			nprobes = atoi(optarg);
			if (nprobes < 1) {
				Fprintf(stderr,
				    "traceroute: nprobes must be >0.\n");
				exit(1);
			}
			break;
		case 'r':
			options |= SO_DONTROUTE;
			break;
		case 's':
			/*
			 * set the ip source address of the outbound
			 * probe (e.g., on a multi-homed host).
			 */
			source = optarg;
			break;
		case 't':
			tos = atoi(optarg);
			if (tos < 0 || tos > 255) {
				Fprintf(stderr,
				    "traceroute: tos must be 0 to 255.\n");
				exit(1);
			}
			break;
		case 'v':
			verbose++;
			break;
		case 'w':
			waittime = atoi(optarg);
			if (waittime <= 1) {
				Fprintf(stderr,
				    "traceroute: wait must be >1 sec.\n");
				exit(1);
			}
			break;
		default:
			usage();
		}
	argc -= optind;
	argv += optind;

	if (argc < 1) 
		usage();

	setlinebuf (stdout);

	(void) bzero((char *)&whereto, sizeof(struct sockaddr));
	to->sin_family = AF_INET;
	to->sin_addr.s_addr = inet_addr(*argv);
	if (to->sin_addr.s_addr != -1) 
		hostname = *argv;
	else {
		hp = gethostbyname(*argv);
		if (hp) {
			to->sin_family = hp->h_addrtype;
			bcopy(hp->h_addr, (caddr_t)&to->sin_addr, hp->h_length);
			hostname = hp->h_name;
		} else {
			(void)fprintf(stderr,
			    "traceroute: unknown host %s\n", *argv);
			exit(1);
		}
	}
	if (*++argv) 
		datalen = atoi(*argv);
	else
		datalen = (*mtuptr++) - sizeof(struct opacket);

	if (datalen < 0 || datalen >= MAXPACKET - sizeof(struct opacket)) {
		Fprintf(stderr,
		    "traceroute: packet size must be 0 <= s < %ld.\n",
		    MAXPACKET - sizeof(struct opacket));
		exit(1);
	}
	datalen += sizeof(struct opacket);
	outpacket = (struct opacket *)malloc((unsigned)datalen);
	if (! outpacket) {
		perror("traceroute: malloc");
		exit(1);
	}
	(void) bzero((char *)outpacket, datalen);
	outpacket->ip.ip_dst = to->sin_addr;
	outpacket->ip.ip_tos = tos;