* Copyright (c) 1990 The Regents of the University of California.
* This code is derived from software contributed to Berkeley by
* %sccs.include.redist.c%
"@(#) Copyright (c) 1990 The Regents of the University of California.\n\
static char sccsid
[] = "@(#)traceroute.c 5.3 (Berkeley) %G%";
* 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 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).
* [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
* 13 128.121.54.72 (128.121.54.72) 259 ms 499 ms 279 ms
* 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
* 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
* 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
* 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 (van@helios.ee.lbl.gov)
* Tue Dec 20 03:50:13 PST 1988
#include <netinet/in_systm.h>
#include <netinet/ip_icmp.h>
#define MAXPACKET 65535 /* max ip packet size */
#define MAXHOSTNAMELEN 64
#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)))
#define Fprintf (void)fprintf
#define Sprintf (void)sprintf
#define Printf (void)printf
extern char *inet_ntoa();
extern u_long
inet_addr();
* format of a (udp) probe packet.
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 */
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 */
u_short port
= 32768+666; /* start udp dest port # for probe packets */
int options
; /* socket options */
int waittime
= 5; /* time to wait for response (in seconds) */
int nflag
; /* print addresses numerically */
struct sockaddr_in from
, *to
;
int ch
, i
, on
, probe
, seq
, tos
, ttl
;
to
= (struct sockaddr_in
*)&whereto
;
while ((ch
= getopt(argc
, argv
, "dm:np:q:rs:t:w:v")) != EOF
)
"traceroute: max ttl must be >1.\n");
"traceroute: port must be >0.\n");
"traceroute: nprobes must be >0.\n");
* set the ip source address of the outbound
* probe (e.g., on a multi-homed host).
if (tos
< 0 || tos
> 255) {
"traceroute: tos must be 0 to 255.\n");
"traceroute: wait must be >1 sec.\n");
(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)
hp
= gethostbyname(*argv
);
to
->sin_family
= hp
->h_addrtype
;
bcopy(hp
->h_addr
, (caddr_t
)&to
->sin_addr
, hp
->h_length
);
"traceroute: unknown host %s\n", *argv
);
if (datalen
< 0 || datalen
>= MAXPACKET
- sizeof(struct opacket
)) {
"traceroute: packet size must be 0 <= s < %ld.\n",
MAXPACKET
- sizeof(struct opacket
));
datalen
+= sizeof(struct opacket
);
outpacket
= (struct opacket
*)malloc((unsigned)datalen
);
perror("traceroute: malloc");
(void) bzero((char *)outpacket
, datalen
);
outpacket
->ip
.ip_dst
= to
->sin_addr
;
outpacket
->ip
.ip_tos
= tos
;
ident
= (getpid() & 0xffff) | 0x8000;
if ((pe
= getprotobyname("icmp")) == NULL
) {
Fprintf(stderr
, "icmp: unknown protocol\n");
if ((s
= socket(AF_INET
, SOCK_RAW
, pe
->p_proto
)) < 0) {
perror("traceroute: icmp socket");
(void) setsockopt(s
, SOL_SOCKET
, SO_DEBUG
,
(char *)&on
, sizeof(on
));
if (options
& SO_DONTROUTE
)
(void) setsockopt(s
, SOL_SOCKET
, SO_DONTROUTE
,
(char *)&on
, sizeof(on
));
if ((sndsock
= socket(AF_INET
, SOCK_RAW
, IPPROTO_RAW
)) < 0) {
perror("traceroute: raw socket");
if (setsockopt(sndsock
, SOL_SOCKET
, SO_SNDBUF
, (char *)&datalen
,
perror("traceroute: SO_SNDBUF");
if (setsockopt(sndsock
, IPPROTO_IP
, IP_HDRINCL
, (char *)&on
,
perror("traceroute: IP_HDRINCL");
(void) setsockopt(sndsock
, SOL_SOCKET
, SO_DEBUG
,
(char *)&on
, sizeof(on
));
if (options
& SO_DONTROUTE
)
(void) setsockopt(sndsock
, SOL_SOCKET
, SO_DONTROUTE
,
(char *)&on
, sizeof(on
));
(void) bzero((char *)&from
, sizeof(struct sockaddr
));
from
.sin_family
= AF_INET
;
from
.sin_addr
.s_addr
= inet_addr(source
);
if (from
.sin_addr
.s_addr
== -1) {
Printf("traceroute: unknown host %s\n", source
);
outpacket
->ip
.ip_src
= from
.sin_addr
;
if (bind(sndsock
, (struct sockaddr
*)&from
, sizeof(from
)) < 0) {
perror ("traceroute: bind:");
Fprintf(stderr
, "traceroute to %s (%s)", hostname
,
inet_ntoa(to
->sin_addr
));
Fprintf(stderr
, " from %s", source
);
Fprintf(stderr
, ", %d hops max, %d byte packets\n", max_ttl
, datalen
);
for (ttl
= 1; ttl
<= max_ttl
; ++ttl
) {
for (probe
= 0; probe
< nprobes
; ++probe
) {
(void) gettimeofday(&tv
, &tz
);
while (cc
= wait_for_reply(s
, &from
)) {
if ((i
= packet_ok(packet
, cc
, &from
, seq
))) {
if (from
.sin_addr
.s_addr
!= lastaddr
) {
print(packet
, cc
, &from
);
lastaddr
= from
.sin_addr
.s_addr
;
ip
= (struct ip
*)packet
;
case ICMP_UNREACH_PROTOCOL
:
case ICMP_UNREACH_NEEDFRAG
:
case ICMP_UNREACH_SRCFAIL
:
if (got_there
|| unreachable
>= nprobes
-1)
wait_for_reply(sock
, from
)
struct sockaddr_in
*from
;
int fromlen
= sizeof (*from
);
wait
.tv_sec
= waittime
; wait
.tv_usec
= 0;
if (select(sock
+1, &fds
, (fd_set
*)0, (fd_set
*)0, &wait
) > 0)
cc
=recvfrom(s
, (char *)packet
, sizeof(packet
), 0,
(struct sockaddr
*)from
, &fromlen
);
struct opacket
*op
= outpacket
;
struct udphdr
*up
= &op
->udp
;
up
->uh_sport
= htons(ident
);
up
->uh_dport
= htons(port
+seq
);
up
->uh_ulen
= htons((u_short
)(datalen
- sizeof(struct ip
)));
(void) gettimeofday(&op
->tv
, &tz
);
i
= sendto(sndsock
, (char *)outpacket
, datalen
, 0, &whereto
,
sizeof(struct sockaddr
));
if (i
< 0 || i
!= datalen
) {
Printf("traceroute: wrote %s %d chars, ret=%d\n", hostname
,
(void) gettimeofday(&tv
, &tz
);
return (tv
.tv_sec
*1000 + (tv
.tv_usec
+ 500)/1000);
* Convert an ICMP "type" field to a printable string.
"Echo Reply", "ICMP 1", "ICMP 2", "Dest Unreachable",
"Source Quench", "Redirect", "ICMP 6", "ICMP 7",
"Echo", "ICMP 9", "ICMP 10", "Time Exceeded",
"Param Problem", "Timestamp", "Timestamp Reply", "Info Request",
packet_ok(buf
, cc
, from
, seq
)
struct sockaddr_in
*from
;
register struct icmp
*icp
;
if (cc
< hlen
+ ICMP_MINLEN
) {
Printf("packet too short (%d bytes) from %s\n", cc
,
inet_ntoa(from
->sin_addr
));
icp
= (struct icmp
*)(buf
+ hlen
);
icp
= (struct icmp
*)buf
;
type
= icp
->icmp_type
; code
= icp
->icmp_code
;
if ((type
== ICMP_TIMXCEED
&& code
== ICMP_TIMXCEED_INTRANS
) ||
up
= (struct udphdr
*)((u_char
*)hip
+ hlen
);
if (hlen
+ 12 <= cc
&& hip
->ip_p
== IPPROTO_UDP
&&
up
->uh_sport
== htons(ident
) &&
up
->uh_dport
== htons(port
+seq
))
return (type
== ICMP_TIMXCEED
? -1 : code
+1);
u_long
*lp
= (u_long
*)&icp
->icmp_ip
;
Printf("\n%d bytes from %s to %s", cc
,
inet_ntoa(from
->sin_addr
), inet_ntoa(ip
->ip_dst
));
Printf(": icmp type %d (%s) code %d\n", type
, pr_type(type
),
for (i
= 4; i
< cc
; i
+= sizeof(long))
Printf("%2d: x%8.8lx\n", i
, *lp
++);
struct sockaddr_in
*from
;
Printf(" %s", inet_ntoa(from
->sin_addr
));
Printf(" %s (%s)", inetname(from
->sin_addr
),
inet_ntoa(from
->sin_addr
));
Printf (" %d bytes to %s", cc
, inet_ntoa (ip
->ip_dst
));
* Checksum routine for Internet Protocol family headers (C Version)
register int nleft
= len
;
register u_short
*w
= addr
;
* Our algorithm is simple, using a 32 bit accumulator (sum),
* we add sequential 16 bit words to it, and at the end, fold
* back all the carry bits from the top 16 bits into the lower
/* mop up an odd byte, if necessary */
* add back carry outs from top 16 bits to low 16 bits
sum
= (sum
>> 16) + (sum
& 0xffff); /* add hi 16 to low 16 */
sum
+= (sum
>> 16); /* add carry */
answer
= ~sum
; /* truncate to 16 bits */
* Subtract 2 timeval structs: out = out - in.
* Out is assumed to be >= in.
register struct timeval
*out
, *in
;
if ((out
->tv_usec
-= in
->tv_usec
) < 0) {
out
->tv_sec
-= in
->tv_sec
;
* Construct an Internet address representation.
* If the nflag has been supplied, give
* numeric value, otherwise try for symbolic name.
static char domain
[MAXHOSTNAMELEN
+ 1];
if (gethostname(domain
, MAXHOSTNAMELEN
) == 0 &&
(cp
= index(domain
, '.')))
(void) strcpy(domain
, cp
+ 1);
if (!nflag
&& in
.s_addr
!= INADDR_ANY
) {
hp
= gethostbyaddr((char *)&in
, sizeof (in
), AF_INET
);
if ((cp
= index(hp
->h_name
, '.')) &&
in
.s_addr
= ntohl(in
.s_addr
);
#define C(x) ((x) & 0xff)
Sprintf(line
, "%lu.%lu.%lu.%lu", C(in
.s_addr
>> 24),
C(in
.s_addr
>> 16), C(in
.s_addr
>> 8), C(in
.s_addr
));
"usage: traceroute [-dnrv] [-m max_ttl] [-p port#] [-q nqueries]\n\t\
[-s src_addr] [-t tos] [-w wait] host [data size]\n");