summaryrefslogtreecommitdiffstats
path: root/sys/netinet/ip_icmp.c
blob: 4bb6b7337ae3ca9ddd0c347bda041c471b6f6a46 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
/*-
 * Copyright (c) 1982, 1986, 1988, 1993
 *	The Regents of the University of California.  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.
 * 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.
 *
 *	@(#)ip_icmp.c	8.2 (Berkeley) 1/4/94
 */

#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");

#include "opt_inet.h"

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/mbuf.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/time.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/rmlock.h>
#include <sys/sysctl.h>
#include <sys/syslog.h>

#include <net/if.h>
#include <net/if_var.h>
#include <net/if_types.h>
#include <net/route.h>
#include <net/vnet.h>

#include <netinet/in.h>
#include <netinet/in_fib.h>
#include <netinet/in_pcb.h>
#include <netinet/in_systm.h>
#include <netinet/in_var.h>
#include <netinet/ip.h>
#include <netinet/ip_icmp.h>
#include <netinet/ip_var.h>
#include <netinet/ip_options.h>
#include <netinet/sctp.h>
#include <netinet/tcp.h>
#include <netinet/tcp_var.h>
#include <netinet/tcpip.h>
#include <netinet/icmp_var.h>

#ifdef INET

#include <machine/in_cksum.h>

#include <security/mac/mac_framework.h>
#endif /* INET */

/*
 * ICMP routines: error generation, receive packet processing, and
 * routines to turnaround packets back to the originator, and
 * host table maintenance routines.
 */
static VNET_DEFINE(int, icmplim) = 200;
#define	V_icmplim			VNET(icmplim)
SYSCTL_INT(_net_inet_icmp, ICMPCTL_ICMPLIM, icmplim, CTLFLAG_VNET | CTLFLAG_RW,
	&VNET_NAME(icmplim), 0,
	"Maximum number of ICMP responses per second");

static VNET_DEFINE(int, icmplim_output) = 1;
#define	V_icmplim_output		VNET(icmplim_output)
SYSCTL_INT(_net_inet_icmp, OID_AUTO, icmplim_output, CTLFLAG_VNET | CTLFLAG_RW,
	&VNET_NAME(icmplim_output), 0,
	"Enable logging of ICMP response rate limiting");

#ifdef INET
VNET_PCPUSTAT_DEFINE(struct icmpstat, icmpstat);
VNET_PCPUSTAT_SYSINIT(icmpstat);
SYSCTL_VNET_PCPUSTAT(_net_inet_icmp, ICMPCTL_STATS, stats, struct icmpstat,
    icmpstat, "ICMP statistics (struct icmpstat, netinet/icmp_var.h)");

#ifdef VIMAGE
VNET_PCPUSTAT_SYSUNINIT(icmpstat);
#endif /* VIMAGE */

static VNET_DEFINE(int, icmpmaskrepl) = 0;
#define	V_icmpmaskrepl			VNET(icmpmaskrepl)
SYSCTL_INT(_net_inet_icmp, ICMPCTL_MASKREPL, maskrepl, CTLFLAG_VNET | CTLFLAG_RW,
	&VNET_NAME(icmpmaskrepl), 0,
	"Reply to ICMP Address Mask Request packets");

static VNET_DEFINE(u_int, icmpmaskfake) = 0;
#define	V_icmpmaskfake			VNET(icmpmaskfake)
SYSCTL_UINT(_net_inet_icmp, OID_AUTO, maskfake, CTLFLAG_VNET | CTLFLAG_RW,
	&VNET_NAME(icmpmaskfake), 0,
	"Fake reply to ICMP Address Mask Request packets");

VNET_DEFINE(int, drop_redirect) = 0;
#define	V_drop_redirect			VNET(drop_redirect)
SYSCTL_INT(_net_inet_icmp, OID_AUTO, drop_redirect, CTLFLAG_VNET | CTLFLAG_RW,
	&VNET_NAME(drop_redirect), 0,
	"Ignore ICMP redirects");

static VNET_DEFINE(int, log_redirect) = 0;
#define	V_log_redirect			VNET(log_redirect)
SYSCTL_INT(_net_inet_icmp, OID_AUTO, log_redirect, CTLFLAG_VNET | CTLFLAG_RW,
	&VNET_NAME(log_redirect), 0,
	"Log ICMP redirects to the console");

static VNET_DEFINE(char, reply_src[IFNAMSIZ]);
#define	V_reply_src			VNET(reply_src)
SYSCTL_STRING(_net_inet_icmp, OID_AUTO, reply_src, CTLFLAG_VNET | CTLFLAG_RW,
	&VNET_NAME(reply_src), IFNAMSIZ,
	"ICMP reply source for non-local packets");

static VNET_DEFINE(int, icmp_rfi) = 0;
#define	V_icmp_rfi			VNET(icmp_rfi)
SYSCTL_INT(_net_inet_icmp, OID_AUTO, reply_from_interface, CTLFLAG_VNET | CTLFLAG_RW,
	&VNET_NAME(icmp_rfi), 0,
	"ICMP reply from incoming interface for non-local packets");

static VNET_DEFINE(int, icmp_quotelen) = 8;
#define	V_icmp_quotelen			VNET(icmp_quotelen)
SYSCTL_INT(_net_inet_icmp, OID_AUTO, quotelen, CTLFLAG_VNET | CTLFLAG_RW,
	&VNET_NAME(icmp_quotelen), 0,
	"Number of bytes from original packet to quote in ICMP reply");

static VNET_DEFINE(int, icmpbmcastecho) = 0;
#define	V_icmpbmcastecho		VNET(icmpbmcastecho)
SYSCTL_INT(_net_inet_icmp, OID_AUTO, bmcastecho, CTLFLAG_VNET | CTLFLAG_RW,
	&VNET_NAME(icmpbmcastecho), 0,
	"Reply to multicast ICMP Echo Request and Timestamp packets");

static VNET_DEFINE(int, icmptstamprepl) = 1;
#define	V_icmptstamprepl		VNET(icmptstamprepl)
SYSCTL_INT(_net_inet_icmp, OID_AUTO, tstamprepl, CTLFLAG_RW,
	&VNET_NAME(icmptstamprepl), 0,
	"Respond to ICMP Timestamp packets");

#ifdef ICMPPRINTFS
int	icmpprintfs = 0;
#endif

static void	icmp_reflect(struct mbuf *);
static void	icmp_send(struct mbuf *, struct mbuf *);

extern	struct protosw inetsw[];

/*
 * Kernel module interface for updating icmpstat.  The argument is an index
 * into icmpstat treated as an array of u_long.  While this encodes the
 * general layout of icmpstat into the caller, it doesn't encode its
 * location, so that future changes to add, for example, per-CPU stats
 * support won't cause binary compatibility problems for kernel modules.
 */
void
kmod_icmpstat_inc(int statnum)
{

	counter_u64_add(VNET(icmpstat)[statnum], 1);
}

/*
 * Generate an error packet of type error
 * in response to bad packet ip.
 */
void
icmp_error(struct mbuf *n, int type, int code, uint32_t dest, int mtu)
{
	register struct ip *oip = mtod(n, struct ip *), *nip;
	register unsigned oiphlen = oip->ip_hl << 2;
	register struct icmp *icp;
	register struct mbuf *m;
	unsigned icmplen, icmpelen, nlen;

	KASSERT((u_int)type <= ICMP_MAXTYPE, ("%s: illegal ICMP type", __func__));
#ifdef ICMPPRINTFS
	if (icmpprintfs)
		printf("icmp_error(%p, %x, %d)\n", oip, type, code);
#endif
	if (type != ICMP_REDIRECT)
		ICMPSTAT_INC(icps_error);
	/*
	 * Don't send error:
	 *  if the original packet was encrypted.
	 *  if not the first fragment of message.
	 *  in response to a multicast or broadcast packet.
	 *  if the old packet protocol was an ICMP error message.
	 */
	if (n->m_flags & M_DECRYPTED)
		goto freeit;
	if (oip->ip_off & htons(~(IP_MF|IP_DF)))
		goto freeit;
	if (n->m_flags & (M_BCAST|M_MCAST))
		goto freeit;
	if (oip->ip_p == IPPROTO_ICMP && type != ICMP_REDIRECT &&
	  n->m_len >= oiphlen + ICMP_MINLEN &&
	  !ICMP_INFOTYPE(((struct icmp *)((caddr_t)oip + oiphlen))->icmp_type)) {
		ICMPSTAT_INC(icps_oldicmp);
		goto freeit;
	}
	/* Drop if IP header plus 8 bytes is not contignous in first mbuf. */
	if (oiphlen + 8 > n->m_len)
		goto freeit;
	/*
	 * Calculate length to quote from original packet and
	 * prevent the ICMP mbuf from overflowing.
	 * Unfortunately this is non-trivial since ip_forward()
	 * sends us truncated packets.
	 */
	nlen = m_length(n, NULL);
	if (oip->ip_p == IPPROTO_TCP) {
		struct tcphdr *th;
		int tcphlen;

		if (oiphlen + sizeof(struct tcphdr) > n->m_len &&
		    n->m_next == NULL)
			goto stdreply;
		if (n->m_len < oiphlen + sizeof(struct tcphdr) &&
		    ((n = m_pullup(n, oiphlen + sizeof(struct tcphdr))) == NULL))
			goto freeit;
		th = (struct tcphdr *)((caddr_t)oip + oiphlen);
		tcphlen = th->th_off << 2;
		if (tcphlen < sizeof(struct tcphdr))
			goto freeit;
		if (ntohs(oip->ip_len) < oiphlen + tcphlen)
			goto freeit;
		if (oiphlen + tcphlen > n->m_len && n->m_next == NULL)
			goto stdreply;
		if (n->m_len < oiphlen + tcphlen && 
		    ((n = m_pullup(n, oiphlen + tcphlen)) == NULL))
			goto freeit;
		icmpelen = max(tcphlen, min(V_icmp_quotelen,
		    ntohs(oip->ip_len) - oiphlen));
	} else if (oip->ip_p == IPPROTO_SCTP) {
		struct sctphdr *sh;
		struct sctp_chunkhdr *ch;

		if (ntohs(oip->ip_len) < oiphlen + sizeof(struct sctphdr))
			goto stdreply;
		if (oiphlen + sizeof(struct sctphdr) > n->m_len &&
		    n->m_next == NULL)
			goto stdreply;
		if (n->m_len < oiphlen + sizeof(struct sctphdr) &&
		    (n = m_pullup(n, oiphlen + sizeof(struct sctphdr))) == NULL)
			goto freeit;
		icmpelen = max(sizeof(struct sctphdr),
		    min(V_icmp_quotelen, ntohs(oip->ip_len) - oiphlen));
		sh = (struct sctphdr *)((caddr_t)oip + oiphlen);
		if (ntohl(sh->v_tag) == 0 &&
		    ntohs(oip->ip_len) >= oiphlen + sizeof(struct sctphdr) + 8 &&
		    (n->m_len >= oiphlen + sizeof(struct sctphdr) + 8 ||
		     n->m_next != NULL)) {
			if (n->m_len < oiphlen + sizeof(struct sctphdr) + 8 &&
			    (n = m_pullup(n, oiphlen + sizeof(struct sctphdr) + 8)) == NULL)
				goto freeit;
			ch = (struct sctp_chunkhdr *)(sh + 1);
			if (ch->chunk_type == SCTP_INITIATION) {
				icmpelen = max(sizeof(struct sctphdr) + 8,
				    min(V_icmp_quotelen, ntohs(oip->ip_len) - oiphlen));
			}
		}
	} else
stdreply:	icmpelen = max(8, min(V_icmp_quotelen, ntohs(oip->ip_len) - oiphlen));

	icmplen = min(oiphlen + icmpelen, nlen);
	if (icmplen < sizeof(struct ip))
		goto freeit;

	if (MHLEN > sizeof(struct ip) + ICMP_MINLEN + icmplen)
		m = m_gethdr(M_NOWAIT, MT_DATA);
	else
		m = m_getcl(M_NOWAIT, MT_DATA, M_PKTHDR);
	if (m == NULL)
		goto freeit;
#ifdef MAC
	mac_netinet_icmp_reply(n, m);
#endif
	icmplen = min(icmplen, M_TRAILINGSPACE(m) - sizeof(struct ip) - ICMP_MINLEN);
	m_align(m, ICMP_MINLEN + icmplen);
	m->m_len = ICMP_MINLEN + icmplen;

	/* XXX MRT  make the outgoing packet use the same FIB
	 * that was associated with the incoming packet
	 */
	M_SETFIB(m, M_GETFIB(n));
	icp = mtod(m, struct icmp *);
	ICMPSTAT_INC(icps_outhist[type]);
	icp->icmp_type = type;
	if (type == ICMP_REDIRECT)
		icp->icmp_gwaddr.s_addr = dest;
	else {
		icp->icmp_void = 0;
		/*
		 * The following assignments assume an overlay with the
		 * just zeroed icmp_void field.
		 */
		if (type == ICMP_PARAMPROB) {
			icp->icmp_pptr = code;
			code = 0;
		} else if (type == ICMP_UNREACH &&
			code == ICMP_UNREACH_NEEDFRAG && mtu) {
			icp->icmp_nextmtu = htons(mtu);
		}
	}
	icp->icmp_code = code;

	/*
	 * Copy the quotation into ICMP message and
	 * convert quoted IP header back to network representation.
	 */
	m_copydata(n, 0, icmplen, (caddr_t)&icp->icmp_ip);
	nip = &icp->icmp_ip;

	/*
	 * Set up ICMP message mbuf and copy old IP header (without options
	 * in front of ICMP message.
	 * If the original mbuf was meant to bypass the firewall, the error
	 * reply should bypass as well.
	 */
	m->m_flags |= n->m_flags & M_SKIP_FIREWALL;
	m->m_data -= sizeof(struct ip);
	m->m_len += sizeof(struct ip);
	m->m_pkthdr.len = m->m_len;
	m->m_pkthdr.rcvif = n->m_pkthdr.rcvif;
	nip = mtod(m, struct ip *);
	bcopy((caddr_t)oip, (caddr_t)nip, sizeof(struct ip));
	nip->ip_len = htons(m->m_len);
	nip->ip_v = IPVERSION;
	nip->ip_hl = 5;
	nip->ip_p = IPPROTO_ICMP;
	nip->ip_tos = 0;
	nip->ip_off = 0;
	icmp_reflect(m);

freeit:
	m_freem(n);
}

/*
 * Process a received ICMP message.
 */
int
icmp_input(struct mbuf **mp, int *offp, int proto)
{
	struct icmp *icp;
	struct in_ifaddr *ia;
	struct mbuf *m = *mp;
	struct ip *ip = mtod(m, struct ip *);
	struct sockaddr_in icmpsrc, icmpdst, icmpgw;
	int hlen = *offp;
	int icmplen = ntohs(ip->ip_len) - *offp;
	int i, code;
	void (*ctlfunc)(int, struct sockaddr *, void *);
	int fibnum;

	*mp = NULL;

	/*
	 * Locate icmp structure in mbuf, and check
	 * that not corrupted and of at least minimum length.
	 */
#ifdef ICMPPRINTFS
	if (icmpprintfs) {
		char srcbuf[INET_ADDRSTRLEN];
		char dstbuf[INET_ADDRSTRLEN];

		printf("icmp_input from %s to %s, len %d\n",
		    inet_ntoa_r(ip->ip_src, srcbuf),
		    inet_ntoa_r(ip->ip_dst, dstbuf), icmplen);
	}
#endif
	if (icmplen < ICMP_MINLEN) {
		ICMPSTAT_INC(icps_tooshort);
		goto freeit;
	}
	i = hlen + min(icmplen, ICMP_ADVLENMIN);
	if (m->m_len < i && (m = m_pullup(m, i)) == NULL)  {
		ICMPSTAT_INC(icps_tooshort);
		return (IPPROTO_DONE);
	}
	ip = mtod(m, struct ip *);
	m->m_len -= hlen;
	m->m_data += hlen;
	icp = mtod(m, struct icmp *);
	if (in_cksum(m, icmplen)) {
		ICMPSTAT_INC(icps_checksum);
		goto freeit;
	}
	m->m_len += hlen;
	m->m_data -= hlen;

#ifdef ICMPPRINTFS
	if (icmpprintfs)
		printf("icmp_input, type %d code %d\n", icp->icmp_type,
		    icp->icmp_code);
#endif

	/*
	 * Message type specific processing.
	 */
	if (icp->icmp_type > ICMP_MAXTYPE)
		goto raw;

	/* Initialize */
	bzero(&icmpsrc, sizeof(icmpsrc));
	icmpsrc.sin_len = sizeof(struct sockaddr_in);
	icmpsrc.sin_family = AF_INET;
	bzero(&icmpdst, sizeof(icmpdst));
	icmpdst.sin_len = sizeof(struct sockaddr_in);
	icmpdst.sin_family = AF_INET;
	bzero(&icmpgw, sizeof(icmpgw));
	icmpgw.sin_len = sizeof(struct sockaddr_in);
	icmpgw.sin_family = AF_INET;

	ICMPSTAT_INC(icps_inhist[icp->icmp_type]);
	code = icp->icmp_code;
	switch (icp->icmp_type) {

	case ICMP_UNREACH:
		switch (code) {
			case ICMP_UNREACH_NET:
			case ICMP_UNREACH_HOST:
			case ICMP_UNREACH_SRCFAIL:
			case ICMP_UNREACH_NET_UNKNOWN:
			case ICMP_UNREACH_HOST_UNKNOWN:
			case ICMP_UNREACH_ISOLATED:
			case ICMP_UNREACH_TOSNET:
			case ICMP_UNREACH_TOSHOST:
			case ICMP_UNREACH_HOST_PRECEDENCE:
			case ICMP_UNREACH_PRECEDENCE_CUTOFF:
				code = PRC_UNREACH_NET;
				break;

			case ICMP_UNREACH_NEEDFRAG:
				code = PRC_MSGSIZE;
				break;

			/*
			 * RFC 1122, Sections 3.2.2.1 and 4.2.3.9.
			 * Treat subcodes 2,3 as immediate RST
			 */
			case ICMP_UNREACH_PROTOCOL:
				code = PRC_UNREACH_PROTOCOL;
				break;
			case ICMP_UNREACH_PORT:
				code = PRC_UNREACH_PORT;
				break;

			case ICMP_UNREACH_NET_PROHIB:
			case ICMP_UNREACH_HOST_PROHIB:
			case ICMP_UNREACH_FILTER_PROHIB:
				code = PRC_UNREACH_ADMIN_PROHIB;
				break;

			default:
				goto badcode;
		}
		goto deliver;

	case ICMP_TIMXCEED:
		if (code > 1)
			goto badcode;
		code += PRC_TIMXCEED_INTRANS;
		goto deliver;

	case ICMP_PARAMPROB:
		if (code > 1)
			goto badcode;
		code = PRC_PARAMPROB;
	deliver:
		/*
		 * Problem with datagram; advise higher level routines.
		 */
		if (icmplen < ICMP_ADVLENMIN || icmplen < ICMP_ADVLEN(icp) ||
		    icp->icmp_ip.ip_hl < (sizeof(struct ip) >> 2)) {
			ICMPSTAT_INC(icps_badlen);
			goto freeit;
		}
		/* Discard ICMP's in response to multicast packets */
		if (IN_MULTICAST(ntohl(icp->icmp_ip.ip_dst.s_addr)))
			goto badcode;
#ifdef ICMPPRINTFS
		if (icmpprintfs)
			printf("deliver to protocol %d\n", icp->icmp_ip.ip_p);
#endif
		icmpsrc.sin_addr = icp->icmp_ip.ip_dst;
		/*
		 * XXX if the packet contains [IPv4 AH TCP], we can't make a
		 * notification to TCP layer.
		 */
		i = sizeof(struct ip) + min(icmplen, ICMP_ADVLENPREF(icp));
		ip_stripoptions(m);
		if (m->m_len < i && (m = m_pullup(m, i)) == NULL) {
			/* This should actually not happen */
			ICMPSTAT_INC(icps_tooshort);
			return (IPPROTO_DONE);
		}
		ip = mtod(m, struct ip *);
		icp = (struct icmp *)(ip + 1);
		/*
		 * The upper layer handler can rely on:
		 * - The outer IP header has no options.
		 * - The outer IP header, the ICMP header, the inner IP header,
		 *   and the first n bytes of the inner payload are contiguous.
		 *   n is at least 8, but might be larger based on 
		 *   ICMP_ADVLENPREF. See its definition in ip_icmp.h.
		 */
		ctlfunc = inetsw[ip_protox[icp->icmp_ip.ip_p]].pr_ctlinput;
		if (ctlfunc)
			(*ctlfunc)(code, (struct sockaddr *)&icmpsrc,
				   (void *)&icp->icmp_ip);
		break;

	badcode:
		ICMPSTAT_INC(icps_badcode);
		break;

	case ICMP_ECHO:
		if (!V_icmpbmcastecho
		    && (m->m_flags & (M_MCAST | M_BCAST)) != 0) {
			ICMPSTAT_INC(icps_bmcastecho);
			break;
		}
		icp->icmp_type = ICMP_ECHOREPLY;
		if (badport_bandlim(BANDLIM_ICMP_ECHO) < 0)
			goto freeit;
		else
			goto reflect;

	case ICMP_TSTAMP:
		if (V_icmptstamprepl == 0)
			break;
		if (!V_icmpbmcastecho
		    && (m->m_flags & (M_MCAST | M_BCAST)) != 0) {
			ICMPSTAT_INC(icps_bmcasttstamp);
			break;
		}
		if (icmplen < ICMP_TSLEN) {
			ICMPSTAT_INC(icps_badlen);
			break;
		}
		icp->icmp_type = ICMP_TSTAMPREPLY;
		icp->icmp_rtime = iptime();
		icp->icmp_ttime = icp->icmp_rtime;	/* bogus, do later! */
		if (badport_bandlim(BANDLIM_ICMP_TSTAMP) < 0)
			goto freeit;
		else
			goto reflect;

	case ICMP_MASKREQ:
		if (V_icmpmaskrepl == 0)
			break;
		/*
		 * We are not able to respond with all ones broadcast
		 * unless we receive it over a point-to-point interface.
		 */
		if (icmplen < ICMP_MASKLEN)
			break;
		switch (ip->ip_dst.s_addr) {

		case INADDR_BROADCAST:
		case INADDR_ANY:
			icmpdst.sin_addr = ip->ip_src;
			break;

		default:
			icmpdst.sin_addr = ip->ip_dst;
		}
		ia = (struct in_ifaddr *)ifaof_ifpforaddr(
			    (struct sockaddr *)&icmpdst, m->m_pkthdr.rcvif);
		if (ia == NULL)
			break;
		if (ia->ia_ifp == NULL) {
			ifa_free(&ia->ia_ifa);
			break;
		}
		icp->icmp_type = ICMP_MASKREPLY;
		if (V_icmpmaskfake == 0)
			icp->icmp_mask = ia->ia_sockmask.sin_addr.s_addr;
		else
			icp->icmp_mask = V_icmpmaskfake;
		if (ip->ip_src.s_addr == 0) {
			if (ia->ia_ifp->if_flags & IFF_BROADCAST)
			    ip->ip_src = satosin(&ia->ia_broadaddr)->sin_addr;
			else if (ia->ia_ifp->if_flags & IFF_POINTOPOINT)
			    ip->ip_src = satosin(&ia->ia_dstaddr)->sin_addr;
		}
		ifa_free(&ia->ia_ifa);
reflect:
		ICMPSTAT_INC(icps_reflect);
		ICMPSTAT_INC(icps_outhist[icp->icmp_type]);
		icmp_reflect(m);
		return (IPPROTO_DONE);

	case ICMP_REDIRECT:
		if (V_log_redirect) {
			u_long src, dst, gw;

			src = ntohl(ip->ip_src.s_addr);
			dst = ntohl(icp->icmp_ip.ip_dst.s_addr);
			gw = ntohl(icp->icmp_gwaddr.s_addr);
			printf("icmp redirect from %d.%d.%d.%d: "
			       "%d.%d.%d.%d => %d.%d.%d.%d\n",
			       (int)(src >> 24), (int)((src >> 16) & 0xff),
			       (int)((src >> 8) & 0xff), (int)(src & 0xff),
			       (int)(dst >> 24), (int)((dst >> 16) & 0xff),
			       (int)((dst >> 8) & 0xff), (int)(dst & 0xff),
			       (int)(gw >> 24), (int)((gw >> 16) & 0xff),
			       (int)((gw >> 8) & 0xff), (int)(gw & 0xff));
		}
		/*
		 * RFC1812 says we must ignore ICMP redirects if we
		 * are acting as router.
		 */
		if (V_drop_redirect || V_ipforwarding)
			break;
		if (code > 3)
			goto badcode;
		if (icmplen < ICMP_ADVLENMIN || icmplen < ICMP_ADVLEN(icp) ||
		    icp->icmp_ip.ip_hl < (sizeof(struct ip) >> 2)) {
			ICMPSTAT_INC(icps_badlen);
			break;
		}
		/*
		 * Short circuit routing redirects to force
		 * immediate change in the kernel's routing
		 * tables.  The message is also handed to anyone
		 * listening on a raw socket (e.g. the routing
		 * daemon for use in updating its tables).
		 */
		icmpgw.sin_addr = ip->ip_src;
		icmpdst.sin_addr = icp->icmp_gwaddr;
#ifdef	ICMPPRINTFS
		if (icmpprintfs) {
			char dstbuf[INET_ADDRSTRLEN];
			char gwbuf[INET_ADDRSTRLEN];

			printf("redirect dst %s to %s\n",
			       inet_ntoa_r(icp->icmp_ip.ip_dst, dstbuf),
			       inet_ntoa_r(icp->icmp_gwaddr, gwbuf));
		}
#endif
		icmpsrc.sin_addr = icp->icmp_ip.ip_dst;
		for ( fibnum = 0; fibnum < rt_numfibs; fibnum++) {
			in_rtredirect((struct sockaddr *)&icmpsrc,
			  (struct sockaddr *)&icmpdst,
			  (struct sockaddr *)0, RTF_GATEWAY | RTF_HOST,
			  (struct sockaddr *)&icmpgw, fibnum);
		}
		pfctlinput(PRC_REDIRECT_HOST, (struct sockaddr *)&icmpsrc);
		break;

	/*
	 * No kernel processing for the following;
	 * just fall through to send to raw listener.
	 */
	case ICMP_ECHOREPLY:
	case ICMP_ROUTERADVERT:
	case ICMP_ROUTERSOLICIT:
	case ICMP_TSTAMPREPLY:
	case ICMP_IREQREPLY:
	case ICMP_MASKREPLY:
	case ICMP_SOURCEQUENCH:
	default:
		break;
	}

raw:
	*mp = m;
	rip_input(mp, offp, proto);
	return (IPPROTO_DONE);

freeit:
	m_freem(m);
	return (IPPROTO_DONE);
}

/*
 * Reflect the ip packet back to the source
 */
static void
icmp_reflect(struct mbuf *m)
{
	struct rm_priotracker in_ifa_tracker;
	struct ip *ip = mtod(m, struct ip *);
	struct ifaddr *ifa;
	struct ifnet *ifp;
	struct in_ifaddr *ia;
	struct in_addr t;
	struct nhop4_extended nh_ext;
	struct mbuf *opts = NULL;
	int optlen = (ip->ip_hl << 2) - sizeof(struct ip);

	if (IN_MULTICAST(ntohl(ip->ip_src.s_addr)) ||
	    IN_EXPERIMENTAL(ntohl(ip->ip_src.s_addr)) ||
	    IN_ZERONET(ntohl(ip->ip_src.s_addr)) ) {
		m_freem(m);	/* Bad return address */
		ICMPSTAT_INC(icps_badaddr);
		goto done;	/* Ip_output() will check for broadcast */
	}

	t = ip->ip_dst;
	ip->ip_dst = ip->ip_src;

	/*
	 * Source selection for ICMP replies:
	 *
	 * If the incoming packet was addressed directly to one of our
	 * own addresses, use dst as the src for the reply.
	 */
	IN_IFADDR_RLOCK(&in_ifa_tracker);
	LIST_FOREACH(ia, INADDR_HASH(t.s_addr), ia_hash) {
		if (t.s_addr == IA_SIN(ia)->sin_addr.s_addr) {
			t = IA_SIN(ia)->sin_addr;
			IN_IFADDR_RUNLOCK(&in_ifa_tracker);
			goto match;
		}
	}
	IN_IFADDR_RUNLOCK(&in_ifa_tracker);

	/*
	 * If the incoming packet was addressed to one of our broadcast
	 * addresses, use the first non-broadcast address which corresponds
	 * to the incoming interface.
	 */
	ifp = m->m_pkthdr.rcvif;
	if (ifp != NULL && ifp->if_flags & IFF_BROADCAST) {
		IF_ADDR_RLOCK(ifp);
		TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
			if (ifa->ifa_addr->sa_family != AF_INET)
				continue;
			ia = ifatoia(ifa);
			if (satosin(&ia->ia_broadaddr)->sin_addr.s_addr ==
			    t.s_addr) {
				t = IA_SIN(ia)->sin_addr;
				IF_ADDR_RUNLOCK(ifp);
				goto match;
			}
		}
		IF_ADDR_RUNLOCK(ifp);
	}
	/*
	 * If the packet was transiting through us, use the address of
	 * the interface the packet came through in.  If that interface
	 * doesn't have a suitable IP address, the normal selection
	 * criteria apply.
	 */
	if (V_icmp_rfi && ifp != NULL) {
		IF_ADDR_RLOCK(ifp);
		TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
			if (ifa->ifa_addr->sa_family != AF_INET)
				continue;
			ia = ifatoia(ifa);
			t = IA_SIN(ia)->sin_addr;
			IF_ADDR_RUNLOCK(ifp);
			goto match;
		}
		IF_ADDR_RUNLOCK(ifp);
	}
	/*
	 * If the incoming packet was not addressed directly to us, use
	 * designated interface for icmp replies specified by sysctl
	 * net.inet.icmp.reply_src (default not set). Otherwise continue
	 * with normal source selection.
	 */
	if (V_reply_src[0] != '\0' && (ifp = ifunit(V_reply_src))) {
		IF_ADDR_RLOCK(ifp);
		TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
			if (ifa->ifa_addr->sa_family != AF_INET)
				continue;
			ia = ifatoia(ifa);
			t = IA_SIN(ia)->sin_addr;
			IF_ADDR_RUNLOCK(ifp);
			goto match;
		}
		IF_ADDR_RUNLOCK(ifp);
	}
	/*
	 * If the packet was transiting through us, use the address of
	 * the interface that is the closest to the packet source.
	 * When we don't have a route back to the packet source, stop here
	 * and drop the packet.
	 */
	if (fib4_lookup_nh_ext(M_GETFIB(m), ip->ip_dst, 0, 0, &nh_ext) != 0) {
		m_freem(m);
		ICMPSTAT_INC(icps_noroute);
		goto done;
	}
	t = nh_ext.nh_src;
match:
#ifdef MAC
	mac_netinet_icmp_replyinplace(m);
#endif
	ip->ip_src = t;
	ip->ip_ttl = V_ip_defttl;

	if (optlen > 0) {
		register u_char *cp;
		int opt, cnt;
		u_int len;

		/*
		 * Retrieve any source routing from the incoming packet;
		 * add on any record-route or timestamp options.
		 */
		cp = (u_char *) (ip + 1);
		if ((opts = ip_srcroute(m)) == NULL &&
		    (opts = m_gethdr(M_NOWAIT, MT_DATA))) {
			opts->m_len = sizeof(struct in_addr);
			mtod(opts, struct in_addr *)->s_addr = 0;
		}
		if (opts) {
#ifdef ICMPPRINTFS
		    if (icmpprintfs)
			    printf("icmp_reflect optlen %d rt %d => ",
				optlen, opts->m_len);
#endif
		    for (cnt = optlen; cnt > 0; cnt -= len, cp += len) {
			    opt = cp[IPOPT_OPTVAL];
			    if (opt == IPOPT_EOL)
				    break;
			    if (opt == IPOPT_NOP)
				    len = 1;
			    else {
				    if (cnt < IPOPT_OLEN + sizeof(*cp))
					    break;
				    len = cp[IPOPT_OLEN];
				    if (len < IPOPT_OLEN + sizeof(*cp) ||
				        len > cnt)
					    break;
			    }
			    /*
			     * Should check for overflow, but it "can't happen"
			     */
			    if (opt == IPOPT_RR || opt == IPOPT_TS ||
				opt == IPOPT_SECURITY) {
				    bcopy((caddr_t)cp,
					mtod(opts, caddr_t) + opts->m_len, len);
				    opts->m_len += len;
			    }
		    }
		    /* Terminate & pad, if necessary */
		    cnt = opts->m_len % 4;
		    if (cnt) {
			    for (; cnt < 4; cnt++) {
				    *(mtod(opts, caddr_t) + opts->m_len) =
					IPOPT_EOL;
				    opts->m_len++;
			    }
		    }
#ifdef ICMPPRINTFS
		    if (icmpprintfs)
			    printf("%d\n", opts->m_len);
#endif
		}
		ip_stripoptions(m);
	}
	m_tag_delete_nonpersistent(m);
	m->m_flags &= ~(M_BCAST|M_MCAST);
	icmp_send(m, opts);
done:
	if (opts)
		(void)m_free(opts);
}

/*
 * Send an icmp packet back to the ip level,
 * after supplying a checksum.
 */
static void
icmp_send(struct mbuf *m, struct mbuf *opts)
{
	register struct ip *ip = mtod(m, struct ip *);
	register int hlen;
	register struct icmp *icp;

	hlen = ip->ip_hl << 2;
	m->m_data += hlen;
	m->m_len -= hlen;
	icp = mtod(m, struct icmp *);
	icp->icmp_cksum = 0;
	icp->icmp_cksum = in_cksum(m, ntohs(ip->ip_len) - hlen);
	m->m_data -= hlen;
	m->m_len += hlen;
	m->m_pkthdr.rcvif = (struct ifnet *)0;
#ifdef ICMPPRINTFS
	if (icmpprintfs) {
		char dstbuf[INET_ADDRSTRLEN];
		char srcbuf[INET_ADDRSTRLEN];

		printf("icmp_send dst %s src %s\n",
		    inet_ntoa_r(ip->ip_dst, dstbuf),
		    inet_ntoa_r(ip->ip_src, srcbuf));
	}
#endif
	(void) ip_output(m, opts, NULL, 0, NULL, NULL);
}

/*
 * Return milliseconds since 00:00 UTC in network format.
 */
uint32_t
iptime(void)
{
	struct timeval atv;
	u_long t;

	getmicrotime(&atv);
	t = (atv.tv_sec % (24*60*60)) * 1000 + atv.tv_usec / 1000;
	return (htonl(t));
}

/*
 * Return the next larger or smaller MTU plateau (table from RFC 1191)
 * given current value MTU.  If DIR is less than zero, a larger plateau
 * is returned; otherwise, a smaller value is returned.
 */
int
ip_next_mtu(int mtu, int dir)
{
	static int mtutab[] = {
		65535, 32000, 17914, 8166, 4352, 2002, 1492, 1280, 1006, 508,
		296, 68, 0
	};
	int i, size;

	size = (sizeof mtutab) / (sizeof mtutab[0]);
	if (dir >= 0) {
		for (i = 0; i < size; i++)
			if (mtu > mtutab[i])
				return mtutab[i];
	} else {
		for (i = size - 1; i >= 0; i--)
			if (mtu < mtutab[i])
				return mtutab[i];
		if (mtu == mtutab[0])
			return mtutab[0];
	}
	return 0;
}
#endif /* INET */


/*
 * badport_bandlim() - check for ICMP bandwidth limit
 *
 *	Return 0 if it is ok to send an ICMP error response, -1 if we have
 *	hit our bandwidth limit and it is not ok.
 *
 *	If icmplim is <= 0, the feature is disabled and 0 is returned.
 *
 *	For now we separate the TCP and UDP subsystems w/ different 'which'
 *	values.  We may eventually remove this separation (and simplify the
 *	code further).
 *
 *	Note that the printing of the error message is delayed so we can
 *	properly print the icmp error rate that the system was trying to do
 *	(i.e. 22000/100 pps, etc...).  This can cause long delays in printing
 *	the 'final' error, but it doesn't make sense to solve the printing
 *	delay with more complex code.
 */

int
badport_bandlim(int which)
{

#define	N(a)	(sizeof (a) / sizeof (a[0]))
	static struct rate {
		const char	*type;
		struct timeval	lasttime;
		int		curpps;
	} rates[BANDLIM_MAX+1] = {
		{ "icmp unreach response" },
		{ "icmp ping response" },
		{ "icmp tstamp response" },
		{ "closed port RST response" },
		{ "open port RST response" },
		{ "icmp6 unreach response" },
		{ "sctp ootb response" }
	};

	/*
	 * Return ok status if feature disabled or argument out of range.
	 */
	if (V_icmplim > 0 && (u_int) which < N(rates)) {
		struct rate *r = &rates[which];
		int opps = r->curpps;

		if (!ppsratecheck(&r->lasttime, &r->curpps, V_icmplim))
			return -1;	/* discard packet */
		/*
		 * If we've dropped below the threshold after having
		 * rate-limited traffic print the message.  This preserves
		 * the previous behaviour at the expense of added complexity.
		 */
		if (V_icmplim_output && opps > V_icmplim)
			log(LOG_NOTICE, "Limiting %s from %d to %d packets/sec\n",
				r->type, opps, V_icmplim);
	}
	return 0;			/* okay to send packet */
#undef N
}
OpenPOWER on IntegriCloud