summaryrefslogtreecommitdiff
path: root/sys/netinet/ip_output.c
blob: 2f248b3e51fff72ef69a5da1378a4f7b58d4ffde (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
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
/*	$OpenBSD: ip_output.c,v 1.30 1998/05/24 23:03:47 provos Exp $	*/
/*	$NetBSD: ip_output.c,v 1.28 1996/02/13 23:43:07 christos Exp $	*/

/*
 * Copyright (c) 1982, 1986, 1988, 1990, 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.
 * 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.
 *
 *	@(#)ip_output.c	8.3 (Berkeley) 1/21/94
 */

#include <sys/param.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/errno.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/proc.h>

#include <net/if.h>
#include <net/route.h>

#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <netinet/in_pcb.h>
#include <netinet/in_var.h>
#include <netinet/ip_var.h>

#ifdef vax
#include <machine/mtpr.h>
#endif

#include <machine/stdarg.h>

#ifdef IPSEC
#include <net/encap.h>
#include <netinet/ip_ipsp.h>
#include <netinet/udp.h>
#include <netinet/tcp.h>
#include <sys/syslog.h>

extern u_int8_t get_sa_require  __P((struct inpcb *));

#endif

static struct mbuf *ip_insertoptions __P((struct mbuf *, struct mbuf *, int *));
static void ip_mloopback
	__P((struct ifnet *, struct mbuf *, struct sockaddr_in *));
#if defined(IPFILTER) || defined(IPFILTER_LKM)
int (*fr_checkp) __P((struct ip *, int, struct ifnet *, int, struct mbuf **));
#endif

#ifdef IPSEC
extern void	encap_sendnotify __P((int, struct tdb *, void *));
extern int ipsec_auth_default_level;
extern int ipsec_esp_trans_default_level;
extern int ipsec_esp_network_default_level;
#endif

/*
 * IP output.  The packet in mbuf chain m contains a skeletal IP
 * header (with len, off, ttl, proto, tos, src, dst).
 * The mbuf chain containing the packet will be freed.
 * The mbuf opt, if present, will not be freed.
 */
int
#if __STDC__
ip_output(struct mbuf *m0, ...)
#else
ip_output(m0, va_alist)
	struct mbuf *m0;
	va_dcl
#endif
{
	register struct ip *ip, *mhip;
	register struct ifnet *ifp;
	register struct mbuf *m = m0;
	register int hlen = sizeof (struct ip);
	int len, off, error = 0;
	struct route iproute;
	struct sockaddr_in *dst;
	struct in_ifaddr *ia;
	struct mbuf *opt;
	struct route *ro;
	int flags;
	struct ip_moptions *imo;
	va_list ap;
#ifdef IPSEC
	struct mbuf *mp;
	struct udphdr *udp;
	struct tcphdr *tcp;
	struct expiration *exp;
	struct inpcb *inp;
#endif

	va_start(ap, m0);
	opt = va_arg(ap, struct mbuf *);
	ro = va_arg(ap, struct route *);
	flags = va_arg(ap, int);
	imo = va_arg(ap, struct ip_moptions *);
#ifdef IPSEC
	inp = va_arg(ap, struct inpcb *);
#endif
	va_end(ap);



#ifdef	DIAGNOSTIC
	if ((m->m_flags & M_PKTHDR) == 0)
		panic("ip_output no HDR");
#endif
	if (opt) {
		m = ip_insertoptions(m, opt, &len);
		hlen = len;
	}
	ip = mtod(m, struct ip *);
	/*
	 * Fill in IP header.
	 */
	if ((flags & (IP_FORWARDING|IP_RAWOUTPUT)) == 0) {
		ip->ip_v = IPVERSION;
		ip->ip_off &= IP_DF;
		ip->ip_id = htons(ip_id++);
		ip->ip_hl = hlen >> 2;
		ipstat.ips_localout++;
	} else {
		hlen = ip->ip_hl << 2;
	}

#ifdef IPSEC
	/*
	 * Check if the packet needs encapsulation
	 */
	if (!(flags & IP_ENCAPSULATED) && 
	    (inp == NULL || 
	     (inp->inp_seclevel[SL_AUTH] != IPSEC_LEVEL_BYPASS ||
	      inp->inp_seclevel[SL_ESP_TRANS] != IPSEC_LEVEL_BYPASS ||
	      inp->inp_seclevel[SL_ESP_NETWORK] != IPSEC_LEVEL_BYPASS))) {
		struct route_enc re0, *re = &re0;
		struct sockaddr_encap *ddst, *gw;
		struct tdb *tdb;
		u_int8_t sa_require, sa_have = 0;

		if (inp == NULL)
			sa_require = get_sa_require(inp);
		else
			sa_require = inp->inp_secrequire;

		bzero((caddr_t) re, sizeof(*re));
		ddst = (struct sockaddr_encap *) &re->re_dst;
		ddst->sen_family = AF_ENCAP;
		ddst->sen_len = SENT_IP4_LEN;
		ddst->sen_type = SENT_IP4;
		ddst->sen_ip_src = ip->ip_src;
		ddst->sen_ip_dst = ip->ip_dst;
		ddst->sen_proto = ip->ip_p;

		switch (ip->ip_p) {
		case IPPROTO_UDP:
			if (m->m_len < hlen + 2 * sizeof(u_int16_t)) {
				if ((m = m_pullup(m, hlen + 2 *
				    sizeof(u_int16_t))) == 0)
					return ENOBUFS;
				ip = mtod(m, struct ip *);
			}
			udp = (struct udphdr *) (mtod(m, u_char *) + hlen);
			ddst->sen_sport = ntohs(udp->uh_sport);
			ddst->sen_dport = ntohs(udp->uh_dport);
			break;

		case IPPROTO_TCP:
			if (m->m_len < hlen + 2 * sizeof(u_int16_t)) {
				if ((m = m_pullup(m, hlen + 2 *
				    sizeof(u_int16_t))) == 0)
					return ENOBUFS;
				ip = mtod(m, struct ip *);
			}
			tcp = (struct tcphdr *) (mtod(m, u_char *) + hlen);
			ddst->sen_sport = ntohs(tcp->th_sport);
			ddst->sen_dport = ntohs(tcp->th_dport);
			break;

		default:
			ddst->sen_sport = 0;
			ddst->sen_dport = 0;
		}

		rtalloc((struct route *) re);
		if (re->re_rt == NULL)
			goto no_encap;

		gw = (struct sockaddr_encap *) (re->re_rt->rt_gateway);

		/*
		 * There might be a specific route, that tells us to avoid
		 * doing IPsec; this is useful for specific routes that we
		 * don't want to have IPsec applied on.
		 */

		if ((gw != NULL) && (gw->sen_ipsp_dst.s_addr == 0) &&
		    (gw->sen_ipsp_sproto == 0) && (gw->sen_ipsp_spi == 0))
			goto no_encap;

		if (gw == NULL || gw->sen_type != SENT_IPSP) {
#ifdef ENCDEBUG
			if (encdebug)
				printf("ip_output(): no gw or gw data not IPSP\n");
#endif /* ENCDEBUG */
			RTFREE(re->re_rt);
			error = EHOSTUNREACH;
			goto bad;
		}

		/* 
		 * For VPNs a route with a reserved SPI of 1 is used to
		 * indicate the need for an SA when none is established.
		 */
		if (ntohl(gw->sen_ipsp_spi) == 0x1) {
			struct tdb tmptdb;

			sa_require = NOTIFY_SATYPE_CONF | NOTIFY_SATYPE_AUTH |
				NOTIFY_SATYPE_TUNNEL;
			tmptdb.tdb_dst.s_addr = gw->sen_ipsp_dst.s_addr;
			tmptdb.tdb_satype = sa_require;
			       
			/* Request SA with key management */
			encap_sendnotify(NOTIFY_REQUEST_SA, &tmptdb, NULL);
			
			/* 
			 * When sa_require is set, the packet will be dropped
			 * at no_encap.
			 */
			goto no_encap;
		}

		ip->ip_len = htons((u_short)ip->ip_len);
		ip->ip_off = htons((u_short)ip->ip_off);
		ip->ip_sum = 0;

		/*
		 * At this point we have an IPSP "gateway" (tunnel) spec.
		 * Use the destination of the tunnel and the SPI to
		 * look up the necessary Tunnel Control Block. Look it up,
		 * and then pass it, along with the packet and the gw,
		 * to the appropriate transformation.
		 */
		tdb = (struct tdb *) gettdb(gw->sen_ipsp_spi, gw->sen_ipsp_dst,
		    gw->sen_ipsp_sproto);

		/*
		 * Now we check if this tdb has all the transforms which
		 * are requried by the socket or our default policy.
		 */
		SPI_CHAIN_ATTRIB(sa_have, tdb_onext, tdb);

		if (sa_require & ~sa_have)
			goto no_encap;

#ifdef ENCDEBUG
		if (encdebug && (tdb == NULL))
			printf("ip_output(): non-existant TDB for SA %08x/%x/%d\n",
			    ntohl(gw->sen_ipsp_spi), gw->sen_ipsp_dst,
			    gw->sen_ipsp_sproto);
#endif ENCDEBUG

		/* Fix the ip_src field if necessary */
		if (ip->ip_src.s_addr == INADDR_ANY) {
		    if (tdb && tdb->tdb_src.s_addr != 0)   /* Provided */
			ip->ip_src = tdb->tdb_src;
		    else
		    {
			if (ro == 0) {
			    ro = &iproute;
			    bzero((caddr_t)ro, sizeof (*ro));
			}

			dst = satosin(&ro->ro_dst);

			/*
			 * If there is a cached route,
			 * check that it is to the same destination
			 * and is still up.  If not, free it and try again.
			 */
			if (ro->ro_rt &&
			    ((ro->ro_rt->rt_flags & RTF_UP) == 0 ||
			     dst->sin_addr.s_addr != ip->ip_dst.s_addr)) {
			    RTFREE(ro->ro_rt);
			    ro->ro_rt = (struct rtentry *)0;
			}

			if (ro->ro_rt == 0) {
			    dst->sin_family = AF_INET;
			    dst->sin_len = sizeof(*dst);
			    dst->sin_addr = ip->ip_dst;
			    rtalloc(ro);
			}			

			if (ro->ro_rt == 0) {
			    ipstat.ips_noroute++;
			    error = EHOSTUNREACH;
			    goto bad;
			}
			
			ia = ifatoia(ro->ro_rt->rt_ifa);
			ro->ro_rt->rt_use++;
			ip->ip_src = ia->ia_addr.sin_addr;
		    }
		}

		/* Now fix the checksum */
		ip->ip_sum = in_cksum(m, hlen);

#ifdef ENCDEBUG
		if (encdebug) {
			printf("ip_output(): tdb=%08x, tdb->tdb_xform=0x%x,",
			    tdb, tdb->tdb_xform);
			printf(" tdb->tdb_xform->xf_output=%x, sproto=%x\n",
			    tdb->tdb_xform->xf_output, tdb->tdb_sproto);
		}
#endif /* ENCDEBUG */

		while (tdb && tdb->tdb_xform) {
			m0 = NULL;

			/* Check if the SPI is invalid */
			if (tdb->tdb_flags & TDBF_INVALID) {
			 	if (encdebug)
				  log(LOG_ALERT, "ip_output(): attempt to use invalid SA %08x/%x/%x\n", ntohl(tdb->tdb_spi), tdb->tdb_dst,
				    tdb->tdb_sproto);
				m_freem(m);
				RTFREE(re->re_rt);
				return ENXIO;
			}

			/* Check for tunneling */
			if ((tdb->tdb_flags & TDBF_TUNNELING) &&
			    (tdb->tdb_xform->xf_type != XF_IP4)){
#ifdef ENCDEBUG
				if (encdebug)
					printf("ip_output(): tunneling\n");
#endif /* ENCDEBUG */

				/*
				 * Register first use,
				 * setup expiration timer
				 */
				if (tdb->tdb_first_use == 0) {
					tdb->tdb_first_use = time.tv_sec;

					if (tdb->tdb_flags & TDBF_FIRSTUSE) {
						exp = get_expiration();
						if (exp == NULL)
							goto expbail;
						exp->exp_dst.s_addr =
						    tdb->tdb_dst.s_addr;
						exp->exp_spi = tdb->tdb_spi;
						exp->exp_sproto =
						    tdb->tdb_sproto;
						exp->exp_timeout =
						    tdb->tdb_first_use +
						    tdb->tdb_exp_first_use;
						put_expiration(exp);
					}

					if ((tdb->tdb_flags &
					    TDBF_SOFT_FIRSTUSE) &&
					    (tdb->tdb_soft_first_use <=
						tdb->tdb_exp_first_use)) {
						exp = get_expiration();
						if (exp == NULL)
							goto expbail;
						exp->exp_dst.s_addr =
						    tdb->tdb_dst.s_addr;
						exp->exp_spi = tdb->tdb_spi;
						exp->exp_sproto =
						    tdb->tdb_sproto;
						exp->exp_timeout =
						    tdb->tdb_first_use +
						    tdb->tdb_soft_first_use;
						put_expiration(exp);
					}
				}

				error = ipe4_output(m, gw, tdb, &mp);
				if (mp == NULL)
					error = EFAULT;
				if (error) {
					RTFREE(re->re_rt);
					return error;
				}
				m = mp;
			}

#ifdef ENCDEBUG
			if (encdebug)
				printf("ip_output(): calling %s\n",
				       tdb->tdb_xform->xf_name);
#endif /* ENCDEBUG */

			/* Register first use, setup expiration timer */
			if (tdb->tdb_first_use == 0) {
			    tdb->tdb_first_use = time.tv_sec;

				if (tdb->tdb_flags & TDBF_FIRSTUSE) {
					exp = get_expiration();
					if (exp == NULL)
						goto expbail;
					exp->exp_dst.s_addr =
					    tdb->tdb_dst.s_addr;
					exp->exp_spi = tdb->tdb_spi;
					exp->exp_sproto = tdb->tdb_sproto;
					exp->exp_timeout = tdb->tdb_first_use +
					    tdb->tdb_exp_first_use;
					put_expiration(exp);
				}

				if ((tdb->tdb_flags & TDBF_SOFT_FIRSTUSE) &&
				    (tdb->tdb_soft_first_use <=
				    tdb->tdb_exp_first_use)) {
					exp = get_expiration();
					if (exp == NULL) {
expbail:
						if (encdebug)
						  log(LOG_WARNING, "ip_output(): no memory for exp timer\n");
						m_freem(m);
						RTFREE(re->re_rt);
						return ENOBUFS;
					}
					exp->exp_dst.s_addr =
					    tdb->tdb_dst.s_addr;
					exp->exp_spi = tdb->tdb_spi;
					exp->exp_sproto = tdb->tdb_sproto;
					exp->exp_timeout = tdb->tdb_first_use +
					    tdb->tdb_soft_first_use;
					put_expiration(exp);
				}
			}

			error = (*(tdb->tdb_xform->xf_output))(m, gw,
			    tdb, &mp);
			if (mp == NULL)
				error = EFAULT;
			if (error) {
				RTFREE(re->re_rt);
				return error;
			}
			tdb = tdb->tdb_onext;
			m = mp;
		}

		/*
		 * At this point, m is pointing to an mbuf chain with the
		 * processed packet. Call ourselves recursively, but
		 * bypass the encap code.
		 */
		RTFREE(re->re_rt);
		ip = mtod(m, struct ip *);
		NTOHS(ip->ip_len);
		NTOHS(ip->ip_off);
		return ip_output(m, NULL, NULL,
		    IP_ENCAPSULATED | IP_RAWOUTPUT, NULL, NULL);

no_encap:
		/* This is for possible future use, don't move or delete */
		if (re->re_rt)
			RTFREE(re->re_rt);
		/* No IPSec processing though it was required, drop packet */
		if (sa_require)
			goto done;
	}
#endif /* IPSEC */

	/*
	 * Route packet.
	 */
	if (ro == 0) {
		ro = &iproute;
		bzero((caddr_t)ro, sizeof (*ro));
	}
	dst = satosin(&ro->ro_dst);
	/*
	 * If there is a cached route,
	 * check that it is to the same destination
	 * and is still up.  If not, free it and try again.
	 */
	if (ro->ro_rt && ((ro->ro_rt->rt_flags & RTF_UP) == 0 ||
	    dst->sin_addr.s_addr != ip->ip_dst.s_addr)) {
		RTFREE(ro->ro_rt);
		ro->ro_rt = (struct rtentry *)0;
	}
	if (ro->ro_rt == 0) {
		dst->sin_family = AF_INET;
		dst->sin_len = sizeof(*dst);
		dst->sin_addr = ip->ip_dst;
	}
	/*
	 * If routing to interface only,
	 * short circuit routing lookup.
	 */
	if (flags & IP_ROUTETOIF) {
		if ((ia = ifatoia(ifa_ifwithdstaddr(sintosa(dst)))) == 0 &&
		    (ia = ifatoia(ifa_ifwithnet(sintosa(dst)))) == 0) {
			ipstat.ips_noroute++;
			error = ENETUNREACH;
			goto bad;
		}
		ifp = ia->ia_ifp;
		ip->ip_ttl = 1;
	} else {
		if (ro->ro_rt == 0)
			rtalloc(ro);
		if (ro->ro_rt == 0) {
			ipstat.ips_noroute++;
			error = EHOSTUNREACH;
			goto bad;
		}
		ia = ifatoia(ro->ro_rt->rt_ifa);
		ifp = ro->ro_rt->rt_ifp;
		ro->ro_rt->rt_use++;
		if (ro->ro_rt->rt_flags & RTF_GATEWAY)
			dst = satosin(ro->ro_rt->rt_gateway);
	}
	if (IN_MULTICAST(ip->ip_dst.s_addr)) {
		struct in_multi *inm;

		m->m_flags |= M_MCAST;
		/*
		 * IP destination address is multicast.  Make sure "dst"
		 * still points to the address in "ro".  (It may have been
		 * changed to point to a gateway address, above.)
		 */
		dst = satosin(&ro->ro_dst);
		/*
		 * See if the caller provided any multicast options
		 */
		if (imo != NULL) {
			ip->ip_ttl = imo->imo_multicast_ttl;
			if (imo->imo_multicast_ifp != NULL)
				ifp = imo->imo_multicast_ifp;
		} else
			ip->ip_ttl = IP_DEFAULT_MULTICAST_TTL;
		/*
		 * Confirm that the outgoing interface supports multicast.
		 */
		if ((ifp->if_flags & IFF_MULTICAST) == 0) {
			ipstat.ips_noroute++;
			error = ENETUNREACH;
			goto bad;
		}
		/*
		 * If source address not specified yet, use address
		 * of outgoing interface.
		 */
		if (ip->ip_src.s_addr == INADDR_ANY) {
			register struct in_ifaddr *ia;

			for (ia = in_ifaddr.tqh_first; ia; ia = ia->ia_list.tqe_next)
				if (ia->ia_ifp == ifp) {
					ip->ip_src = ia->ia_addr.sin_addr;
					break;
				}
		}

		IN_LOOKUP_MULTI(ip->ip_dst, ifp, inm);
		if (inm != NULL &&
		   (imo == NULL || imo->imo_multicast_loop)) {
			/*
			 * If we belong to the destination multicast group
			 * on the outgoing interface, and the caller did not
			 * forbid loopback, loop back a copy.
			 */
			ip_mloopback(ifp, m, dst);
		}
#ifdef MROUTING
		else {
			/*
			 * If we are acting as a multicast router, perform
			 * multicast forwarding as if the packet had just
			 * arrived on the interface to which we are about
			 * to send.  The multicast forwarding function
			 * recursively calls this function, using the
			 * IP_FORWARDING flag to prevent infinite recursion.
			 *
			 * Multicasts that are looped back by ip_mloopback(),
			 * above, will be forwarded by the ip_input() routine,
			 * if necessary.
			 */
			extern struct socket *ip_mrouter;

			if (ip_mrouter && (flags & IP_FORWARDING) == 0) {
				if (ip_mforward(m, ifp) != 0) {
					m_freem(m);
					goto done;
				}
			}
		}
#endif
		/*
		 * Multicasts with a time-to-live of zero may be looped-
		 * back, above, but must not be transmitted on a network.
		 * Also, multicasts addressed to the loopback interface
		 * are not sent -- the above call to ip_mloopback() will
		 * loop back a copy if this host actually belongs to the
		 * destination group on the loopback interface.
		 */
		if (ip->ip_ttl == 0 || (ifp->if_flags & IFF_LOOPBACK) != 0) {
			m_freem(m);
			goto done;
		}

		goto sendit;
	}
#ifndef notdef
	/*
	 * If source address not specified yet, use address
	 * of outgoing interface.
	 */
	if (ip->ip_src.s_addr == INADDR_ANY)
		ip->ip_src = ia->ia_addr.sin_addr;
#endif
	/*
	 * Look for broadcast address and
	 * and verify user is allowed to send
	 * such a packet.
	 */
	if (in_broadcast(dst->sin_addr, ifp)) {
		if ((ifp->if_flags & IFF_BROADCAST) == 0) {
			error = EADDRNOTAVAIL;
			goto bad;
		}
		if ((flags & IP_ALLOWBROADCAST) == 0) {
			error = EACCES;
			goto bad;
		}
		/* don't allow broadcast messages to be fragmented */
		if ((u_int16_t)ip->ip_len > ifp->if_mtu) {
			error = EMSGSIZE;
			goto bad;
		}
		m->m_flags |= M_BCAST;
	} else
		m->m_flags &= ~M_BCAST;

#if defined(IPFILTER) || defined(IPFILTER_LKM)
	/*
	 * looks like most checking has been done now...do a filter check
	 */
	{
		struct mbuf *m0 = m;
		if (fr_checkp && (*fr_checkp)(ip, hlen, ifp, 1, &m0)) {
			error = EHOSTUNREACH;
			goto done;
		} else
			ip = mtod(m = m0, struct ip *);
	}
#endif
sendit:
	/*
	 * If small enough for interface, can just send directly.
	 */
	if ((u_int16_t)ip->ip_len <= ifp->if_mtu) {
		ip->ip_len = htons((u_int16_t)ip->ip_len);
		ip->ip_off = htons((u_int16_t)ip->ip_off);
		ip->ip_sum = 0;
		ip->ip_sum = in_cksum(m, hlen);
		error = (*ifp->if_output)(ifp, m, sintosa(dst), ro->ro_rt);
		goto done;
	}
	/*
	 * Too large for interface; fragment if possible.
	 * Must be able to put at least 8 bytes per fragment.
	 */
	if (ip->ip_off & IP_DF) {
		error = EMSGSIZE;
		ipstat.ips_cantfrag++;
		goto bad;
	}
	len = (ifp->if_mtu - hlen) &~ 7;
	if (len < 8) {
		error = EMSGSIZE;
		goto bad;
	}

    {
	int mhlen, firstlen = len;
	struct mbuf **mnext = &m->m_nextpkt;

	/*
	 * Loop through length of segment after first fragment,
	 * make new header and copy data of each part and link onto chain.
	 */
	m0 = m;
	mhlen = sizeof (struct ip);
	for (off = hlen + len; off < (u_int16_t)ip->ip_len; off += len) {
		MGETHDR(m, M_DONTWAIT, MT_HEADER);
		if (m == 0) {
			error = ENOBUFS;
			ipstat.ips_odropped++;
			goto sendorfree;
		}
		*mnext = m;
		mnext = &m->m_nextpkt;
		m->m_data += max_linkhdr;
		mhip = mtod(m, struct ip *);
		*mhip = *ip;
		if (hlen > sizeof (struct ip)) {
			mhlen = ip_optcopy(ip, mhip) + sizeof (struct ip);
			mhip->ip_hl = mhlen >> 2;
		}
		m->m_len = mhlen;
		mhip->ip_off = ((off - hlen) >> 3) + (ip->ip_off & ~IP_MF);
		if (ip->ip_off & IP_MF)
			mhip->ip_off |= IP_MF;
		if (off + len >= (u_int16_t)ip->ip_len)
			len = (u_int16_t)ip->ip_len - off;
		else
			mhip->ip_off |= IP_MF;
		mhip->ip_len = htons((u_int16_t)(len + mhlen));
		m->m_next = m_copy(m0, off, len);
		if (m->m_next == 0) {
			error = ENOBUFS;	/* ??? */
			ipstat.ips_odropped++;
			goto sendorfree;
		}
		m->m_pkthdr.len = mhlen + len;
		m->m_pkthdr.rcvif = (struct ifnet *)0;
		mhip->ip_off = htons((u_int16_t)mhip->ip_off);
		mhip->ip_sum = 0;
		mhip->ip_sum = in_cksum(m, mhlen);
		ipstat.ips_ofragments++;
	}
	/*
	 * Update first fragment by trimming what's been copied out
	 * and updating header, then send each fragment (in order).
	 */
	m = m0;
	m_adj(m, hlen + firstlen - (u_int16_t)ip->ip_len);
	m->m_pkthdr.len = hlen + firstlen;
	ip->ip_len = htons((u_int16_t)m->m_pkthdr.len);
	ip->ip_off = htons((u_int16_t)(ip->ip_off | IP_MF));
	ip->ip_sum = 0;
	ip->ip_sum = in_cksum(m, hlen);
sendorfree:
	for (m = m0; m; m = m0) {
		m0 = m->m_nextpkt;
		m->m_nextpkt = 0;
		if (error == 0)
			error = (*ifp->if_output)(ifp, m, sintosa(dst),
			    ro->ro_rt);
		else
			m_freem(m);
	}

	if (error == 0)
		ipstat.ips_fragmented++;
    }
done:
	if (ro == &iproute && (flags & IP_ROUTETOIF) == 0 && ro->ro_rt)
		RTFREE(ro->ro_rt);
	return (error);
bad:
	m_freem(m0);
	goto done;
}

/*
 * Insert IP options into preformed packet.
 * Adjust IP destination as required for IP source routing,
 * as indicated by a non-zero in_addr at the start of the options.
 */
static struct mbuf *
ip_insertoptions(m, opt, phlen)
	register struct mbuf *m;
	struct mbuf *opt;
	int *phlen;
{
	register struct ipoption *p = mtod(opt, struct ipoption *);
	struct mbuf *n;
	register struct ip *ip = mtod(m, struct ip *);
	unsigned optlen;

	optlen = opt->m_len - sizeof(p->ipopt_dst);
	if (optlen + (u_int16_t)ip->ip_len > IP_MAXPACKET)
		return (m);		/* XXX should fail */
	if (p->ipopt_dst.s_addr)
		ip->ip_dst = p->ipopt_dst;
	if (m->m_flags & M_EXT || m->m_data - optlen < m->m_pktdat) {
		MGETHDR(n, M_DONTWAIT, MT_HEADER);
		if (n == 0)
			return (m);
		n->m_pkthdr.len = m->m_pkthdr.len + optlen;
		m->m_len -= sizeof(struct ip);
		m->m_data += sizeof(struct ip);
		n->m_next = m;
		m = n;
		m->m_len = optlen + sizeof(struct ip);
		m->m_data += max_linkhdr;
		bcopy((caddr_t)ip, mtod(m, caddr_t), sizeof(struct ip));
	} else {
		m->m_data -= optlen;
		m->m_len += optlen;
		m->m_pkthdr.len += optlen;
		ovbcopy((caddr_t)ip, mtod(m, caddr_t), sizeof(struct ip));
	}
	ip = mtod(m, struct ip *);
	bcopy((caddr_t)p->ipopt_list, (caddr_t)(ip + 1), (unsigned)optlen);
	*phlen = sizeof(struct ip) + optlen;
	ip->ip_len += optlen;
	return (m);
}

/*
 * Copy options from ip to jp,
 * omitting those not copied during fragmentation.
 */
int
ip_optcopy(ip, jp)
	struct ip *ip, *jp;
{
	register u_char *cp, *dp;
	int opt, optlen, cnt;

	cp = (u_char *)(ip + 1);
	dp = (u_char *)(jp + 1);
	cnt = (ip->ip_hl << 2) - sizeof (struct ip);
	for (; cnt > 0; cnt -= optlen, cp += optlen) {
		opt = cp[0];
		if (opt == IPOPT_EOL)
			break;
		if (opt == IPOPT_NOP) {
			/* Preserve for IP mcast tunnel's LSRR alignment. */
			*dp++ = IPOPT_NOP;
			optlen = 1;
			continue;
		} else
			optlen = cp[IPOPT_OLEN];
		/* bogus lengths should have been caught by ip_dooptions */
		if (optlen > cnt)
			optlen = cnt;
		if (IPOPT_COPIED(opt)) {
			bcopy((caddr_t)cp, (caddr_t)dp, (unsigned)optlen);
			dp += optlen;
		}
	}
	for (optlen = dp - (u_char *)(jp+1); optlen & 0x3; optlen++)
		*dp++ = IPOPT_EOL;
	return (optlen);
}

/*
 * IP socket option processing.
 */
int
ip_ctloutput(op, so, level, optname, mp)
	int op;
	struct socket *so;
	int level, optname;
	struct mbuf **mp;
{
	register struct inpcb *inp = sotoinpcb(so);
	register struct mbuf *m = *mp;
	register int optval = 0;
#ifdef IPSEC
	struct proc *p = curproc; /* XXX */
#endif
	int error = 0;

	if (level != IPPROTO_IP) {
		error = EINVAL;
		if (op == PRCO_SETOPT && *mp)
			(void) m_free(*mp);
	} else switch (op) {

	case PRCO_SETOPT:
		switch (optname) {
		case IP_OPTIONS:
#ifdef notyet
		case IP_RETOPTS:
			return (ip_pcbopts(optname, &inp->inp_options, m));
#else
			return (ip_pcbopts(&inp->inp_options, m));
#endif

		case IP_TOS:
		case IP_TTL:
		case IP_RECVOPTS:
		case IP_RECVRETOPTS:
		case IP_RECVDSTADDR:
			if (m == NULL || m->m_len != sizeof(int))
				error = EINVAL;
			else {
				optval = *mtod(m, int *);
				switch (optname) {

				case IP_TOS:
					inp->inp_ip.ip_tos = optval;
					break;

				case IP_TTL:
					inp->inp_ip.ip_ttl = optval;
					break;
#define	OPTSET(bit) \
	if (optval) \
		inp->inp_flags |= bit; \
	else \
		inp->inp_flags &= ~bit;

				case IP_RECVOPTS:
					OPTSET(INP_RECVOPTS);
					break;

				case IP_RECVRETOPTS:
					OPTSET(INP_RECVRETOPTS);
					break;

				case IP_RECVDSTADDR:
					OPTSET(INP_RECVDSTADDR);
					break;
				}
			}
			break;
#undef OPTSET

		case IP_MULTICAST_IF:
		case IP_MULTICAST_TTL:
		case IP_MULTICAST_LOOP:
		case IP_ADD_MEMBERSHIP:
		case IP_DROP_MEMBERSHIP:
			error = ip_setmoptions(optname, &inp->inp_moptions, m);
			break;

		case IP_PORTRANGE:
			if (m == 0 || m->m_len != sizeof(int))
				error = EINVAL;
			else {
				optval = *mtod(m, int *);

				switch (optval) {

				case IP_PORTRANGE_DEFAULT:
					inp->inp_flags &= ~(INP_LOWPORT);
					inp->inp_flags &= ~(INP_HIGHPORT);
					break;

				case IP_PORTRANGE_HIGH:
					inp->inp_flags &= ~(INP_LOWPORT);
					inp->inp_flags |= INP_HIGHPORT;
					break;

				case IP_PORTRANGE_LOW:
					inp->inp_flags &= ~(INP_HIGHPORT);
					inp->inp_flags |= INP_LOWPORT;
					break;

				default:

					error = EINVAL;
					break;
				}
			}
			break;

		case IP_AUTH_LEVEL:
		case IP_ESP_TRANS_LEVEL:
		case IP_ESP_NETWORK_LEVEL:
#ifndef IPSEC
			error = EINVAL;
#else
			if (m == 0 || m->m_len != sizeof(int)) {
				error = EINVAL;
				break;
			}
			optval = *mtod(m, u_char *);

			if (optval < IPSEC_LEVEL_BYPASS || 
			    optval > IPSEC_LEVEL_UNIQUE) {
				error = EINVAL;
				break;
			}
				
			switch (optname) {
			case IP_AUTH_LEVEL:
			        if (optval < ipsec_auth_default_level &&
				    suser(p->p_ucred, &p->p_acflag)) {
					error = EACCES;
					break;
				}
				inp->inp_seclevel[SL_AUTH] = optval;
				break;

			case IP_ESP_TRANS_LEVEL:
			        if (optval < ipsec_esp_trans_default_level &&
				    suser(p->p_ucred, &p->p_acflag)) {
					error = EACCES;
					break;
				}
				inp->inp_seclevel[SL_ESP_TRANS] = optval;
				break;

			case IP_ESP_NETWORK_LEVEL:
			        if (optval < ipsec_esp_network_default_level &&
				    suser(p->p_ucred, &p->p_acflag)) {
					error = EACCES;
					break;
				}
				inp->inp_seclevel[SL_ESP_NETWORK] = optval;
				break;
			}
			if (!error)
				inp->inp_secrequire = get_sa_require(inp);
#endif
			break;

		default:
			error = ENOPROTOOPT;
			break;
		}
		if (m)
			(void)m_free(m);
		break;

	case PRCO_GETOPT:
		switch (optname) {
		case IP_OPTIONS:
		case IP_RETOPTS:
			*mp = m = m_get(M_WAIT, MT_SOOPTS);
			if (inp->inp_options) {
				m->m_len = inp->inp_options->m_len;
				bcopy(mtod(inp->inp_options, caddr_t),
				    mtod(m, caddr_t), (unsigned)m->m_len);
			} else
				m->m_len = 0;
			break;

		case IP_TOS:
		case IP_TTL:
		case IP_RECVOPTS:
		case IP_RECVRETOPTS:
		case IP_RECVDSTADDR:
			*mp = m = m_get(M_WAIT, MT_SOOPTS);
			m->m_len = sizeof(int);
			switch (optname) {

			case IP_TOS:
				optval = inp->inp_ip.ip_tos;
				break;

			case IP_TTL:
				optval = inp->inp_ip.ip_ttl;
				break;

#define	OPTBIT(bit)	(inp->inp_flags & bit ? 1 : 0)

			case IP_RECVOPTS:
				optval = OPTBIT(INP_RECVOPTS);
				break;

			case IP_RECVRETOPTS:
				optval = OPTBIT(INP_RECVRETOPTS);
				break;

			case IP_RECVDSTADDR:
				optval = OPTBIT(INP_RECVDSTADDR);
				break;
			}
			*mtod(m, int *) = optval;
			break;

		case IP_MULTICAST_IF:
		case IP_MULTICAST_TTL:
		case IP_MULTICAST_LOOP:
		case IP_ADD_MEMBERSHIP:
		case IP_DROP_MEMBERSHIP:
			error = ip_getmoptions(optname, inp->inp_moptions, mp);
			break;

		case IP_PORTRANGE:
			*mp = m = m_get(M_WAIT, MT_SOOPTS);
			m->m_len = sizeof(int);

			if (inp->inp_flags & INP_HIGHPORT)
				optval = IP_PORTRANGE_HIGH;
			else if (inp->inp_flags & INP_LOWPORT)
				optval = IP_PORTRANGE_LOW;
			else
				optval = 0;

			*mtod(m, int *) = optval;
			break;

		case IP_AUTH_LEVEL:
		case IP_ESP_TRANS_LEVEL:
		case IP_ESP_NETWORK_LEVEL:
#ifndef IPSEC
			*mtod(m, int *) = IPSEC_LEVEL_NONE;
#else
			switch (optname) {
			case IP_AUTH_LEVEL:
				    optval = inp->inp_seclevel[SL_AUTH];
				    break;

			case IP_ESP_TRANS_LEVEL:
				    optval = inp->inp_seclevel[SL_ESP_TRANS];
				    break;

			case IP_ESP_NETWORK_LEVEL:
				    optval = inp->inp_seclevel[SL_ESP_NETWORK];
				    break;
			}
			*mtod(m, int *) = optval;
#endif
			break;
		default:
			error = ENOPROTOOPT;
			break;
		}
		break;
	}
	return (error);
}

/*
 * Set up IP options in pcb for insertion in output packets.
 * Store in mbuf with pointer in pcbopt, adding pseudo-option
 * with destination address if source routed.
 */
int
#ifdef notyet
ip_pcbopts(optname, pcbopt, m)
	int optname;
#else
ip_pcbopts(pcbopt, m)
#endif
	struct mbuf **pcbopt;
	register struct mbuf *m;
{
	register int cnt, optlen;
	register u_char *cp;
	u_char opt;

	/* turn off any old options */
	if (*pcbopt)
		(void)m_free(*pcbopt);
	*pcbopt = 0;
	if (m == (struct mbuf *)0 || m->m_len == 0) {
		/*
		 * Only turning off any previous options.
		 */
		if (m)
			(void)m_free(m);
		return (0);
	}

#ifndef	vax
	if (m->m_len % sizeof(int32_t))
		goto bad;
#endif
	/*
	 * IP first-hop destination address will be stored before
	 * actual options; move other options back
	 * and clear it when none present.
	 */
	if (m->m_data + m->m_len + sizeof(struct in_addr) >= &m->m_dat[MLEN])
		goto bad;
	cnt = m->m_len;
	m->m_len += sizeof(struct in_addr);
	cp = mtod(m, u_char *) + sizeof(struct in_addr);
	ovbcopy(mtod(m, caddr_t), (caddr_t)cp, (unsigned)cnt);
	bzero(mtod(m, caddr_t), sizeof(struct in_addr));

	for (; cnt > 0; cnt -= optlen, cp += optlen) {
		opt = cp[IPOPT_OPTVAL];
		if (opt == IPOPT_EOL)
			break;
		if (opt == IPOPT_NOP)
			optlen = 1;
		else {
			optlen = cp[IPOPT_OLEN];
			if (optlen <= IPOPT_OLEN || optlen > cnt)
				goto bad;
		}
		switch (opt) {

		default:
			break;

		case IPOPT_LSRR:
		case IPOPT_SSRR:
			/*
			 * user process specifies route as:
			 *	->A->B->C->D
			 * D must be our final destination (but we can't
			 * check that since we may not have connected yet).
			 * A is first hop destination, which doesn't appear in
			 * actual IP option, but is stored before the options.
			 */
			if (optlen < IPOPT_MINOFF - 1 + sizeof(struct in_addr))
				goto bad;
			m->m_len -= sizeof(struct in_addr);
			cnt -= sizeof(struct in_addr);
			optlen -= sizeof(struct in_addr);
			cp[IPOPT_OLEN] = optlen;
			/*
			 * Move first hop before start of options.
			 */
			bcopy((caddr_t)&cp[IPOPT_OFFSET+1], mtod(m, caddr_t),
			    sizeof(struct in_addr));
			/*
			 * Then copy rest of options back
			 * to close up the deleted entry.
			 */
			ovbcopy((caddr_t)(&cp[IPOPT_OFFSET+1] +
			    sizeof(struct in_addr)),
			    (caddr_t)&cp[IPOPT_OFFSET+1],
			    (unsigned)cnt + sizeof(struct in_addr));
			break;
		}
	}
	if (m->m_len > MAX_IPOPTLEN + sizeof(struct in_addr))
		goto bad;
	*pcbopt = m;
	return (0);

bad:
	(void)m_free(m);
	return (EINVAL);
}

/*
 * Set the IP multicast options in response to user setsockopt().
 */
int
ip_setmoptions(optname, imop, m)
	int optname;
	struct ip_moptions **imop;
	struct mbuf *m;
{
	register int error = 0;
	u_char loop;
	register int i;
	struct in_addr addr;
	register struct ip_mreq *mreq;
	register struct ifnet *ifp;
	register struct ip_moptions *imo = *imop;
	struct route ro;
	register struct sockaddr_in *dst;

	if (imo == NULL) {
		/*
		 * No multicast option buffer attached to the pcb;
		 * allocate one and initialize to default values.
		 */
		imo = (struct ip_moptions *)malloc(sizeof(*imo), M_IPMOPTS,
		    M_WAITOK);

		if (imo == NULL)
			return (ENOBUFS);
		*imop = imo;
		imo->imo_multicast_ifp = NULL;
		imo->imo_multicast_ttl = IP_DEFAULT_MULTICAST_TTL;
		imo->imo_multicast_loop = IP_DEFAULT_MULTICAST_LOOP;
		imo->imo_num_memberships = 0;
	}

	switch (optname) {

	case IP_MULTICAST_IF:
		/*
		 * Select the interface for outgoing multicast packets.
		 */
		if (m == NULL || m->m_len != sizeof(struct in_addr)) {
			error = EINVAL;
			break;
		}
		addr = *(mtod(m, struct in_addr *));
		/*
		 * INADDR_ANY is used to remove a previous selection.
		 * When no interface is selected, a default one is
		 * chosen every time a multicast packet is sent.
		 */
		if (addr.s_addr == INADDR_ANY) {
			imo->imo_multicast_ifp = NULL;
			break;
		}
		/*
		 * The selected interface is identified by its local
		 * IP address.  Find the interface and confirm that
		 * it supports multicasting.
		 */
		INADDR_TO_IFP(addr, ifp);
		if (ifp == NULL || (ifp->if_flags & IFF_MULTICAST) == 0) {
			error = EADDRNOTAVAIL;
			break;
		}
		imo->imo_multicast_ifp = ifp;
		break;

	case IP_MULTICAST_TTL:
		/*
		 * Set the IP time-to-live for outgoing multicast packets.
		 */
		if (m == NULL || m->m_len != 1) {
			error = EINVAL;
			break;
		}
		imo->imo_multicast_ttl = *(mtod(m, u_char *));
		break;

	case IP_MULTICAST_LOOP:
		/*
		 * Set the loopback flag for outgoing multicast packets.
		 * Must be zero or one.
		 */
		if (m == NULL || m->m_len != 1 ||
		   (loop = *(mtod(m, u_char *))) > 1) {
			error = EINVAL;
			break;
		}
		imo->imo_multicast_loop = loop;
		break;

	case IP_ADD_MEMBERSHIP:
		/*
		 * Add a multicast group membership.
		 * Group must be a valid IP multicast address.
		 */
		if (m == NULL || m->m_len != sizeof(struct ip_mreq)) {
			error = EINVAL;
			break;
		}
		mreq = mtod(m, struct ip_mreq *);
		if (!IN_MULTICAST(mreq->imr_multiaddr.s_addr)) {
			error = EINVAL;
			break;
		}
		/*
		 * If no interface address was provided, use the interface of
		 * the route to the given multicast address.
		 */
		if (mreq->imr_interface.s_addr == INADDR_ANY) {
			ro.ro_rt = NULL;
			dst = satosin(&ro.ro_dst);
			dst->sin_len = sizeof(*dst);
			dst->sin_family = AF_INET;
			dst->sin_addr = mreq->imr_multiaddr;
			rtalloc(&ro);
			if (ro.ro_rt == NULL) {
				error = EADDRNOTAVAIL;
				break;
			}
			ifp = ro.ro_rt->rt_ifp;
			rtfree(ro.ro_rt);
		} else {
			INADDR_TO_IFP(mreq->imr_interface, ifp);
		}
		/*
		 * See if we found an interface, and confirm that it
		 * supports multicast.
		 */
		if (ifp == NULL || (ifp->if_flags & IFF_MULTICAST) == 0) {
			error = EADDRNOTAVAIL;
			break;
		}
		/*
		 * See if the membership already exists or if all the
		 * membership slots are full.
		 */
		for (i = 0; i < imo->imo_num_memberships; ++i) {
			if (imo->imo_membership[i]->inm_ifp == ifp &&
			    imo->imo_membership[i]->inm_addr.s_addr
						== mreq->imr_multiaddr.s_addr)
				break;
		}
		if (i < imo->imo_num_memberships) {
			error = EADDRINUSE;
			break;
		}
		if (i == IP_MAX_MEMBERSHIPS) {
			error = ETOOMANYREFS;
			break;
		}
		/*
		 * Everything looks good; add a new record to the multicast
		 * address list for the given interface.
		 */
		if ((imo->imo_membership[i] =
		    in_addmulti(&mreq->imr_multiaddr, ifp)) == NULL) {
			error = ENOBUFS;
			break;
		}
		++imo->imo_num_memberships;
		break;

	case IP_DROP_MEMBERSHIP:
		/*
		 * Drop a multicast group membership.
		 * Group must be a valid IP multicast address.
		 */
		if (m == NULL || m->m_len != sizeof(struct ip_mreq)) {
			error = EINVAL;
			break;
		}
		mreq = mtod(m, struct ip_mreq *);
		if (!IN_MULTICAST(mreq->imr_multiaddr.s_addr)) {
			error = EINVAL;
			break;
		}
		/*
		 * If an interface address was specified, get a pointer
		 * to its ifnet structure.
		 */
		if (mreq->imr_interface.s_addr == INADDR_ANY)
			ifp = NULL;
		else {
			INADDR_TO_IFP(mreq->imr_interface, ifp);
			if (ifp == NULL) {
				error = EADDRNOTAVAIL;
				break;
			}
		}
		/*
		 * Find the membership in the membership array.
		 */
		for (i = 0; i < imo->imo_num_memberships; ++i) {
			if ((ifp == NULL ||
			     imo->imo_membership[i]->inm_ifp == ifp) &&
			     imo->imo_membership[i]->inm_addr.s_addr ==
			     mreq->imr_multiaddr.s_addr)
				break;
		}
		if (i == imo->imo_num_memberships) {
			error = EADDRNOTAVAIL;
			break;
		}
		/*
		 * Give up the multicast address record to which the
		 * membership points.
		 */
		in_delmulti(imo->imo_membership[i]);
		/*
		 * Remove the gap in the membership array.
		 */
		for (++i; i < imo->imo_num_memberships; ++i)
			imo->imo_membership[i-1] = imo->imo_membership[i];
		--imo->imo_num_memberships;
		break;

	default:
		error = EOPNOTSUPP;
		break;
	}

	/*
	 * If all options have default values, no need to keep the mbuf.
	 */
	if (imo->imo_multicast_ifp == NULL &&
	    imo->imo_multicast_ttl == IP_DEFAULT_MULTICAST_TTL &&
	    imo->imo_multicast_loop == IP_DEFAULT_MULTICAST_LOOP &&
	    imo->imo_num_memberships == 0) {
		free(*imop, M_IPMOPTS);
		*imop = NULL;
	}

	return (error);
}

/*
 * Return the IP multicast options in response to user getsockopt().
 */
int
ip_getmoptions(optname, imo, mp)
	int optname;
	register struct ip_moptions *imo;
	register struct mbuf **mp;
{
	u_char *ttl;
	u_char *loop;
	struct in_addr *addr;
	struct in_ifaddr *ia;

	*mp = m_get(M_WAIT, MT_SOOPTS);

	switch (optname) {

	case IP_MULTICAST_IF:
		addr = mtod(*mp, struct in_addr *);
		(*mp)->m_len = sizeof(struct in_addr);
		if (imo == NULL || imo->imo_multicast_ifp == NULL)
			addr->s_addr = INADDR_ANY;
		else {
			IFP_TO_IA(imo->imo_multicast_ifp, ia);
			addr->s_addr = (ia == NULL) ? INADDR_ANY
					: ia->ia_addr.sin_addr.s_addr;
		}
		return (0);

	case IP_MULTICAST_TTL:
		ttl = mtod(*mp, u_char *);
		(*mp)->m_len = 1;
		*ttl = (imo == NULL) ? IP_DEFAULT_MULTICAST_TTL
				     : imo->imo_multicast_ttl;
		return (0);

	case IP_MULTICAST_LOOP:
		loop = mtod(*mp, u_char *);
		(*mp)->m_len = 1;
		*loop = (imo == NULL) ? IP_DEFAULT_MULTICAST_LOOP
				      : imo->imo_multicast_loop;
		return (0);

	default:
		return (EOPNOTSUPP);
	}
}

/*
 * Discard the IP multicast options.
 */
void
ip_freemoptions(imo)
	register struct ip_moptions *imo;
{
	register int i;

	if (imo != NULL) {
		for (i = 0; i < imo->imo_num_memberships; ++i)
			in_delmulti(imo->imo_membership[i]);
		free(imo, M_IPMOPTS);
	}
}

/*
 * Routine called from ip_output() to loop back a copy of an IP multicast
 * packet to the input queue of a specified interface.  Note that this
 * calls the output routine of the loopback "driver", but with an interface
 * pointer that might NOT be &loif -- easier than replicating that code here.
 */
static void
ip_mloopback(ifp, m, dst)
	struct ifnet *ifp;
	register struct mbuf *m;
	register struct sockaddr_in *dst;
{
	register struct ip *ip;
	struct mbuf *copym;

	copym = m_copy(m, 0, M_COPYALL);
	if (copym != NULL) {
		/*
		 * We don't bother to fragment if the IP length is greater
		 * than the interface's MTU.  Can this possibly matter?
		 */
		ip = mtod(copym, struct ip *);
		ip->ip_len = htons((u_int16_t)ip->ip_len);
		ip->ip_off = htons((u_int16_t)ip->ip_off);
		ip->ip_sum = 0;
		ip->ip_sum = in_cksum(copym, ip->ip_hl << 2);
		(void) looutput(ifp, copym, sintosa(dst), NULL);
	}
}