aboutsummaryrefslogtreecommitdiff
path: root/sys/netinet6/ip6_input.c
blob: 712b9923d8e71cb24a40cdb1f7c8c6a871aafb50 (plain) (blame)
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
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
/*-
 * SPDX-License-Identifier: BSD-3-Clause
 *
 * Copyright (C) 1995, 1996, 1997, and 1998 WIDE Project.
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. Neither the name of the project nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE PROJECT AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE PROJECT OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 *	$KAME: ip6_input.c,v 1.259 2002/01/21 04:58:09 jinmei Exp $
 */

/*-
 * 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.
 * 3. 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_input.c	8.2 (Berkeley) 1/4/94
 */

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

#include "opt_inet.h"
#include "opt_inet6.h"
#include "opt_ipsec.h"
#include "opt_route.h"
#include "opt_rss.h"

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/hhook.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/proc.h>
#include <sys/domain.h>
#include <sys/protosw.h>
#include <sys/sdt.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/errno.h>
#include <sys/time.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/rmlock.h>
#include <sys/syslog.h>
#include <sys/sysctl.h>

#include <net/if.h>
#include <net/if_var.h>
#include <net/if_types.h>
#include <net/if_dl.h>
#include <net/route.h>
#include <net/netisr.h>
#include <net/rss_config.h>
#include <net/pfil.h>
#include <net/vnet.h>

#include <netinet/in.h>
#include <netinet/in_kdtrace.h>
#include <netinet/ip_var.h>
#include <netinet/in_systm.h>
#include <net/if_llatbl.h>
#ifdef INET
#include <netinet/ip.h>
#include <netinet/ip_icmp.h>
#endif /* INET */
#include <netinet/ip6.h>
#include <netinet6/in6_var.h>
#include <netinet6/ip6_var.h>
#include <netinet/in_pcb.h>
#include <netinet/icmp6.h>
#include <netinet6/scope6_var.h>
#include <netinet6/in6_ifattach.h>
#include <netinet6/mld6_var.h>
#include <netinet6/nd6.h>
#include <netinet6/in6_rss.h>

#include <netipsec/ipsec_support.h>

#include <netinet6/ip6protosw.h>

extern struct domain inet6domain;

u_char ip6_protox[IPPROTO_MAX];
VNET_DEFINE(struct in6_ifaddrhead, in6_ifaddrhead);
VNET_DEFINE(struct in6_ifaddrlisthead *, in6_ifaddrhashtbl);
VNET_DEFINE(u_long, in6_ifaddrhmask);

static struct netisr_handler ip6_nh = {
	.nh_name = "ip6",
	.nh_handler = ip6_input,
	.nh_proto = NETISR_IPV6,
#ifdef RSS
	.nh_m2cpuid = rss_soft_m2cpuid_v6,
	.nh_policy = NETISR_POLICY_CPU,
	.nh_dispatch = NETISR_DISPATCH_HYBRID,
#else
	.nh_policy = NETISR_POLICY_FLOW,
#endif
};

static int
sysctl_netinet6_intr_queue_maxlen(SYSCTL_HANDLER_ARGS)
{
	int error, qlimit;

	netisr_getqlimit(&ip6_nh, &qlimit);
	error = sysctl_handle_int(oidp, &qlimit, 0, req);
	if (error || !req->newptr)
		return (error);
	if (qlimit < 1)
		return (EINVAL);
	return (netisr_setqlimit(&ip6_nh, qlimit));
}
SYSCTL_DECL(_net_inet6_ip6);
SYSCTL_PROC(_net_inet6_ip6, IPV6CTL_INTRQMAXLEN, intr_queue_maxlen,
    CTLTYPE_INT|CTLFLAG_RW, 0, 0, sysctl_netinet6_intr_queue_maxlen, "I",
    "Maximum size of the IPv6 input queue");

#ifdef RSS
static struct netisr_handler ip6_direct_nh = {
	.nh_name = "ip6_direct",
	.nh_handler = ip6_direct_input,
	.nh_proto = NETISR_IPV6_DIRECT,
	.nh_m2cpuid = rss_soft_m2cpuid_v6,
	.nh_policy = NETISR_POLICY_CPU,
	.nh_dispatch = NETISR_DISPATCH_HYBRID,
};

static int
sysctl_netinet6_intr_direct_queue_maxlen(SYSCTL_HANDLER_ARGS)
{
	int error, qlimit;

	netisr_getqlimit(&ip6_direct_nh, &qlimit);
	error = sysctl_handle_int(oidp, &qlimit, 0, req);
	if (error || !req->newptr)
		return (error);
	if (qlimit < 1)
		return (EINVAL);
	return (netisr_setqlimit(&ip6_direct_nh, qlimit));
}
SYSCTL_PROC(_net_inet6_ip6, IPV6CTL_INTRDQMAXLEN, intr_direct_queue_maxlen,
    CTLTYPE_INT|CTLFLAG_RW, 0, 0, sysctl_netinet6_intr_direct_queue_maxlen,
    "I", "Maximum size of the IPv6 direct input queue");

#endif

VNET_DEFINE(struct pfil_head, inet6_pfil_hook);

VNET_PCPUSTAT_DEFINE(struct ip6stat, ip6stat);
VNET_PCPUSTAT_SYSINIT(ip6stat);
#ifdef VIMAGE
VNET_PCPUSTAT_SYSUNINIT(ip6stat);
#endif /* VIMAGE */

struct rmlock in6_ifaddr_lock;
RM_SYSINIT(in6_ifaddr_lock, &in6_ifaddr_lock, "in6_ifaddr_lock");

static int ip6_hopopts_input(u_int32_t *, u_int32_t *, struct mbuf **, int *);
#ifdef PULLDOWN_TEST
static struct mbuf *ip6_pullexthdr(struct mbuf *, size_t, int);
#endif

/*
 * IP6 initialization: fill in IP6 protocol switch table.
 * All protocols not implemented in kernel go to raw IP6 protocol handler.
 */
void
ip6_init(void)
{
	struct protosw *pr;
	int i;

	TUNABLE_INT_FETCH("net.inet6.ip6.auto_linklocal",
	    &V_ip6_auto_linklocal);
	TUNABLE_INT_FETCH("net.inet6.ip6.accept_rtadv", &V_ip6_accept_rtadv);
	TUNABLE_INT_FETCH("net.inet6.ip6.no_radr", &V_ip6_no_radr);

	CK_STAILQ_INIT(&V_in6_ifaddrhead);
	V_in6_ifaddrhashtbl = hashinit(IN6ADDR_NHASH, M_IFADDR,
	    &V_in6_ifaddrhmask);

	/* Initialize packet filter hooks. */
	V_inet6_pfil_hook.ph_type = PFIL_TYPE_AF;
	V_inet6_pfil_hook.ph_af = AF_INET6;
	if ((i = pfil_head_register(&V_inet6_pfil_hook)) != 0)
		printf("%s: WARNING: unable to register pfil hook, "
			"error %d\n", __func__, i);

	if (hhook_head_register(HHOOK_TYPE_IPSEC_IN, AF_INET6,
	    &V_ipsec_hhh_in[HHOOK_IPSEC_INET6],
	    HHOOK_WAITOK | HHOOK_HEADISINVNET) != 0)
		printf("%s: WARNING: unable to register input helper hook\n",
		    __func__);
	if (hhook_head_register(HHOOK_TYPE_IPSEC_OUT, AF_INET6,
	    &V_ipsec_hhh_out[HHOOK_IPSEC_INET6],
	    HHOOK_WAITOK | HHOOK_HEADISINVNET) != 0)
		printf("%s: WARNING: unable to register output helper hook\n",
		    __func__);

	scope6_init();
	addrsel_policy_init();
	nd6_init();
	frag6_init();

	V_ip6_desync_factor = arc4random() % MAX_TEMP_DESYNC_FACTOR;

	/* Skip global initialization stuff for non-default instances. */
#ifdef VIMAGE
	if (!IS_DEFAULT_VNET(curvnet)) {
		netisr_register_vnet(&ip6_nh);
#ifdef RSS
		netisr_register_vnet(&ip6_direct_nh);
#endif
		return;
	}
#endif

	pr = pffindproto(PF_INET6, IPPROTO_RAW, SOCK_RAW);
	if (pr == NULL)
		panic("ip6_init");

	/* Initialize the entire ip6_protox[] array to IPPROTO_RAW. */
	for (i = 0; i < IPPROTO_MAX; i++)
		ip6_protox[i] = pr - inet6sw;
	/*
	 * Cycle through IP protocols and put them into the appropriate place
	 * in ip6_protox[].
	 */
	for (pr = inet6domain.dom_protosw;
	    pr < inet6domain.dom_protoswNPROTOSW; pr++)
		if (pr->pr_domain->dom_family == PF_INET6 &&
		    pr->pr_protocol && pr->pr_protocol != IPPROTO_RAW) {
			/* Be careful to only index valid IP protocols. */
			if (pr->pr_protocol < IPPROTO_MAX)
				ip6_protox[pr->pr_protocol] = pr - inet6sw;
		}

	netisr_register(&ip6_nh);
#ifdef RSS
	netisr_register(&ip6_direct_nh);
#endif
}

/*
 * The protocol to be inserted into ip6_protox[] must be already registered
 * in inet6sw[], either statically or through pf_proto_register().
 */
int
ip6proto_register(short ip6proto)
{
	struct protosw *pr;

	/* Sanity checks. */
	if (ip6proto <= 0 || ip6proto >= IPPROTO_MAX)
		return (EPROTONOSUPPORT);

	/*
	 * The protocol slot must not be occupied by another protocol
	 * already.  An index pointing to IPPROTO_RAW is unused.
	 */
	pr = pffindproto(PF_INET6, IPPROTO_RAW, SOCK_RAW);
	if (pr == NULL)
		return (EPFNOSUPPORT);
	if (ip6_protox[ip6proto] != pr - inet6sw)	/* IPPROTO_RAW */
		return (EEXIST);

	/*
	 * Find the protocol position in inet6sw[] and set the index.
	 */
	for (pr = inet6domain.dom_protosw;
	    pr < inet6domain.dom_protoswNPROTOSW; pr++) {
		if (pr->pr_domain->dom_family == PF_INET6 &&
		    pr->pr_protocol && pr->pr_protocol == ip6proto) {
			ip6_protox[pr->pr_protocol] = pr - inet6sw;
			return (0);
		}
	}
	return (EPROTONOSUPPORT);
}

int
ip6proto_unregister(short ip6proto)
{
	struct protosw *pr;

	/* Sanity checks. */
	if (ip6proto <= 0 || ip6proto >= IPPROTO_MAX)
		return (EPROTONOSUPPORT);

	/* Check if the protocol was indeed registered. */
	pr = pffindproto(PF_INET6, IPPROTO_RAW, SOCK_RAW);
	if (pr == NULL)
		return (EPFNOSUPPORT);
	if (ip6_protox[ip6proto] == pr - inet6sw)	/* IPPROTO_RAW */
		return (ENOENT);

	/* Reset the protocol slot to IPPROTO_RAW. */
	ip6_protox[ip6proto] = pr - inet6sw;
	return (0);
}

#ifdef VIMAGE
static void
ip6_destroy(void *unused __unused)
{
	struct ifaddr *ifa, *nifa;
	struct ifnet *ifp;
	int error;

#ifdef RSS
	netisr_unregister_vnet(&ip6_direct_nh);
#endif
	netisr_unregister_vnet(&ip6_nh);

	if ((error = pfil_head_unregister(&V_inet6_pfil_hook)) != 0)
		printf("%s: WARNING: unable to unregister pfil hook, "
		    "error %d\n", __func__, error);
	error = hhook_head_deregister(V_ipsec_hhh_in[HHOOK_IPSEC_INET6]);
	if (error != 0) {
		printf("%s: WARNING: unable to deregister input helper hook "
		    "type HHOOK_TYPE_IPSEC_IN, id HHOOK_IPSEC_INET6: "
		    "error %d returned\n", __func__, error);
	}
	error = hhook_head_deregister(V_ipsec_hhh_out[HHOOK_IPSEC_INET6]);
	if (error != 0) {
		printf("%s: WARNING: unable to deregister output helper hook "
		    "type HHOOK_TYPE_IPSEC_OUT, id HHOOK_IPSEC_INET6: "
		    "error %d returned\n", __func__, error);
	}

	/* Cleanup addresses. */
	IFNET_RLOCK();
	CK_STAILQ_FOREACH(ifp, &V_ifnet, if_link) {
		/* Cannot lock here - lock recursion. */
		/* IF_ADDR_LOCK(ifp); */
		CK_STAILQ_FOREACH_SAFE(ifa, &ifp->if_addrhead, ifa_link, nifa) {

			if (ifa->ifa_addr->sa_family != AF_INET6)
				continue;
			in6_purgeaddr(ifa);
		}
		/* IF_ADDR_UNLOCK(ifp); */
		in6_ifdetach_destroy(ifp);
		mld_domifdetach(ifp);
		/* Make sure any routes are gone as well. */
		rt_flushifroutes_af(ifp, AF_INET6);
	}
	IFNET_RUNLOCK();

	nd6_destroy();
	in6_ifattach_destroy();

	hashdestroy(V_in6_ifaddrhashtbl, M_IFADDR, V_in6_ifaddrhmask);
}

VNET_SYSUNINIT(inet6, SI_SUB_PROTO_DOMAIN, SI_ORDER_THIRD, ip6_destroy, NULL);
#endif

static int
ip6_input_hbh(struct mbuf *m, uint32_t *plen, uint32_t *rtalert, int *off,
    int *nxt, int *ours)
{
	struct ip6_hdr *ip6;
	struct ip6_hbh *hbh;

	if (ip6_hopopts_input(plen, rtalert, &m, off)) {
#if 0	/*touches NULL pointer*/
		in6_ifstat_inc(m->m_pkthdr.rcvif, ifs6_in_discard);
#endif
		goto out;	/* m have already been freed */
	}

	/* adjust pointer */
	ip6 = mtod(m, struct ip6_hdr *);

	/*
	 * if the payload length field is 0 and the next header field
	 * indicates Hop-by-Hop Options header, then a Jumbo Payload
	 * option MUST be included.
	 */
	if (ip6->ip6_plen == 0 && *plen == 0) {
		/*
		 * Note that if a valid jumbo payload option is
		 * contained, ip6_hopopts_input() must set a valid
		 * (non-zero) payload length to the variable plen.
		 */
		IP6STAT_INC(ip6s_badoptions);
		in6_ifstat_inc(m->m_pkthdr.rcvif, ifs6_in_discard);
		in6_ifstat_inc(m->m_pkthdr.rcvif, ifs6_in_hdrerr);
		icmp6_error(m, ICMP6_PARAM_PROB,
			    ICMP6_PARAMPROB_HEADER,
			    (caddr_t)&ip6->ip6_plen - (caddr_t)ip6);
		goto out;
	}
#ifndef PULLDOWN_TEST
	/* ip6_hopopts_input() ensures that mbuf is contiguous */
	hbh = (struct ip6_hbh *)(ip6 + 1);
#else
	IP6_EXTHDR_GET(hbh, struct ip6_hbh *, m, sizeof(struct ip6_hdr),
		sizeof(struct ip6_hbh));
	if (hbh == NULL) {
		IP6STAT_INC(ip6s_tooshort);
		goto out;
	}
#endif
	*nxt = hbh->ip6h_nxt;

	/*
	 * If we are acting as a router and the packet contains a
	 * router alert option, see if we know the option value.
	 * Currently, we only support the option value for MLD, in which
	 * case we should pass the packet to the multicast routing
	 * daemon.
	 */
	if (*rtalert != ~0) {
		switch (*rtalert) {
		case IP6OPT_RTALERT_MLD:
			if (V_ip6_forwarding)
				*ours = 1;
			break;
		default:
			/*
			 * RFC2711 requires unrecognized values must be
			 * silently ignored.
			 */
			break;
		}
	}

	return (0);

out:
	return (1);
}

#ifdef RSS
/*
 * IPv6 direct input routine.
 *
 * This is called when reinjecting completed fragments where
 * all of the previous checking and book-keeping has been done.
 */
void
ip6_direct_input(struct mbuf *m)
{
	int off, nxt;
	int nest;
	struct m_tag *mtag;
	struct ip6_direct_ctx *ip6dc;

	mtag = m_tag_locate(m, MTAG_ABI_IPV6, IPV6_TAG_DIRECT, NULL);
	KASSERT(mtag != NULL, ("Reinjected packet w/o direct ctx tag!"));

	ip6dc = (struct ip6_direct_ctx *)(mtag + 1);
	nxt = ip6dc->ip6dc_nxt;
	off = ip6dc->ip6dc_off;

	nest = 0;

	m_tag_delete(m, mtag);

	while (nxt != IPPROTO_DONE) {
		if (V_ip6_hdrnestlimit && (++nest > V_ip6_hdrnestlimit)) {
			IP6STAT_INC(ip6s_toomanyhdr);
			goto bad;
		}

		/*
		 * protection against faulty packet - there should be
		 * more sanity checks in header chain processing.
		 */
		if (m->m_pkthdr.len < off) {
			IP6STAT_INC(ip6s_tooshort);
			in6_ifstat_inc(m->m_pkthdr.rcvif, ifs6_in_truncated);
			goto bad;
		}

#if defined(IPSEC) || defined(IPSEC_SUPPORT)
		if (IPSEC_ENABLED(ipv6)) {
			if (IPSEC_INPUT(ipv6, m, off, nxt) != 0)
				return;
		}
#endif /* IPSEC */

		nxt = (*inet6sw[ip6_protox[nxt]].pr_input)(&m, &off, nxt);
	}
	return;
bad:
	m_freem(m);
}
#endif

void
ip6_input(struct mbuf *m)
{
	struct in6_addr odst;
	struct ip6_hdr *ip6;
	struct in6_ifaddr *ia;
	struct ifnet *rcvif;
	u_int32_t plen;
	u_int32_t rtalert = ~0;
	int off = sizeof(struct ip6_hdr), nest;
	int nxt, ours = 0;
	int srcrt = 0;

	/*
	 * Drop the packet if IPv6 operation is disabled on the interface.
	 */
	rcvif = m->m_pkthdr.rcvif;
	if ((ND_IFINFO(rcvif)->flags & ND6_IFF_IFDISABLED))
		goto bad;

#if defined(IPSEC) || defined(IPSEC_SUPPORT)
	/*
	 * should the inner packet be considered authentic?
	 * see comment in ah4_input().
	 * NB: m cannot be NULL when passed to the input routine
	 */

	m->m_flags &= ~M_AUTHIPHDR;
	m->m_flags &= ~M_AUTHIPDGM;

#endif /* IPSEC */

	if (m->m_flags & M_FASTFWD_OURS) {
		/*
		 * Firewall changed destination to local.
		 */
		ip6 = mtod(m, struct ip6_hdr *);
		goto passin;
	}

	/*
	 * mbuf statistics
	 */
	if (m->m_flags & M_EXT) {
		if (m->m_next)
			IP6STAT_INC(ip6s_mext2m);
		else
			IP6STAT_INC(ip6s_mext1);
	} else {
		if (m->m_next) {
			if (m->m_flags & M_LOOP) {
				IP6STAT_INC(ip6s_m2m[V_loif->if_index]);
			} else if (rcvif->if_index < IP6S_M2MMAX)
				IP6STAT_INC(ip6s_m2m[rcvif->if_index]);
			else
				IP6STAT_INC(ip6s_m2m[0]);
		} else
			IP6STAT_INC(ip6s_m1);
	}

	in6_ifstat_inc(rcvif, ifs6_in_receive);
	IP6STAT_INC(ip6s_total);

#ifndef PULLDOWN_TEST
	/*
	 * L2 bridge code and some other code can return mbuf chain
	 * that does not conform to KAME requirement.  too bad.
	 * XXX: fails to join if interface MTU > MCLBYTES.  jumbogram?
	 */
	if (m && m->m_next != NULL && m->m_pkthdr.len < MCLBYTES) {
		struct mbuf *n;

		if (m->m_pkthdr.len > MHLEN)
			n = m_getcl(M_NOWAIT, MT_DATA, M_PKTHDR);
		else
			n = m_gethdr(M_NOWAIT, MT_DATA);
		if (n == NULL)
			goto bad;

		m_move_pkthdr(n, m);
		m_copydata(m, 0, n->m_pkthdr.len, mtod(n, caddr_t));
		n->m_len = n->m_pkthdr.len;
		m_freem(m);
		m = n;
	}
	IP6_EXTHDR_CHECK(m, 0, sizeof(struct ip6_hdr), /* nothing */);
#endif

	if (m->m_len < sizeof(struct ip6_hdr)) {
		if ((m = m_pullup(m, sizeof(struct ip6_hdr))) == NULL) {
			IP6STAT_INC(ip6s_toosmall);
			in6_ifstat_inc(rcvif, ifs6_in_hdrerr);
			goto bad;
		}
	}

	ip6 = mtod(m, struct ip6_hdr *);
	if ((ip6->ip6_vfc & IPV6_VERSION_MASK) != IPV6_VERSION) {
		IP6STAT_INC(ip6s_badvers);
		in6_ifstat_inc(rcvif, ifs6_in_hdrerr);
		goto bad;
	}

	IP6STAT_INC(ip6s_nxthist[ip6->ip6_nxt]);
	IP_PROBE(receive, NULL, NULL, ip6, rcvif, NULL, ip6);

	/*
	 * Check against address spoofing/corruption.
	 */
	if (IN6_IS_ADDR_MULTICAST(&ip6->ip6_src) ||
	    IN6_IS_ADDR_UNSPECIFIED(&ip6->ip6_dst)) {
		/*
		 * XXX: "badscope" is not very suitable for a multicast source.
		 */
		IP6STAT_INC(ip6s_badscope);
		in6_ifstat_inc(rcvif, ifs6_in_addrerr);
		goto bad;
	}
	if (IN6_IS_ADDR_MC_INTFACELOCAL(&ip6->ip6_dst) &&
	    !(m->m_flags & M_LOOP)) {
		/*
		 * In this case, the packet should come from the loopback
		 * interface.  However, we cannot just check the if_flags,
		 * because ip6_mloopback() passes the "actual" interface
		 * as the outgoing/incoming interface.
		 */
		IP6STAT_INC(ip6s_badscope);
		in6_ifstat_inc(rcvif, ifs6_in_addrerr);
		goto bad;
	}
	if (IN6_IS_ADDR_MULTICAST(&ip6->ip6_dst) &&
	    IPV6_ADDR_MC_SCOPE(&ip6->ip6_dst) == 0) {
		/*
		 * RFC4291 2.7:
		 * Nodes must not originate a packet to a multicast address
		 * whose scop field contains the reserved value 0; if such
		 * a packet is received, it must be silently dropped.
		 */
		IP6STAT_INC(ip6s_badscope);
		in6_ifstat_inc(rcvif, ifs6_in_addrerr);
		goto bad;
	}
#ifdef ALTQ
	if (altq_input != NULL && (*altq_input)(m, AF_INET6) == 0) {
		/* packet is dropped by traffic conditioner */
		return;
	}
#endif
	/*
	 * The following check is not documented in specs.  A malicious
	 * party may be able to use IPv4 mapped addr to confuse tcp/udp stack
	 * and bypass security checks (act as if it was from 127.0.0.1 by using
	 * IPv6 src ::ffff:127.0.0.1).  Be cautious.
	 *
	 * This check chokes if we are in an SIIT cloud.  As none of BSDs
	 * support IPv4-less kernel compilation, we cannot support SIIT
	 * environment at all.  So, it makes more sense for us to reject any
	 * malicious packets for non-SIIT environment, than try to do a
	 * partial support for SIIT environment.
	 */
	if (IN6_IS_ADDR_V4MAPPED(&ip6->ip6_src) ||
	    IN6_IS_ADDR_V4MAPPED(&ip6->ip6_dst)) {
		IP6STAT_INC(ip6s_badscope);
		in6_ifstat_inc(rcvif, ifs6_in_addrerr);
		goto bad;
	}
#if 0
	/*
	 * Reject packets with IPv4 compatible addresses (auto tunnel).
	 *
	 * The code forbids auto tunnel relay case in RFC1933 (the check is
	 * stronger than RFC1933).  We may want to re-enable it if mech-xx
	 * is revised to forbid relaying case.
	 */
	if (IN6_IS_ADDR_V4COMPAT(&ip6->ip6_src) ||
	    IN6_IS_ADDR_V4COMPAT(&ip6->ip6_dst)) {
		IP6STAT_INC(ip6s_badscope);
		in6_ifstat_inc(m->m_pkthdr.rcvif, ifs6_in_addrerr);
		goto bad;
	}
#endif
	/*
	 * Try to forward the packet, but if we fail continue.
	 * ip6_tryforward() does not generate redirects, so fall
	 * through to normal processing if redirects are required.
	 * ip6_tryforward() does inbound and outbound packet firewall
	 * processing. If firewall has decided that destination becomes
	 * our local address, it sets M_FASTFWD_OURS flag. In this
	 * case skip another inbound firewall processing and update
	 * ip6 pointer.
	 */
	if (V_ip6_forwarding != 0 && V_ip6_sendredirects == 0
#if defined(IPSEC) || defined(IPSEC_SUPPORT)
	    && (!IPSEC_ENABLED(ipv6) ||
	    IPSEC_CAPS(ipv6, m, IPSEC_CAP_OPERABLE) == 0)
#endif
	    ) {
		if ((m = ip6_tryforward(m)) == NULL)
			return;
		if (m->m_flags & M_FASTFWD_OURS) {
			ip6 = mtod(m, struct ip6_hdr *);
			goto passin;
		}
	}
#if defined(IPSEC) || defined(IPSEC_SUPPORT)
	/*
	 * Bypass packet filtering for packets previously handled by IPsec.
	 */
	if (IPSEC_ENABLED(ipv6) &&
	    IPSEC_CAPS(ipv6, m, IPSEC_CAP_BYPASS_FILTER) != 0)
			goto passin;
#endif
	/*
	 * Run through list of hooks for input packets.
	 *
	 * NB: Beware of the destination address changing
	 *     (e.g. by NAT rewriting).  When this happens,
	 *     tell ip6_forward to do the right thing.
	 */

	/* Jump over all PFIL processing if hooks are not active. */
	if (!PFIL_HOOKED(&V_inet6_pfil_hook))
		goto passin;

	odst = ip6->ip6_dst;
	if (pfil_run_hooks(&V_inet6_pfil_hook, &m,
	    m->m_pkthdr.rcvif, PFIL_IN, 0, NULL))
		return;
	if (m == NULL)			/* consumed by filter */
		return;
	ip6 = mtod(m, struct ip6_hdr *);
	srcrt = !IN6_ARE_ADDR_EQUAL(&odst, &ip6->ip6_dst);
	if ((m->m_flags & (M_IP6_NEXTHOP | M_FASTFWD_OURS)) == M_IP6_NEXTHOP &&
	    m_tag_find(m, PACKET_TAG_IPFORWARD, NULL) != NULL) {
		/*
		 * Directly ship the packet on.  This allows forwarding
		 * packets originally destined to us to some other directly
		 * connected host.
		 */
		ip6_forward(m, 1);
		return;
	}

passin:
	/*
	 * Disambiguate address scope zones (if there is ambiguity).
	 * We first make sure that the original source or destination address
	 * is not in our internal form for scoped addresses.  Such addresses
	 * are not necessarily invalid spec-wise, but we cannot accept them due
	 * to the usage conflict.
	 * in6_setscope() then also checks and rejects the cases where src or
	 * dst are the loopback address and the receiving interface
	 * is not loopback.
	 */
	if (in6_clearscope(&ip6->ip6_src) || in6_clearscope(&ip6->ip6_dst)) {
		IP6STAT_INC(ip6s_badscope); /* XXX */
		goto bad;
	}
	if (in6_setscope(&ip6->ip6_src, rcvif, NULL) ||
	    in6_setscope(&ip6->ip6_dst, rcvif, NULL)) {
		IP6STAT_INC(ip6s_badscope);
		goto bad;
	}
	if (m->m_flags & M_FASTFWD_OURS) {
		m->m_flags &= ~M_FASTFWD_OURS;
		ours = 1;
		goto hbhcheck;
	}
	/*
	 * Multicast check. Assume packet is for us to avoid
	 * prematurely taking locks.
	 */
	if (IN6_IS_ADDR_MULTICAST(&ip6->ip6_dst)) {
		ours = 1;
		in6_ifstat_inc(rcvif, ifs6_in_mcast);
		goto hbhcheck;
	}
	/*
	 * Unicast check
	 * XXX: For now we keep link-local IPv6 addresses with embedded
	 *      scope zone id, therefore we use zero zoneid here.
	 */
	ia = in6ifa_ifwithaddr(&ip6->ip6_dst, 0 /* XXX */);
	if (ia != NULL) {
		if (ia->ia6_flags & IN6_IFF_NOTREADY) {
			char ip6bufs[INET6_ADDRSTRLEN];
			char ip6bufd[INET6_ADDRSTRLEN];
			/* address is not ready, so discard the packet. */
			nd6log((LOG_INFO,
			    "ip6_input: packet to an unready address %s->%s\n",
			    ip6_sprintf(ip6bufs, &ip6->ip6_src),
			    ip6_sprintf(ip6bufd, &ip6->ip6_dst)));
			ifa_free(&ia->ia_ifa);
			goto bad;
		}
		/* Count the packet in the ip address stats */
		counter_u64_add(ia->ia_ifa.ifa_ipackets, 1);
		counter_u64_add(ia->ia_ifa.ifa_ibytes, m->m_pkthdr.len);
		ifa_free(&ia->ia_ifa);
		ours = 1;
		goto hbhcheck;
	}

	/*
	 * Now there is no reason to process the packet if it's not our own
	 * and we're not a router.
	 */
	if (!V_ip6_forwarding) {
		IP6STAT_INC(ip6s_cantforward);
		goto bad;
	}

  hbhcheck:
	/*
	 * Process Hop-by-Hop options header if it's contained.
	 * m may be modified in ip6_hopopts_input().
	 * If a JumboPayload option is included, plen will also be modified.
	 */
	plen = (u_int32_t)ntohs(ip6->ip6_plen);
	if (ip6->ip6_nxt == IPPROTO_HOPOPTS) {
		if (ip6_input_hbh(m, &plen, &rtalert, &off, &nxt, &ours) != 0)
			return;
	} else
		nxt = ip6->ip6_nxt;

	/*
	 * Use mbuf flags to propagate Router Alert option to
	 * ICMPv6 layer, as hop-by-hop options have been stripped.
	 */
	if (rtalert != ~0)
		m->m_flags |= M_RTALERT_MLD;

	/*
	 * Check that the amount of data in the buffers
	 * is as at least much as the IPv6 header would have us expect.
	 * Trim mbufs if longer than we expect.
	 * Drop packet if shorter than we expect.
	 */
	if (m->m_pkthdr.len - sizeof(struct ip6_hdr) < plen) {
		IP6STAT_INC(ip6s_tooshort);
		in6_ifstat_inc(rcvif, ifs6_in_truncated);
		goto bad;
	}
	if (m->m_pkthdr.len > sizeof(struct ip6_hdr) + plen) {
		if (m->m_len == m->m_pkthdr.len) {
			m->m_len = sizeof(struct ip6_hdr) + plen;
			m->m_pkthdr.len = sizeof(struct ip6_hdr) + plen;
		} else
			m_adj(m, sizeof(struct ip6_hdr) + plen - m->m_pkthdr.len);
	}

	/*
	 * Forward if desirable.
	 */
	if (V_ip6_mrouter &&
	    IN6_IS_ADDR_MULTICAST(&ip6->ip6_dst)) {
		/*
		 * If we are acting as a multicast router, all
		 * incoming multicast packets are passed to the
		 * kernel-level multicast forwarding function.
		 * The packet is returned (relatively) intact; if
		 * ip6_mforward() returns a non-zero value, the packet
		 * must be discarded, else it may be accepted below.
		 *
		 * XXX TODO: Check hlim and multicast scope here to avoid
		 * unnecessarily calling into ip6_mforward().
		 */
		if (ip6_mforward && ip6_mforward(ip6, rcvif, m)) {
			IP6STAT_INC(ip6s_cantforward);
			goto bad;
		}
	} else if (!ours) {
		ip6_forward(m, srcrt);
		return;
	}

	ip6 = mtod(m, struct ip6_hdr *);

	/*
	 * Malicious party may be able to use IPv4 mapped addr to confuse
	 * tcp/udp stack and bypass security checks (act as if it was from
	 * 127.0.0.1 by using IPv6 src ::ffff:127.0.0.1).  Be cautious.
	 *
	 * For SIIT end node behavior, you may want to disable the check.
	 * However, you will  become vulnerable to attacks using IPv4 mapped
	 * source.
	 */
	if (IN6_IS_ADDR_V4MAPPED(&ip6->ip6_src) ||
	    IN6_IS_ADDR_V4MAPPED(&ip6->ip6_dst)) {
		IP6STAT_INC(ip6s_badscope);
		in6_ifstat_inc(rcvif, ifs6_in_addrerr);
		goto bad;
	}

	/*
	 * Tell launch routine the next header
	 */
	IP6STAT_INC(ip6s_delivered);
	in6_ifstat_inc(rcvif, ifs6_in_deliver);
	nest = 0;

	while (nxt != IPPROTO_DONE) {
		if (V_ip6_hdrnestlimit && (++nest > V_ip6_hdrnestlimit)) {
			IP6STAT_INC(ip6s_toomanyhdr);
			goto bad;
		}

		/*
		 * protection against faulty packet - there should be
		 * more sanity checks in header chain processing.
		 */
		if (m->m_pkthdr.len < off) {
			IP6STAT_INC(ip6s_tooshort);
			in6_ifstat_inc(rcvif, ifs6_in_truncated);
			goto bad;
		}

#if defined(IPSEC) || defined(IPSEC_SUPPORT)
		if (IPSEC_ENABLED(ipv6)) {
			if (IPSEC_INPUT(ipv6, m, off, nxt) != 0)
				return;
		}
#endif /* IPSEC */

		nxt = (*inet6sw[ip6_protox[nxt]].pr_input)(&m, &off, nxt);
	}
	return;
bad:
	in6_ifstat_inc(rcvif, ifs6_in_discard);
	if (m != NULL)
		m_freem(m);
}

/*
 * Hop-by-Hop options header processing. If a valid jumbo payload option is
 * included, the real payload length will be stored in plenp.
 *
 * rtalertp - XXX: should be stored more smart way
 */
static int
ip6_hopopts_input(u_int32_t *plenp, u_int32_t *rtalertp,
    struct mbuf **mp, int *offp)
{
	struct mbuf *m = *mp;
	int off = *offp, hbhlen;
	struct ip6_hbh *hbh;

	/* validation of the length of the header */
#ifndef PULLDOWN_TEST
	IP6_EXTHDR_CHECK(m, off, sizeof(*hbh), -1);
	hbh = (struct ip6_hbh *)(mtod(m, caddr_t) + off);
	hbhlen = (hbh->ip6h_len + 1) << 3;

	IP6_EXTHDR_CHECK(m, off, hbhlen, -1);
	hbh = (struct ip6_hbh *)(mtod(m, caddr_t) + off);
#else
	IP6_EXTHDR_GET(hbh, struct ip6_hbh *, m,
		sizeof(struct ip6_hdr), sizeof(struct ip6_hbh));
	if (hbh == NULL) {
		IP6STAT_INC(ip6s_tooshort);
		return -1;
	}
	hbhlen = (hbh->ip6h_len + 1) << 3;
	IP6_EXTHDR_GET(hbh, struct ip6_hbh *, m, sizeof(struct ip6_hdr),
		hbhlen);
	if (hbh == NULL) {
		IP6STAT_INC(ip6s_tooshort);
		return -1;
	}
#endif
	off += hbhlen;
	hbhlen -= sizeof(struct ip6_hbh);
	if (ip6_process_hopopts(m, (u_int8_t *)hbh + sizeof(struct ip6_hbh),
				hbhlen, rtalertp, plenp) < 0)
		return (-1);

	*offp = off;
	*mp = m;
	return (0);
}

/*
 * Search header for all Hop-by-hop options and process each option.
 * This function is separate from ip6_hopopts_input() in order to
 * handle a case where the sending node itself process its hop-by-hop
 * options header. In such a case, the function is called from ip6_output().
 *
 * The function assumes that hbh header is located right after the IPv6 header
 * (RFC2460 p7), opthead is pointer into data content in m, and opthead to
 * opthead + hbhlen is located in contiguous memory region.
 */
int
ip6_process_hopopts(struct mbuf *m, u_int8_t *opthead, int hbhlen,
    u_int32_t *rtalertp, u_int32_t *plenp)
{
	struct ip6_hdr *ip6;
	int optlen = 0;
	u_int8_t *opt = opthead;
	u_int16_t rtalert_val;
	u_int32_t jumboplen;
	const int erroff = sizeof(struct ip6_hdr) + sizeof(struct ip6_hbh);

	for (; hbhlen > 0; hbhlen -= optlen, opt += optlen) {
		switch (*opt) {
		case IP6OPT_PAD1:
			optlen = 1;
			break;
		case IP6OPT_PADN:
			if (hbhlen < IP6OPT_MINLEN) {
				IP6STAT_INC(ip6s_toosmall);
				goto bad;
			}
			optlen = *(opt + 1) + 2;
			break;
		case IP6OPT_ROUTER_ALERT:
			/* XXX may need check for alignment */
			if (hbhlen < IP6OPT_RTALERT_LEN) {
				IP6STAT_INC(ip6s_toosmall);
				goto bad;
			}
			if (*(opt + 1) != IP6OPT_RTALERT_LEN - 2) {
				/* XXX stat */
				icmp6_error(m, ICMP6_PARAM_PROB,
				    ICMP6_PARAMPROB_HEADER,
				    erroff + opt + 1 - opthead);
				return (-1);
			}
			optlen = IP6OPT_RTALERT_LEN;
			bcopy((caddr_t)(opt + 2), (caddr_t)&rtalert_val, 2);
			*rtalertp = ntohs(rtalert_val);
			break;
		case IP6OPT_JUMBO:
			/* XXX may need check for alignment */
			if (hbhlen < IP6OPT_JUMBO_LEN) {
				IP6STAT_INC(ip6s_toosmall);
				goto bad;
			}
			if (*(opt + 1) != IP6OPT_JUMBO_LEN - 2) {
				/* XXX stat */
				icmp6_error(m, ICMP6_PARAM_PROB,
				    ICMP6_PARAMPROB_HEADER,
				    erroff + opt + 1 - opthead);
				return (-1);
			}
			optlen = IP6OPT_JUMBO_LEN;

			/*
			 * IPv6 packets that have non 0 payload length
			 * must not contain a jumbo payload option.
			 */
			ip6 = mtod(m, struct ip6_hdr *);
			if (ip6->ip6_plen) {
				IP6STAT_INC(ip6s_badoptions);
				icmp6_error(m, ICMP6_PARAM_PROB,
				    ICMP6_PARAMPROB_HEADER,
				    erroff + opt - opthead);
				return (-1);
			}

			/*
			 * We may see jumbolen in unaligned location, so
			 * we'd need to perform bcopy().
			 */
			bcopy(opt + 2, &jumboplen, sizeof(jumboplen));
			jumboplen = (u_int32_t)htonl(jumboplen);

#if 1
			/*
			 * if there are multiple jumbo payload options,
			 * *plenp will be non-zero and the packet will be
			 * rejected.
			 * the behavior may need some debate in ipngwg -
			 * multiple options does not make sense, however,
			 * there's no explicit mention in specification.
			 */
			if (*plenp != 0) {
				IP6STAT_INC(ip6s_badoptions);
				icmp6_error(m, ICMP6_PARAM_PROB,
				    ICMP6_PARAMPROB_HEADER,
				    erroff + opt + 2 - opthead);
				return (-1);
			}
#endif

			/*
			 * jumbo payload length must be larger than 65535.
			 */
			if (jumboplen <= IPV6_MAXPACKET) {
				IP6STAT_INC(ip6s_badoptions);
				icmp6_error(m, ICMP6_PARAM_PROB,
				    ICMP6_PARAMPROB_HEADER,
				    erroff + opt + 2 - opthead);
				return (-1);
			}
			*plenp = jumboplen;

			break;
		default:		/* unknown option */
			if (hbhlen < IP6OPT_MINLEN) {
				IP6STAT_INC(ip6s_toosmall);
				goto bad;
			}
			optlen = ip6_unknown_opt(opt, m,
			    erroff + opt - opthead);
			if (optlen == -1)
				return (-1);
			optlen += 2;
			break;
		}
	}

	return (0);

  bad:
	m_freem(m);
	return (-1);
}

/*
 * Unknown option processing.
 * The third argument `off' is the offset from the IPv6 header to the option,
 * which is necessary if the IPv6 header the and option header and IPv6 header
 * is not contiguous in order to return an ICMPv6 error.
 */
int
ip6_unknown_opt(u_int8_t *optp, struct mbuf *m, int off)
{
	struct ip6_hdr *ip6;

	switch (IP6OPT_TYPE(*optp)) {
	case IP6OPT_TYPE_SKIP: /* ignore the option */
		return ((int)*(optp + 1));
	case IP6OPT_TYPE_DISCARD:	/* silently discard */
		m_freem(m);
		return (-1);
	case IP6OPT_TYPE_FORCEICMP: /* send ICMP even if multicasted */
		IP6STAT_INC(ip6s_badoptions);
		icmp6_error(m, ICMP6_PARAM_PROB, ICMP6_PARAMPROB_OPTION, off);
		return (-1);
	case IP6OPT_TYPE_ICMP: /* send ICMP if not multicasted */
		IP6STAT_INC(ip6s_badoptions);
		ip6 = mtod(m, struct ip6_hdr *);
		if (IN6_IS_ADDR_MULTICAST(&ip6->ip6_dst) ||
		    (m->m_flags & (M_BCAST|M_MCAST)))
			m_freem(m);
		else
			icmp6_error(m, ICMP6_PARAM_PROB,
				    ICMP6_PARAMPROB_OPTION, off);
		return (-1);
	}

	m_freem(m);		/* XXX: NOTREACHED */
	return (-1);
}

/*
 * Create the "control" list for this pcb.
 * These functions will not modify mbuf chain at all.
 *
 * With KAME mbuf chain restriction:
 * The routine will be called from upper layer handlers like tcp6_input().
 * Thus the routine assumes that the caller (tcp6_input) have already
 * called IP6_EXTHDR_CHECK() and all the extension headers are located in the
 * very first mbuf on the mbuf chain.
 *
 * ip6_savecontrol_v4 will handle those options that are possible to be
 * set on a v4-mapped socket.
 * ip6_savecontrol will directly call ip6_savecontrol_v4 to handle those
 * options and handle the v6-only ones itself.
 */
struct mbuf **
ip6_savecontrol_v4(struct inpcb *inp, struct mbuf *m, struct mbuf **mp,
    int *v4only)
{
	struct ip6_hdr *ip6 = mtod(m, struct ip6_hdr *);

#ifdef SO_TIMESTAMP
	if ((inp->inp_socket->so_options & SO_TIMESTAMP) != 0) {
		union {
			struct timeval tv;
			struct bintime bt;
			struct timespec ts;
		} t;
		struct bintime boottimebin, bt1;
		struct timespec ts1;
		bool stamped;

		stamped = false;
		switch (inp->inp_socket->so_ts_clock) {
		case SO_TS_REALTIME_MICRO:
			if ((m->m_flags & (M_PKTHDR | M_TSTMP)) == (M_PKTHDR |
			    M_TSTMP)) {
				mbuf_tstmp2timespec(m, &ts1);
				timespec2bintime(&ts1, &bt1);
				getboottimebin(&boottimebin);
				bintime_add(&bt1, &boottimebin);
				bintime2timeval(&bt1, &t.tv);
			} else {
				microtime(&t.tv);
			}
			*mp = sbcreatecontrol((caddr_t) &t.tv, sizeof(t.tv),
			    SCM_TIMESTAMP, SOL_SOCKET);
			if (*mp != NULL) {
				mp = &(*mp)->m_next;
				stamped = true;
			}
			break;

		case SO_TS_BINTIME:
			if ((m->m_flags & (M_PKTHDR | M_TSTMP)) == (M_PKTHDR |
			    M_TSTMP)) {
				mbuf_tstmp2timespec(m, &ts1);
				timespec2bintime(&ts1, &t.bt);
				getboottimebin(&boottimebin);
				bintime_add(&t.bt, &boottimebin);
			} else {
				bintime(&t.bt);
			}
			*mp = sbcreatecontrol((caddr_t)&t.bt, sizeof(t.bt),
			    SCM_BINTIME, SOL_SOCKET);
			if (*mp != NULL) {
				mp = &(*mp)->m_next;
				stamped = true;
			}
			break;

		case SO_TS_REALTIME:
			if ((m->m_flags & (M_PKTHDR | M_TSTMP)) == (M_PKTHDR |
			    M_TSTMP)) {
				mbuf_tstmp2timespec(m, &t.ts);
				getboottimebin(&boottimebin);
				bintime2timespec(&boottimebin, &ts1);
				timespecadd(&t.ts, &ts1, &t.ts);
			} else {
				nanotime(&t.ts);
			}
			*mp = sbcreatecontrol((caddr_t)&t.ts, sizeof(t.ts),
			    SCM_REALTIME, SOL_SOCKET);
			if (*mp != NULL) {
				mp = &(*mp)->m_next;
				stamped = true;
			}
			break;

		case SO_TS_MONOTONIC:
			if ((m->m_flags & (M_PKTHDR | M_TSTMP)) == (M_PKTHDR |
			    M_TSTMP))
				mbuf_tstmp2timespec(m, &t.ts);
			else
				nanouptime(&t.ts);
			*mp = sbcreatecontrol((caddr_t)&t.ts, sizeof(t.ts),
			    SCM_MONOTONIC, SOL_SOCKET);
			if (*mp != NULL) {
				mp = &(*mp)->m_next;
				stamped = true;
			}
			break;

		default:
			panic("unknown (corrupted) so_ts_clock");
		}
		if (stamped && (m->m_flags & (M_PKTHDR | M_TSTMP)) ==
		    (M_PKTHDR | M_TSTMP)) {
			struct sock_timestamp_info sti;

			bzero(&sti, sizeof(sti));
			sti.st_info_flags = ST_INFO_HW;
			if ((m->m_flags & M_TSTMP_HPREC) != 0)
				sti.st_info_flags |= ST_INFO_HW_HPREC;
			*mp = sbcreatecontrol((caddr_t)&sti, sizeof(sti),
			    SCM_TIME_INFO, SOL_SOCKET);
			if (*mp != NULL)
				mp = &(*mp)->m_next;
		}
	}
#endif

#define IS2292(inp, x, y)	(((inp)->inp_flags & IN6P_RFC2292) ? (x) : (y))
	/* RFC 2292 sec. 5 */
	if ((inp->inp_flags & IN6P_PKTINFO) != 0) {
		struct in6_pktinfo pi6;

		if ((ip6->ip6_vfc & IPV6_VERSION_MASK) != IPV6_VERSION) {
#ifdef INET
			struct ip *ip;

			ip = mtod(m, struct ip *);
			pi6.ipi6_addr.s6_addr32[0] = 0;
			pi6.ipi6_addr.s6_addr32[1] = 0;
			pi6.ipi6_addr.s6_addr32[2] = IPV6_ADDR_INT32_SMP;
			pi6.ipi6_addr.s6_addr32[3] = ip->ip_dst.s_addr;
#else
			/* We won't hit this code */
			bzero(&pi6.ipi6_addr, sizeof(struct in6_addr));
#endif
		} else {	
			bcopy(&ip6->ip6_dst, &pi6.ipi6_addr, sizeof(struct in6_addr));
			in6_clearscope(&pi6.ipi6_addr);	/* XXX */
		}
		pi6.ipi6_ifindex =
		    (m && m->m_pkthdr.rcvif) ? m->m_pkthdr.rcvif->if_index : 0;

		*mp = sbcreatecontrol((caddr_t) &pi6,
		    sizeof(struct in6_pktinfo),
		    IS2292(inp, IPV6_2292PKTINFO, IPV6_PKTINFO), IPPROTO_IPV6);
		if (*mp)
			mp = &(*mp)->m_next;
	}

	if ((inp->inp_flags & IN6P_HOPLIMIT) != 0) {
		int hlim;

		if ((ip6->ip6_vfc & IPV6_VERSION_MASK) != IPV6_VERSION) {
#ifdef INET
			struct ip *ip;

			ip = mtod(m, struct ip *);
			hlim = ip->ip_ttl;
#else
			/* We won't hit this code */
			hlim = 0;
#endif
		} else {
			hlim = ip6->ip6_hlim & 0xff;
		}
		*mp = sbcreatecontrol((caddr_t) &hlim, sizeof(int),
		    IS2292(inp, IPV6_2292HOPLIMIT, IPV6_HOPLIMIT),
		    IPPROTO_IPV6);
		if (*mp)
			mp = &(*mp)->m_next;
	}

	if ((inp->inp_flags & IN6P_TCLASS) != 0) {
		int tclass;

		if ((ip6->ip6_vfc & IPV6_VERSION_MASK) != IPV6_VERSION) {
#ifdef INET
			struct ip *ip;

			ip = mtod(m, struct ip *);
			tclass = ip->ip_tos;
#else
			/* We won't hit this code */
			tclass = 0;
#endif
		} else {
			u_int32_t flowinfo;

			flowinfo = (u_int32_t)ntohl(ip6->ip6_flow & IPV6_FLOWINFO_MASK);
			flowinfo >>= 20;
			tclass = flowinfo & 0xff;
		}
		*mp = sbcreatecontrol((caddr_t) &tclass, sizeof(int),
		    IPV6_TCLASS, IPPROTO_IPV6);
		if (*mp)
			mp = &(*mp)->m_next;
	}

	if (v4only != NULL) {
		if ((ip6->ip6_vfc & IPV6_VERSION_MASK) != IPV6_VERSION) {
			*v4only = 1;
		} else {
			*v4only = 0;
		}
	}

	return (mp);
}

void
ip6_savecontrol(struct inpcb *in6p, struct mbuf *m, struct mbuf **mp)
{
	struct ip6_hdr *ip6 = mtod(m, struct ip6_hdr *);
	int v4only = 0;

	mp = ip6_savecontrol_v4(in6p, m, mp, &v4only);
	if (v4only)
		return;

	/*
	 * IPV6_HOPOPTS socket option.  Recall that we required super-user
	 * privilege for the option (see ip6_ctloutput), but it might be too
	 * strict, since there might be some hop-by-hop options which can be
	 * returned to normal user.
	 * See also RFC 2292 section 6 (or RFC 3542 section 8).
	 */
	if ((in6p->inp_flags & IN6P_HOPOPTS) != 0) {
		/*
		 * Check if a hop-by-hop options header is contatined in the
		 * received packet, and if so, store the options as ancillary
		 * data. Note that a hop-by-hop options header must be
		 * just after the IPv6 header, which is assured through the
		 * IPv6 input processing.
		 */
		if (ip6->ip6_nxt == IPPROTO_HOPOPTS) {
			struct ip6_hbh *hbh;
			int hbhlen = 0;
#ifdef PULLDOWN_TEST
			struct mbuf *ext;
#endif

#ifndef PULLDOWN_TEST
			hbh = (struct ip6_hbh *)(ip6 + 1);
			hbhlen = (hbh->ip6h_len + 1) << 3;
#else
			ext = ip6_pullexthdr(m, sizeof(struct ip6_hdr),
			    ip6->ip6_nxt);
			if (ext == NULL) {
				IP6STAT_INC(ip6s_tooshort);
				return;
			}
			hbh = mtod(ext, struct ip6_hbh *);
			hbhlen = (hbh->ip6h_len + 1) << 3;
			if (hbhlen != ext->m_len) {
				m_freem(ext);
				IP6STAT_INC(ip6s_tooshort);
				return;
			}
#endif

			/*
			 * XXX: We copy the whole header even if a
			 * jumbo payload option is included, the option which
			 * is to be removed before returning according to
			 * RFC2292.
			 * Note: this constraint is removed in RFC3542
			 */
			*mp = sbcreatecontrol((caddr_t)hbh, hbhlen,
			    IS2292(in6p, IPV6_2292HOPOPTS, IPV6_HOPOPTS),
			    IPPROTO_IPV6);
			if (*mp)
				mp = &(*mp)->m_next;
#ifdef PULLDOWN_TEST
			m_freem(ext);
#endif
		}
	}

	if ((in6p->inp_flags & (IN6P_RTHDR | IN6P_DSTOPTS)) != 0) {
		int nxt = ip6->ip6_nxt, off = sizeof(struct ip6_hdr);

		/*
		 * Search for destination options headers or routing
		 * header(s) through the header chain, and stores each
		 * header as ancillary data.
		 * Note that the order of the headers remains in
		 * the chain of ancillary data.
		 */
		while (1) {	/* is explicit loop prevention necessary? */
			struct ip6_ext *ip6e = NULL;
			int elen;
#ifdef PULLDOWN_TEST
			struct mbuf *ext = NULL;
#endif

			/*
			 * if it is not an extension header, don't try to
			 * pull it from the chain.
			 */
			switch (nxt) {
			case IPPROTO_DSTOPTS:
			case IPPROTO_ROUTING:
			case IPPROTO_HOPOPTS:
			case IPPROTO_AH: /* is it possible? */
				break;
			default:
				goto loopend;
			}

#ifndef PULLDOWN_TEST
			if (off + sizeof(*ip6e) > m->m_len)
				goto loopend;
			ip6e = (struct ip6_ext *)(mtod(m, caddr_t) + off);
			if (nxt == IPPROTO_AH)
				elen = (ip6e->ip6e_len + 2) << 2;
			else
				elen = (ip6e->ip6e_len + 1) << 3;
			if (off + elen > m->m_len)
				goto loopend;
#else
			ext = ip6_pullexthdr(m, off, nxt);
			if (ext == NULL) {
				IP6STAT_INC(ip6s_tooshort);
				return;
			}
			ip6e = mtod(ext, struct ip6_ext *);
			if (nxt == IPPROTO_AH)
				elen = (ip6e->ip6e_len + 2) << 2;
			else
				elen = (ip6e->ip6e_len + 1) << 3;
			if (elen != ext->m_len) {
				m_freem(ext);
				IP6STAT_INC(ip6s_tooshort);
				return;
			}
#endif

			switch (nxt) {
			case IPPROTO_DSTOPTS:
				if (!(in6p->inp_flags & IN6P_DSTOPTS))
					break;

				*mp = sbcreatecontrol((caddr_t)ip6e, elen,
				    IS2292(in6p,
					IPV6_2292DSTOPTS, IPV6_DSTOPTS),
				    IPPROTO_IPV6);
				if (*mp)
					mp = &(*mp)->m_next;
				break;
			case IPPROTO_ROUTING:
				if (!(in6p->inp_flags & IN6P_RTHDR))
					break;

				*mp = sbcreatecontrol((caddr_t)ip6e, elen,
				    IS2292(in6p, IPV6_2292RTHDR, IPV6_RTHDR),
				    IPPROTO_IPV6);
				if (*mp)
					mp = &(*mp)->m_next;
				break;
			case IPPROTO_HOPOPTS:
			case IPPROTO_AH: /* is it possible? */
				break;

			default:
				/*
				 * other cases have been filtered in the above.
				 * none will visit this case.  here we supply
				 * the code just in case (nxt overwritten or
				 * other cases).
				 */
#ifdef PULLDOWN_TEST
				m_freem(ext);
#endif
				goto loopend;

			}

			/* proceed with the next header. */
			off += elen;
			nxt = ip6e->ip6e_nxt;
			ip6e = NULL;
#ifdef PULLDOWN_TEST
			m_freem(ext);
			ext = NULL;
#endif
		}
	  loopend:
		;
	}

	if (in6p->inp_flags2 & INP_RECVFLOWID) {
		uint32_t flowid, flow_type;

		flowid = m->m_pkthdr.flowid;
		flow_type = M_HASHTYPE_GET(m);

		/*
		 * XXX should handle the failure of one or the
		 * other - don't populate both?
		 */
		*mp = sbcreatecontrol((caddr_t) &flowid,
		    sizeof(uint32_t), IPV6_FLOWID, IPPROTO_IPV6);
		if (*mp)
			mp = &(*mp)->m_next;
		*mp = sbcreatecontrol((caddr_t) &flow_type,
		    sizeof(uint32_t), IPV6_FLOWTYPE, IPPROTO_IPV6);
		if (*mp)
			mp = &(*mp)->m_next;
	}

#ifdef	RSS
	if (in6p->inp_flags2 & INP_RECVRSSBUCKETID) {
		uint32_t flowid, flow_type;
		uint32_t rss_bucketid;

		flowid = m->m_pkthdr.flowid;
		flow_type = M_HASHTYPE_GET(m);

		if (rss_hash2bucket(flowid, flow_type, &rss_bucketid) == 0) {
			*mp = sbcreatecontrol((caddr_t) &rss_bucketid,
			   sizeof(uint32_t), IPV6_RSSBUCKETID, IPPROTO_IPV6);
			if (*mp)
				mp = &(*mp)->m_next;
		}
	}
#endif

}
#undef IS2292

void
ip6_notify_pmtu(struct inpcb *inp, struct sockaddr_in6 *dst, u_int32_t mtu)
{
	struct socket *so;
	struct mbuf *m_mtu;
	struct ip6_mtuinfo mtuctl;

	KASSERT(inp != NULL, ("%s: inp == NULL", __func__));
	/*
	 * Notify the error by sending IPV6_PATHMTU ancillary data if
	 * application wanted to know the MTU value.
	 * NOTE: we notify disconnected sockets, because some udp
	 * applications keep sending sockets disconnected.
	 * NOTE: our implementation doesn't notify connected sockets that has
	 * foreign address that is different than given destination addresses
	 * (this is permitted by RFC 3542).
	 */
	if ((inp->inp_flags & IN6P_MTU) == 0 || (
	    !IN6_IS_ADDR_UNSPECIFIED(&inp->in6p_faddr) &&
	    !IN6_ARE_ADDR_EQUAL(&inp->in6p_faddr, &dst->sin6_addr)))
		return;

	mtuctl.ip6m_mtu = mtu;
	mtuctl.ip6m_addr = *dst;
	if (sa6_recoverscope(&mtuctl.ip6m_addr))
		return;

	if ((m_mtu = sbcreatecontrol((caddr_t)&mtuctl, sizeof(mtuctl),
	    IPV6_PATHMTU, IPPROTO_IPV6)) == NULL)
		return;

	so =  inp->inp_socket;
	if (sbappendaddr(&so->so_rcv, (struct sockaddr *)dst, NULL, m_mtu)
	    == 0) {
		m_freem(m_mtu);
		/* XXX: should count statistics */
	} else
		sorwakeup(so);
}

#ifdef PULLDOWN_TEST
/*
 * pull single extension header from mbuf chain.  returns single mbuf that
 * contains the result, or NULL on error.
 */
static struct mbuf *
ip6_pullexthdr(struct mbuf *m, size_t off, int nxt)
{
	struct ip6_ext ip6e;
	size_t elen;
	struct mbuf *n;

#ifdef DIAGNOSTIC
	switch (nxt) {
	case IPPROTO_DSTOPTS:
	case IPPROTO_ROUTING:
	case IPPROTO_HOPOPTS:
	case IPPROTO_AH: /* is it possible? */
		break;
	default:
		printf("ip6_pullexthdr: invalid nxt=%d\n", nxt);
	}
#endif

	m_copydata(m, off, sizeof(ip6e), (caddr_t)&ip6e);
	if (nxt == IPPROTO_AH)
		elen = (ip6e.ip6e_len + 2) << 2;
	else
		elen = (ip6e.ip6e_len + 1) << 3;

	if (elen > MLEN)
		n = m_getcl(M_NOWAIT, MT_DATA, 0);
	else
		n = m_get(M_NOWAIT, MT_DATA);
	if (n == NULL)
		return NULL;

	m_copydata(m, off, elen, mtod(n, caddr_t));
	n->m_len = elen;
	return n;
}
#endif

/*
 * Get pointer to the previous header followed by the header
 * currently processed.
 */
int
ip6_get_prevhdr(const struct mbuf *m, int off)
{
	struct ip6_ext ip6e;
	struct ip6_hdr *ip6;
	int len, nlen, nxt;

	if (off == sizeof(struct ip6_hdr))
		return (offsetof(struct ip6_hdr, ip6_nxt));
	if (off < sizeof(struct ip6_hdr))
		panic("%s: off < sizeof(struct ip6_hdr)", __func__);

	ip6 = mtod(m, struct ip6_hdr *);
	nxt = ip6->ip6_nxt;
	len = sizeof(struct ip6_hdr);
	nlen = 0;
	while (len < off) {
		m_copydata(m, len, sizeof(ip6e), (caddr_t)&ip6e);
		switch (nxt) {
		case IPPROTO_FRAGMENT:
			nlen = sizeof(struct ip6_frag);
			break;
		case IPPROTO_AH:
			nlen = (ip6e.ip6e_len + 2) << 2;
			break;
		default:
			nlen = (ip6e.ip6e_len + 1) << 3;
		}
		len += nlen;
		nxt = ip6e.ip6e_nxt;
	}
	return (len - nlen);
}

/*
 * get next header offset.  m will be retained.
 */
int
ip6_nexthdr(const struct mbuf *m, int off, int proto, int *nxtp)
{
	struct ip6_hdr ip6;
	struct ip6_ext ip6e;
	struct ip6_frag fh;

	/* just in case */
	if (m == NULL)
		panic("ip6_nexthdr: m == NULL");
	if ((m->m_flags & M_PKTHDR) == 0 || m->m_pkthdr.len < off)
		return -1;

	switch (proto) {
	case IPPROTO_IPV6:
		if (m->m_pkthdr.len < off + sizeof(ip6))
			return -1;
		m_copydata(m, off, sizeof(ip6), (caddr_t)&ip6);
		if (nxtp)
			*nxtp = ip6.ip6_nxt;
		off += sizeof(ip6);
		return off;

	case IPPROTO_FRAGMENT:
		/*
		 * terminate parsing if it is not the first fragment,
		 * it does not make sense to parse through it.
		 */
		if (m->m_pkthdr.len < off + sizeof(fh))
			return -1;
		m_copydata(m, off, sizeof(fh), (caddr_t)&fh);
		/* IP6F_OFF_MASK = 0xfff8(BigEndian), 0xf8ff(LittleEndian) */
		if (fh.ip6f_offlg & IP6F_OFF_MASK)
			return -1;
		if (nxtp)
			*nxtp = fh.ip6f_nxt;
		off += sizeof(struct ip6_frag);
		return off;

	case IPPROTO_AH:
		if (m->m_pkthdr.len < off + sizeof(ip6e))
			return -1;
		m_copydata(m, off, sizeof(ip6e), (caddr_t)&ip6e);
		if (nxtp)
			*nxtp = ip6e.ip6e_nxt;
		off += (ip6e.ip6e_len + 2) << 2;
		return off;

	case IPPROTO_HOPOPTS:
	case IPPROTO_ROUTING:
	case IPPROTO_DSTOPTS:
		if (m->m_pkthdr.len < off + sizeof(ip6e))
			return -1;
		m_copydata(m, off, sizeof(ip6e), (caddr_t)&ip6e);
		if (nxtp)
			*nxtp = ip6e.ip6e_nxt;
		off += (ip6e.ip6e_len + 1) << 3;
		return off;

	case IPPROTO_NONE:
	case IPPROTO_ESP:
	case IPPROTO_IPCOMP:
		/* give up */
		return -1;

	default:
		return -1;
	}

	/* NOTREACHED */
}

/*
 * get offset for the last header in the chain.  m will be kept untainted.
 */
int
ip6_lasthdr(const struct mbuf *m, int off, int proto, int *nxtp)
{
	int newoff;
	int nxt;

	if (!nxtp) {
		nxt = -1;
		nxtp = &nxt;
	}
	while (1) {
		newoff = ip6_nexthdr(m, off, proto, nxtp);
		if (newoff < 0)
			return off;
		else if (newoff < off)
			return -1;	/* invalid */
		else if (newoff == off)
			return newoff;

		off = newoff;
		proto = *nxtp;
	}
}

/*
 * System control for IP6
 */

u_char	inet6ctlerrmap[PRC_NCMDS] = {
	0,		0,		0,		0,
	0,		EMSGSIZE,	EHOSTDOWN,	EHOSTUNREACH,
	EHOSTUNREACH,	EHOSTUNREACH,	ECONNREFUSED,	ECONNREFUSED,
	EMSGSIZE,	EHOSTUNREACH,	0,		0,
	0,		0,		EHOSTUNREACH,	0,
	ENOPROTOOPT,	ECONNREFUSED
};