summaryrefslogtreecommitdiff
path: root/sys/netinet6/nd6.c
blob: 6faced72f2d9962811319d80b554af6cd8b6f6b9 (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
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
/*	$OpenBSD: nd6.c,v 1.190 2016/08/22 16:01:52 mpi Exp $	*/
/*	$KAME: nd6.c,v 1.280 2002/06/08 19:52:07 itojun Exp $	*/

/*
 * 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.
 */

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/timeout.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/socket.h>
#include <sys/sockio.h>
#include <sys/time.h>
#include <sys/kernel.h>
#include <sys/pool.h>
#include <sys/protosw.h>
#include <sys/errno.h>
#include <sys/ioctl.h>
#include <sys/syslog.h>
#include <sys/queue.h>
#include <sys/task.h>

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

#include <netinet/in.h>
#include <netinet/if_ether.h>
#include <netinet/ip_ipsp.h>

#include <netinet6/in6_var.h>
#include <netinet/ip6.h>
#include <netinet6/ip6_var.h>
#include <netinet6/nd6.h>
#include <netinet/icmp6.h>

#define ND6_SLOWTIMER_INTERVAL (60 * 60) /* 1 hour */
#define ND6_RECALC_REACHTM_INTERVAL (60 * 120) /* 2 hours */

/* timer values */
int	nd6_prune	= 1;	/* walk list every 1 seconds */
int	nd6_delay	= 5;	/* delay first probe time 5 second */
int	nd6_umaxtries	= 3;	/* maximum unicast query */
int	nd6_mmaxtries	= 3;	/* maximum multicast query */
int	nd6_gctimer	= (60 * 60 * 24); /* 1 day: garbage collection timer */

/* preventing too many loops in ND option parsing */
int nd6_maxndopt = 10;	/* max # of ND options allowed */

int nd6_maxnudhint = 0;	/* max # of subsequent upper layer hints */

#ifdef ND6_DEBUG
int nd6_debug = 1;
#else
int nd6_debug = 0;
#endif

TAILQ_HEAD(llinfo_nd6_head, llinfo_nd6) nd6_list;
struct	pool nd6_pool;		/* pool for llinfo_nd6 structures */
int	nd6_inuse, nd6_allocated;

struct nd_drhead nd_defrouter;
struct nd_prhead nd_prefix = { 0 };

int nd6_recalc_reachtm_interval = ND6_RECALC_REACHTM_INTERVAL;

void nd6_slowtimo(void *);
void nd6_invalidate(struct rtentry *);
struct llinfo_nd6 *nd6_free(struct rtentry *, int);
void nd6_llinfo_timer(void *);

struct timeout nd6_slowtimo_ch;
struct timeout nd6_timer_ch;
struct task nd6_timer_task;
void nd6_timer_work(void *);

int fill_drlist(void *, size_t *, size_t);
int fill_prlist(void *, size_t *, size_t);

void
nd6_init(void)
{
	static int nd6_init_done = 0;

	if (nd6_init_done) {
		log(LOG_NOTICE, "%s called more than once\n", __func__);
		return;
	}

	TAILQ_INIT(&nd6_list);
	pool_init(&nd6_pool, sizeof(struct llinfo_nd6), 0, 0, 0, "nd6", NULL);

	/* initialization of the default router list */
	TAILQ_INIT(&nd_defrouter);

	task_set(&nd6_timer_task, nd6_timer_work, NULL);

	nd6_init_done = 1;

	/* start timer */
	timeout_set(&nd6_slowtimo_ch, nd6_slowtimo, NULL);
	timeout_add_sec(&nd6_slowtimo_ch, ND6_SLOWTIMER_INTERVAL);

	nd6_rs_init();
}

struct nd_ifinfo *
nd6_ifattach(struct ifnet *ifp)
{
	struct nd_ifinfo *nd;

	nd = malloc(sizeof(*nd), M_IP6NDP, M_WAITOK | M_ZERO);

	nd->initialized = 1;

	nd->basereachable = REACHABLE_TIME;
	nd->reachable = ND_COMPUTE_RTIME(nd->basereachable);
	nd->retrans = RETRANS_TIMER;
	/* per-interface IFXF_AUTOCONF6 needs to be set too to accept RAs */
	nd->flags = (ND6_IFF_PERFORMNUD | ND6_IFF_ACCEPT_RTADV);

	return nd;
}

void
nd6_ifdetach(struct nd_ifinfo *nd)
{

	free(nd, M_IP6NDP, sizeof(*nd));
}

void
nd6_option_init(void *opt, int icmp6len, union nd_opts *ndopts)
{
	bzero(ndopts, sizeof(*ndopts));
	ndopts->nd_opts_search = (struct nd_opt_hdr *)opt;
	ndopts->nd_opts_last
		= (struct nd_opt_hdr *)(((u_char *)opt) + icmp6len);

	if (icmp6len == 0) {
		ndopts->nd_opts_done = 1;
		ndopts->nd_opts_search = NULL;
	}
}

/*
 * Take one ND option.
 */
struct nd_opt_hdr *
nd6_option(union nd_opts *ndopts)
{
	struct nd_opt_hdr *nd_opt;
	int olen;

	if (!ndopts)
		panic("ndopts == NULL in nd6_option");
	if (!ndopts->nd_opts_last)
		panic("uninitialized ndopts in nd6_option");
	if (!ndopts->nd_opts_search)
		return NULL;
	if (ndopts->nd_opts_done)
		return NULL;

	nd_opt = ndopts->nd_opts_search;

	/* make sure nd_opt_len is inside the buffer */
	if ((caddr_t)&nd_opt->nd_opt_len >= (caddr_t)ndopts->nd_opts_last) {
		bzero(ndopts, sizeof(*ndopts));
		return NULL;
	}

	olen = nd_opt->nd_opt_len << 3;
	if (olen == 0) {
		/*
		 * Message validation requires that all included
		 * options have a length that is greater than zero.
		 */
		bzero(ndopts, sizeof(*ndopts));
		return NULL;
	}

	ndopts->nd_opts_search = (struct nd_opt_hdr *)((caddr_t)nd_opt + olen);
	if (ndopts->nd_opts_search > ndopts->nd_opts_last) {
		/* option overruns the end of buffer, invalid */
		bzero(ndopts, sizeof(*ndopts));
		return NULL;
	} else if (ndopts->nd_opts_search == ndopts->nd_opts_last) {
		/* reached the end of options chain */
		ndopts->nd_opts_done = 1;
		ndopts->nd_opts_search = NULL;
	}
	return nd_opt;
}

/*
 * Parse multiple ND options.
 * This function is much easier to use, for ND routines that do not need
 * multiple options of the same type.
 */
int
nd6_options(union nd_opts *ndopts)
{
	struct nd_opt_hdr *nd_opt;
	int i = 0;

	if (!ndopts)
		panic("ndopts == NULL in nd6_options");
	if (!ndopts->nd_opts_last)
		panic("uninitialized ndopts in nd6_options");
	if (!ndopts->nd_opts_search)
		return 0;

	while (1) {
		nd_opt = nd6_option(ndopts);
		if (!nd_opt && !ndopts->nd_opts_last) {
			/*
			 * Message validation requires that all included
			 * options have a length that is greater than zero.
			 */
			icmp6stat.icp6s_nd_badopt++;
			bzero(ndopts, sizeof(*ndopts));
			return -1;
		}

		if (!nd_opt)
			goto skip1;

		switch (nd_opt->nd_opt_type) {
		case ND_OPT_SOURCE_LINKADDR:
		case ND_OPT_TARGET_LINKADDR:
		case ND_OPT_MTU:
		case ND_OPT_REDIRECTED_HEADER:
			if (ndopts->nd_opt_array[nd_opt->nd_opt_type]) {
				nd6log((LOG_INFO,
				    "duplicated ND6 option found (type=%d)\n",
				    nd_opt->nd_opt_type));
				/* XXX bark? */
			} else {
				ndopts->nd_opt_array[nd_opt->nd_opt_type]
					= nd_opt;
			}
			break;
		case ND_OPT_PREFIX_INFORMATION:
			if (ndopts->nd_opt_array[nd_opt->nd_opt_type] == 0) {
				ndopts->nd_opt_array[nd_opt->nd_opt_type]
					= nd_opt;
			}
			ndopts->nd_opts_pi_end =
				(struct nd_opt_prefix_info *)nd_opt;
			break;
		default:
			/*
			 * Unknown options must be silently ignored,
			 * to accommodate future extension to the protocol.
			 */
			nd6log((LOG_DEBUG,
			    "nd6_options: unsupported option %d - "
			    "option ignored\n", nd_opt->nd_opt_type));
		}

skip1:
		i++;
		if (i > nd6_maxndopt) {
			icmp6stat.icp6s_nd_toomanyopt++;
			nd6log((LOG_INFO, "too many loop in nd opt\n"));
			break;
		}

		if (ndopts->nd_opts_done)
			break;
	}

	return 0;
}

/*
 * ND6 timer routine to handle ND6 entries
 */
void
nd6_llinfo_settimer(struct llinfo_nd6 *ln, int secs)
{
	int s;

	s = splsoftnet();

	if (secs < 0) {
		ln->ln_rt->rt_expire = 0;
		timeout_del(&ln->ln_timer_ch);
	} else {
		ln->ln_rt->rt_expire = time_uptime + secs;
		timeout_add_sec(&ln->ln_timer_ch, secs);
	}

	splx(s);
}

void
nd6_llinfo_timer(void *arg)
{
	int s;
	struct llinfo_nd6 *ln;
	struct rtentry *rt;
	struct sockaddr_in6 *dst;
	struct ifnet *ifp;
	struct nd_ifinfo *ndi = NULL;

	s = splsoftnet();

	ln = (struct llinfo_nd6 *)arg;

	if ((rt = ln->ln_rt) == NULL)
		panic("ln->ln_rt == NULL");
	if ((ifp = if_get(rt->rt_ifidx)) == NULL) {
		splx(s);
		return;
	}
	ndi = ND_IFINFO(ifp);
	dst = satosin6(rt_key(rt));

	/* sanity check */
	if (rt->rt_llinfo != NULL && (struct llinfo_nd6 *)rt->rt_llinfo != ln)
		panic("rt_llinfo(%p) is not equal to ln(%p)",
		      rt->rt_llinfo, ln);
	if (!dst)
		panic("dst=0 in nd6_timer(ln=%p)", ln);

	switch (ln->ln_state) {
	case ND6_LLINFO_INCOMPLETE:
		if (ln->ln_asked < nd6_mmaxtries) {
			ln->ln_asked++;
			nd6_llinfo_settimer(ln, ndi->retrans / 1000);
			nd6_ns_output(ifp, NULL, &dst->sin6_addr, ln, 0);
		} else {
			struct mbuf *m = ln->ln_hold;
			if (m) {
				ln->ln_hold = NULL;
				/*
				 * Fake rcvif to make the ICMP error
				 * more helpful in diagnosing for the
				 * receiver.
				 * XXX: should we consider
				 * older rcvif?
				 */
				m->m_pkthdr.ph_ifidx = rt->rt_ifidx;

				icmp6_error(m, ICMP6_DST_UNREACH,
				    ICMP6_DST_UNREACH_ADDR, 0);
				if (ln->ln_hold == m) {
					/* m is back in ln_hold. Discard. */
					m_freem(ln->ln_hold);
					ln->ln_hold = NULL;
				}
			}
			(void)nd6_free(rt, 0);
			ln = NULL;
		}
		break;
	case ND6_LLINFO_REACHABLE:
		if (!ND6_LLINFO_PERMANENT(ln)) {
			ln->ln_state = ND6_LLINFO_STALE;
			nd6_llinfo_settimer(ln, nd6_gctimer);
		}
		break;

	case ND6_LLINFO_STALE:
	case ND6_LLINFO_PURGE:
		/* Garbage Collection(RFC 2461 5.3) */
		if (!ND6_LLINFO_PERMANENT(ln)) {
			(void)nd6_free(rt, 1);
			ln = NULL;
		}
		break;

	case ND6_LLINFO_DELAY:
		if (ndi && (ndi->flags & ND6_IFF_PERFORMNUD) != 0) {
			/* We need NUD */
			ln->ln_asked = 1;
			ln->ln_state = ND6_LLINFO_PROBE;
			nd6_llinfo_settimer(ln, ndi->retrans / 1000);
			nd6_ns_output(ifp, &dst->sin6_addr,
			    &dst->sin6_addr, ln, 0);
		} else {
			ln->ln_state = ND6_LLINFO_STALE; /* XXX */
			nd6_llinfo_settimer(ln, nd6_gctimer);
		}
		break;
	case ND6_LLINFO_PROBE:
		if (ln->ln_asked < nd6_umaxtries) {
			ln->ln_asked++;
			nd6_llinfo_settimer(ln, ndi->retrans / 1000);
			nd6_ns_output(ifp, &dst->sin6_addr,
			    &dst->sin6_addr, ln, 0);
		} else {
			(void)nd6_free(rt, 0);
			ln = NULL;
		}
		break;
	}

	if_put(ifp);
	splx(s);
}

/*
 * ND6 timer routine to expire default route list and prefix list
 */
void
nd6_timer_work(void *null)
{
	int s;
	struct nd_defrouter *dr, *ndr;
	struct nd_prefix *pr, *npr;
	struct in6_ifaddr *ia6, *nia6;

	s = splsoftnet();
	timeout_set(&nd6_timer_ch, nd6_timer, NULL);
	timeout_add_sec(&nd6_timer_ch, nd6_prune);

	/* expire default router list */
	TAILQ_FOREACH_SAFE(dr, &nd_defrouter, dr_entry, ndr)
		if (dr->expire && dr->expire < time_second)
			defrtrlist_del(dr);

	/*
	 * expire interface addresses.
	 * in the past the loop was inside prefix expiry processing.
	 * However, from a stricter spec-conformance standpoint, we should
	 * rather separate address lifetimes and prefix lifetimes.
	 */
	TAILQ_FOREACH_SAFE(ia6, &in6_ifaddr, ia_list, nia6) {
		/* check address lifetime */
		if (IFA6_IS_INVALID(ia6)) {
			in6_purgeaddr(&ia6->ia_ifa);
		} else if (IFA6_IS_DEPRECATED(ia6)) {
			ia6->ia6_flags |= IN6_IFF_DEPRECATED;
		} else {
			/*
			 * A new RA might have made a deprecated address
			 * preferred.
			 */
			ia6->ia6_flags &= ~IN6_IFF_DEPRECATED;
		}
	}

	/* expire prefix list */
	LIST_FOREACH_SAFE(pr, &nd_prefix, ndpr_entry, npr) {
		/*
		 * check prefix lifetime.
		 * since pltime is just for autoconf, pltime processing for
		 * prefix is not necessary.
		 */
		if (pr->ndpr_vltime != ND6_INFINITE_LIFETIME &&
		    time_second - pr->ndpr_lastupdate > pr->ndpr_vltime) {
			/*
			 * address expiration and prefix expiration are
			 * separate.  NEVER perform in6_purgeaddr here.
			 */

			prelist_remove(pr);
		}
	}
	splx(s);
}

void
nd6_timer(void *ignored_arg)
{
	task_add(systq, &nd6_timer_task);
}

/*
 * Nuke neighbor cache/prefix/default router management table, right before
 * ifp goes away.
 */
void
nd6_purge(struct ifnet *ifp)
{
	struct llinfo_nd6 *ln, *nln;
	struct nd_defrouter *dr, *ndr;
	struct nd_prefix *pr, *npr;

	/*
	 * Nuke default router list entries toward ifp.
	 * We defer removal of default router list entries that is installed
	 * in the routing table, in order to keep additional side effects as
	 * small as possible.
	 */
	TAILQ_FOREACH_SAFE(dr, &nd_defrouter, dr_entry, ndr) {
		if (dr->installed)
			continue;

		if (dr->ifp == ifp)
			defrtrlist_del(dr);
	}
	TAILQ_FOREACH_SAFE(dr, &nd_defrouter, dr_entry, ndr) {
		if (!dr->installed)
			continue;

		if (dr->ifp == ifp)
			defrtrlist_del(dr);
	}

	/* Nuke prefix list entries toward ifp */
	LIST_FOREACH_SAFE(pr, &nd_prefix, ndpr_entry, npr) {
		if (pr->ndpr_ifp == ifp)
			prelist_remove(pr);
	}

	if (ifp->if_xflags & IFXF_AUTOCONF6) {
		/* refresh default router list */
		defrouter_select();
	}

	/*
	 * Nuke neighbor cache entries for the ifp.
	 */
	TAILQ_FOREACH_SAFE(ln, &nd6_list, ln_list, nln) {
		struct rtentry *rt;
		struct sockaddr_dl *sdl;

		rt = ln->ln_rt;
		if (rt != NULL && rt->rt_gateway != NULL &&
		    rt->rt_gateway->sa_family == AF_LINK) {
			sdl = satosdl(rt->rt_gateway);
			if (sdl->sdl_index == ifp->if_index)
				nln = nd6_free(rt, 0);
		}
	}
}

struct rtentry *
nd6_lookup(struct in6_addr *addr6, int create, struct ifnet *ifp,
    u_int rtableid)
{
	struct rtentry *rt;
	struct sockaddr_in6 sin6;
	int flags;

	bzero(&sin6, sizeof(sin6));
	sin6.sin6_len = sizeof(struct sockaddr_in6);
	sin6.sin6_family = AF_INET6;
	sin6.sin6_addr = *addr6;
	flags = (create) ? RT_RESOLVE : 0;

	rt = rtalloc(sin6tosa(&sin6), flags, rtableid);
	if (rt != NULL && (rt->rt_flags & RTF_LLINFO) == 0) {
		/*
		 * This is the case for the default route.
		 * If we want to create a neighbor cache for the address, we
		 * should free the route for the destination and allocate an
		 * interface route.
		 */
		if (create) {
			rtfree(rt);
			rt = NULL;
		}
	}
	if (rt == NULL) {
		if (create && ifp) {
			struct rt_addrinfo info;
			int error;

			/*
			 * If no route is available and create is set,
			 * we allocate a host route for the destination
			 * and treat it like an interface route.
			 * This hack is necessary for a neighbor which can't
			 * be covered by our own prefix.
			 */
			struct ifaddr *ifa =
			    ifaof_ifpforaddr(sin6tosa(&sin6), ifp);
			if (ifa == NULL)
				return (NULL);

			/*
			 * Create a new route.  RTF_LLINFO is necessary
			 * to create a Neighbor Cache entry for the
			 * destination in nd6_rtrequest which will be
			 * called in rtrequest.
			 */
			bzero(&info, sizeof(info));
			info.rti_flags = RTF_HOST | RTF_LLINFO;
			info.rti_info[RTAX_DST] = sin6tosa(&sin6);
			info.rti_info[RTAX_GATEWAY] = sdltosa(ifp->if_sadl);
			error = rtrequest(RTM_ADD, &info, RTP_CONNECTED, &rt,
			    rtableid);
			if (error)
				return (NULL);
			if (rt->rt_llinfo != NULL) {
				struct llinfo_nd6 *ln =
				    (struct llinfo_nd6 *)rt->rt_llinfo;
				ln->ln_state = ND6_LLINFO_NOSTATE;
			}
		} else
			return (NULL);
	}
	/*
	 * Validation for the entry.
	 * Note that the check for rt_llinfo is necessary because a cloned
	 * route from a parent route that has the L flag (e.g. the default
	 * route to a p2p interface) may have the flag, too, while the
	 * destination is not actually a neighbor.
	 */
	if ((rt->rt_flags & RTF_GATEWAY) || (rt->rt_flags & RTF_LLINFO) == 0 ||
	    rt->rt_gateway->sa_family != AF_LINK || rt->rt_llinfo == NULL ||
	    (ifp != NULL && rt->rt_ifidx != ifp->if_index)) {
		if (create) {
			char addr[INET6_ADDRSTRLEN];
			nd6log((LOG_DEBUG, "%s: failed to lookup %s (if=%s)\n",
			    __func__,
			    inet_ntop(AF_INET6, addr6, addr, sizeof(addr)),
			    ifp ? ifp->if_xname : "unspec"));
		}
		rtfree(rt);
		return (NULL);
	}
	return (rt);
}

/*
 * Detect if a given IPv6 address identifies a neighbor on a given link.
 * XXX: should take care of the destination of a p2p link?
 */
int
nd6_is_addr_neighbor(struct sockaddr_in6 *addr, struct ifnet *ifp)
{
	struct nd_prefix *pr;
	struct in6_ifaddr *ia6;
	struct ifaddr *ifa;
	struct rtentry *rt;

	/*
	 * A link-local address is always a neighbor.
	 * XXX: we should use the sin6_scope_id field rather than the embedded
	 * interface index.
	 * XXX: a link does not necessarily specify a single interface.
	 */
	if (IN6_IS_ADDR_LINKLOCAL(&addr->sin6_addr) &&
	    ntohs(*(u_int16_t *)&addr->sin6_addr.s6_addr[2]) == ifp->if_index)
		return (1);

	TAILQ_FOREACH(ifa, &ifp->if_addrlist, ifa_list) {
		if (ifa->ifa_addr->sa_family != AF_INET6)
			continue;

		ia6 = ifatoia6(ifa);

		/* Prefix check down below. */
		if (ia6->ia6_flags & IN6_IFF_AUTOCONF)
			continue;

		if (IN6_ARE_MASKED_ADDR_EQUAL(&addr->sin6_addr,
		    &ia6->ia_addr.sin6_addr,
		    &ia6->ia_prefixmask.sin6_addr))
			return (1);
	}

	/*
	 * If the address matches one of our on-link prefixes, it should be a
	 * neighbor.
	 */
	LIST_FOREACH(pr, &nd_prefix, ndpr_entry) {
		if (pr->ndpr_ifp != ifp)
			continue;

		if (!(pr->ndpr_stateflags & NDPRF_ONLINK))
			continue;

		if (IN6_ARE_MASKED_ADDR_EQUAL(&pr->ndpr_prefix.sin6_addr,
		    &addr->sin6_addr, &pr->ndpr_mask))
			return (1);
	}

	/*
	 * Even if the address matches none of our addresses, it might be
	 * in the neighbor cache.
	 */
	rt = nd6_lookup(&addr->sin6_addr, 0, ifp, ifp->if_rdomain);
	if (rt != NULL) {
		rtfree(rt);
		return (1);
	}

	return (0);
}

void
nd6_invalidate(struct rtentry *rt)
{
	struct llinfo_nd6 *ln = (struct llinfo_nd6 *)rt->rt_llinfo;

	m_freem(ln->ln_hold);
	ln->ln_hold = NULL;
	ln->ln_state = ND6_LLINFO_INCOMPLETE;
	ln->ln_asked = 0;
}

/*
 * Free an nd6 llinfo entry.
 * Since the function would cause significant changes in the kernel, DO NOT
 * make it global, unless you have a strong reason for the change, and are sure
 * that the change is safe.
 */
struct llinfo_nd6 *
nd6_free(struct rtentry *rt, int gc)
{
	struct llinfo_nd6 *ln = (struct llinfo_nd6 *)rt->rt_llinfo, *next;
	struct in6_addr in6 = satosin6(rt_key(rt))->sin6_addr;
	struct nd_defrouter *dr;
	struct ifnet *ifp;
	int s;

	/*
	 * we used to have pfctlinput(PRC_HOSTDEAD) here.
	 * even though it is not harmful, it was not really necessary.
	 */
	ifp = if_get(rt->rt_ifidx);

	s = splsoftnet();
	if (!ip6_forwarding) {
		dr = defrouter_lookup(&satosin6(rt_key(rt))->sin6_addr,
		    rt->rt_ifidx);

		if (dr != NULL && dr->expire &&
		    ln->ln_state == ND6_LLINFO_STALE && gc) {
			/*
			 * If the reason for the deletion is just garbage
			 * collection, and the neighbor is an active default
			 * router, do not delete it.  Instead, reset the GC
			 * timer using the router's lifetime.
			 * Simply deleting the entry would affect default
			 * router selection, which is not necessarily a good
			 * thing, especially when we're using router preference
			 * values.
			 * XXX: the check for ln_state would be redundant,
			 *      but we intentionally keep it just in case.
			 */
			if (dr->expire > time_second) {
				nd6_llinfo_settimer(ln,
				    dr->expire - time_second);
			} else
				nd6_llinfo_settimer(ln, nd6_gctimer);
			splx(s);
			if_put(ifp);
			return (TAILQ_NEXT(ln, ln_list));
		}

		if (ln->ln_router || dr) {
			/*
			 * rt6_flush must be called whether or not the neighbor
			 * is in the Default Router List.
			 * See a corresponding comment in nd6_na_input().
			 */
			rt6_flush(&in6, ifp);
		}

		if (dr) {
			/*
			 * Unreachability of a router might affect the default
			 * router selection and on-link detection of advertised
			 * prefixes.
			 */

			/*
			 * Temporarily fake the state to choose a new default
			 * router and to perform on-link determination of
			 * prefixes correctly.
			 * Below the state will be set correctly,
			 * or the entry itself will be deleted.
			 */
			ln->ln_state = ND6_LLINFO_INCOMPLETE;

			/*
			 * Since defrouter_select() does not affect the
			 * on-link determination and MIP6 needs the check
			 * before the default router selection, we perform
			 * the check now.
			 */
			pfxlist_onlink_check();

			/*
			 * refresh default router list
			 */
			defrouter_select();
		}
	}

	/*
	 * Before deleting the entry, remember the next entry as the
	 * return value.  We need this because pfxlist_onlink_check() above
	 * might have freed other entries (particularly the old next entry) as
	 * a side effect (XXX).
	 */
	next = TAILQ_NEXT(ln, ln_list);

	/*
	 * Detach the route from the routing tree and the list of neighbor
	 * caches, and disable the route entry not to be used in already
	 * cached routes.
	 */
	if (!ISSET(rt->rt_flags, RTF_STATIC|RTF_CACHED))
		rtdeletemsg(rt, ifp, ifp->if_rdomain);
	splx(s);

	if_put(ifp);

	return (next);
}

/*
 * Upper-layer reachability hint for Neighbor Unreachability Detection.
 *
 * XXX cost-effective methods?
 */
void
nd6_nud_hint(struct rtentry *rt)
{
	struct llinfo_nd6 *ln;
	struct ifnet *ifp;

	ifp = if_get(rt->rt_ifidx);
	if (ifp == NULL)
		return;

	if ((rt->rt_flags & RTF_GATEWAY) != 0 ||
	    (rt->rt_flags & RTF_LLINFO) == 0 ||
	    rt->rt_llinfo == NULL || rt->rt_gateway == NULL ||
	    rt->rt_gateway->sa_family != AF_LINK) {
		/* This is not a host route. */
		goto out;
	}

	ln = (struct llinfo_nd6 *)rt->rt_llinfo;
	if (ln->ln_state < ND6_LLINFO_REACHABLE)
		goto out;

	/*
	 * if we get upper-layer reachability confirmation many times,
	 * it is possible we have false information.
	 */
	ln->ln_byhint++;
	if (ln->ln_byhint > nd6_maxnudhint)
		goto out;

	ln->ln_state = ND6_LLINFO_REACHABLE;
	if (!ND6_LLINFO_PERMANENT(ln))
		nd6_llinfo_settimer(ln, ND_IFINFO(ifp)->reachable);
out:
	if_put(ifp);
}

void
nd6_rtrequest(struct ifnet *ifp, int req, struct rtentry *rt)
{
	struct sockaddr *gate = rt->rt_gateway;
	struct llinfo_nd6 *ln = (struct llinfo_nd6 *)rt->rt_llinfo;
	struct ifaddr *ifa;
	struct nd_defrouter *dr;

	if (req == RTM_DELETE && (rt->rt_flags & RTF_GATEWAY) &&
	    (IN6_ARE_ADDR_EQUAL(&(satosin6(rt_key(rt)))->sin6_addr,
	    &in6addr_any) && rt_plen(rt) == 0)) {
		dr = defrouter_lookup(&satosin6(gate)->sin6_addr,
		    ifp->if_index);
		if (dr)
			dr->installed = 0;
	}

	if (ISSET(rt->rt_flags, RTF_GATEWAY|RTF_MULTICAST))
		return;

	if (nd6_need_cache(ifp) == 0 && (rt->rt_flags & RTF_HOST) == 0) {
		/*
		 * This is probably an interface direct route for a link
		 * which does not need neighbor caches (e.g. fe80::%lo0/64).
		 * We do not need special treatment below for such a route.
		 * Moreover, the RTF_LLINFO flag which would be set below
		 * would annoy the ndp(8) command.
		 */
		return;
	}

	if (req == RTM_RESOLVE && nd6_need_cache(ifp) == 0) {
		/*
		 * For routing daemons like ospf6d we allow neighbor discovery
		 * based on the cloning route only.  This allows us to sent
		 * packets directly into a network without having an address
		 * with matching prefix on the interface.  If the cloning
		 * route is used for an stf interface, we would mistakenly
		 * make a neighbor cache for the host route, and would see
		 * strange neighbor solicitation for the corresponding
		 * destination.  In order to avoid confusion, we check if the
		 * interface is suitable for neighbor discovery, and stop the
		 * process if not.  Additionally, we remove the LLINFO flag
		 * so that ndp(8) will not try to get the neighbor information
		 * of the destination.
		 */
		rt->rt_flags &= ~RTF_LLINFO;
		return;
	}

	switch (req) {
	case RTM_ADD:
		if ((rt->rt_flags & RTF_CLONING) ||
		    ((rt->rt_flags & (RTF_LLINFO | RTF_LOCAL)) && ln == NULL)) {
			if (ln != NULL)
				nd6_llinfo_settimer(ln, 0);
			if ((rt->rt_flags & RTF_CLONING) != 0)
				break;
		}
		/*
		 * In IPv4 code, we try to announce new RTF_ANNOUNCE entry here.
		 * We don't do that here since llinfo is not ready yet.
		 *
		 * There are also couple of other things to be discussed:
		 * - unsolicited NA code needs improvement beforehand
		 * - RFC2461 says we MAY send multicast unsolicited NA
		 *   (7.2.6 paragraph 4), however, it also says that we
		 *   SHOULD provide a mechanism to prevent multicast NA storm.
		 *   we don't have anything like it right now.
		 *   note that the mechanism needs a mutual agreement
		 *   between proxies, which means that we need to implement
		 *   a new protocol, or a new kludge.
		 * - from RFC2461 6.2.4, host MUST NOT send an unsolicited NA.
		 *   we need to check ip6forwarding before sending it.
		 *   (or should we allow proxy ND configuration only for
		 *   routers?  there's no mention about proxy ND from hosts)
		 */
#if 0
		/* XXX it does not work */
		if (rt->rt_flags & RTF_ANNOUNCE)
			nd6_na_output(ifp,
			      &satosin6(rt_key(rt))->sin6_addr,
			      &satosin6(rt_key(rt))->sin6_addr,
			      ip6_forwarding ? ND_NA_FLAG_ROUTER : 0,
			      1, NULL);
#endif
		/* FALLTHROUGH */
	case RTM_RESOLVE:
		if (gate->sa_family != AF_LINK ||
		    gate->sa_len < sizeof(struct sockaddr_dl)) {
			log(LOG_DEBUG, "%s: bad gateway value: %s\n",
			    __func__, ifp->if_xname);
			break;
		}
		satosdl(gate)->sdl_type = ifp->if_type;
		satosdl(gate)->sdl_index = ifp->if_index;
		if (ln != NULL)
			break;	/* This happens on a route change */
		/*
		 * Case 2: This route may come from cloning, or a manual route
		 * add with a LL address.
		 */
		ln = pool_get(&nd6_pool, PR_NOWAIT | PR_ZERO);
		rt->rt_llinfo = (caddr_t)ln;
		if (ln == NULL) {
			log(LOG_DEBUG, "%s: pool get failed\n", __func__);
			break;
		}
		nd6_inuse++;
		nd6_allocated++;
		ln->ln_rt = rt;
		timeout_set(&ln->ln_timer_ch, nd6_llinfo_timer, ln);
		/* this is required for "ndp" command. - shin */
		if (req == RTM_ADD) {
		        /*
			 * gate should have some valid AF_LINK entry,
			 * and ln expire should have some lifetime
			 * which is specified by ndp command.
			 */
			ln->ln_state = ND6_LLINFO_REACHABLE;
			ln->ln_byhint = 0;
		} else {
		        /*
			 * When req == RTM_RESOLVE, rt is created and
			 * initialized in rtrequest(), so rt_expire is 0.
			 */
			ln->ln_state = ND6_LLINFO_NOSTATE;
			nd6_llinfo_settimer(ln, 0);
		}
		rt->rt_flags |= RTF_LLINFO;
		TAILQ_INSERT_HEAD(&nd6_list, ln, ln_list);

		/*
		 * If we have too many cache entries, initiate immediate
		 * purging for some "less recently used" entries.  Note that
		 * we cannot directly call nd6_free() here because it would
		 * cause re-entering rtable related routines triggering an LOR
		 * problem for FreeBSD.
		 */
		if (ip6_neighborgcthresh >= 0 &&
		    nd6_inuse >= ip6_neighborgcthresh) {
			int i;

			for (i = 0; i < 10; i++) {
				struct llinfo_nd6 *ln_end;

				ln_end = TAILQ_LAST(&nd6_list, llinfo_nd6_head);
				if (ln_end == ln)
					break;

				/* Move this entry to the head */
				TAILQ_REMOVE(&nd6_list, ln_end, ln_list);
				TAILQ_INSERT_HEAD(&nd6_list, ln_end, ln_list);

				if (ND6_LLINFO_PERMANENT(ln_end))
					continue;

				if (ln_end->ln_state > ND6_LLINFO_INCOMPLETE)
					ln_end->ln_state = ND6_LLINFO_STALE;
				else
					ln_end->ln_state = ND6_LLINFO_PURGE;
				nd6_llinfo_settimer(ln_end, 0);
			}
		}

		/*
		 * check if rt_key(rt) is one of my address assigned
		 * to the interface.
		 */
		ifa = &in6ifa_ifpwithaddr(ifp,
		    &satosin6(rt_key(rt))->sin6_addr)->ia_ifa;
		if (ifa) {
			nd6_llinfo_settimer(ln, -1);
			ln->ln_state = ND6_LLINFO_REACHABLE;
			ln->ln_byhint = 0;
			KASSERT(ifa == rt->rt_ifa);
		} else if (rt->rt_flags & RTF_ANNOUNCE) {
			nd6_llinfo_settimer(ln, -1);
			ln->ln_state = ND6_LLINFO_REACHABLE;
			ln->ln_byhint = 0;

			/* join solicited node multicast for proxy ND */
			if (ifp->if_flags & IFF_MULTICAST) {
				struct in6_addr llsol;
				int error;

				llsol = satosin6(rt_key(rt))->sin6_addr;
				llsol.s6_addr16[0] = htons(0xff02);
				llsol.s6_addr16[1] = htons(ifp->if_index);
				llsol.s6_addr32[1] = 0;
				llsol.s6_addr32[2] = htonl(1);
				llsol.s6_addr8[12] = 0xff;

				if (in6_addmulti(&llsol, ifp, &error)) {
					char addr[INET6_ADDRSTRLEN];
					nd6log((LOG_ERR, "%s: failed to join "
					    "%s (errno=%d)\n", ifp->if_xname,
					    inet_ntop(AF_INET6, &llsol,
						addr, sizeof(addr)),
					    error));
				}
			}
		}
		break;

	case RTM_DELETE:
		if (ln == NULL)
			break;
		/* leave from solicited node multicast for proxy ND */
		if ((rt->rt_flags & RTF_ANNOUNCE) != 0 &&
		    (ifp->if_flags & IFF_MULTICAST) != 0) {
			struct in6_addr llsol;
			struct in6_multi *in6m;

			llsol = satosin6(rt_key(rt))->sin6_addr;
			llsol.s6_addr16[0] = htons(0xff02);
			llsol.s6_addr16[1] = htons(ifp->if_index);
			llsol.s6_addr32[1] = 0;
			llsol.s6_addr32[2] = htonl(1);
			llsol.s6_addr8[12] = 0xff;

			IN6_LOOKUP_MULTI(llsol, ifp, in6m);
			if (in6m)
				in6_delmulti(in6m);
		}
		nd6_inuse--;
		TAILQ_REMOVE(&nd6_list, ln, ln_list);
		nd6_llinfo_settimer(ln, -1);
		rt->rt_llinfo = NULL;
		rt->rt_flags &= ~RTF_LLINFO;
		m_freem(ln->ln_hold);
		pool_put(&nd6_pool, ln);
		break;

	case RTM_INVALIDATE:
		nd6_invalidate(rt);
		break;
	}
}

int
nd6_ioctl(u_long cmd, caddr_t data, struct ifnet *ifp)
{
	struct in6_ndireq *ndi = (struct in6_ndireq *)data;
	struct in6_nbrinfo *nbi = (struct in6_nbrinfo *)data;
	struct rtentry *rt;
	int error = 0;
	int s;

	switch (cmd) {
	case SIOCGIFINFO_IN6:
		ndi->ndi = *ND_IFINFO(ifp);
		memset(&ndi->ndi.randomseed0, 0, sizeof ndi->ndi.randomseed0);
		memset(&ndi->ndi.randomseed1, 0, sizeof ndi->ndi.randomseed1);
		memset(&ndi->ndi.randomid, 0, sizeof ndi->ndi.randomid);
		break;
	case SIOCSIFINFO_FLAGS:
		ND_IFINFO(ifp)->flags = ndi->ndi.flags;
		break;
	case SIOCSNDFLUSH_IN6:	/* XXX: the ioctl name is confusing... */
		/* sync kernel routing table with the default router list */
		defrouter_reset();
		defrouter_select();
		break;
	case SIOCSPFXFLUSH_IN6:
	{
		/* flush all the prefix advertised by routers */
		struct nd_prefix *pr, *npr;

		s = splsoftnet();
		/* First purge the addresses referenced by a prefix. */
		LIST_FOREACH_SAFE(pr, &nd_prefix, ndpr_entry, npr) {
			struct in6_ifaddr *ia6, *ia6_next;

			if (IN6_IS_ADDR_LINKLOCAL(&pr->ndpr_prefix.sin6_addr))
				continue; /* XXX */

			/* do we really have to remove addresses as well? */
			TAILQ_FOREACH_SAFE(ia6, &in6_ifaddr, ia_list, ia6_next) {
				if ((ia6->ia6_flags & IN6_IFF_AUTOCONF) == 0)
					continue;

				if (ia6->ia6_ndpr == pr)
					in6_purgeaddr(&ia6->ia_ifa);
			}
		}
		/*
		 * Purging the addresses might remove the prefix as well.
		 * So run the loop again to access only prefixes that have
		 * not been freed already.
		 */
		LIST_FOREACH_SAFE(pr, &nd_prefix, ndpr_entry, npr) {
			if (IN6_IS_ADDR_LINKLOCAL(&pr->ndpr_prefix.sin6_addr))
				continue; /* XXX */

			prelist_remove(pr);
		}
		splx(s);
		break;
	}
	case SIOCSRTRFLUSH_IN6:
	{
		/* flush all the default routers */
		struct nd_defrouter *dr, *ndr;

		s = splsoftnet();
		defrouter_reset();
		TAILQ_FOREACH_SAFE(dr, &nd_defrouter, dr_entry, ndr)
			defrtrlist_del(dr);
		defrouter_select();
		splx(s);
		break;
	}
	case SIOCGNBRINFO_IN6:
	{
		struct llinfo_nd6 *ln;
		struct in6_addr nb_addr = nbi->addr; /* make local for safety */
		time_t expire;

		/*
		 * XXX: KAME specific hack for scoped addresses
		 *      XXXX: for other scopes than link-local?
		 */
		if (IN6_IS_ADDR_LINKLOCAL(&nbi->addr) ||
		    IN6_IS_ADDR_MC_LINKLOCAL(&nbi->addr)) {
			u_int16_t *idp = (u_int16_t *)&nb_addr.s6_addr[2];

			if (*idp == 0)
				*idp = htons(ifp->if_index);
		}

		s = splsoftnet();
		rt = nd6_lookup(&nb_addr, 0, ifp, ifp->if_rdomain);
		if (rt == NULL ||
		    (ln = (struct llinfo_nd6 *)rt->rt_llinfo) == NULL) {
			error = EINVAL;
			rtfree(rt);
			splx(s);
			break;
		}
		expire = ln->ln_rt->rt_expire;
		if (expire != 0) {
			expire -= time_uptime;
			expire += time_second;
		}

		nbi->state = ln->ln_state;
		nbi->asked = ln->ln_asked;
		nbi->isrouter = ln->ln_router;
		nbi->expire = expire;
		rtfree(rt);
		splx(s);

		break;
	}
	}
	return (error);
}

/*
 * Create neighbor cache entry and cache link-layer address,
 * on reception of inbound ND6 packets.  (RS/RA/NS/redirect)
 *
 * type - ICMP6 type
 * code - type dependent information
 */
void
nd6_cache_lladdr(struct ifnet *ifp, struct in6_addr *from, char *lladdr,
    int lladdrlen, int type, int code)
{
	struct rtentry *rt = NULL;
	struct llinfo_nd6 *ln = NULL;
	int is_newentry;
	struct sockaddr_dl *sdl = NULL;
	int do_update;
	int olladdr;
	int llchange;
	int newstate = 0;

	if (!ifp)
		panic("ifp == NULL in nd6_cache_lladdr");
	if (!from)
		panic("from == NULL in nd6_cache_lladdr");

	/* nothing must be updated for unspecified address */
	if (IN6_IS_ADDR_UNSPECIFIED(from))
		return;

	/*
	 * Validation about ifp->if_addrlen and lladdrlen must be done in
	 * the caller.
	 *
	 * XXX If the link does not have link-layer address, what should
	 * we do? (ifp->if_addrlen == 0)
	 * Spec says nothing in sections for RA, RS and NA.  There's small
	 * description on it in NS section (RFC 2461 7.2.3).
	 */

	rt = nd6_lookup(from, 0, ifp, ifp->if_rdomain);
	if (rt == NULL) {
#if 0
		/* nothing must be done if there's no lladdr */
		if (!lladdr || !lladdrlen)
			return NULL;
#endif

		rt = nd6_lookup(from, 1, ifp, ifp->if_rdomain);
		is_newentry = 1;
	} else {
		/* do nothing if static ndp is set */
		if (rt->rt_flags & RTF_STATIC) {
			rtfree(rt);
			return;
		}
		is_newentry = 0;
	}

	if (!rt)
		return;
	if ((rt->rt_flags & (RTF_GATEWAY | RTF_LLINFO)) != RTF_LLINFO) {
fail:
		(void)nd6_free(rt, 0);
		rtfree(rt);
		return;
	}
	ln = (struct llinfo_nd6 *)rt->rt_llinfo;
	if (ln == NULL)
		goto fail;
	if (rt->rt_gateway == NULL)
		goto fail;
	if (rt->rt_gateway->sa_family != AF_LINK)
		goto fail;
	sdl = satosdl(rt->rt_gateway);

	olladdr = (sdl->sdl_alen) ? 1 : 0;
	if (olladdr && lladdr) {
		if (bcmp(lladdr, LLADDR(sdl), ifp->if_addrlen))
			llchange = 1;
		else
			llchange = 0;
	} else
		llchange = 0;

	/*
	 * newentry olladdr  lladdr  llchange	(*=record)
	 *	0	n	n	--	(1)
	 *	0	y	n	--	(2)
	 *	0	n	y	--	(3) * STALE
	 *	0	y	y	n	(4) *
	 *	0	y	y	y	(5) * STALE
	 *	1	--	n	--	(6)   NOSTATE(= PASSIVE)
	 *	1	--	y	--	(7) * STALE
	 */

	if (llchange) {
		char addr[INET6_ADDRSTRLEN];
		log(LOG_INFO, "ndp info overwritten for %s by %s on %s\n",
		    inet_ntop(AF_INET6, from, addr, sizeof(addr)),
		    ether_sprintf(lladdr), ifp->if_xname);
	}
	if (lladdr) {		/* (3-5) and (7) */
		/*
		 * Record source link-layer address
		 * XXX is it dependent to ifp->if_type?
		 */
		sdl->sdl_alen = ifp->if_addrlen;
		bcopy(lladdr, LLADDR(sdl), ifp->if_addrlen);
	}

	if (!is_newentry) {
		if ((!olladdr && lladdr) ||		/* (3) */
		    (olladdr && lladdr && llchange)) {	/* (5) */
			do_update = 1;
			newstate = ND6_LLINFO_STALE;
		} else					/* (1-2,4) */
			do_update = 0;
	} else {
		do_update = 1;
		if (!lladdr)				/* (6) */
			newstate = ND6_LLINFO_NOSTATE;
		else					/* (7) */
			newstate = ND6_LLINFO_STALE;
	}

	if (do_update) {
		/*
		 * Update the state of the neighbor cache.
		 */
		ln->ln_state = newstate;

		if (ln->ln_state == ND6_LLINFO_STALE) {
			/*
			 * Since nd6_resolve() in ifp->if_output() will cause
			 * state transition to DELAY and reset the timer,
			 * we must set the timer now, although it is actually
			 * meaningless.
			 */
			nd6_llinfo_settimer(ln, nd6_gctimer);

			if (ln->ln_hold) {
				struct mbuf *n = ln->ln_hold;
				ln->ln_hold = NULL;
				/*
				 * we assume ifp is not a p2p here, so just
				 * set the 2nd argument as the 1st one.
				 */
				ifp->if_output(ifp, n, rt_key(rt), rt);
				if (ln->ln_hold == n) {
					/* n is back in ln_hold. Discard. */
					m_freem(ln->ln_hold);
					ln->ln_hold = NULL;
				}
			}
		} else if (ln->ln_state == ND6_LLINFO_INCOMPLETE) {
			/* probe right away */
			nd6_llinfo_settimer((void *)ln, 0);
		}
	}

	/*
	 * ICMP6 type dependent behavior.
	 *
	 * NS: clear IsRouter if new entry
	 * RS: clear IsRouter
	 * RA: set IsRouter if there's lladdr
	 * redir: clear IsRouter if new entry
	 *
	 * RA case, (1):
	 * The spec says that we must set IsRouter in the following cases:
	 * - If lladdr exist, set IsRouter.  This means (1-5).
	 * - If it is old entry (!newentry), set IsRouter.  This means (7).
	 * So, based on the spec, in (1-5) and (7) cases we must set IsRouter.
	 * A question arises for (1) case.  (1) case has no lladdr in the
	 * neighbor cache, this is similar to (6).
	 * This case is rare but we figured that we MUST NOT set IsRouter.
	 *
	 * newentry olladdr  lladdr  llchange	    NS  RS  RA	redir
	 *							D R
	 *	0	n	n	--	(1)	c   ?     s
	 *	0	y	n	--	(2)	c   s     s
	 *	0	n	y	--	(3)	c   s     s
	 *	0	y	y	n	(4)	c   s     s
	 *	0	y	y	y	(5)	c   s     s
	 *	1	--	n	--	(6) c	c	c s
	 *	1	--	y	--	(7) c	c   s	c s
	 *
	 *					(c=clear s=set)
	 */
	switch (type & 0xff) {
	case ND_NEIGHBOR_SOLICIT:
		/*
		 * New entry must have is_router flag cleared.
		 */
		if (is_newentry)	/* (6-7) */
			ln->ln_router = 0;
		break;
	case ND_REDIRECT:
		/*
		 * If the icmp is a redirect to a better router, always set the
		 * is_router flag.  Otherwise, if the entry is newly created,
		 * clear the flag.  [RFC 2461, sec 8.3]
		 */
		if (code == ND_REDIRECT_ROUTER)
			ln->ln_router = 1;
		else if (is_newentry) /* (6-7) */
			ln->ln_router = 0;
		break;
	case ND_ROUTER_SOLICIT:
		/*
		 * is_router flag must always be cleared.
		 */
		ln->ln_router = 0;
		break;
	case ND_ROUTER_ADVERT:
		/*
		 * Mark an entry with lladdr as a router.
		 */
		if ((!is_newentry && (olladdr || lladdr)) ||	/* (2-5) */
		    (is_newentry && lladdr)) {			/* (7) */
			ln->ln_router = 1;
		}
		break;
	}

	/*
	 * When the link-layer address of a router changes, select the
	 * best router again.  In particular, when the neighbor entry is newly
	 * created, it might affect the selection policy.
	 * Question: can we restrict the first condition to the "is_newentry"
	 * case?
	 * XXX: when we hear an RA from a new router with the link-layer
	 * address option, defrouter_select() is called twice, since
	 * defrtrlist_update called the function as well.  However, I believe
	 * we can compromise the overhead, since it only happens the first
	 * time.
	 */
	if (do_update && ln->ln_router && (ifp->if_xflags & IFXF_AUTOCONF6))
		defrouter_select();

	rtfree(rt);
}

void
nd6_slowtimo(void *ignored_arg)
{
	int s = splsoftnet();
	struct nd_ifinfo *nd6if;
	struct ifnet *ifp;

	timeout_set(&nd6_slowtimo_ch, nd6_slowtimo, NULL);
	timeout_add_sec(&nd6_slowtimo_ch, ND6_SLOWTIMER_INTERVAL);
	TAILQ_FOREACH(ifp, &ifnet, if_list) {
		nd6if = ND_IFINFO(ifp);
		if (nd6if->basereachable && /* already initialized */
		    (nd6if->recalctm -= ND6_SLOWTIMER_INTERVAL) <= 0) {
			/*
			 * Since reachable time rarely changes by router
			 * advertisements, we SHOULD insure that a new random
			 * value gets recomputed at least once every few hours.
			 * (RFC 2461, 6.3.4)
			 */
			nd6if->recalctm = nd6_recalc_reachtm_interval;
			nd6if->reachable = ND_COMPUTE_RTIME(nd6if->basereachable);
		}
	}
	splx(s);
}

int
nd6_resolve(struct ifnet *ifp, struct rtentry *rt0, struct mbuf *m,
    struct sockaddr *dst, u_char *desten)
{
	struct sockaddr_dl *sdl;
	struct rtentry *rt;
	struct llinfo_nd6 *ln = NULL;

	if (m->m_flags & M_MCAST) {
		ETHER_MAP_IPV6_MULTICAST(&satosin6(dst)->sin6_addr, desten);
		return (0);
	}

	rt = rt_getll(rt0);

	if (ISSET(rt->rt_flags, RTF_REJECT) &&
	    (rt->rt_expire == 0 || time_uptime < rt->rt_expire)) {
		m_freem(m);
		return (rt == rt0 ? EHOSTDOWN : EHOSTUNREACH);
	}

	/*
	 * Address resolution or Neighbor Unreachability Detection
	 * for the next hop.
	 * At this point, the destination of the packet must be a unicast
	 * or an anycast address(i.e. not a multicast).
	 */
	if (!ISSET(rt->rt_flags, RTF_LLINFO)) {
		char addr[INET6_ADDRSTRLEN];
		log(LOG_DEBUG, "%s: %s: route contains no ND information\n",
		    __func__, inet_ntop(AF_INET6,
		    &satosin6(rt_key(rt))->sin6_addr, addr, sizeof(addr)));
		m_freem(m);
		return (EINVAL);
	}

	if (rt->rt_gateway->sa_family != AF_LINK) {
		printf("%s: something odd happens\n", __func__);
		m_freem(m);
		return (EINVAL);
	}

	ln = (struct llinfo_nd6 *)rt->rt_llinfo;
	KASSERT(ln != NULL);

	/*
	 * Move this entry to the head of the queue so that it is less likely
	 * for this entry to be a target of forced garbage collection (see
	 * nd6_rtrequest()).
	 */
	TAILQ_REMOVE(&nd6_list, ln, ln_list);
	TAILQ_INSERT_HEAD(&nd6_list, ln, ln_list);

	/*
	 * The first time we send a packet to a neighbor whose entry is
	 * STALE, we have to change the state to DELAY and a sets a timer to
	 * expire in DELAY_FIRST_PROBE_TIME seconds to ensure do
	 * neighbor unreachability detection on expiration.
	 * (RFC 2461 7.3.3)
	 */
	if (ln->ln_state == ND6_LLINFO_STALE) {
		ln->ln_asked = 0;
		ln->ln_state = ND6_LLINFO_DELAY;
		nd6_llinfo_settimer(ln, nd6_delay);
	}

	/*
	 * If the neighbor cache entry has a state other than INCOMPLETE
	 * (i.e. its link-layer address is already resolved), just
	 * send the packet.
	 */
	if (ln->ln_state > ND6_LLINFO_INCOMPLETE) {
		sdl = satosdl(rt->rt_gateway);
		if (sdl->sdl_alen != ETHER_ADDR_LEN) {
			char addr[INET6_ADDRSTRLEN];
			log(LOG_DEBUG, "%s: %s: incorrect nd6 information\n",
			    __func__,
			    inet_ntop(AF_INET6, &satosin6(dst)->sin6_addr,
				addr, sizeof(addr)));
			m_freem(m);
			return (EINVAL);
		}

		bcopy(LLADDR(sdl), desten, sdl->sdl_alen);
		return (0);
	}

	/*
	 * There is a neighbor cache entry, but no ethernet address
	 * response yet.  Replace the held mbuf (if any) with this
	 * latest one.
	 */
	if (ln->ln_state == ND6_LLINFO_NOSTATE)
		ln->ln_state = ND6_LLINFO_INCOMPLETE;
	m_freem(ln->ln_hold);
	ln->ln_hold = m;

	/*
	 * If there has been no NS for the neighbor after entering the
	 * INCOMPLETE state, send the first solicitation.
	 */
	if (!ND6_LLINFO_PERMANENT(ln) && ln->ln_asked == 0) {
		ln->ln_asked++;
		nd6_llinfo_settimer(ln, ND_IFINFO(ifp)->retrans / 1000);
		nd6_ns_output(ifp, NULL, &satosin6(dst)->sin6_addr, ln, 0);
	}
	return (EAGAIN);
}

int
nd6_need_cache(struct ifnet *ifp)
{
	/*
	 * RFC2893 says:
	 * - unidirectional tunnels needs no ND
	 */
	switch (ifp->if_type) {
	case IFT_ETHER:
	case IFT_IEEE80211:
	case IFT_CARP:
		return (1);
	default:
		return (0);
	}
}

/*
 * oldp - syscall arg, need copyout
 * newp - syscall arg, need copyin
 */

int
nd6_sysctl(int name, void *oldp, size_t *oldlenp, void *newp, size_t newlen)
{
	void *p;
	size_t ol;
	int error;

	error = 0;

	if (newp)
		return EPERM;
	if (oldp && !oldlenp)
		return EINVAL;
	ol = oldlenp ? *oldlenp : 0;

	if (oldp) {
		p = malloc(ol, M_TEMP, M_WAITOK | M_CANFAIL);
		if (!p)
			return ENOMEM;
	} else
		p = NULL;
	switch (name) {
	case ICMPV6CTL_ND6_DRLIST:
		error = fill_drlist(p, oldlenp, ol);
		if (!error && p && oldp)
			error = copyout(p, oldp, *oldlenp);
		break;

	case ICMPV6CTL_ND6_PRLIST:
		error = fill_prlist(p, oldlenp, ol);
		if (!error && p && oldp)
			error = copyout(p, oldp, *oldlenp);
		break;

	default:
		error = ENOPROTOOPT;
		break;
	}
	free(p, M_TEMP, ol);

	return (error);
}

int
fill_drlist(void *oldp, size_t *oldlenp, size_t ol)
{
	int error = 0, s;
	struct in6_defrouter *d = NULL, *de = NULL;
	struct nd_defrouter *dr;
	size_t l;

	s = splsoftnet();

	if (oldp) {
		d = (struct in6_defrouter *)oldp;
		de = (struct in6_defrouter *)((caddr_t)oldp + *oldlenp);
	}
	l = 0;

	TAILQ_FOREACH(dr, &nd_defrouter, dr_entry) {
		if (oldp && d + 1 <= de) {
			bzero(d, sizeof(*d));
			d->rtaddr.sin6_family = AF_INET6;
			d->rtaddr.sin6_len = sizeof(struct sockaddr_in6);
			in6_recoverscope(&d->rtaddr, &dr->rtaddr);
			d->flags = dr->flags;
			d->rtlifetime = dr->rtlifetime;
			d->expire = dr->expire;
			d->if_index = dr->ifp->if_index;
		}

		l += sizeof(*d);
		if (d)
			d++;
	}

	if (oldp) {
		*oldlenp = l;	/* (caddr_t)d - (caddr_t)oldp */
		if (l > ol)
			error = ENOMEM;
	} else
		*oldlenp = l;

	splx(s);

	return (error);
}

int
fill_prlist(void *oldp, size_t *oldlenp, size_t ol)
{
	int error = 0, s;
	struct nd_prefix *pr;
	char *p = NULL, *ps = NULL;
	char *pe = NULL;
	size_t l;

	s = splsoftnet();

	if (oldp) {
		ps = p = (char *)oldp;
		pe = (char *)oldp + *oldlenp;
	}
	l = 0;

	LIST_FOREACH(pr, &nd_prefix, ndpr_entry) {
		u_short advrtrs;
		struct sockaddr_in6 sin6;
		struct nd_pfxrouter *pfr;
		struct in6_prefix pfx;

		if (oldp && p + sizeof(struct in6_prefix) <= pe) {
			memset(&pfx, 0, sizeof(pfx));
			ps = p;

			pfx.prefix = pr->ndpr_prefix;
			in6_recoverscope(&pfx.prefix,
			    &pfx.prefix.sin6_addr);
			pfx.raflags = pr->ndpr_raf;
			pfx.prefixlen = pr->ndpr_plen;
			pfx.vltime = pr->ndpr_vltime;
			pfx.pltime = pr->ndpr_pltime;
			pfx.if_index = pr->ndpr_ifp->if_index;
			if (pr->ndpr_vltime == ND6_INFINITE_LIFETIME)
				pfx.expire = 0;
			else {
				time_t maxexpire;

				/* XXX: we assume time_t is signed. */
				maxexpire = (time_t)~(1ULL <<
				    ((sizeof(maxexpire) * 8) - 1));
				if (pr->ndpr_vltime <
				    maxexpire - pr->ndpr_lastupdate) {
					pfx.expire = pr->ndpr_lastupdate +
						pr->ndpr_vltime;
				} else
					pfx.expire = maxexpire;
			}
			pfx.refcnt = pr->ndpr_refcnt;
			pfx.flags = pr->ndpr_stateflags;
			pfx.origin = PR_ORIG_RA;

			p += sizeof(pfx); l += sizeof(pfx);

			advrtrs = 0;
			LIST_FOREACH(pfr, &pr->ndpr_advrtrs, pfr_entry) {
				if (p + sizeof(sin6) > pe) {
					advrtrs++;
					continue;
				}
				bzero(&sin6, sizeof(sin6));
				sin6.sin6_family = AF_INET6;
				sin6.sin6_len = sizeof(struct sockaddr_in6);
				in6_recoverscope(&sin6, &pfr->router->rtaddr);
				advrtrs++;
				memcpy(p, &sin6, sizeof(sin6));
				p += sizeof(sin6);
				l += sizeof(sin6);
			}
			pfx.advrtrs = advrtrs;
			memcpy(ps, &pfx, sizeof(pfx));
		}
		else {
			l += sizeof(pfx);
			advrtrs = 0;
			LIST_FOREACH(pfr, &pr->ndpr_advrtrs, pfr_entry) {
				advrtrs++;
				l += sizeof(sin6);
			}
		}
	}

	if (oldp) {
		*oldlenp = l;	/* (caddr_t)d - (caddr_t)oldp */
		if (l > ol)
			error = ENOMEM;
	} else
		*oldlenp = l;

	splx(s);

	return (error);
}