summaryrefslogtreecommitdiffstats
path: root/sys/netinet6/ip6_mroute.c
blob: a22111010db3d0bc4f61795f1c64a16fe9129866 (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
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
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
/*-
 * Copyright (C) 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_mroute.c,v 1.58 2001/12/18 02:36:31 itojun Exp $
 */

/*-
 * Copyright (c) 1989 Stephen Deering
 * Copyright (c) 1992, 1993
 *      The Regents of the University of California.  All rights reserved.
 *
 * This code is derived from software contributed to Berkeley by
 * Stephen Deering of Stanford University.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 *	@(#)ip_mroute.c	8.2 (Berkeley) 11/15/93
 *	BSDI ip_mroute.c,v 2.10 1996/11/14 00:29:52 jch Exp
 */

/*
 * IP multicast forwarding procedures
 *
 * Written by David Waitzman, BBN Labs, August 1988.
 * Modified by Steve Deering, Stanford, February 1989.
 * Modified by Mark J. Steiglitz, Stanford, May, 1991
 * Modified by Van Jacobson, LBL, January 1993
 * Modified by Ajit Thyagarajan, PARC, August 1993
 * Modified by Bill Fenner, PARC, April 1994
 *
 * MROUTING Revision: 3.5.1.2 + PIM-SMv2 (pimd) Support
 */

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

#include "opt_inet6.h"

#include <sys/param.h>
#include <sys/callout.h>
#include <sys/errno.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/module.h>
#include <sys/domain.h>
#include <sys/protosw.h>
#include <sys/signalvar.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/sockio.h>
#include <sys/sx.h>
#include <sys/sysctl.h>
#include <sys/syslog.h>
#include <sys/systm.h>
#include <sys/time.h>

#include <net/if.h>
#include <net/if_types.h>
#include <net/raw_cb.h>
#include <net/vnet.h>

#include <netinet/in.h>
#include <netinet/in_var.h>
#include <netinet/icmp6.h>
#include <netinet/ip_encap.h>

#include <netinet/ip6.h>
#include <netinet6/ip6_var.h>
#include <netinet6/scope6_var.h>
#include <netinet6/nd6.h>
#include <netinet6/ip6_mroute.h>
#include <netinet6/ip6protosw.h>
#include <netinet6/pim6.h>
#include <netinet6/pim6_var.h>

static MALLOC_DEFINE(M_MRTABLE6, "mf6c", "multicast forwarding cache entry");

/* XXX: this is a very common idiom; move to <sys/mbuf.h> ? */
#define M_HASCL(m) ((m)->m_flags & M_EXT)

static int	ip6_mdq(struct mbuf *, struct ifnet *, struct mf6c *);
static void	phyint_send(struct ip6_hdr *, struct mif6 *, struct mbuf *);
static int	register_send(struct ip6_hdr *, struct mif6 *, struct mbuf *);
static int	set_pim6(int *);
static int	socket_send(struct socket *, struct mbuf *,
		    struct sockaddr_in6 *);

extern int in6_mcast_loop;
extern struct domain inet6domain;

static const struct encaptab *pim6_encap_cookie;
static const struct ip6protosw in6_pim_protosw = {
	.pr_type =		SOCK_RAW,
	.pr_domain =		&inet6domain,
	.pr_protocol =		IPPROTO_PIM,
	.pr_flags =		PR_ATOMIC|PR_ADDR|PR_LASTHDR,
	.pr_input =		pim6_input,
	.pr_output =		rip6_output,
	.pr_ctloutput =		rip6_ctloutput,
	.pr_usrreqs =		&rip6_usrreqs
};
static int pim6_encapcheck(const struct mbuf *, int, int, void *);

static VNET_DEFINE(int, ip6_mrouter_ver) = 0;
#define	V_ip6_mrouter_ver	VNET(ip6_mrouter_ver)

SYSCTL_DECL(_net_inet6);
SYSCTL_DECL(_net_inet6_ip6);
static SYSCTL_NODE(_net_inet6, IPPROTO_PIM, pim, CTLFLAG_RW, 0, "PIM");

static struct mrt6stat mrt6stat;
SYSCTL_STRUCT(_net_inet6_ip6, OID_AUTO, mrt6stat, CTLFLAG_RW,
    &mrt6stat, mrt6stat,
    "Multicast Routing Statistics (struct mrt6stat, netinet6/ip6_mroute.h)");

#define NO_RTE_FOUND	0x1
#define RTE_FOUND	0x2

static struct mtx mrouter6_mtx;
#define	MROUTER6_LOCK()		mtx_lock(&mrouter6_mtx)
#define	MROUTER6_UNLOCK()	mtx_unlock(&mrouter6_mtx)
#define	MROUTER6_LOCK_ASSERT()	do {					\
	mtx_assert(&mrouter6_mtx, MA_OWNED);				\
	NET_ASSERT_GIANT();						\
} while (0)
#define	MROUTER6_LOCK_INIT()	\
	mtx_init(&mrouter6_mtx, "IPv6 multicast forwarding", NULL, MTX_DEF)
#define	MROUTER6_LOCK_DESTROY()	mtx_destroy(&mrouter6_mtx)

static struct mf6c *mf6ctable[MF6CTBLSIZ];
SYSCTL_OPAQUE(_net_inet6_ip6, OID_AUTO, mf6ctable, CTLFLAG_RD,
    &mf6ctable, sizeof(mf6ctable), "S,*mf6ctable[MF6CTBLSIZ]",
    "IPv6 Multicast Forwarding Table (struct *mf6ctable[MF6CTBLSIZ], "
    "netinet6/ip6_mroute.h)");

static struct mtx mfc6_mtx;
#define	MFC6_LOCK()		mtx_lock(&mfc6_mtx)
#define	MFC6_UNLOCK()		mtx_unlock(&mfc6_mtx)
#define	MFC6_LOCK_ASSERT()	do {					\
	mtx_assert(&mfc6_mtx, MA_OWNED);				\
	NET_ASSERT_GIANT();						\
} while (0)
#define	MFC6_LOCK_INIT()		\
	mtx_init(&mfc6_mtx, "IPv6 multicast forwarding cache", NULL, MTX_DEF)
#define	MFC6_LOCK_DESTROY()	mtx_destroy(&mfc6_mtx)

static u_char n6expire[MF6CTBLSIZ];

static struct mif6 mif6table[MAXMIFS];
SYSCTL_OPAQUE(_net_inet6_ip6, OID_AUTO, mif6table, CTLFLAG_RD,
    &mif6table, sizeof(mif6table), "S,mif6[MAXMIFS]",
    "IPv6 Multicast Interfaces (struct mif6[MAXMIFS], netinet6/ip6_mroute.h)");

static struct mtx mif6_mtx;
#define	MIF6_LOCK()		mtx_lock(&mif6_mtx)
#define	MIF6_UNLOCK()		mtx_unlock(&mif6_mtx)
#define	MIF6_LOCK_ASSERT()	mtx_assert(&mif6_mtx, MA_OWNED)
#define	MIF6_LOCK_INIT()	\
	mtx_init(&mif6_mtx, "IPv6 multicast interfaces", NULL, MTX_DEF)
#define	MIF6_LOCK_DESTROY()	mtx_destroy(&mif6_mtx)

#ifdef MRT6DEBUG
static VNET_DEFINE(u_int, mrt6debug) = 0;	/* debug level */
#define	V_mrt6debug		VNET(mrt6debug)
#define DEBUG_MFC	0x02
#define DEBUG_FORWARD	0x04
#define DEBUG_EXPIRE	0x08
#define DEBUG_XMIT	0x10
#define DEBUG_REG	0x20
#define DEBUG_PIM	0x40
#endif

static void	expire_upcalls(void *);
#define	EXPIRE_TIMEOUT	(hz / 4)	/* 4x / second */
#define	UPCALL_EXPIRE	6		/* number of timeouts */

/*
 * XXX TODO: maintain a count to if_allmulti() calls in struct ifnet.
 */

/*
 * 'Interfaces' associated with decapsulator (so we can tell
 * packets that went through it from ones that get reflected
 * by a broken gateway).  Different from IPv4 register_if,
 * these interfaces are linked into the system ifnet list,
 * because per-interface IPv6 statistics are maintained in
 * ifp->if_afdata.  But it does not have any routes point
 * to them.  I.e., packets can't be sent this way.  They
 * only exist as a placeholder for multicast source
 * verification.
 */
static struct ifnet *multicast_register_if6;

#define ENCAP_HOPS 64

/*
 * Private variables.
 */
static mifi_t nummifs = 0;
static mifi_t reg_mif_num = (mifi_t)-1;

static struct pim6stat pim6stat;
SYSCTL_STRUCT(_net_inet6_pim, PIM6CTL_STATS, stats, CTLFLAG_RW,
    &pim6stat, pim6stat,
    "PIM Statistics (struct pim6stat, netinet6/pim_var.h)");

static VNET_DEFINE(int, pim6);
#define	V_pim6		VNET(pim6)

/*
 * Hash function for a source, group entry
 */
#define MF6CHASH(a, g) MF6CHASHMOD((a).s6_addr32[0] ^ (a).s6_addr32[1] ^ \
				   (a).s6_addr32[2] ^ (a).s6_addr32[3] ^ \
				   (g).s6_addr32[0] ^ (g).s6_addr32[1] ^ \
				   (g).s6_addr32[2] ^ (g).s6_addr32[3])

/*
 * Find a route for a given origin IPv6 address and Multicast group address.
 */
#define MF6CFIND(o, g, rt) do { \
	struct mf6c *_rt = mf6ctable[MF6CHASH(o,g)]; \
	rt = NULL; \
	mrt6stat.mrt6s_mfc_lookups++; \
	while (_rt) { \
		if (IN6_ARE_ADDR_EQUAL(&_rt->mf6c_origin.sin6_addr, &(o)) && \
		    IN6_ARE_ADDR_EQUAL(&_rt->mf6c_mcastgrp.sin6_addr, &(g)) && \
		    (_rt->mf6c_stall == NULL)) { \
			rt = _rt; \
			break; \
		} \
		_rt = _rt->mf6c_next; \
	} \
	if (rt == NULL) { \
		mrt6stat.mrt6s_mfc_misses++; \
	} \
} while (/*CONSTCOND*/ 0)

/*
 * Macros to compute elapsed time efficiently
 * Borrowed from Van Jacobson's scheduling code
 * XXX: replace with timersub() ?
 */
#define TV_DELTA(a, b, delta) do { \
	    int xxs; \
		\
	    delta = (a).tv_usec - (b).tv_usec; \
	    if ((xxs = (a).tv_sec - (b).tv_sec)) { \
	       switch (xxs) { \
		      case 2: \
			  delta += 1000000; \
			      /* FALLTHROUGH */ \
		      case 1: \
			  delta += 1000000; \
			  break; \
		      default: \
			  delta += (1000000 * xxs); \
	       } \
	    } \
} while (/*CONSTCOND*/ 0)

/* XXX: replace with timercmp(a, b, <) ? */
#define TV_LT(a, b) (((a).tv_usec < (b).tv_usec && \
	      (a).tv_sec <= (b).tv_sec) || (a).tv_sec < (b).tv_sec)

#ifdef UPCALL_TIMING
#define UPCALL_MAX	50
static u_long upcall_data[UPCALL_MAX + 1];
static void collate();
#endif /* UPCALL_TIMING */

static int ip6_mrouter_init(struct socket *, int, int);
static int add_m6fc(struct mf6cctl *);
static int add_m6if(struct mif6ctl *);
static int del_m6fc(struct mf6cctl *);
static int del_m6if(mifi_t *);
static int del_m6if_locked(mifi_t *);
static int get_mif6_cnt(struct sioc_mif_req6 *);
static int get_sg_cnt(struct sioc_sg_req6 *);

static struct callout expire_upcalls_ch;

int X_ip6_mforward(struct ip6_hdr *, struct ifnet *, struct mbuf *);
int X_ip6_mrouter_done(void);
int X_ip6_mrouter_set(struct socket *, struct sockopt *);
int X_ip6_mrouter_get(struct socket *, struct sockopt *);
int X_mrt6_ioctl(u_long, caddr_t);

/*
 * Handle MRT setsockopt commands to modify the multicast routing tables.
 */
int
X_ip6_mrouter_set(struct socket *so, struct sockopt *sopt)
{
	int error = 0;
	int optval;
	struct mif6ctl mifc;
	struct mf6cctl mfcc;
	mifi_t mifi;

	if (so != V_ip6_mrouter && sopt->sopt_name != MRT6_INIT)
		return (EACCES);

	switch (sopt->sopt_name) {
	case MRT6_INIT:
#ifdef MRT6_OINIT
	case MRT6_OINIT:
#endif
		error = sooptcopyin(sopt, &optval, sizeof(optval),
		    sizeof(optval));
		if (error)
			break;
		error = ip6_mrouter_init(so, optval, sopt->sopt_name);
		break;
	case MRT6_DONE:
		error = X_ip6_mrouter_done();
		break;
	case MRT6_ADD_MIF:
		error = sooptcopyin(sopt, &mifc, sizeof(mifc), sizeof(mifc));
		if (error)
			break;
		error = add_m6if(&mifc);
		break;
	case MRT6_ADD_MFC:
		error = sooptcopyin(sopt, &mfcc, sizeof(mfcc), sizeof(mfcc));
		if (error)
			break;
		error = add_m6fc(&mfcc);
		break;
	case MRT6_DEL_MFC:
		error = sooptcopyin(sopt, &mfcc, sizeof(mfcc), sizeof(mfcc));
		if (error)
			break;
		error = del_m6fc(&mfcc);
		break;
	case MRT6_DEL_MIF:
		error = sooptcopyin(sopt, &mifi, sizeof(mifi), sizeof(mifi));
		if (error)
			break;
		error = del_m6if(&mifi);
		break;
	case MRT6_PIM:
		error = sooptcopyin(sopt, &optval, sizeof(optval),
		    sizeof(optval));
		if (error)
			break;
		error = set_pim6(&optval);
		break;
	default:
		error = EOPNOTSUPP;
		break;
	}

	return (error);
}

/*
 * Handle MRT getsockopt commands
 */
int
X_ip6_mrouter_get(struct socket *so, struct sockopt *sopt)
{
	int error = 0;

	if (so != V_ip6_mrouter)
		return (EACCES);

	switch (sopt->sopt_name) {
		case MRT6_PIM:
			error = sooptcopyout(sopt, &V_pim6, sizeof(V_pim6));
			break;
	}
	return (error);
}

/*
 * Handle ioctl commands to obtain information from the cache
 */
int
X_mrt6_ioctl(u_long cmd, caddr_t data)
{
	int ret;

	ret = EINVAL;

	switch (cmd) {
	case SIOCGETSGCNT_IN6:
		ret = get_sg_cnt((struct sioc_sg_req6 *)data);
		break;

	case SIOCGETMIFCNT_IN6:
		ret = get_mif6_cnt((struct sioc_mif_req6 *)data);
		break;

	default:
		break;
	}

	return (ret);
}

/*
 * returns the packet, byte, rpf-failure count for the source group provided
 */
static int
get_sg_cnt(struct sioc_sg_req6 *req)
{
	struct mf6c *rt;
	int ret;

	ret = 0;

	MFC6_LOCK();

	MF6CFIND(req->src.sin6_addr, req->grp.sin6_addr, rt);
	if (rt == NULL) {
		ret = ESRCH;
	} else {
		req->pktcnt = rt->mf6c_pkt_cnt;
		req->bytecnt = rt->mf6c_byte_cnt;
		req->wrong_if = rt->mf6c_wrong_if;
	}

	MFC6_UNLOCK();

	return (ret);
}

/*
 * returns the input and output packet and byte counts on the mif provided
 */
static int
get_mif6_cnt(struct sioc_mif_req6 *req)
{
	mifi_t mifi;
	int ret;

	ret = 0;
	mifi = req->mifi;

	MIF6_LOCK();

	if (mifi >= nummifs) {
		ret = EINVAL;
	} else {
		req->icount = mif6table[mifi].m6_pkt_in;
		req->ocount = mif6table[mifi].m6_pkt_out;
		req->ibytes = mif6table[mifi].m6_bytes_in;
		req->obytes = mif6table[mifi].m6_bytes_out;
	}

	MIF6_UNLOCK();

	return (ret);
}

static int
set_pim6(int *i)
{
	if ((*i != 1) && (*i != 0))
		return (EINVAL);

	V_pim6 = *i;

	return (0);
}

/*
 * Enable multicast routing
 */
static int
ip6_mrouter_init(struct socket *so, int v, int cmd)
{

#ifdef MRT6DEBUG
	if (V_mrt6debug)
		log(LOG_DEBUG,
		    "ip6_mrouter_init: so_type = %d, pr_protocol = %d\n",
		    so->so_type, so->so_proto->pr_protocol);
#endif

	if (so->so_type != SOCK_RAW ||
	    so->so_proto->pr_protocol != IPPROTO_ICMPV6)
		return (EOPNOTSUPP);

	if (v != 1)
		return (ENOPROTOOPT);

	MROUTER6_LOCK();

	if (V_ip6_mrouter != NULL) {
		MROUTER6_UNLOCK();
		return (EADDRINUSE);
	}

	V_ip6_mrouter = so;
	V_ip6_mrouter_ver = cmd;

	bzero((caddr_t)mf6ctable, sizeof(mf6ctable));
	bzero((caddr_t)n6expire, sizeof(n6expire));

	V_pim6 = 0;/* used for stubbing out/in pim stuff */

	callout_init(&expire_upcalls_ch, 0);
	callout_reset(&expire_upcalls_ch, EXPIRE_TIMEOUT,
	    expire_upcalls, NULL);

	MROUTER6_UNLOCK();

#ifdef MRT6DEBUG
	if (V_mrt6debug)
		log(LOG_DEBUG, "ip6_mrouter_init\n");
#endif

	return (0);
}

/*
 * Disable IPv6 multicast forwarding.
 */
int
X_ip6_mrouter_done(void)
{
	mifi_t mifi;
	int i;
	struct mf6c *rt;
	struct rtdetq *rte;

	MROUTER6_LOCK();

	if (V_ip6_mrouter == NULL) {
		MROUTER6_UNLOCK();
		return (EINVAL);
	}

	/*
	 * For each phyint in use, disable promiscuous reception of all IPv6
	 * multicasts.
	 */
	for (mifi = 0; mifi < nummifs; mifi++) {
		if (mif6table[mifi].m6_ifp &&
		    !(mif6table[mifi].m6_flags & MIFF_REGISTER)) {
			if_allmulti(mif6table[mifi].m6_ifp, 0);
		}
	}
	bzero((caddr_t)mif6table, sizeof(mif6table));
	nummifs = 0;

	V_pim6 = 0; /* used to stub out/in pim specific code */

	callout_stop(&expire_upcalls_ch);

	/*
	 * Free all multicast forwarding cache entries.
	 */
	MFC6_LOCK();
	for (i = 0; i < MF6CTBLSIZ; i++) {
		rt = mf6ctable[i];
		while (rt) {
			struct mf6c *frt;

			for (rte = rt->mf6c_stall; rte != NULL; ) {
				struct rtdetq *n = rte->next;

				m_free(rte->m);
				free(rte, M_MRTABLE6);
				rte = n;
			}
			frt = rt;
			rt = rt->mf6c_next;
			free(frt, M_MRTABLE6);
		}
	}
	bzero((caddr_t)mf6ctable, sizeof(mf6ctable));
	MFC6_UNLOCK();

	/*
	 * Reset register interface
	 */
	if (reg_mif_num != (mifi_t)-1 && multicast_register_if6 != NULL) {
		if_detach(multicast_register_if6);
		if_free(multicast_register_if6);
		reg_mif_num = (mifi_t)-1;
		multicast_register_if6 = NULL;
	}

	V_ip6_mrouter = NULL;
	V_ip6_mrouter_ver = 0;

	MROUTER6_UNLOCK();

#ifdef MRT6DEBUG
	if (V_mrt6debug)
		log(LOG_DEBUG, "ip6_mrouter_done\n");
#endif

	return (0);
}

static struct sockaddr_in6 sin6 = { sizeof(sin6), AF_INET6 };

/*
 * Add a mif to the mif table
 */
static int
add_m6if(struct mif6ctl *mifcp)
{
	struct mif6 *mifp;
	struct ifnet *ifp;
	int error;

	MIF6_LOCK();

	if (mifcp->mif6c_mifi >= MAXMIFS) {
		MIF6_UNLOCK();
		return (EINVAL);
	}
	mifp = mif6table + mifcp->mif6c_mifi;
	if (mifp->m6_ifp != NULL) {
		MIF6_UNLOCK();
		return (EADDRINUSE); /* XXX: is it appropriate? */
	}
	if (mifcp->mif6c_pifi == 0 || mifcp->mif6c_pifi > V_if_index) {
		MIF6_UNLOCK();
		return (ENXIO);
	}

	ifp = ifnet_byindex(mifcp->mif6c_pifi);

	if (mifcp->mif6c_flags & MIFF_REGISTER) {
		if (reg_mif_num == (mifi_t)-1) {
			ifp = if_alloc(IFT_OTHER);

			if_initname(ifp, "register_mif", 0);
			ifp->if_flags |= IFF_LOOPBACK;
			if_attach(ifp);
			multicast_register_if6 = ifp;
			reg_mif_num = mifcp->mif6c_mifi;
			/*
			 * it is impossible to guess the ifindex of the
			 * register interface.  So mif6c_pifi is automatically
			 * calculated.
			 */
			mifcp->mif6c_pifi = ifp->if_index;
		} else {
			ifp = multicast_register_if6;
		}
	} else {
		/* Make sure the interface supports multicast */
		if ((ifp->if_flags & IFF_MULTICAST) == 0) {
			MIF6_UNLOCK();
			return (EOPNOTSUPP);
		}

		error = if_allmulti(ifp, 1);
		if (error) {
			MIF6_UNLOCK();
			return (error);
		}
	}

	mifp->m6_flags     = mifcp->mif6c_flags;
	mifp->m6_ifp       = ifp;

	/* initialize per mif pkt counters */
	mifp->m6_pkt_in    = 0;
	mifp->m6_pkt_out   = 0;
	mifp->m6_bytes_in  = 0;
	mifp->m6_bytes_out = 0;

	/* Adjust nummifs up if the mifi is higher than nummifs */
	if (nummifs <= mifcp->mif6c_mifi)
		nummifs = mifcp->mif6c_mifi + 1;

	MIF6_UNLOCK();

#ifdef MRT6DEBUG
	if (V_mrt6debug)
		log(LOG_DEBUG,
		    "add_mif #%d, phyint %s\n",
		    mifcp->mif6c_mifi,
		    ifp->if_xname);
#endif

	return (0);
}

/*
 * Delete a mif from the mif table
 */
static int
del_m6if_locked(mifi_t *mifip)
{
	struct mif6 *mifp = mif6table + *mifip;
	mifi_t mifi;
	struct ifnet *ifp;

	MIF6_LOCK_ASSERT();

	if (*mifip >= nummifs)
		return (EINVAL);
	if (mifp->m6_ifp == NULL)
		return (EINVAL);

	if (!(mifp->m6_flags & MIFF_REGISTER)) {
		/* XXX: TODO: Maintain an ALLMULTI refcount in struct ifnet. */
		ifp = mifp->m6_ifp;
		if_allmulti(ifp, 0);
	} else {
		if (reg_mif_num != (mifi_t)-1 &&
		    multicast_register_if6 != NULL) {
			if_detach(multicast_register_if6);
			if_free(multicast_register_if6);
			reg_mif_num = (mifi_t)-1;
			multicast_register_if6 = NULL;
		}
	}

	bzero((caddr_t)mifp, sizeof(*mifp));

	/* Adjust nummifs down */
	for (mifi = nummifs; mifi > 0; mifi--)
		if (mif6table[mifi - 1].m6_ifp)
			break;
	nummifs = mifi;

#ifdef MRT6DEBUG
	if (V_mrt6debug)
		log(LOG_DEBUG, "del_m6if %d, nummifs %d\n", *mifip, nummifs);
#endif

	return (0);
}

static int
del_m6if(mifi_t *mifip)
{
	int cc;

	MIF6_LOCK();
	cc = del_m6if_locked(mifip);
	MIF6_UNLOCK();

	return (cc);
}

/*
 * Add an mfc entry
 */
static int
add_m6fc(struct mf6cctl *mfccp)
{
	struct mf6c *rt;
	u_long hash;
	struct rtdetq *rte;
	u_short nstl;
	char ip6bufo[INET6_ADDRSTRLEN], ip6bufg[INET6_ADDRSTRLEN];

	MFC6_LOCK();

	MF6CFIND(mfccp->mf6cc_origin.sin6_addr,
		 mfccp->mf6cc_mcastgrp.sin6_addr, rt);

	/* If an entry already exists, just update the fields */
	if (rt) {
#ifdef MRT6DEBUG
		if (V_mrt6debug & DEBUG_MFC) {
		    log(LOG_DEBUG,
			"add_m6fc no upcall h %d o %s g %s p %x\n",
			ip6_sprintf(ip6bufo, &mfccp->mf6cc_origin.sin6_addr),
			ip6_sprintf(ip6bufg, &mfccp->mf6cc_mcastgrp.sin6_addr),
			mfccp->mf6cc_parent);
		}
#endif

		rt->mf6c_parent = mfccp->mf6cc_parent;
		rt->mf6c_ifset = mfccp->mf6cc_ifset;

		MFC6_UNLOCK();
		return (0);
	}

	/*
	 * Find the entry for which the upcall was made and update
	 */
	hash = MF6CHASH(mfccp->mf6cc_origin.sin6_addr,
			mfccp->mf6cc_mcastgrp.sin6_addr);
	for (rt = mf6ctable[hash], nstl = 0; rt; rt = rt->mf6c_next) {
		if (IN6_ARE_ADDR_EQUAL(&rt->mf6c_origin.sin6_addr,
				       &mfccp->mf6cc_origin.sin6_addr) &&
		    IN6_ARE_ADDR_EQUAL(&rt->mf6c_mcastgrp.sin6_addr,
				       &mfccp->mf6cc_mcastgrp.sin6_addr) &&
		    (rt->mf6c_stall != NULL)) {

			if (nstl++)
				log(LOG_ERR,
				    "add_m6fc: %s o %s g %s p %x dbx %p\n",
				    "multiple kernel entries",
				    ip6_sprintf(ip6bufo,
					    &mfccp->mf6cc_origin.sin6_addr),
				    ip6_sprintf(ip6bufg,
					    &mfccp->mf6cc_mcastgrp.sin6_addr),
				    mfccp->mf6cc_parent, rt->mf6c_stall);

#ifdef MRT6DEBUG
			if (V_mrt6debug & DEBUG_MFC)
				log(LOG_DEBUG,
				    "add_m6fc o %s g %s p %x dbg %x\n",
				    ip6_sprintf(ip6bufo,
					    &mfccp->mf6cc_origin.sin6_addr),
				    ip6_sprintf(ip6bufg,
					    &mfccp->mf6cc_mcastgrp.sin6_addr),
				    mfccp->mf6cc_parent, rt->mf6c_stall);
#endif

			rt->mf6c_origin     = mfccp->mf6cc_origin;
			rt->mf6c_mcastgrp   = mfccp->mf6cc_mcastgrp;
			rt->mf6c_parent     = mfccp->mf6cc_parent;
			rt->mf6c_ifset	    = mfccp->mf6cc_ifset;
			/* initialize pkt counters per src-grp */
			rt->mf6c_pkt_cnt    = 0;
			rt->mf6c_byte_cnt   = 0;
			rt->mf6c_wrong_if   = 0;

			rt->mf6c_expire = 0;	/* Don't clean this guy up */
			n6expire[hash]--;

			/* free packets Qed at the end of this entry */
			for (rte = rt->mf6c_stall; rte != NULL; ) {
				struct rtdetq *n = rte->next;
				ip6_mdq(rte->m, rte->ifp, rt);
				m_freem(rte->m);
#ifdef UPCALL_TIMING
				collate(&(rte->t));
#endif /* UPCALL_TIMING */
				free(rte, M_MRTABLE6);
				rte = n;
			}
			rt->mf6c_stall = NULL;
		}
	}

	/*
	 * It is possible that an entry is being inserted without an upcall
	 */
	if (nstl == 0) {
#ifdef MRT6DEBUG
		if (V_mrt6debug & DEBUG_MFC)
		    log(LOG_DEBUG,
			"add_mfc no upcall h %d o %s g %s p %x\n",
			hash,
			ip6_sprintf(ip6bufo, &mfccp->mf6cc_origin.sin6_addr),
			ip6_sprintf(ip6bufg, &mfccp->mf6cc_mcastgrp.sin6_addr),
			mfccp->mf6cc_parent);
#endif

		for (rt = mf6ctable[hash]; rt; rt = rt->mf6c_next) {

			if (IN6_ARE_ADDR_EQUAL(&rt->mf6c_origin.sin6_addr,
					       &mfccp->mf6cc_origin.sin6_addr)&&
			    IN6_ARE_ADDR_EQUAL(&rt->mf6c_mcastgrp.sin6_addr,
					       &mfccp->mf6cc_mcastgrp.sin6_addr)) {

				rt->mf6c_origin     = mfccp->mf6cc_origin;
				rt->mf6c_mcastgrp   = mfccp->mf6cc_mcastgrp;
				rt->mf6c_parent     = mfccp->mf6cc_parent;
				rt->mf6c_ifset	    = mfccp->mf6cc_ifset;
				/* initialize pkt counters per src-grp */
				rt->mf6c_pkt_cnt    = 0;
				rt->mf6c_byte_cnt   = 0;
				rt->mf6c_wrong_if   = 0;

				if (rt->mf6c_expire)
					n6expire[hash]--;
				rt->mf6c_expire	   = 0;
			}
		}
		if (rt == NULL) {
			/* no upcall, so make a new entry */
			rt = (struct mf6c *)malloc(sizeof(*rt), M_MRTABLE6,
						  M_NOWAIT);
			if (rt == NULL) {
				MFC6_UNLOCK();
				return (ENOBUFS);
			}

			/* insert new entry at head of hash chain */
			rt->mf6c_origin     = mfccp->mf6cc_origin;
			rt->mf6c_mcastgrp   = mfccp->mf6cc_mcastgrp;
			rt->mf6c_parent     = mfccp->mf6cc_parent;
			rt->mf6c_ifset	    = mfccp->mf6cc_ifset;
			/* initialize pkt counters per src-grp */
			rt->mf6c_pkt_cnt    = 0;
			rt->mf6c_byte_cnt   = 0;
			rt->mf6c_wrong_if   = 0;
			rt->mf6c_expire     = 0;
			rt->mf6c_stall = NULL;

			/* link into table */
			rt->mf6c_next  = mf6ctable[hash];
			mf6ctable[hash] = rt;
		}
	}

	MFC6_UNLOCK();
	return (0);
}

#ifdef UPCALL_TIMING
/*
 * collect delay statistics on the upcalls
 */
static void
collate(struct timeval *t)
{
	u_long d;
	struct timeval tp;
	u_long delta;

	GET_TIME(tp);

	if (TV_LT(*t, tp))
	{
		TV_DELTA(tp, *t, delta);

		d = delta >> 10;
		if (d > UPCALL_MAX)
			d = UPCALL_MAX;

		++upcall_data[d];
	}
}
#endif /* UPCALL_TIMING */

/*
 * Delete an mfc entry
 */
static int
del_m6fc(struct mf6cctl *mfccp)
{
	struct sockaddr_in6	origin;
	struct sockaddr_in6	mcastgrp;
	struct mf6c		*rt;
	struct mf6c		**nptr;
	u_long		hash;

	origin = mfccp->mf6cc_origin;
	mcastgrp = mfccp->mf6cc_mcastgrp;
	hash = MF6CHASH(origin.sin6_addr, mcastgrp.sin6_addr);

#ifdef MRT6DEBUG
	if (V_mrt6debug & DEBUG_MFC) {
		char ip6bufo[INET6_ADDRSTRLEN], ip6bufg[INET6_ADDRSTRLEN];
		log(LOG_DEBUG,"del_m6fc orig %s mcastgrp %s\n",
		    ip6_sprintf(ip6bufo, &origin.sin6_addr),
		    ip6_sprintf(ip6bufg, &mcastgrp.sin6_addr));
	}
#endif

	MFC6_LOCK();

	nptr = &mf6ctable[hash];
	while ((rt = *nptr) != NULL) {
		if (IN6_ARE_ADDR_EQUAL(&origin.sin6_addr,
				       &rt->mf6c_origin.sin6_addr) &&
		    IN6_ARE_ADDR_EQUAL(&mcastgrp.sin6_addr,
				       &rt->mf6c_mcastgrp.sin6_addr) &&
		    rt->mf6c_stall == NULL)
			break;

		nptr = &rt->mf6c_next;
	}
	if (rt == NULL) {
		MFC6_UNLOCK();
		return (EADDRNOTAVAIL);
	}

	*nptr = rt->mf6c_next;
	free(rt, M_MRTABLE6);

	MFC6_UNLOCK();

	return (0);
}

static int
socket_send(struct socket *s, struct mbuf *mm, struct sockaddr_in6 *src)
{

	if (s) {
		if (sbappendaddr(&s->so_rcv,
				 (struct sockaddr *)src,
				 mm, (struct mbuf *)0) != 0) {
			sorwakeup(s);
			return (0);
		}
	}
	m_freem(mm);
	return (-1);
}

/*
 * IPv6 multicast forwarding function. This function assumes that the packet
 * pointed to by "ip6" has arrived on (or is about to be sent to) the interface
 * pointed to by "ifp", and the packet is to be relayed to other networks
 * that have members of the packet's destination IPv6 multicast group.
 *
 * The packet is returned unscathed to the caller, unless it is
 * erroneous, in which case a non-zero return value tells the caller to
 * discard it.
 *
 * NOTE: this implementation assumes that m->m_pkthdr.rcvif is NULL iff
 * this function is called in the originating context (i.e., not when
 * forwarding a packet from other node).  ip6_output(), which is currently the
 * only function that calls this function is called in the originating context,
 * explicitly ensures this condition.  It is caller's responsibility to ensure
 * that if this function is called from somewhere else in the originating
 * context in the future.
 */
int
X_ip6_mforward(struct ip6_hdr *ip6, struct ifnet *ifp, struct mbuf *m)
{
	struct mf6c *rt;
	struct mif6 *mifp;
	struct mbuf *mm;
	mifi_t mifi;
	char ip6bufs[INET6_ADDRSTRLEN], ip6bufd[INET6_ADDRSTRLEN];

#ifdef MRT6DEBUG
	if (V_mrt6debug & DEBUG_FORWARD)
		log(LOG_DEBUG, "ip6_mforward: src %s, dst %s, ifindex %d\n",
		    ip6_sprintf(ip6bufs, &ip6->ip6_src),
		    ip6_sprintf(ip6bufd, &ip6->ip6_dst),
		    ifp->if_index);
#endif

	/*
	 * Don't forward a packet with Hop limit of zero or one,
	 * or a packet destined to a local-only group.
	 */
	if (ip6->ip6_hlim <= 1 || IN6_IS_ADDR_MC_INTFACELOCAL(&ip6->ip6_dst) ||
	    IN6_IS_ADDR_MC_LINKLOCAL(&ip6->ip6_dst))
		return (0);
	ip6->ip6_hlim--;

	/*
	 * Source address check: do not forward packets with unspecified
	 * source. It was discussed in July 2000, on ipngwg mailing list.
	 * This is rather more serious than unicast cases, because some
	 * MLD packets can be sent with the unspecified source address
	 * (although such packets must normally set 1 to the hop limit field).
	 */
	if (IN6_IS_ADDR_UNSPECIFIED(&ip6->ip6_src)) {
		V_ip6stat.ip6s_cantforward++;
		if (V_ip6_log_time + V_ip6_log_interval < time_second) {
			V_ip6_log_time = time_second;
			log(LOG_DEBUG,
			    "cannot forward "
			    "from %s to %s nxt %d received on %s\n",
			    ip6_sprintf(ip6bufs, &ip6->ip6_src),
			    ip6_sprintf(ip6bufd, &ip6->ip6_dst),
			    ip6->ip6_nxt,
			    if_name(m->m_pkthdr.rcvif));
		}
		return (0);
	}

	MFC6_LOCK();

	/*
	 * Determine forwarding mifs from the forwarding cache table
	 */
	MF6CFIND(ip6->ip6_src, ip6->ip6_dst, rt);

	/* Entry exists, so forward if necessary */
	if (rt) {
		MFC6_UNLOCK();
		return (ip6_mdq(m, ifp, rt));
	} else {
		/*
		 * If we don't have a route for packet's origin,
		 * Make a copy of the packet &
		 * send message to routing daemon
		 */

		struct mbuf *mb0;
		struct rtdetq *rte;
		u_long hash;
/*		int i, npkts;*/
#ifdef UPCALL_TIMING
		struct timeval tp;

		GET_TIME(tp);
#endif /* UPCALL_TIMING */

		mrt6stat.mrt6s_no_route++;
#ifdef MRT6DEBUG
		if (V_mrt6debug & (DEBUG_FORWARD | DEBUG_MFC))
			log(LOG_DEBUG, "ip6_mforward: no rte s %s g %s\n",
			    ip6_sprintf(ip6bufs, &ip6->ip6_src),
			    ip6_sprintf(ip6bufd, &ip6->ip6_dst));
#endif

		/*
		 * Allocate mbufs early so that we don't do extra work if we
		 * are just going to fail anyway.
		 */
		rte = (struct rtdetq *)malloc(sizeof(*rte), M_MRTABLE6,
					      M_NOWAIT);
		if (rte == NULL) {
			MFC6_UNLOCK();
			return (ENOBUFS);
		}
		mb0 = m_copy(m, 0, M_COPYALL);
		/*
		 * Pullup packet header if needed before storing it,
		 * as other references may modify it in the meantime.
		 */
		if (mb0 &&
		    (M_HASCL(mb0) || mb0->m_len < sizeof(struct ip6_hdr)))
			mb0 = m_pullup(mb0, sizeof(struct ip6_hdr));
		if (mb0 == NULL) {
			free(rte, M_MRTABLE6);
			MFC6_UNLOCK();
			return (ENOBUFS);
		}

		/* is there an upcall waiting for this packet? */
		hash = MF6CHASH(ip6->ip6_src, ip6->ip6_dst);
		for (rt = mf6ctable[hash]; rt; rt = rt->mf6c_next) {
			if (IN6_ARE_ADDR_EQUAL(&ip6->ip6_src,
					       &rt->mf6c_origin.sin6_addr) &&
			    IN6_ARE_ADDR_EQUAL(&ip6->ip6_dst,
					       &rt->mf6c_mcastgrp.sin6_addr) &&
			    (rt->mf6c_stall != NULL))
				break;
		}

		if (rt == NULL) {
			struct mrt6msg *im;
#ifdef MRT6_OINIT
			struct omrt6msg *oim;
#endif

			/* no upcall, so make a new entry */
			rt = (struct mf6c *)malloc(sizeof(*rt), M_MRTABLE6,
						  M_NOWAIT);
			if (rt == NULL) {
				free(rte, M_MRTABLE6);
				m_freem(mb0);
				MFC6_UNLOCK();
				return (ENOBUFS);
			}
			/*
			 * Make a copy of the header to send to the user
			 * level process
			 */
			mm = m_copy(mb0, 0, sizeof(struct ip6_hdr));

			if (mm == NULL) {
				free(rte, M_MRTABLE6);
				m_freem(mb0);
				free(rt, M_MRTABLE6);
				MFC6_UNLOCK();
				return (ENOBUFS);
			}

			/*
			 * Send message to routing daemon
			 */
			sin6.sin6_addr = ip6->ip6_src;

			im = NULL;
#ifdef MRT6_OINIT
			oim = NULL;
#endif
			switch (V_ip6_mrouter_ver) {
#ifdef MRT6_OINIT
			case MRT6_OINIT:
				oim = mtod(mm, struct omrt6msg *);
				oim->im6_msgtype = MRT6MSG_NOCACHE;
				oim->im6_mbz = 0;
				break;
#endif
			case MRT6_INIT:
				im = mtod(mm, struct mrt6msg *);
				im->im6_msgtype = MRT6MSG_NOCACHE;
				im->im6_mbz = 0;
				break;
			default:
				free(rte, M_MRTABLE6);
				m_freem(mb0);
				free(rt, M_MRTABLE6);
				MFC6_UNLOCK();
				return (EINVAL);
			}

#ifdef MRT6DEBUG
			if (V_mrt6debug & DEBUG_FORWARD)
				log(LOG_DEBUG,
				    "getting the iif info in the kernel\n");
#endif

			for (mifp = mif6table, mifi = 0;
			     mifi < nummifs && mifp->m6_ifp != ifp;
			     mifp++, mifi++)
				;

			switch (V_ip6_mrouter_ver) {
#ifdef MRT6_OINIT
			case MRT6_OINIT:
				oim->im6_mif = mifi;
				break;
#endif
			case MRT6_INIT:
				im->im6_mif = mifi;
				break;
			}

			if (socket_send(V_ip6_mrouter, mm, &sin6) < 0) {
				log(LOG_WARNING, "ip6_mforward: ip6_mrouter "
				    "socket queue full\n");
				mrt6stat.mrt6s_upq_sockfull++;
				free(rte, M_MRTABLE6);
				m_freem(mb0);
				free(rt, M_MRTABLE6);
				MFC6_UNLOCK();
				return (ENOBUFS);
			}

			mrt6stat.mrt6s_upcalls++;

			/* insert new entry at head of hash chain */
			bzero(rt, sizeof(*rt));
			rt->mf6c_origin.sin6_family = AF_INET6;
			rt->mf6c_origin.sin6_len = sizeof(struct sockaddr_in6);
			rt->mf6c_origin.sin6_addr = ip6->ip6_src;
			rt->mf6c_mcastgrp.sin6_family = AF_INET6;
			rt->mf6c_mcastgrp.sin6_len = sizeof(struct sockaddr_in6);
			rt->mf6c_mcastgrp.sin6_addr = ip6->ip6_dst;
			rt->mf6c_expire = UPCALL_EXPIRE;
			n6expire[hash]++;
			rt->mf6c_parent = MF6C_INCOMPLETE_PARENT;

			/* link into table */
			rt->mf6c_next  = mf6ctable[hash];
			mf6ctable[hash] = rt;
			/* Add this entry to the end of the queue */
			rt->mf6c_stall = rte;
		} else {
			/* determine if q has overflowed */
			struct rtdetq **p;
			int npkts = 0;

			for (p = &rt->mf6c_stall; *p != NULL; p = &(*p)->next)
				if (++npkts > MAX_UPQ6) {
					mrt6stat.mrt6s_upq_ovflw++;
					free(rte, M_MRTABLE6);
					m_freem(mb0);
					MFC6_UNLOCK();
					return (0);
				}

			/* Add this entry to the end of the queue */
			*p = rte;
		}

		rte->next = NULL;
		rte->m = mb0;
		rte->ifp = ifp;
#ifdef UPCALL_TIMING
		rte->t = tp;
#endif /* UPCALL_TIMING */

		MFC6_UNLOCK();

		return (0);
	}
}

/*
 * Clean up cache entries if upcalls are not serviced
 * Call from the Slow Timeout mechanism, every half second.
 */
static void
expire_upcalls(void *unused)
{
	struct rtdetq *rte;
	struct mf6c *mfc, **nptr;
	int i;

	MFC6_LOCK();
	for (i = 0; i < MF6CTBLSIZ; i++) {
		if (n6expire[i] == 0)
			continue;
		nptr = &mf6ctable[i];
		while ((mfc = *nptr) != NULL) {
			rte = mfc->mf6c_stall;
			/*
			 * Skip real cache entries
			 * Make sure it wasn't marked to not expire (shouldn't happen)
			 * If it expires now
			 */
			if (rte != NULL &&
			    mfc->mf6c_expire != 0 &&
			    --mfc->mf6c_expire == 0) {
#ifdef MRT6DEBUG
				if (V_mrt6debug & DEBUG_EXPIRE) {
					char ip6bufo[INET6_ADDRSTRLEN];
					char ip6bufg[INET6_ADDRSTRLEN];
					log(LOG_DEBUG, "expire_upcalls: expiring (%s %s)\n",
					    ip6_sprintf(ip6bufo, &mfc->mf6c_origin.sin6_addr),
					    ip6_sprintf(ip6bufg, &mfc->mf6c_mcastgrp.sin6_addr));
				}
#endif
				/*
				 * drop all the packets
				 * free the mbuf with the pkt, if, timing info
				 */
				do {
					struct rtdetq *n = rte->next;
					m_freem(rte->m);
					free(rte, M_MRTABLE6);
					rte = n;
				} while (rte != NULL);
				mrt6stat.mrt6s_cache_cleanups++;
				n6expire[i]--;

				*nptr = mfc->mf6c_next;
				free(mfc, M_MRTABLE6);
			} else {
				nptr = &mfc->mf6c_next;
			}
		}
	}
	MFC6_UNLOCK();
	callout_reset(&expire_upcalls_ch, EXPIRE_TIMEOUT,
	    expire_upcalls, NULL);
}

/*
 * Packet forwarding routine once entry in the cache is made
 */
static int
ip6_mdq(struct mbuf *m, struct ifnet *ifp, struct mf6c *rt)
{
	struct ip6_hdr *ip6 = mtod(m, struct ip6_hdr *);
	mifi_t mifi, iif;
	struct mif6 *mifp;
	int plen = m->m_pkthdr.len;
	struct in6_addr src0, dst0; /* copies for local work */
	u_int32_t iszone, idzone, oszone, odzone;
	int error = 0;

/*
 * Macro to send packet on mif.  Since RSVP packets don't get counted on
 * input, they shouldn't get counted on output, so statistics keeping is
 * separate.
 */

#define MC6_SEND(ip6, mifp, m) do {				\
	if ((mifp)->m6_flags & MIFF_REGISTER)			\
		register_send((ip6), (mifp), (m));		\
	else							\
		phyint_send((ip6), (mifp), (m));		\
} while (/*CONSTCOND*/ 0)

	/*
	 * Don't forward if it didn't arrive from the parent mif
	 * for its origin.
	 */
	mifi = rt->mf6c_parent;
	if ((mifi >= nummifs) || (mif6table[mifi].m6_ifp != ifp)) {
		/* came in the wrong interface */
#ifdef MRT6DEBUG
		if (V_mrt6debug & DEBUG_FORWARD)
			log(LOG_DEBUG,
			    "wrong if: ifid %d mifi %d mififid %x\n",
			    ifp->if_index, mifi,
			    mif6table[mifi].m6_ifp->if_index);
#endif
		mrt6stat.mrt6s_wrong_if++;
		rt->mf6c_wrong_if++;
		/*
		 * If we are doing PIM processing, and we are forwarding
		 * packets on this interface, send a message to the
		 * routing daemon.
		 */
		/* have to make sure this is a valid mif */
		if (mifi < nummifs && mif6table[mifi].m6_ifp)
			if (V_pim6 && (m->m_flags & M_LOOP) == 0) {
				/*
				 * Check the M_LOOP flag to avoid an
				 * unnecessary PIM assert.
				 * XXX: M_LOOP is an ad-hoc hack...
				 */
				static struct sockaddr_in6 sin6 =
				{ sizeof(sin6), AF_INET6 };

				struct mbuf *mm;
				struct mrt6msg *im;
#ifdef MRT6_OINIT
				struct omrt6msg *oim;
#endif

				mm = m_copy(m, 0, sizeof(struct ip6_hdr));
				if (mm &&
				    (M_HASCL(mm) ||
				     mm->m_len < sizeof(struct ip6_hdr)))
					mm = m_pullup(mm, sizeof(struct ip6_hdr));
				if (mm == NULL)
					return (ENOBUFS);

#ifdef MRT6_OINIT
				oim = NULL;
#endif
				im = NULL;
				switch (V_ip6_mrouter_ver) {
#ifdef MRT6_OINIT
				case MRT6_OINIT:
					oim = mtod(mm, struct omrt6msg *);
					oim->im6_msgtype = MRT6MSG_WRONGMIF;
					oim->im6_mbz = 0;
					break;
#endif
				case MRT6_INIT:
					im = mtod(mm, struct mrt6msg *);
					im->im6_msgtype = MRT6MSG_WRONGMIF;
					im->im6_mbz = 0;
					break;
				default:
					m_freem(mm);
					return (EINVAL);
				}

				for (mifp = mif6table, iif = 0;
				     iif < nummifs && mifp &&
					     mifp->m6_ifp != ifp;
				     mifp++, iif++)
					;

				switch (V_ip6_mrouter_ver) {
#ifdef MRT6_OINIT
				case MRT6_OINIT:
					oim->im6_mif = iif;
					sin6.sin6_addr = oim->im6_src;
					break;
#endif
				case MRT6_INIT:
					im->im6_mif = iif;
					sin6.sin6_addr = im->im6_src;
					break;
				}

				mrt6stat.mrt6s_upcalls++;

				if (socket_send(V_ip6_mrouter, mm, &sin6) < 0) {
#ifdef MRT6DEBUG
					if (V_mrt6debug)
						log(LOG_WARNING, "mdq, ip6_mrouter socket queue full\n");
#endif
					++mrt6stat.mrt6s_upq_sockfull;
					return (ENOBUFS);
				}	/* if socket Q full */
			}		/* if PIM */
		return (0);
	}			/* if wrong iif */

	/* If I sourced this packet, it counts as output, else it was input. */
	if (m->m_pkthdr.rcvif == NULL) {
		/* XXX: is rcvif really NULL when output?? */
		mif6table[mifi].m6_pkt_out++;
		mif6table[mifi].m6_bytes_out += plen;
	} else {
		mif6table[mifi].m6_pkt_in++;
		mif6table[mifi].m6_bytes_in += plen;
	}
	rt->mf6c_pkt_cnt++;
	rt->mf6c_byte_cnt += plen;

	/*
	 * For each mif, forward a copy of the packet if there are group
	 * members downstream on the interface.
	 */
	src0 = ip6->ip6_src;
	dst0 = ip6->ip6_dst;
	if ((error = in6_setscope(&src0, ifp, &iszone)) != 0 ||
	    (error = in6_setscope(&dst0, ifp, &idzone)) != 0) {
		V_ip6stat.ip6s_badscope++;
		return (error);
	}
	for (mifp = mif6table, mifi = 0; mifi < nummifs; mifp++, mifi++) {
		if (IF_ISSET(mifi, &rt->mf6c_ifset)) {
			/*
			 * check if the outgoing packet is going to break
			 * a scope boundary.
			 * XXX For packets through PIM register tunnel
			 * interface, we believe a routing daemon.
			 */
			if (!(mif6table[rt->mf6c_parent].m6_flags &
			      MIFF_REGISTER) &&
			    !(mif6table[mifi].m6_flags & MIFF_REGISTER)) {
				if (in6_setscope(&src0, mif6table[mifi].m6_ifp,
				    &oszone) ||
				    in6_setscope(&dst0, mif6table[mifi].m6_ifp,
				    &odzone) ||
				    iszone != oszone ||
				    idzone != odzone) {
					V_ip6stat.ip6s_badscope++;
					continue;
				}
			}

			mifp->m6_pkt_out++;
			mifp->m6_bytes_out += plen;
			MC6_SEND(ip6, mifp, m);
		}
	}
	return (0);
}

static void
phyint_send(struct ip6_hdr *ip6, struct mif6 *mifp, struct mbuf *m)
{
	struct mbuf *mb_copy;
	struct ifnet *ifp = mifp->m6_ifp;
	int error = 0;
	u_long linkmtu;

	/*
	 * Make a new reference to the packet; make sure that
	 * the IPv6 header is actually copied, not just referenced,
	 * so that ip6_output() only scribbles on the copy.
	 */
	mb_copy = m_copy(m, 0, M_COPYALL);
	if (mb_copy &&
	    (M_HASCL(mb_copy) || mb_copy->m_len < sizeof(struct ip6_hdr)))
		mb_copy = m_pullup(mb_copy, sizeof(struct ip6_hdr));
	if (mb_copy == NULL) {
		return;
	}
	/* set MCAST flag to the outgoing packet */
	mb_copy->m_flags |= M_MCAST;

	/*
	 * If we sourced the packet, call ip6_output since we may devide
	 * the packet into fragments when the packet is too big for the
	 * outgoing interface.
	 * Otherwise, we can simply send the packet to the interface
	 * sending queue.
	 */
	if (m->m_pkthdr.rcvif == NULL) {
		struct ip6_moptions im6o;

		im6o.im6o_multicast_ifp = ifp;
		/* XXX: ip6_output will override ip6->ip6_hlim */
		im6o.im6o_multicast_hlim = ip6->ip6_hlim;
		im6o.im6o_multicast_loop = 1;
		error = ip6_output(mb_copy, NULL, NULL, IPV6_FORWARDING, &im6o,
		    NULL, NULL);

#ifdef MRT6DEBUG
		if (V_mrt6debug & DEBUG_XMIT)
			log(LOG_DEBUG, "phyint_send on mif %d err %d\n",
			    mifp - mif6table, error);
#endif
		return;
	}

	/*
	 * If configured to loop back multicasts by default,
	 * loop back a copy now.
	 */
	if (in6_mcast_loop) {
		struct sockaddr_in6 dst6;

		bzero(&dst6, sizeof(dst6));
		dst6.sin6_len = sizeof(struct sockaddr_in6);
		dst6.sin6_family = AF_INET6;
		dst6.sin6_addr = ip6->ip6_dst;
		ip6_mloopback(ifp, m, &dst6);
	}

	/*
	 * Put the packet into the sending queue of the outgoing interface
	 * if it would fit in the MTU of the interface.
	 */
	linkmtu = IN6_LINKMTU(ifp);
	if (mb_copy->m_pkthdr.len <= linkmtu || linkmtu < IPV6_MMTU) {
		struct sockaddr_in6 dst6;

		bzero(&dst6, sizeof(dst6));
		dst6.sin6_len = sizeof(struct sockaddr_in6);
		dst6.sin6_family = AF_INET6;
		dst6.sin6_addr = ip6->ip6_dst;
		/*
		 * We just call if_output instead of nd6_output here, since
		 * we need no ND for a multicast forwarded packet...right?
		 */
		error = (*ifp->if_output)(ifp, mb_copy,
		    (struct sockaddr *)&dst6, NULL);
#ifdef MRT6DEBUG
		if (V_mrt6debug & DEBUG_XMIT)
			log(LOG_DEBUG, "phyint_send on mif %d err %d\n",
			    mifp - mif6table, error);
#endif
	} else {
		/*
		 * pMTU discovery is intentionally disabled by default, since
		 * various router may notify pMTU in multicast, which can be
		 * a DDoS to a router
		 */
		if (V_ip6_mcast_pmtu)
			icmp6_error(mb_copy, ICMP6_PACKET_TOO_BIG, 0, linkmtu);
		else {
#ifdef MRT6DEBUG
			if (V_mrt6debug & DEBUG_XMIT) {
				char ip6bufs[INET6_ADDRSTRLEN];
				char ip6bufd[INET6_ADDRSTRLEN];
				log(LOG_DEBUG,
				    "phyint_send: packet too big on %s o %s "
				    "g %s size %d(discarded)\n",
				    if_name(ifp),
				    ip6_sprintf(ip6bufs, &ip6->ip6_src),
				    ip6_sprintf(ip6bufd, &ip6->ip6_dst),
				    mb_copy->m_pkthdr.len);
			}
#endif /* MRT6DEBUG */
			m_freem(mb_copy); /* simply discard the packet */
		}
	}
}

static int
register_send(struct ip6_hdr *ip6, struct mif6 *mif, struct mbuf *m)
{
	struct mbuf *mm;
	int i, len = m->m_pkthdr.len;
	static struct sockaddr_in6 sin6 = { sizeof(sin6), AF_INET6 };
	struct mrt6msg *im6;

#ifdef MRT6DEBUG
	if (V_mrt6debug) {
		char ip6bufs[INET6_ADDRSTRLEN], ip6bufd[INET6_ADDRSTRLEN];
		log(LOG_DEBUG, "** IPv6 register_send **\n src %s dst %s\n",
		    ip6_sprintf(ip6bufs, &ip6->ip6_src),
		    ip6_sprintf(ip6bufd, &ip6->ip6_dst));
	}
#endif
	++pim6stat.pim6s_snd_registers;

	/* Make a copy of the packet to send to the user level process */
	MGETHDR(mm, M_NOWAIT, MT_HEADER);
	if (mm == NULL)
		return (ENOBUFS);
	mm->m_pkthdr.rcvif = NULL;
	mm->m_data += max_linkhdr;
	mm->m_len = sizeof(struct ip6_hdr);

	if ((mm->m_next = m_copy(m, 0, M_COPYALL)) == NULL) {
		m_freem(mm);
		return (ENOBUFS);
	}
	i = MHLEN - M_LEADINGSPACE(mm);
	if (i > len)
		i = len;
	mm = m_pullup(mm, i);
	if (mm == NULL)
		return (ENOBUFS);
/* TODO: check it! */
	mm->m_pkthdr.len = len + sizeof(struct ip6_hdr);

	/*
	 * Send message to routing daemon
	 */
	sin6.sin6_addr = ip6->ip6_src;

	im6 = mtod(mm, struct mrt6msg *);
	im6->im6_msgtype      = MRT6MSG_WHOLEPKT;
	im6->im6_mbz          = 0;

	im6->im6_mif = mif - mif6table;

	/* iif info is not given for reg. encap.n */
	mrt6stat.mrt6s_upcalls++;

	if (socket_send(V_ip6_mrouter, mm, &sin6) < 0) {
#ifdef MRT6DEBUG
		if (V_mrt6debug)
			log(LOG_WARNING,
			    "register_send: ip6_mrouter socket queue full\n");
#endif
		++mrt6stat.mrt6s_upq_sockfull;
		return (ENOBUFS);
	}
	return (0);
}

/*
 * pim6_encapcheck() is called by the encap6_input() path at runtime to
 * determine if a packet is for PIM; allowing PIM to be dynamically loaded
 * into the kernel.
 */
static int
pim6_encapcheck(const struct mbuf *m, int off, int proto, void *arg)
{

#ifdef DIAGNOSTIC
    KASSERT(proto == IPPROTO_PIM, ("not for IPPROTO_PIM"));
#endif
    if (proto != IPPROTO_PIM)
	return 0;	/* not for us; reject the datagram. */

    return 64;		/* claim the datagram. */
}

/*
 * PIM sparse mode hook
 * Receives the pim control messages, and passes them up to the listening
 * socket, using rip6_input.
 * The only message processed is the REGISTER pim message; the pim header
 * is stripped off, and the inner packet is passed to register_mforward.
 */
int
pim6_input(struct mbuf **mp, int *offp, int proto)
{
	struct pim *pim; /* pointer to a pim struct */
	struct ip6_hdr *ip6;
	int pimlen;
	struct mbuf *m = *mp;
	int minlen;
	int off = *offp;

	++pim6stat.pim6s_rcv_total;

	ip6 = mtod(m, struct ip6_hdr *);
	pimlen = m->m_pkthdr.len - *offp;

	/*
	 * Validate lengths
	 */
	if (pimlen < PIM_MINLEN) {
		++pim6stat.pim6s_rcv_tooshort;
#ifdef MRT6DEBUG
		if (V_mrt6debug & DEBUG_PIM)
			log(LOG_DEBUG,"pim6_input: PIM packet too short\n");
#endif
		m_freem(m);
		return (IPPROTO_DONE);
	}

	/*
	 * if the packet is at least as big as a REGISTER, go ahead
	 * and grab the PIM REGISTER header size, to avoid another
	 * possible m_pullup() later.
	 *
	 * PIM_MINLEN       == pimhdr + u_int32 == 8
	 * PIM6_REG_MINLEN   == pimhdr + reghdr + eip6hdr == 4 + 4 + 40
	 */
	minlen = (pimlen >= PIM6_REG_MINLEN) ? PIM6_REG_MINLEN : PIM_MINLEN;

	/*
	 * Make sure that the IP6 and PIM headers in contiguous memory, and
	 * possibly the PIM REGISTER header
	 */
#ifndef PULLDOWN_TEST
	IP6_EXTHDR_CHECK(m, off, minlen, IPPROTO_DONE);
	/* adjust pointer */
	ip6 = mtod(m, struct ip6_hdr *);

	/* adjust mbuf to point to the PIM header */
	pim = (struct pim *)((caddr_t)ip6 + off);
#else
	IP6_EXTHDR_GET(pim, struct pim *, m, off, minlen);
	if (pim == NULL) {
		pim6stat.pim6s_rcv_tooshort++;
		return (IPPROTO_DONE);
	}
#endif

#define PIM6_CHECKSUM
#ifdef PIM6_CHECKSUM
	{
		int cksumlen;

		/*
		 * Validate checksum.
		 * If PIM REGISTER, exclude the data packet
		 */
		if (pim->pim_type == PIM_REGISTER)
			cksumlen = PIM_MINLEN;
		else
			cksumlen = pimlen;

		if (in6_cksum(m, IPPROTO_PIM, off, cksumlen)) {
			++pim6stat.pim6s_rcv_badsum;
#ifdef MRT6DEBUG
			if (V_mrt6debug & DEBUG_PIM)
				log(LOG_DEBUG,
				    "pim6_input: invalid checksum\n");
#endif
			m_freem(m);
			return (IPPROTO_DONE);
		}
	}
#endif /* PIM_CHECKSUM */

	/* PIM version check */
	if (pim->pim_ver != PIM_VERSION) {
		++pim6stat.pim6s_rcv_badversion;
#ifdef MRT6DEBUG
		log(LOG_ERR,
		    "pim6_input: incorrect version %d, expecting %d\n",
		    pim->pim_ver, PIM_VERSION);
#endif
		m_freem(m);
		return (IPPROTO_DONE);
	}

	if (pim->pim_type == PIM_REGISTER) {
		/*
		 * since this is a REGISTER, we'll make a copy of the register
		 * headers ip6+pim+u_int32_t+encap_ip6, to be passed up to the
		 * routing daemon.
		 */
		static struct sockaddr_in6 dst = { sizeof(dst), AF_INET6 };

		struct mbuf *mcp;
		struct ip6_hdr *eip6;
		u_int32_t *reghdr;
		int rc;
#ifdef MRT6DEBUG
		char ip6bufs[INET6_ADDRSTRLEN], ip6bufd[INET6_ADDRSTRLEN];
#endif

		++pim6stat.pim6s_rcv_registers;

		if ((reg_mif_num >= nummifs) || (reg_mif_num == (mifi_t) -1)) {
#ifdef MRT6DEBUG
			if (V_mrt6debug & DEBUG_PIM)
				log(LOG_DEBUG,
				    "pim6_input: register mif not set: %d\n",
				    reg_mif_num);
#endif
			m_freem(m);
			return (IPPROTO_DONE);
		}

		reghdr = (u_int32_t *)(pim + 1);

		if ((ntohl(*reghdr) & PIM_NULL_REGISTER))
			goto pim6_input_to_daemon;

		/*
		 * Validate length
		 */
		if (pimlen < PIM6_REG_MINLEN) {
			++pim6stat.pim6s_rcv_tooshort;
			++pim6stat.pim6s_rcv_badregisters;
#ifdef MRT6DEBUG
			log(LOG_ERR,
			    "pim6_input: register packet size too "
			    "small %d from %s\n",
			    pimlen, ip6_sprintf(ip6bufs, &ip6->ip6_src));
#endif
			m_freem(m);
			return (IPPROTO_DONE);
		}

		eip6 = (struct ip6_hdr *) (reghdr + 1);
#ifdef MRT6DEBUG
		if (V_mrt6debug & DEBUG_PIM)
			log(LOG_DEBUG,
			    "pim6_input[register], eip6: %s -> %s, "
			    "eip6 plen %d\n",
			    ip6_sprintf(ip6bufs, &eip6->ip6_src),
			    ip6_sprintf(ip6bufd, &eip6->ip6_dst),
			    ntohs(eip6->ip6_plen));
#endif

		/* verify the version number of the inner packet */
		if ((eip6->ip6_vfc & IPV6_VERSION_MASK) != IPV6_VERSION) {
			++pim6stat.pim6s_rcv_badregisters;
#ifdef MRT6DEBUG
			log(LOG_DEBUG, "pim6_input: invalid IP version (%d) "
			    "of the inner packet\n",
			    (eip6->ip6_vfc & IPV6_VERSION));
#endif
			m_freem(m);
			return (IPPROTO_NONE);
		}

		/* verify the inner packet is destined to a mcast group */
		if (!IN6_IS_ADDR_MULTICAST(&eip6->ip6_dst)) {
			++pim6stat.pim6s_rcv_badregisters;
#ifdef MRT6DEBUG
			if (V_mrt6debug & DEBUG_PIM)
				log(LOG_DEBUG,
				    "pim6_input: inner packet of register "
				    "is not multicast %s\n",
				    ip6_sprintf(ip6bufd, &eip6->ip6_dst));
#endif
			m_freem(m);
			return (IPPROTO_DONE);
		}

		/*
		 * make a copy of the whole header to pass to the daemon later.
		 */
		mcp = m_copy(m, 0, off + PIM6_REG_MINLEN);
		if (mcp == NULL) {
#ifdef MRT6DEBUG
			log(LOG_ERR,
			    "pim6_input: pim register: "
			    "could not copy register head\n");
#endif
			m_freem(m);
			return (IPPROTO_DONE);
		}

		/*
		 * forward the inner ip6 packet; point m_data at the inner ip6.
		 */
		m_adj(m, off + PIM_MINLEN);
#ifdef MRT6DEBUG
		if (V_mrt6debug & DEBUG_PIM) {
			log(LOG_DEBUG,
			    "pim6_input: forwarding decapsulated register: "
			    "src %s, dst %s, mif %d\n",
			    ip6_sprintf(ip6bufs, &eip6->ip6_src),
			    ip6_sprintf(ip6bufd, &eip6->ip6_dst),
			    reg_mif_num);
		}
#endif

		rc = if_simloop(mif6table[reg_mif_num].m6_ifp, m,
				dst.sin6_family, 0);

		/* prepare the register head to send to the mrouting daemon */
		m = mcp;
	}

	/*
	 * Pass the PIM message up to the daemon; if it is a register message
	 * pass the 'head' only up to the daemon. This includes the
	 * encapsulator ip6 header, pim header, register header and the
	 * encapsulated ip6 header.
	 */
  pim6_input_to_daemon:
	rip6_input(&m, offp, proto);
	return (IPPROTO_DONE);
}

static int
ip6_mroute_modevent(module_t mod, int type, void *unused)
{

	switch (type) {
	case MOD_LOAD:
		MROUTER6_LOCK_INIT();
		MFC6_LOCK_INIT();
		MIF6_LOCK_INIT();

		pim6_encap_cookie = encap_attach_func(AF_INET6, IPPROTO_PIM,
			pim6_encapcheck,
			(const struct protosw *)&in6_pim_protosw, NULL);
		if (pim6_encap_cookie == NULL) {
			printf("ip6_mroute: unable to attach pim6 encap\n");
			MIF6_LOCK_DESTROY();
			MFC6_LOCK_DESTROY();
			MROUTER6_LOCK_DESTROY();
			return (EINVAL);
		}

		ip6_mforward = X_ip6_mforward;
		ip6_mrouter_done = X_ip6_mrouter_done;
		ip6_mrouter_get = X_ip6_mrouter_get;
		ip6_mrouter_set = X_ip6_mrouter_set;
		mrt6_ioctl = X_mrt6_ioctl;
		break;

	case MOD_UNLOAD:
		if (V_ip6_mrouter != NULL)
			return EINVAL;

		if (pim6_encap_cookie) {
			encap_detach(pim6_encap_cookie);
			pim6_encap_cookie = NULL;
		}
		X_ip6_mrouter_done();
		ip6_mforward = NULL;
		ip6_mrouter_done = NULL;
		ip6_mrouter_get = NULL;
		ip6_mrouter_set = NULL;
		mrt6_ioctl = NULL;

		MIF6_LOCK_DESTROY();
		MFC6_LOCK_DESTROY();
		MROUTER6_LOCK_DESTROY();
		break;

	default:
		return (EOPNOTSUPP);
	}

	return (0);
}

static moduledata_t ip6_mroutemod = {
	"ip6_mroute",
	ip6_mroute_modevent,
	0
};

DECLARE_MODULE(ip6_mroute, ip6_mroutemod, SI_SUB_PSEUDO, SI_ORDER_ANY);
OpenPOWER on IntegriCloud