summaryrefslogtreecommitdiffstats
path: root/sys/netinet/ip_mroute.c
blob: 6449696d9dc3fcc3bd60d2dca8692e9c68361854 (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
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
/*
 * 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 1995
 *
 * MROUTING Revision: 3.5
 * $FreeBSD$
 */

#include "opt_mac.h"
#include "opt_mrouting.h"
#include "opt_random_ip_id.h"

#include <sys/param.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/mac.h>
#include <sys/malloc.h>
#include <sys/mbuf.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/route.h>
#include <netinet/in.h>
#include <netinet/igmp.h>
#include <netinet/in_systm.h>
#include <netinet/in_var.h>
#include <netinet/ip.h>
#include <netinet/ip_encap.h>
#include <netinet/ip_mroute.h>
#include <netinet/ip_var.h>
#include <netinet/udp.h>
#include <machine/in_cksum.h>

#ifndef MROUTING
extern u_long	_ip_mcast_src(int vifi);
extern int	_ip_mforward(struct ip *ip, struct ifnet *ifp, struct mbuf *m,
		    struct ip_moptions *imo);
extern int	_ip_mrouter_done(void);
extern int	_ip_mrouter_get(struct socket *so, struct sockopt *sopt);
extern int	_ip_mrouter_set(struct socket *so, struct sockopt *sopt);
extern int	_mrt_ioctl(int req, caddr_t data);

/*
 * Dummy routines and globals used when multicast routing is not compiled in.
 */

struct socket  *ip_mrouter  = NULL;
u_int		rsvpdebug = 0;

int
_ip_mrouter_set(so, sopt)
	struct socket *so;
	struct sockopt *sopt;
{
	return(EOPNOTSUPP);
}

int (*ip_mrouter_set)(struct socket *, struct sockopt *) = _ip_mrouter_set;


int
_ip_mrouter_get(so, sopt)
	struct socket *so;
	struct sockopt *sopt;
{
	return(EOPNOTSUPP);
}

int (*ip_mrouter_get)(struct socket *, struct sockopt *) = _ip_mrouter_get;

int
_ip_mrouter_done()
{
	return(0);
}

int (*ip_mrouter_done)(void) = _ip_mrouter_done;

int
_ip_mforward(ip, ifp, m, imo)
	struct ip *ip;
	struct ifnet *ifp;
	struct mbuf *m;
	struct ip_moptions *imo;
{
	return(0);
}

int (*ip_mforward)(struct ip *, struct ifnet *, struct mbuf *,
		   struct ip_moptions *) = _ip_mforward;

int
_mrt_ioctl(int req, caddr_t data)
{
	return EOPNOTSUPP;
}

int (*mrt_ioctl)(int, caddr_t) = _mrt_ioctl;

void
rsvp_input(m, off)		/* XXX must fixup manually */
	struct mbuf *m;
	int off;
{
    /* Can still get packets with rsvp_on = 0 if there is a local member
     * of the group to which the RSVP packet is addressed.  But in this
     * case we want to throw the packet away.
     */
    if (!rsvp_on) {
	m_freem(m);
	return;
    }
 
    if (ip_rsvpd != NULL) {
	if (rsvpdebug)
	    printf("rsvp_input: Sending packet up old-style socket\n");
	rip_input(m, off);
	return;
    }
    /* Drop the packet */
    m_freem(m);
}

int (*legal_vif_num)(int) = 0;

/*
 * This should never be called, since IP_MULTICAST_VIF should fail, but
 * just in case it does get called, the code a little lower in ip_output
 * will assign the packet a local address.
 */
u_long
_ip_mcast_src(int vifi) { return INADDR_ANY; }
u_long (*ip_mcast_src)(int) = _ip_mcast_src;

int
ip_rsvp_vif_init(so, sopt)
    struct socket *so;
    struct sockopt *sopt;
{
    return(EINVAL);
}

int
ip_rsvp_vif_done(so, sopt)
    struct socket *so;
    struct sockopt *sopt;
{
    return(EINVAL);
}

void
ip_rsvp_force_done(so)
    struct socket *so;
{
    return;
}

#else /* MROUTING */

#define M_HASCL(m)	((m)->m_flags & M_EXT)

static MALLOC_DEFINE(M_MRTABLE, "mroutetbl", "multicast routing tables");

#ifndef MROUTE_KLD
/* The socket used to communicate with the multicast routing daemon.  */
struct socket  *ip_mrouter  = NULL;
#endif

#if defined(MROUTING) || defined(MROUTE_KLD)
static struct mrtstat	mrtstat;
SYSCTL_STRUCT(_net_inet_ip, OID_AUTO, mrtstat, CTLFLAG_RW,
    &mrtstat, mrtstat, "Multicast Routing Statistics (struct mrtstat, netinet/ip_mroute.h)");
#endif

static struct mfc	*mfctable[MFCTBLSIZ];
static u_char		nexpire[MFCTBLSIZ];
static struct vif	viftable[MAXVIFS];
static u_int	mrtdebug = 0;	  /* debug level 	*/
#define		DEBUG_MFC	0x02
#define		DEBUG_FORWARD	0x04
#define		DEBUG_EXPIRE	0x08
#define		DEBUG_XMIT	0x10
static u_int  	tbfdebug = 0;     /* tbf debug level 	*/
static u_int	rsvpdebug = 0;	  /* rsvp debug level   */

static struct callout_handle expire_upcalls_ch;

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

/*
 * Define the token bucket filter structures
 * tbftable -> each vif has one of these for storing info 
 */

static struct tbf tbftable[MAXVIFS];
#define		TBF_REPROCESS	(hz / 100)	/* 100x / second */

/*
 * 'Interfaces' associated with decapsulator (so we can tell
 * packets that went through it from ones that get reflected
 * by a broken gateway).  These interfaces are never linked into
 * the system ifnet list & no 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_decap_if[MAXVIFS];

#define ENCAP_TTL 64
#define ENCAP_PROTO IPPROTO_IPIP	/* 4 */

/* prototype IP hdr for encapsulated packets */
static struct ip multicast_encap_iphdr = {
#if BYTE_ORDER == LITTLE_ENDIAN
	sizeof(struct ip) >> 2, IPVERSION,
#else
	IPVERSION, sizeof(struct ip) >> 2,
#endif
	0,				/* tos */
	sizeof(struct ip),		/* total length */
	0,				/* id */
	0,				/* frag offset */
	ENCAP_TTL, ENCAP_PROTO,	
	0,				/* checksum */
};

/*
 * Private variables.
 */
static vifi_t	   numvifs = 0;
static const struct encaptab *encap_cookie = NULL;

/*
 * one-back cache used by mroute_encapcheck to locate a tunnel's vif
 * given a datagram's src ip address.
 */
static u_long last_encap_src;
static struct vif *last_encap_vif;

static u_long	X_ip_mcast_src(int vifi);
static int	X_ip_mforward(struct ip *ip, struct ifnet *ifp, struct mbuf *m, struct ip_moptions *imo);
static int	X_ip_mrouter_done(void);
static int	X_ip_mrouter_get(struct socket *so, struct sockopt *m);
static int	X_ip_mrouter_set(struct socket *so, struct sockopt *m);
static int	X_legal_vif_num(int vif);
static int	X_mrt_ioctl(int cmd, caddr_t data);

static int get_sg_cnt(struct sioc_sg_req *);
static int get_vif_cnt(struct sioc_vif_req *);
static int ip_mrouter_init(struct socket *, int);
static int add_vif(struct vifctl *);
static int del_vif(vifi_t);
static int add_mfc(struct mfcctl *);
static int del_mfc(struct mfcctl *);
static int socket_send(struct socket *, struct mbuf *, struct sockaddr_in *);
static int set_assert(int);
static void expire_upcalls(void *);
static int ip_mdq(struct mbuf *, struct ifnet *, struct mfc *,
		  vifi_t);
static void phyint_send(struct ip *, struct vif *, struct mbuf *);
static void encap_send(struct ip *, struct vif *, struct mbuf *);
static void tbf_control(struct vif *, struct mbuf *, struct ip *, u_long);
static void tbf_queue(struct vif *, struct mbuf *);
static void tbf_process_q(struct vif *);
static void tbf_reprocess_q(void *);
static int tbf_dq_sel(struct vif *, struct ip *);
static void tbf_send_packet(struct vif *, struct mbuf *);
static void tbf_update_tokens(struct vif *);
static int priority(struct vif *, struct ip *);

/*
 * whether or not special PIM assert processing is enabled.
 */
static int pim_assert;
/*
 * Rate limit for assert notification messages, in usec
 */
#define ASSERT_MSG_TIME		3000000

/*
 * Hash function for a source, group entry
 */
#define MFCHASH(a, g) MFCHASHMOD(((a) >> 20) ^ ((a) >> 10) ^ (a) ^ \
			((g) >> 20) ^ ((g) >> 10) ^ (g))

/*
 * Find a route for a given origin IP address and Multicast group address
 * Type of service parameter to be added in the future!!!
 */

#define MFCFIND(o, g, rt) { \
	register struct mfc *_rt = mfctable[MFCHASH(o,g)]; \
	rt = NULL; \
	++mrtstat.mrts_mfc_lookups; \
	while (_rt) { \
		if ((_rt->mfc_origin.s_addr == o) && \
		    (_rt->mfc_mcastgrp.s_addr == g) && \
		    (_rt->mfc_stall == NULL)) { \
			rt = _rt; \
			break; \
		} \
		_rt = _rt->mfc_next; \
	} \
	if (rt == NULL) { \
		++mrtstat.mrts_mfc_misses; \
	} \
}


/*
 * Macros to compute elapsed time efficiently
 * Borrowed from Van Jacobson's scheduling code
 */
#define TV_DELTA(a, b, delta) { \
	    register 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); \
	       } \
	    } \
}

#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
u_long upcall_data[51];
static void collate(struct timeval *);
#endif /* UPCALL_TIMING */


/*
 * Handle MRT setsockopt commands to modify the multicast routing tables.
 */
static int
X_ip_mrouter_set(so, sopt)
	struct socket *so;
	struct sockopt *sopt;
{
	int	error, optval;
	vifi_t	vifi;
	struct	vifctl vifc;
	struct	mfcctl mfc;

	if (so != ip_mrouter && sopt->sopt_name != MRT_INIT)
		return (EPERM);

	error = 0;
	switch (sopt->sopt_name) {
	case MRT_INIT:
		error = sooptcopyin(sopt, &optval, sizeof optval, 
				    sizeof optval);
		if (error)
			break;
		error = ip_mrouter_init(so, optval);
		break;

	case MRT_DONE:
		error = ip_mrouter_done();
		break;

	case MRT_ADD_VIF:
		error = sooptcopyin(sopt, &vifc, sizeof vifc, sizeof vifc);
		if (error)
			break;
		error = add_vif(&vifc);
		break;

	case MRT_DEL_VIF:
		error = sooptcopyin(sopt, &vifi, sizeof vifi, sizeof vifi);
		if (error)
			break;
		error = del_vif(vifi);
		break;

	case MRT_ADD_MFC:
	case MRT_DEL_MFC:
		error = sooptcopyin(sopt, &mfc, sizeof mfc, sizeof mfc);
		if (error)
			break;
		if (sopt->sopt_name == MRT_ADD_MFC)
			error = add_mfc(&mfc);
		else
			error = del_mfc(&mfc);
		break;

	case MRT_ASSERT:
		error = sooptcopyin(sopt, &optval, sizeof optval, 
				    sizeof optval);
		if (error)
			break;
		set_assert(optval);
		break;

	default:
		error = EOPNOTSUPP;
		break;
	}
	return (error);
}

#ifndef MROUTE_KLD
int (*ip_mrouter_set)(struct socket *, struct sockopt *) = X_ip_mrouter_set;
#endif

/*
 * Handle MRT getsockopt commands
 */
static int
X_ip_mrouter_get(so, sopt)
	struct socket *so;
	struct sockopt *sopt;
{
	int error;
	static int version = 0x0305; /* !!! why is this here? XXX */

	switch (sopt->sopt_name) {
	case MRT_VERSION:
		error = sooptcopyout(sopt, &version, sizeof version);
		break;

	case MRT_ASSERT:
		error = sooptcopyout(sopt, &pim_assert, sizeof pim_assert);
		break;
	default:
		error = EOPNOTSUPP;
		break;
	}
	return (error);
}

#ifndef MROUTE_KLD
int (*ip_mrouter_get)(struct socket *, struct sockopt *) = X_ip_mrouter_get;
#endif

/*
 * Handle ioctl commands to obtain information from the cache
 */
static int
X_mrt_ioctl(cmd, data)
    int cmd;
    caddr_t data;
{
    int error = 0;

    switch (cmd) {
	case (SIOCGETVIFCNT):
	    return (get_vif_cnt((struct sioc_vif_req *)data));
	    break;
	case (SIOCGETSGCNT):
	    return (get_sg_cnt((struct sioc_sg_req *)data));
	    break;
	default:
	    return (EINVAL);
	    break;
    }
    return error;
}

#ifndef MROUTE_KLD
int (*mrt_ioctl)(int, caddr_t) = X_mrt_ioctl;
#endif

/*
 * returns the packet, byte, rpf-failure count for the source group provided
 */
static int
get_sg_cnt(req)
    register struct sioc_sg_req *req;
{
    register struct mfc *rt;
    int s;

    s = splnet();
    MFCFIND(req->src.s_addr, req->grp.s_addr, rt);
    splx(s);
    if (rt != NULL) {
	req->pktcnt = rt->mfc_pkt_cnt;
	req->bytecnt = rt->mfc_byte_cnt;
	req->wrong_if = rt->mfc_wrong_if;
    } else
	req->pktcnt = req->bytecnt = req->wrong_if = 0xffffffff;

    return 0;
}

/*
 * returns the input and output packet and byte counts on the vif provided
 */
static int
get_vif_cnt(req)
    register struct sioc_vif_req *req;
{
    register vifi_t vifi = req->vifi;

    if (vifi >= numvifs) return EINVAL;

    req->icount = viftable[vifi].v_pkt_in;
    req->ocount = viftable[vifi].v_pkt_out;
    req->ibytes = viftable[vifi].v_bytes_in;
    req->obytes = viftable[vifi].v_bytes_out;

    return 0;
}

/*
 * Enable multicast routing
 */
static int
ip_mrouter_init(so, version)
	struct socket *so;
	int version;
{
    if (mrtdebug)
	log(LOG_DEBUG,"ip_mrouter_init: so_type = %d, pr_protocol = %d\n",
		so->so_type, so->so_proto->pr_protocol);

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

    if (version != 1)
	return ENOPROTOOPT;

    if (ip_mrouter != NULL) return EADDRINUSE;

    ip_mrouter = so;

    bzero((caddr_t)mfctable, sizeof(mfctable));
    bzero((caddr_t)nexpire, sizeof(nexpire));

    pim_assert = 0;

    expire_upcalls_ch = timeout(expire_upcalls, (caddr_t)NULL, EXPIRE_TIMEOUT);

    if (mrtdebug)
	log(LOG_DEBUG, "ip_mrouter_init\n");

    return 0;
}

/*
 * Disable multicast routing
 */
static int
X_ip_mrouter_done()
{
    vifi_t vifi;
    int i;
    struct ifnet *ifp;
    struct ifreq ifr;
    struct mfc *rt;
    struct rtdetq *rte;
    int s;

    s = splnet();

    /*
     * For each phyint in use, disable promiscuous reception of all IP
     * multicasts.
     */
    for (vifi = 0; vifi < numvifs; vifi++) {
	if (viftable[vifi].v_lcl_addr.s_addr != 0 &&
	    !(viftable[vifi].v_flags & VIFF_TUNNEL)) {
	    ((struct sockaddr_in *)&(ifr.ifr_addr))->sin_family = AF_INET;
	    ((struct sockaddr_in *)&(ifr.ifr_addr))->sin_addr.s_addr
								= INADDR_ANY;
	    ifp = viftable[vifi].v_ifp;
	    if_allmulti(ifp, 0);
	}
    }
    bzero((caddr_t)tbftable, sizeof(tbftable));
    bzero((caddr_t)viftable, sizeof(viftable));
    numvifs = 0;
    pim_assert = 0;

    untimeout(expire_upcalls, (caddr_t)NULL, expire_upcalls_ch);

    /*
     * Free all multicast forwarding cache entries.
     */
    for (i = 0; i < MFCTBLSIZ; i++) {
	for (rt = mfctable[i]; rt != NULL; ) {
	    struct mfc *nr = rt->mfc_next;

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

		m_freem(rte->m);
		free(rte, M_MRTABLE);
		rte = n;
	    }
	    free(rt, M_MRTABLE);
	    rt = nr;
	}
    }

    bzero((caddr_t)mfctable, sizeof(mfctable));

    /*
     * Reset de-encapsulation cache
     */
    last_encap_src = 0;
    last_encap_vif = NULL;
    if (encap_cookie) {
	encap_detach(encap_cookie);
	encap_cookie = NULL;
    }
 
    ip_mrouter = NULL;

    splx(s);

    if (mrtdebug)
	log(LOG_DEBUG, "ip_mrouter_done\n");

    return 0;
}

#ifndef MROUTE_KLD
int (*ip_mrouter_done)(void) = X_ip_mrouter_done;
#endif

/*
 * Set PIM assert processing global
 */
static int
set_assert(i)
	int i;
{
    if ((i != 1) && (i != 0))
	return EINVAL;

    pim_assert = i;

    return 0;
}

/*
 * Decide if a packet is from a tunnelled peer.
 * Return 0 if not, 64 if so.
 */
static int
mroute_encapcheck(const struct mbuf *m, int off, int proto, void *arg)
{
    struct ip *ip = mtod(m, struct ip *);
    int hlen = ip->ip_hl << 2;
    register struct vif *vifp;

    /*
     * don't claim the packet if it's not to a multicast destination or if
     * we don't have an encapsulating tunnel with the source.
     * Note:  This code assumes that the remote site IP address
     * uniquely identifies the tunnel (i.e., that this site has
     * at most one tunnel with the remote site).
     */
    if (! IN_MULTICAST(ntohl(((struct ip *)((char *)ip + hlen))->ip_dst.s_addr))) {
	return 0;
    }
    if (ip->ip_src.s_addr != last_encap_src) {
	register struct vif *vife;
	
	vifp = viftable;
	vife = vifp + numvifs;
	last_encap_src = ip->ip_src.s_addr;
	last_encap_vif = 0;
	for ( ; vifp < vife; ++vifp)
	    if (vifp->v_rmt_addr.s_addr == ip->ip_src.s_addr) {
		if ((vifp->v_flags & (VIFF_TUNNEL|VIFF_SRCRT))
		    == VIFF_TUNNEL)
		    last_encap_vif = vifp;
		break;
	    }
    }
    if ((vifp = last_encap_vif) == 0) {
	last_encap_src = 0;
	return 0;
    }
    return 64;
}

/*
 * De-encapsulate a packet and feed it back through ip input (this
 * routine is called whenever IP gets a packet that mroute_encap_func()
 * claimed).
 */
static void
mroute_encap_input(struct mbuf *m, int off)
{
    struct ip *ip = mtod(m, struct ip *);
    int hlen = ip->ip_hl << 2;

    if (hlen > sizeof(struct ip))
      ip_stripoptions(m, (struct mbuf *) 0);
    m->m_data += sizeof(struct ip);
    m->m_len -= sizeof(struct ip);
    m->m_pkthdr.len -= sizeof(struct ip);

    m->m_pkthdr.rcvif = last_encap_vif->v_ifp;

    (void) IF_HANDOFF(&ipintrq, m, NULL);
	/*
	 * normally we would need a "schednetisr(NETISR_IP)"
	 * here but we were called by ip_input and it is going
	 * to loop back & try to dequeue the packet we just
	 * queued as soon as we return so we avoid the
	 * unnecessary software interrrupt.
	 */
}

extern struct domain inetdomain;
static struct protosw mroute_encap_protosw =
{ SOCK_RAW,	&inetdomain,	IPPROTO_IPV4,	PR_ATOMIC|PR_ADDR,
  mroute_encap_input,	0,	0,		rip_ctloutput,
  0,
  0,		0,		0,		0,
  &rip_usrreqs
};

/*
 * Add a vif to the vif table
 */
static int
add_vif(vifcp)
    register struct vifctl *vifcp;
{
    register struct vif *vifp = viftable + vifcp->vifc_vifi;
    static struct sockaddr_in sin = {sizeof sin, AF_INET};
    struct ifaddr *ifa;
    struct ifnet *ifp;
    int error, s;
    struct tbf *v_tbf = tbftable + vifcp->vifc_vifi;

    if (vifcp->vifc_vifi >= MAXVIFS)  return EINVAL;
    if (vifp->v_lcl_addr.s_addr != 0) return EADDRINUSE;

    /* Find the interface with an address in AF_INET family */
    sin.sin_addr = vifcp->vifc_lcl_addr;
    ifa = ifa_ifwithaddr((struct sockaddr *)&sin);
    if (ifa == 0) return EADDRNOTAVAIL;
    ifp = ifa->ifa_ifp;

    if (vifcp->vifc_flags & VIFF_TUNNEL) {
	if ((vifcp->vifc_flags & VIFF_SRCRT) == 0) {
		/*
		 * An encapsulating tunnel is wanted.  Tell
		 * mroute_encap_input() to start paying attention
		 * to encapsulated packets.
		 */
		if (encap_cookie == NULL) {
			encap_cookie = encap_attach_func(AF_INET, IPPROTO_IPV4,
				mroute_encapcheck,
				(struct protosw *)&mroute_encap_protosw, NULL);

			if (encap_cookie == NULL) {
				printf("ip_mroute: unable to attach encap\n");
				return (EIO);	/* XXX */
			}
			for (s = 0; s < MAXVIFS; ++s) {
				multicast_decap_if[s].if_name = "mdecap";
				multicast_decap_if[s].if_unit = s;
			}
		}
		/*
		 * Set interface to fake encapsulator interface
		 */
		ifp = &multicast_decap_if[vifcp->vifc_vifi];
		/*
		 * Prepare cached route entry
		 */
		bzero(&vifp->v_route, sizeof(vifp->v_route));
	} else {
	    log(LOG_ERR, "source routed tunnels not supported\n");
	    return EOPNOTSUPP;
	}
    } else {
	/* Make sure the interface supports multicast */
	if ((ifp->if_flags & IFF_MULTICAST) == 0)
	    return EOPNOTSUPP;

	/* Enable promiscuous reception of all IP multicasts from the if */
	s = splnet();
	error = if_allmulti(ifp, 1);
	splx(s);
	if (error)
	    return error;
    }

    s = splnet();
    /* define parameters for the tbf structure */
    vifp->v_tbf = v_tbf;
    GET_TIME(vifp->v_tbf->tbf_last_pkt_t);
    vifp->v_tbf->tbf_n_tok = 0;
    vifp->v_tbf->tbf_q_len = 0;
    vifp->v_tbf->tbf_max_q_len = MAXQSIZE;
    vifp->v_tbf->tbf_q = vifp->v_tbf->tbf_t = NULL;

    vifp->v_flags     = vifcp->vifc_flags;
    vifp->v_threshold = vifcp->vifc_threshold;
    vifp->v_lcl_addr  = vifcp->vifc_lcl_addr;
    vifp->v_rmt_addr  = vifcp->vifc_rmt_addr;
    vifp->v_ifp       = ifp;
    /* scaling up here allows division by 1024 in critical code */
    vifp->v_rate_limit= vifcp->vifc_rate_limit * 1024 / 1000;
    vifp->v_rsvp_on   = 0;
    vifp->v_rsvpd     = NULL;
    /* initialize per vif pkt counters */
    vifp->v_pkt_in    = 0;
    vifp->v_pkt_out   = 0;
    vifp->v_bytes_in  = 0;
    vifp->v_bytes_out = 0;
    splx(s);

    /* Adjust numvifs up if the vifi is higher than numvifs */
    if (numvifs <= vifcp->vifc_vifi) numvifs = vifcp->vifc_vifi + 1;

    if (mrtdebug)
	log(LOG_DEBUG, "add_vif #%d, lcladdr %lx, %s %lx, thresh %x, rate %d\n",
	    vifcp->vifc_vifi, 
	    (u_long)ntohl(vifcp->vifc_lcl_addr.s_addr),
	    (vifcp->vifc_flags & VIFF_TUNNEL) ? "rmtaddr" : "mask",
	    (u_long)ntohl(vifcp->vifc_rmt_addr.s_addr),
	    vifcp->vifc_threshold,
	    vifcp->vifc_rate_limit);    

    return 0;
}

/*
 * Delete a vif from the vif table
 */
static int
del_vif(vifi)
	vifi_t vifi;
{
    register struct vif *vifp = &viftable[vifi];
    register struct mbuf *m;
    struct ifnet *ifp;
    struct ifreq ifr;
    int s;

    if (vifi >= numvifs) return EINVAL;
    if (vifp->v_lcl_addr.s_addr == 0) return EADDRNOTAVAIL;

    s = splnet();

    if (!(vifp->v_flags & VIFF_TUNNEL)) {
	((struct sockaddr_in *)&(ifr.ifr_addr))->sin_family = AF_INET;
	((struct sockaddr_in *)&(ifr.ifr_addr))->sin_addr.s_addr = INADDR_ANY;
	ifp = vifp->v_ifp;
	if_allmulti(ifp, 0);
    }

    if (vifp == last_encap_vif) {
	last_encap_vif = 0;
	last_encap_src = 0;
    }

    /*
     * Free packets queued at the interface
     */
    while (vifp->v_tbf->tbf_q) {
	m = vifp->v_tbf->tbf_q;
	vifp->v_tbf->tbf_q = m->m_act;
	m_freem(m);
    }

    bzero((caddr_t)vifp->v_tbf, sizeof(*(vifp->v_tbf)));
    bzero((caddr_t)vifp, sizeof (*vifp));

    if (mrtdebug)
      log(LOG_DEBUG, "del_vif %d, numvifs %d\n", vifi, numvifs);

    /* Adjust numvifs down */
    for (vifi = numvifs; vifi > 0; vifi--)
	if (viftable[vifi-1].v_lcl_addr.s_addr != 0) break;
    numvifs = vifi;

    splx(s);

    return 0;
}

/*
 * Add an mfc entry
 */
static int
add_mfc(mfccp)
    struct mfcctl *mfccp;
{
    struct mfc *rt;
    u_long hash;
    struct rtdetq *rte;
    register u_short nstl;
    int s;
    int i;

    MFCFIND(mfccp->mfcc_origin.s_addr, mfccp->mfcc_mcastgrp.s_addr, rt);

    /* If an entry already exists, just update the fields */
    if (rt) {
	if (mrtdebug & DEBUG_MFC)
	    log(LOG_DEBUG,"add_mfc update o %lx g %lx p %x\n",
		(u_long)ntohl(mfccp->mfcc_origin.s_addr),
		(u_long)ntohl(mfccp->mfcc_mcastgrp.s_addr),
		mfccp->mfcc_parent);

	s = splnet();
	rt->mfc_parent = mfccp->mfcc_parent;
	for (i = 0; i < numvifs; i++)
	    rt->mfc_ttls[i] = mfccp->mfcc_ttls[i];
	splx(s);
	return 0;
    }

    /* 
     * Find the entry for which the upcall was made and update
     */
    s = splnet();
    hash = MFCHASH(mfccp->mfcc_origin.s_addr, mfccp->mfcc_mcastgrp.s_addr);
    for (rt = mfctable[hash], nstl = 0; rt; rt = rt->mfc_next) {

	if ((rt->mfc_origin.s_addr == mfccp->mfcc_origin.s_addr) &&
	    (rt->mfc_mcastgrp.s_addr == mfccp->mfcc_mcastgrp.s_addr) &&
	    (rt->mfc_stall != NULL)) {
  
	    if (nstl++)
		log(LOG_ERR, "add_mfc %s o %lx g %lx p %x dbx %p\n",
		    "multiple kernel entries",
		    (u_long)ntohl(mfccp->mfcc_origin.s_addr),
		    (u_long)ntohl(mfccp->mfcc_mcastgrp.s_addr),
		    mfccp->mfcc_parent, (void *)rt->mfc_stall);

	    if (mrtdebug & DEBUG_MFC)
		log(LOG_DEBUG,"add_mfc o %lx g %lx p %x dbg %p\n",
		    (u_long)ntohl(mfccp->mfcc_origin.s_addr),
		    (u_long)ntohl(mfccp->mfcc_mcastgrp.s_addr),
		    mfccp->mfcc_parent, (void *)rt->mfc_stall);

	    rt->mfc_origin     = mfccp->mfcc_origin;
	    rt->mfc_mcastgrp   = mfccp->mfcc_mcastgrp;
	    rt->mfc_parent     = mfccp->mfcc_parent;
	    for (i = 0; i < numvifs; i++)
		rt->mfc_ttls[i] = mfccp->mfcc_ttls[i];
	    /* initialize pkt counters per src-grp */
	    rt->mfc_pkt_cnt    = 0;
	    rt->mfc_byte_cnt   = 0;
	    rt->mfc_wrong_if   = 0;
	    rt->mfc_last_assert.tv_sec = rt->mfc_last_assert.tv_usec = 0;

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

	    /* free packets Qed at the end of this entry */
	    for (rte = rt->mfc_stall; rte != NULL; ) {
		struct rtdetq *n = rte->next;

		ip_mdq(rte->m, rte->ifp, rt, -1);
		m_freem(rte->m);
#ifdef UPCALL_TIMING
		collate(&(rte->t));
#endif /* UPCALL_TIMING */
		free(rte, M_MRTABLE);
		rte = n;
	    }
	    rt->mfc_stall = NULL;
	}
    }

    /*
     * It is possible that an entry is being inserted without an upcall
     */
    if (nstl == 0) {
	if (mrtdebug & DEBUG_MFC)
	    log(LOG_DEBUG,"add_mfc no upcall h %lu o %lx g %lx p %x\n",
		hash, (u_long)ntohl(mfccp->mfcc_origin.s_addr),
		(u_long)ntohl(mfccp->mfcc_mcastgrp.s_addr),
		mfccp->mfcc_parent);
	
	for (rt = mfctable[hash]; rt != NULL; rt = rt->mfc_next) {
	    
	    if ((rt->mfc_origin.s_addr == mfccp->mfcc_origin.s_addr) &&
		(rt->mfc_mcastgrp.s_addr == mfccp->mfcc_mcastgrp.s_addr)) {

		rt->mfc_origin     = mfccp->mfcc_origin;
		rt->mfc_mcastgrp   = mfccp->mfcc_mcastgrp;
		rt->mfc_parent     = mfccp->mfcc_parent;
		for (i = 0; i < numvifs; i++)
		    rt->mfc_ttls[i] = mfccp->mfcc_ttls[i];
		/* initialize pkt counters per src-grp */
		rt->mfc_pkt_cnt    = 0;
		rt->mfc_byte_cnt   = 0;
		rt->mfc_wrong_if   = 0;
		rt->mfc_last_assert.tv_sec = rt->mfc_last_assert.tv_usec = 0;
		if (rt->mfc_expire)
		    nexpire[hash]--;
		rt->mfc_expire	   = 0;
	    }
	}
	if (rt == NULL) {
	    /* no upcall, so make a new entry */
	    rt = (struct mfc *)malloc(sizeof(*rt), M_MRTABLE, M_NOWAIT);
	    if (rt == NULL) {
		splx(s);
		return ENOBUFS;
	    }
	    
	    /* insert new entry at head of hash chain */
	    rt->mfc_origin     = mfccp->mfcc_origin;
	    rt->mfc_mcastgrp   = mfccp->mfcc_mcastgrp;
	    rt->mfc_parent     = mfccp->mfcc_parent;
	    for (i = 0; i < numvifs; i++)
		    rt->mfc_ttls[i] = mfccp->mfcc_ttls[i];
	    /* initialize pkt counters per src-grp */
	    rt->mfc_pkt_cnt    = 0;
	    rt->mfc_byte_cnt   = 0;
	    rt->mfc_wrong_if   = 0;
	    rt->mfc_last_assert.tv_sec = rt->mfc_last_assert.tv_usec = 0;
	    rt->mfc_expire     = 0;
	    rt->mfc_stall      = NULL;
	    
	    /* link into table */
	    rt->mfc_next = mfctable[hash];
	    mfctable[hash] = rt;
	}
    }
    splx(s);
    return 0;
}

#ifdef UPCALL_TIMING
/*
 * collect delay statistics on the upcalls 
 */
static void collate(t)
register struct timeval *t;
{
    register u_long d;
    register struct timeval tp;
    register u_long delta;
    
    GET_TIME(tp);
    
    if (TV_LT(*t, tp))
    {
	TV_DELTA(tp, *t, delta);
	
	d = delta >> 10;
	if (d > 50)
	    d = 50;
	
	++upcall_data[d];
    }
}
#endif /* UPCALL_TIMING */

/*
 * Delete an mfc entry
 */
static int
del_mfc(mfccp)
    struct mfcctl *mfccp;
{
    struct in_addr 	origin;
    struct in_addr 	mcastgrp;
    struct mfc 		*rt;
    struct mfc	 	**nptr;
    u_long 		hash;
    int s;

    origin = mfccp->mfcc_origin;
    mcastgrp = mfccp->mfcc_mcastgrp;
    hash = MFCHASH(origin.s_addr, mcastgrp.s_addr);

    if (mrtdebug & DEBUG_MFC)
	log(LOG_DEBUG,"del_mfc orig %lx mcastgrp %lx\n",
	    (u_long)ntohl(origin.s_addr), (u_long)ntohl(mcastgrp.s_addr));

    s = splnet();

    nptr = &mfctable[hash];
    while ((rt = *nptr) != NULL) {
	if (origin.s_addr == rt->mfc_origin.s_addr &&
	    mcastgrp.s_addr == rt->mfc_mcastgrp.s_addr &&
	    rt->mfc_stall == NULL)
	    break;

	nptr = &rt->mfc_next;
    }
    if (rt == NULL) {
	splx(s);
	return EADDRNOTAVAIL;
    }

    *nptr = rt->mfc_next;
    free(rt, M_MRTABLE);

    splx(s);

    return 0;
}

/*
 * Send a message to mrouted on the multicast routing socket
 */
static int
socket_send(s, mm, src)
	struct socket *s;
	struct mbuf *mm;
	struct sockaddr_in *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;
}

/*
 * IP multicast forwarding function. This function assumes that the packet
 * pointed to by "ip" 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 IP 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.
 */

#define TUNNEL_LEN  12  /* # bytes of IP option for tunnel encapsulation  */

static int
X_ip_mforward(ip, ifp, m, imo)
    register struct ip *ip;
    struct ifnet *ifp;
    struct mbuf *m;
    struct ip_moptions *imo;
{
    register struct mfc *rt;
    register u_char *ipoptions;
    static struct sockaddr_in 	k_igmpsrc	= { sizeof k_igmpsrc, AF_INET };
    static int srctun = 0;
    register struct mbuf *mm;
    int s;
    vifi_t vifi;
    struct vif *vifp;

    if (mrtdebug & DEBUG_FORWARD)
	log(LOG_DEBUG, "ip_mforward: src %lx, dst %lx, ifp %p\n",
	    (u_long)ntohl(ip->ip_src.s_addr), (u_long)ntohl(ip->ip_dst.s_addr),
	    (void *)ifp);

    if (ip->ip_hl < (sizeof(struct ip) + TUNNEL_LEN) >> 2 ||
	(ipoptions = (u_char *)(ip + 1))[1] != IPOPT_LSRR ) {
	/*
	 * Packet arrived via a physical interface or
	 * an encapsulated tunnel.
	 */
    } else {
	/*
	 * Packet arrived through a source-route tunnel.
	 * Source-route tunnels are no longer supported.
	 */
	if ((srctun++ % 1000) == 0)
	    log(LOG_ERR,
		"ip_mforward: received source-routed packet from %lx\n",
		(u_long)ntohl(ip->ip_src.s_addr));

	return 1;
    }

    if ((imo) && ((vifi = imo->imo_multicast_vif) < numvifs)) {
	if (ip->ip_ttl < 255)
		ip->ip_ttl++;	/* compensate for -1 in *_send routines */
	if (rsvpdebug && ip->ip_p == IPPROTO_RSVP) {
	    vifp = viftable + vifi;
	    printf("Sending IPPROTO_RSVP from %lx to %lx on vif %d (%s%s%d)\n",
		(long)ntohl(ip->ip_src.s_addr), (long)ntohl(ip->ip_dst.s_addr),
		vifi,
		(vifp->v_flags & VIFF_TUNNEL) ? "tunnel on " : "",
		vifp->v_ifp->if_name, vifp->v_ifp->if_unit);
	}
	return (ip_mdq(m, ifp, NULL, vifi));
    }
    if (rsvpdebug && ip->ip_p == IPPROTO_RSVP) {
	printf("Warning: IPPROTO_RSVP from %lx to %lx without vif option\n",
	    (long)ntohl(ip->ip_src.s_addr), (long)ntohl(ip->ip_dst.s_addr));
	if(!imo)
		printf("In fact, no options were specified at all\n");
    }

    /*
     * Don't forward a packet with time-to-live of zero or one,
     * or a packet destined to a local-only group.
     */
    if (ip->ip_ttl <= 1 ||
	ntohl(ip->ip_dst.s_addr) <= INADDR_MAX_LOCAL_GROUP)
	return 0;

    /*
     * Determine forwarding vifs from the forwarding cache table
     */
    s = splnet();
    MFCFIND(ip->ip_src.s_addr, ip->ip_dst.s_addr, rt);

    /* Entry exists, so forward if necessary */
    if (rt != NULL) {
	splx(s);
	return (ip_mdq(m, ifp, rt, -1));
    } else {
	/*
	 * If we don't have a route for packet's origin,
	 * Make a copy of the packet &
	 * send message to routing daemon
	 */

	register struct mbuf *mb0;
	register struct rtdetq *rte;
	register u_long hash;
	int hlen = ip->ip_hl << 2;
#ifdef UPCALL_TIMING
	struct timeval tp;

	GET_TIME(tp);
#endif

	mrtstat.mrts_no_route++;
	if (mrtdebug & (DEBUG_FORWARD | DEBUG_MFC))
	    log(LOG_DEBUG, "ip_mforward: no rte s %lx g %lx\n",
		(u_long)ntohl(ip->ip_src.s_addr),
		(u_long)ntohl(ip->ip_dst.s_addr));

	/*
	 * Allocate mbufs early so that we don't do extra work if we are
	 * just going to fail anyway.  Make sure to pullup the header so
	 * that other people can't step on it.
	 */
	rte = (struct rtdetq *)malloc((sizeof *rte), M_MRTABLE, M_NOWAIT);
	if (rte == NULL) {
	    splx(s);
	    return ENOBUFS;
	}
	mb0 = m_copy(m, 0, M_COPYALL);
	if (mb0 && (M_HASCL(mb0) || mb0->m_len < hlen))
	    mb0 = m_pullup(mb0, hlen);
	if (mb0 == NULL) {
	    free(rte, M_MRTABLE);
	    splx(s);
	    return ENOBUFS;
	}

	/* is there an upcall waiting for this packet? */
	hash = MFCHASH(ip->ip_src.s_addr, ip->ip_dst.s_addr);
	for (rt = mfctable[hash]; rt; rt = rt->mfc_next) {
	    if ((ip->ip_src.s_addr == rt->mfc_origin.s_addr) &&
		(ip->ip_dst.s_addr == rt->mfc_mcastgrp.s_addr) &&
		(rt->mfc_stall != NULL))
		break;
	}

	if (rt == NULL) {
	    int i;
	    struct igmpmsg *im;

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

	    /* 
	     * Send message to routing daemon to install 
	     * a route into the kernel table
	     */
	    k_igmpsrc.sin_addr = ip->ip_src;
	    
	    im = mtod(mm, struct igmpmsg *);
	    im->im_msgtype	= IGMPMSG_NOCACHE;
	    im->im_mbz		= 0;

	    mrtstat.mrts_upcalls++;

	    if (socket_send(ip_mrouter, mm, &k_igmpsrc) < 0) {
		log(LOG_WARNING, "ip_mforward: ip_mrouter socket queue full\n");
		++mrtstat.mrts_upq_sockfull;
		free(rte, M_MRTABLE);
		m_freem(mb0);
		free(rt, M_MRTABLE);
		splx(s);
		return ENOBUFS;
	    }

	    /* insert new entry at head of hash chain */
	    rt->mfc_origin.s_addr     = ip->ip_src.s_addr;
	    rt->mfc_mcastgrp.s_addr   = ip->ip_dst.s_addr;
	    rt->mfc_expire	      = UPCALL_EXPIRE;
	    nexpire[hash]++;
	    for (i = 0; i < numvifs; i++)
		rt->mfc_ttls[i] = 0;
	    rt->mfc_parent = -1;

	    /* link into table */
	    rt->mfc_next   = mfctable[hash];
	    mfctable[hash] = rt;
	    rt->mfc_stall = rte;

	} else {
	    /* determine if q has overflowed */
	    int npkts = 0;
	    struct rtdetq **p;

	    for (p = &rt->mfc_stall; *p != NULL; p = &(*p)->next)
		npkts++;

	    if (npkts > MAX_UPQ) {
		mrtstat.mrts_upq_ovflw++;
		free(rte, M_MRTABLE);
		m_freem(mb0);
		splx(s);
		return 0;
	    }

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

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

	splx(s);

	return 0;
    }		
}

#ifndef MROUTE_KLD
int (*ip_mforward)(struct ip *, struct ifnet *, struct mbuf *,
		   struct ip_moptions *) = X_ip_mforward;
#endif

/*
 * Clean up the cache entry if upcall is not serviced
 */
static void
expire_upcalls(void *unused)
{
    struct rtdetq *rte;
    struct mfc *mfc, **nptr;
    int i;
    int s;

    s = splnet();
    for (i = 0; i < MFCTBLSIZ; i++) {
	if (nexpire[i] == 0)
	    continue;
	nptr = &mfctable[i];
	for (mfc = *nptr; mfc != NULL; mfc = *nptr) {
	    /*
	     * Skip real cache entries
	     * Make sure it wasn't marked to not expire (shouldn't happen)
	     * If it expires now
	     */
	    if (mfc->mfc_stall != NULL &&
	        mfc->mfc_expire != 0 &&
		--mfc->mfc_expire == 0) {
		if (mrtdebug & DEBUG_EXPIRE)
		    log(LOG_DEBUG, "expire_upcalls: expiring (%lx %lx)\n",
			(u_long)ntohl(mfc->mfc_origin.s_addr),
			(u_long)ntohl(mfc->mfc_mcastgrp.s_addr));
		/*
		 * drop all the packets
		 * free the mbuf with the pkt, if, timing info
		 */
		for (rte = mfc->mfc_stall; rte; ) {
		    struct rtdetq *n = rte->next;

		    m_freem(rte->m);
		    free(rte, M_MRTABLE);
		    rte = n;
		}
		++mrtstat.mrts_cache_cleanups;
		nexpire[i]--;

		*nptr = mfc->mfc_next;
		free(mfc, M_MRTABLE);
	    } else {
		nptr = &mfc->mfc_next;
	    }
	}
    }
    splx(s);
    expire_upcalls_ch = timeout(expire_upcalls, (caddr_t)NULL, EXPIRE_TIMEOUT);
}

/*
 * Packet forwarding routine once entry in the cache is made
 */
static int
ip_mdq(m, ifp, rt, xmt_vif)
    register struct mbuf *m;
    register struct ifnet *ifp;
    register struct mfc *rt;
    register vifi_t xmt_vif;
{
    register struct ip  *ip = mtod(m, struct ip *);
    register vifi_t vifi;
    register struct vif *vifp;
    register int plen = ip->ip_len;

/*
 * Macro to send packet on vif.  Since RSVP packets don't get counted on
 * input, they shouldn't get counted on output, so statistics keeping is
 * separate.
 */
#define MC_SEND(ip,vifp,m) {                             \
                if ((vifp)->v_flags & VIFF_TUNNEL)  	 \
                    encap_send((ip), (vifp), (m));       \
                else                                     \
                    phyint_send((ip), (vifp), (m));      \
}

    /*
     * If xmt_vif is not -1, send on only the requested vif.
     *
     * (since vifi_t is u_short, -1 becomes MAXUSHORT, which > numvifs.)
     */
    if (xmt_vif < numvifs) {
	MC_SEND(ip, viftable + xmt_vif, m);
	return 1;
    }

    /*
     * Don't forward if it didn't arrive from the parent vif for its origin.
     */
    vifi = rt->mfc_parent;
    if ((vifi >= numvifs) || (viftable[vifi].v_ifp != ifp)) {
	/* came in the wrong interface */
	if (mrtdebug & DEBUG_FORWARD)
	    log(LOG_DEBUG, "wrong if: ifp %p vifi %d vififp %p\n",
		(void *)ifp, vifi, (void *)viftable[vifi].v_ifp); 
	++mrtstat.mrts_wrong_if;
	++rt->mfc_wrong_if;
	/*
	 * If we are doing PIM assert processing, and we are forwarding
	 * packets on this interface, and it is a broadcast medium
	 * interface (and not a tunnel), send a message to the routing daemon.
	 */
	if (pim_assert && rt->mfc_ttls[vifi] &&
		(ifp->if_flags & IFF_BROADCAST) &&
		!(viftable[vifi].v_flags & VIFF_TUNNEL)) {
	    struct sockaddr_in k_igmpsrc;
	    struct mbuf *mm;
	    struct igmpmsg *im;
	    int hlen = ip->ip_hl << 2;
	    struct timeval now;
	    register u_long delta;

	    GET_TIME(now);

	    TV_DELTA(rt->mfc_last_assert, now, delta);

	    if (delta > ASSERT_MSG_TIME) {
		mm = m_copy(m, 0, hlen);
		if (mm && (M_HASCL(mm) || mm->m_len < hlen))
		    mm = m_pullup(mm, hlen);
		if (mm == NULL) {
		    return ENOBUFS;
		}

		rt->mfc_last_assert = now;

		im = mtod(mm, struct igmpmsg *);
		im->im_msgtype	= IGMPMSG_WRONGVIF;
		im->im_mbz		= 0;
		im->im_vif		= vifi;

		k_igmpsrc.sin_addr = im->im_src;

		socket_send(ip_mrouter, mm, &k_igmpsrc);
	    }
	}
	return 0;
    }

    /* If I sourced this packet, it counts as output, else it was input. */
    if (ip->ip_src.s_addr == viftable[vifi].v_lcl_addr.s_addr) {
	viftable[vifi].v_pkt_out++;
	viftable[vifi].v_bytes_out += plen;
    } else {
	viftable[vifi].v_pkt_in++;
	viftable[vifi].v_bytes_in += plen;
    }
    rt->mfc_pkt_cnt++;
    rt->mfc_byte_cnt += plen;

    /*
     * For each vif, decide if a copy of the packet should be forwarded.
     * Forward if:
     *		- the ttl exceeds the vif's threshold
     *		- there are group members downstream on interface
     */
    for (vifp = viftable, vifi = 0; vifi < numvifs; vifp++, vifi++)
	if ((rt->mfc_ttls[vifi] > 0) &&
	    (ip->ip_ttl > rt->mfc_ttls[vifi])) {
	    vifp->v_pkt_out++;
	    vifp->v_bytes_out += plen;
	    MC_SEND(ip, vifp, m);
	}

    return 0;
}

/*
 * check if a vif number is legal/ok. This is used by ip_output, to export
 * numvifs there, 
 */
static int
X_legal_vif_num(vif)
    int vif;
{
    if (vif >= 0 && vif < numvifs)
       return(1);
    else
       return(0);
}

#ifndef MROUTE_KLD
int (*legal_vif_num)(int) = X_legal_vif_num;
#endif

/*
 * Return the local address used by this vif
 */
static u_long
X_ip_mcast_src(vifi)
    int vifi;
{
    if (vifi >= 0 && vifi < numvifs)
	return viftable[vifi].v_lcl_addr.s_addr;
    else
	return INADDR_ANY;
}

#ifndef MROUTE_KLD
u_long (*ip_mcast_src)(int) = X_ip_mcast_src;
#endif

static void
phyint_send(ip, vifp, m)
    struct ip *ip;
    struct vif *vifp;
    struct mbuf *m;
{
    register struct mbuf *mb_copy;
    register int hlen = ip->ip_hl << 2;

    /*
     * Make a new reference to the packet; make sure that
     * the IP header is actually copied, not just referenced,
     * so that ip_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 < hlen))
	mb_copy = m_pullup(mb_copy, hlen);
    if (mb_copy == NULL)
	return;

    if (vifp->v_rate_limit == 0)
	tbf_send_packet(vifp, mb_copy);
    else
	tbf_control(vifp, mb_copy, mtod(mb_copy, struct ip *), ip->ip_len);
}

static void
encap_send(ip, vifp, m)
    register struct ip *ip;
    register struct vif *vifp;
    register struct mbuf *m;
{
    register struct mbuf *mb_copy;
    register struct ip *ip_copy;
    register int i, len = ip->ip_len;

    /*
     * copy the old packet & pullup its IP header into the
     * new mbuf so we can modify it.  Try to fill the new
     * mbuf since if we don't the ethernet driver will.
     */
    MGETHDR(mb_copy, M_DONTWAIT, MT_HEADER);
    if (mb_copy == NULL)
	return;
#ifdef MAC
    mac_create_mbuf_multicast_encap(m, vifp->v_ifp, mb_copy);
#endif
    mb_copy->m_data += max_linkhdr;
    mb_copy->m_len = sizeof(multicast_encap_iphdr);

    if ((mb_copy->m_next = m_copy(m, 0, M_COPYALL)) == NULL) {
	m_freem(mb_copy);
	return;
    }
    i = MHLEN - M_LEADINGSPACE(mb_copy);
    if (i > len)
	i = len;
    mb_copy = m_pullup(mb_copy, i);
    if (mb_copy == NULL)
	return;
    mb_copy->m_pkthdr.len = len + sizeof(multicast_encap_iphdr);

    /*
     * fill in the encapsulating IP header.
     */
    ip_copy = mtod(mb_copy, struct ip *);
    *ip_copy = multicast_encap_iphdr;
#ifdef RANDOM_IP_ID
    ip_copy->ip_id = ip_randomid();
#else
    ip_copy->ip_id = htons(ip_id++);
#endif
    ip_copy->ip_len += len;
    ip_copy->ip_src = vifp->v_lcl_addr;
    ip_copy->ip_dst = vifp->v_rmt_addr;

    /*
     * turn the encapsulated IP header back into a valid one.
     */
    ip = (struct ip *)((caddr_t)ip_copy + sizeof(multicast_encap_iphdr));
    --ip->ip_ttl;
    ip->ip_len = htons(ip->ip_len);
    ip->ip_off = htons(ip->ip_off);
    ip->ip_sum = 0;
    mb_copy->m_data += sizeof(multicast_encap_iphdr);
    ip->ip_sum = in_cksum(mb_copy, ip->ip_hl << 2);
    mb_copy->m_data -= sizeof(multicast_encap_iphdr);

    if (vifp->v_rate_limit == 0)
	tbf_send_packet(vifp, mb_copy);
    else
	tbf_control(vifp, mb_copy, ip, ip_copy->ip_len);
}

/*
 * Token bucket filter module
 */

static void
tbf_control(vifp, m, ip, p_len)
	register struct vif *vifp;
	register struct mbuf *m;
	register struct ip *ip;
	register u_long p_len;
{
    register struct tbf *t = vifp->v_tbf;

    if (p_len > MAX_BKT_SIZE) {
	/* drop if packet is too large */
	mrtstat.mrts_pkt2large++;
	m_freem(m);
	return;
    }

    tbf_update_tokens(vifp);

    /* if there are enough tokens, 
     * and the queue is empty,
     * send this packet out
     */

    if (t->tbf_q_len == 0) {
	/* queue empty, send packet if enough tokens */
	if (p_len <= t->tbf_n_tok) {
	    t->tbf_n_tok -= p_len;
	    tbf_send_packet(vifp, m);
	} else {
	    /* queue packet and timeout till later */
	    tbf_queue(vifp, m);
	    timeout(tbf_reprocess_q, (caddr_t)vifp, TBF_REPROCESS);
	}
    } else if (t->tbf_q_len < t->tbf_max_q_len) {
	/* finite queue length, so queue pkts and process queue */
	tbf_queue(vifp, m);
	tbf_process_q(vifp);
    } else {
	/* queue length too much, try to dq and queue and process */
	if (!tbf_dq_sel(vifp, ip)) {
	    mrtstat.mrts_q_overflow++;
	    m_freem(m);
	    return;
	} else {
	    tbf_queue(vifp, m);
	    tbf_process_q(vifp);
	}
    }
    return;
}

/* 
 * adds a packet to the queue at the interface
 */
static void
tbf_queue(vifp, m) 
	register struct vif *vifp;
	register struct mbuf *m;
{
    register int s = splnet();
    register struct tbf *t = vifp->v_tbf;

    if (t->tbf_t == NULL) {
	/* Queue was empty */
	t->tbf_q = m;
    } else {
	/* Insert at tail */
	t->tbf_t->m_act = m;
    }

    /* Set new tail pointer */
    t->tbf_t = m;

#ifdef DIAGNOSTIC
    /* Make sure we didn't get fed a bogus mbuf */
    if (m->m_act)
	panic("tbf_queue: m_act");
#endif
    m->m_act = NULL;

    t->tbf_q_len++;

    splx(s);
}


/* 
 * processes the queue at the interface
 */
static void
tbf_process_q(vifp)
    register struct vif *vifp;
{
    register struct mbuf *m;
    register int len;
    register int s = splnet();
    register struct tbf *t = vifp->v_tbf;

    /* loop through the queue at the interface and send as many packets
     * as possible
     */
    while (t->tbf_q_len > 0) {
	m = t->tbf_q;

	len = mtod(m, struct ip *)->ip_len;

	/* determine if the packet can be sent */
	if (len <= t->tbf_n_tok) {
	    /* if so,
	     * reduce no of tokens, dequeue the packet,
	     * send the packet.
	     */
	    t->tbf_n_tok -= len;

	    t->tbf_q = m->m_act;
	    if (--t->tbf_q_len == 0)
		t->tbf_t = NULL;

	    m->m_act = NULL;
	    tbf_send_packet(vifp, m);

	} else break;
    }
    splx(s);
}

static void
tbf_reprocess_q(xvifp)
	void *xvifp;
{
    register struct vif *vifp = xvifp;
    if (ip_mrouter == NULL) 
	return;

    tbf_update_tokens(vifp);

    tbf_process_q(vifp);

    if (vifp->v_tbf->tbf_q_len)
	timeout(tbf_reprocess_q, (caddr_t)vifp, TBF_REPROCESS);
}

/* function that will selectively discard a member of the queue
 * based on the precedence value and the priority
 */
static int
tbf_dq_sel(vifp, ip)
    register struct vif *vifp;
    register struct ip *ip;
{
    register int s = splnet();
    register u_int p;
    register struct mbuf *m, *last;
    register struct mbuf **np;
    register struct tbf *t = vifp->v_tbf;

    p = priority(vifp, ip);

    np = &t->tbf_q;
    last = NULL;
    while ((m = *np) != NULL) {
	if (p > priority(vifp, mtod(m, struct ip *))) {
	    *np = m->m_act;
	    /* If we're removing the last packet, fix the tail pointer */
	    if (m == t->tbf_t)
		t->tbf_t = last;
	    m_freem(m);
	    /* it's impossible for the queue to be empty, but
	     * we check anyway. */
	    if (--t->tbf_q_len == 0)
		t->tbf_t = NULL;
	    splx(s);
	    mrtstat.mrts_drop_sel++;
	    return(1);
	}
	np = &m->m_act;
	last = m;
    }
    splx(s);
    return(0);
}

static void
tbf_send_packet(vifp, m)
    register struct vif *vifp;
    register struct mbuf *m;
{
    struct ip_moptions imo;
    int error;
    static struct route ro;
    int s = splnet();

    if (vifp->v_flags & VIFF_TUNNEL) {
	/* If tunnel options */
	ip_output(m, (struct mbuf *)0, &vifp->v_route,
		  IP_FORWARDING, (struct ip_moptions *)0, NULL);
    } else {
	imo.imo_multicast_ifp  = vifp->v_ifp;
	imo.imo_multicast_ttl  = mtod(m, struct ip *)->ip_ttl - 1;
	imo.imo_multicast_loop = 1;
	imo.imo_multicast_vif  = -1;

	/*
	 * Re-entrancy should not be a problem here, because
	 * the packets that we send out and are looped back at us
	 * should get rejected because they appear to come from
	 * the loopback interface, thus preventing looping.
	 */
	error = ip_output(m, (struct mbuf *)0, &ro,
			  IP_FORWARDING, &imo, NULL);

	if (mrtdebug & DEBUG_XMIT)
	    log(LOG_DEBUG, "phyint_send on vif %d err %d\n", 
		vifp - viftable, error);
    }
    splx(s);
}

/* determine the current time and then
 * the elapsed time (between the last time and time now)
 * in milliseconds & update the no. of tokens in the bucket
 */
static void
tbf_update_tokens(vifp)
    register struct vif *vifp;
{
    struct timeval tp;
    register u_long tm;
    register int s = splnet();
    register struct tbf *t = vifp->v_tbf;

    GET_TIME(tp);

    TV_DELTA(tp, t->tbf_last_pkt_t, tm);

    /*
     * This formula is actually
     * "time in seconds" * "bytes/second".
     *
     * (tm / 1000000) * (v_rate_limit * 1000 * (1000/1024) / 8)
     *
     * The (1000/1024) was introduced in add_vif to optimize
     * this divide into a shift.
     */
    t->tbf_n_tok += tm * vifp->v_rate_limit / 1024 / 8;
    t->tbf_last_pkt_t = tp;

    if (t->tbf_n_tok > MAX_BKT_SIZE)
	t->tbf_n_tok = MAX_BKT_SIZE;

    splx(s);
}

static int
priority(vifp, ip)
    register struct vif *vifp;
    register struct ip *ip;
{
    register int prio;

    /* temporary hack; may add general packet classifier some day */

    /*
     * The UDP port space is divided up into four priority ranges:
     * [0, 16384)     : unclassified - lowest priority
     * [16384, 32768) : audio - highest priority
     * [32768, 49152) : whiteboard - medium priority
     * [49152, 65536) : video - low priority
     */
    if (ip->ip_p == IPPROTO_UDP) {
	struct udphdr *udp = (struct udphdr *)(((char *)ip) + (ip->ip_hl << 2));
	switch (ntohs(udp->uh_dport) & 0xc000) {
	    case 0x4000:
		prio = 70;
		break;
	    case 0x8000:
		prio = 60;
		break;
	    case 0xc000:
		prio = 55;
		break;
	    default:
		prio = 50;
		break;
	}
	if (tbfdebug > 1)
		log(LOG_DEBUG, "port %x prio%d\n", ntohs(udp->uh_dport), prio);
    } else {
	    prio = 50;
    }
    return prio;
}

/*
 * End of token bucket filter modifications 
 */

int
ip_rsvp_vif_init(so, sopt)
	struct socket *so;
	struct sockopt *sopt;
{
    int error, i, s;

    if (rsvpdebug)
	printf("ip_rsvp_vif_init: so_type = %d, pr_protocol = %d\n",
	       so->so_type, so->so_proto->pr_protocol);

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

    /* Check mbuf. */
    error = sooptcopyin(sopt, &i, sizeof i, sizeof i);
    if (error)
	    return (error);
 
    if (rsvpdebug)
	printf("ip_rsvp_vif_init: vif = %d rsvp_on = %d\n", i, rsvp_on);
 
    s = splnet();

    /* Check vif. */
    if (!legal_vif_num(i)) {
	splx(s);
	return EADDRNOTAVAIL;
    }

    /* Check if socket is available. */
    if (viftable[i].v_rsvpd != NULL) {
	splx(s);
	return EADDRINUSE;
    }

    viftable[i].v_rsvpd = so;
    /* This may seem silly, but we need to be sure we don't over-increment
     * the RSVP counter, in case something slips up.
     */
    if (!viftable[i].v_rsvp_on) {
	viftable[i].v_rsvp_on = 1;
	rsvp_on++;
    }

    splx(s);
    return 0;
}

int
ip_rsvp_vif_done(so, sopt)
	struct socket *so;
	struct sockopt *sopt;
{
	int error, i, s;
 
	if (rsvpdebug)
		printf("ip_rsvp_vif_done: so_type = %d, pr_protocol = %d\n",
		       so->so_type, so->so_proto->pr_protocol);
 
	if (so->so_type != SOCK_RAW || 
	    so->so_proto->pr_protocol != IPPROTO_RSVP)
		return EOPNOTSUPP;
 
	error = sooptcopyin(sopt, &i, sizeof i, sizeof i);
	if (error)
		return (error);
 
	s = splnet();
 
	/* Check vif. */
	if (!legal_vif_num(i)) {
		splx(s);
		return EADDRNOTAVAIL;
	}

	if (rsvpdebug)
		printf("ip_rsvp_vif_done: v_rsvpd = %p so = %p\n",
		       viftable[i].v_rsvpd, so);

	/*
	 * XXX as an additional consistency check, one could make sure
	 * that viftable[i].v_rsvpd == so, otherwise passing so as
	 * first parameter is pretty useless.
	 */
	viftable[i].v_rsvpd = NULL;
	/*
	 * This may seem silly, but we need to be sure we don't over-decrement
	 * the RSVP counter, in case something slips up.
	 */
	if (viftable[i].v_rsvp_on) {
		viftable[i].v_rsvp_on = 0;
		rsvp_on--;
	}

	splx(s);
	return 0;
}

void
ip_rsvp_force_done(so)
    struct socket *so;
{
    int vifi;
    register int s;

    /* Don't bother if it is not the right type of socket. */
    if (so->so_type != SOCK_RAW || so->so_proto->pr_protocol != IPPROTO_RSVP)
	return;

    s = splnet();

    /* The socket may be attached to more than one vif...this
     * is perfectly legal.
     */
    for (vifi = 0; vifi < numvifs; vifi++) {
	if (viftable[vifi].v_rsvpd == so) {
	    viftable[vifi].v_rsvpd = NULL;
	    /* This may seem silly, but we need to be sure we don't
	     * over-decrement the RSVP counter, in case something slips up.
	     */
	    if (viftable[vifi].v_rsvp_on) {
		viftable[vifi].v_rsvp_on = 0;
		rsvp_on--;
	    }
	}
    }

    splx(s);
    return;
}

void
rsvp_input(m, off)
	struct mbuf *m;
	int off;
{
    int vifi;
    register struct ip *ip = mtod(m, struct ip *);
    static struct sockaddr_in rsvp_src = { sizeof rsvp_src, AF_INET };
    register int s;
    struct ifnet *ifp;

    if (rsvpdebug)
	printf("rsvp_input: rsvp_on %d\n",rsvp_on);

    /* Can still get packets with rsvp_on = 0 if there is a local member
     * of the group to which the RSVP packet is addressed.  But in this
     * case we want to throw the packet away.
     */
    if (!rsvp_on) {
	m_freem(m);
	return;
    }

    s = splnet();

    if (rsvpdebug)
	printf("rsvp_input: check vifs\n");

#ifdef DIAGNOSTIC
    if (!(m->m_flags & M_PKTHDR))
	    panic("rsvp_input no hdr");
#endif

    ifp = m->m_pkthdr.rcvif;
    /* Find which vif the packet arrived on. */
    for (vifi = 0; vifi < numvifs; vifi++)
	if (viftable[vifi].v_ifp == ifp)
	    break;

    if (vifi == numvifs || viftable[vifi].v_rsvpd == NULL) {
	/*
	 * If the old-style non-vif-associated socket is set,
	 * then use it.  Otherwise, drop packet since there
	 * is no specific socket for this vif.
	 */
	if (ip_rsvpd != NULL) {
	    if (rsvpdebug)
		printf("rsvp_input: Sending packet up old-style socket\n");
	    rip_input(m, off);  /* xxx */
	} else {
	    if (rsvpdebug && vifi == numvifs)
		printf("rsvp_input: Can't find vif for packet.\n");
	    else if (rsvpdebug && viftable[vifi].v_rsvpd == NULL)
		printf("rsvp_input: No socket defined for vif %d\n",vifi);
	    m_freem(m);
	}
	splx(s);
	return;
    }
    rsvp_src.sin_addr = ip->ip_src;

    if (rsvpdebug && m)
	printf("rsvp_input: m->m_len = %d, sbspace() = %ld\n",
	       m->m_len,sbspace(&(viftable[vifi].v_rsvpd->so_rcv)));

    if (socket_send(viftable[vifi].v_rsvpd, m, &rsvp_src) < 0) {
	if (rsvpdebug)
	    printf("rsvp_input: Failed to append to socket\n");
    } else {
	if (rsvpdebug)
	    printf("rsvp_input: send packet up\n");
    }

    splx(s);
}

#ifdef MROUTE_KLD

static int
ip_mroute_modevent(module_t mod, int type, void *unused)
{
	int s;

	switch (type) {
		static u_long (*old_ip_mcast_src)(int);
		static int (*old_ip_mrouter_set)(struct socket *,
			struct sockopt *);
		static int (*old_ip_mrouter_get)(struct socket *,
			struct sockopt *);
		static int (*old_ip_mrouter_done)(void);
		static int (*old_ip_mforward)(struct ip *, struct ifnet *,
			struct mbuf *, struct ip_moptions *);
		static int (*old_mrt_ioctl)(int, caddr_t);
		static int (*old_legal_vif_num)(int);

	case MOD_LOAD:
		s = splnet();
		/* XXX Protect against multiple loading */
		old_ip_mcast_src = ip_mcast_src;
		ip_mcast_src = X_ip_mcast_src;
		old_ip_mrouter_get = ip_mrouter_get;
		ip_mrouter_get = X_ip_mrouter_get;
		old_ip_mrouter_set = ip_mrouter_set;
		ip_mrouter_set = X_ip_mrouter_set;
		old_ip_mrouter_done = ip_mrouter_done;
		ip_mrouter_done = X_ip_mrouter_done;
		old_ip_mforward = ip_mforward;
		ip_mforward = X_ip_mforward;
		old_mrt_ioctl = mrt_ioctl;
		mrt_ioctl = X_mrt_ioctl;
		old_legal_vif_num = legal_vif_num;
		legal_vif_num = X_legal_vif_num;

		splx(s);
		return 0;

	case MOD_UNLOAD:
		if (ip_mrouter)
		  return EINVAL;

		s = splnet();
		ip_mrouter_get = old_ip_mrouter_get;
		ip_mrouter_set = old_ip_mrouter_set;
		ip_mrouter_done = old_ip_mrouter_done;
		ip_mforward = old_ip_mforward;
		mrt_ioctl = old_mrt_ioctl;
		legal_vif_num = old_legal_vif_num;
		splx(s);
		return 0;

	default:
		break;
	}
	return 0;
}

static moduledata_t ip_mroutemod = {
	"ip_mroute",
	ip_mroute_modevent,
	0
};
DECLARE_MODULE(ip_mroute, ip_mroutemod, SI_SUB_PSEUDO, SI_ORDER_ANY);

#endif /* MROUTE_KLD */
#endif /* MROUTING */
OpenPOWER on IntegriCloud