summaryrefslogtreecommitdiffstats
path: root/sys/netinet/ip_input.c
blob: 8173a25ab4185b9ba2b3c360bc43fbbea6a4b6fa (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
/*
 * Copyright (c) 1982, 1986, 1988, 1993
 *	The Regents of the University of California.  All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgement:
 *	This product includes software developed by the University of
 *	California, Berkeley and its contributors.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 *	@(#)ip_input.c	8.2 (Berkeley) 1/4/94
 * $FreeBSD$
 */

#include "opt_bootp.h"
#include "opt_ipfw.h"
#include "opt_ipdn.h"
#include "opt_ipdivert.h"
#include "opt_ipfilter.h"
#include "opt_ipstealth.h"
#include "opt_ipsec.h"
#include "opt_mac.h"
#include "opt_pfil_hooks.h"
#include "opt_random_ip_id.h"

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/mac.h>
#include <sys/mbuf.h>
#include <sys/malloc.h>
#include <sys/domain.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/time.h>
#include <sys/kernel.h>
#include <sys/syslog.h>
#include <sys/sysctl.h>

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

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

#include <sys/socketvar.h>

#include <netinet/ip_fw.h>
#include <netinet/ip_dummynet.h>

#ifdef IPSEC
#include <netinet6/ipsec.h>
#include <netkey/key.h>
#endif

#ifdef FAST_IPSEC
#include <netipsec/ipsec.h>
#include <netipsec/key.h>
#endif

int rsvp_on = 0;

int	ipforwarding = 0;
SYSCTL_INT(_net_inet_ip, IPCTL_FORWARDING, forwarding, CTLFLAG_RW,
    &ipforwarding, 0, "Enable IP forwarding between interfaces");

static int	ipsendredirects = 1; /* XXX */
SYSCTL_INT(_net_inet_ip, IPCTL_SENDREDIRECTS, redirect, CTLFLAG_RW,
    &ipsendredirects, 0, "Enable sending IP redirects");

int	ip_defttl = IPDEFTTL;
SYSCTL_INT(_net_inet_ip, IPCTL_DEFTTL, ttl, CTLFLAG_RW,
    &ip_defttl, 0, "Maximum TTL on IP packets");

static int	ip_dosourceroute = 0;
SYSCTL_INT(_net_inet_ip, IPCTL_SOURCEROUTE, sourceroute, CTLFLAG_RW,
    &ip_dosourceroute, 0, "Enable forwarding source routed IP packets");

static int	ip_acceptsourceroute = 0;
SYSCTL_INT(_net_inet_ip, IPCTL_ACCEPTSOURCEROUTE, accept_sourceroute, 
    CTLFLAG_RW, &ip_acceptsourceroute, 0, 
    "Enable accepting source routed IP packets");

static int	ip_keepfaith = 0;
SYSCTL_INT(_net_inet_ip, IPCTL_KEEPFAITH, keepfaith, CTLFLAG_RW,
	&ip_keepfaith,	0,
	"Enable packet capture for FAITH IPv4->IPv6 translater daemon");

static int	ip_nfragpackets = 0;
static int	ip_maxfragpackets;	/* initialized in ip_init() */
SYSCTL_INT(_net_inet_ip, OID_AUTO, maxfragpackets, CTLFLAG_RW,
	&ip_maxfragpackets, 0,
	"Maximum number of IPv4 fragment reassembly queue entries");

/*
 * XXX - Setting ip_checkinterface mostly implements the receive side of
 * the Strong ES model described in RFC 1122, but since the routing table
 * and transmit implementation do not implement the Strong ES model,
 * setting this to 1 results in an odd hybrid.
 *
 * XXX - ip_checkinterface currently must be disabled if you use ipnat
 * to translate the destination address to another local interface.
 *
 * XXX - ip_checkinterface must be disabled if you add IP aliases
 * to the loopback interface instead of the interface where the
 * packets for those addresses are received.
 */
static int	ip_checkinterface = 1;
SYSCTL_INT(_net_inet_ip, OID_AUTO, check_interface, CTLFLAG_RW,
    &ip_checkinterface, 0, "Verify packet arrives on correct interface");

#ifdef DIAGNOSTIC
static int	ipprintfs = 0;
#endif

static int	ipqmaxlen = IFQ_MAXLEN;

extern	struct domain inetdomain;
extern	struct protosw inetsw[];
u_char	ip_protox[IPPROTO_MAX];
struct	in_ifaddrhead in_ifaddrhead; 		/* first inet address */
struct	in_ifaddrhashhead *in_ifaddrhashtbl;	/* inet addr hash table  */
u_long 	in_ifaddrhmask;				/* mask for hash table */

SYSCTL_INT(_net_inet_ip, IPCTL_INTRQMAXLEN, intr_queue_maxlen, CTLFLAG_RW,
    &ipintrq.ifq_maxlen, 0, "Maximum size of the IP input queue");
SYSCTL_INT(_net_inet_ip, IPCTL_INTRQDROPS, intr_queue_drops, CTLFLAG_RD,
    &ipintrq.ifq_drops, 0, "Number of packets dropped from the IP input queue");

struct ipstat ipstat;
SYSCTL_STRUCT(_net_inet_ip, IPCTL_STATS, stats, CTLFLAG_RW,
    &ipstat, ipstat, "IP statistics (struct ipstat, netinet/ip_var.h)");

/* Packet reassembly stuff */
#define IPREASS_NHASH_LOG2      6
#define IPREASS_NHASH           (1 << IPREASS_NHASH_LOG2)
#define IPREASS_HMASK           (IPREASS_NHASH - 1)
#define IPREASS_HASH(x,y) \
	(((((x) & 0xF) | ((((x) >> 8) & 0xF) << 4)) ^ (y)) & IPREASS_HMASK)

static TAILQ_HEAD(ipqhead, ipq) ipq[IPREASS_NHASH];
static int    nipq = 0;         /* total # of reass queues */
static int    maxnipq;

#ifdef IPCTL_DEFMTU
SYSCTL_INT(_net_inet_ip, IPCTL_DEFMTU, mtu, CTLFLAG_RW,
    &ip_mtu, 0, "Default MTU");
#endif

#ifdef IPSTEALTH
static int	ipstealth = 0;
SYSCTL_INT(_net_inet_ip, OID_AUTO, stealth, CTLFLAG_RW,
    &ipstealth, 0, "");
#endif


/* Firewall hooks */
ip_fw_chk_t *ip_fw_chk_ptr;
int fw_enable = 1 ;

/* Dummynet hooks */
ip_dn_io_t *ip_dn_io_ptr;


/*
 * XXX this is ugly -- the following two global variables are
 * used to store packet state while it travels through the stack.
 * Note that the code even makes assumptions on the size and
 * alignment of fields inside struct ip_srcrt so e.g. adding some
 * fields will break the code. This needs to be fixed.
 *
 * We need to save the IP options in case a protocol wants to respond
 * to an incoming packet over the same route if the packet got here
 * using IP source routing.  This allows connection establishment and
 * maintenance when the remote end is on a network that is not known
 * to us.
 */
static int	ip_nhops = 0;
static	struct ip_srcrt {
	struct	in_addr dst;			/* final destination */
	char	nop;				/* one NOP to align */
	char	srcopt[IPOPT_OFFSET + 1];	/* OPTVAL, OLEN and OFFSET */
	struct	in_addr route[MAX_IPOPTLEN/sizeof(struct in_addr)];
} ip_srcrt;

static void	save_rte(u_char *, struct in_addr);
static int	ip_dooptions(struct mbuf *m, int,
			struct sockaddr_in *next_hop);
static void	ip_forward(struct mbuf *m, int srcrt,
			struct sockaddr_in *next_hop);
static void	ip_freef(struct ipqhead *, struct ipq *);
static struct	mbuf *ip_reass(struct mbuf *, struct ipqhead *,
		struct ipq *, u_int32_t *, u_int16_t *);
static void	ipintr(void);

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

	TAILQ_INIT(&in_ifaddrhead);
	in_ifaddrhashtbl = hashinit(INADDR_NHASH, M_IFADDR, &in_ifaddrhmask);
	pr = pffindproto(PF_INET, IPPROTO_RAW, SOCK_RAW);
	if (pr == 0)
		panic("ip_init");
	for (i = 0; i < IPPROTO_MAX; i++)
		ip_protox[i] = pr - inetsw;
	for (pr = inetdomain.dom_protosw;
	    pr < inetdomain.dom_protoswNPROTOSW; pr++)
		if (pr->pr_domain->dom_family == PF_INET &&
		    pr->pr_protocol && pr->pr_protocol != IPPROTO_RAW)
			ip_protox[pr->pr_protocol] = pr - inetsw;

	for (i = 0; i < IPREASS_NHASH; i++)
	    TAILQ_INIT(&ipq[i]);

	maxnipq = nmbclusters / 4;
	ip_maxfragpackets = nmbclusters / 4;

#ifndef RANDOM_IP_ID
	ip_id = time_second & 0xffff;
#endif
	ipintrq.ifq_maxlen = ipqmaxlen;
	mtx_init(&ipintrq.ifq_mtx, "ip_inq", NULL, MTX_DEF);
	ipintrq_present = 1;

	register_netisr(NETISR_IP, ipintr);
}

/*
 * XXX watch out this one. It is perhaps used as a cache for
 * the most recently used route ? it is cleared in in_addroute()
 * when a new route is successfully created.
 */
struct	route ipforward_rt;

/*
 * Ip input routine.  Checksum and byte swap header.  If fragmented
 * try to reassemble.  Process options.  Pass to next level.
 */
void
ip_input(struct mbuf *m)
{
	struct ip *ip;
	struct ipq *fp;
	struct in_ifaddr *ia = NULL;
	struct ifaddr *ifa;
	int    i, hlen, checkif;
	u_short sum;
	struct in_addr pkt_dst;
	u_int32_t divert_info = 0;		/* packet divert/tee info */
	struct ip_fw_args args;
#ifdef PFIL_HOOKS
	struct packet_filter_hook *pfh;
	struct mbuf *m0;
	int rv;
#endif /* PFIL_HOOKS */
#ifdef FAST_IPSEC
	struct m_tag *mtag;
	struct tdb_ident *tdbi;
	struct secpolicy *sp;
	int s, error;
#endif /* FAST_IPSEC */

	args.eh = NULL;
	args.oif = NULL;
	args.rule = NULL;
	args.divert_rule = 0;			/* divert cookie */
	args.next_hop = NULL;

	/* Grab info from MT_TAG mbufs prepended to the chain.	*/
	for (; m && m->m_type == MT_TAG; m = m->m_next) {
		switch(m->_m_tag_id) {
		default:
			printf("ip_input: unrecognised MT_TAG tag %d\n",
			    m->_m_tag_id);
			break;

		case PACKET_TAG_DUMMYNET:
			args.rule = ((struct dn_pkt *)m)->rule;
			break;

		case PACKET_TAG_DIVERT:
			args.divert_rule = (intptr_t)m->m_hdr.mh_data & 0xffff;
			break;

		case PACKET_TAG_IPFORWARD:
			args.next_hop = (struct sockaddr_in *)m->m_hdr.mh_data;
			break;
		}
	}

	KASSERT(m != NULL && (m->m_flags & M_PKTHDR) != 0,
	    ("ip_input: no HDR"));

	if (args.rule) {	/* dummynet already filtered us */
		ip = mtod(m, struct ip *);
		hlen = ip->ip_hl << 2;
		goto iphack ;
	}

	ipstat.ips_total++;

	if (m->m_pkthdr.len < sizeof(struct ip))
		goto tooshort;

	if (m->m_len < sizeof (struct ip) &&
	    (m = m_pullup(m, sizeof (struct ip))) == 0) {
		ipstat.ips_toosmall++;
		return;
	}
	ip = mtod(m, struct ip *);

	if (ip->ip_v != IPVERSION) {
		ipstat.ips_badvers++;
		goto bad;
	}

	hlen = ip->ip_hl << 2;
	if (hlen < sizeof(struct ip)) {	/* minimum header length */
		ipstat.ips_badhlen++;
		goto bad;
	}
	if (hlen > m->m_len) {
		if ((m = m_pullup(m, hlen)) == 0) {
			ipstat.ips_badhlen++;
			return;
		}
		ip = mtod(m, struct ip *);
	}

	/* 127/8 must not appear on wire - RFC1122 */
	if ((ntohl(ip->ip_dst.s_addr) >> IN_CLASSA_NSHIFT) == IN_LOOPBACKNET ||
	    (ntohl(ip->ip_src.s_addr) >> IN_CLASSA_NSHIFT) == IN_LOOPBACKNET) {
		if ((m->m_pkthdr.rcvif->if_flags & IFF_LOOPBACK) == 0) {
			ipstat.ips_badaddr++;
			goto bad;
		}
	}

	if (m->m_pkthdr.csum_flags & CSUM_IP_CHECKED) {
		sum = !(m->m_pkthdr.csum_flags & CSUM_IP_VALID);
	} else {
		if (hlen == sizeof(struct ip)) {
			sum = in_cksum_hdr(ip);
		} else {
			sum = in_cksum(m, hlen);
		}
	}
	if (sum) {
		ipstat.ips_badsum++;
		goto bad;
	}

	/*
	 * Convert fields to host representation.
	 */
	ip->ip_len = ntohs(ip->ip_len);
	if (ip->ip_len < hlen) {
		ipstat.ips_badlen++;
		goto bad;
	}
	ip->ip_off = ntohs(ip->ip_off);

	/*
	 * Check that the amount of data in the buffers
	 * is as at least much as the IP header would have us expect.
	 * Trim mbufs if longer than we expect.
	 * Drop packet if shorter than we expect.
	 */
	if (m->m_pkthdr.len < ip->ip_len) {
tooshort:
		ipstat.ips_tooshort++;
		goto bad;
	}
	if (m->m_pkthdr.len > ip->ip_len) {
		if (m->m_len == m->m_pkthdr.len) {
			m->m_len = ip->ip_len;
			m->m_pkthdr.len = ip->ip_len;
		} else
			m_adj(m, ip->ip_len - m->m_pkthdr.len);
	}

	/*
	 * IpHack's section.
	 * Right now when no processing on packet has done
	 * and it is still fresh out of network we do our black
	 * deals with it.
	 * - Firewall: deny/allow/divert
	 * - Xlate: translate packet's addr/port (NAT).
	 * - Pipe: pass pkt through dummynet.
	 * - Wrap: fake packet's addr/port <unimpl.>
	 * - Encapsulate: put it in another IP and send out. <unimp.>
 	 */

iphack:

#ifdef PFIL_HOOKS
	/*
	 * Run through list of hooks for input packets.  If there are any
	 * filters which require that additional packets in the flow are
	 * not fast-forwarded, they must clear the M_CANFASTFWD flag.
	 * Note that filters must _never_ set this flag, as another filter
	 * in the list may have previously cleared it.
	 */
	m0 = m;
	pfh = pfil_hook_get(PFIL_IN, &inetsw[ip_protox[IPPROTO_IP]].pr_pfh);
	for (; pfh; pfh = TAILQ_NEXT(pfh, pfil_link))
		if (pfh->pfil_func) {
			rv = pfh->pfil_func(ip, hlen,
					    m->m_pkthdr.rcvif, 0, &m0);
			if (rv)
				return;
			m = m0;
			if (m == NULL)
				return;
			ip = mtod(m, struct ip *);
		}
#endif /* PFIL_HOOKS */

	if (fw_enable && IPFW_LOADED) {
		/*
		 * If we've been forwarded from the output side, then
		 * skip the firewall a second time
		 */
		if (args.next_hop)
			goto ours;

		args.m = m;
		i = ip_fw_chk_ptr(&args);
		m = args.m;

		if ( (i & IP_FW_PORT_DENY_FLAG) || m == NULL) { /* drop */
			if (m)
				m_freem(m);
			return;
		}
		ip = mtod(m, struct ip *); /* just in case m changed */
		if (i == 0 && args.next_hop == NULL)	/* common case */
			goto pass;
                if (DUMMYNET_LOADED && (i & IP_FW_PORT_DYNT_FLAG) != 0) {
			/* Send packet to the appropriate pipe */
			ip_dn_io_ptr(m, i&0xffff, DN_TO_IP_IN, &args);
			return;
		}
#ifdef IPDIVERT
		if (i != 0 && (i & IP_FW_PORT_DYNT_FLAG) == 0) {
			/* Divert or tee packet */
			divert_info = i;
			goto ours;
		}
#endif
		if (i == 0 && args.next_hop != NULL)
			goto pass;
		/*
		 * if we get here, the packet must be dropped
		 */
		m_freem(m);
		return;
	}
pass:

	/*
	 * Process options and, if not destined for us,
	 * ship it on.  ip_dooptions returns 1 when an
	 * error was detected (causing an icmp message
	 * to be sent and the original packet to be freed).
	 */
	ip_nhops = 0;		/* for source routed packets */
	if (hlen > sizeof (struct ip) && ip_dooptions(m, 0, args.next_hop))
		return;

        /* greedy RSVP, snatches any PATH packet of the RSVP protocol and no
         * matter if it is destined to another node, or whether it is 
         * a multicast one, RSVP wants it! and prevents it from being forwarded
         * anywhere else. Also checks if the rsvp daemon is running before
	 * grabbing the packet.
         */
	if (rsvp_on && ip->ip_p==IPPROTO_RSVP) 
		goto ours;

	/*
	 * Check our list of addresses, to see if the packet is for us.
	 * If we don't have any addresses, assume any unicast packet
	 * we receive might be for us (and let the upper layers deal
	 * with it).
	 */
	if (TAILQ_EMPTY(&in_ifaddrhead) &&
	    (m->m_flags & (M_MCAST|M_BCAST)) == 0)
		goto ours;

	/*
	 * Cache the destination address of the packet; this may be
	 * changed by use of 'ipfw fwd'.
	 */
	pkt_dst = args.next_hop ? args.next_hop->sin_addr : ip->ip_dst;

	/*
	 * Enable a consistency check between the destination address
	 * and the arrival interface for a unicast packet (the RFC 1122
	 * strong ES model) if IP forwarding is disabled and the packet
	 * is not locally generated and the packet is not subject to
	 * 'ipfw fwd'.
	 *
	 * XXX - Checking also should be disabled if the destination
	 * address is ipnat'ed to a different interface.
	 *
	 * XXX - Checking is incompatible with IP aliases added
	 * to the loopback interface instead of the interface where
	 * the packets are received.
	 */
	checkif = ip_checkinterface && (ipforwarding == 0) && 
	    m->m_pkthdr.rcvif != NULL &&
	    ((m->m_pkthdr.rcvif->if_flags & IFF_LOOPBACK) == 0) &&
	    (args.next_hop == NULL);

	/*
	 * Check for exact addresses in the hash bucket.
	 */
	LIST_FOREACH(ia, INADDR_HASH(pkt_dst.s_addr), ia_hash) {
		/*
		 * If the address matches, verify that the packet
		 * arrived via the correct interface if checking is
		 * enabled.
		 */
		if (IA_SIN(ia)->sin_addr.s_addr == pkt_dst.s_addr && 
		    (!checkif || ia->ia_ifp == m->m_pkthdr.rcvif))
			goto ours;
	}
	/*
	 * Check for broadcast addresses.
	 *
	 * Only accept broadcast packets that arrive via the matching
	 * interface.  Reception of forwarded directed broadcasts would
	 * be handled via ip_forward() and ether_output() with the loopback
	 * into the stack for SIMPLEX interfaces handled by ether_output().
	 */
	if (m->m_pkthdr.rcvif->if_flags & IFF_BROADCAST) {
	        TAILQ_FOREACH(ifa, &m->m_pkthdr.rcvif->if_addrhead, ifa_link) {
			if (ifa->ifa_addr->sa_family != AF_INET)
				continue;
			ia = ifatoia(ifa);
			if (satosin(&ia->ia_broadaddr)->sin_addr.s_addr ==
			    pkt_dst.s_addr)
				goto ours;
			if (ia->ia_netbroadcast.s_addr == pkt_dst.s_addr)
				goto ours;
#ifdef BOOTP_COMPAT
			if (IA_SIN(ia)->sin_addr.s_addr == INADDR_ANY)
				goto ours;
#endif
		}
	}
	if (IN_MULTICAST(ntohl(ip->ip_dst.s_addr))) {
		struct in_multi *inm;
		if (ip_mrouter) {
			/*
			 * If we are acting as a multicast router, all
			 * incoming multicast packets are passed to the
			 * kernel-level multicast forwarding function.
			 * The packet is returned (relatively) intact; if
			 * ip_mforward() returns a non-zero value, the packet
			 * must be discarded, else it may be accepted below.
			 */
			if (ip_mforward(ip, m->m_pkthdr.rcvif, m, 0) != 0) {
				ipstat.ips_cantforward++;
				m_freem(m);
				return;
			}

			/*
			 * The process-level routing daemon needs to receive
			 * all multicast IGMP packets, whether or not this
			 * host belongs to their destination groups.
			 */
			if (ip->ip_p == IPPROTO_IGMP)
				goto ours;
			ipstat.ips_forward++;
		}
		/*
		 * See if we belong to the destination multicast group on the
		 * arrival interface.
		 */
		IN_LOOKUP_MULTI(ip->ip_dst, m->m_pkthdr.rcvif, inm);
		if (inm == NULL) {
			ipstat.ips_notmember++;
			m_freem(m);
			return;
		}
		goto ours;
	}
	if (ip->ip_dst.s_addr == (u_long)INADDR_BROADCAST)
		goto ours;
	if (ip->ip_dst.s_addr == INADDR_ANY)
		goto ours;

	/*
	 * FAITH(Firewall Aided Internet Translator)
	 */
	if (m->m_pkthdr.rcvif && m->m_pkthdr.rcvif->if_type == IFT_FAITH) {
		if (ip_keepfaith) {
			if (ip->ip_p == IPPROTO_TCP || ip->ip_p == IPPROTO_ICMP) 
				goto ours;
		}
		m_freem(m);
		return;
	}

	/*
	 * Not for us; forward if possible and desirable.
	 */
	if (ipforwarding == 0) {
		ipstat.ips_cantforward++;
		m_freem(m);
	} else {
#ifdef IPSEC
		/*
		 * Enforce inbound IPsec SPD.
		 */
		if (ipsec4_in_reject(m, NULL)) {
			ipsecstat.in_polvio++;
			goto bad;
		}
#endif /* IPSEC */
#ifdef FAST_IPSEC
		mtag = m_tag_find(m, PACKET_TAG_IPSEC_IN_DONE, NULL);
		s = splnet();
		if (mtag != NULL) {
			tdbi = (struct tdb_ident *)(mtag + 1);
			sp = ipsec_getpolicy(tdbi, IPSEC_DIR_INBOUND);
		} else {
			sp = ipsec_getpolicybyaddr(m, IPSEC_DIR_INBOUND,
						   IP_FORWARDING, &error);   
		}
		if (sp == NULL) {	/* NB: can happen if error */
			splx(s);
			/*XXX error stat???*/
			DPRINTF(("ip_input: no SP for forwarding\n"));	/*XXX*/
			goto bad;
		}

		/*
		 * Check security policy against packet attributes.
		 */
		error = ipsec_in_reject(sp, m);
		KEY_FREESP(&sp);
		splx(s);
		if (error) {
			ipstat.ips_cantforward++;
			goto bad;
		}
#endif /* FAST_IPSEC */
		ip_forward(m, 0, args.next_hop);
	}
	return;

ours:
#ifdef IPSTEALTH
	/*
	 * IPSTEALTH: Process non-routing options only
	 * if the packet is destined for us.
	 */
	if (ipstealth && hlen > sizeof (struct ip) &&
	    ip_dooptions(m, 1, args.next_hop))
		return;
#endif /* IPSTEALTH */

	/* Count the packet in the ip address stats */
	if (ia != NULL) {
		ia->ia_ifa.if_ipackets++;
		ia->ia_ifa.if_ibytes += m->m_pkthdr.len;
	}

	/*
	 * If offset or IP_MF are set, must reassemble.
	 * Otherwise, nothing need be done.
	 * (We could look in the reassembly queue to see
	 * if the packet was previously fragmented,
	 * but it's not worth the time; just let them time out.)
	 */
	if (ip->ip_off & (IP_MF | IP_OFFMASK)) {

		sum = IPREASS_HASH(ip->ip_src.s_addr, ip->ip_id);
		/*
		 * Look for queue of fragments
		 * of this datagram.
		 */
		TAILQ_FOREACH(fp, &ipq[sum], ipq_list)
			if (ip->ip_id == fp->ipq_id &&
			    ip->ip_src.s_addr == fp->ipq_src.s_addr &&
			    ip->ip_dst.s_addr == fp->ipq_dst.s_addr &&
#ifdef MAC
			    mac_fragment_match(m, fp) &&
#endif
			    ip->ip_p == fp->ipq_p)
				goto found;

		fp = 0;

		/* check if there's a place for the new queue */
		if (nipq > maxnipq) {
		    /*
		     * drop something from the tail of the current queue
		     * before proceeding further
		     */
		    struct ipq *q = TAILQ_LAST(&ipq[sum], ipqhead);
		    if (q == NULL) {   /* gak */
			for (i = 0; i < IPREASS_NHASH; i++) {
			    struct ipq *r = TAILQ_LAST(&ipq[i], ipqhead);
			    if (r) {
				ip_freef(&ipq[i], r);
				break;
			    }
			}
		    } else
			ip_freef(&ipq[sum], q);
		}
found:
		/*
		 * Adjust ip_len to not reflect header,
		 * convert offset of this to bytes.
		 */
		ip->ip_len -= hlen;
		if (ip->ip_off & IP_MF) {
		        /*
		         * Make sure that fragments have a data length
			 * that's a non-zero multiple of 8 bytes.
		         */
			if (ip->ip_len == 0 || (ip->ip_len & 0x7) != 0) {
				ipstat.ips_toosmall++; /* XXX */
				goto bad;
			}
			m->m_flags |= M_FRAG;
		} else
			m->m_flags &= ~M_FRAG;
		ip->ip_off <<= 3;

		/*
		 * Attempt reassembly; if it succeeds, proceed.
		 * ip_reass() will return a different mbuf, and update
		 * the divert info in divert_info and args.divert_rule.
		 */
		ipstat.ips_fragments++;
		m->m_pkthdr.header = ip;
		m = ip_reass(m,
		    &ipq[sum], fp, &divert_info, &args.divert_rule);
		if (m == 0)
			return;
		ipstat.ips_reassembled++;
		ip = mtod(m, struct ip *);
		/* Get the header length of the reassembled packet */
		hlen = ip->ip_hl << 2;
#ifdef IPDIVERT
		/* Restore original checksum before diverting packet */
		if (divert_info != 0) {
			ip->ip_len += hlen;
			ip->ip_len = htons(ip->ip_len);
			ip->ip_off = htons(ip->ip_off);
			ip->ip_sum = 0;
			if (hlen == sizeof(struct ip))
				ip->ip_sum = in_cksum_hdr(ip);
			else
				ip->ip_sum = in_cksum(m, hlen);
			ip->ip_off = ntohs(ip->ip_off);
			ip->ip_len = ntohs(ip->ip_len);
			ip->ip_len -= hlen;
		}
#endif
	} else
		ip->ip_len -= hlen;

#ifdef IPDIVERT
	/*
	 * Divert or tee packet to the divert protocol if required.
	 */
	if (divert_info != 0) {
		struct mbuf *clone = NULL;

		/* Clone packet if we're doing a 'tee' */
		if ((divert_info & IP_FW_PORT_TEE_FLAG) != 0)
			clone = m_dup(m, M_DONTWAIT);

		/* Restore packet header fields to original values */
		ip->ip_len += hlen;
		ip->ip_len = htons(ip->ip_len);
		ip->ip_off = htons(ip->ip_off);

		/* Deliver packet to divert input routine */
		divert_packet(m, 1, divert_info & 0xffff, args.divert_rule);
		ipstat.ips_delivered++;

		/* If 'tee', continue with original packet */
		if (clone == NULL)
			return;
		m = clone;
		ip = mtod(m, struct ip *);
		ip->ip_len += hlen;
		/*
		 * Jump backwards to complete processing of the
		 * packet. But first clear divert_info to avoid
		 * entering this block again.
		 * We do not need to clear args.divert_rule
		 * or args.next_hop as they will not be used.
		 */
		divert_info = 0;
		goto pass;
	}
#endif

#ifdef IPSEC
	/*
	 * enforce IPsec policy checking if we are seeing last header.
	 * note that we do not visit this with protocols with pcb layer
	 * code - like udp/tcp/raw ip.
	 */
	if ((inetsw[ip_protox[ip->ip_p]].pr_flags & PR_LASTHDR) != 0 &&
	    ipsec4_in_reject(m, NULL)) {
		ipsecstat.in_polvio++;
		goto bad;
	}
#endif
#if FAST_IPSEC
	/*
	 * enforce IPsec policy checking if we are seeing last header.
	 * note that we do not visit this with protocols with pcb layer
	 * code - like udp/tcp/raw ip.
	 */
	if ((inetsw[ip_protox[ip->ip_p]].pr_flags & PR_LASTHDR) != 0) {
		/*
		 * Check if the packet has already had IPsec processing
		 * done.  If so, then just pass it along.  This tag gets
		 * set during AH, ESP, etc. input handling, before the
		 * packet is returned to the ip input queue for delivery.
		 */ 
		mtag = m_tag_find(m, PACKET_TAG_IPSEC_IN_DONE, NULL);
		s = splnet();
		if (mtag != NULL) {
			tdbi = (struct tdb_ident *)(mtag + 1);
			sp = ipsec_getpolicy(tdbi, IPSEC_DIR_INBOUND);
		} else {
			sp = ipsec_getpolicybyaddr(m, IPSEC_DIR_INBOUND,
						   IP_FORWARDING, &error);   
		}
		if (sp != NULL) {
			/*
			 * Check security policy against packet attributes.
			 */
			error = ipsec_in_reject(sp, m);
			KEY_FREESP(&sp);
		} else {
			/* XXX error stat??? */
			error = EINVAL;
DPRINTF(("ip_input: no SP, packet discarded\n"));/*XXX*/
			goto bad;
		}
		splx(s);
		if (error)
			goto bad;
	}
#endif /* FAST_IPSEC */

	/*
	 * Switch out to protocol's input routine.
	 */
	ipstat.ips_delivered++;
	if (args.next_hop && ip->ip_p == IPPROTO_TCP) {
		/* TCP needs IPFORWARD info if available */
		struct m_hdr tag;

		tag.mh_type = MT_TAG;
		tag.mh_flags = PACKET_TAG_IPFORWARD;
		tag.mh_data = (caddr_t)args.next_hop;
		tag.mh_next = m;

		(*inetsw[ip_protox[ip->ip_p]].pr_input)(
			(struct mbuf *)&tag, hlen);
	} else
		(*inetsw[ip_protox[ip->ip_p]].pr_input)(m, hlen);
	return;
bad:
	m_freem(m);
}

/*
 * IP software interrupt routine - to go away sometime soon
 */
static void
ipintr(void)
{
	struct mbuf *m;

	while (1) {
		IF_DEQUEUE(&ipintrq, m);
		if (m == 0)
			return;
		ip_input(m);
	}
}

/*
 * Take incoming datagram fragment and try to reassemble it into
 * whole datagram.  If a chain for reassembly of this datagram already
 * exists, then it is given as fp; otherwise have to make a chain.
 *
 * When IPDIVERT enabled, keep additional state with each packet that
 * tells us if we need to divert or tee the packet we're building.
 * In particular, *divinfo includes the port and TEE flag,
 * *divert_rule is the number of the matching rule.
 */

static struct mbuf *
ip_reass(struct mbuf *m, struct ipqhead *head, struct ipq *fp,
	u_int32_t *divinfo, u_int16_t *divert_rule)
{
	struct ip *ip = mtod(m, struct ip *);
	register struct mbuf *p, *q, *nq;
	struct mbuf *t;
	int hlen = ip->ip_hl << 2;
	int i, next;

	/*
	 * Presence of header sizes in mbufs
	 * would confuse code below.
	 */
	m->m_data += hlen;
	m->m_len -= hlen;

	/*
	 * If first fragment to arrive, create a reassembly queue.
	 */
	if (fp == 0) {
		/*
		 * Enforce upper bound on number of fragmented packets
		 * for which we attempt reassembly;
		 * If maxfrag is 0, never accept fragments.
		 * If maxfrag is -1, accept all fragments without limitation.
		 */
		if ((ip_maxfragpackets >= 0) && (ip_nfragpackets >= ip_maxfragpackets))
			goto dropfrag;
		ip_nfragpackets++;
		if ((t = m_get(M_DONTWAIT, MT_FTABLE)) == NULL)
			goto dropfrag;
		fp = mtod(t, struct ipq *);
#ifdef MAC
		mac_init_ipq(fp);
		mac_create_ipq(m, fp);
#endif
		TAILQ_INSERT_HEAD(head, fp, ipq_list);
		nipq++;
		fp->ipq_ttl = IPFRAGTTL;
		fp->ipq_p = ip->ip_p;
		fp->ipq_id = ip->ip_id;
		fp->ipq_src = ip->ip_src;
		fp->ipq_dst = ip->ip_dst;
		fp->ipq_frags = m;
		m->m_nextpkt = NULL;
#ifdef IPDIVERT
		fp->ipq_div_info = 0;
		fp->ipq_div_cookie = 0;
#endif
		goto inserted;
	} else {
#ifdef MAC
		mac_update_ipq(m, fp);
#endif
	}

#define GETIP(m)	((struct ip*)((m)->m_pkthdr.header))

	/*
	 * Find a segment which begins after this one does.
	 */
	for (p = NULL, q = fp->ipq_frags; q; p = q, q = q->m_nextpkt)
		if (GETIP(q)->ip_off > ip->ip_off)
			break;

	/*
	 * If there is a preceding segment, it may provide some of
	 * our data already.  If so, drop the data from the incoming
	 * segment.  If it provides all of our data, drop us, otherwise
	 * stick new segment in the proper place.
	 *
	 * If some of the data is dropped from the the preceding
	 * segment, then it's checksum is invalidated.
	 */
	if (p) {
		i = GETIP(p)->ip_off + GETIP(p)->ip_len - ip->ip_off;
		if (i > 0) {
			if (i >= ip->ip_len)
				goto dropfrag;
			m_adj(m, i);
			m->m_pkthdr.csum_flags = 0;
			ip->ip_off += i;
			ip->ip_len -= i;
		}
		m->m_nextpkt = p->m_nextpkt;
		p->m_nextpkt = m;
	} else {
		m->m_nextpkt = fp->ipq_frags;
		fp->ipq_frags = m;
	}

	/*
	 * While we overlap succeeding segments trim them or,
	 * if they are completely covered, dequeue them.
	 */
	for (; q != NULL && ip->ip_off + ip->ip_len > GETIP(q)->ip_off;
	     q = nq) {
		i = (ip->ip_off + ip->ip_len) -
		    GETIP(q)->ip_off;
		if (i < GETIP(q)->ip_len) {
			GETIP(q)->ip_len -= i;
			GETIP(q)->ip_off += i;
			m_adj(q, i);
			q->m_pkthdr.csum_flags = 0;
			break;
		}
		nq = q->m_nextpkt;
		m->m_nextpkt = nq;
		m_freem(q);
	}

inserted:

#ifdef IPDIVERT
	/*
	 * Transfer firewall instructions to the fragment structure.
	 * Only trust info in the fragment at offset 0.
	 */
	if (ip->ip_off == 0) {
		fp->ipq_div_info = *divinfo;
		fp->ipq_div_cookie = *divert_rule;
	}
	*divinfo = 0;
	*divert_rule = 0;
#endif

	/*
	 * Check for complete reassembly.
	 */
	next = 0;
	for (p = NULL, q = fp->ipq_frags; q; p = q, q = q->m_nextpkt) {
		if (GETIP(q)->ip_off != next)
			return (0);
		next += GETIP(q)->ip_len;
	}
	/* Make sure the last packet didn't have the IP_MF flag */
	if (p->m_flags & M_FRAG)
		return (0);

	/*
	 * Reassembly is complete.  Make sure the packet is a sane size.
	 */
	q = fp->ipq_frags;
	ip = GETIP(q);
	if (next + (ip->ip_hl << 2) > IP_MAXPACKET) {
		ipstat.ips_toolong++;
		ip_freef(head, fp);
		return (0);
	}

	/*
	 * Concatenate fragments.
	 */
	m = q;
	t = m->m_next;
	m->m_next = 0;
	m_cat(m, t);
	nq = q->m_nextpkt;
	q->m_nextpkt = 0;
	for (q = nq; q != NULL; q = nq) {
		nq = q->m_nextpkt;
		q->m_nextpkt = NULL;
		m->m_pkthdr.csum_flags &= q->m_pkthdr.csum_flags;
		m->m_pkthdr.csum_data += q->m_pkthdr.csum_data;
		m_cat(m, q);
	}
#ifdef MAC
	mac_create_datagram_from_ipq(fp, m);
	mac_destroy_ipq(fp);
#endif

#ifdef IPDIVERT
	/*
	 * Extract firewall instructions from the fragment structure.
	 */
	*divinfo = fp->ipq_div_info;
	*divert_rule = fp->ipq_div_cookie;
#endif

	/*
	 * Create header for new ip packet by
	 * modifying header of first packet;
	 * dequeue and discard fragment reassembly header.
	 * Make header visible.
	 */
	ip->ip_len = next;
	ip->ip_src = fp->ipq_src;
	ip->ip_dst = fp->ipq_dst;
	TAILQ_REMOVE(head, fp, ipq_list);
	nipq--;
	(void) m_free(dtom(fp));
	ip_nfragpackets--;
	m->m_len += (ip->ip_hl << 2);
	m->m_data -= (ip->ip_hl << 2);
	/* some debugging cruft by sklower, below, will go away soon */
	if (m->m_flags & M_PKTHDR)	/* XXX this should be done elsewhere */
		m_fixhdr(m);
	return (m);

dropfrag:
#ifdef IPDIVERT
	*divinfo = 0;
	*divert_rule = 0;
#endif
	ipstat.ips_fragdropped++;
	m_freem(m);
	return (0);

#undef GETIP
}

/*
 * Free a fragment reassembly header and all
 * associated datagrams.
 */
static void
ip_freef(fhp, fp)
	struct ipqhead *fhp;
	struct ipq *fp;
{
	register struct mbuf *q;

	while (fp->ipq_frags) {
		q = fp->ipq_frags;
		fp->ipq_frags = q->m_nextpkt;
		m_freem(q);
	}
	TAILQ_REMOVE(fhp, fp, ipq_list);
	(void) m_free(dtom(fp));
	ip_nfragpackets--;
	nipq--;
}

/*
 * IP timer processing;
 * if a timer expires on a reassembly
 * queue, discard it.
 */
void
ip_slowtimo()
{
	register struct ipq *fp;
	int s = splnet();
	int i;

	for (i = 0; i < IPREASS_NHASH; i++) {
		for(fp = TAILQ_FIRST(&ipq[i]); fp;) {
			struct ipq *fpp;

			fpp = fp;
			fp = TAILQ_NEXT(fp, ipq_list);
			if(--fpp->ipq_ttl == 0) {
				ipstat.ips_fragtimeout++;
				ip_freef(&ipq[i], fpp);
			}
		}
	}
	/*
	 * If we are over the maximum number of fragments
	 * (due to the limit being lowered), drain off
	 * enough to get down to the new limit.
	 */
	for (i = 0; i < IPREASS_NHASH; i++) {
		if (ip_maxfragpackets >= 0) {
			while (ip_nfragpackets > ip_maxfragpackets &&
				!TAILQ_EMPTY(&ipq[i])) {
				ipstat.ips_fragdropped++;
				ip_freef(&ipq[i], TAILQ_FIRST(&ipq[i]));
			}
		}
	}
	ipflow_slowtimo();
	splx(s);
}

/*
 * Drain off all datagram fragments.
 */
void
ip_drain()
{
	int     i;

	for (i = 0; i < IPREASS_NHASH; i++) {
		while(!TAILQ_EMPTY(&ipq[i])) {
			ipstat.ips_fragdropped++;
			ip_freef(&ipq[i], TAILQ_FIRST(&ipq[i]));
		}
	}
	in_rtqdrain();
}

/*
 * Do option processing on a datagram,
 * possibly discarding it if bad options are encountered,
 * or forwarding it if source-routed.
 * The pass argument is used when operating in the IPSTEALTH
 * mode to tell what options to process:
 * [LS]SRR (pass 0) or the others (pass 1).
 * The reason for as many as two passes is that when doing IPSTEALTH,
 * non-routing options should be processed only if the packet is for us.
 * Returns 1 if packet has been forwarded/freed,
 * 0 if the packet should be processed further.
 */
static int
ip_dooptions(struct mbuf *m, int pass, struct sockaddr_in *next_hop)
{
	struct ip *ip = mtod(m, struct ip *);
	u_char *cp;
	struct in_ifaddr *ia;
	int opt, optlen, cnt, off, code, type = ICMP_PARAMPROB, forward = 0;
	struct in_addr *sin, dst;
	n_time ntime;
	struct	sockaddr_in ipaddr = { sizeof(ipaddr), AF_INET };

	dst = ip->ip_dst;
	cp = (u_char *)(ip + 1);
	cnt = (ip->ip_hl << 2) - sizeof (struct ip);
	for (; cnt > 0; cnt -= optlen, cp += optlen) {
		opt = cp[IPOPT_OPTVAL];
		if (opt == IPOPT_EOL)
			break;
		if (opt == IPOPT_NOP)
			optlen = 1;
		else {
			if (cnt < IPOPT_OLEN + sizeof(*cp)) {
				code = &cp[IPOPT_OLEN] - (u_char *)ip;
				goto bad;
			}
			optlen = cp[IPOPT_OLEN];
			if (optlen < IPOPT_OLEN + sizeof(*cp) || optlen > cnt) {
				code = &cp[IPOPT_OLEN] - (u_char *)ip;
				goto bad;
			}
		}
		switch (opt) {

		default:
			break;

		/*
		 * Source routing with record.
		 * Find interface with current destination address.
		 * If none on this machine then drop if strictly routed,
		 * or do nothing if loosely routed.
		 * Record interface address and bring up next address
		 * component.  If strictly routed make sure next
		 * address is on directly accessible net.
		 */
		case IPOPT_LSRR:
		case IPOPT_SSRR:
#ifdef IPSTEALTH
			if (ipstealth && pass > 0)
				break;
#endif
			if (optlen < IPOPT_OFFSET + sizeof(*cp)) {
				code = &cp[IPOPT_OLEN] - (u_char *)ip;
				goto bad;
			}
			if ((off = cp[IPOPT_OFFSET]) < IPOPT_MINOFF) {
				code = &cp[IPOPT_OFFSET] - (u_char *)ip;
				goto bad;
			}
			ipaddr.sin_addr = ip->ip_dst;
			ia = (struct in_ifaddr *)
				ifa_ifwithaddr((struct sockaddr *)&ipaddr);
			if (ia == 0) {
				if (opt == IPOPT_SSRR) {
					type = ICMP_UNREACH;
					code = ICMP_UNREACH_SRCFAIL;
					goto bad;
				}
				if (!ip_dosourceroute)
					goto nosourcerouting;
				/*
				 * Loose routing, and not at next destination
				 * yet; nothing to do except forward.
				 */
				break;
			}
			off--;			/* 0 origin */
			if (off > optlen - (int)sizeof(struct in_addr)) {
				/*
				 * End of source route.  Should be for us.
				 */
				if (!ip_acceptsourceroute)
					goto nosourcerouting;
				save_rte(cp, ip->ip_src);
				break;
			}
#ifdef IPSTEALTH
			if (ipstealth)
				goto dropit;
#endif
			if (!ip_dosourceroute) {
				if (ipforwarding) {
					char buf[16]; /* aaa.bbb.ccc.ddd\0 */
					/*
					 * Acting as a router, so generate ICMP
					 */
nosourcerouting:
					strcpy(buf, inet_ntoa(ip->ip_dst));
					log(LOG_WARNING, 
					    "attempted source route from %s to %s\n",
					    inet_ntoa(ip->ip_src), buf);
					type = ICMP_UNREACH;
					code = ICMP_UNREACH_SRCFAIL;
					goto bad;
				} else {
					/*
					 * Not acting as a router, so silently drop.
					 */
#ifdef IPSTEALTH
dropit:
#endif
					ipstat.ips_cantforward++;
					m_freem(m);
					return (1);
				}
			}

			/*
			 * locate outgoing interface
			 */
			(void)memcpy(&ipaddr.sin_addr, cp + off,
			    sizeof(ipaddr.sin_addr));

			if (opt == IPOPT_SSRR) {
#define	INA	struct in_ifaddr *
#define	SA	struct sockaddr *
			    if ((ia = (INA)ifa_ifwithdstaddr((SA)&ipaddr)) == 0)
				ia = (INA)ifa_ifwithnet((SA)&ipaddr);
			} else
				ia = ip_rtaddr(ipaddr.sin_addr, &ipforward_rt);
			if (ia == 0) {
				type = ICMP_UNREACH;
				code = ICMP_UNREACH_SRCFAIL;
				goto bad;
			}
			ip->ip_dst = ipaddr.sin_addr;
			(void)memcpy(cp + off, &(IA_SIN(ia)->sin_addr),
			    sizeof(struct in_addr));
			cp[IPOPT_OFFSET] += sizeof(struct in_addr);
			/*
			 * Let ip_intr's mcast routing check handle mcast pkts
			 */
			forward = !IN_MULTICAST(ntohl(ip->ip_dst.s_addr));
			break;

		case IPOPT_RR:
#ifdef IPSTEALTH
			if (ipstealth && pass == 0)
				break;
#endif
			if (optlen < IPOPT_OFFSET + sizeof(*cp)) {
				code = &cp[IPOPT_OFFSET] - (u_char *)ip;
				goto bad;
			}
			if ((off = cp[IPOPT_OFFSET]) < IPOPT_MINOFF) {
				code = &cp[IPOPT_OFFSET] - (u_char *)ip;
				goto bad;
			}
			/*
			 * If no space remains, ignore.
			 */
			off--;			/* 0 origin */
			if (off > optlen - (int)sizeof(struct in_addr))
				break;
			(void)memcpy(&ipaddr.sin_addr, &ip->ip_dst,
			    sizeof(ipaddr.sin_addr));
			/*
			 * locate outgoing interface; if we're the destination,
			 * use the incoming interface (should be same).
			 */
			if ((ia = (INA)ifa_ifwithaddr((SA)&ipaddr)) == 0 &&
			    (ia = ip_rtaddr(ipaddr.sin_addr,
			    &ipforward_rt)) == 0) {
				type = ICMP_UNREACH;
				code = ICMP_UNREACH_HOST;
				goto bad;
			}
			(void)memcpy(cp + off, &(IA_SIN(ia)->sin_addr),
			    sizeof(struct in_addr));
			cp[IPOPT_OFFSET] += sizeof(struct in_addr);
			break;

		case IPOPT_TS:
#ifdef IPSTEALTH
			if (ipstealth && pass == 0)
				break;
#endif
			code = cp - (u_char *)ip;
			if (optlen < 4 || optlen > 40) {
				code = &cp[IPOPT_OLEN] - (u_char *)ip;
				goto bad;
			}
			if ((off = cp[IPOPT_OFFSET]) < 5) {
				code = &cp[IPOPT_OLEN] - (u_char *)ip;
				goto bad;
			}
			if (off > optlen - (int)sizeof(int32_t)) {
				cp[IPOPT_OFFSET + 1] += (1 << 4);
				if ((cp[IPOPT_OFFSET + 1] & 0xf0) == 0) {
					code = &cp[IPOPT_OFFSET] - (u_char *)ip;
					goto bad;
				}
				break;
			}
			off--;				/* 0 origin */
			sin = (struct in_addr *)(cp + off);
			switch (cp[IPOPT_OFFSET + 1] & 0x0f) {

			case IPOPT_TS_TSONLY:
				break;

			case IPOPT_TS_TSANDADDR:
				if (off + sizeof(n_time) +
				    sizeof(struct in_addr) > optlen) {
					code = &cp[IPOPT_OFFSET] - (u_char *)ip;
					goto bad;
				}
				ipaddr.sin_addr = dst;
				ia = (INA)ifaof_ifpforaddr((SA)&ipaddr,
							    m->m_pkthdr.rcvif);
				if (ia == 0)
					continue;
				(void)memcpy(sin, &IA_SIN(ia)->sin_addr,
				    sizeof(struct in_addr));
				cp[IPOPT_OFFSET] += sizeof(struct in_addr);
				off += sizeof(struct in_addr);
				break;

			case IPOPT_TS_PRESPEC:
				if (off + sizeof(n_time) +
				    sizeof(struct in_addr) > optlen) {
					code = &cp[IPOPT_OFFSET] - (u_char *)ip;
					goto bad;
				}
				(void)memcpy(&ipaddr.sin_addr, sin,
				    sizeof(struct in_addr));
				if (ifa_ifwithaddr((SA)&ipaddr) == 0)
					continue;
				cp[IPOPT_OFFSET] += sizeof(struct in_addr);
				off += sizeof(struct in_addr);
				break;

			default:
				code = &cp[IPOPT_OFFSET + 1] - (u_char *)ip;
				goto bad;
			}
			ntime = iptime();
			(void)memcpy(cp + off, &ntime, sizeof(n_time));
			cp[IPOPT_OFFSET] += sizeof(n_time);
		}
	}
	if (forward && ipforwarding) {
		ip_forward(m, 1, next_hop);
		return (1);
	}
	return (0);
bad:
	icmp_error(m, type, code, 0, 0);
	ipstat.ips_badoptions++;
	return (1);
}

/*
 * Given address of next destination (final or next hop),
 * return internet address info of interface to be used to get there.
 */
struct in_ifaddr *
ip_rtaddr(dst, rt)
	struct in_addr dst;
	struct route *rt;
{
	register struct sockaddr_in *sin;

	sin = (struct sockaddr_in *)&rt->ro_dst;

	if (rt->ro_rt == 0 ||
	    !(rt->ro_rt->rt_flags & RTF_UP) ||
	    dst.s_addr != sin->sin_addr.s_addr) {
		if (rt->ro_rt) {
			RTFREE(rt->ro_rt);
			rt->ro_rt = 0;
		}
		sin->sin_family = AF_INET;
		sin->sin_len = sizeof(*sin);
		sin->sin_addr = dst;

		rtalloc_ign(rt, RTF_PRCLONING);
	}
	if (rt->ro_rt == 0)
		return ((struct in_ifaddr *)0);
	return (ifatoia(rt->ro_rt->rt_ifa));
}

/*
 * Save incoming source route for use in replies,
 * to be picked up later by ip_srcroute if the receiver is interested.
 */
static void
save_rte(option, dst)
	u_char *option;
	struct in_addr dst;
{
	unsigned olen;

	olen = option[IPOPT_OLEN];
#ifdef DIAGNOSTIC
	if (ipprintfs)
		printf("save_rte: olen %d\n", olen);
#endif
	if (olen > sizeof(ip_srcrt) - (1 + sizeof(dst)))
		return;
	bcopy(option, ip_srcrt.srcopt, olen);
	ip_nhops = (olen - IPOPT_OFFSET - 1) / sizeof(struct in_addr);
	ip_srcrt.dst = dst;
}

/*
 * Retrieve incoming source route for use in replies,
 * in the same form used by setsockopt.
 * The first hop is placed before the options, will be removed later.
 */
struct mbuf *
ip_srcroute()
{
	register struct in_addr *p, *q;
	register struct mbuf *m;

	if (ip_nhops == 0)
		return ((struct mbuf *)0);
	m = m_get(M_DONTWAIT, MT_HEADER);
	if (m == 0)
		return ((struct mbuf *)0);

#define OPTSIZ	(sizeof(ip_srcrt.nop) + sizeof(ip_srcrt.srcopt))

	/* length is (nhops+1)*sizeof(addr) + sizeof(nop + srcrt header) */
	m->m_len = ip_nhops * sizeof(struct in_addr) + sizeof(struct in_addr) +
	    OPTSIZ;
#ifdef DIAGNOSTIC
	if (ipprintfs)
		printf("ip_srcroute: nhops %d mlen %d", ip_nhops, m->m_len);
#endif

	/*
	 * First save first hop for return route
	 */
	p = &ip_srcrt.route[ip_nhops - 1];
	*(mtod(m, struct in_addr *)) = *p--;
#ifdef DIAGNOSTIC
	if (ipprintfs)
		printf(" hops %lx", (u_long)ntohl(mtod(m, struct in_addr *)->s_addr));
#endif

	/*
	 * Copy option fields and padding (nop) to mbuf.
	 */
	ip_srcrt.nop = IPOPT_NOP;
	ip_srcrt.srcopt[IPOPT_OFFSET] = IPOPT_MINOFF;
	(void)memcpy(mtod(m, caddr_t) + sizeof(struct in_addr),
	    &ip_srcrt.nop, OPTSIZ);
	q = (struct in_addr *)(mtod(m, caddr_t) +
	    sizeof(struct in_addr) + OPTSIZ);
#undef OPTSIZ
	/*
	 * Record return path as an IP source route,
	 * reversing the path (pointers are now aligned).
	 */
	while (p >= ip_srcrt.route) {
#ifdef DIAGNOSTIC
		if (ipprintfs)
			printf(" %lx", (u_long)ntohl(q->s_addr));
#endif
		*q++ = *p--;
	}
	/*
	 * Last hop goes to final destination.
	 */
	*q = ip_srcrt.dst;
#ifdef DIAGNOSTIC
	if (ipprintfs)
		printf(" %lx\n", (u_long)ntohl(q->s_addr));
#endif
	return (m);
}

/*
 * Strip out IP options, at higher
 * level protocol in the kernel.
 * Second argument is buffer to which options
 * will be moved, and return value is their length.
 * XXX should be deleted; last arg currently ignored.
 */
void
ip_stripoptions(m, mopt)
	register struct mbuf *m;
	struct mbuf *mopt;
{
	register int i;
	struct ip *ip = mtod(m, struct ip *);
	register caddr_t opts;
	int olen;

	olen = (ip->ip_hl << 2) - sizeof (struct ip);
	opts = (caddr_t)(ip + 1);
	i = m->m_len - (sizeof (struct ip) + olen);
	bcopy(opts + olen, opts, (unsigned)i);
	m->m_len -= olen;
	if (m->m_flags & M_PKTHDR)
		m->m_pkthdr.len -= olen;
	ip->ip_v = IPVERSION;
	ip->ip_hl = sizeof(struct ip) >> 2;
}

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

/*
 * Forward a packet.  If some error occurs return the sender
 * an icmp packet.  Note we can't always generate a meaningful
 * icmp message because icmp doesn't have a large enough repertoire
 * of codes and types.
 *
 * If not forwarding, just drop the packet.  This could be confusing
 * if ipforwarding was zero but some routing protocol was advancing
 * us as a gateway to somewhere.  However, we must let the routing
 * protocol deal with that.
 *
 * The srcrt parameter indicates whether the packet is being forwarded
 * via a source route.
 */
static void
ip_forward(struct mbuf *m, int srcrt, struct sockaddr_in *next_hop)
{
	struct ip *ip = mtod(m, struct ip *);
	struct rtentry *rt;
	int error, type = 0, code = 0;
	struct mbuf *mcopy;
	n_long dest;
	struct in_addr pkt_dst;
	struct ifnet *destifp;
#if defined(IPSEC) || defined(FAST_IPSEC)
	struct ifnet dummyifp;
#endif

	dest = 0;
	/*
	 * Cache the destination address of the packet; this may be
	 * changed by use of 'ipfw fwd'.
	 */
	pkt_dst = next_hop ? next_hop->sin_addr : ip->ip_dst;

#ifdef DIAGNOSTIC
	if (ipprintfs)
		printf("forward: src %lx dst %lx ttl %x\n",
		    (u_long)ip->ip_src.s_addr, (u_long)pkt_dst.s_addr,
		    ip->ip_ttl);
#endif


	if (m->m_flags & (M_BCAST|M_MCAST) || in_canforward(pkt_dst) == 0) {
		ipstat.ips_cantforward++;
		m_freem(m);
		return;
	}
#ifdef IPSTEALTH
	if (!ipstealth) {
#endif
		if (ip->ip_ttl <= IPTTLDEC) {
			icmp_error(m, ICMP_TIMXCEED, ICMP_TIMXCEED_INTRANS,
			    dest, 0);
			return;
		}
#ifdef IPSTEALTH
	}
#endif

	if (ip_rtaddr(pkt_dst, &ipforward_rt) == 0) {
		icmp_error(m, ICMP_UNREACH, ICMP_UNREACH_HOST, dest, 0);
		return;
	} else
		rt = ipforward_rt.ro_rt;

	/*
	 * Save the IP header and at most 8 bytes of the payload,
	 * in case we need to generate an ICMP message to the src.
	 *
	 * XXX this can be optimized a lot by saving the data in a local
	 * buffer on the stack (72 bytes at most), and only allocating the
	 * mbuf if really necessary. The vast majority of the packets
	 * are forwarded without having to send an ICMP back (either
	 * because unnecessary, or because rate limited), so we are
	 * really we are wasting a lot of work here.
	 *
	 * We don't use m_copy() because it might return a reference
	 * to a shared cluster. Both this function and ip_output()
	 * assume exclusive access to the IP header in `m', so any
	 * data in a cluster may change before we reach icmp_error().
	 */
	MGET(mcopy, M_DONTWAIT, m->m_type);
	if (mcopy != NULL) {
		M_COPY_PKTHDR(mcopy, m);
		mcopy->m_len = imin((ip->ip_hl << 2) + 8,
		    (int)ip->ip_len);
		m_copydata(m, 0, mcopy->m_len, mtod(mcopy, caddr_t));
#ifdef MAC
		/*
		 * XXXMAC: This will eventually become an explicit
		 * labeling point.
		 */
		mac_create_mbuf_from_mbuf(m, mcopy);
#endif
	}

#ifdef IPSTEALTH
	if (!ipstealth) {
#endif
		ip->ip_ttl -= IPTTLDEC;
#ifdef IPSTEALTH
	}
#endif

	/*
	 * If forwarding packet using same interface that it came in on,
	 * perhaps should send a redirect to sender to shortcut a hop.
	 * Only send redirect if source is sending directly to us,
	 * and if packet was not source routed (or has any options).
	 * Also, don't send redirect if forwarding using a default route
	 * or a route modified by a redirect.
	 */
	if (rt->rt_ifp == m->m_pkthdr.rcvif &&
	    (rt->rt_flags & (RTF_DYNAMIC|RTF_MODIFIED)) == 0 &&
	    satosin(rt_key(rt))->sin_addr.s_addr != 0 &&
	    ipsendredirects && !srcrt && !next_hop) {
#define	RTA(rt)	((struct in_ifaddr *)(rt->rt_ifa))
		u_long src = ntohl(ip->ip_src.s_addr);

		if (RTA(rt) &&
		    (src & RTA(rt)->ia_subnetmask) == RTA(rt)->ia_subnet) {
		    if (rt->rt_flags & RTF_GATEWAY)
			dest = satosin(rt->rt_gateway)->sin_addr.s_addr;
		    else
			dest = pkt_dst.s_addr;
		    /* Router requirements says to only send host redirects */
		    type = ICMP_REDIRECT;
		    code = ICMP_REDIRECT_HOST;
#ifdef DIAGNOSTIC
		    if (ipprintfs)
		        printf("redirect (%d) to %lx\n", code, (u_long)dest);
#endif
		}
	}

    {
	struct m_hdr tag;

	if (next_hop) {
		/* Pass IPFORWARD info if available */
 
		tag.mh_type = MT_TAG;
		tag.mh_flags = PACKET_TAG_IPFORWARD;
		tag.mh_data = (caddr_t)next_hop;
		tag.mh_next = m;
		m = (struct mbuf *)&tag;
	}
	error = ip_output(m, (struct mbuf *)0, &ipforward_rt, 
			  IP_FORWARDING, 0, NULL);
    }
	if (error)
		ipstat.ips_cantforward++;
	else {
		ipstat.ips_forward++;
		if (type)
			ipstat.ips_redirectsent++;
		else {
			if (mcopy) {
				ipflow_create(&ipforward_rt, mcopy);
				m_freem(mcopy);
			}
			return;
		}
	}
	if (mcopy == NULL)
		return;
	destifp = NULL;

	switch (error) {

	case 0:				/* forwarded, but need redirect */
		/* type, code set above */
		break;

	case ENETUNREACH:		/* shouldn't happen, checked above */
	case EHOSTUNREACH:
	case ENETDOWN:
	case EHOSTDOWN:
	default:
		type = ICMP_UNREACH;
		code = ICMP_UNREACH_HOST;
		break;

	case EMSGSIZE:
		type = ICMP_UNREACH;
		code = ICMP_UNREACH_NEEDFRAG;
#ifdef IPSEC
		/*
		 * If the packet is routed over IPsec tunnel, tell the
		 * originator the tunnel MTU.
		 *	tunnel MTU = if MTU - sizeof(IP) - ESP/AH hdrsiz
		 * XXX quickhack!!!
		 */
		if (ipforward_rt.ro_rt) {
			struct secpolicy *sp = NULL;
			int ipsecerror;
			int ipsechdr;
			struct route *ro;

			sp = ipsec4_getpolicybyaddr(mcopy,
						    IPSEC_DIR_OUTBOUND,
			                            IP_FORWARDING,
			                            &ipsecerror);

			if (sp == NULL)
				destifp = ipforward_rt.ro_rt->rt_ifp;
			else {
				/* count IPsec header size */
				ipsechdr = ipsec4_hdrsiz(mcopy,
							 IPSEC_DIR_OUTBOUND,
							 NULL);

				/*
				 * find the correct route for outer IPv4
				 * header, compute tunnel MTU.
				 *
				 * XXX BUG ALERT
				 * The "dummyifp" code relies upon the fact
				 * that icmp_error() touches only ifp->if_mtu.
				 */
				/*XXX*/
				destifp = NULL;
				if (sp->req != NULL
				 && sp->req->sav != NULL
				 && sp->req->sav->sah != NULL) {
					ro = &sp->req->sav->sah->sa_route;
					if (ro->ro_rt && ro->ro_rt->rt_ifp) {
						dummyifp.if_mtu =
						    ro->ro_rt->rt_ifp->if_mtu;
						dummyifp.if_mtu -= ipsechdr;
						destifp = &dummyifp;
					}
				}

				key_freesp(sp);
			}
		}
#elif FAST_IPSEC
		/*
		 * If the packet is routed over IPsec tunnel, tell the
		 * originator the tunnel MTU.
		 *	tunnel MTU = if MTU - sizeof(IP) - ESP/AH hdrsiz
		 * XXX quickhack!!!
		 */
		if (ipforward_rt.ro_rt) {
			struct secpolicy *sp = NULL;
			int ipsecerror;
			int ipsechdr;
			struct route *ro;

			sp = ipsec_getpolicybyaddr(mcopy,
						   IPSEC_DIR_OUTBOUND,
			                           IP_FORWARDING,
			                           &ipsecerror);

			if (sp == NULL)
				destifp = ipforward_rt.ro_rt->rt_ifp;
			else {
				/* count IPsec header size */
				ipsechdr = ipsec4_hdrsiz(mcopy,
							 IPSEC_DIR_OUTBOUND,
							 NULL);

				/*
				 * find the correct route for outer IPv4
				 * header, compute tunnel MTU.
				 *
				 * XXX BUG ALERT
				 * The "dummyifp" code relies upon the fact
				 * that icmp_error() touches only ifp->if_mtu.
				 */
				/*XXX*/
				destifp = NULL;
				if (sp->req != NULL
				 && sp->req->sav != NULL
				 && sp->req->sav->sah != NULL) {
					ro = &sp->req->sav->sah->sa_route;
					if (ro->ro_rt && ro->ro_rt->rt_ifp) {
						dummyifp.if_mtu =
						    ro->ro_rt->rt_ifp->if_mtu;
						dummyifp.if_mtu -= ipsechdr;
						destifp = &dummyifp;
					}
				}

				KEY_FREESP(&sp);
			}
		}
#else /* !IPSEC && !FAST_IPSEC */
		if (ipforward_rt.ro_rt)
			destifp = ipforward_rt.ro_rt->rt_ifp;
#endif /*IPSEC*/
		ipstat.ips_cantfrag++;
		break;

	case ENOBUFS:
		type = ICMP_SOURCEQUENCH;
		code = 0;
		break;

	case EACCES:			/* ipfw denied packet */
		m_freem(mcopy);
		return;
	}
	icmp_error(mcopy, type, code, dest, destifp);
}

void
ip_savecontrol(inp, mp, ip, m)
	register struct inpcb *inp;
	register struct mbuf **mp;
	register struct ip *ip;
	register struct mbuf *m;
{
	if (inp->inp_socket->so_options & SO_TIMESTAMP) {
		struct timeval tv;

		microtime(&tv);
		*mp = sbcreatecontrol((caddr_t) &tv, sizeof(tv),
			SCM_TIMESTAMP, SOL_SOCKET);
		if (*mp)
			mp = &(*mp)->m_next;
	}
	if (inp->inp_flags & INP_RECVDSTADDR) {
		*mp = sbcreatecontrol((caddr_t) &ip->ip_dst,
		    sizeof(struct in_addr), IP_RECVDSTADDR, IPPROTO_IP);
		if (*mp)
			mp = &(*mp)->m_next;
	}
#ifdef notyet
	/* XXX
	 * Moving these out of udp_input() made them even more broken
	 * than they already were.
	 */
	/* options were tossed already */
	if (inp->inp_flags & INP_RECVOPTS) {
		*mp = sbcreatecontrol((caddr_t) opts_deleted_above,
		    sizeof(struct in_addr), IP_RECVOPTS, IPPROTO_IP);
		if (*mp)
			mp = &(*mp)->m_next;
	}
	/* ip_srcroute doesn't do what we want here, need to fix */
	if (inp->inp_flags & INP_RECVRETOPTS) {
		*mp = sbcreatecontrol((caddr_t) ip_srcroute(),
		    sizeof(struct in_addr), IP_RECVRETOPTS, IPPROTO_IP);
		if (*mp)
			mp = &(*mp)->m_next;
	}
#endif
	if (inp->inp_flags & INP_RECVIF) {
		struct ifnet *ifp;
		struct sdlbuf {
			struct sockaddr_dl sdl;
			u_char	pad[32];
		} sdlbuf;
		struct sockaddr_dl *sdp;
		struct sockaddr_dl *sdl2 = &sdlbuf.sdl;

		if (((ifp = m->m_pkthdr.rcvif)) 
		&& ( ifp->if_index && (ifp->if_index <= if_index))) {
			sdp = (struct sockaddr_dl *)
			    (ifaddr_byindex(ifp->if_index)->ifa_addr);
			/*
			 * Change our mind and don't try copy.
			 */
			if ((sdp->sdl_family != AF_LINK)
			|| (sdp->sdl_len > sizeof(sdlbuf))) {
				goto makedummy;
			}
			bcopy(sdp, sdl2, sdp->sdl_len);
		} else {
makedummy:	
			sdl2->sdl_len
				= offsetof(struct sockaddr_dl, sdl_data[0]);
			sdl2->sdl_family = AF_LINK;
			sdl2->sdl_index = 0;
			sdl2->sdl_nlen = sdl2->sdl_alen = sdl2->sdl_slen = 0;
		}
		*mp = sbcreatecontrol((caddr_t) sdl2, sdl2->sdl_len,
			IP_RECVIF, IPPROTO_IP);
		if (*mp)
			mp = &(*mp)->m_next;
	}
}

/*
 * XXX these routines are called from the upper part of the kernel.
 * They need to be locked when we remove Giant.
 *
 * They could also be moved to ip_mroute.c, since all the RSVP
 *  handling is done there already.
 */
static int ip_rsvp_on;
struct socket *ip_rsvpd;
int
ip_rsvp_init(struct socket *so)
{
	if (so->so_type != SOCK_RAW ||
	    so->so_proto->pr_protocol != IPPROTO_RSVP)
	  return EOPNOTSUPP;

	if (ip_rsvpd != NULL)
	  return EADDRINUSE;

	ip_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 (!ip_rsvp_on) {
		ip_rsvp_on = 1;
		rsvp_on++;
	}

	return 0;
}

int
ip_rsvp_done(void)
{
	ip_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 (ip_rsvp_on) {
		ip_rsvp_on = 0;
		rsvp_on--;
	}
	return 0;
}
OpenPOWER on IntegriCloud