summaryrefslogtreecommitdiffstats
path: root/sys/netinet/ip_input.c
blob: c265d02b4e28a0d6d365eae4a264c72a314efa2e (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
/*-
 * 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.
 * 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
 */

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

#include "opt_bootp.h"
#include "opt_ipfw.h"
#include "opt_ipstealth.h"
#include "opt_ipsec.h"
#include "opt_kdtrace.h"
#include "opt_route.h"

#include <sys/param.h>
#include <sys/systm.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/lock.h>
#include <sys/rwlock.h>
#include <sys/sdt.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/vnet.h>
#include <net/flowtable.h>

#include <netinet/in.h>
#include <netinet/in_kdtrace.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_fw.h>
#include <netinet/ip_icmp.h>
#include <netinet/ip_options.h>
#include <machine/in_cksum.h>
#include <netinet/ip_carp.h>
#ifdef IPSEC
#include <netinet/ip_ipsec.h>
#endif /* IPSEC */

#include <sys/socketvar.h>

#include <security/mac/mac_framework.h>

#ifdef CTASSERT
CTASSERT(sizeof(struct ip) == 20);
#endif

struct	rwlock in_ifaddr_lock;
RW_SYSINIT(in_ifaddr_lock, &in_ifaddr_lock, "in_ifaddr_lock");

VNET_DEFINE(int, rsvp_on);

VNET_DEFINE(int, ipforwarding);
SYSCTL_VNET_INT(_net_inet_ip, IPCTL_FORWARDING, forwarding, CTLFLAG_RW,
    &VNET_NAME(ipforwarding), 0,
    "Enable IP forwarding between interfaces");

static VNET_DEFINE(int, ipsendredirects) = 1;	/* XXX */
#define	V_ipsendredirects	VNET(ipsendredirects)
SYSCTL_VNET_INT(_net_inet_ip, IPCTL_SENDREDIRECTS, redirect, CTLFLAG_RW,
    &VNET_NAME(ipsendredirects), 0,
    "Enable sending IP redirects");

static VNET_DEFINE(int, ip_keepfaith);
#define	V_ip_keepfaith		VNET(ip_keepfaith)
SYSCTL_VNET_INT(_net_inet_ip, IPCTL_KEEPFAITH, keepfaith, CTLFLAG_RW,
    &VNET_NAME(ip_keepfaith), 0,
    "Enable packet capture for FAITH IPv4->IPv6 translater daemon");

static VNET_DEFINE(int, ip_sendsourcequench);
#define	V_ip_sendsourcequench	VNET(ip_sendsourcequench)
SYSCTL_VNET_INT(_net_inet_ip, OID_AUTO, sendsourcequench, CTLFLAG_RW,
    &VNET_NAME(ip_sendsourcequench), 0,
    "Enable the transmission of source quench packets");

VNET_DEFINE(int, ip_do_randomid);
SYSCTL_VNET_INT(_net_inet_ip, OID_AUTO, random_id, CTLFLAG_RW,
    &VNET_NAME(ip_do_randomid), 0,
    "Assign random ip_id values");

/*
 * 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 VNET_DEFINE(int, ip_checkinterface);
#define	V_ip_checkinterface	VNET(ip_checkinterface)
SYSCTL_VNET_INT(_net_inet_ip, OID_AUTO, check_interface, CTLFLAG_RW,
    &VNET_NAME(ip_checkinterface), 0,
    "Verify packet arrives on correct interface");

VNET_DEFINE(struct pfil_head, inet_pfil_hook);	/* Packet filter hooks */

static struct netisr_handler ip_nh = {
	.nh_name = "ip",
	.nh_handler = ip_input,
	.nh_proto = NETISR_IP,
	.nh_policy = NETISR_POLICY_FLOW,
};

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

static VNET_DEFINE(uma_zone_t, ipq_zone);
static VNET_DEFINE(TAILQ_HEAD(ipqhead, ipq), ipq[IPREASS_NHASH]);
static struct mtx ipqlock;

#define	V_ipq_zone		VNET(ipq_zone)
#define	V_ipq			VNET(ipq)

#define	IPQ_LOCK()	mtx_lock(&ipqlock)
#define	IPQ_UNLOCK()	mtx_unlock(&ipqlock)
#define	IPQ_LOCK_INIT()	mtx_init(&ipqlock, "ipqlock", NULL, MTX_DEF)
#define	IPQ_LOCK_ASSERT()	mtx_assert(&ipqlock, MA_OWNED)

static void	maxnipq_update(void);
static void	ipq_zone_change(void *);
static void	ip_drain_locked(void);

static VNET_DEFINE(int, maxnipq);  /* Administrative limit on # reass queues. */
static VNET_DEFINE(int, nipq);			/* Total # of reass queues */
#define	V_maxnipq		VNET(maxnipq)
#define	V_nipq			VNET(nipq)
SYSCTL_VNET_INT(_net_inet_ip, OID_AUTO, fragpackets, CTLFLAG_RD,
    &VNET_NAME(nipq), 0,
    "Current number of IPv4 fragment reassembly queue entries");

static VNET_DEFINE(int, maxfragsperpacket);
#define	V_maxfragsperpacket	VNET(maxfragsperpacket)
SYSCTL_VNET_INT(_net_inet_ip, OID_AUTO, maxfragsperpacket, CTLFLAG_RW,
    &VNET_NAME(maxfragsperpacket), 0,
    "Maximum number of IPv4 fragments allowed per packet");

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

#ifdef IPSTEALTH
VNET_DEFINE(int, ipstealth);
SYSCTL_VNET_INT(_net_inet_ip, OID_AUTO, stealth, CTLFLAG_RW,
    &VNET_NAME(ipstealth), 0,
    "IP stealth mode, no TTL decrementation on forwarding");
#endif

#ifdef FLOWTABLE
static VNET_DEFINE(int, ip_output_flowtable_size) = 2048;
VNET_DEFINE(struct flowtable *, ip_ft);
#define	V_ip_output_flowtable_size	VNET(ip_output_flowtable_size)

SYSCTL_VNET_INT(_net_inet_ip, OID_AUTO, output_flowtable_size, CTLFLAG_RDTUN,
    &VNET_NAME(ip_output_flowtable_size), 2048,
    "number of entries in the per-cpu output flow caches");
#endif

static void	ip_freef(struct ipqhead *, struct ipq *);

/*
 * IP statistics are stored in the "array" of counter(9)s.
 */
VNET_PCPUSTAT_DEFINE(struct ipstat, ipstat);
VNET_PCPUSTAT_SYSINIT(ipstat);
SYSCTL_VNET_PCPUSTAT(_net_inet_ip, IPCTL_STATS, stats, struct ipstat, ipstat,
    "IP statistics (struct ipstat, netinet/ip_var.h)");

#ifdef VIMAGE
VNET_PCPUSTAT_SYSUNINIT(ipstat);
#endif /* VIMAGE */

/*
 * Kernel module interface for updating ipstat.  The argument is an index
 * into ipstat treated as an array.
 */
void
kmod_ipstat_inc(int statnum)
{

	counter_u64_add(VNET(ipstat)[statnum], 1);
}

void
kmod_ipstat_dec(int statnum)
{

	counter_u64_add(VNET(ipstat)[statnum], -1);
}

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

	netisr_getqlimit(&ip_nh, &qlimit);
	error = sysctl_handle_int(oidp, &qlimit, 0, req);
	if (error || !req->newptr)
		return (error);
	if (qlimit < 1)
		return (EINVAL);
	return (netisr_setqlimit(&ip_nh, qlimit));
}
SYSCTL_PROC(_net_inet_ip, IPCTL_INTRQMAXLEN, intr_queue_maxlen,
    CTLTYPE_INT|CTLFLAG_RW, 0, 0, sysctl_netinet_intr_queue_maxlen, "I",
    "Maximum size of the IP input queue");

static int
sysctl_netinet_intr_queue_drops(SYSCTL_HANDLER_ARGS)
{
	u_int64_t qdrops_long;
	int error, qdrops;

	netisr_getqdrops(&ip_nh, &qdrops_long);
	qdrops = qdrops_long;
	error = sysctl_handle_int(oidp, &qdrops, 0, req);
	if (error || !req->newptr)
		return (error);
	if (qdrops != 0)
		return (EINVAL);
	netisr_clearqdrops(&ip_nh);
	return (0);
}

SYSCTL_PROC(_net_inet_ip, IPCTL_INTRQDROPS, intr_queue_drops,
    CTLTYPE_INT|CTLFLAG_RD, 0, 0, sysctl_netinet_intr_queue_drops, "I",
    "Number of packets dropped from the IP input queue");

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

	V_ip_id = time_second & 0xffff;

	TAILQ_INIT(&V_in_ifaddrhead);
	V_in_ifaddrhashtbl = hashinit(INADDR_NHASH, M_IFADDR, &V_in_ifaddrhmask);

	/* Initialize IP reassembly queue. */
	for (i = 0; i < IPREASS_NHASH; i++)
		TAILQ_INIT(&V_ipq[i]);
	V_maxnipq = nmbclusters / 32;
	V_maxfragsperpacket = 16;
	V_ipq_zone = uma_zcreate("ipq", sizeof(struct ipq), NULL, NULL, NULL,
	    NULL, UMA_ALIGN_PTR, 0);
	maxnipq_update();

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

#ifdef FLOWTABLE
	if (TUNABLE_INT_FETCH("net.inet.ip.output_flowtable_size",
		&V_ip_output_flowtable_size)) {
		if (V_ip_output_flowtable_size < 256)
			V_ip_output_flowtable_size = 256;
		if (!powerof2(V_ip_output_flowtable_size)) {
			printf("flowtable must be power of 2 size\n");
			V_ip_output_flowtable_size = 2048;
		}
	} else {
		/*
		 * round up to the next power of 2
		 */
		V_ip_output_flowtable_size = 1 << fls((1024 + maxusers * 64)-1);
	}
	V_ip_ft = flowtable_alloc("ipv4", V_ip_output_flowtable_size, FL_PCPU);
#endif

	/* Skip initialization of globals for non-default instances. */
	if (!IS_DEFAULT_VNET(curvnet))
		return;

	pr = pffindproto(PF_INET, IPPROTO_RAW, SOCK_RAW);
	if (pr == NULL)
		panic("ip_init: PF_INET not found");

	/* Initialize the entire ip_protox[] array to IPPROTO_RAW. */
	for (i = 0; i < IPPROTO_MAX; i++)
		ip_protox[i] = pr - inetsw;
	/*
	 * Cycle through IP protocols and put them into the appropriate place
	 * in ip_protox[].
	 */
	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) {
			/* Be careful to only index valid IP protocols. */
			if (pr->pr_protocol < IPPROTO_MAX)
				ip_protox[pr->pr_protocol] = pr - inetsw;
		}

	EVENTHANDLER_REGISTER(nmbclusters_change, ipq_zone_change,
		NULL, EVENTHANDLER_PRI_ANY);

	/* Initialize various other remaining things. */
	IPQ_LOCK_INIT();
	netisr_register(&ip_nh);
}

#ifdef VIMAGE
void
ip_destroy(void)
{
	int i;

	if ((i = pfil_head_unregister(&V_inet_pfil_hook)) != 0)
		printf("%s: WARNING: unable to unregister pfil hook, "
		    "error %d\n", __func__, i);

	/* Cleanup in_ifaddr hash table; should be empty. */
	hashdestroy(V_in_ifaddrhashtbl, M_IFADDR, V_in_ifaddrhmask);

	IPQ_LOCK();
	ip_drain_locked();
	IPQ_UNLOCK();

	uma_zdestroy(V_ipq_zone);
}
#endif

/*
 * 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 = NULL;
	struct in_ifaddr *ia = NULL;
	struct ifaddr *ifa;
	struct ifnet *ifp;
	int    checkif, hlen = 0;
	uint16_t sum, ip_len;
	int dchg = 0;				/* dest changed after fw */
	struct in_addr odst;			/* original dst address */

	M_ASSERTPKTHDR(m);

	if (m->m_flags & M_FASTFWD_OURS) {
		m->m_flags &= ~M_FASTFWD_OURS;
		/* Set up some basics that will be used later. */
		ip = mtod(m, struct ip *);
		hlen = ip->ip_hl << 2;
		ip_len = ntohs(ip->ip_len);
		goto ours;
	}

	IPSTAT_INC(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))) == NULL) {
		IPSTAT_INC(ips_toosmall);
		return;
	}
	ip = mtod(m, struct ip *);

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

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

	IP_PROBE(receive, NULL, NULL, ip, m->m_pkthdr.rcvif, ip, NULL);

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

#ifdef ALTQ
	if (altq_input != NULL && (*altq_input)(m, AF_INET) == 0)
		/* packet is dropped by traffic conditioner */
		return;
#endif

	ip_len = ntohs(ip->ip_len);
	if (ip_len < hlen) {
		IPSTAT_INC(ips_badlen);
		goto bad;
	}

	/*
	 * 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_len) {
tooshort:
		IPSTAT_INC(ips_tooshort);
		goto bad;
	}
	if (m->m_pkthdr.len > ip_len) {
		if (m->m_len == m->m_pkthdr.len) {
			m->m_len = ip_len;
			m->m_pkthdr.len = ip_len;
		} else
			m_adj(m, ip_len - m->m_pkthdr.len);
	}
#ifdef IPSEC
	/*
	 * Bypass packet filtering for packets previously handled by IPsec.
	 */
	if (ip_ipsec_filtertunnel(m))
		goto passin;
#endif /* IPSEC */

	/*
	 * Run through list of hooks for input packets.
	 *
	 * NB: Beware of the destination address changing (e.g.
	 *     by NAT rewriting).  When this happens, tell
	 *     ip_forward to do the right thing.
	 */

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

	odst = ip->ip_dst;
	if (pfil_run_hooks(&V_inet_pfil_hook, &m, ifp, PFIL_IN, NULL) != 0)
		return;
	if (m == NULL)			/* consumed by filter */
		return;

	ip = mtod(m, struct ip *);
	dchg = (odst.s_addr != ip->ip_dst.s_addr);
	ifp = m->m_pkthdr.rcvif;

	if (m->m_flags & M_FASTFWD_OURS) {
		m->m_flags &= ~M_FASTFWD_OURS;
		goto ours;
	}
	if (m->m_flags & M_IP_NEXTHOP) {
		dchg = (m_tag_find(m, PACKET_TAG_IPFORWARD, NULL) != NULL);
		if (dchg != 0) {
			/*
			 * Directly ship the packet on.  This allows
			 * forwarding packets originally destined to us
			 * to some other directly connected host.
			 */
			ip_forward(m, 1);
			return;
		}
	}
passin:

	/*
	 * 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).
	 */
	if (hlen > sizeof (struct ip) && ip_dooptions(m, 0))
		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 (V_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(&V_in_ifaddrhead) &&
	    (m->m_flags & (M_MCAST|M_BCAST)) == 0)
		goto ours;

	/*
	 * 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.
	 *
	 * XXX - This is the case for carp vhost IPs as well so we
	 * insert a workaround. If the packet got here, we already
	 * checked with carp_iamatch() and carp_forus().
	 */
	checkif = V_ip_checkinterface && (V_ipforwarding == 0) && 
	    ifp != NULL && ((ifp->if_flags & IFF_LOOPBACK) == 0) &&
	    ifp->if_carp == NULL && (dchg == 0);

	/*
	 * Check for exact addresses in the hash bucket.
	 */
	/* IN_IFADDR_RLOCK(); */
	LIST_FOREACH(ia, INADDR_HASH(ip->ip_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 == ip->ip_dst.s_addr && 
		    (!checkif || ia->ia_ifp == ifp)) {
			ifa_ref(&ia->ia_ifa);
			/* IN_IFADDR_RUNLOCK(); */
			goto ours;
		}
	}
	/* IN_IFADDR_RUNLOCK(); */

	/*
	 * 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 (ifp != NULL && ifp->if_flags & IFF_BROADCAST) {
		IF_ADDR_RLOCK(ifp);
	        TAILQ_FOREACH(ifa, &ifp->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 ==
			    ip->ip_dst.s_addr) {
				ifa_ref(ifa);
				IF_ADDR_RUNLOCK(ifp);
				goto ours;
			}
#ifdef BOOTP_COMPAT
			if (IA_SIN(ia)->sin_addr.s_addr == INADDR_ANY) {
				ifa_ref(ifa);
				IF_ADDR_RUNLOCK(ifp);
				goto ours;
			}
#endif
		}
		IF_ADDR_RUNLOCK(ifp);
		ia = NULL;
	}
	/* RFC 3927 2.7: Do not forward datagrams for 169.254.0.0/16. */
	if (IN_LINKLOCAL(ntohl(ip->ip_dst.s_addr))) {
		IPSTAT_INC(ips_cantforward);
		m_freem(m);
		return;
	}
	if (IN_MULTICAST(ntohl(ip->ip_dst.s_addr))) {
		if (V_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_mforward(ip, ifp, m, 0) != 0) {
				IPSTAT_INC(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_INC(ips_forward);
		}
		/*
		 * Assume the packet is for us, to avoid prematurely taking
		 * a lock on the in_multi hash. Protocols must perform
		 * their own filtering and update statistics accordingly.
		 */
		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 (ifp && ifp->if_type == IFT_FAITH) {
		if (V_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 (V_ipforwarding == 0) {
		IPSTAT_INC(ips_cantforward);
		m_freem(m);
	} else {
#ifdef IPSEC
		if (ip_ipsec_fwd(m))
			goto bad;
#endif /* IPSEC */
		ip_forward(m, dchg);
	}
	return;

ours:
#ifdef IPSTEALTH
	/*
	 * IPSTEALTH: Process non-routing options only
	 * if the packet is destined for us.
	 */
	if (V_ipstealth && hlen > sizeof (struct ip) && ip_dooptions(m, 1)) {
		if (ia != NULL)
			ifa_free(&ia->ia_ifa);
		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;
		ifa_free(&ia->ia_ifa);
	}

	/*
	 * Attempt reassembly; if it succeeds, proceed.
	 * ip_reass() will return a different mbuf.
	 */
	if (ip->ip_off & htons(IP_MF | IP_OFFMASK)) {
		m = ip_reass(m);
		if (m == NULL)
			return;
		ip = mtod(m, struct ip *);
		/* Get the header length of the reassembled packet */
		hlen = ip->ip_hl << 2;
	}

#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 (ip_ipsec_input(m))
		goto bad;
#endif /* IPSEC */

	/*
	 * Switch out to protocol's input routine.
	 */
	IPSTAT_INC(ips_delivered);

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

/*
 * After maxnipq has been updated, propagate the change to UMA.  The UMA zone
 * max has slightly different semantics than the sysctl, for historical
 * reasons.
 */
static void
maxnipq_update(void)
{

	/*
	 * -1 for unlimited allocation.
	 */
	if (V_maxnipq < 0)
		uma_zone_set_max(V_ipq_zone, 0);
	/*
	 * Positive number for specific bound.
	 */
	if (V_maxnipq > 0)
		uma_zone_set_max(V_ipq_zone, V_maxnipq);
	/*
	 * Zero specifies no further fragment queue allocation -- set the
	 * bound very low, but rely on implementation elsewhere to actually
	 * prevent allocation and reclaim current queues.
	 */
	if (V_maxnipq == 0)
		uma_zone_set_max(V_ipq_zone, 1);
}

static void
ipq_zone_change(void *tag)
{

	if (V_maxnipq > 0 && V_maxnipq < (nmbclusters / 32)) {
		V_maxnipq = nmbclusters / 32;
		maxnipq_update();
	}
}

static int
sysctl_maxnipq(SYSCTL_HANDLER_ARGS)
{
	int error, i;

	i = V_maxnipq;
	error = sysctl_handle_int(oidp, &i, 0, req);
	if (error || !req->newptr)
		return (error);

	/*
	 * XXXRW: Might be a good idea to sanity check the argument and place
	 * an extreme upper bound.
	 */
	if (i < -1)
		return (EINVAL);
	V_maxnipq = i;
	maxnipq_update();
	return (0);
}

SYSCTL_PROC(_net_inet_ip, OID_AUTO, maxfragpackets, CTLTYPE_INT|CTLFLAG_RW,
    NULL, 0, sysctl_maxnipq, "I",
    "Maximum number of IPv4 fragment reassembly queue entries");

/*
 * Take incoming datagram fragment and try to reassemble it into
 * whole datagram.  If the argument is the first fragment or one
 * in between the function will return NULL and store the mbuf
 * in the fragment chain.  If the argument is the last fragment
 * the packet will be reassembled and the pointer to the new
 * mbuf returned for further processing.  Only m_tags attached
 * to the first packet/fragment are preserved.
 * The IP header is *NOT* adjusted out of iplen.
 */
struct mbuf *
ip_reass(struct mbuf *m)
{
	struct ip *ip;
	struct mbuf *p, *q, *nq, *t;
	struct ipq *fp = NULL;
	struct ipqhead *head;
	int i, hlen, next;
	u_int8_t ecn, ecn0;
	u_short hash;

	/* If maxnipq or maxfragsperpacket are 0, never accept fragments. */
	if (V_maxnipq == 0 || V_maxfragsperpacket == 0) {
		IPSTAT_INC(ips_fragments);
		IPSTAT_INC(ips_fragdropped);
		m_freem(m);
		return (NULL);
	}

	ip = mtod(m, struct ip *);
	hlen = ip->ip_hl << 2;

	hash = IPREASS_HASH(ip->ip_src.s_addr, ip->ip_id);
	head = &V_ipq[hash];
	IPQ_LOCK();

	/*
	 * Look for queue of fragments
	 * of this datagram.
	 */
	TAILQ_FOREACH(fp, head, 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_ipq_match(m, fp) &&
#endif
		    ip->ip_p == fp->ipq_p)
			goto found;

	fp = NULL;

	/*
	 * Attempt to trim the number of allocated fragment queues if it
	 * exceeds the administrative limit.
	 */
	if ((V_nipq > V_maxnipq) && (V_maxnipq > 0)) {
		/*
		 * drop something from the tail of the current queue
		 * before proceeding further
		 */
		struct ipq *q = TAILQ_LAST(head, ipqhead);
		if (q == NULL) {   /* gak */
			for (i = 0; i < IPREASS_NHASH; i++) {
				struct ipq *r = TAILQ_LAST(&V_ipq[i], ipqhead);
				if (r) {
					IPSTAT_ADD(ips_fragtimeout,
					    r->ipq_nfrags);
					ip_freef(&V_ipq[i], r);
					break;
				}
			}
		} else {
			IPSTAT_ADD(ips_fragtimeout, q->ipq_nfrags);
			ip_freef(head, q);
		}
	}

found:
	/*
	 * Adjust ip_len to not reflect header,
	 * convert offset of this to bytes.
	 */
	ip->ip_len = htons(ntohs(ip->ip_len) - hlen);
	if (ip->ip_off & htons(IP_MF)) {
		/*
		 * Make sure that fragments have a data length
		 * that's a non-zero multiple of 8 bytes.
		 */
		if (ip->ip_len == htons(0) || (ntohs(ip->ip_len) & 0x7) != 0) {
			IPSTAT_INC(ips_toosmall); /* XXX */
			goto dropfrag;
		}
		m->m_flags |= M_IP_FRAG;
	} else
		m->m_flags &= ~M_IP_FRAG;
	ip->ip_off = htons(ntohs(ip->ip_off) << 3);

	/*
	 * Attempt reassembly; if it succeeds, proceed.
	 * ip_reass() will return a different mbuf.
	 */
	IPSTAT_INC(ips_fragments);
	m->m_pkthdr.PH_loc.ptr = ip;

	/* Previous ip_reass() started here. */
	/*
	 * 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 == NULL) {
		fp = uma_zalloc(V_ipq_zone, M_NOWAIT);
		if (fp == NULL)
			goto dropfrag;
#ifdef MAC
		if (mac_ipq_init(fp, M_NOWAIT) != 0) {
			uma_zfree(V_ipq_zone, fp);
			fp = NULL;
			goto dropfrag;
		}
		mac_ipq_create(m, fp);
#endif
		TAILQ_INSERT_HEAD(head, fp, ipq_list);
		V_nipq++;
		fp->ipq_nfrags = 1;
		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;
		goto done;
	} else {
		fp->ipq_nfrags++;
#ifdef MAC
		mac_ipq_update(m, fp);
#endif
	}

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

	/*
	 * Handle ECN by comparing this segment with the first one;
	 * if CE is set, do not lose CE.
	 * drop if CE and not-ECT are mixed for the same packet.
	 */
	ecn = ip->ip_tos & IPTOS_ECN_MASK;
	ecn0 = GETIP(fp->ipq_frags)->ip_tos & IPTOS_ECN_MASK;
	if (ecn == IPTOS_ECN_CE) {
		if (ecn0 == IPTOS_ECN_NOTECT)
			goto dropfrag;
		if (ecn0 != IPTOS_ECN_CE)
			GETIP(fp->ipq_frags)->ip_tos |= IPTOS_ECN_CE;
	}
	if (ecn == IPTOS_ECN_NOTECT && ecn0 != IPTOS_ECN_NOTECT)
		goto dropfrag;

	/*
	 * Find a segment which begins after this one does.
	 */
	for (p = NULL, q = fp->ipq_frags; q; p = q, q = q->m_nextpkt)
		if (ntohs(GETIP(q)->ip_off) > ntohs(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 preceding
	 * segment, then it's checksum is invalidated.
	 */
	if (p) {
		i = ntohs(GETIP(p)->ip_off) + ntohs(GETIP(p)->ip_len) -
		    ntohs(ip->ip_off);
		if (i > 0) {
			if (i >= ntohs(ip->ip_len))
				goto dropfrag;
			m_adj(m, i);
			m->m_pkthdr.csum_flags = 0;
			ip->ip_off = htons(ntohs(ip->ip_off) + i);
			ip->ip_len = htons(ntohs(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 && ntohs(ip->ip_off) + ntohs(ip->ip_len) >
	    ntohs(GETIP(q)->ip_off); q = nq) {
		i = (ntohs(ip->ip_off) + ntohs(ip->ip_len)) -
		    ntohs(GETIP(q)->ip_off);
		if (i < ntohs(GETIP(q)->ip_len)) {
			GETIP(q)->ip_len = htons(ntohs(GETIP(q)->ip_len) - i);
			GETIP(q)->ip_off = htons(ntohs(GETIP(q)->ip_off) + i);
			m_adj(q, i);
			q->m_pkthdr.csum_flags = 0;
			break;
		}
		nq = q->m_nextpkt;
		m->m_nextpkt = nq;
		IPSTAT_INC(ips_fragdropped);
		fp->ipq_nfrags--;
		m_freem(q);
	}

	/*
	 * Check for complete reassembly and perform frag per packet
	 * limiting.
	 *
	 * Frag limiting is performed here so that the nth frag has
	 * a chance to complete the packet before we drop the packet.
	 * As a result, n+1 frags are actually allowed per packet, but
	 * only n will ever be stored. (n = maxfragsperpacket.)
	 *
	 */
	next = 0;
	for (p = NULL, q = fp->ipq_frags; q; p = q, q = q->m_nextpkt) {
		if (ntohs(GETIP(q)->ip_off) != next) {
			if (fp->ipq_nfrags > V_maxfragsperpacket) {
				IPSTAT_ADD(ips_fragdropped, fp->ipq_nfrags);
				ip_freef(head, fp);
			}
			goto done;
		}
		next += ntohs(GETIP(q)->ip_len);
	}
	/* Make sure the last packet didn't have the IP_MF flag */
	if (p->m_flags & M_IP_FRAG) {
		if (fp->ipq_nfrags > V_maxfragsperpacket) {
			IPSTAT_ADD(ips_fragdropped, fp->ipq_nfrags);
			ip_freef(head, fp);
		}
		goto done;
	}

	/*
	 * 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_INC(ips_toolong);
		IPSTAT_ADD(ips_fragdropped, fp->ipq_nfrags);
		ip_freef(head, fp);
		goto done;
	}

	/*
	 * Concatenate fragments.
	 */
	m = q;
	t = m->m_next;
	m->m_next = NULL;
	m_cat(m, t);
	nq = q->m_nextpkt;
	q->m_nextpkt = NULL;
	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);
	}
	/*
	 * In order to do checksumming faster we do 'end-around carry' here
	 * (and not in for{} loop), though it implies we are not going to
	 * reassemble more than 64k fragments.
	 */
	m->m_pkthdr.csum_data =
	    (m->m_pkthdr.csum_data & 0xffff) + (m->m_pkthdr.csum_data >> 16);
#ifdef MAC
	mac_ipq_reassemble(fp, m);
	mac_ipq_destroy(fp);
#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 = htons((ip->ip_hl << 2) + next);
	ip->ip_src = fp->ipq_src;
	ip->ip_dst = fp->ipq_dst;
	TAILQ_REMOVE(head, fp, ipq_list);
	V_nipq--;
	uma_zfree(V_ipq_zone, fp);
	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);
	IPSTAT_INC(ips_reassembled);
	IPQ_UNLOCK();
	return (m);

dropfrag:
	IPSTAT_INC(ips_fragdropped);
	if (fp != NULL)
		fp->ipq_nfrags--;
	m_freem(m);
done:
	IPQ_UNLOCK();
	return (NULL);

#undef GETIP
}

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

	IPQ_LOCK_ASSERT();

	while (fp->ipq_frags) {
		q = fp->ipq_frags;
		fp->ipq_frags = q->m_nextpkt;
		m_freem(q);
	}
	TAILQ_REMOVE(fhp, fp, ipq_list);
	uma_zfree(V_ipq_zone, fp);
	V_nipq--;
}

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

	VNET_LIST_RLOCK_NOSLEEP();
	IPQ_LOCK();
	VNET_FOREACH(vnet_iter) {
		CURVNET_SET(vnet_iter);
		for (i = 0; i < IPREASS_NHASH; i++) {
			for(fp = TAILQ_FIRST(&V_ipq[i]); fp;) {
				struct ipq *fpp;

				fpp = fp;
				fp = TAILQ_NEXT(fp, ipq_list);
				if(--fpp->ipq_ttl == 0) {
					IPSTAT_ADD(ips_fragtimeout,
					    fpp->ipq_nfrags);
					ip_freef(&V_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.
		 */
		if (V_maxnipq >= 0 && V_nipq > V_maxnipq) {
			for (i = 0; i < IPREASS_NHASH; i++) {
				while (V_nipq > V_maxnipq &&
				    !TAILQ_EMPTY(&V_ipq[i])) {
					IPSTAT_ADD(ips_fragdropped,
					    TAILQ_FIRST(&V_ipq[i])->ipq_nfrags);
					ip_freef(&V_ipq[i],
					    TAILQ_FIRST(&V_ipq[i]));
				}
			}
		}
		CURVNET_RESTORE();
	}
	IPQ_UNLOCK();
	VNET_LIST_RUNLOCK_NOSLEEP();
}

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

	IPQ_LOCK_ASSERT();

	for (i = 0; i < IPREASS_NHASH; i++) {
		while(!TAILQ_EMPTY(&V_ipq[i])) {
			IPSTAT_ADD(ips_fragdropped,
			    TAILQ_FIRST(&V_ipq[i])->ipq_nfrags);
			ip_freef(&V_ipq[i], TAILQ_FIRST(&V_ipq[i]));
		}
	}
}

void
ip_drain(void)
{
	VNET_ITERATOR_DECL(vnet_iter);

	VNET_LIST_RLOCK_NOSLEEP();
	IPQ_LOCK();
	VNET_FOREACH(vnet_iter) {
		CURVNET_SET(vnet_iter);
		ip_drain_locked();
		CURVNET_RESTORE();
	}
	IPQ_UNLOCK();
	VNET_LIST_RUNLOCK_NOSLEEP();
	in_rtqdrain();
}

/*
 * The protocol to be inserted into ip_protox[] must be already registered
 * in inetsw[], either statically or through pf_proto_register().
 */
int
ipproto_register(short ipproto)
{
	struct protosw *pr;

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

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

	/* Find the protocol position in inetsw[] and set the index. */
	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) {
			ip_protox[pr->pr_protocol] = pr - inetsw;
			return (0);
		}
	}
	return (EPROTONOSUPPORT);
}

int
ipproto_unregister(short ipproto)
{
	struct protosw *pr;

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

	/* Check if the protocol was indeed registered. */
	pr = pffindproto(PF_INET, IPPROTO_RAW, SOCK_RAW);
	if (pr == NULL)
		return (EPFNOSUPPORT);
	if (ip_protox[ipproto] == pr - inetsw)  /* IPPROTO_RAW */
		return (ENOENT);

	/* Reset the protocol slot to IPPROTO_RAW. */
	ip_protox[ipproto] = pr - inetsw;
	return (0);
}

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

	bzero(&sro, sizeof(sro));
	sin = (struct sockaddr_in *)&sro.ro_dst;
	sin->sin_family = AF_INET;
	sin->sin_len = sizeof(*sin);
	sin->sin_addr = dst;
	in_rtalloc_ign(&sro, 0, fibnum);

	if (sro.ro_rt == NULL)
		return (NULL);

	ia = ifatoia(sro.ro_rt->rt_ifa);
	ifa_ref(&ia->ia_ifa);
	RTFREE(sro.ro_rt);
	return (ia);
}

u_char inetctlerrmap[PRC_NCMDS] = {
	0,		0,		0,		0,
	0,		EMSGSIZE,	EHOSTDOWN,	EHOSTUNREACH,
	EHOSTUNREACH,	EHOSTUNREACH,	ECONNREFUSED,	ECONNREFUSED,
	EMSGSIZE,	EHOSTUNREACH,	0,		0,
	0,		0,		EHOSTUNREACH,	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.
 */
void
ip_forward(struct mbuf *m, int srcrt)
{
	struct ip *ip = mtod(m, struct ip *);
	struct in_ifaddr *ia;
	struct mbuf *mcopy;
	struct in_addr dest;
	struct route ro;
	int error, type = 0, code = 0, mtu = 0;

	if (m->m_flags & (M_BCAST|M_MCAST) || in_canforward(ip->ip_dst) == 0) {
		IPSTAT_INC(ips_cantforward);
		m_freem(m);
		return;
	}
#ifdef IPSTEALTH
	if (!V_ipstealth) {
#endif
		if (ip->ip_ttl <= IPTTLDEC) {
			icmp_error(m, ICMP_TIMXCEED, ICMP_TIMXCEED_INTRANS,
			    0, 0);
			return;
		}
#ifdef IPSTEALTH
	}
#endif

	ia = ip_rtaddr(ip->ip_dst, M_GETFIB(m));
#ifndef IPSEC
	/*
	 * 'ia' may be NULL if there is no route for this destination.
	 * In case of IPsec, Don't discard it just yet, but pass it to
	 * ip_output in case of outgoing IPsec policy.
	 */
	if (!srcrt && ia == NULL) {
		icmp_error(m, ICMP_UNREACH, ICMP_UNREACH_HOST, 0, 0);
		return;
	}
#endif

	/*
	 * 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().
	 */
	mcopy = m_gethdr(M_NOWAIT, m->m_type);
	if (mcopy != NULL && !m_dup_pkthdr(mcopy, m, M_NOWAIT)) {
		/*
		 * It's probably ok if the pkthdr dup fails (because
		 * the deep copy of the tag chain failed), but for now
		 * be conservative and just discard the copy since
		 * code below may some day want the tags.
		 */
		m_free(mcopy);
		mcopy = NULL;
	}
	if (mcopy != NULL) {
		mcopy->m_len = min(ntohs(ip->ip_len), M_TRAILINGSPACE(mcopy));
		mcopy->m_pkthdr.len = mcopy->m_len;
		m_copydata(m, 0, mcopy->m_len, mtod(mcopy, caddr_t));
	}

#ifdef IPSTEALTH
	if (!V_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.
	 */
	dest.s_addr = 0;
	if (!srcrt && V_ipsendredirects &&
	    ia != NULL && ia->ia_ifp == m->m_pkthdr.rcvif) {
		struct sockaddr_in *sin;
		struct rtentry *rt;

		bzero(&ro, sizeof(ro));
		sin = (struct sockaddr_in *)&ro.ro_dst;
		sin->sin_family = AF_INET;
		sin->sin_len = sizeof(*sin);
		sin->sin_addr = ip->ip_dst;
		in_rtalloc_ign(&ro, 0, M_GETFIB(m));

		rt = ro.ro_rt;

		if (rt && (rt->rt_flags & (RTF_DYNAMIC|RTF_MODIFIED)) == 0 &&
		    satosin(rt_key(rt))->sin_addr.s_addr != 0) {
#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.s_addr = satosin(rt->rt_gateway)->sin_addr.s_addr;
				else
					dest.s_addr = ip->ip_dst.s_addr;
				/* Router requirements says to only send host redirects */
				type = ICMP_REDIRECT;
				code = ICMP_REDIRECT_HOST;
			}
		}
		if (rt)
			RTFREE(rt);
	}

	/*
	 * Try to cache the route MTU from ip_output so we can consider it for
	 * the ICMP_UNREACH_NEEDFRAG "Next-Hop MTU" field described in RFC1191.
	 */
	bzero(&ro, sizeof(ro));

	error = ip_output(m, NULL, &ro, IP_FORWARDING, NULL, NULL);

	if (error == EMSGSIZE && ro.ro_rt)
		mtu = ro.ro_rt->rt_rmx.rmx_mtu;
	RO_RTFREE(&ro);

	if (error)
		IPSTAT_INC(ips_cantforward);
	else {
		IPSTAT_INC(ips_forward);
		if (type)
			IPSTAT_INC(ips_redirectsent);
		else {
			if (mcopy)
				m_freem(mcopy);
			if (ia != NULL)
				ifa_free(&ia->ia_ifa);
			return;
		}
	}
	if (mcopy == NULL) {
		if (ia != NULL)
			ifa_free(&ia->ia_ifa);
		return;
	}

	switch (error) {

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

	case ENETUNREACH:
	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 IPsec is configured for this path,
		 * override any possibly mtu value set by ip_output.
		 */ 
		mtu = ip_ipsec_mtu(mcopy, mtu);
#endif /* IPSEC */
		/*
		 * If the MTU was set before make sure we are below the
		 * interface MTU.
		 * If the MTU wasn't set before use the interface mtu or
		 * fall back to the next smaller mtu step compared to the
		 * current packet size.
		 */
		if (mtu != 0) {
			if (ia != NULL)
				mtu = min(mtu, ia->ia_ifp->if_mtu);
		} else {
			if (ia != NULL)
				mtu = ia->ia_ifp->if_mtu;
			else
				mtu = ip_next_mtu(ntohs(ip->ip_len), 0);
		}
		IPSTAT_INC(ips_cantfrag);
		break;

	case ENOBUFS:
		/*
		 * A router should not generate ICMP_SOURCEQUENCH as
		 * required in RFC1812 Requirements for IP Version 4 Routers.
		 * Source quench could be a big problem under DoS attacks,
		 * or if the underlying interface is rate-limited.
		 * Those who need source quench packets may re-enable them
		 * via the net.inet.ip.sendsourcequench sysctl.
		 */
		if (V_ip_sendsourcequench == 0) {
			m_freem(mcopy);
			if (ia != NULL)
				ifa_free(&ia->ia_ifa);
			return;
		} else {
			type = ICMP_SOURCEQUENCH;
			code = 0;
		}
		break;

	case EACCES:			/* ipfw denied packet */
		m_freem(mcopy);
		if (ia != NULL)
			ifa_free(&ia->ia_ifa);
		return;
	}
	if (ia != NULL)
		ifa_free(&ia->ia_ifa);
	icmp_error(mcopy, type, code, dest.s_addr, mtu);
}

void
ip_savecontrol(struct inpcb *inp, struct mbuf **mp, struct ip *ip,
    struct mbuf *m)
{

	if (inp->inp_socket->so_options & (SO_BINTIME | SO_TIMESTAMP)) {
		struct bintime bt;

		bintime(&bt);
		if (inp->inp_socket->so_options & SO_BINTIME) {
			*mp = sbcreatecontrol((caddr_t)&bt, sizeof(bt),
			    SCM_BINTIME, SOL_SOCKET);
			if (*mp)
				mp = &(*mp)->m_next;
		}
		if (inp->inp_socket->so_options & SO_TIMESTAMP) {
			struct timeval tv;

			bintime2timeval(&bt, &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;
	}
	if (inp->inp_flags & INP_RECVTTL) {
		*mp = sbcreatecontrol((caddr_t)&ip->ip_ttl,
		    sizeof(u_char), IP_RECVTTL, 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(m),
		    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 <= V_if_index) {
			sdp = (struct sockaddr_dl *)ifp->if_addr->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;
	}
	if (inp->inp_flags & INP_RECVTOS) {
		*mp = sbcreatecontrol((caddr_t)&ip->ip_tos,
		    sizeof(u_char), IP_RECVTOS, IPPROTO_IP);
		if (*mp)
			mp = &(*mp)->m_next;
	}
}

/*
 * XXXRW: Multicast routing code in ip_mroute.c is generally MPSAFE, but the
 * ip_rsvp and ip_rsvp_on variables need to be interlocked with rsvp_on
 * locking.  This code remains in ip_input.c as ip_mroute.c is optionally
 * compiled.
 */
static VNET_DEFINE(int, ip_rsvp_on);
VNET_DEFINE(struct socket *, ip_rsvpd);

#define	V_ip_rsvp_on		VNET(ip_rsvp_on)

int
ip_rsvp_init(struct socket *so)
{

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

	if (V_ip_rsvpd != NULL)
		return EADDRINUSE;

	V_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 (!V_ip_rsvp_on) {
		V_ip_rsvp_on = 1;
		V_rsvp_on++;
	}

	return 0;
}

int
ip_rsvp_done(void)
{

	V_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 (V_ip_rsvp_on) {
		V_ip_rsvp_on = 0;
		V_rsvp_on--;
	}
	return 0;
}

void
rsvp_input(struct mbuf *m, int off)	/* XXX must fixup manually */
{

	if (rsvp_input_p) { /* call the real one if loaded */
		rsvp_input_p(m, off);
		return;
	}

	/* 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 (!V_rsvp_on) {
		m_freem(m);
		return;
	}

	if (V_ip_rsvpd != NULL) { 
		rip_input(m, off);
		return;
	}
	/* Drop the packet */
	m_freem(m);
}
OpenPOWER on IntegriCloud