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
|
/* Connection state tracking for netfilter. This is separated from,
but required by, the NAT layer; it can also be used by an iptables
extension. */
/* (C) 1999-2001 Paul `Rusty' Russell
* (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* 23 Apr 2001: Harald Welte <laforge@gnumonks.org>
* - new API and handling of conntrack/nat helpers
* - now capable of multiple expectations for one master
* 16 Jul 2002: Harald Welte <laforge@gnumonks.org>
* - add usage/reference counts to ip_conntrack_expect
* - export ip_conntrack[_expect]_{find_get,put} functions
* */
#include <linux/config.h>
#include <linux/types.h>
#include <linux/icmp.h>
#include <linux/ip.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/proc_fs.h>
#include <linux/vmalloc.h>
#include <net/checksum.h>
#include <net/ip.h>
#include <linux/stddef.h>
#include <linux/sysctl.h>
#include <linux/slab.h>
#include <linux/random.h>
#include <linux/jhash.h>
#include <linux/err.h>
#include <linux/percpu.h>
#include <linux/moduleparam.h>
#include <linux/notifier.h>
/* ip_conntrack_lock protects the main hash table, protocol/helper/expected
registrations, conntrack timers*/
#define ASSERT_READ_LOCK(x)
#define ASSERT_WRITE_LOCK(x)
#include <linux/netfilter_ipv4/ip_conntrack.h>
#include <linux/netfilter_ipv4/ip_conntrack_protocol.h>
#include <linux/netfilter_ipv4/ip_conntrack_helper.h>
#include <linux/netfilter_ipv4/ip_conntrack_core.h>
#include <linux/netfilter_ipv4/listhelp.h>
#define IP_CONNTRACK_VERSION "2.3"
#if 0
#define DEBUGP printk
#else
#define DEBUGP(format, args...)
#endif
DEFINE_RWLOCK(ip_conntrack_lock);
/* ip_conntrack_standalone needs this */
atomic_t ip_conntrack_count = ATOMIC_INIT(0);
void (*ip_conntrack_destroyed)(struct ip_conntrack *conntrack) = NULL;
LIST_HEAD(ip_conntrack_expect_list);
struct ip_conntrack_protocol *ip_ct_protos[MAX_IP_CT_PROTO];
static LIST_HEAD(helpers);
unsigned int ip_conntrack_htable_size = 0;
int ip_conntrack_max;
struct list_head *ip_conntrack_hash;
static kmem_cache_t *ip_conntrack_cachep;
static kmem_cache_t *ip_conntrack_expect_cachep;
struct ip_conntrack ip_conntrack_untracked;
unsigned int ip_ct_log_invalid;
static LIST_HEAD(unconfirmed);
static int ip_conntrack_vmalloc;
static unsigned int ip_conntrack_next_id = 1;
static unsigned int ip_conntrack_expect_next_id = 1;
#ifdef CONFIG_IP_NF_CONNTRACK_EVENTS
struct notifier_block *ip_conntrack_chain;
struct notifier_block *ip_conntrack_expect_chain;
DEFINE_PER_CPU(struct ip_conntrack_ecache, ip_conntrack_ecache);
/* deliver cached events and clear cache entry - must be called with locally
* disabled softirqs */
static inline void
__ip_ct_deliver_cached_events(struct ip_conntrack_ecache *ecache)
{
DEBUGP("ecache: delivering events for %p\n", ecache->ct);
if (is_confirmed(ecache->ct) && !is_dying(ecache->ct) && ecache->events)
notifier_call_chain(&ip_conntrack_chain, ecache->events,
ecache->ct);
ecache->events = 0;
ip_conntrack_put(ecache->ct);
ecache->ct = NULL;
}
/* Deliver all cached events for a particular conntrack. This is called
* by code prior to async packet handling or freeing the skb */
void ip_ct_deliver_cached_events(const struct ip_conntrack *ct)
{
struct ip_conntrack_ecache *ecache;
local_bh_disable();
ecache = &__get_cpu_var(ip_conntrack_ecache);
if (ecache->ct == ct)
__ip_ct_deliver_cached_events(ecache);
local_bh_enable();
}
void __ip_ct_event_cache_init(struct ip_conntrack *ct)
{
struct ip_conntrack_ecache *ecache;
/* take care of delivering potentially old events */
ecache = &__get_cpu_var(ip_conntrack_ecache);
BUG_ON(ecache->ct == ct);
if (ecache->ct)
__ip_ct_deliver_cached_events(ecache);
/* initialize for this conntrack/packet */
ecache->ct = ct;
nf_conntrack_get(&ct->ct_general);
}
/* flush the event cache - touches other CPU's data and must not be called while
* packets are still passing through the code */
static void ip_ct_event_cache_flush(void)
{
struct ip_conntrack_ecache *ecache;
int cpu;
for_each_cpu(cpu) {
ecache = &per_cpu(ip_conntrack_ecache, cpu);
if (ecache->ct)
ip_conntrack_put(ecache->ct);
}
}
#else
static inline void ip_ct_event_cache_flush(void) {}
#endif /* CONFIG_IP_NF_CONNTRACK_EVENTS */
DEFINE_PER_CPU(struct ip_conntrack_stat, ip_conntrack_stat);
static int ip_conntrack_hash_rnd_initted;
static unsigned int ip_conntrack_hash_rnd;
static u_int32_t
hash_conntrack(const struct ip_conntrack_tuple *tuple)
{
#if 0
dump_tuple(tuple);
#endif
return (jhash_3words(tuple->src.ip,
(tuple->dst.ip ^ tuple->dst.protonum),
(tuple->src.u.all | (tuple->dst.u.all << 16)),
ip_conntrack_hash_rnd) % ip_conntrack_htable_size);
}
int
ip_ct_get_tuple(const struct iphdr *iph,
const struct sk_buff *skb,
unsigned int dataoff,
struct ip_conntrack_tuple *tuple,
const struct ip_conntrack_protocol *protocol)
{
/* Never happen */
if (iph->frag_off & htons(IP_OFFSET)) {
printk("ip_conntrack_core: Frag of proto %u.\n",
iph->protocol);
return 0;
}
tuple->src.ip = iph->saddr;
tuple->dst.ip = iph->daddr;
tuple->dst.protonum = iph->protocol;
tuple->dst.dir = IP_CT_DIR_ORIGINAL;
return protocol->pkt_to_tuple(skb, dataoff, tuple);
}
int
ip_ct_invert_tuple(struct ip_conntrack_tuple *inverse,
const struct ip_conntrack_tuple *orig,
const struct ip_conntrack_protocol *protocol)
{
inverse->src.ip = orig->dst.ip;
inverse->dst.ip = orig->src.ip;
inverse->dst.protonum = orig->dst.protonum;
inverse->dst.dir = !orig->dst.dir;
return protocol->invert_tuple(inverse, orig);
}
/* ip_conntrack_expect helper functions */
static void unlink_expect(struct ip_conntrack_expect *exp)
{
ASSERT_WRITE_LOCK(&ip_conntrack_lock);
IP_NF_ASSERT(!timer_pending(&exp->timeout));
list_del(&exp->list);
CONNTRACK_STAT_INC(expect_delete);
exp->master->expecting--;
}
void __ip_ct_expect_unlink_destroy(struct ip_conntrack_expect *exp)
{
unlink_expect(exp);
ip_conntrack_expect_put(exp);
}
static void expectation_timed_out(unsigned long ul_expect)
{
struct ip_conntrack_expect *exp = (void *)ul_expect;
write_lock_bh(&ip_conntrack_lock);
unlink_expect(exp);
write_unlock_bh(&ip_conntrack_lock);
ip_conntrack_expect_put(exp);
}
struct ip_conntrack_expect *
__ip_conntrack_expect_find(const struct ip_conntrack_tuple *tuple)
{
struct ip_conntrack_expect *i;
list_for_each_entry(i, &ip_conntrack_expect_list, list) {
if (ip_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask)) {
atomic_inc(&i->use);
return i;
}
}
return NULL;
}
/* Just find a expectation corresponding to a tuple. */
struct ip_conntrack_expect *
ip_conntrack_expect_find_get(const struct ip_conntrack_tuple *tuple)
{
struct ip_conntrack_expect *i;
read_lock_bh(&ip_conntrack_lock);
i = __ip_conntrack_expect_find(tuple);
read_unlock_bh(&ip_conntrack_lock);
return i;
}
/* If an expectation for this connection is found, it gets delete from
* global list then returned. */
static struct ip_conntrack_expect *
find_expectation(const struct ip_conntrack_tuple *tuple)
{
struct ip_conntrack_expect *i;
list_for_each_entry(i, &ip_conntrack_expect_list, list) {
/* If master is not in hash table yet (ie. packet hasn't left
this machine yet), how can other end know about expected?
Hence these are not the droids you are looking for (if
master ct never got confirmed, we'd hold a reference to it
and weird things would happen to future packets). */
if (ip_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask)
&& is_confirmed(i->master)
&& del_timer(&i->timeout)) {
unlink_expect(i);
return i;
}
}
return NULL;
}
/* delete all expectations for this conntrack */
void ip_ct_remove_expectations(struct ip_conntrack *ct)
{
struct ip_conntrack_expect *i, *tmp;
/* Optimization: most connection never expect any others. */
if (ct->expecting == 0)
return;
list_for_each_entry_safe(i, tmp, &ip_conntrack_expect_list, list) {
if (i->master == ct && del_timer(&i->timeout)) {
unlink_expect(i);
ip_conntrack_expect_put(i);
}
}
}
static void
clean_from_lists(struct ip_conntrack *ct)
{
unsigned int ho, hr;
DEBUGP("clean_from_lists(%p)\n", ct);
ASSERT_WRITE_LOCK(&ip_conntrack_lock);
ho = hash_conntrack(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
hr = hash_conntrack(&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
LIST_DELETE(&ip_conntrack_hash[ho], &ct->tuplehash[IP_CT_DIR_ORIGINAL]);
LIST_DELETE(&ip_conntrack_hash[hr], &ct->tuplehash[IP_CT_DIR_REPLY]);
/* Destroy all pending expectations */
ip_ct_remove_expectations(ct);
}
static void
destroy_conntrack(struct nf_conntrack *nfct)
{
struct ip_conntrack *ct = (struct ip_conntrack *)nfct;
struct ip_conntrack_protocol *proto;
DEBUGP("destroy_conntrack(%p)\n", ct);
IP_NF_ASSERT(atomic_read(&nfct->use) == 0);
IP_NF_ASSERT(!timer_pending(&ct->timeout));
set_bit(IPS_DYING_BIT, &ct->status);
/* To make sure we don't get any weird locking issues here:
* destroy_conntrack() MUST NOT be called with a write lock
* to ip_conntrack_lock!!! -HW */
proto = __ip_conntrack_proto_find(ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.protonum);
if (proto && proto->destroy)
proto->destroy(ct);
if (ip_conntrack_destroyed)
ip_conntrack_destroyed(ct);
write_lock_bh(&ip_conntrack_lock);
/* Expectations will have been removed in clean_from_lists,
* except TFTP can create an expectation on the first packet,
* before connection is in the list, so we need to clean here,
* too. */
ip_ct_remove_expectations(ct);
/* We overload first tuple to link into unconfirmed list. */
if (!is_confirmed(ct)) {
BUG_ON(list_empty(&ct->tuplehash[IP_CT_DIR_ORIGINAL].list));
list_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].list);
}
CONNTRACK_STAT_INC(delete);
write_unlock_bh(&ip_conntrack_lock);
if (ct->master)
ip_conntrack_put(ct->master);
DEBUGP("destroy_conntrack: returning ct=%p to slab\n", ct);
ip_conntrack_free(ct);
}
static void death_by_timeout(unsigned long ul_conntrack)
{
struct ip_conntrack *ct = (void *)ul_conntrack;
ip_conntrack_event(IPCT_DESTROY, ct);
write_lock_bh(&ip_conntrack_lock);
/* Inside lock so preempt is disabled on module removal path.
* Otherwise we can get spurious warnings. */
CONNTRACK_STAT_INC(delete_list);
clean_from_lists(ct);
write_unlock_bh(&ip_conntrack_lock);
ip_conntrack_put(ct);
}
static inline int
conntrack_tuple_cmp(const struct ip_conntrack_tuple_hash *i,
const struct ip_conntrack_tuple *tuple,
const struct ip_conntrack *ignored_conntrack)
{
ASSERT_READ_LOCK(&ip_conntrack_lock);
return tuplehash_to_ctrack(i) != ignored_conntrack
&& ip_ct_tuple_equal(tuple, &i->tuple);
}
struct ip_conntrack_tuple_hash *
__ip_conntrack_find(const struct ip_conntrack_tuple *tuple,
const struct ip_conntrack *ignored_conntrack)
{
struct ip_conntrack_tuple_hash *h;
unsigned int hash = hash_conntrack(tuple);
ASSERT_READ_LOCK(&ip_conntrack_lock);
list_for_each_entry(h, &ip_conntrack_hash[hash], list) {
if (conntrack_tuple_cmp(h, tuple, ignored_conntrack)) {
CONNTRACK_STAT_INC(found);
return h;
}
CONNTRACK_STAT_INC(searched);
}
return NULL;
}
/* Find a connection corresponding to a tuple. */
struct ip_conntrack_tuple_hash *
ip_conntrack_find_get(const struct ip_conntrack_tuple *tuple,
const struct ip_conntrack *ignored_conntrack)
{
struct ip_conntrack_tuple_hash *h;
read_lock_bh(&ip_conntrack_lock);
h = __ip_conntrack_find(tuple, ignored_conntrack);
if (h)
atomic_inc(&tuplehash_to_ctrack(h)->ct_general.use);
read_unlock_bh(&ip_conntrack_lock);
return h;
}
static void __ip_conntrack_hash_insert(struct ip_conntrack *ct,
unsigned int hash,
unsigned int repl_hash)
{
ct->id = ++ip_conntrack_next_id;
list_prepend(&ip_conntrack_hash[hash],
&ct->tuplehash[IP_CT_DIR_ORIGINAL].list);
list_prepend(&ip_conntrack_hash[repl_hash],
&ct->tuplehash[IP_CT_DIR_REPLY].list);
}
void ip_conntrack_hash_insert(struct ip_conntrack *ct)
{
unsigned int hash, repl_hash;
hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
repl_hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
write_lock_bh(&ip_conntrack_lock);
__ip_conntrack_hash_insert(ct, hash, repl_hash);
write_unlock_bh(&ip_conntrack_lock);
}
/* Confirm a connection given skb; places it in hash table */
int
__ip_conntrack_confirm(struct sk_buff **pskb)
{
unsigned int hash, repl_hash;
struct ip_conntrack *ct;
enum ip_conntrack_info ctinfo;
ct = ip_conntrack_get(*pskb, &ctinfo);
/* ipt_REJECT uses ip_conntrack_attach to attach related
ICMP/TCP RST packets in other direction. Actual packet
which created connection will be IP_CT_NEW or for an
expected connection, IP_CT_RELATED. */
if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
return NF_ACCEPT;
hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
repl_hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
/* We're not in hash table, and we refuse to set up related
connections for unconfirmed conns. But packet copies and
REJECT will give spurious warnings here. */
/* IP_NF_ASSERT(atomic_read(&ct->ct_general.use) == 1); */
/* No external references means noone else could have
confirmed us. */
IP_NF_ASSERT(!is_confirmed(ct));
DEBUGP("Confirming conntrack %p\n", ct);
write_lock_bh(&ip_conntrack_lock);
/* See if there's one in the list already, including reverse:
NAT could have grabbed it without realizing, since we're
not in the hash. If there is, we lost race. */
if (!LIST_FIND(&ip_conntrack_hash[hash],
conntrack_tuple_cmp,
struct ip_conntrack_tuple_hash *,
&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, NULL)
&& !LIST_FIND(&ip_conntrack_hash[repl_hash],
conntrack_tuple_cmp,
struct ip_conntrack_tuple_hash *,
&ct->tuplehash[IP_CT_DIR_REPLY].tuple, NULL)) {
/* Remove from unconfirmed list */
list_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].list);
__ip_conntrack_hash_insert(ct, hash, repl_hash);
/* Timer relative to confirmation time, not original
setting time, otherwise we'd get timer wrap in
weird delay cases. */
ct->timeout.expires += jiffies;
add_timer(&ct->timeout);
atomic_inc(&ct->ct_general.use);
set_bit(IPS_CONFIRMED_BIT, &ct->status);
CONNTRACK_STAT_INC(insert);
write_unlock_bh(&ip_conntrack_lock);
if (ct->helper)
ip_conntrack_event_cache(IPCT_HELPER, *pskb);
#ifdef CONFIG_IP_NF_NAT_NEEDED
if (test_bit(IPS_SRC_NAT_DONE_BIT, &ct->status) ||
test_bit(IPS_DST_NAT_DONE_BIT, &ct->status))
ip_conntrack_event_cache(IPCT_NATINFO, *pskb);
#endif
ip_conntrack_event_cache(master_ct(ct) ?
IPCT_RELATED : IPCT_NEW, *pskb);
return NF_ACCEPT;
}
CONNTRACK_STAT_INC(insert_failed);
write_unlock_bh(&ip_conntrack_lock);
return NF_DROP;
}
/* Returns true if a connection correspondings to the tuple (required
for NAT). */
int
ip_conntrack_tuple_taken(const struct ip_conntrack_tuple *tuple,
const struct ip_conntrack *ignored_conntrack)
{
struct ip_conntrack_tuple_hash *h;
read_lock_bh(&ip_conntrack_lock);
h = __ip_conntrack_find(tuple, ignored_conntrack);
read_unlock_bh(&ip_conntrack_lock);
return h != NULL;
}
/* There's a small race here where we may free a just-assured
connection. Too bad: we're in trouble anyway. */
static inline int unreplied(const struct ip_conntrack_tuple_hash *i)
{
return !(test_bit(IPS_ASSURED_BIT, &tuplehash_to_ctrack(i)->status));
}
static int early_drop(struct list_head *chain)
{
/* Traverse backwards: gives us oldest, which is roughly LRU */
struct ip_conntrack_tuple_hash *h;
struct ip_conntrack *ct = NULL;
int dropped = 0;
read_lock_bh(&ip_conntrack_lock);
h = LIST_FIND_B(chain, unreplied, struct ip_conntrack_tuple_hash *);
if (h) {
ct = tuplehash_to_ctrack(h);
atomic_inc(&ct->ct_general.use);
}
read_unlock_bh(&ip_conntrack_lock);
if (!ct)
return dropped;
if (del_timer(&ct->timeout)) {
death_by_timeout((unsigned long)ct);
dropped = 1;
CONNTRACK_STAT_INC(early_drop);
}
ip_conntrack_put(ct);
return dropped;
}
static inline int helper_cmp(const struct ip_conntrack_helper *i,
const struct ip_conntrack_tuple *rtuple)
{
return ip_ct_tuple_mask_cmp(rtuple, &i->tuple, &i->mask);
}
static struct ip_conntrack_helper *
__ip_conntrack_helper_find( const struct ip_conntrack_tuple *tuple)
{
return LIST_FIND(&helpers, helper_cmp,
struct ip_conntrack_helper *,
tuple);
}
struct ip_conntrack_helper *
ip_conntrack_helper_find_get( const struct ip_conntrack_tuple *tuple)
{
struct ip_conntrack_helper *helper;
/* need ip_conntrack_lock to assure that helper exists until
* try_module_get() is called */
read_lock_bh(&ip_conntrack_lock);
helper = __ip_conntrack_helper_find(tuple);
if (helper) {
/* need to increase module usage count to assure helper will
* not go away while the caller is e.g. busy putting a
* conntrack in the hash that uses the helper */
if (!try_module_get(helper->me))
helper = NULL;
}
read_unlock_bh(&ip_conntrack_lock);
return helper;
}
void ip_conntrack_helper_put(struct ip_conntrack_helper *helper)
{
module_put(helper->me);
}
struct ip_conntrack_protocol *
__ip_conntrack_proto_find(u_int8_t protocol)
{
return ip_ct_protos[protocol];
}
/* this is guaranteed to always return a valid protocol helper, since
* it falls back to generic_protocol */
struct ip_conntrack_protocol *
ip_conntrack_proto_find_get(u_int8_t protocol)
{
struct ip_conntrack_protocol *p;
preempt_disable();
p = __ip_conntrack_proto_find(protocol);
if (p) {
if (!try_module_get(p->me))
p = &ip_conntrack_generic_protocol;
}
preempt_enable();
return p;
}
void ip_conntrack_proto_put(struct ip_conntrack_protocol *p)
{
module_put(p->me);
}
struct ip_conntrack *ip_conntrack_alloc(struct ip_conntrack_tuple *orig,
struct ip_conntrack_tuple *repl)
{
struct ip_conntrack *conntrack;
if (!ip_conntrack_hash_rnd_initted) {
get_random_bytes(&ip_conntrack_hash_rnd, 4);
ip_conntrack_hash_rnd_initted = 1;
}
if (ip_conntrack_max
&& atomic_read(&ip_conntrack_count) >= ip_conntrack_max) {
unsigned int hash = hash_conntrack(orig);
/* Try dropping from this hash chain. */
if (!early_drop(&ip_conntrack_hash[hash])) {
if (net_ratelimit())
printk(KERN_WARNING
"ip_conntrack: table full, dropping"
" packet.\n");
return ERR_PTR(-ENOMEM);
}
}
conntrack = kmem_cache_alloc(ip_conntrack_cachep, GFP_ATOMIC);
if (!conntrack) {
DEBUGP("Can't allocate conntrack.\n");
return NULL;
}
memset(conntrack, 0, sizeof(*conntrack));
atomic_set(&conntrack->ct_general.use, 1);
conntrack->ct_general.destroy = destroy_conntrack;
conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig;
conntrack->tuplehash[IP_CT_DIR_REPLY].tuple = *repl;
/* Don't set timer yet: wait for confirmation */
init_timer(&conntrack->timeout);
conntrack->timeout.data = (unsigned long)conntrack;
conntrack->timeout.function = death_by_timeout;
atomic_inc(&ip_conntrack_count);
return conntrack;
}
void
ip_conntrack_free(struct ip_conntrack *conntrack)
{
atomic_dec(&ip_conntrack_count);
kmem_cache_free(ip_conntrack_cachep, conntrack);
}
/* Allocate a new conntrack: we return -ENOMEM if classification
* failed due to stress. Otherwise it really is unclassifiable */
static struct ip_conntrack_tuple_hash *
init_conntrack(struct ip_conntrack_tuple *tuple,
struct ip_conntrack_protocol *protocol,
struct sk_buff *skb)
{
struct ip_conntrack *conntrack;
struct ip_conntrack_tuple repl_tuple;
struct ip_conntrack_expect *exp;
if (!ip_ct_invert_tuple(&repl_tuple, tuple, protocol)) {
DEBUGP("Can't invert tuple.\n");
return NULL;
}
if (!(conntrack = ip_conntrack_alloc(tuple, &repl_tuple)))
return NULL;
if (!protocol->new(conntrack, skb)) {
ip_conntrack_free(conntrack);
return NULL;
}
write_lock_bh(&ip_conntrack_lock);
exp = find_expectation(tuple);
if (exp) {
DEBUGP("conntrack: expectation arrives ct=%p exp=%p\n",
conntrack, exp);
/* Welcome, Mr. Bond. We've been expecting you... */
__set_bit(IPS_EXPECTED_BIT, &conntrack->status);
conntrack->master = exp->master;
#ifdef CONFIG_IP_NF_CONNTRACK_MARK
conntrack->mark = exp->master->mark;
#endif
#if defined(CONFIG_IP_NF_TARGET_MASQUERADE) || \
defined(CONFIG_IP_NF_TARGET_MASQUERADE_MODULE)
/* this is ugly, but there is no other place where to put it */
conntrack->nat.masq_index = exp->master->nat.masq_index;
#endif
nf_conntrack_get(&conntrack->master->ct_general);
CONNTRACK_STAT_INC(expect_new);
} else {
conntrack->helper = __ip_conntrack_helper_find(&repl_tuple);
CONNTRACK_STAT_INC(new);
}
/* Overload tuple linked list to put us in unconfirmed list. */
list_add(&conntrack->tuplehash[IP_CT_DIR_ORIGINAL].list, &unconfirmed);
write_unlock_bh(&ip_conntrack_lock);
if (exp) {
if (exp->expectfn)
exp->expectfn(conntrack, exp);
ip_conntrack_expect_put(exp);
}
return &conntrack->tuplehash[IP_CT_DIR_ORIGINAL];
}
/* On success, returns conntrack ptr, sets skb->nfct and ctinfo */
static inline struct ip_conntrack *
resolve_normal_ct(struct sk_buff *skb,
struct ip_conntrack_protocol *proto,
int *set_reply,
unsigned int hooknum,
enum ip_conntrack_info *ctinfo)
{
struct ip_conntrack_tuple tuple;
struct ip_conntrack_tuple_hash *h;
struct ip_conntrack *ct;
IP_NF_ASSERT((skb->nh.iph->frag_off & htons(IP_OFFSET)) == 0);
if (!ip_ct_get_tuple(skb->nh.iph, skb, skb->nh.iph->ihl*4,
&tuple,proto))
return NULL;
/* look for tuple match */
h = ip_conntrack_find_get(&tuple, NULL);
if (!h) {
h = init_conntrack(&tuple, proto, skb);
if (!h)
return NULL;
if (IS_ERR(h))
return (void *)h;
}
ct = tuplehash_to_ctrack(h);
/* It exists; we have (non-exclusive) reference. */
if (DIRECTION(h) == IP_CT_DIR_REPLY) {
*ctinfo = IP_CT_ESTABLISHED + IP_CT_IS_REPLY;
/* Please set reply bit if this packet OK */
*set_reply = 1;
} else {
/* Once we've had two way comms, always ESTABLISHED. */
if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
DEBUGP("ip_conntrack_in: normal packet for %p\n",
ct);
*ctinfo = IP_CT_ESTABLISHED;
} else if (test_bit(IPS_EXPECTED_BIT, &ct->status)) {
DEBUGP("ip_conntrack_in: related packet for %p\n",
ct);
*ctinfo = IP_CT_RELATED;
} else {
DEBUGP("ip_conntrack_in: new packet for %p\n",
ct);
*ctinfo = IP_CT_NEW;
}
*set_reply = 0;
}
skb->nfct = &ct->ct_general;
skb->nfctinfo = *ctinfo;
return ct;
}
/* Netfilter hook itself. */
unsigned int ip_conntrack_in(unsigned int hooknum,
struct sk_buff **pskb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct ip_conntrack *ct;
enum ip_conntrack_info ctinfo;
struct ip_conntrack_protocol *proto;
int set_reply = 0;
int ret;
/* Previously seen (loopback or untracked)? Ignore. */
if ((*pskb)->nfct) {
CONNTRACK_STAT_INC(ignore);
return NF_ACCEPT;
}
/* Never happen */
if ((*pskb)->nh.iph->frag_off & htons(IP_OFFSET)) {
if (net_ratelimit()) {
printk(KERN_ERR "ip_conntrack_in: Frag of proto %u (hook=%u)\n",
(*pskb)->nh.iph->protocol, hooknum);
}
return NF_DROP;
}
/* Doesn't cover locally-generated broadcast, so not worth it. */
#if 0
/* Ignore broadcast: no `connection'. */
if ((*pskb)->pkt_type == PACKET_BROADCAST) {
printk("Broadcast packet!\n");
return NF_ACCEPT;
} else if (((*pskb)->nh.iph->daddr & htonl(0x000000FF))
== htonl(0x000000FF)) {
printk("Should bcast: %u.%u.%u.%u->%u.%u.%u.%u (sk=%p, ptype=%u)\n",
NIPQUAD((*pskb)->nh.iph->saddr),
NIPQUAD((*pskb)->nh.iph->daddr),
(*pskb)->sk, (*pskb)->pkt_type);
}
#endif
proto = __ip_conntrack_proto_find((*pskb)->nh.iph->protocol);
/* It may be an special packet, error, unclean...
* inverse of the return code tells to the netfilter
* core what to do with the packet. */
if (proto->error != NULL
&& (ret = proto->error(*pskb, &ctinfo, hooknum)) <= 0) {
CONNTRACK_STAT_INC(error);
CONNTRACK_STAT_INC(invalid);
return -ret;
}
if (!(ct = resolve_normal_ct(*pskb, proto,&set_reply,hooknum,&ctinfo))) {
/* Not valid part of a connection */
CONNTRACK_STAT_INC(invalid);
return NF_ACCEPT;
}
if (IS_ERR(ct)) {
/* Too stressed to deal. */
CONNTRACK_STAT_INC(drop);
return NF_DROP;
}
IP_NF_ASSERT((*pskb)->nfct);
ret = proto->packet(ct, *pskb, ctinfo);
if (ret < 0) {
/* Invalid: inverse of the return code tells
* the netfilter core what to do*/
nf_conntrack_put((*pskb)->nfct);
(*pskb)->nfct = NULL;
CONNTRACK_STAT_INC(invalid);
return -ret;
}
if (set_reply && !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status))
ip_conntrack_event_cache(IPCT_STATUS, *pskb);
return ret;
}
int invert_tuplepr(struct ip_conntrack_tuple *inverse,
const struct ip_conntrack_tuple *orig)
{
return ip_ct_invert_tuple(inverse, orig,
__ip_conntrack_proto_find(orig->dst.protonum));
}
/* Would two expected things clash? */
static inline int expect_clash(const struct ip_conntrack_expect *a,
const struct ip_conntrack_expect *b)
{
/* Part covered by intersection of masks must be unequal,
otherwise they clash */
struct ip_conntrack_tuple intersect_mask
= { { a->mask.src.ip & b->mask.src.ip,
{ a->mask.src.u.all & b->mask.src.u.all } },
{ a->mask.dst.ip & b->mask.dst.ip,
{ a->mask.dst.u.all & b->mask.dst.u.all },
a->mask.dst.protonum & b->mask.dst.protonum } };
return ip_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask);
}
static inline int expect_matches(const struct ip_conntrack_expect *a,
const struct ip_conntrack_expect *b)
{
return a->master == b->master
&& ip_ct_tuple_equal(&a->tuple, &b->tuple)
&& ip_ct_tuple_equal(&a->mask, &b->mask);
}
/* Generally a bad idea to call this: could have matched already. */
void ip_conntrack_unexpect_related(struct ip_conntrack_expect *exp)
{
struct ip_conntrack_expect *i;
write_lock_bh(&ip_conntrack_lock);
/* choose the the oldest expectation to evict */
list_for_each_entry_reverse(i, &ip_conntrack_expect_list, list) {
if (expect_matches(i, exp) && del_timer(&i->timeout)) {
unlink_expect(i);
write_unlock_bh(&ip_conntrack_lock);
ip_conntrack_expect_put(i);
return;
}
}
write_unlock_bh(&ip_conntrack_lock);
}
struct ip_conntrack_expect *ip_conntrack_expect_alloc(struct ip_conntrack *me)
{
struct ip_conntrack_expect *new;
new = kmem_cache_alloc(ip_conntrack_expect_cachep, GFP_ATOMIC);
if (!new) {
DEBUGP("expect_related: OOM allocating expect\n");
return NULL;
}
new->master = me;
atomic_inc(&new->master->ct_general.use);
atomic_set(&new->use, 1);
return new;
}
void ip_conntrack_expect_put(struct ip_conntrack_expect *exp)
{
if (atomic_dec_and_test(&exp->use)) {
ip_conntrack_put(exp->master);
kmem_cache_free(ip_conntrack_expect_cachep, exp);
}
}
static void ip_conntrack_expect_insert(struct ip_conntrack_expect *exp)
{
atomic_inc(&exp->use);
exp->master->expecting++;
list_add(&exp->list, &ip_conntrack_expect_list);
init_timer(&exp->timeout);
exp->timeout.data = (unsigned long)exp;
exp->timeout.function = expectation_timed_out;
exp->timeout.expires = jiffies + exp->master->helper->timeout * HZ;
add_timer(&exp->timeout);
exp->id = ++ip_conntrack_expect_next_id;
atomic_inc(&exp->use);
CONNTRACK_STAT_INC(expect_create);
}
/* Race with expectations being used means we could have none to find; OK. */
static void evict_oldest_expect(struct ip_conntrack *master)
{
struct ip_conntrack_expect *i;
list_for_each_entry_reverse(i, &ip_conntrack_expect_list, list) {
if (i->master == master) {
if (del_timer(&i->timeout)) {
unlink_expect(i);
ip_conntrack_expect_put(i);
}
break;
}
}
}
static inline int refresh_timer(struct ip_conntrack_expect *i)
{
if (!del_timer(&i->timeout))
return 0;
i->timeout.expires = jiffies + i->master->helper->timeout*HZ;
add_timer(&i->timeout);
return 1;
}
int ip_conntrack_expect_related(struct ip_conntrack_expect *expect)
{
struct ip_conntrack_expect *i;
int ret;
DEBUGP("ip_conntrack_expect_related %p\n", related_to);
DEBUGP("tuple: "); DUMP_TUPLE(&expect->tuple);
DEBUGP("mask: "); DUMP_TUPLE(&expect->mask);
write_lock_bh(&ip_conntrack_lock);
list_for_each_entry(i, &ip_conntrack_expect_list, list) {
if (expect_matches(i, expect)) {
/* Refresh timer: if it's dying, ignore.. */
if (refresh_timer(i)) {
ret = 0;
goto out;
}
} else if (expect_clash(i, expect)) {
ret = -EBUSY;
goto out;
}
}
/* Will be over limit? */
if (expect->master->helper->max_expected &&
expect->master->expecting >= expect->master->helper->max_expected)
evict_oldest_expect(expect->master);
ip_conntrack_expect_insert(expect);
ip_conntrack_expect_event(IPEXP_NEW, expect);
ret = 0;
out:
write_unlock_bh(&ip_conntrack_lock);
return ret;
}
/* Alter reply tuple (maybe alter helper). This is for NAT, and is
implicitly racy: see __ip_conntrack_confirm */
void ip_conntrack_alter_reply(struct ip_conntrack *conntrack,
const struct ip_conntrack_tuple *newreply)
{
write_lock_bh(&ip_conntrack_lock);
/* Should be unconfirmed, so not in hash table yet */
IP_NF_ASSERT(!is_confirmed(conntrack));
DEBUGP("Altering reply tuple of %p to ", conntrack);
DUMP_TUPLE(newreply);
conntrack->tuplehash[IP_CT_DIR_REPLY].tuple = *newreply;
if (!conntrack->master && conntrack->expecting == 0)
conntrack->helper = __ip_conntrack_helper_find(newreply);
write_unlock_bh(&ip_conntrack_lock);
}
int ip_conntrack_helper_register(struct ip_conntrack_helper *me)
{
BUG_ON(me->timeout == 0);
write_lock_bh(&ip_conntrack_lock);
list_prepend(&helpers, me);
write_unlock_bh(&ip_conntrack_lock);
return 0;
}
struct ip_conntrack_helper *
__ip_conntrack_helper_find_byname(const char *name)
{
struct ip_conntrack_helper *h;
list_for_each_entry(h, &helpers, list) {
if (!strcmp(h->name, name))
return h;
}
return NULL;
}
static inline int unhelp(struct ip_conntrack_tuple_hash *i,
const struct ip_conntrack_helper *me)
{
if (tuplehash_to_ctrack(i)->helper == me) {
ip_conntrack_event(IPCT_HELPER, tuplehash_to_ctrack(i));
tuplehash_to_ctrack(i)->helper = NULL;
}
return 0;
}
void ip_conntrack_helper_unregister(struct ip_conntrack_helper *me)
{
unsigned int i;
struct ip_conntrack_expect *exp, *tmp;
/* Need write lock here, to delete helper. */
write_lock_bh(&ip_conntrack_lock);
LIST_DELETE(&helpers, me);
/* Get rid of expectations */
list_for_each_entry_safe(exp, tmp, &ip_conntrack_expect_list, list) {
if (exp->master->helper == me && del_timer(&exp->timeout)) {
unlink_expect(exp);
ip_conntrack_expect_put(exp);
}
}
/* Get rid of expecteds, set helpers to NULL. */
LIST_FIND_W(&unconfirmed, unhelp, struct ip_conntrack_tuple_hash*, me);
for (i = 0; i < ip_conntrack_htable_size; i++)
LIST_FIND_W(&ip_conntrack_hash[i], unhelp,
struct ip_conntrack_tuple_hash *, me);
write_unlock_bh(&ip_conntrack_lock);
/* Someone could be still looking at the helper in a bh. */
synchronize_net();
}
static inline void ct_add_counters(struct ip_conntrack *ct,
enum ip_conntrack_info ctinfo,
const struct sk_buff *skb)
{
#ifdef CONFIG_IP_NF_CT_ACCT
if (skb) {
ct->counters[CTINFO2DIR(ctinfo)].packets++;
ct->counters[CTINFO2DIR(ctinfo)].bytes +=
ntohs(skb->nh.iph->tot_len);
}
#endif
}
/* Refresh conntrack for this many jiffies and do accounting (if skb != NULL) */
void ip_ct_refresh_acct(struct ip_conntrack *ct,
enum ip_conntrack_info ctinfo,
const struct sk_buff *skb,
unsigned long extra_jiffies)
{
IP_NF_ASSERT(ct->timeout.data == (unsigned long)ct);
/* If not in hash table, timer will not be active yet */
if (!is_confirmed(ct)) {
ct->timeout.expires = extra_jiffies;
ct_add_counters(ct, ctinfo, skb);
} else {
write_lock_bh(&ip_conntrack_lock);
/* Need del_timer for race avoidance (may already be dying). */
if (del_timer(&ct->timeout)) {
ct->timeout.expires = jiffies + extra_jiffies;
add_timer(&ct->timeout);
ip_conntrack_event_cache(IPCT_REFRESH, skb);
}
ct_add_counters(ct, ctinfo, skb);
write_unlock_bh(&ip_conntrack_lock);
}
}
#if defined(CONFIG_IP_NF_CONNTRACK_NETLINK) || \
defined(CONFIG_IP_NF_CONNTRACK_NETLINK_MODULE)
/* Generic function for tcp/udp/sctp/dccp and alike. This needs to be
* in ip_conntrack_core, since we don't want the protocols to autoload
* or depend on ctnetlink */
int ip_ct_port_tuple_to_nfattr(struct sk_buff *skb,
const struct ip_conntrack_tuple *tuple)
{
NFA_PUT(skb, CTA_PROTO_SRC_PORT, sizeof(u_int16_t),
&tuple->src.u.tcp.port);
NFA_PUT(skb, CTA_PROTO_DST_PORT, sizeof(u_int16_t),
&tuple->dst.u.tcp.port);
return 0;
nfattr_failure:
return -1;
}
int ip_ct_port_nfattr_to_tuple(struct nfattr *tb[],
struct ip_conntrack_tuple *t)
{
if (!tb[CTA_PROTO_SRC_PORT-1] || !tb[CTA_PROTO_DST_PORT-1])
return -EINVAL;
t->src.u.tcp.port =
*(u_int16_t *)NFA_DATA(tb[CTA_PROTO_SRC_PORT-1]);
t->dst.u.tcp.port =
*(u_int16_t *)NFA_DATA(tb[CTA_PROTO_DST_PORT-1]);
return 0;
}
#endif
/* Returns new sk_buff, or NULL */
struct sk_buff *
ip_ct_gather_frags(struct sk_buff *skb, u_int32_t user)
{
skb_orphan(skb);
local_bh_disable();
skb = ip_defrag(skb, user);
local_bh_enable();
if (skb)
ip_send_check(skb->nh.iph);
return skb;
}
/* Used by ipt_REJECT. */
static void ip_conntrack_attach(struct sk_buff *nskb, struct sk_buff *skb)
{
struct ip_conntrack *ct;
enum ip_conntrack_info ctinfo;
/* This ICMP is in reverse direction to the packet which caused it */
ct = ip_conntrack_get(skb, &ctinfo);
if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL)
ctinfo = IP_CT_RELATED + IP_CT_IS_REPLY;
else
ctinfo = IP_CT_RELATED;
/* Attach to new skbuff, and increment count */
nskb->nfct = &ct->ct_general;
nskb->nfctinfo = ctinfo;
nf_conntrack_get(nskb->nfct);
}
static inline int
do_iter(const struct ip_conntrack_tuple_hash *i,
int (*iter)(struct ip_conntrack *i, void *data),
void *data)
{
return iter(tuplehash_to_ctrack(i), data);
}
/* Bring out ya dead! */
static struct ip_conntrack_tuple_hash *
get_next_corpse(int (*iter)(struct ip_conntrack *i, void *data),
void *data, unsigned int *bucket)
{
struct ip_conntrack_tuple_hash *h = NULL;
write_lock_bh(&ip_conntrack_lock);
for (; *bucket < ip_conntrack_htable_size; (*bucket)++) {
h = LIST_FIND_W(&ip_conntrack_hash[*bucket], do_iter,
struct ip_conntrack_tuple_hash *, iter, data);
if (h)
break;
}
if (!h)
h = LIST_FIND_W(&unconfirmed, do_iter,
struct ip_conntrack_tuple_hash *, iter, data);
if (h)
atomic_inc(&tuplehash_to_ctrack(h)->ct_general.use);
write_unlock_bh(&ip_conntrack_lock);
return h;
}
void
ip_ct_iterate_cleanup(int (*iter)(struct ip_conntrack *i, void *), void *data)
{
struct ip_conntrack_tuple_hash *h;
unsigned int bucket = 0;
while ((h = get_next_corpse(iter, data, &bucket)) != NULL) {
struct ip_conntrack *ct = tuplehash_to_ctrack(h);
/* Time to push up daises... */
if (del_timer(&ct->timeout))
death_by_timeout((unsigned long)ct);
/* ... else the timer will get him soon. */
ip_conntrack_put(ct);
}
}
/* Fast function for those who don't want to parse /proc (and I don't
blame them). */
/* Reversing the socket's dst/src point of view gives us the reply
mapping. */
static int
getorigdst(struct sock *sk, int optval, void __user *user, int *len)
{
struct inet_sock *inet = inet_sk(sk);
struct ip_conntrack_tuple_hash *h;
struct ip_conntrack_tuple tuple;
IP_CT_TUPLE_U_BLANK(&tuple);
tuple.src.ip = inet->rcv_saddr;
tuple.src.u.tcp.port = inet->sport;
tuple.dst.ip = inet->daddr;
tuple.dst.u.tcp.port = inet->dport;
tuple.dst.protonum = IPPROTO_TCP;
/* We only do TCP at the moment: is there a better way? */
if (strcmp(sk->sk_prot->name, "TCP")) {
DEBUGP("SO_ORIGINAL_DST: Not a TCP socket\n");
return -ENOPROTOOPT;
}
if ((unsigned int) *len < sizeof(struct sockaddr_in)) {
DEBUGP("SO_ORIGINAL_DST: len %u not %u\n",
*len, sizeof(struct sockaddr_in));
return -EINVAL;
}
h = ip_conntrack_find_get(&tuple, NULL);
if (h) {
struct sockaddr_in sin;
struct ip_conntrack *ct = tuplehash_to_ctrack(h);
sin.sin_family = AF_INET;
sin.sin_port = ct->tuplehash[IP_CT_DIR_ORIGINAL]
.tuple.dst.u.tcp.port;
sin.sin_addr.s_addr = ct->tuplehash[IP_CT_DIR_ORIGINAL]
.tuple.dst.ip;
DEBUGP("SO_ORIGINAL_DST: %u.%u.%u.%u %u\n",
NIPQUAD(sin.sin_addr.s_addr), ntohs(sin.sin_port));
ip_conntrack_put(ct);
if (copy_to_user(user, &sin, sizeof(sin)) != 0)
return -EFAULT;
else
return 0;
}
DEBUGP("SO_ORIGINAL_DST: Can't find %u.%u.%u.%u/%u-%u.%u.%u.%u/%u.\n",
NIPQUAD(tuple.src.ip), ntohs(tuple.src.u.tcp.port),
NIPQUAD(tuple.dst.ip), ntohs(tuple.dst.u.tcp.port));
return -ENOENT;
}
static struct nf_sockopt_ops so_getorigdst = {
.pf = PF_INET,
.get_optmin = SO_ORIGINAL_DST,
.get_optmax = SO_ORIGINAL_DST+1,
.get = &getorigdst,
};
static int kill_all(struct ip_conntrack *i, void *data)
{
return 1;
}
static void free_conntrack_hash(void)
{
if (ip_conntrack_vmalloc)
vfree(ip_conntrack_hash);
else
free_pages((unsigned long)ip_conntrack_hash,
get_order(sizeof(struct list_head)
* ip_conntrack_htable_size));
}
void ip_conntrack_flush()
{
/* This makes sure all current packets have passed through
netfilter framework. Roll on, two-stage module
delete... */
synchronize_net();
ip_ct_event_cache_flush();
i_see_dead_people:
ip_ct_iterate_cleanup(kill_all, NULL);
if (atomic_read(&ip_conntrack_count) != 0) {
schedule();
goto i_see_dead_people;
}
/* wait until all references to ip_conntrack_untracked are dropped */
while (atomic_read(&ip_conntrack_untracked.ct_general.use) > 1)
schedule();
}
/* Mishearing the voices in his head, our hero wonders how he's
supposed to kill the mall. */
void ip_conntrack_cleanup(void)
{
ip_ct_attach = NULL;
ip_conntrack_flush();
kmem_cache_destroy(ip_conntrack_cachep);
kmem_cache_destroy(ip_conntrack_expect_cachep);
free_conntrack_hash();
nf_unregister_sockopt(&so_getorigdst);
}
static int hashsize;
module_param(hashsize, int, 0400);
int __init ip_conntrack_init(void)
{
unsigned int i;
int ret;
/* Idea from tcp.c: use 1/16384 of memory. On i386: 32MB
* machine has 256 buckets. >= 1GB machines have 8192 buckets. */
if (hashsize) {
ip_conntrack_htable_size = hashsize;
} else {
ip_conntrack_htable_size
= (((num_physpages << PAGE_SHIFT) / 16384)
/ sizeof(struct list_head));
if (num_physpages > (1024 * 1024 * 1024 / PAGE_SIZE))
ip_conntrack_htable_size = 8192;
if (ip_conntrack_htable_size < 16)
ip_conntrack_htable_size = 16;
}
ip_conntrack_max = 8 * ip_conntrack_htable_size;
printk("ip_conntrack version %s (%u buckets, %d max)"
" - %Zd bytes per conntrack\n", IP_CONNTRACK_VERSION,
ip_conntrack_htable_size, ip_conntrack_max,
sizeof(struct ip_conntrack));
ret = nf_register_sockopt(&so_getorigdst);
if (ret != 0) {
printk(KERN_ERR "Unable to register netfilter socket option\n");
return ret;
}
/* AK: the hash table is twice as big than needed because it
uses list_head. it would be much nicer to caches to use a
single pointer list head here. */
ip_conntrack_vmalloc = 0;
ip_conntrack_hash
=(void*)__get_free_pages(GFP_KERNEL,
get_order(sizeof(struct list_head)
*ip_conntrack_htable_size));
if (!ip_conntrack_hash) {
ip_conntrack_vmalloc = 1;
printk(KERN_WARNING "ip_conntrack: falling back to vmalloc.\n");
ip_conntrack_hash = vmalloc(sizeof(struct list_head)
* ip_conntrack_htable_size);
}
if (!ip_conntrack_hash) {
printk(KERN_ERR "Unable to create ip_conntrack_hash\n");
goto err_unreg_sockopt;
}
ip_conntrack_cachep = kmem_cache_create("ip_conntrack",
sizeof(struct ip_conntrack), 0,
0, NULL, NULL);
if (!ip_conntrack_cachep) {
printk(KERN_ERR "Unable to create ip_conntrack slab cache\n");
goto err_free_hash;
}
ip_conntrack_expect_cachep = kmem_cache_create("ip_conntrack_expect",
sizeof(struct ip_conntrack_expect),
0, 0, NULL, NULL);
if (!ip_conntrack_expect_cachep) {
printk(KERN_ERR "Unable to create ip_expect slab cache\n");
goto err_free_conntrack_slab;
}
/* Don't NEED lock here, but good form anyway. */
write_lock_bh(&ip_conntrack_lock);
for (i = 0; i < MAX_IP_CT_PROTO; i++)
ip_ct_protos[i] = &ip_conntrack_generic_protocol;
/* Sew in builtin protocols. */
ip_ct_protos[IPPROTO_TCP] = &ip_conntrack_protocol_tcp;
ip_ct_protos[IPPROTO_UDP] = &ip_conntrack_protocol_udp;
ip_ct_protos[IPPROTO_ICMP] = &ip_conntrack_protocol_icmp;
write_unlock_bh(&ip_conntrack_lock);
for (i = 0; i < ip_conntrack_htable_size; i++)
INIT_LIST_HEAD(&ip_conntrack_hash[i]);
/* For use by ipt_REJECT */
ip_ct_attach = ip_conntrack_attach;
/* Set up fake conntrack:
- to never be deleted, not in any hashes */
atomic_set(&ip_conntrack_untracked.ct_general.use, 1);
/* - and look it like as a confirmed connection */
set_bit(IPS_CONFIRMED_BIT, &ip_conntrack_untracked.status);
return ret;
err_free_conntrack_slab:
kmem_cache_destroy(ip_conntrack_cachep);
err_free_hash:
free_conntrack_hash();
err_unreg_sockopt:
nf_unregister_sockopt(&so_getorigdst);
return -ENOMEM;
}
|