summaryrefslogtreecommitdiffstats
path: root/net/netfilter/x_tables.c
blob: 55802e97f906d1987ed78b4296584deb38e5f876 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
/*
 * x_tables core - Backend for {ip,ip6,arp}_tables
 *
 * Copyright (C) 2006-2006 Harald Welte <laforge@netfilter.org>
 * Copyright (C) 2006-2012 Patrick McHardy <kaber@trash.net>
 *
 * Based on existing ip_tables code which is
 *   Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling
 *   Copyright (C) 2000-2005 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.
 *
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/socket.h>
#include <linux/net.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/string.h>
#include <linux/vmalloc.h>
#include <linux/mutex.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/audit.h>
#include <linux/user_namespace.h>
#include <net/net_namespace.h>

#include <linux/netfilter/x_tables.h>
#include <linux/netfilter_arp.h>
#include <linux/netfilter_ipv4/ip_tables.h>
#include <linux/netfilter_ipv6/ip6_tables.h>
#include <linux/netfilter_arp/arp_tables.h>

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>");
MODULE_DESCRIPTION("{ip,ip6,arp,eb}_tables backend module");

#define SMP_ALIGN(x) (((x) + SMP_CACHE_BYTES-1) & ~(SMP_CACHE_BYTES-1))
#define XT_PCPU_BLOCK_SIZE 4096

struct compat_delta {
	unsigned int offset; /* offset in kernel */
	int delta; /* delta in 32bit user land */
};

struct xt_af {
	struct mutex mutex;
	struct list_head match;
	struct list_head target;
#ifdef CONFIG_COMPAT
	struct mutex compat_mutex;
	struct compat_delta *compat_tab;
	unsigned int number; /* number of slots in compat_tab[] */
	unsigned int cur; /* number of used slots in compat_tab[] */
#endif
};

static struct xt_af *xt;

static const char *const xt_prefix[NFPROTO_NUMPROTO] = {
	[NFPROTO_UNSPEC] = "x",
	[NFPROTO_IPV4]   = "ip",
	[NFPROTO_ARP]    = "arp",
	[NFPROTO_BRIDGE] = "eb",
	[NFPROTO_IPV6]   = "ip6",
};

/* Registration hooks for targets. */
int xt_register_target(struct xt_target *target)
{
	u_int8_t af = target->family;

	mutex_lock(&xt[af].mutex);
	list_add(&target->list, &xt[af].target);
	mutex_unlock(&xt[af].mutex);
	return 0;
}
EXPORT_SYMBOL(xt_register_target);

void
xt_unregister_target(struct xt_target *target)
{
	u_int8_t af = target->family;

	mutex_lock(&xt[af].mutex);
	list_del(&target->list);
	mutex_unlock(&xt[af].mutex);
}
EXPORT_SYMBOL(xt_unregister_target);

int
xt_register_targets(struct xt_target *target, unsigned int n)
{
	unsigned int i;
	int err = 0;

	for (i = 0; i < n; i++) {
		err = xt_register_target(&target[i]);
		if (err)
			goto err;
	}
	return err;

err:
	if (i > 0)
		xt_unregister_targets(target, i);
	return err;
}
EXPORT_SYMBOL(xt_register_targets);

void
xt_unregister_targets(struct xt_target *target, unsigned int n)
{
	while (n-- > 0)
		xt_unregister_target(&target[n]);
}
EXPORT_SYMBOL(xt_unregister_targets);

int xt_register_match(struct xt_match *match)
{
	u_int8_t af = match->family;

	mutex_lock(&xt[af].mutex);
	list_add(&match->list, &xt[af].match);
	mutex_unlock(&xt[af].mutex);
	return 0;
}
EXPORT_SYMBOL(xt_register_match);

void
xt_unregister_match(struct xt_match *match)
{
	u_int8_t af = match->family;

	mutex_lock(&xt[af].mutex);
	list_del(&match->list);
	mutex_unlock(&xt[af].mutex);
}
EXPORT_SYMBOL(xt_unregister_match);

int
xt_register_matches(struct xt_match *match, unsigned int n)
{
	unsigned int i;
	int err = 0;

	for (i = 0; i < n; i++) {
		err = xt_register_match(&match[i]);
		if (err)
			goto err;
	}
	return err;

err:
	if (i > 0)
		xt_unregister_matches(match, i);
	return err;
}
EXPORT_SYMBOL(xt_register_matches);

void
xt_unregister_matches(struct xt_match *match, unsigned int n)
{
	while (n-- > 0)
		xt_unregister_match(&match[n]);
}
EXPORT_SYMBOL(xt_unregister_matches);


/*
 * These are weird, but module loading must not be done with mutex
 * held (since they will register), and we have to have a single
 * function to use.
 */

/* Find match, grabs ref.  Returns ERR_PTR() on error. */
struct xt_match *xt_find_match(u8 af, const char *name, u8 revision)
{
	struct xt_match *m;
	int err = -ENOENT;

	mutex_lock(&xt[af].mutex);
	list_for_each_entry(m, &xt[af].match, list) {
		if (strcmp(m->name, name) == 0) {
			if (m->revision == revision) {
				if (try_module_get(m->me)) {
					mutex_unlock(&xt[af].mutex);
					return m;
				}
			} else
				err = -EPROTOTYPE; /* Found something. */
		}
	}
	mutex_unlock(&xt[af].mutex);

	if (af != NFPROTO_UNSPEC)
		/* Try searching again in the family-independent list */
		return xt_find_match(NFPROTO_UNSPEC, name, revision);

	return ERR_PTR(err);
}
EXPORT_SYMBOL(xt_find_match);

struct xt_match *
xt_request_find_match(uint8_t nfproto, const char *name, uint8_t revision)
{
	struct xt_match *match;

	match = xt_find_match(nfproto, name, revision);
	if (IS_ERR(match)) {
		request_module("%st_%s", xt_prefix[nfproto], name);
		match = xt_find_match(nfproto, name, revision);
	}

	return match;
}
EXPORT_SYMBOL_GPL(xt_request_find_match);

/* Find target, grabs ref.  Returns ERR_PTR() on error. */
struct xt_target *xt_find_target(u8 af, const char *name, u8 revision)
{
	struct xt_target *t;
	int err = -ENOENT;

	mutex_lock(&xt[af].mutex);
	list_for_each_entry(t, &xt[af].target, list) {
		if (strcmp(t->name, name) == 0) {
			if (t->revision == revision) {
				if (try_module_get(t->me)) {
					mutex_unlock(&xt[af].mutex);
					return t;
				}
			} else
				err = -EPROTOTYPE; /* Found something. */
		}
	}
	mutex_unlock(&xt[af].mutex);

	if (af != NFPROTO_UNSPEC)
		/* Try searching again in the family-independent list */
		return xt_find_target(NFPROTO_UNSPEC, name, revision);

	return ERR_PTR(err);
}
EXPORT_SYMBOL(xt_find_target);

struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision)
{
	struct xt_target *target;

	target = xt_find_target(af, name, revision);
	if (IS_ERR(target)) {
		request_module("%st_%s", xt_prefix[af], name);
		target = xt_find_target(af, name, revision);
	}

	return target;
}
EXPORT_SYMBOL_GPL(xt_request_find_target);


static int xt_obj_to_user(u16 __user *psize, u16 size,
			  void __user *pname, const char *name,
			  u8 __user *prev, u8 rev)
{
	if (put_user(size, psize))
		return -EFAULT;
	if (copy_to_user(pname, name, strlen(name) + 1))
		return -EFAULT;
	if (put_user(rev, prev))
		return -EFAULT;

	return 0;
}

#define XT_OBJ_TO_USER(U, K, TYPE, C_SIZE)				\
	xt_obj_to_user(&U->u.TYPE##_size, C_SIZE ? : K->u.TYPE##_size,	\
		       U->u.user.name, K->u.kernel.TYPE->name,		\
		       &U->u.user.revision, K->u.kernel.TYPE->revision)

int xt_data_to_user(void __user *dst, const void *src,
		    int usersize, int size, int aligned_size)
{
	usersize = usersize ? : size;
	if (copy_to_user(dst, src, usersize))
		return -EFAULT;
	if (usersize != aligned_size &&
	    clear_user(dst + usersize, aligned_size - usersize))
		return -EFAULT;

	return 0;
}
EXPORT_SYMBOL_GPL(xt_data_to_user);

#define XT_DATA_TO_USER(U, K, TYPE)					\
	xt_data_to_user(U->data, K->data,				\
			K->u.kernel.TYPE->usersize,			\
			K->u.kernel.TYPE->TYPE##size,			\
			XT_ALIGN(K->u.kernel.TYPE->TYPE##size))

int xt_match_to_user(const struct xt_entry_match *m,
		     struct xt_entry_match __user *u)
{
	return XT_OBJ_TO_USER(u, m, match, 0) ||
	       XT_DATA_TO_USER(u, m, match);
}
EXPORT_SYMBOL_GPL(xt_match_to_user);

int xt_target_to_user(const struct xt_entry_target *t,
		      struct xt_entry_target __user *u)
{
	return XT_OBJ_TO_USER(u, t, target, 0) ||
	       XT_DATA_TO_USER(u, t, target);
}
EXPORT_SYMBOL_GPL(xt_target_to_user);

static int match_revfn(u8 af, const char *name, u8 revision, int *bestp)
{
	const struct xt_match *m;
	int have_rev = 0;

	list_for_each_entry(m, &xt[af].match, list) {
		if (strcmp(m->name, name) == 0) {
			if (m->revision > *bestp)
				*bestp = m->revision;
			if (m->revision == revision)
				have_rev = 1;
		}
	}

	if (af != NFPROTO_UNSPEC && !have_rev)
		return match_revfn(NFPROTO_UNSPEC, name, revision, bestp);

	return have_rev;
}

static int target_revfn(u8 af, const char *name, u8 revision, int *bestp)
{
	const struct xt_target *t;
	int have_rev = 0;

	list_for_each_entry(t, &xt[af].target, list) {
		if (strcmp(t->name, name) == 0) {
			if (t->revision > *bestp)
				*bestp = t->revision;
			if (t->revision == revision)
				have_rev = 1;
		}
	}

	if (af != NFPROTO_UNSPEC && !have_rev)
		return target_revfn(NFPROTO_UNSPEC, name, revision, bestp);

	return have_rev;
}

/* Returns true or false (if no such extension at all) */
int xt_find_revision(u8 af, const char *name, u8 revision, int target,
		     int *err)
{
	int have_rev, best = -1;

	mutex_lock(&xt[af].mutex);
	if (target == 1)
		have_rev = target_revfn(af, name, revision, &best);
	else
		have_rev = match_revfn(af, name, revision, &best);
	mutex_unlock(&xt[af].mutex);

	/* Nothing at all?  Return 0 to try loading module. */
	if (best == -1) {
		*err = -ENOENT;
		return 0;
	}

	*err = best;
	if (!have_rev)
		*err = -EPROTONOSUPPORT;
	return 1;
}
EXPORT_SYMBOL_GPL(xt_find_revision);

static char *
textify_hooks(char *buf, size_t size, unsigned int mask, uint8_t nfproto)
{
	static const char *const inetbr_names[] = {
		"PREROUTING", "INPUT", "FORWARD",
		"OUTPUT", "POSTROUTING", "BROUTING",
	};
	static const char *const arp_names[] = {
		"INPUT", "FORWARD", "OUTPUT",
	};
	const char *const *names;
	unsigned int i, max;
	char *p = buf;
	bool np = false;
	int res;

	names = (nfproto == NFPROTO_ARP) ? arp_names : inetbr_names;
	max   = (nfproto == NFPROTO_ARP) ? ARRAY_SIZE(arp_names) :
	                                   ARRAY_SIZE(inetbr_names);
	*p = '\0';
	for (i = 0; i < max; ++i) {
		if (!(mask & (1 << i)))
			continue;
		res = snprintf(p, size, "%s%s", np ? "/" : "", names[i]);
		if (res > 0) {
			size -= res;
			p += res;
		}
		np = true;
	}

	return buf;
}

int xt_check_match(struct xt_mtchk_param *par,
		   unsigned int size, u_int8_t proto, bool inv_proto)
{
	int ret;

	if (XT_ALIGN(par->match->matchsize) != size &&
	    par->match->matchsize != -1) {
		/*
		 * ebt_among is exempt from centralized matchsize checking
		 * because it uses a dynamic-size data set.
		 */
		pr_err("%s_tables: %s.%u match: invalid size "
		       "%u (kernel) != (user) %u\n",
		       xt_prefix[par->family], par->match->name,
		       par->match->revision,
		       XT_ALIGN(par->match->matchsize), size);
		return -EINVAL;
	}
	if (par->match->table != NULL &&
	    strcmp(par->match->table, par->table) != 0) {
		pr_err("%s_tables: %s match: only valid in %s table, not %s\n",
		       xt_prefix[par->family], par->match->name,
		       par->match->table, par->table);
		return -EINVAL;
	}
	if (par->match->hooks && (par->hook_mask & ~par->match->hooks) != 0) {
		char used[64], allow[64];

		pr_err("%s_tables: %s match: used from hooks %s, but only "
		       "valid from %s\n",
		       xt_prefix[par->family], par->match->name,
		       textify_hooks(used, sizeof(used), par->hook_mask,
		                     par->family),
		       textify_hooks(allow, sizeof(allow), par->match->hooks,
		                     par->family));
		return -EINVAL;
	}
	if (par->match->proto && (par->match->proto != proto || inv_proto)) {
		pr_err("%s_tables: %s match: only valid for protocol %u\n",
		       xt_prefix[par->family], par->match->name,
		       par->match->proto);
		return -EINVAL;
	}
	if (par->match->checkentry != NULL) {
		ret = par->match->checkentry(par);
		if (ret < 0)
			return ret;
		else if (ret > 0)
			/* Flag up potential errors. */
			return -EIO;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(xt_check_match);

/** xt_check_entry_match - check that matches end before start of target
 *
 * @match: beginning of xt_entry_match
 * @target: beginning of this rules target (alleged end of matches)
 * @alignment: alignment requirement of match structures
 *
 * Validates that all matches add up to the beginning of the target,
 * and that each match covers at least the base structure size.
 *
 * Return: 0 on success, negative errno on failure.
 */
static int xt_check_entry_match(const char *match, const char *target,
				const size_t alignment)
{
	const struct xt_entry_match *pos;
	int length = target - match;

	if (length == 0) /* no matches */
		return 0;

	pos = (struct xt_entry_match *)match;
	do {
		if ((unsigned long)pos % alignment)
			return -EINVAL;

		if (length < (int)sizeof(struct xt_entry_match))
			return -EINVAL;

		if (pos->u.match_size < sizeof(struct xt_entry_match))
			return -EINVAL;

		if (pos->u.match_size > length)
			return -EINVAL;

		length -= pos->u.match_size;
		pos = ((void *)((char *)(pos) + (pos)->u.match_size));
	} while (length > 0);

	return 0;
}

#ifdef CONFIG_COMPAT
int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta)
{
	struct xt_af *xp = &xt[af];

	if (!xp->compat_tab) {
		if (!xp->number)
			return -EINVAL;
		xp->compat_tab = vmalloc(sizeof(struct compat_delta) * xp->number);
		if (!xp->compat_tab)
			return -ENOMEM;
		xp->cur = 0;
	}

	if (xp->cur >= xp->number)
		return -EINVAL;

	if (xp->cur)
		delta += xp->compat_tab[xp->cur - 1].delta;
	xp->compat_tab[xp->cur].offset = offset;
	xp->compat_tab[xp->cur].delta = delta;
	xp->cur++;
	return 0;
}
EXPORT_SYMBOL_GPL(xt_compat_add_offset);

void xt_compat_flush_offsets(u_int8_t af)
{
	if (xt[af].compat_tab) {
		vfree(xt[af].compat_tab);
		xt[af].compat_tab = NULL;
		xt[af].number = 0;
		xt[af].cur = 0;
	}
}
EXPORT_SYMBOL_GPL(xt_compat_flush_offsets);

int xt_compat_calc_jump(u_int8_t af, unsigned int offset)
{
	struct compat_delta *tmp = xt[af].compat_tab;
	int mid, left = 0, right = xt[af].cur - 1;

	while (left <= right) {
		mid = (left + right) >> 1;
		if (offset > tmp[mid].offset)
			left = mid + 1;
		else if (offset < tmp[mid].offset)
			right = mid - 1;
		else
			return mid ? tmp[mid - 1].delta : 0;
	}
	return left ? tmp[left - 1].delta : 0;
}
EXPORT_SYMBOL_GPL(xt_compat_calc_jump);

void xt_compat_init_offsets(u_int8_t af, unsigned int number)
{
	xt[af].number = number;
	xt[af].cur = 0;
}
EXPORT_SYMBOL(xt_compat_init_offsets);

int xt_compat_match_offset(const struct xt_match *match)
{
	u_int16_t csize = match->compatsize ? : match->matchsize;
	return XT_ALIGN(match->matchsize) - COMPAT_XT_ALIGN(csize);
}
EXPORT_SYMBOL_GPL(xt_compat_match_offset);

void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
			       unsigned int *size)
{
	const struct xt_match *match = m->u.kernel.match;
	struct compat_xt_entry_match *cm = (struct compat_xt_entry_match *)m;
	int pad, off = xt_compat_match_offset(match);
	u_int16_t msize = cm->u.user.match_size;
	char name[sizeof(m->u.user.name)];

	m = *dstptr;
	memcpy(m, cm, sizeof(*cm));
	if (match->compat_from_user)
		match->compat_from_user(m->data, cm->data);
	else
		memcpy(m->data, cm->data, msize - sizeof(*cm));
	pad = XT_ALIGN(match->matchsize) - match->matchsize;
	if (pad > 0)
		memset(m->data + match->matchsize, 0, pad);

	msize += off;
	m->u.user.match_size = msize;
	strlcpy(name, match->name, sizeof(name));
	module_put(match->me);
	strncpy(m->u.user.name, name, sizeof(m->u.user.name));

	*size += off;
	*dstptr += msize;
}
EXPORT_SYMBOL_GPL(xt_compat_match_from_user);

#define COMPAT_XT_DATA_TO_USER(U, K, TYPE, C_SIZE)			\
	xt_data_to_user(U->data, K->data,				\
			K->u.kernel.TYPE->usersize,			\
			C_SIZE,						\
			COMPAT_XT_ALIGN(C_SIZE))

int xt_compat_match_to_user(const struct xt_entry_match *m,
			    void __user **dstptr, unsigned int *size)
{
	const struct xt_match *match = m->u.kernel.match;
	struct compat_xt_entry_match __user *cm = *dstptr;
	int off = xt_compat_match_offset(match);
	u_int16_t msize = m->u.user.match_size - off;

	if (XT_OBJ_TO_USER(cm, m, match, msize))
		return -EFAULT;

	if (match->compat_to_user) {
		if (match->compat_to_user((void __user *)cm->data, m->data))
			return -EFAULT;
	} else {
		if (COMPAT_XT_DATA_TO_USER(cm, m, match, msize - sizeof(*cm)))
			return -EFAULT;
	}

	*size -= off;
	*dstptr += msize;
	return 0;
}
EXPORT_SYMBOL_GPL(xt_compat_match_to_user);

/* non-compat version may have padding after verdict */
struct compat_xt_standard_target {
	struct compat_xt_entry_target t;
	compat_uint_t verdict;
};

int xt_compat_check_entry_offsets(const void *base, const char *elems,
				  unsigned int target_offset,
				  unsigned int next_offset)
{
	long size_of_base_struct = elems - (const char *)base;
	const struct compat_xt_entry_target *t;
	const char *e = base;

	if (target_offset < size_of_base_struct)
		return -EINVAL;

	if (target_offset + sizeof(*t) > next_offset)
		return -EINVAL;

	t = (void *)(e + target_offset);
	if (t->u.target_size < sizeof(*t))
		return -EINVAL;

	if (target_offset + t->u.target_size > next_offset)
		return -EINVAL;

	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 &&
	    COMPAT_XT_ALIGN(target_offset + sizeof(struct compat_xt_standard_target)) != next_offset)
		return -EINVAL;

	/* compat_xt_entry match has less strict alignment requirements,
	 * otherwise they are identical.  In case of padding differences
	 * we need to add compat version of xt_check_entry_match.
	 */
	BUILD_BUG_ON(sizeof(struct compat_xt_entry_match) != sizeof(struct xt_entry_match));

	return xt_check_entry_match(elems, base + target_offset,
				    __alignof__(struct compat_xt_entry_match));
}
EXPORT_SYMBOL(xt_compat_check_entry_offsets);
#endif /* CONFIG_COMPAT */

/**
 * xt_check_entry_offsets - validate arp/ip/ip6t_entry
 *
 * @base: pointer to arp/ip/ip6t_entry
 * @elems: pointer to first xt_entry_match, i.e. ip(6)t_entry->elems
 * @target_offset: the arp/ip/ip6_t->target_offset
 * @next_offset: the arp/ip/ip6_t->next_offset
 *
 * validates that target_offset and next_offset are sane and that all
 * match sizes (if any) align with the target offset.
 *
 * This function does not validate the targets or matches themselves, it
 * only tests that all the offsets and sizes are correct, that all
 * match structures are aligned, and that the last structure ends where
 * the target structure begins.
 *
 * Also see xt_compat_check_entry_offsets for CONFIG_COMPAT version.
 *
 * The arp/ip/ip6t_entry structure @base must have passed following tests:
 * - it must point to a valid memory location
 * - base to base + next_offset must be accessible, i.e. not exceed allocated
 *   length.
 *
 * A well-formed entry looks like this:
 *
 * ip(6)t_entry   match [mtdata]  match [mtdata] target [tgdata] ip(6)t_entry
 * e->elems[]-----'                              |               |
 *                matchsize                      |               |
 *                                matchsize      |               |
 *                                               |               |
 * target_offset---------------------------------'               |
 * next_offset---------------------------------------------------'
 *
 * elems[]: flexible array member at end of ip(6)/arpt_entry struct.
 *          This is where matches (if any) and the target reside.
 * target_offset: beginning of target.
 * next_offset: start of the next rule; also: size of this rule.
 * Since targets have a minimum size, target_offset + minlen <= next_offset.
 *
 * Every match stores its size, sum of sizes must not exceed target_offset.
 *
 * Return: 0 on success, negative errno on failure.
 */
int xt_check_entry_offsets(const void *base,
			   const char *elems,
			   unsigned int target_offset,
			   unsigned int next_offset)
{
	long size_of_base_struct = elems - (const char *)base;
	const struct xt_entry_target *t;
	const char *e = base;

	/* target start is within the ip/ip6/arpt_entry struct */
	if (target_offset < size_of_base_struct)
		return -EINVAL;

	if (target_offset + sizeof(*t) > next_offset)
		return -EINVAL;

	t = (void *)(e + target_offset);
	if (t->u.target_size < sizeof(*t))
		return -EINVAL;

	if (target_offset + t->u.target_size > next_offset)
		return -EINVAL;

	if (strcmp(t->u.user.name, XT_STANDARD_TARGET) == 0 &&
	    XT_ALIGN(target_offset + sizeof(struct xt_standard_target)) != next_offset)
		return -EINVAL;

	return xt_check_entry_match(elems, base + target_offset,
				    __alignof__(struct xt_entry_match));
}
EXPORT_SYMBOL(xt_check_entry_offsets);

/**
 * xt_alloc_entry_offsets - allocate array to store rule head offsets
 *
 * @size: number of entries
 *
 * Return: NULL or kmalloc'd or vmalloc'd array
 */
unsigned int *xt_alloc_entry_offsets(unsigned int size)
{
	return kvmalloc_array(size, sizeof(unsigned int), GFP_KERNEL | __GFP_ZERO);

}
EXPORT_SYMBOL(xt_alloc_entry_offsets);

/**
 * xt_find_jump_offset - check if target is a valid jump offset
 *
 * @offsets: array containing all valid rule start offsets of a rule blob
 * @target: the jump target to search for
 * @size: entries in @offset
 */
bool xt_find_jump_offset(const unsigned int *offsets,
			 unsigned int target, unsigned int size)
{
	int m, low = 0, hi = size;

	while (hi > low) {
		m = (low + hi) / 2u;

		if (offsets[m] > target)
			hi = m;
		else if (offsets[m] < target)
			low = m + 1;
		else
			return true;
	}

	return false;
}
EXPORT_SYMBOL(xt_find_jump_offset);

int xt_check_target(struct xt_tgchk_param *par,
		    unsigned int size, u_int8_t proto, bool inv_proto)
{
	int ret;

	if (XT_ALIGN(par->target->targetsize) != size) {
		pr_err("%s_tables: %s.%u target: invalid size "
		       "%u (kernel) != (user) %u\n",
		       xt_prefix[par->family], par->target->name,
		       par->target->revision,
		       XT_ALIGN(par->target->targetsize), size);
		return -EINVAL;
	}
	if (par->target->table != NULL &&
	    strcmp(par->target->table, par->table) != 0) {
		pr_err("%s_tables: %s target: only valid in %s table, not %s\n",
		       xt_prefix[par->family], par->target->name,
		       par->target->table, par->table);
		return -EINVAL;
	}
	if (par->target->hooks && (par->hook_mask & ~par->target->hooks) != 0) {
		char used[64], allow[64];

		pr_err("%s_tables: %s target: used from hooks %s, but only "
		       "usable from %s\n",
		       xt_prefix[par->family], par->target->name,
		       textify_hooks(used, sizeof(used), par->hook_mask,
		                     par->family),
		       textify_hooks(allow, sizeof(allow), par->target->hooks,
		                     par->family));
		return -EINVAL;
	}
	if (par->target->proto && (par->target->proto != proto || inv_proto)) {
		pr_err("%s_tables: %s target: only valid for protocol %u\n",
		       xt_prefix[par->family], par->target->name,
		       par->target->proto);
		return -EINVAL;
	}
	if (par->target->checkentry != NULL) {
		ret = par->target->checkentry(par);
		if (ret < 0)
			return ret;
		else if (ret > 0)
			/* Flag up potential errors. */
			return -EIO;
	}
	return 0;
}
EXPORT_SYMBOL_GPL(xt_check_target);

/**
 * xt_copy_counters_from_user - copy counters and metadata from userspace
 *
 * @user: src pointer to userspace memory
 * @len: alleged size of userspace memory
 * @info: where to store the xt_counters_info metadata
 * @compat: true if we setsockopt call is done by 32bit task on 64bit kernel
 *
 * Copies counter meta data from @user and stores it in @info.
 *
 * vmallocs memory to hold the counters, then copies the counter data
 * from @user to the new memory and returns a pointer to it.
 *
 * If @compat is true, @info gets converted automatically to the 64bit
 * representation.
 *
 * The metadata associated with the counters is stored in @info.
 *
 * Return: returns pointer that caller has to test via IS_ERR().
 * If IS_ERR is false, caller has to vfree the pointer.
 */
void *xt_copy_counters_from_user(const void __user *user, unsigned int len,
				 struct xt_counters_info *info, bool compat)
{
	void *mem;
	u64 size;

#ifdef CONFIG_COMPAT
	if (compat) {
		/* structures only differ in size due to alignment */
		struct compat_xt_counters_info compat_tmp;

		if (len <= sizeof(compat_tmp))
			return ERR_PTR(-EINVAL);

		len -= sizeof(compat_tmp);
		if (copy_from_user(&compat_tmp, user, sizeof(compat_tmp)) != 0)
			return ERR_PTR(-EFAULT);

		memcpy(info->name, compat_tmp.name, sizeof(info->name) - 1);
		info->num_counters = compat_tmp.num_counters;
		user += sizeof(compat_tmp);
	} else
#endif
	{
		if (len <= sizeof(*info))
			return ERR_PTR(-EINVAL);

		len -= sizeof(*info);
		if (copy_from_user(info, user, sizeof(*info)) != 0)
			return ERR_PTR(-EFAULT);

		user += sizeof(*info);
	}
	info->name[sizeof(info->name) - 1] = '\0';

	size = sizeof(struct xt_counters);
	size *= info->num_counters;

	if (size != (u64)len)
		return ERR_PTR(-EINVAL);

	mem = vmalloc(len);
	if (!mem)
		return ERR_PTR(-ENOMEM);

	if (copy_from_user(mem, user, len) == 0)
		return mem;

	vfree(mem);
	return ERR_PTR(-EFAULT);
}
EXPORT_SYMBOL_GPL(xt_copy_counters_from_user);

#ifdef CONFIG_COMPAT
int xt_compat_target_offset(const struct xt_target *target)
{
	u_int16_t csize = target->compatsize ? : target->targetsize;
	return XT_ALIGN(target->targetsize) - COMPAT_XT_ALIGN(csize);
}
EXPORT_SYMBOL_GPL(xt_compat_target_offset);

void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr,
				unsigned int *size)
{
	const struct xt_target *target = t->u.kernel.target;
	struct compat_xt_entry_target *ct = (struct compat_xt_entry_target *)t;
	int pad, off = xt_compat_target_offset(target);
	u_int16_t tsize = ct->u.user.target_size;
	char name[sizeof(t->u.user.name)];

	t = *dstptr;
	memcpy(t, ct, sizeof(*ct));
	if (target->compat_from_user)
		target->compat_from_user(t->data, ct->data);
	else
		memcpy(t->data, ct->data, tsize - sizeof(*ct));
	pad = XT_ALIGN(target->targetsize) - target->targetsize;
	if (pad > 0)
		memset(t->data + target->targetsize, 0, pad);

	tsize += off;
	t->u.user.target_size = tsize;
	strlcpy(name, target->name, sizeof(name));
	module_put(target->me);
	strncpy(t->u.user.name, name, sizeof(t->u.user.name));

	*size += off;
	*dstptr += tsize;
}
EXPORT_SYMBOL_GPL(xt_compat_target_from_user);

int xt_compat_target_to_user(const struct xt_entry_target *t,
			     void __user **dstptr, unsigned int *size)
{
	const struct xt_target *target = t->u.kernel.target;
	struct compat_xt_entry_target __user *ct = *dstptr;
	int off = xt_compat_target_offset(target);
	u_int16_t tsize = t->u.user.target_size - off;

	if (XT_OBJ_TO_USER(ct, t, target, tsize))
		return -EFAULT;

	if (target->compat_to_user) {
		if (target->compat_to_user((void __user *)ct->data, t->data))
			return -EFAULT;
	} else {
		if (COMPAT_XT_DATA_TO_USER(ct, t, target, tsize - sizeof(*ct)))
			return -EFAULT;
	}

	*size -= off;
	*dstptr += tsize;
	return 0;
}
EXPORT_SYMBOL_GPL(xt_compat_target_to_user);
#endif

struct xt_table_info *xt_alloc_table_info(unsigned int size)
{
	struct xt_table_info *info = NULL;
	size_t sz = sizeof(*info) + size;

	if (sz < sizeof(*info))
		return NULL;

	/* Pedantry: prevent them from hitting BUG() in vmalloc.c --RR */
	if ((SMP_ALIGN(size) >> PAGE_SHIFT) + 2 > totalram_pages)
		return NULL;

	info = kvmalloc(sz, GFP_KERNEL);
	if (!info)
		return NULL;

	memset(info, 0, sizeof(*info));
	info->size = size;
	return info;
}
EXPORT_SYMBOL(xt_alloc_table_info);

void xt_free_table_info(struct xt_table_info *info)
{
	int cpu;

	if (info->jumpstack != NULL) {
		for_each_possible_cpu(cpu)
			kvfree(info->jumpstack[cpu]);
		kvfree(info->jumpstack);
	}

	kvfree(info);
}
EXPORT_SYMBOL(xt_free_table_info);

/* Find table by name, grabs mutex & ref.  Returns NULL on error. */
struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af,
				    const char *name)
{
	struct xt_table *t, *found = NULL;

	mutex_lock(&xt[af].mutex);
	list_for_each_entry(t, &net->xt.tables[af], list)
		if (strcmp(t->name, name) == 0 && try_module_get(t->me))
			return t;

	if (net == &init_net)
		goto out;

	/* Table doesn't exist in this netns, re-try init */
	list_for_each_entry(t, &init_net.xt.tables[af], list) {
		if (strcmp(t->name, name))
			continue;
		if (!try_module_get(t->me)) {
			mutex_unlock(&xt[af].mutex);
			return NULL;
		}

		mutex_unlock(&xt[af].mutex);
		if (t->table_init(net) != 0) {
			module_put(t->me);
			return NULL;
		}

		found = t;

		mutex_lock(&xt[af].mutex);
		break;
	}

	if (!found)
		goto out;

	/* and once again: */
	list_for_each_entry(t, &net->xt.tables[af], list)
		if (strcmp(t->name, name) == 0)
			return t;

	module_put(found->me);
 out:
	mutex_unlock(&xt[af].mutex);
	return NULL;
}
EXPORT_SYMBOL_GPL(xt_find_table_lock);

void xt_table_unlock(struct xt_table *table)
{
	mutex_unlock(&xt[table->af].mutex);
}
EXPORT_SYMBOL_GPL(xt_table_unlock);

#ifdef CONFIG_COMPAT
void xt_compat_lock(u_int8_t af)
{
	mutex_lock(&xt[af].compat_mutex);
}
EXPORT_SYMBOL_GPL(xt_compat_lock);

void xt_compat_unlock(u_int8_t af)
{
	mutex_unlock(&xt[af].compat_mutex);
}
EXPORT_SYMBOL_GPL(xt_compat_unlock);
#endif

DEFINE_PER_CPU(seqcount_t, xt_recseq);
EXPORT_PER_CPU_SYMBOL_GPL(xt_recseq);

struct static_key xt_tee_enabled __read_mostly;
EXPORT_SYMBOL_GPL(xt_tee_enabled);

static int xt_jumpstack_alloc(struct xt_table_info *i)
{
	unsigned int size;
	int cpu;

	size = sizeof(void **) * nr_cpu_ids;
	if (size > PAGE_SIZE)
		i->jumpstack = kvzalloc(size, GFP_KERNEL);
	else
		i->jumpstack = kzalloc(size, GFP_KERNEL);
	if (i->jumpstack == NULL)
		return -ENOMEM;

	/* ruleset without jumps -- no stack needed */
	if (i->stacksize == 0)
		return 0;

	/* Jumpstack needs to be able to record two full callchains, one
	 * from the first rule set traversal, plus one table reentrancy
	 * via -j TEE without clobbering the callchain that brought us to
	 * TEE target.
	 *
	 * This is done by allocating two jumpstacks per cpu, on reentry
	 * the upper half of the stack is used.
	 *
	 * see the jumpstack setup in ipt_do_table() for more details.
	 */
	size = sizeof(void *) * i->stacksize * 2u;
	for_each_possible_cpu(cpu) {
		i->jumpstack[cpu] = kvmalloc_node(size, GFP_KERNEL,
			cpu_to_node(cpu));
		if (i->jumpstack[cpu] == NULL)
			/*
			 * Freeing will be done later on by the callers. The
			 * chain is: xt_replace_table -> __do_replace ->
			 * do_replace -> xt_free_table_info.
			 */
			return -ENOMEM;
	}

	return 0;
}

struct xt_table_info *
xt_replace_table(struct xt_table *table,
	      unsigned int num_counters,
	      struct xt_table_info *newinfo,
	      int *error)
{
	struct xt_table_info *private;
	unsigned int cpu;
	int ret;

	ret = xt_jumpstack_alloc(newinfo);
	if (ret < 0) {
		*error = ret;
		return NULL;
	}

	/* Do the substitution. */
	local_bh_disable();
	private = table->private;

	/* Check inside lock: is the old number correct? */
	if (num_counters != private->number) {
		pr_debug("num_counters != table->private->number (%u/%u)\n",
			 num_counters, private->number);
		local_bh_enable();
		*error = -EAGAIN;
		return NULL;
	}

	newinfo->initial_entries = private->initial_entries;
	/*
	 * Ensure contents of newinfo are visible before assigning to
	 * private.
	 */
	smp_wmb();
	table->private = newinfo;

	/* make sure all cpus see new ->private value */
	smp_wmb();

	/*
	 * Even though table entries have now been swapped, other CPU's
	 * may still be using the old entries...
	 */
	local_bh_enable();

	/* ... so wait for even xt_recseq on all cpus */
	for_each_possible_cpu(cpu) {
		seqcount_t *s = &per_cpu(xt_recseq, cpu);
		u32 seq = raw_read_seqcount(s);

		if (seq & 1) {
			do {
				cond_resched();
				cpu_relax();
			} while (seq == raw_read_seqcount(s));
		}
	}

#ifdef CONFIG_AUDIT
	if (audit_enabled) {
		audit_log(current->audit_context, GFP_KERNEL,
			  AUDIT_NETFILTER_CFG,
			  "table=%s family=%u entries=%u",
			  table->name, table->af, private->number);
	}
#endif

	return private;
}
EXPORT_SYMBOL_GPL(xt_replace_table);

struct xt_table *xt_register_table(struct net *net,
				   const struct xt_table *input_table,
				   struct xt_table_info *bootstrap,
				   struct xt_table_info *newinfo)
{
	int ret;
	struct xt_table_info *private;
	struct xt_table *t, *table;

	/* Don't add one object to multiple lists. */
	table = kmemdup(input_table, sizeof(struct xt_table), GFP_KERNEL);
	if (!table) {
		ret = -ENOMEM;
		goto out;
	}

	mutex_lock(&xt[table->af].mutex);
	/* Don't autoload: we'd eat our tail... */
	list_for_each_entry(t, &net->xt.tables[table->af], list) {
		if (strcmp(t->name, table->name) == 0) {
			ret = -EEXIST;
			goto unlock;
		}
	}

	/* Simplifies replace_table code. */
	table->private = bootstrap;

	if (!xt_replace_table(table, 0, newinfo, &ret))
		goto unlock;

	private = table->private;
	pr_debug("table->private->number = %u\n", private->number);

	/* save number of initial entries */
	private->initial_entries = private->number;

	list_add(&table->list, &net->xt.tables[table->af]);
	mutex_unlock(&xt[table->af].mutex);
	return table;

unlock:
	mutex_unlock(&xt[table->af].mutex);
	kfree(table);
out:
	return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(xt_register_table);

void *xt_unregister_table(struct xt_table *table)
{
	struct xt_table_info *private;

	mutex_lock(&xt[table->af].mutex);
	private = table->private;
	list_del(&table->list);
	mutex_unlock(&xt[table->af].mutex);
	kfree(table);

	return private;
}
EXPORT_SYMBOL_GPL(xt_unregister_table);

#ifdef CONFIG_PROC_FS
struct xt_names_priv {
	struct seq_net_private p;
	u_int8_t af;
};
static void *xt_table_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct xt_names_priv *priv = seq->private;
	struct net *net = seq_file_net(seq);
	u_int8_t af = priv->af;

	mutex_lock(&xt[af].mutex);
	return seq_list_start(&net->xt.tables[af], *pos);
}

static void *xt_table_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct xt_names_priv *priv = seq->private;
	struct net *net = seq_file_net(seq);
	u_int8_t af = priv->af;

	return seq_list_next(v, &net->xt.tables[af], pos);
}

static void xt_table_seq_stop(struct seq_file *seq, void *v)
{
	struct xt_names_priv *priv = seq->private;
	u_int8_t af = priv->af;

	mutex_unlock(&xt[af].mutex);
}

static int xt_table_seq_show(struct seq_file *seq, void *v)
{
	struct xt_table *table = list_entry(v, struct xt_table, list);

	if (*table->name)
		seq_printf(seq, "%s\n", table->name);
	return 0;
}

static const struct seq_operations xt_table_seq_ops = {
	.start	= xt_table_seq_start,
	.next	= xt_table_seq_next,
	.stop	= xt_table_seq_stop,
	.show	= xt_table_seq_show,
};

static int xt_table_open(struct inode *inode, struct file *file)
{
	int ret;
	struct xt_names_priv *priv;

	ret = seq_open_net(inode, file, &xt_table_seq_ops,
			   sizeof(struct xt_names_priv));
	if (!ret) {
		priv = ((struct seq_file *)file->private_data)->private;
		priv->af = (unsigned long)PDE_DATA(inode);
	}
	return ret;
}

static const struct file_operations xt_table_ops = {
	.owner	 = THIS_MODULE,
	.open	 = xt_table_open,
	.read	 = seq_read,
	.llseek	 = seq_lseek,
	.release = seq_release_net,
};

/*
 * Traverse state for ip{,6}_{tables,matches} for helping crossing
 * the multi-AF mutexes.
 */
struct nf_mttg_trav {
	struct list_head *head, *curr;
	uint8_t class, nfproto;
};

enum {
	MTTG_TRAV_INIT,
	MTTG_TRAV_NFP_UNSPEC,
	MTTG_TRAV_NFP_SPEC,
	MTTG_TRAV_DONE,
};

static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos,
    bool is_target)
{
	static const uint8_t next_class[] = {
		[MTTG_TRAV_NFP_UNSPEC] = MTTG_TRAV_NFP_SPEC,
		[MTTG_TRAV_NFP_SPEC]   = MTTG_TRAV_DONE,
	};
	struct nf_mttg_trav *trav = seq->private;

	switch (trav->class) {
	case MTTG_TRAV_INIT:
		trav->class = MTTG_TRAV_NFP_UNSPEC;
		mutex_lock(&xt[NFPROTO_UNSPEC].mutex);
		trav->head = trav->curr = is_target ?
			&xt[NFPROTO_UNSPEC].target : &xt[NFPROTO_UNSPEC].match;
 		break;
	case MTTG_TRAV_NFP_UNSPEC:
		trav->curr = trav->curr->next;
		if (trav->curr != trav->head)
			break;
		mutex_unlock(&xt[NFPROTO_UNSPEC].mutex);
		mutex_lock(&xt[trav->nfproto].mutex);
		trav->head = trav->curr = is_target ?
			&xt[trav->nfproto].target : &xt[trav->nfproto].match;
		trav->class = next_class[trav->class];
		break;
	case MTTG_TRAV_NFP_SPEC:
		trav->curr = trav->curr->next;
		if (trav->curr != trav->head)
			break;
		/* fallthru, _stop will unlock */
	default:
		return NULL;
	}

	if (ppos != NULL)
		++*ppos;
	return trav;
}

static void *xt_mttg_seq_start(struct seq_file *seq, loff_t *pos,
    bool is_target)
{
	struct nf_mttg_trav *trav = seq->private;
	unsigned int j;

	trav->class = MTTG_TRAV_INIT;
	for (j = 0; j < *pos; ++j)
		if (xt_mttg_seq_next(seq, NULL, NULL, is_target) == NULL)
			return NULL;
	return trav;
}

static void xt_mttg_seq_stop(struct seq_file *seq, void *v)
{
	struct nf_mttg_trav *trav = seq->private;

	switch (trav->class) {
	case MTTG_TRAV_NFP_UNSPEC:
		mutex_unlock(&xt[NFPROTO_UNSPEC].mutex);
		break;
	case MTTG_TRAV_NFP_SPEC:
		mutex_unlock(&xt[trav->nfproto].mutex);
		break;
	}
}

static void *xt_match_seq_start(struct seq_file *seq, loff_t *pos)
{
	return xt_mttg_seq_start(seq, pos, false);
}

static void *xt_match_seq_next(struct seq_file *seq, void *v, loff_t *ppos)
{
	return xt_mttg_seq_next(seq, v, ppos, false);
}

static int xt_match_seq_show(struct seq_file *seq, void *v)
{
	const struct nf_mttg_trav *trav = seq->private;
	const struct xt_match *match;

	switch (trav->class) {
	case MTTG_TRAV_NFP_UNSPEC:
	case MTTG_TRAV_NFP_SPEC:
		if (trav->curr == trav->head)
			return 0;
		match = list_entry(trav->curr, struct xt_match, list);
		if (*match->name)
			seq_printf(seq, "%s\n", match->name);
	}
	return 0;
}

static const struct seq_operations xt_match_seq_ops = {
	.start	= xt_match_seq_start,
	.next	= xt_match_seq_next,
	.stop	= xt_mttg_seq_stop,
	.show	= xt_match_seq_show,
};

static int xt_match_open(struct inode *inode, struct file *file)
{
	struct nf_mttg_trav *trav;
	trav = __seq_open_private(file, &xt_match_seq_ops, sizeof(*trav));
	if (!trav)
		return -ENOMEM;

	trav->nfproto = (unsigned long)PDE_DATA(inode);
	return 0;
}

static const struct file_operations xt_match_ops = {
	.owner	 = THIS_MODULE,
	.open	 = xt_match_open,
	.read	 = seq_read,
	.llseek	 = seq_lseek,
	.release = seq_release_private,
};

static void *xt_target_seq_start(struct seq_file *seq, loff_t *pos)
{
	return xt_mttg_seq_start(seq, pos, true);
}

static void *xt_target_seq_next(struct seq_file *seq, void *v, loff_t *ppos)
{
	return xt_mttg_seq_next(seq, v, ppos, true);
}

static int xt_target_seq_show(struct seq_file *seq, void *v)
{
	const struct nf_mttg_trav *trav = seq->private;
	const struct xt_target *target;

	switch (trav->class) {
	case MTTG_TRAV_NFP_UNSPEC:
	case MTTG_TRAV_NFP_SPEC:
		if (trav->curr == trav->head)
			return 0;
		target = list_entry(trav->curr, struct xt_target, list);
		if (*target->name)
			seq_printf(seq, "%s\n", target->name);
	}
	return 0;
}

static const struct seq_operations xt_target_seq_ops = {
	.start	= xt_target_seq_start,
	.next	= xt_target_seq_next,
	.stop	= xt_mttg_seq_stop,
	.show	= xt_target_seq_show,
};

static int xt_target_open(struct inode *inode, struct file *file)
{
	struct nf_mttg_trav *trav;
	trav = __seq_open_private(file, &xt_target_seq_ops, sizeof(*trav));
	if (!trav)
		return -ENOMEM;

	trav->nfproto = (unsigned long)PDE_DATA(inode);
	return 0;
}

static const struct file_operations xt_target_ops = {
	.owner	 = THIS_MODULE,
	.open	 = xt_target_open,
	.read	 = seq_read,
	.llseek	 = seq_lseek,
	.release = seq_release_private,
};

#define FORMAT_TABLES	"_tables_names"
#define	FORMAT_MATCHES	"_tables_matches"
#define FORMAT_TARGETS 	"_tables_targets"

#endif /* CONFIG_PROC_FS */

/**
 * xt_hook_ops_alloc - set up hooks for a new table
 * @table:	table with metadata needed to set up hooks
 * @fn:		Hook function
 *
 * This function will create the nf_hook_ops that the x_table needs
 * to hand to xt_hook_link_net().
 */
struct nf_hook_ops *
xt_hook_ops_alloc(const struct xt_table *table, nf_hookfn *fn)
{
	unsigned int hook_mask = table->valid_hooks;
	uint8_t i, num_hooks = hweight32(hook_mask);
	uint8_t hooknum;
	struct nf_hook_ops *ops;

	if (!num_hooks)
		return ERR_PTR(-EINVAL);

	ops = kcalloc(num_hooks, sizeof(*ops), GFP_KERNEL);
	if (ops == NULL)
		return ERR_PTR(-ENOMEM);

	for (i = 0, hooknum = 0; i < num_hooks && hook_mask != 0;
	     hook_mask >>= 1, ++hooknum) {
		if (!(hook_mask & 1))
			continue;
		ops[i].hook     = fn;
		ops[i].pf       = table->af;
		ops[i].hooknum  = hooknum;
		ops[i].priority = table->priority;
		++i;
	}

	return ops;
}
EXPORT_SYMBOL_GPL(xt_hook_ops_alloc);

int xt_proto_init(struct net *net, u_int8_t af)
{
#ifdef CONFIG_PROC_FS
	char buf[XT_FUNCTION_MAXNAMELEN];
	struct proc_dir_entry *proc;
	kuid_t root_uid;
	kgid_t root_gid;
#endif

	if (af >= ARRAY_SIZE(xt_prefix))
		return -EINVAL;


#ifdef CONFIG_PROC_FS
	root_uid = make_kuid(net->user_ns, 0);
	root_gid = make_kgid(net->user_ns, 0);

	strlcpy(buf, xt_prefix[af], sizeof(buf));
	strlcat(buf, FORMAT_TABLES, sizeof(buf));
	proc = proc_create_data(buf, 0440, net->proc_net, &xt_table_ops,
				(void *)(unsigned long)af);
	if (!proc)
		goto out;
	if (uid_valid(root_uid) && gid_valid(root_gid))
		proc_set_user(proc, root_uid, root_gid);

	strlcpy(buf, xt_prefix[af], sizeof(buf));
	strlcat(buf, FORMAT_MATCHES, sizeof(buf));
	proc = proc_create_data(buf, 0440, net->proc_net, &xt_match_ops,
				(void *)(unsigned long)af);
	if (!proc)
		goto out_remove_tables;
	if (uid_valid(root_uid) && gid_valid(root_gid))
		proc_set_user(proc, root_uid, root_gid);

	strlcpy(buf, xt_prefix[af], sizeof(buf));
	strlcat(buf, FORMAT_TARGETS, sizeof(buf));
	proc = proc_create_data(buf, 0440, net->proc_net, &xt_target_ops,
				(void *)(unsigned long)af);
	if (!proc)
		goto out_remove_matches;
	if (uid_valid(root_uid) && gid_valid(root_gid))
		proc_set_user(proc, root_uid, root_gid);
#endif

	return 0;

#ifdef CONFIG_PROC_FS
out_remove_matches:
	strlcpy(buf, xt_prefix[af], sizeof(buf));
	strlcat(buf, FORMAT_MATCHES, sizeof(buf));
	remove_proc_entry(buf, net->proc_net);

out_remove_tables:
	strlcpy(buf, xt_prefix[af], sizeof(buf));
	strlcat(buf, FORMAT_TABLES, sizeof(buf));
	remove_proc_entry(buf, net->proc_net);
out:
	return -1;
#endif
}
EXPORT_SYMBOL_GPL(xt_proto_init);

void xt_proto_fini(struct net *net, u_int8_t af)
{
#ifdef CONFIG_PROC_FS
	char buf[XT_FUNCTION_MAXNAMELEN];

	strlcpy(buf, xt_prefix[af], sizeof(buf));
	strlcat(buf, FORMAT_TABLES, sizeof(buf));
	remove_proc_entry(buf, net->proc_net);

	strlcpy(buf, xt_prefix[af], sizeof(buf));
	strlcat(buf, FORMAT_TARGETS, sizeof(buf));
	remove_proc_entry(buf, net->proc_net);

	strlcpy(buf, xt_prefix[af], sizeof(buf));
	strlcat(buf, FORMAT_MATCHES, sizeof(buf));
	remove_proc_entry(buf, net->proc_net);
#endif /*CONFIG_PROC_FS*/
}
EXPORT_SYMBOL_GPL(xt_proto_fini);

/**
 * xt_percpu_counter_alloc - allocate x_tables rule counter
 *
 * @state: pointer to xt_percpu allocation state
 * @counter: pointer to counter struct inside the ip(6)/arpt_entry struct
 *
 * On SMP, the packet counter [ ip(6)t_entry->counters.pcnt ] will then
 * contain the address of the real (percpu) counter.
 *
 * Rule evaluation needs to use xt_get_this_cpu_counter() helper
 * to fetch the real percpu counter.
 *
 * To speed up allocation and improve data locality, a 4kb block is
 * allocated.
 *
 * xt_percpu_counter_alloc_state contains the base address of the
 * allocated page and the current sub-offset.
 *
 * returns false on error.
 */
bool xt_percpu_counter_alloc(struct xt_percpu_counter_alloc_state *state,
			     struct xt_counters *counter)
{
	BUILD_BUG_ON(XT_PCPU_BLOCK_SIZE < (sizeof(*counter) * 2));

	if (nr_cpu_ids <= 1)
		return true;

	if (!state->mem) {
		state->mem = __alloc_percpu(XT_PCPU_BLOCK_SIZE,
					    XT_PCPU_BLOCK_SIZE);
		if (!state->mem)
			return false;
	}
	counter->pcnt = (__force unsigned long)(state->mem + state->off);
	state->off += sizeof(*counter);
	if (state->off > (XT_PCPU_BLOCK_SIZE - sizeof(*counter))) {
		state->mem = NULL;
		state->off = 0;
	}
	return true;
}
EXPORT_SYMBOL_GPL(xt_percpu_counter_alloc);

void xt_percpu_counter_free(struct xt_counters *counters)
{
	unsigned long pcnt = counters->pcnt;

	if (nr_cpu_ids > 1 && (pcnt & (XT_PCPU_BLOCK_SIZE - 1)) == 0)
		free_percpu((void __percpu *)pcnt);
}
EXPORT_SYMBOL_GPL(xt_percpu_counter_free);

static int __net_init xt_net_init(struct net *net)
{
	int i;

	for (i = 0; i < NFPROTO_NUMPROTO; i++)
		INIT_LIST_HEAD(&net->xt.tables[i]);
	return 0;
}

static void __net_exit xt_net_exit(struct net *net)
{
	int i;

	for (i = 0; i < NFPROTO_NUMPROTO; i++)
		WARN_ON_ONCE(!list_empty(&net->xt.tables[i]));
}

static struct pernet_operations xt_net_ops = {
	.init = xt_net_init,
	.exit = xt_net_exit,
};

static int __init xt_init(void)
{
	unsigned int i;
	int rv;

	for_each_possible_cpu(i) {
		seqcount_init(&per_cpu(xt_recseq, i));
	}

	xt = kmalloc(sizeof(struct xt_af) * NFPROTO_NUMPROTO, GFP_KERNEL);
	if (!xt)
		return -ENOMEM;

	for (i = 0; i < NFPROTO_NUMPROTO; i++) {
		mutex_init(&xt[i].mutex);
#ifdef CONFIG_COMPAT
		mutex_init(&xt[i].compat_mutex);
		xt[i].compat_tab = NULL;
#endif
		INIT_LIST_HEAD(&xt[i].target);
		INIT_LIST_HEAD(&xt[i].match);
	}
	rv = register_pernet_subsys(&xt_net_ops);
	if (rv < 0)
		kfree(xt);
	return rv;
}

static void __exit xt_fini(void)
{
	unregister_pernet_subsys(&xt_net_ops);
	kfree(xt);
}

module_init(xt_init);
module_exit(xt_fini);