aboutsummaryrefslogtreecommitdiff
path: root/net/netfilter/nf_conntrack_core.c
blob: ed9ce7c63252eab326f93e0714181bd57ab5b3fc (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
/* 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) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
 * (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.org>
 * (C) 2005-2012 Patrick McHardy <kaber@trash.net>
 *
 * 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/types.h>
#include <linux/netfilter.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/skbuff.h>
#include <linux/proc_fs.h>
#include <linux/vmalloc.h>
#include <linux/stddef.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>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/socket.h>
#include <linux/mm.h>
#include <linux/nsproxy.h>
#include <linux/rculist_nulls.h>

#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_l3proto.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_expect.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_seqadj.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_extend.h>
#include <net/netfilter/nf_conntrack_acct.h>
#include <net/netfilter/nf_conntrack_ecache.h>
#include <net/netfilter/nf_conntrack_zones.h>
#include <net/netfilter/nf_conntrack_timestamp.h>
#include <net/netfilter/nf_conntrack_timeout.h>
#include <net/netfilter/nf_conntrack_labels.h>
#include <net/netfilter/nf_conntrack_synproxy.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_core.h>
#include <net/netfilter/nf_nat_helper.h>
#include <net/netns/hash.h>

#define NF_CONNTRACK_VERSION	"0.5.0"

int (*nfnetlink_parse_nat_setup_hook)(struct nf_conn *ct,
				      enum nf_nat_manip_type manip,
				      const struct nlattr *attr) __read_mostly;
EXPORT_SYMBOL_GPL(nfnetlink_parse_nat_setup_hook);

__cacheline_aligned_in_smp spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS];
EXPORT_SYMBOL_GPL(nf_conntrack_locks);

__cacheline_aligned_in_smp DEFINE_SPINLOCK(nf_conntrack_expect_lock);
EXPORT_SYMBOL_GPL(nf_conntrack_expect_lock);

struct hlist_nulls_head *nf_conntrack_hash __read_mostly;
EXPORT_SYMBOL_GPL(nf_conntrack_hash);

struct conntrack_gc_work {
	struct delayed_work	dwork;
	u32			last_bucket;
	bool			exiting;
	long			next_gc_run;
};

static __read_mostly struct kmem_cache *nf_conntrack_cachep;
static __read_mostly spinlock_t nf_conntrack_locks_all_lock;
static __read_mostly DEFINE_SPINLOCK(nf_conntrack_locks_all_lock);
static __read_mostly bool nf_conntrack_locks_all;

/* every gc cycle scans at most 1/GC_MAX_BUCKETS_DIV part of table */
#define GC_MAX_BUCKETS_DIV	128u
/* upper bound of full table scan */
#define GC_MAX_SCAN_JIFFIES	(16u * HZ)
/* desired ratio of entries found to be expired */
#define GC_EVICT_RATIO	50u

static struct conntrack_gc_work conntrack_gc_work;

void nf_conntrack_lock(spinlock_t *lock) __acquires(lock)
{
	/* 1) Acquire the lock */
	spin_lock(lock);

	/* 2) read nf_conntrack_locks_all, with ACQUIRE semantics
	 * It pairs with the smp_store_release() in nf_conntrack_all_unlock()
	 */
	if (likely(smp_load_acquire(&nf_conntrack_locks_all) == false))
		return;

	/* fast path failed, unlock */
	spin_unlock(lock);

	/* Slow path 1) get global lock */
	spin_lock(&nf_conntrack_locks_all_lock);

	/* Slow path 2) get the lock we want */
	spin_lock(lock);

	/* Slow path 3) release the global lock */
	spin_unlock(&nf_conntrack_locks_all_lock);
}
EXPORT_SYMBOL_GPL(nf_conntrack_lock);

static void nf_conntrack_double_unlock(unsigned int h1, unsigned int h2)
{
	h1 %= CONNTRACK_LOCKS;
	h2 %= CONNTRACK_LOCKS;
	spin_unlock(&nf_conntrack_locks[h1]);
	if (h1 != h2)
		spin_unlock(&nf_conntrack_locks[h2]);
}

/* return true if we need to recompute hashes (in case hash table was resized) */
static bool nf_conntrack_double_lock(struct net *net, unsigned int h1,
				     unsigned int h2, unsigned int sequence)
{
	h1 %= CONNTRACK_LOCKS;
	h2 %= CONNTRACK_LOCKS;
	if (h1 <= h2) {
		nf_conntrack_lock(&nf_conntrack_locks[h1]);
		if (h1 != h2)
			spin_lock_nested(&nf_conntrack_locks[h2],
					 SINGLE_DEPTH_NESTING);
	} else {
		nf_conntrack_lock(&nf_conntrack_locks[h2]);
		spin_lock_nested(&nf_conntrack_locks[h1],
				 SINGLE_DEPTH_NESTING);
	}
	if (read_seqcount_retry(&nf_conntrack_generation, sequence)) {
		nf_conntrack_double_unlock(h1, h2);
		return true;
	}
	return false;
}

static void nf_conntrack_all_lock(void)
{
	int i;

	spin_lock(&nf_conntrack_locks_all_lock);

	nf_conntrack_locks_all = true;

	for (i = 0; i < CONNTRACK_LOCKS; i++) {
		spin_lock(&nf_conntrack_locks[i]);

		/* This spin_unlock provides the "release" to ensure that
		 * nf_conntrack_locks_all==true is visible to everyone that
		 * acquired spin_lock(&nf_conntrack_locks[]).
		 */
		spin_unlock(&nf_conntrack_locks[i]);
	}
}

static void nf_conntrack_all_unlock(void)
{
	/* All prior stores must be complete before we clear
	 * 'nf_conntrack_locks_all'. Otherwise nf_conntrack_lock()
	 * might observe the false value but not the entire
	 * critical section.
	 * It pairs with the smp_load_acquire() in nf_conntrack_lock()
	 */
	smp_store_release(&nf_conntrack_locks_all, false);
	spin_unlock(&nf_conntrack_locks_all_lock);
}

unsigned int nf_conntrack_htable_size __read_mostly;
EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);

unsigned int nf_conntrack_max __read_mostly;
seqcount_t nf_conntrack_generation __read_mostly;

DEFINE_PER_CPU(struct nf_conn, nf_conntrack_untracked);
EXPORT_PER_CPU_SYMBOL(nf_conntrack_untracked);

static unsigned int nf_conntrack_hash_rnd __read_mostly;

static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple,
			      const struct net *net)
{
	unsigned int n;
	u32 seed;

	get_random_once(&nf_conntrack_hash_rnd, sizeof(nf_conntrack_hash_rnd));

	/* The direction must be ignored, so we hash everything up to the
	 * destination ports (which is a multiple of 4) and treat the last
	 * three bytes manually.
	 */
	seed = nf_conntrack_hash_rnd ^ net_hash_mix(net);
	n = (sizeof(tuple->src) + sizeof(tuple->dst.u3)) / sizeof(u32);
	return jhash2((u32 *)tuple, n, seed ^
		      (((__force __u16)tuple->dst.u.all << 16) |
		      tuple->dst.protonum));
}

static u32 scale_hash(u32 hash)
{
	return reciprocal_scale(hash, nf_conntrack_htable_size);
}

static u32 __hash_conntrack(const struct net *net,
			    const struct nf_conntrack_tuple *tuple,
			    unsigned int size)
{
	return reciprocal_scale(hash_conntrack_raw(tuple, net), size);
}

static u32 hash_conntrack(const struct net *net,
			  const struct nf_conntrack_tuple *tuple)
{
	return scale_hash(hash_conntrack_raw(tuple, net));
}

bool
nf_ct_get_tuple(const struct sk_buff *skb,
		unsigned int nhoff,
		unsigned int dataoff,
		u_int16_t l3num,
		u_int8_t protonum,
		struct net *net,
		struct nf_conntrack_tuple *tuple,
		const struct nf_conntrack_l3proto *l3proto,
		const struct nf_conntrack_l4proto *l4proto)
{
	memset(tuple, 0, sizeof(*tuple));

	tuple->src.l3num = l3num;
	if (l3proto->pkt_to_tuple(skb, nhoff, tuple) == 0)
		return false;

	tuple->dst.protonum = protonum;
	tuple->dst.dir = IP_CT_DIR_ORIGINAL;

	return l4proto->pkt_to_tuple(skb, dataoff, net, tuple);
}
EXPORT_SYMBOL_GPL(nf_ct_get_tuple);

bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff,
		       u_int16_t l3num,
		       struct net *net, struct nf_conntrack_tuple *tuple)
{
	struct nf_conntrack_l3proto *l3proto;
	struct nf_conntrack_l4proto *l4proto;
	unsigned int protoff;
	u_int8_t protonum;
	int ret;

	rcu_read_lock();

	l3proto = __nf_ct_l3proto_find(l3num);
	ret = l3proto->get_l4proto(skb, nhoff, &protoff, &protonum);
	if (ret != NF_ACCEPT) {
		rcu_read_unlock();
		return false;
	}

	l4proto = __nf_ct_l4proto_find(l3num, protonum);

	ret = nf_ct_get_tuple(skb, nhoff, protoff, l3num, protonum, net, tuple,
			      l3proto, l4proto);

	rcu_read_unlock();
	return ret;
}
EXPORT_SYMBOL_GPL(nf_ct_get_tuplepr);

bool
nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
		   const struct nf_conntrack_tuple *orig,
		   const struct nf_conntrack_l3proto *l3proto,
		   const struct nf_conntrack_l4proto *l4proto)
{
	memset(inverse, 0, sizeof(*inverse));

	inverse->src.l3num = orig->src.l3num;
	if (l3proto->invert_tuple(inverse, orig) == 0)
		return false;

	inverse->dst.dir = !orig->dst.dir;

	inverse->dst.protonum = orig->dst.protonum;
	return l4proto->invert_tuple(inverse, orig);
}
EXPORT_SYMBOL_GPL(nf_ct_invert_tuple);

static void
clean_from_lists(struct nf_conn *ct)
{
	pr_debug("clean_from_lists(%p)\n", ct);
	hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
	hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode);

	/* Destroy all pending expectations */
	nf_ct_remove_expectations(ct);
}

/* must be called with local_bh_disable */
static void nf_ct_add_to_dying_list(struct nf_conn *ct)
{
	struct ct_pcpu *pcpu;

	/* add this conntrack to the (per cpu) dying list */
	ct->cpu = smp_processor_id();
	pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);

	spin_lock(&pcpu->lock);
	hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
			     &pcpu->dying);
	spin_unlock(&pcpu->lock);
}

/* must be called with local_bh_disable */
static void nf_ct_add_to_unconfirmed_list(struct nf_conn *ct)
{
	struct ct_pcpu *pcpu;

	/* add this conntrack to the (per cpu) unconfirmed list */
	ct->cpu = smp_processor_id();
	pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);

	spin_lock(&pcpu->lock);
	hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
			     &pcpu->unconfirmed);
	spin_unlock(&pcpu->lock);
}

/* must be called with local_bh_disable */
static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct)
{
	struct ct_pcpu *pcpu;

	/* We overload first tuple to link into unconfirmed or dying list.*/
	pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);

	spin_lock(&pcpu->lock);
	BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode));
	hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
	spin_unlock(&pcpu->lock);
}

/* Released via destroy_conntrack() */
struct nf_conn *nf_ct_tmpl_alloc(struct net *net,
				 const struct nf_conntrack_zone *zone,
				 gfp_t flags)
{
	struct nf_conn *tmpl;

	tmpl = kzalloc(sizeof(*tmpl), flags);
	if (tmpl == NULL)
		return NULL;

	tmpl->status = IPS_TEMPLATE;
	write_pnet(&tmpl->ct_net, net);
	nf_ct_zone_add(tmpl, zone);
	atomic_set(&tmpl->ct_general.use, 0);

	return tmpl;
}
EXPORT_SYMBOL_GPL(nf_ct_tmpl_alloc);

void nf_ct_tmpl_free(struct nf_conn *tmpl)
{
	nf_ct_ext_destroy(tmpl);
	nf_ct_ext_free(tmpl);
	kfree(tmpl);
}
EXPORT_SYMBOL_GPL(nf_ct_tmpl_free);

static void
destroy_conntrack(struct nf_conntrack *nfct)
{
	struct nf_conn *ct = (struct nf_conn *)nfct;
	struct nf_conntrack_l4proto *l4proto;

	pr_debug("destroy_conntrack(%p)\n", ct);
	NF_CT_ASSERT(atomic_read(&nfct->use) == 0);

	if (unlikely(nf_ct_is_template(ct))) {
		nf_ct_tmpl_free(ct);
		return;
	}
	rcu_read_lock();
	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
	if (l4proto->destroy)
		l4proto->destroy(ct);

	rcu_read_unlock();

	local_bh_disable();
	/* 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.
	 */
	nf_ct_remove_expectations(ct);

	nf_ct_del_from_dying_or_unconfirmed_list(ct);

	local_bh_enable();

	if (ct->master)
		nf_ct_put(ct->master);

	pr_debug("destroy_conntrack: returning ct=%p to slab\n", ct);
	nf_conntrack_free(ct);
}

static void nf_ct_delete_from_lists(struct nf_conn *ct)
{
	struct net *net = nf_ct_net(ct);
	unsigned int hash, reply_hash;
	unsigned int sequence;

	nf_ct_helper_destroy(ct);

	local_bh_disable();
	do {
		sequence = read_seqcount_begin(&nf_conntrack_generation);
		hash = hash_conntrack(net,
				      &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
		reply_hash = hash_conntrack(net,
					   &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
	} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));

	clean_from_lists(ct);
	nf_conntrack_double_unlock(hash, reply_hash);

	nf_ct_add_to_dying_list(ct);

	local_bh_enable();
}

bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report)
{
	struct nf_conn_tstamp *tstamp;

	if (test_and_set_bit(IPS_DYING_BIT, &ct->status))
		return false;

	tstamp = nf_conn_tstamp_find(ct);
	if (tstamp && tstamp->stop == 0)
		tstamp->stop = ktime_get_real_ns();

	if (nf_conntrack_event_report(IPCT_DESTROY, ct,
				    portid, report) < 0) {
		/* destroy event was not delivered. nf_ct_put will
		 * be done by event cache worker on redelivery.
		 */
		nf_ct_delete_from_lists(ct);
		nf_conntrack_ecache_delayed_work(nf_ct_net(ct));
		return false;
	}

	nf_conntrack_ecache_work(nf_ct_net(ct));
	nf_ct_delete_from_lists(ct);
	nf_ct_put(ct);
	return true;
}
EXPORT_SYMBOL_GPL(nf_ct_delete);

static inline bool
nf_ct_key_equal(struct nf_conntrack_tuple_hash *h,
		const struct nf_conntrack_tuple *tuple,
		const struct nf_conntrack_zone *zone,
		const struct net *net)
{
	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);

	/* A conntrack can be recreated with the equal tuple,
	 * so we need to check that the conntrack is confirmed
	 */
	return nf_ct_tuple_equal(tuple, &h->tuple) &&
	       nf_ct_zone_equal(ct, zone, NF_CT_DIRECTION(h)) &&
	       nf_ct_is_confirmed(ct) &&
	       net_eq(net, nf_ct_net(ct));
}

/* caller must hold rcu readlock and none of the nf_conntrack_locks */
static void nf_ct_gc_expired(struct nf_conn *ct)
{
	if (!atomic_inc_not_zero(&ct->ct_general.use))
		return;

	if (nf_ct_should_gc(ct))
		nf_ct_kill(ct);

	nf_ct_put(ct);
}

/*
 * Warning :
 * - Caller must take a reference on returned object
 *   and recheck nf_ct_tuple_equal(tuple, &h->tuple)
 */
static struct nf_conntrack_tuple_hash *
____nf_conntrack_find(struct net *net, const struct nf_conntrack_zone *zone,
		      const struct nf_conntrack_tuple *tuple, u32 hash)
{
	struct nf_conntrack_tuple_hash *h;
	struct hlist_nulls_head *ct_hash;
	struct hlist_nulls_node *n;
	unsigned int bucket, hsize;

begin:
	nf_conntrack_get_ht(&ct_hash, &hsize);
	bucket = reciprocal_scale(hash, hsize);

	hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[bucket], hnnode) {
		struct nf_conn *ct;

		ct = nf_ct_tuplehash_to_ctrack(h);
		if (nf_ct_is_expired(ct)) {
			nf_ct_gc_expired(ct);
			continue;
		}

		if (nf_ct_is_dying(ct))
			continue;

		if (nf_ct_key_equal(h, tuple, zone, net))
			return h;
	}
	/*
	 * if the nulls value we got at the end of this lookup is
	 * not the expected one, we must restart lookup.
	 * We probably met an item that was moved to another chain.
	 */
	if (get_nulls_value(n) != bucket) {
		NF_CT_STAT_INC_ATOMIC(net, search_restart);
		goto begin;
	}

	return NULL;
}

/* Find a connection corresponding to a tuple. */
static struct nf_conntrack_tuple_hash *
__nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone,
			const struct nf_conntrack_tuple *tuple, u32 hash)
{
	struct nf_conntrack_tuple_hash *h;
	struct nf_conn *ct;

	rcu_read_lock();
begin:
	h = ____nf_conntrack_find(net, zone, tuple, hash);
	if (h) {
		ct = nf_ct_tuplehash_to_ctrack(h);
		if (unlikely(nf_ct_is_dying(ct) ||
			     !atomic_inc_not_zero(&ct->ct_general.use)))
			h = NULL;
		else {
			if (unlikely(!nf_ct_key_equal(h, tuple, zone, net))) {
				nf_ct_put(ct);
				goto begin;
			}
		}
	}
	rcu_read_unlock();

	return h;
}

struct nf_conntrack_tuple_hash *
nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone,
		      const struct nf_conntrack_tuple *tuple)
{
	return __nf_conntrack_find_get(net, zone, tuple,
				       hash_conntrack_raw(tuple, net));
}
EXPORT_SYMBOL_GPL(nf_conntrack_find_get);

static void __nf_conntrack_hash_insert(struct nf_conn *ct,
				       unsigned int hash,
				       unsigned int reply_hash)
{
	hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
			   &nf_conntrack_hash[hash]);
	hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode,
			   &nf_conntrack_hash[reply_hash]);
}

int
nf_conntrack_hash_check_insert(struct nf_conn *ct)
{
	const struct nf_conntrack_zone *zone;
	struct net *net = nf_ct_net(ct);
	unsigned int hash, reply_hash;
	struct nf_conntrack_tuple_hash *h;
	struct hlist_nulls_node *n;
	unsigned int sequence;

	zone = nf_ct_zone(ct);

	local_bh_disable();
	do {
		sequence = read_seqcount_begin(&nf_conntrack_generation);
		hash = hash_conntrack(net,
				      &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
		reply_hash = hash_conntrack(net,
					   &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
	} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));

	/* See if there's one in the list already, including reverse */
	hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode)
		if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
				    zone, net))
			goto out;

	hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode)
		if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
				    zone, net))
			goto out;

	smp_wmb();
	/* The caller holds a reference to this object */
	atomic_set(&ct->ct_general.use, 2);
	__nf_conntrack_hash_insert(ct, hash, reply_hash);
	nf_conntrack_double_unlock(hash, reply_hash);
	NF_CT_STAT_INC(net, insert);
	local_bh_enable();
	return 0;

out:
	nf_conntrack_double_unlock(hash, reply_hash);
	NF_CT_STAT_INC(net, insert_failed);
	local_bh_enable();
	return -EEXIST;
}
EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert);

static inline void nf_ct_acct_update(struct nf_conn *ct,
				     enum ip_conntrack_info ctinfo,
				     unsigned int len)
{
	struct nf_conn_acct *acct;

	acct = nf_conn_acct_find(ct);
	if (acct) {
		struct nf_conn_counter *counter = acct->counter;

		atomic64_inc(&counter[CTINFO2DIR(ctinfo)].packets);
		atomic64_add(len, &counter[CTINFO2DIR(ctinfo)].bytes);
	}
}

static void nf_ct_acct_merge(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
			     const struct nf_conn *loser_ct)
{
	struct nf_conn_acct *acct;

	acct = nf_conn_acct_find(loser_ct);
	if (acct) {
		struct nf_conn_counter *counter = acct->counter;
		unsigned int bytes;

		/* u32 should be fine since we must have seen one packet. */
		bytes = atomic64_read(&counter[CTINFO2DIR(ctinfo)].bytes);
		nf_ct_acct_update(ct, ctinfo, bytes);
	}
}

/* Resolve race on insertion if this protocol allows this. */
static int nf_ct_resolve_clash(struct net *net, struct sk_buff *skb,
			       enum ip_conntrack_info ctinfo,
			       struct nf_conntrack_tuple_hash *h)
{
	/* This is the conntrack entry already in hashes that won race. */
	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
	struct nf_conntrack_l4proto *l4proto;

	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
	if (l4proto->allow_clash &&
	    !nfct_nat(ct) &&
	    !nf_ct_is_dying(ct) &&
	    atomic_inc_not_zero(&ct->ct_general.use)) {
		nf_ct_acct_merge(ct, ctinfo, (struct nf_conn *)skb->nfct);
		nf_conntrack_put(skb->nfct);
		/* Assign conntrack already in hashes to this skbuff. Don't
		 * modify skb->nfctinfo to ensure consistent stateful filtering.
		 */
		skb->nfct = &ct->ct_general;
		return NF_ACCEPT;
	}
	NF_CT_STAT_INC(net, drop);
	return NF_DROP;
}

/* Confirm a connection given skb; places it in hash table */
int
__nf_conntrack_confirm(struct sk_buff *skb)
{
	const struct nf_conntrack_zone *zone;
	unsigned int hash, reply_hash;
	struct nf_conntrack_tuple_hash *h;
	struct nf_conn *ct;
	struct nf_conn_help *help;
	struct nf_conn_tstamp *tstamp;
	struct hlist_nulls_node *n;
	enum ip_conntrack_info ctinfo;
	struct net *net;
	unsigned int sequence;
	int ret = NF_DROP;

	ct = nf_ct_get(skb, &ctinfo);
	net = nf_ct_net(ct);

	/* ipt_REJECT uses nf_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;

	zone = nf_ct_zone(ct);
	local_bh_disable();

	do {
		sequence = read_seqcount_begin(&nf_conntrack_generation);
		/* reuse the hash saved before */
		hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev;
		hash = scale_hash(hash);
		reply_hash = hash_conntrack(net,
					   &ct->tuplehash[IP_CT_DIR_REPLY].tuple);

	} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));

	/* 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.
	 */
	/* NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 1); */

	/* No external references means no one else could have
	 * confirmed us.
	 */
	NF_CT_ASSERT(!nf_ct_is_confirmed(ct));
	pr_debug("Confirming conntrack %p\n", ct);
	/* We have to check the DYING flag after unlink to prevent
	 * a race against nf_ct_get_next_corpse() possibly called from
	 * user context, else we insert an already 'dead' hash, blocking
	 * further use of that particular connection -JM.
	 */
	nf_ct_del_from_dying_or_unconfirmed_list(ct);

	if (unlikely(nf_ct_is_dying(ct))) {
		nf_ct_add_to_dying_list(ct);
		goto dying;
	}

	/* 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. */
	hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode)
		if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
				    zone, net))
			goto out;

	hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode)
		if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
				    zone, net))
			goto out;

	/* Timer relative to confirmation time, not original
	   setting time, otherwise we'd get timer wrap in
	   weird delay cases. */
	ct->timeout += nfct_time_stamp;
	atomic_inc(&ct->ct_general.use);
	ct->status |= IPS_CONFIRMED;

	/* set conntrack timestamp, if enabled. */
	tstamp = nf_conn_tstamp_find(ct);
	if (tstamp) {
		if (skb->tstamp.tv64 == 0)
			__net_timestamp(skb);

		tstamp->start = ktime_to_ns(skb->tstamp);
	}
	/* Since the lookup is lockless, hash insertion must be done after
	 * starting the timer and setting the CONFIRMED bit. The RCU barriers
	 * guarantee that no other CPU can find the conntrack before the above
	 * stores are visible.
	 */
	__nf_conntrack_hash_insert(ct, hash, reply_hash);
	nf_conntrack_double_unlock(hash, reply_hash);
	local_bh_enable();

	help = nfct_help(ct);
	if (help && help->helper)
		nf_conntrack_event_cache(IPCT_HELPER, ct);

	nf_conntrack_event_cache(master_ct(ct) ?
				 IPCT_RELATED : IPCT_NEW, ct);
	return NF_ACCEPT;

out:
	nf_ct_add_to_dying_list(ct);
	ret = nf_ct_resolve_clash(net, skb, ctinfo, h);
dying:
	nf_conntrack_double_unlock(hash, reply_hash);
	NF_CT_STAT_INC(net, insert_failed);
	local_bh_enable();
	return ret;
}
EXPORT_SYMBOL_GPL(__nf_conntrack_confirm);

/* Returns true if a connection correspondings to the tuple (required
   for NAT). */
int
nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
			 const struct nf_conn *ignored_conntrack)
{
	struct net *net = nf_ct_net(ignored_conntrack);
	const struct nf_conntrack_zone *zone;
	struct nf_conntrack_tuple_hash *h;
	struct hlist_nulls_head *ct_hash;
	unsigned int hash, hsize;
	struct hlist_nulls_node *n;
	struct nf_conn *ct;

	zone = nf_ct_zone(ignored_conntrack);

	rcu_read_lock();
 begin:
	nf_conntrack_get_ht(&ct_hash, &hsize);
	hash = __hash_conntrack(net, tuple, hsize);

	hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[hash], hnnode) {
		ct = nf_ct_tuplehash_to_ctrack(h);

		if (ct == ignored_conntrack)
			continue;

		if (nf_ct_is_expired(ct)) {
			nf_ct_gc_expired(ct);
			continue;
		}

		if (nf_ct_key_equal(h, tuple, zone, net)) {
			NF_CT_STAT_INC_ATOMIC(net, found);
			rcu_read_unlock();
			return 1;
		}
	}

	if (get_nulls_value(n) != hash) {
		NF_CT_STAT_INC_ATOMIC(net, search_restart);
		goto begin;
	}

	rcu_read_unlock();

	return 0;
}
EXPORT_SYMBOL_GPL(nf_conntrack_tuple_taken);

#define NF_CT_EVICTION_RANGE	8

/* There's a small race here where we may free a just-assured
   connection.  Too bad: we're in trouble anyway. */
static unsigned int early_drop_list(struct net *net,
				    struct hlist_nulls_head *head)
{
	struct nf_conntrack_tuple_hash *h;
	struct hlist_nulls_node *n;
	unsigned int drops = 0;
	struct nf_conn *tmp;

	hlist_nulls_for_each_entry_rcu(h, n, head, hnnode) {
		tmp = nf_ct_tuplehash_to_ctrack(h);

		if (nf_ct_is_expired(tmp)) {
			nf_ct_gc_expired(tmp);
			continue;
		}

		if (test_bit(IPS_ASSURED_BIT, &tmp->status) ||
		    !net_eq(nf_ct_net(tmp), net) ||
		    nf_ct_is_dying(tmp))
			continue;

		if (!atomic_inc_not_zero(&tmp->ct_general.use))
			continue;

		/* kill only if still in same netns -- might have moved due to
		 * SLAB_DESTROY_BY_RCU rules.
		 *
		 * We steal the timer reference.  If that fails timer has
		 * already fired or someone else deleted it. Just drop ref
		 * and move to next entry.
		 */
		if (net_eq(nf_ct_net(tmp), net) &&
		    nf_ct_is_confirmed(tmp) &&
		    nf_ct_delete(tmp, 0, 0))
			drops++;

		nf_ct_put(tmp);
	}

	return drops;
}

static noinline int early_drop(struct net *net, unsigned int _hash)
{
	unsigned int i;

	for (i = 0; i < NF_CT_EVICTION_RANGE; i++) {
		struct hlist_nulls_head *ct_hash;
		unsigned int hash, hsize, drops;

		rcu_read_lock();
		nf_conntrack_get_ht(&ct_hash, &hsize);
		hash = reciprocal_scale(_hash++, hsize);

		drops = early_drop_list(net, &ct_hash[hash]);
		rcu_read_unlock();

		if (drops) {
			NF_CT_STAT_ADD_ATOMIC(net, early_drop, drops);
			return true;
		}
	}

	return false;
}

static void gc_worker(struct work_struct *work)
{
	unsigned int min_interval = max(HZ / GC_MAX_BUCKETS_DIV, 1u);
	unsigned int i, goal, buckets = 0, expired_count = 0;
	struct conntrack_gc_work *gc_work;
	unsigned int ratio, scanned = 0;
	unsigned long next_run;

	gc_work = container_of(work, struct conntrack_gc_work, dwork.work);

	goal = nf_conntrack_htable_size / GC_MAX_BUCKETS_DIV;
	i = gc_work->last_bucket;

	do {
		struct nf_conntrack_tuple_hash *h;
		struct hlist_nulls_head *ct_hash;
		struct hlist_nulls_node *n;
		unsigned int hashsz;
		struct nf_conn *tmp;

		i++;
		rcu_read_lock();

		nf_conntrack_get_ht(&ct_hash, &hashsz);
		if (i >= hashsz)
			i = 0;

		hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[i], hnnode) {
			tmp = nf_ct_tuplehash_to_ctrack(h);

			scanned++;
			if (nf_ct_is_expired(tmp)) {
				nf_ct_gc_expired(tmp);
				expired_count++;
				continue;
			}
		}

		/* could check get_nulls_value() here and restart if ct
		 * was moved to another chain.  But given gc is best-effort
		 * we will just continue with next hash slot.
		 */
		rcu_read_unlock();
		cond_resched_rcu_qs();
	} while (++buckets < goal);

	if (gc_work->exiting)
		return;

	/*
	 * Eviction will normally happen from the packet path, and not
	 * from this gc worker.
	 *
	 * This worker is only here to reap expired entries when system went
	 * idle after a busy period.
	 *
	 * The heuristics below are supposed to balance conflicting goals:
	 *
	 * 1. Minimize time until we notice a stale entry
	 * 2. Maximize scan intervals to not waste cycles
	 *
	 * Normally, expire ratio will be close to 0.
	 *
	 * As soon as a sizeable fraction of the entries have expired
	 * increase scan frequency.
	 */
	ratio = scanned ? expired_count * 100 / scanned : 0;
	if (ratio > GC_EVICT_RATIO) {
		gc_work->next_gc_run = min_interval;
	} else {
		unsigned int max = GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV;

		BUILD_BUG_ON((GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV) == 0);

		gc_work->next_gc_run += min_interval;
		if (gc_work->next_gc_run > max)
			gc_work->next_gc_run = max;
	}

	next_run = gc_work->next_gc_run;
	gc_work->last_bucket = i;
	queue_delayed_work(system_long_wq, &gc_work->dwork, next_run);
}

static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work)
{
	INIT_DELAYED_WORK(&gc_work->dwork, gc_worker);
	gc_work->next_gc_run = HZ;
	gc_work->exiting = false;
}

static struct nf_conn *
__nf_conntrack_alloc(struct net *net,
		     const struct nf_conntrack_zone *zone,
		     const struct nf_conntrack_tuple *orig,
		     const struct nf_conntrack_tuple *repl,
		     gfp_t gfp, u32 hash)
{
	struct nf_conn *ct;

	/* We don't want any race condition at early drop stage */
	atomic_inc(&net->ct.count);

	if (nf_conntrack_max &&
	    unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) {
		if (!early_drop(net, hash)) {
			atomic_dec(&net->ct.count);
			net_warn_ratelimited("nf_conntrack: table full, dropping packet\n");
			return ERR_PTR(-ENOMEM);
		}
	}

	/*
	 * Do not use kmem_cache_zalloc(), as this cache uses
	 * SLAB_DESTROY_BY_RCU.
	 */
	ct = kmem_cache_alloc(nf_conntrack_cachep, gfp);
	if (ct == NULL)
		goto out;

	spin_lock_init(&ct->lock);
	ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig;
	ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.pprev = NULL;
	ct->tuplehash[IP_CT_DIR_REPLY].tuple = *repl;
	/* save hash for reusing when confirming */
	*(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash;
	ct->status = 0;
	write_pnet(&ct->ct_net, net);
	memset(&ct->__nfct_init_offset[0], 0,
	       offsetof(struct nf_conn, proto) -
	       offsetof(struct nf_conn, __nfct_init_offset[0]));

	nf_ct_zone_add(ct, zone);

	/* Because we use RCU lookups, we set ct_general.use to zero before
	 * this is inserted in any list.
	 */
	atomic_set(&ct->ct_general.use, 0);
	return ct;
out:
	atomic_dec(&net->ct.count);
	return ERR_PTR(-ENOMEM);
}

struct nf_conn *nf_conntrack_alloc(struct net *net,
				   const struct nf_conntrack_zone *zone,
				   const struct nf_conntrack_tuple *orig,
				   const struct nf_conntrack_tuple *repl,
				   gfp_t gfp)
{
	return __nf_conntrack_alloc(net, zone, orig, repl, gfp, 0);
}
EXPORT_SYMBOL_GPL(nf_conntrack_alloc);

void nf_conntrack_free(struct nf_conn *ct)
{
	struct net *net = nf_ct_net(ct);

	/* A freed object has refcnt == 0, that's
	 * the golden rule for SLAB_DESTROY_BY_RCU
	 */
	NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 0);

	nf_ct_ext_destroy(ct);
	nf_ct_ext_free(ct);
	kmem_cache_free(nf_conntrack_cachep, ct);
	smp_mb__before_atomic();
	atomic_dec(&net->ct.count);
}
EXPORT_SYMBOL_GPL(nf_conntrack_free);


/* Allocate a new conntrack: we return -ENOMEM if classification
   failed due to stress.  Otherwise it really is unclassifiable. */
static struct nf_conntrack_tuple_hash *
init_conntrack(struct net *net, struct nf_conn *tmpl,
	       const struct nf_conntrack_tuple *tuple,
	       struct nf_conntrack_l3proto *l3proto,
	       struct nf_conntrack_l4proto *l4proto,
	       struct sk_buff *skb,
	       unsigned int dataoff, u32 hash)
{
	struct nf_conn *ct;
	struct nf_conn_help *help;
	struct nf_conntrack_tuple repl_tuple;
	struct nf_conntrack_ecache *ecache;
	struct nf_conntrack_expect *exp = NULL;
	const struct nf_conntrack_zone *zone;
	struct nf_conn_timeout *timeout_ext;
	struct nf_conntrack_zone tmp;
	unsigned int *timeouts;

	if (!nf_ct_invert_tuple(&repl_tuple, tuple, l3proto, l4proto)) {
		pr_debug("Can't invert tuple.\n");
		return NULL;
	}

	zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
	ct = __nf_conntrack_alloc(net, zone, tuple, &repl_tuple, GFP_ATOMIC,
				  hash);
	if (IS_ERR(ct))
		return (struct nf_conntrack_tuple_hash *)ct;

	if (!nf_ct_add_synproxy(ct, tmpl)) {
		nf_conntrack_free(ct);
		return ERR_PTR(-ENOMEM);
	}

	timeout_ext = tmpl ? nf_ct_timeout_find(tmpl) : NULL;
	if (timeout_ext) {
		timeouts = nf_ct_timeout_data(timeout_ext);
		if (unlikely(!timeouts))
			timeouts = l4proto->get_timeouts(net);
	} else {
		timeouts = l4proto->get_timeouts(net);
	}

	if (!l4proto->new(ct, skb, dataoff, timeouts)) {
		nf_conntrack_free(ct);
		pr_debug("can't track with proto module\n");
		return NULL;
	}

	if (timeout_ext)
		nf_ct_timeout_ext_add(ct, rcu_dereference(timeout_ext->timeout),
				      GFP_ATOMIC);

	nf_ct_acct_ext_add(ct, GFP_ATOMIC);
	nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
	nf_ct_labels_ext_add(ct);

	ecache = tmpl ? nf_ct_ecache_find(tmpl) : NULL;
	nf_ct_ecache_ext_add(ct, ecache ? ecache->ctmask : 0,
				 ecache ? ecache->expmask : 0,
			     GFP_ATOMIC);

	local_bh_disable();
	if (net->ct.expect_count) {
		spin_lock(&nf_conntrack_expect_lock);
		exp = nf_ct_find_expectation(net, zone, tuple);
		if (exp) {
			pr_debug("expectation arrives ct=%p exp=%p\n",
				 ct, exp);
			/* Welcome, Mr. Bond.  We've been expecting you... */
			__set_bit(IPS_EXPECTED_BIT, &ct->status);
			/* exp->master safe, refcnt bumped in nf_ct_find_expectation */
			ct->master = exp->master;
			if (exp->helper) {
				help = nf_ct_helper_ext_add(ct, exp->helper,
							    GFP_ATOMIC);
				if (help)
					rcu_assign_pointer(help->helper, exp->helper);
			}

#ifdef CONFIG_NF_CONNTRACK_MARK
			ct->mark = exp->master->mark;
#endif
#ifdef CONFIG_NF_CONNTRACK_SECMARK
			ct->secmark = exp->master->secmark;
#endif
			NF_CT_STAT_INC(net, expect_new);
		}
		spin_unlock(&nf_conntrack_expect_lock);
	}
	if (!exp)
		__nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC);

	/* Now it is inserted into the unconfirmed list, bump refcount */
	nf_conntrack_get(&ct->ct_general);
	nf_ct_add_to_unconfirmed_list(ct);

	local_bh_enable();

	if (exp) {
		if (exp->expectfn)
			exp->expectfn(ct, exp);
		nf_ct_expect_put(exp);
	}

	return &ct->tuplehash[IP_CT_DIR_ORIGINAL];
}

/* On success, returns conntrack ptr, sets skb->nfct and ctinfo */
static inline struct nf_conn *
resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
		  struct sk_buff *skb,
		  unsigned int dataoff,
		  u_int16_t l3num,
		  u_int8_t protonum,
		  struct nf_conntrack_l3proto *l3proto,
		  struct nf_conntrack_l4proto *l4proto,
		  int *set_reply,
		  enum ip_conntrack_info *ctinfo)
{
	const struct nf_conntrack_zone *zone;
	struct nf_conntrack_tuple tuple;
	struct nf_conntrack_tuple_hash *h;
	struct nf_conntrack_zone tmp;
	struct nf_conn *ct;
	u32 hash;

	if (!nf_ct_get_tuple(skb, skb_network_offset(skb),
			     dataoff, l3num, protonum, net, &tuple, l3proto,
			     l4proto)) {
		pr_debug("Can't get tuple\n");
		return NULL;
	}

	/* look for tuple match */
	zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
	hash = hash_conntrack_raw(&tuple, net);
	h = __nf_conntrack_find_get(net, zone, &tuple, hash);
	if (!h) {
		h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto,
				   skb, dataoff, hash);
		if (!h)
			return NULL;
		if (IS_ERR(h))
			return (void *)h;
	}
	ct = nf_ct_tuplehash_to_ctrack(h);

	/* It exists; we have (non-exclusive) reference. */
	if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) {
		*ctinfo = IP_CT_ESTABLISHED_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)) {
			pr_debug("normal packet for %p\n", ct);
			*ctinfo = IP_CT_ESTABLISHED;
		} else if (test_bit(IPS_EXPECTED_BIT, &ct->status)) {
			pr_debug("related packet for %p\n", ct);
			*ctinfo = IP_CT_RELATED;
		} else {
			pr_debug("new packet for %p\n", ct);
			*ctinfo = IP_CT_NEW;
		}
		*set_reply = 0;
	}
	skb->nfct = &ct->ct_general;
	skb->nfctinfo = *ctinfo;
	return ct;
}

unsigned int
nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
		struct sk_buff *skb)
{
	struct nf_conn *ct, *tmpl = NULL;
	enum ip_conntrack_info ctinfo;
	struct nf_conntrack_l3proto *l3proto;
	struct nf_conntrack_l4proto *l4proto;
	unsigned int *timeouts;
	unsigned int dataoff;
	u_int8_t protonum;
	int set_reply = 0;
	int ret;

	if (skb->nfct) {
		/* Previously seen (loopback or untracked)?  Ignore. */
		tmpl = (struct nf_conn *)skb->nfct;
		if (!nf_ct_is_template(tmpl)) {
			NF_CT_STAT_INC_ATOMIC(net, ignore);
			return NF_ACCEPT;
		}
		skb->nfct = NULL;
	}

	/* rcu_read_lock()ed by nf_hook_thresh */
	l3proto = __nf_ct_l3proto_find(pf);
	ret = l3proto->get_l4proto(skb, skb_network_offset(skb),
				   &dataoff, &protonum);
	if (ret <= 0) {
		pr_debug("not prepared to track yet or error occurred\n");
		NF_CT_STAT_INC_ATOMIC(net, error);
		NF_CT_STAT_INC_ATOMIC(net, invalid);
		ret = -ret;
		goto out;
	}

	l4proto = __nf_ct_l4proto_find(pf, protonum);

	/* 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 (l4proto->error != NULL) {
		ret = l4proto->error(net, tmpl, skb, dataoff, &ctinfo,
				     pf, hooknum);
		if (ret <= 0) {
			NF_CT_STAT_INC_ATOMIC(net, error);
			NF_CT_STAT_INC_ATOMIC(net, invalid);
			ret = -ret;
			goto out;
		}
		/* ICMP[v6] protocol trackers may assign one conntrack. */
		if (skb->nfct)
			goto out;
	}

	ct = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum,
			       l3proto, l4proto, &set_reply, &ctinfo);
	if (!ct) {
		/* Not valid part of a connection */
		NF_CT_STAT_INC_ATOMIC(net, invalid);
		ret = NF_ACCEPT;
		goto out;
	}

	if (IS_ERR(ct)) {
		/* Too stressed to deal. */
		NF_CT_STAT_INC_ATOMIC(net, drop);
		ret = NF_DROP;
		goto out;
	}

	NF_CT_ASSERT(skb->nfct);

	/* Decide what timeout policy we want to apply to this flow. */
	timeouts = nf_ct_timeout_lookup(net, ct, l4proto);

	ret = l4proto->packet(ct, skb, dataoff, ctinfo, pf, hooknum, timeouts);
	if (ret <= 0) {
		/* Invalid: inverse of the return code tells
		 * the netfilter core what to do */
		pr_debug("nf_conntrack_in: Can't track with proto module\n");
		nf_conntrack_put(skb->nfct);
		skb->nfct = NULL;
		NF_CT_STAT_INC_ATOMIC(net, invalid);
		if (ret == -NF_DROP)
			NF_CT_STAT_INC_ATOMIC(net, drop);
		ret = -ret;
		goto out;
	}

	if (set_reply && !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status))
		nf_conntrack_event_cache(IPCT_REPLY, ct);
out:
	if (tmpl) {
		/* Special case: we have to repeat this hook, assign the
		 * template again to this packet. We assume that this packet
		 * has no conntrack assigned. This is used by nf_ct_tcp. */
		if (ret == NF_REPEAT)
			skb->nfct = (struct nf_conntrack *)tmpl;
		else
			nf_ct_put(tmpl);
	}

	return ret;
}
EXPORT_SYMBOL_GPL(nf_conntrack_in);

bool nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse,
			  const struct nf_conntrack_tuple *orig)
{
	bool ret;

	rcu_read_lock();
	ret = nf_ct_invert_tuple(inverse, orig,
				 __nf_ct_l3proto_find(orig->src.l3num),
				 __nf_ct_l4proto_find(orig->src.l3num,
						      orig->dst.protonum));
	rcu_read_unlock();
	return ret;
}
EXPORT_SYMBOL_GPL(nf_ct_invert_tuplepr);

/* Alter reply tuple (maybe alter helper).  This is for NAT, and is
   implicitly racy: see __nf_conntrack_confirm */
void nf_conntrack_alter_reply(struct nf_conn *ct,
			      const struct nf_conntrack_tuple *newreply)
{
	struct nf_conn_help *help = nfct_help(ct);

	/* Should be unconfirmed, so not in hash table yet */
	NF_CT_ASSERT(!nf_ct_is_confirmed(ct));

	pr_debug("Altering reply tuple of %p to ", ct);
	nf_ct_dump_tuple(newreply);

	ct->tuplehash[IP_CT_DIR_REPLY].tuple = *newreply;
	if (ct->master || (help && !hlist_empty(&help->expectations)))
		return;

	rcu_read_lock();
	__nf_ct_try_assign_helper(ct, NULL, GFP_ATOMIC);
	rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(nf_conntrack_alter_reply);

/* Refresh conntrack for this many jiffies and do accounting if do_acct is 1 */
void __nf_ct_refresh_acct(struct nf_conn *ct,
			  enum ip_conntrack_info ctinfo,
			  const struct sk_buff *skb,
			  unsigned long extra_jiffies,
			  int do_acct)
{
	NF_CT_ASSERT(skb);

	/* Only update if this is not a fixed timeout */
	if (test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status))
		goto acct;

	/* If not in hash table, timer will not be active yet */
	if (nf_ct_is_confirmed(ct))
		extra_jiffies += nfct_time_stamp;

	ct->timeout = extra_jiffies;
acct:
	if (do_acct)
		nf_ct_acct_update(ct, ctinfo, skb->len);
}
EXPORT_SYMBOL_GPL(__nf_ct_refresh_acct);

bool nf_ct_kill_acct(struct nf_conn *ct,
		     enum ip_conntrack_info ctinfo,
		     const struct sk_buff *skb)
{
	nf_ct_acct_update(ct, ctinfo, skb->len);

	return nf_ct_delete(ct, 0, 0);
}
EXPORT_SYMBOL_GPL(nf_ct_kill_acct);

#if IS_ENABLED(CONFIG_NF_CT_NETLINK)

#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_conntrack.h>
#include <linux/mutex.h>

/* 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 nf_ct_port_tuple_to_nlattr(struct sk_buff *skb,
			       const struct nf_conntrack_tuple *tuple)
{
	if (nla_put_be16(skb, CTA_PROTO_SRC_PORT, tuple->src.u.tcp.port) ||
	    nla_put_be16(skb, CTA_PROTO_DST_PORT, tuple->dst.u.tcp.port))
		goto nla_put_failure;
	return 0;

nla_put_failure:
	return -1;
}
EXPORT_SYMBOL_GPL(nf_ct_port_tuple_to_nlattr);

const struct nla_policy nf_ct_port_nla_policy[CTA_PROTO_MAX+1] = {
	[CTA_PROTO_SRC_PORT]  = { .type = NLA_U16 },
	[CTA_PROTO_DST_PORT]  = { .type = NLA_U16 },
};
EXPORT_SYMBOL_GPL(nf_ct_port_nla_policy);

int nf_ct_port_nlattr_to_tuple(struct nlattr *tb[],
			       struct nf_conntrack_tuple *t)
{
	if (!tb[CTA_PROTO_SRC_PORT] || !tb[CTA_PROTO_DST_PORT])
		return -EINVAL;

	t->src.u.tcp.port = nla_get_be16(tb[CTA_PROTO_SRC_PORT]);
	t->dst.u.tcp.port = nla_get_be16(tb[CTA_PROTO_DST_PORT]);

	return 0;
}
EXPORT_SYMBOL_GPL(nf_ct_port_nlattr_to_tuple);

int nf_ct_port_nlattr_tuple_size(void)
{
	return nla_policy_len(nf_ct_port_nla_policy, CTA_PROTO_MAX + 1);
}
EXPORT_SYMBOL_GPL(nf_ct_port_nlattr_tuple_size);
#endif

/* Used by ipt_REJECT and ip6t_REJECT. */
static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb)
{
	struct nf_conn *ct;
	enum ip_conntrack_info ctinfo;

	/* This ICMP is in reverse direction to the packet which caused it */
	ct = nf_ct_get(skb, &ctinfo);
	if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL)
		ctinfo = IP_CT_RELATED_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);
}

/* Bring out ya dead! */
static struct nf_conn *
get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data),
		void *data, unsigned int *bucket)
{
	struct nf_conntrack_tuple_hash *h;
	struct nf_conn *ct;
	struct hlist_nulls_node *n;
	int cpu;
	spinlock_t *lockp;

	for (; *bucket < nf_conntrack_htable_size; (*bucket)++) {
		lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS];
		local_bh_disable();
		nf_conntrack_lock(lockp);
		if (*bucket < nf_conntrack_htable_size) {
			hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[*bucket], hnnode) {
				if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
					continue;
				ct = nf_ct_tuplehash_to_ctrack(h);
				if (net_eq(nf_ct_net(ct), net) &&
				    iter(ct, data))
					goto found;
			}
		}
		spin_unlock(lockp);
		local_bh_enable();
		cond_resched();
	}

	for_each_possible_cpu(cpu) {
		struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);

		spin_lock_bh(&pcpu->lock);
		hlist_nulls_for_each_entry(h, n, &pcpu->unconfirmed, hnnode) {
			ct = nf_ct_tuplehash_to_ctrack(h);
			if (iter(ct, data))
				set_bit(IPS_DYING_BIT, &ct->status);
		}
		spin_unlock_bh(&pcpu->lock);
		cond_resched();
	}
	return NULL;
found:
	atomic_inc(&ct->ct_general.use);
	spin_unlock(lockp);
	local_bh_enable();
	return ct;
}

void nf_ct_iterate_cleanup(struct net *net,
			   int (*iter)(struct nf_conn *i, void *data),
			   void *data, u32 portid, int report)
{
	struct nf_conn *ct;
	unsigned int bucket = 0;

	might_sleep();

	if (atomic_read(&net->ct.count) == 0)
		return;

	while ((ct = get_next_corpse(net, iter, data, &bucket)) != NULL) {
		/* Time to push up daises... */

		nf_ct_delete(ct, portid, report);
		nf_ct_put(ct);
		cond_resched();
	}
}
EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup);

static int kill_all(struct nf_conn *i, void *data)
{
	return 1;
}

void nf_ct_free_hashtable(void *hash, unsigned int size)
{
	if (is_vmalloc_addr(hash))
		vfree(hash);
	else
		free_pages((unsigned long)hash,
			   get_order(sizeof(struct hlist_head) * size));
}
EXPORT_SYMBOL_GPL(nf_ct_free_hashtable);

static int untrack_refs(void)
{
	int cnt = 0, cpu;

	for_each_possible_cpu(cpu) {
		struct nf_conn *ct = &per_cpu(nf_conntrack_untracked, cpu);

		cnt += atomic_read(&ct->ct_general.use) - 1;
	}
	return cnt;
}

void nf_conntrack_cleanup_start(void)
{
	conntrack_gc_work.exiting = true;
	RCU_INIT_POINTER(ip_ct_attach, NULL);
}

void nf_conntrack_cleanup_end(void)
{
	RCU_INIT_POINTER(nf_ct_destroy, NULL);
	while (untrack_refs() > 0)
		schedule();

	cancel_delayed_work_sync(&conntrack_gc_work.dwork);
	nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size);

	nf_conntrack_proto_fini();
	nf_conntrack_seqadj_fini();
	nf_conntrack_labels_fini();
	nf_conntrack_helper_fini();
	nf_conntrack_timeout_fini();
	nf_conntrack_ecache_fini();
	nf_conntrack_tstamp_fini();
	nf_conntrack_acct_fini();
	nf_conntrack_expect_fini();

	kmem_cache_destroy(nf_conntrack_cachep);
}

/*
 * Mishearing the voices in his head, our hero wonders how he's
 * supposed to kill the mall.
 */
void nf_conntrack_cleanup_net(struct net *net)
{
	LIST_HEAD(single);

	list_add(&net->exit_list, &single);
	nf_conntrack_cleanup_net_list(&single);
}

void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list)
{
	int busy;
	struct net *net;

	/*
	 * This makes sure all current packets have passed through
	 *  netfilter framework.  Roll on, two-stage module
	 *  delete...
	 */
	synchronize_net();
i_see_dead_people:
	busy = 0;
	list_for_each_entry(net, net_exit_list, exit_list) {
		nf_ct_iterate_cleanup(net, kill_all, NULL, 0, 0);
		if (atomic_read(&net->ct.count) != 0)
			busy = 1;
	}
	if (busy) {
		schedule();
		goto i_see_dead_people;
	}

	list_for_each_entry(net, net_exit_list, exit_list) {
		nf_conntrack_proto_pernet_fini(net);
		nf_conntrack_helper_pernet_fini(net);
		nf_conntrack_ecache_pernet_fini(net);
		nf_conntrack_tstamp_pernet_fini(net);
		nf_conntrack_acct_pernet_fini(net);
		nf_conntrack_expect_pernet_fini(net);
		free_percpu(net->ct.stat);
		free_percpu(net->ct.pcpu_lists);
	}
}

void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls)
{
	struct hlist_nulls_head *hash;
	unsigned int nr_slots, i;
	size_t sz;

	if (*sizep > (UINT_MAX / sizeof(struct hlist_nulls_head)))
		return NULL;

	BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head));
	nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head));

	if (nr_slots > (UINT_MAX / sizeof(struct hlist_nulls_head)))
		return NULL;

	sz = nr_slots * sizeof(struct hlist_nulls_head);
	hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO,
					get_order(sz));
	if (!hash)
		hash = vzalloc(sz);

	if (hash && nulls)
		for (i = 0; i < nr_slots; i++)
			INIT_HLIST_NULLS_HEAD(&hash[i], i);

	return hash;
}
EXPORT_SYMBOL_GPL(nf_ct_alloc_hashtable);

int nf_conntrack_hash_resize(unsigned int hashsize)
{
	int i, bucket;
	unsigned int old_size;
	struct hlist_nulls_head *hash, *old_hash;
	struct nf_conntrack_tuple_hash *h;
	struct nf_conn *ct;

	if (!hashsize)
		return -EINVAL;

	hash = nf_ct_alloc_hashtable(&hashsize, 1);
	if (!hash)
		return -ENOMEM;

	old_size = nf_conntrack_htable_size;
	if (old_size == hashsize) {
		nf_ct_free_hashtable(hash, hashsize);
		return 0;
	}

	local_bh_disable();
	nf_conntrack_all_lock();
	write_seqcount_begin(&nf_conntrack_generation);

	/* Lookups in the old hash might happen in parallel, which means we
	 * might get false negatives during connection lookup. New connections
	 * created because of a false negative won't make it into the hash
	 * though since that required taking the locks.
	 */

	for (i = 0; i < nf_conntrack_htable_size; i++) {
		while (!hlist_nulls_empty(&nf_conntrack_hash[i])) {
			h = hlist_nulls_entry(nf_conntrack_hash[i].first,
					      struct nf_conntrack_tuple_hash, hnnode);
			ct = nf_ct_tuplehash_to_ctrack(h);
			hlist_nulls_del_rcu(&h->hnnode);
			bucket = __hash_conntrack(nf_ct_net(ct),
						  &h->tuple, hashsize);
			hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]);
		}
	}
	old_size = nf_conntrack_htable_size;
	old_hash = nf_conntrack_hash;

	nf_conntrack_hash = hash;
	nf_conntrack_htable_size = hashsize;

	write_seqcount_end(&nf_conntrack_generation);
	nf_conntrack_all_unlock();
	local_bh_enable();

	synchronize_net();
	nf_ct_free_hashtable(old_hash, old_size);
	return 0;
}

int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
{
	unsigned int hashsize;
	int rc;

	if (current->nsproxy->net_ns != &init_net)
		return -EOPNOTSUPP;

	/* On boot, we can set this without any fancy locking. */
	if (!nf_conntrack_htable_size)
		return param_set_uint(val, kp);

	rc = kstrtouint(val, 0, &hashsize);
	if (rc)
		return rc;

	return nf_conntrack_hash_resize(hashsize);
}
EXPORT_SYMBOL_GPL(nf_conntrack_set_hashsize);

module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint,
		  &nf_conntrack_htable_size, 0600);

void nf_ct_untracked_status_or(unsigned long bits)
{
	int cpu;

	for_each_possible_cpu(cpu)
		per_cpu(nf_conntrack_untracked, cpu).status |= bits;
}
EXPORT_SYMBOL_GPL(nf_ct_untracked_status_or);

int nf_conntrack_init_start(void)
{
	int max_factor = 8;
	int ret = -ENOMEM;
	int i, cpu;

	seqcount_init(&nf_conntrack_generation);

	for (i = 0; i < CONNTRACK_LOCKS; i++)
		spin_lock_init(&nf_conntrack_locks[i]);

	if (!nf_conntrack_htable_size) {
		/* Idea from tcp.c: use 1/16384 of memory.
		 * On i386: 32MB machine has 512 buckets.
		 * >= 1GB machines have 16384 buckets.
		 * >= 4GB machines have 65536 buckets.
		 */
		nf_conntrack_htable_size
			= (((totalram_pages << PAGE_SHIFT) / 16384)
			   / sizeof(struct hlist_head));
		if (totalram_pages > (4 * (1024 * 1024 * 1024 / PAGE_SIZE)))
			nf_conntrack_htable_size = 65536;
		else if (totalram_pages > (1024 * 1024 * 1024 / PAGE_SIZE))
			nf_conntrack_htable_size = 16384;
		if (nf_conntrack_htable_size < 32)
			nf_conntrack_htable_size = 32;

		/* Use a max. factor of four by default to get the same max as
		 * with the old struct list_heads. When a table size is given
		 * we use the old value of 8 to avoid reducing the max.
		 * entries. */
		max_factor = 4;
	}

	nf_conntrack_hash = nf_ct_alloc_hashtable(&nf_conntrack_htable_size, 1);
	if (!nf_conntrack_hash)
		return -ENOMEM;

	nf_conntrack_max = max_factor * nf_conntrack_htable_size;

	nf_conntrack_cachep = kmem_cache_create("nf_conntrack",
						sizeof(struct nf_conn), 0,
						SLAB_DESTROY_BY_RCU | SLAB_HWCACHE_ALIGN, NULL);
	if (!nf_conntrack_cachep)
		goto err_cachep;

	printk(KERN_INFO "nf_conntrack version %s (%u buckets, %d max)\n",
	       NF_CONNTRACK_VERSION, nf_conntrack_htable_size,
	       nf_conntrack_max);

	ret = nf_conntrack_expect_init();
	if (ret < 0)
		goto err_expect;

	ret = nf_conntrack_acct_init();
	if (ret < 0)
		goto err_acct;

	ret = nf_conntrack_tstamp_init();
	if (ret < 0)
		goto err_tstamp;

	ret = nf_conntrack_ecache_init();
	if (ret < 0)
		goto err_ecache;

	ret = nf_conntrack_timeout_init();
	if (ret < 0)
		goto err_timeout;

	ret = nf_conntrack_helper_init();
	if (ret < 0)
		goto err_helper;

	ret = nf_conntrack_labels_init();
	if (ret < 0)
		goto err_labels;

	ret = nf_conntrack_seqadj_init();
	if (ret < 0)
		goto err_seqadj;

	ret = nf_conntrack_proto_init();
	if (ret < 0)
		goto err_proto;

	/* Set up fake conntrack: to never be deleted, not in any hashes */
	for_each_possible_cpu(cpu) {
		struct nf_conn *ct = &per_cpu(nf_conntrack_untracked, cpu);
		write_pnet(&ct->ct_net, &init_net);
		atomic_set(&ct->ct_general.use, 1);
	}
	/*  - and look it like as a confirmed connection */
	nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED);

	conntrack_gc_work_init(&conntrack_gc_work);
	queue_delayed_work(system_long_wq, &conntrack_gc_work.dwork, HZ);

	return 0;

err_proto:
	nf_conntrack_seqadj_fini();
err_seqadj:
	nf_conntrack_labels_fini();
err_labels:
	nf_conntrack_helper_fini();
err_helper:
	nf_conntrack_timeout_fini();
err_timeout:
	nf_conntrack_ecache_fini();
err_ecache:
	nf_conntrack_tstamp_fini();
err_tstamp:
	nf_conntrack_acct_fini();
err_acct:
	nf_conntrack_expect_fini();
err_expect:
	kmem_cache_destroy(nf_conntrack_cachep);
err_cachep:
	nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size);
	return ret;
}

void nf_conntrack_init_end(void)
{
	/* For use by REJECT target */
	RCU_INIT_POINTER(ip_ct_attach, nf_conntrack_attach);
	RCU_INIT_POINTER(nf_ct_destroy, destroy_conntrack);
}

/*
 * We need to use special "null" values, not used in hash table
 */
#define UNCONFIRMED_NULLS_VAL	((1<<30)+0)
#define DYING_NULLS_VAL		((1<<30)+1)
#define TEMPLATE_NULLS_VAL	((1<<30)+2)

int nf_conntrack_init_net(struct net *net)
{
	int ret = -ENOMEM;
	int cpu;

	atomic_set(&net->ct.count, 0);

	net->ct.pcpu_lists = alloc_percpu(struct ct_pcpu);
	if (!net->ct.pcpu_lists)
		goto err_stat;

	for_each_possible_cpu(cpu) {
		struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);

		spin_lock_init(&pcpu->lock);
		INIT_HLIST_NULLS_HEAD(&pcpu->unconfirmed, UNCONFIRMED_NULLS_VAL);
		INIT_HLIST_NULLS_HEAD(&pcpu->dying, DYING_NULLS_VAL);
	}

	net->ct.stat = alloc_percpu(struct ip_conntrack_stat);
	if (!net->ct.stat)
		goto err_pcpu_lists;

	ret = nf_conntrack_expect_pernet_init(net);
	if (ret < 0)
		goto err_expect;
	ret = nf_conntrack_acct_pernet_init(net);
	if (ret < 0)
		goto err_acct;
	ret = nf_conntrack_tstamp_pernet_init(net);
	if (ret < 0)
		goto err_tstamp;
	ret = nf_conntrack_ecache_pernet_init(net);
	if (ret < 0)
		goto err_ecache;
	ret = nf_conntrack_helper_pernet_init(net);
	if (ret < 0)
		goto err_helper;
	ret = nf_conntrack_proto_pernet_init(net);
	if (ret < 0)
		goto err_proto;
	return 0;

err_proto:
	nf_conntrack_helper_pernet_fini(net);
err_helper:
	nf_conntrack_ecache_pernet_fini(net);
err_ecache:
	nf_conntrack_tstamp_pernet_fini(net);
err_tstamp:
	nf_conntrack_acct_pernet_fini(net);
err_acct:
	nf_conntrack_expect_pernet_fini(net);
err_expect:
	free_percpu(net->ct.stat);
err_pcpu_lists:
	free_percpu(net->ct.pcpu_lists);
err_stat:
	return ret;
}