aboutsummaryrefslogtreecommitdiffstats
path: root/net/netfilter/ipvs/ip_vs_core.c
blob: 5d2b806a862e6834ff6c61aee5c0e0a899bbe4b8 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
/*
 * IPVS         An implementation of the IP virtual server support for the
 *              LINUX operating system.  IPVS is now implemented as a module
 *              over the Netfilter framework. IPVS can be used to build a
 *              high-performance and highly available server based on a
 *              cluster of servers.
 *
 * Authors:     Wensong Zhang <wensong@linuxvirtualserver.org>
 *              Peter Kese <peter.kese@ijs.si>
 *              Julian Anastasov <ja@ssi.bg>
 *
 *              This program is free software; you can redistribute it and/or
 *              modify it under the terms of the GNU General Public License
 *              as published by the Free Software Foundation; either version
 *              2 of the License, or (at your option) any later version.
 *
 * The IPVS code for kernel 2.2 was done by Wensong Zhang and Peter Kese,
 * with changes/fixes from Julian Anastasov, Lars Marowsky-Bree, Horms
 * and others.
 *
 * Changes:
 *	Paul `Rusty' Russell		properly handle non-linear skbs
 *	Harald Welte			don't use nfcache
 *
 */

#define KMSG_COMPONENT "IPVS"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/sctp.h>
#include <linux/icmp.h>
#include <linux/slab.h>

#include <net/ip.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/icmp.h>                   /* for icmp_send */
#include <net/route.h>
#include <net/ip6_checksum.h>
#include <net/netns/generic.h>		/* net_generic() */

#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>

#ifdef CONFIG_IP_VS_IPV6
#include <net/ipv6.h>
#include <linux/netfilter_ipv6.h>
#include <net/ip6_route.h>
#endif

#include <net/ip_vs.h>


EXPORT_SYMBOL(register_ip_vs_scheduler);
EXPORT_SYMBOL(unregister_ip_vs_scheduler);
EXPORT_SYMBOL(ip_vs_proto_name);
EXPORT_SYMBOL(ip_vs_conn_new);
EXPORT_SYMBOL(ip_vs_conn_in_get);
EXPORT_SYMBOL(ip_vs_conn_out_get);
#ifdef CONFIG_IP_VS_PROTO_TCP
EXPORT_SYMBOL(ip_vs_tcp_conn_listen);
#endif
EXPORT_SYMBOL(ip_vs_conn_put);
#ifdef CONFIG_IP_VS_DEBUG
EXPORT_SYMBOL(ip_vs_get_debug_level);
#endif

static int ip_vs_net_id __read_mostly;
/* netns cnt used for uniqueness */
static atomic_t ipvs_netns_cnt = ATOMIC_INIT(0);

/* ID used in ICMP lookups */
#define icmp_id(icmph)          (((icmph)->un).echo.id)
#define icmpv6_id(icmph)        (icmph->icmp6_dataun.u_echo.identifier)

const char *ip_vs_proto_name(unsigned int proto)
{
	static char buf[20];

	switch (proto) {
	case IPPROTO_IP:
		return "IP";
	case IPPROTO_UDP:
		return "UDP";
	case IPPROTO_TCP:
		return "TCP";
	case IPPROTO_SCTP:
		return "SCTP";
	case IPPROTO_ICMP:
		return "ICMP";
#ifdef CONFIG_IP_VS_IPV6
	case IPPROTO_ICMPV6:
		return "ICMPv6";
#endif
	default:
		sprintf(buf, "IP_%u", proto);
		return buf;
	}
}

void ip_vs_init_hash_table(struct list_head *table, int rows)
{
	while (--rows >= 0)
		INIT_LIST_HEAD(&table[rows]);
}

static inline void
ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
{
	struct ip_vs_dest *dest = cp->dest;
	struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));

	if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
		struct ip_vs_cpu_stats *s;
		struct ip_vs_service *svc;

		s = this_cpu_ptr(dest->stats.cpustats);
		u64_stats_update_begin(&s->syncp);
		s->cnt.inpkts++;
		s->cnt.inbytes += skb->len;
		u64_stats_update_end(&s->syncp);

		rcu_read_lock();
		svc = rcu_dereference(dest->svc);
		s = this_cpu_ptr(svc->stats.cpustats);
		u64_stats_update_begin(&s->syncp);
		s->cnt.inpkts++;
		s->cnt.inbytes += skb->len;
		u64_stats_update_end(&s->syncp);
		rcu_read_unlock();

		s = this_cpu_ptr(ipvs->tot_stats.cpustats);
		u64_stats_update_begin(&s->syncp);
		s->cnt.inpkts++;
		s->cnt.inbytes += skb->len;
		u64_stats_update_end(&s->syncp);
	}
}


static inline void
ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
{
	struct ip_vs_dest *dest = cp->dest;
	struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));

	if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
		struct ip_vs_cpu_stats *s;
		struct ip_vs_service *svc;

		s = this_cpu_ptr(dest->stats.cpustats);
		u64_stats_update_begin(&s->syncp);
		s->cnt.outpkts++;
		s->cnt.outbytes += skb->len;
		u64_stats_update_end(&s->syncp);

		rcu_read_lock();
		svc = rcu_dereference(dest->svc);
		s = this_cpu_ptr(svc->stats.cpustats);
		u64_stats_update_begin(&s->syncp);
		s->cnt.outpkts++;
		s->cnt.outbytes += skb->len;
		u64_stats_update_end(&s->syncp);
		rcu_read_unlock();

		s = this_cpu_ptr(ipvs->tot_stats.cpustats);
		u64_stats_update_begin(&s->syncp);
		s->cnt.outpkts++;
		s->cnt.outbytes += skb->len;
		u64_stats_update_end(&s->syncp);
	}
}


static inline void
ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
{
	struct netns_ipvs *ipvs = net_ipvs(svc->net);
	struct ip_vs_cpu_stats *s;

	s = this_cpu_ptr(cp->dest->stats.cpustats);
	u64_stats_update_begin(&s->syncp);
	s->cnt.conns++;
	u64_stats_update_end(&s->syncp);

	s = this_cpu_ptr(svc->stats.cpustats);
	u64_stats_update_begin(&s->syncp);
	s->cnt.conns++;
	u64_stats_update_end(&s->syncp);

	s = this_cpu_ptr(ipvs->tot_stats.cpustats);
	u64_stats_update_begin(&s->syncp);
	s->cnt.conns++;
	u64_stats_update_end(&s->syncp);
}


static inline void
ip_vs_set_state(struct ip_vs_conn *cp, int direction,
		const struct sk_buff *skb,
		struct ip_vs_proto_data *pd)
{
	if (likely(pd->pp->state_transition))
		pd->pp->state_transition(cp, direction, skb, pd);
}

static inline int
ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc,
			      struct sk_buff *skb, int protocol,
			      const union nf_inet_addr *caddr, __be16 cport,
			      const union nf_inet_addr *vaddr, __be16 vport,
			      struct ip_vs_conn_param *p)
{
	ip_vs_conn_fill_param(svc->net, svc->af, protocol, caddr, cport, vaddr,
			      vport, p);
	p->pe = rcu_dereference(svc->pe);
	if (p->pe && p->pe->fill_param)
		return p->pe->fill_param(p, skb);

	return 0;
}

/*
 *  IPVS persistent scheduling function
 *  It creates a connection entry according to its template if exists,
 *  or selects a server and creates a connection entry plus a template.
 *  Locking: we are svc user (svc->refcnt), so we hold all dests too
 *  Protocols supported: TCP, UDP
 */
static struct ip_vs_conn *
ip_vs_sched_persist(struct ip_vs_service *svc,
		    struct sk_buff *skb, __be16 src_port, __be16 dst_port,
		    int *ignored, struct ip_vs_iphdr *iph)
{
	struct ip_vs_conn *cp = NULL;
	struct ip_vs_dest *dest;
	struct ip_vs_conn *ct;
	__be16 dport = 0;		/* destination port to forward */
	unsigned int flags;
	struct ip_vs_conn_param param;
	const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) };
	union nf_inet_addr snet;	/* source network of the client,
					   after masking */

	/* Mask saddr with the netmask to adjust template granularity */
#ifdef CONFIG_IP_VS_IPV6
	if (svc->af == AF_INET6)
		ipv6_addr_prefix(&snet.in6, &iph->saddr.in6,
				 (__force __u32) svc->netmask);
	else
#endif
		snet.ip = iph->saddr.ip & svc->netmask;

	IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u "
		      "mnet %s\n",
		      IP_VS_DBG_ADDR(svc->af, &iph->saddr), ntohs(src_port),
		      IP_VS_DBG_ADDR(svc->af, &iph->daddr), ntohs(dst_port),
		      IP_VS_DBG_ADDR(svc->af, &snet));

	/*
	 * As far as we know, FTP is a very complicated network protocol, and
	 * it uses control connection and data connections. For active FTP,
	 * FTP server initialize data connection to the client, its source port
	 * is often 20. For passive FTP, FTP server tells the clients the port
	 * that it passively listens to,  and the client issues the data
	 * connection. In the tunneling or direct routing mode, the load
	 * balancer is on the client-to-server half of connection, the port
	 * number is unknown to the load balancer. So, a conn template like
	 * <caddr, 0, vaddr, 0, daddr, 0> is created for persistent FTP
	 * service, and a template like <caddr, 0, vaddr, vport, daddr, dport>
	 * is created for other persistent services.
	 */
	{
		int protocol = iph->protocol;
		const union nf_inet_addr *vaddr = &iph->daddr;
		__be16 vport = 0;

		if (dst_port == svc->port) {
			/* non-FTP template:
			 * <protocol, caddr, 0, vaddr, vport, daddr, dport>
			 * FTP template:
			 * <protocol, caddr, 0, vaddr, 0, daddr, 0>
			 */
			if (svc->port != FTPPORT)
				vport = dst_port;
		} else {
			/* Note: persistent fwmark-based services and
			 * persistent port zero service are handled here.
			 * fwmark template:
			 * <IPPROTO_IP,caddr,0,fwmark,0,daddr,0>
			 * port zero template:
			 * <protocol,caddr,0,vaddr,0,daddr,0>
			 */
			if (svc->fwmark) {
				protocol = IPPROTO_IP;
				vaddr = &fwmark;
			}
		}
		/* return *ignored = -1 so NF_DROP can be used */
		if (ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0,
						  vaddr, vport, &param) < 0) {
			*ignored = -1;
			return NULL;
		}
	}

	/* Check if a template already exists */
	ct = ip_vs_ct_in_get(&param);
	if (!ct || !ip_vs_check_template(ct)) {
		struct ip_vs_scheduler *sched;

		/*
		 * No template found or the dest of the connection
		 * template is not available.
		 * return *ignored=0 i.e. ICMP and NF_DROP
		 */
		sched = rcu_dereference(svc->scheduler);
		dest = sched->schedule(svc, skb, iph);
		if (!dest) {
			IP_VS_DBG(1, "p-schedule: no dest found.\n");
			kfree(param.pe_data);
			*ignored = 0;
			return NULL;
		}

		if (dst_port == svc->port && svc->port != FTPPORT)
			dport = dest->port;

		/* Create a template
		 * This adds param.pe_data to the template,
		 * and thus param.pe_data will be destroyed
		 * when the template expires */
		ct = ip_vs_conn_new(&param, dest->af, &dest->addr, dport,
				    IP_VS_CONN_F_TEMPLATE, dest, skb->mark);
		if (ct == NULL) {
			kfree(param.pe_data);
			*ignored = -1;
			return NULL;
		}

		ct->timeout = svc->timeout;
	} else {
		/* set destination with the found template */
		dest = ct->dest;
		kfree(param.pe_data);
	}

	dport = dst_port;
	if (dport == svc->port && dest->port)
		dport = dest->port;

	flags = (svc->flags & IP_VS_SVC_F_ONEPACKET
		 && iph->protocol == IPPROTO_UDP) ?
		IP_VS_CONN_F_ONE_PACKET : 0;

	/*
	 *    Create a new connection according to the template
	 */
	ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol, &iph->saddr,
			      src_port, &iph->daddr, dst_port, &param);

	cp = ip_vs_conn_new(&param, dest->af, &dest->addr, dport, flags, dest,
			    skb->mark);
	if (cp == NULL) {
		ip_vs_conn_put(ct);
		*ignored = -1;
		return NULL;
	}

	/*
	 *    Add its control
	 */
	ip_vs_control_add(cp, ct);
	ip_vs_conn_put(ct);

	ip_vs_conn_stats(cp, svc);
	return cp;
}


/*
 *  IPVS main scheduling function
 *  It selects a server according to the virtual service, and
 *  creates a connection entry.
 *  Protocols supported: TCP, UDP
 *
 *  Usage of *ignored
 *
 * 1 :   protocol tried to schedule (eg. on SYN), found svc but the
 *       svc/scheduler decides that this packet should be accepted with
 *       NF_ACCEPT because it must not be scheduled.
 *
 * 0 :   scheduler can not find destination, so try bypass or
 *       return ICMP and then NF_DROP (ip_vs_leave).
 *
 * -1 :  scheduler tried to schedule but fatal error occurred, eg.
 *       ip_vs_conn_new failure (ENOMEM) or ip_vs_sip_fill_param
 *       failure such as missing Call-ID, ENOMEM on skb_linearize
 *       or pe_data. In this case we should return NF_DROP without
 *       any attempts to send ICMP with ip_vs_leave.
 */
struct ip_vs_conn *
ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
	       struct ip_vs_proto_data *pd, int *ignored,
	       struct ip_vs_iphdr *iph)
{
	struct ip_vs_protocol *pp = pd->pp;
	struct ip_vs_conn *cp = NULL;
	struct ip_vs_scheduler *sched;
	struct ip_vs_dest *dest;
	__be16 _ports[2], *pptr;
	unsigned int flags;

	*ignored = 1;
	/*
	 * IPv6 frags, only the first hit here.
	 */
	pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph);
	if (pptr == NULL)
		return NULL;

	/*
	 * FTPDATA needs this check when using local real server.
	 * Never schedule Active FTPDATA connections from real server.
	 * For LVS-NAT they must be already created. For other methods
	 * with persistence the connection is created on SYN+ACK.
	 */
	if (pptr[0] == FTPDATA) {
		IP_VS_DBG_PKT(12, svc->af, pp, skb, 0,
			      "Not scheduling FTPDATA");
		return NULL;
	}

	/*
	 *    Do not schedule replies from local real server.
	 */
	if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
	    (cp = pp->conn_in_get(svc->af, skb, iph, 1))) {
		IP_VS_DBG_PKT(12, svc->af, pp, skb, 0,
			      "Not scheduling reply for existing connection");
		__ip_vs_conn_put(cp);
		return NULL;
	}

	/*
	 *    Persistent service
	 */
	if (svc->flags & IP_VS_SVC_F_PERSISTENT)
		return ip_vs_sched_persist(svc, skb, pptr[0], pptr[1], ignored,
					   iph);

	*ignored = 0;

	/*
	 *    Non-persistent service
	 */
	if (!svc->fwmark && pptr[1] != svc->port) {
		if (!svc->port)
			pr_err("Schedule: port zero only supported "
			       "in persistent services, "
			       "check your ipvs configuration\n");
		return NULL;
	}

	sched = rcu_dereference(svc->scheduler);
	dest = sched->schedule(svc, skb, iph);
	if (dest == NULL) {
		IP_VS_DBG(1, "Schedule: no dest found.\n");
		return NULL;
	}

	flags = (svc->flags & IP_VS_SVC_F_ONEPACKET
		 && iph->protocol == IPPROTO_UDP) ?
		IP_VS_CONN_F_ONE_PACKET : 0;

	/*
	 *    Create a connection entry.
	 */
	{
		struct ip_vs_conn_param p;

		ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol,
				      &iph->saddr, pptr[0], &iph->daddr,
				      pptr[1], &p);
		cp = ip_vs_conn_new(&p, dest->af, &dest->addr,
				    dest->port ? dest->port : pptr[1],
				    flags, dest, skb->mark);
		if (!cp) {
			*ignored = -1;
			return NULL;
		}
	}

	IP_VS_DBG_BUF(6, "Schedule fwd:%c c:%s:%u v:%s:%u "
		      "d:%s:%u conn->flags:%X conn->refcnt:%d\n",
		      ip_vs_fwd_tag(cp),
		      IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport),
		      IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport),
		      IP_VS_DBG_ADDR(cp->daf, &cp->daddr), ntohs(cp->dport),
		      cp->flags, atomic_read(&cp->refcnt));

	ip_vs_conn_stats(cp, svc);
	return cp;
}


/*
 *  Pass or drop the packet.
 *  Called by ip_vs_in, when the virtual service is available but
 *  no destination is available for a new connection.
 */
int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
		struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph)
{
	__be16 _ports[2], *pptr;
#ifdef CONFIG_SYSCTL
	struct net *net;
	struct netns_ipvs *ipvs;
	int unicast;
#endif

	pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph);
	if (pptr == NULL) {
		return NF_DROP;
	}

#ifdef CONFIG_SYSCTL
	net = skb_net(skb);

#ifdef CONFIG_IP_VS_IPV6
	if (svc->af == AF_INET6)
		unicast = ipv6_addr_type(&iph->daddr.in6) & IPV6_ADDR_UNICAST;
	else
#endif
		unicast = (inet_addr_type(net, iph->daddr.ip) == RTN_UNICAST);

	/* if it is fwmark-based service, the cache_bypass sysctl is up
	   and the destination is a non-local unicast, then create
	   a cache_bypass connection entry */
	ipvs = net_ipvs(net);
	if (ipvs->sysctl_cache_bypass && svc->fwmark && unicast) {
		int ret;
		struct ip_vs_conn *cp;
		unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET &&
				      iph->protocol == IPPROTO_UDP) ?
				      IP_VS_CONN_F_ONE_PACKET : 0;
		union nf_inet_addr daddr =  { .all = { 0, 0, 0, 0 } };

		/* create a new connection entry */
		IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__);
		{
			struct ip_vs_conn_param p;
			ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol,
					      &iph->saddr, pptr[0],
					      &iph->daddr, pptr[1], &p);
			cp = ip_vs_conn_new(&p, svc->af, &daddr, 0,
					    IP_VS_CONN_F_BYPASS | flags,
					    NULL, skb->mark);
			if (!cp)
				return NF_DROP;
		}

		/* statistics */
		ip_vs_in_stats(cp, skb);

		/* set state */
		ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);

		/* transmit the first SYN packet */
		ret = cp->packet_xmit(skb, cp, pd->pp, iph);
		/* do not touch skb anymore */

		atomic_inc(&cp->in_pkts);
		ip_vs_conn_put(cp);
		return ret;
	}
#endif

	/*
	 * When the virtual ftp service is presented, packets destined
	 * for other services on the VIP may get here (except services
	 * listed in the ipvs table), pass the packets, because it is
	 * not ipvs job to decide to drop the packets.
	 */
	if ((svc->port == FTPPORT) && (pptr[1] != FTPPORT))
		return NF_ACCEPT;

	/*
	 * Notify the client that the destination is unreachable, and
	 * release the socket buffer.
	 * Since it is in IP layer, the TCP socket is not actually
	 * created, the TCP RST packet cannot be sent, instead that
	 * ICMP_PORT_UNREACH is sent here no matter it is TCP/UDP. --WZ
	 */
#ifdef CONFIG_IP_VS_IPV6
	if (svc->af == AF_INET6) {
		if (!skb->dev) {
			struct net *net_ = dev_net(skb_dst(skb)->dev);

			skb->dev = net_->loopback_dev;
		}
		icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0);
	} else
#endif
		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);

	return NF_DROP;
}

#ifdef CONFIG_SYSCTL

static int sysctl_snat_reroute(struct sk_buff *skb)
{
	struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
	return ipvs->sysctl_snat_reroute;
}

static int sysctl_nat_icmp_send(struct net *net)
{
	struct netns_ipvs *ipvs = net_ipvs(net);
	return ipvs->sysctl_nat_icmp_send;
}

static int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs)
{
	return ipvs->sysctl_expire_nodest_conn;
}

#else

static int sysctl_snat_reroute(struct sk_buff *skb) { return 0; }
static int sysctl_nat_icmp_send(struct net *net) { return 0; }
static int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs) { return 0; }

#endif

__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset)
{
	return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0));
}

static inline enum ip_defrag_users ip_vs_defrag_user(unsigned int hooknum)
{
	if (NF_INET_LOCAL_IN == hooknum)
		return IP_DEFRAG_VS_IN;
	if (NF_INET_FORWARD == hooknum)
		return IP_DEFRAG_VS_FWD;
	return IP_DEFRAG_VS_OUT;
}

static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user)
{
	int err;

	local_bh_disable();
	err = ip_defrag(skb, user);
	local_bh_enable();
	if (!err)
		ip_send_check(ip_hdr(skb));

	return err;
}

static int ip_vs_route_me_harder(int af, struct sk_buff *skb,
				 unsigned int hooknum)
{
	if (!sysctl_snat_reroute(skb))
		return 0;
	/* Reroute replies only to remote clients (FORWARD and LOCAL_OUT) */
	if (NF_INET_LOCAL_IN == hooknum)
		return 0;
#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6) {
		struct dst_entry *dst = skb_dst(skb);

		if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) &&
		    ip6_route_me_harder(skb) != 0)
			return 1;
	} else
#endif
		if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
		    ip_route_me_harder(skb, RTN_LOCAL) != 0)
			return 1;

	return 0;
}

/*
 * Packet has been made sufficiently writable in caller
 * - inout: 1=in->out, 0=out->in
 */
void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
		    struct ip_vs_conn *cp, int inout)
{
	struct iphdr *iph	 = ip_hdr(skb);
	unsigned int icmp_offset = iph->ihl*4;
	struct icmphdr *icmph	 = (struct icmphdr *)(skb_network_header(skb) +
						      icmp_offset);
	struct iphdr *ciph	 = (struct iphdr *)(icmph + 1);

	if (inout) {
		iph->saddr = cp->vaddr.ip;
		ip_send_check(iph);
		ciph->daddr = cp->vaddr.ip;
		ip_send_check(ciph);
	} else {
		iph->daddr = cp->daddr.ip;
		ip_send_check(iph);
		ciph->saddr = cp->daddr.ip;
		ip_send_check(ciph);
	}

	/* the TCP/UDP/SCTP port */
	if (IPPROTO_TCP == ciph->protocol || IPPROTO_UDP == ciph->protocol ||
	    IPPROTO_SCTP == ciph->protocol) {
		__be16 *ports = (void *)ciph + ciph->ihl*4;

		if (inout)
			ports[1] = cp->vport;
		else
			ports[0] = cp->dport;
	}

	/* And finally the ICMP checksum */
	icmph->checksum = 0;
	icmph->checksum = ip_vs_checksum_complete(skb, icmp_offset);
	skb->ip_summed = CHECKSUM_UNNECESSARY;

	if (inout)
		IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph,
			"Forwarding altered outgoing ICMP");
	else
		IP_VS_DBG_PKT(11, AF_INET, pp, skb, (void *)ciph - (void *)iph,
			"Forwarding altered incoming ICMP");
}

#ifdef CONFIG_IP_VS_IPV6
void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
		    struct ip_vs_conn *cp, int inout)
{
	struct ipv6hdr *iph	 = ipv6_hdr(skb);
	unsigned int icmp_offset = 0;
	unsigned int offs	 = 0; /* header offset*/
	int protocol;
	struct icmp6hdr *icmph;
	struct ipv6hdr *ciph;
	unsigned short fragoffs;

	ipv6_find_hdr(skb, &icmp_offset, IPPROTO_ICMPV6, &fragoffs, NULL);
	icmph = (struct icmp6hdr *)(skb_network_header(skb) + icmp_offset);
	offs = icmp_offset + sizeof(struct icmp6hdr);
	ciph = (struct ipv6hdr *)(skb_network_header(skb) + offs);

	protocol = ipv6_find_hdr(skb, &offs, -1, &fragoffs, NULL);

	if (inout) {
		iph->saddr = cp->vaddr.in6;
		ciph->daddr = cp->vaddr.in6;
	} else {
		iph->daddr = cp->daddr.in6;
		ciph->saddr = cp->daddr.in6;
	}

	/* the TCP/UDP/SCTP port */
	if (!fragoffs && (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol ||
			  IPPROTO_SCTP == protocol)) {
		__be16 *ports = (void *)(skb_network_header(skb) + offs);

		IP_VS_DBG(11, "%s() changed port %d to %d\n", __func__,
			      ntohs(inout ? ports[1] : ports[0]),
			      ntohs(inout ? cp->vport : cp->dport));
		if (inout)
			ports[1] = cp->vport;
		else
			ports[0] = cp->dport;
	}

	/* And finally the ICMP checksum */
	icmph->icmp6_cksum = ~csum_ipv6_magic(&iph->saddr, &iph->daddr,
					      skb->len - icmp_offset,
					      IPPROTO_ICMPV6, 0);
	skb->csum_start = skb_network_header(skb) - skb->head + icmp_offset;
	skb->csum_offset = offsetof(struct icmp6hdr, icmp6_cksum);
	skb->ip_summed = CHECKSUM_PARTIAL;

	if (inout)
		IP_VS_DBG_PKT(11, AF_INET6, pp, skb,
			      (void *)ciph - (void *)iph,
			      "Forwarding altered outgoing ICMPv6");
	else
		IP_VS_DBG_PKT(11, AF_INET6, pp, skb,
			      (void *)ciph - (void *)iph,
			      "Forwarding altered incoming ICMPv6");
}
#endif

/* Handle relevant response ICMP messages - forward to the right
 * destination host.
 */
static int handle_response_icmp(int af, struct sk_buff *skb,
				union nf_inet_addr *snet,
				__u8 protocol, struct ip_vs_conn *cp,
				struct ip_vs_protocol *pp,
				unsigned int offset, unsigned int ihl,
				unsigned int hooknum)
{
	unsigned int verdict = NF_DROP;

	if (IP_VS_FWD_METHOD(cp) != 0) {
		pr_err("shouldn't reach here, because the box is on the "
		       "half connection in the tun/dr module.\n");
	}

	/* Ensure the checksum is correct */
	if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) {
		/* Failed checksum! */
		IP_VS_DBG_BUF(1, "Forward ICMP: failed checksum from %s!\n",
			      IP_VS_DBG_ADDR(af, snet));
		goto out;
	}

	if (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol ||
	    IPPROTO_SCTP == protocol)
		offset += 2 * sizeof(__u16);
	if (!skb_make_writable(skb, offset))
		goto out;

#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6)
		ip_vs_nat_icmp_v6(skb, pp, cp, 1);
	else
#endif
		ip_vs_nat_icmp(skb, pp, cp, 1);

	if (ip_vs_route_me_harder(af, skb, hooknum))
		goto out;

	/* do the statistics and put it back */
	ip_vs_out_stats(cp, skb);

	skb->ipvs_property = 1;
	if (!(cp->flags & IP_VS_CONN_F_NFCT))
		ip_vs_notrack(skb);
	else
		ip_vs_update_conntrack(skb, cp, 0);
	verdict = NF_ACCEPT;

out:
	__ip_vs_conn_put(cp);

	return verdict;
}

/*
 *	Handle ICMP messages in the inside-to-outside direction (outgoing).
 *	Find any that might be relevant, check against existing connections.
 *	Currently handles error types - unreachable, quench, ttl exceeded.
 */
static int ip_vs_out_icmp(struct sk_buff *skb, int *related,
			  unsigned int hooknum)
{
	struct iphdr *iph;
	struct icmphdr	_icmph, *ic;
	struct iphdr	_ciph, *cih;	/* The ip header contained within the ICMP */
	struct ip_vs_iphdr ciph;
	struct ip_vs_conn *cp;
	struct ip_vs_protocol *pp;
	unsigned int offset, ihl;
	union nf_inet_addr snet;

	*related = 1;

	/* reassemble IP fragments */
	if (ip_is_fragment(ip_hdr(skb))) {
		if (ip_vs_gather_frags(skb, ip_vs_defrag_user(hooknum)))
			return NF_STOLEN;
	}

	iph = ip_hdr(skb);
	offset = ihl = iph->ihl * 4;
	ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph);
	if (ic == NULL)
		return NF_DROP;

	IP_VS_DBG(12, "Outgoing ICMP (%d,%d) %pI4->%pI4\n",
		  ic->type, ntohs(icmp_id(ic)),
		  &iph->saddr, &iph->daddr);

	/*
	 * Work through seeing if this is for us.
	 * These checks are supposed to be in an order that means easy
	 * things are checked first to speed up processing.... however
	 * this means that some packets will manage to get a long way
	 * down this stack and then be rejected, but that's life.
	 */
	if ((ic->type != ICMP_DEST_UNREACH) &&
	    (ic->type != ICMP_SOURCE_QUENCH) &&
	    (ic->type != ICMP_TIME_EXCEEDED)) {
		*related = 0;
		return NF_ACCEPT;
	}

	/* Now find the contained IP header */
	offset += sizeof(_icmph);
	cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
	if (cih == NULL)
		return NF_ACCEPT; /* The packet looks wrong, ignore */

	pp = ip_vs_proto_get(cih->protocol);
	if (!pp)
		return NF_ACCEPT;

	/* Is the embedded protocol header present? */
	if (unlikely(cih->frag_off & htons(IP_OFFSET) &&
		     pp->dont_defrag))
		return NF_ACCEPT;

	IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset,
		      "Checking outgoing ICMP for");

	ip_vs_fill_ip4hdr(cih, &ciph);
	ciph.len += offset;
	/* The embedded headers contain source and dest in reverse order */
	cp = pp->conn_out_get(AF_INET, skb, &ciph, 1);
	if (!cp)
		return NF_ACCEPT;

	snet.ip = iph->saddr;
	return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp,
				    pp, ciph.len, ihl, hooknum);
}

#ifdef CONFIG_IP_VS_IPV6
static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related,
			     unsigned int hooknum, struct ip_vs_iphdr *ipvsh)
{
	struct icmp6hdr	_icmph, *ic;
	struct ipv6hdr _ip6h, *ip6h; /* The ip header contained within ICMP */
	struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */
	struct ip_vs_conn *cp;
	struct ip_vs_protocol *pp;
	union nf_inet_addr snet;
	unsigned int writable;

	*related = 1;
	ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph, ipvsh);
	if (ic == NULL)
		return NF_DROP;

	/*
	 * Work through seeing if this is for us.
	 * These checks are supposed to be in an order that means easy
	 * things are checked first to speed up processing.... however
	 * this means that some packets will manage to get a long way
	 * down this stack and then be rejected, but that's life.
	 */
	if (ic->icmp6_type & ICMPV6_INFOMSG_MASK) {
		*related = 0;
		return NF_ACCEPT;
	}
	/* Fragment header that is before ICMP header tells us that:
	 * it's not an error message since they can't be fragmented.
	 */
	if (ipvsh->flags & IP6_FH_F_FRAG)
		return NF_DROP;

	IP_VS_DBG(8, "Outgoing ICMPv6 (%d,%d) %pI6c->%pI6c\n",
		  ic->icmp6_type, ntohs(icmpv6_id(ic)),
		  &ipvsh->saddr, &ipvsh->daddr);

	/* Now find the contained IP header */
	ciph.len = ipvsh->len + sizeof(_icmph);
	ip6h = skb_header_pointer(skb, ciph.len, sizeof(_ip6h), &_ip6h);
	if (ip6h == NULL)
		return NF_ACCEPT; /* The packet looks wrong, ignore */
	ciph.saddr.in6 = ip6h->saddr; /* conn_out_get() handles reverse order */
	ciph.daddr.in6 = ip6h->daddr;
	/* skip possible IPv6 exthdrs of contained IPv6 packet */
	ciph.protocol = ipv6_find_hdr(skb, &ciph.len, -1, &ciph.fragoffs, NULL);
	if (ciph.protocol < 0)
		return NF_ACCEPT; /* Contained IPv6 hdr looks wrong, ignore */

	pp = ip_vs_proto_get(ciph.protocol);
	if (!pp)
		return NF_ACCEPT;

	/* The embedded headers contain source and dest in reverse order */
	cp = pp->conn_out_get(AF_INET6, skb, &ciph, 1);
	if (!cp)
		return NF_ACCEPT;

	snet.in6 = ciph.saddr.in6;
	writable = ciph.len;
	return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp,
				    pp, writable, sizeof(struct ipv6hdr),
				    hooknum);
}
#endif

/*
 * Check if sctp chunc is ABORT chunk
 */
static inline int is_sctp_abort(const struct sk_buff *skb, int nh_len)
{
	sctp_chunkhdr_t *sch, schunk;
	sch = skb_header_pointer(skb, nh_len + sizeof(sctp_sctphdr_t),
			sizeof(schunk), &schunk);
	if (sch == NULL)
		return 0;
	if (sch->type == SCTP_CID_ABORT)
		return 1;
	return 0;
}

static inline int is_tcp_reset(const struct sk_buff *skb, int nh_len)
{
	struct tcphdr _tcph, *th;

	th = skb_header_pointer(skb, nh_len, sizeof(_tcph), &_tcph);
	if (th == NULL)
		return 0;
	return th->rst;
}

static inline bool is_new_conn(const struct sk_buff *skb,
			       struct ip_vs_iphdr *iph)
{
	switch (iph->protocol) {
	case IPPROTO_TCP: {
		struct tcphdr _tcph, *th;

		th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph);
		if (th == NULL)
			return false;
		return th->syn;
	}
	case IPPROTO_SCTP: {
		sctp_chunkhdr_t *sch, schunk;

		sch = skb_header_pointer(skb, iph->len + sizeof(sctp_sctphdr_t),
					 sizeof(schunk), &schunk);
		if (sch == NULL)
			return false;
		return sch->type == SCTP_CID_INIT;
	}
	default:
		return false;
	}
}

static inline bool is_new_conn_expected(const struct ip_vs_conn *cp,
					int conn_reuse_mode)
{
	/* Controlled (FTP DATA or persistence)? */
	if (cp->control)
		return false;

	switch (cp->protocol) {
	case IPPROTO_TCP:
		return (cp->state == IP_VS_TCP_S_TIME_WAIT) ||
			((conn_reuse_mode & 2) &&
			 (cp->state == IP_VS_TCP_S_FIN_WAIT) &&
			 (cp->flags & IP_VS_CONN_F_NOOUTPUT));
	case IPPROTO_SCTP:
		return cp->state == IP_VS_SCTP_S_CLOSED;
	default:
		return false;
	}
}

/* Handle response packets: rewrite addresses and send away...
 */
static unsigned int
handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
		struct ip_vs_conn *cp, struct ip_vs_iphdr *iph,
		unsigned int hooknum)
{
	struct ip_vs_protocol *pp = pd->pp;

	IP_VS_DBG_PKT(11, af, pp, skb, 0, "Outgoing packet");

	if (!skb_make_writable(skb, iph->len))
		goto drop;

	/* mangle the packet */
	if (pp->snat_handler && !pp->snat_handler(skb, pp, cp, iph))
		goto drop;

#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6)
		ipv6_hdr(skb)->saddr = cp->vaddr.in6;
	else
#endif
	{
		ip_hdr(skb)->saddr = cp->vaddr.ip;
		ip_send_check(ip_hdr(skb));
	}

	/*
	 * nf_iterate does not expect change in the skb->dst->dev.
	 * It looks like it is not fatal to enable this code for hooks
	 * where our handlers are at the end of the chain list and
	 * when all next handlers use skb->dst->dev and not outdev.
	 * It will definitely route properly the inout NAT traffic
	 * when multiple paths are used.
	 */

	/* For policy routing, packets originating from this
	 * machine itself may be routed differently to packets
	 * passing through.  We want this packet to be routed as
	 * if it came from this machine itself.  So re-compute
	 * the routing information.
	 */
	if (ip_vs_route_me_harder(af, skb, hooknum))
		goto drop;

	IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT");

	ip_vs_out_stats(cp, skb);
	ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd);
	skb->ipvs_property = 1;
	if (!(cp->flags & IP_VS_CONN_F_NFCT))
		ip_vs_notrack(skb);
	else
		ip_vs_update_conntrack(skb, cp, 0);
	ip_vs_conn_put(cp);

	LeaveFunction(11);
	return NF_ACCEPT;

drop:
	ip_vs_conn_put(cp);
	kfree_skb(skb);
	LeaveFunction(11);
	return NF_STOLEN;
}

/*
 *	Check if outgoing packet belongs to the established ip_vs_conn.
 */
static unsigned int
ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
{
	struct net *net = NULL;
	struct ip_vs_iphdr iph;
	struct ip_vs_protocol *pp;
	struct ip_vs_proto_data *pd;
	struct ip_vs_conn *cp;

	EnterFunction(11);

	/* Already marked as IPVS request or reply? */
	if (skb->ipvs_property)
		return NF_ACCEPT;

	/* Bad... Do not break raw sockets */
	if (unlikely(skb->sk != NULL && hooknum == NF_INET_LOCAL_OUT &&
		     af == AF_INET)) {
		struct sock *sk = skb->sk;
		struct inet_sock *inet = inet_sk(skb->sk);

		if (inet && sk->sk_family == PF_INET && inet->nodefrag)
			return NF_ACCEPT;
	}

	if (unlikely(!skb_dst(skb)))
		return NF_ACCEPT;

	net = skb_net(skb);
	if (!net_ipvs(net)->enable)
		return NF_ACCEPT;

	ip_vs_fill_iph_skb(af, skb, &iph);
#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6) {
		if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
			int related;
			int verdict = ip_vs_out_icmp_v6(skb, &related,
							hooknum, &iph);

			if (related)
				return verdict;
		}
	} else
#endif
		if (unlikely(iph.protocol == IPPROTO_ICMP)) {
			int related;
			int verdict = ip_vs_out_icmp(skb, &related, hooknum);

			if (related)
				return verdict;
		}

	pd = ip_vs_proto_data_get(net, iph.protocol);
	if (unlikely(!pd))
		return NF_ACCEPT;
	pp = pd->pp;

	/* reassemble IP fragments */
#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET)
#endif
		if (unlikely(ip_is_fragment(ip_hdr(skb)) && !pp->dont_defrag)) {
			if (ip_vs_gather_frags(skb,
					       ip_vs_defrag_user(hooknum)))
				return NF_STOLEN;

			ip_vs_fill_ip4hdr(skb_network_header(skb), &iph);
		}

	/*
	 * Check if the packet belongs to an existing entry
	 */
	cp = pp->conn_out_get(af, skb, &iph, 0);

	if (likely(cp))
		return handle_response(af, skb, pd, cp, &iph, hooknum);
	if (sysctl_nat_icmp_send(net) &&
	    (pp->protocol == IPPROTO_TCP ||
	     pp->protocol == IPPROTO_UDP ||
	     pp->protocol == IPPROTO_SCTP)) {
		__be16 _ports[2], *pptr;

		pptr = frag_safe_skb_hp(skb, iph.len,
					 sizeof(_ports), _ports, &iph);
		if (pptr == NULL)
			return NF_ACCEPT;	/* Not for me */
		if (ip_vs_has_real_service(net, af, iph.protocol, &iph.saddr,
					   pptr[0])) {
			/*
			 * Notify the real server: there is no
			 * existing entry if it is not RST
			 * packet or not TCP packet.
			 */
			if ((iph.protocol != IPPROTO_TCP &&
			     iph.protocol != IPPROTO_SCTP)
			     || ((iph.protocol == IPPROTO_TCP
				  && !is_tcp_reset(skb, iph.len))
				 || (iph.protocol == IPPROTO_SCTP
					&& !is_sctp_abort(skb,
						iph.len)))) {
#ifdef CONFIG_IP_VS_IPV6
				if (af == AF_INET6) {
					if (!skb->dev)
						skb->dev = net->loopback_dev;
					icmpv6_send(skb,
						    ICMPV6_DEST_UNREACH,
						    ICMPV6_PORT_UNREACH,
						    0);
				} else
#endif
					icmp_send(skb,
						  ICMP_DEST_UNREACH,
						  ICMP_PORT_UNREACH, 0);
				return NF_DROP;
			}
		}
	}
	IP_VS_DBG_PKT(12, af, pp, skb, 0,
		      "ip_vs_out: packet continues traversal as normal");
	return NF_ACCEPT;
}

/*
 *	It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain,
 *	used only for VS/NAT.
 *	Check if packet is reply for established ip_vs_conn.
 */
static unsigned int
ip_vs_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb,
	     const struct nf_hook_state *state)
{
	return ip_vs_out(ops->hooknum, skb, AF_INET);
}

/*
 *	It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT.
 *	Check if packet is reply for established ip_vs_conn.
 */
static unsigned int
ip_vs_local_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb,
		   const struct nf_hook_state *state)
{
	return ip_vs_out(ops->hooknum, skb, AF_INET);
}

#ifdef CONFIG_IP_VS_IPV6

/*
 *	It is hooked at the NF_INET_FORWARD and NF_INET_LOCAL_IN chain,
 *	used only for VS/NAT.
 *	Check if packet is reply for established ip_vs_conn.
 */
static unsigned int
ip_vs_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb,
	     const struct nf_hook_state *state)
{
	return ip_vs_out(ops->hooknum, skb, AF_INET6);
}

/*
 *	It is hooked at the NF_INET_LOCAL_OUT chain, used only for VS/NAT.
 *	Check if packet is reply for established ip_vs_conn.
 */
static unsigned int
ip_vs_local_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb,
		   const struct nf_hook_state *state)
{
	return ip_vs_out(ops->hooknum, skb, AF_INET6);
}

#endif

/*
 *	Handle ICMP messages in the outside-to-inside direction (incoming).
 *	Find any that might be relevant, check against existing connections,
 *	forward to the right destination host if relevant.
 *	Currently handles error types - unreachable, quench, ttl exceeded.
 */
static int
ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
{
	struct net *net = NULL;
	struct iphdr *iph;
	struct icmphdr	_icmph, *ic;
	struct iphdr	_ciph, *cih;	/* The ip header contained within the ICMP */
	struct ip_vs_iphdr ciph;
	struct ip_vs_conn *cp;
	struct ip_vs_protocol *pp;
	struct ip_vs_proto_data *pd;
	unsigned int offset, offset2, ihl, verdict;
	bool ipip;

	*related = 1;

	/* reassemble IP fragments */
	if (ip_is_fragment(ip_hdr(skb))) {
		if (ip_vs_gather_frags(skb, ip_vs_defrag_user(hooknum)))
			return NF_STOLEN;
	}

	iph = ip_hdr(skb);
	offset = ihl = iph->ihl * 4;
	ic = skb_header_pointer(skb, offset, sizeof(_icmph), &_icmph);
	if (ic == NULL)
		return NF_DROP;

	IP_VS_DBG(12, "Incoming ICMP (%d,%d) %pI4->%pI4\n",
		  ic->type, ntohs(icmp_id(ic)),
		  &iph->saddr, &iph->daddr);

	/*
	 * Work through seeing if this is for us.
	 * These checks are supposed to be in an order that means easy
	 * things are checked first to speed up processing.... however
	 * this means that some packets will manage to get a long way
	 * down this stack and then be rejected, but that's life.
	 */
	if ((ic->type != ICMP_DEST_UNREACH) &&
	    (ic->type != ICMP_SOURCE_QUENCH) &&
	    (ic->type != ICMP_TIME_EXCEEDED)) {
		*related = 0;
		return NF_ACCEPT;
	}

	/* Now find the contained IP header */
	offset += sizeof(_icmph);
	cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
	if (cih == NULL)
		return NF_ACCEPT; /* The packet looks wrong, ignore */

	net = skb_net(skb);

	/* Special case for errors for IPIP packets */
	ipip = false;
	if (cih->protocol == IPPROTO_IPIP) {
		if (unlikely(cih->frag_off & htons(IP_OFFSET)))
			return NF_ACCEPT;
		/* Error for our IPIP must arrive at LOCAL_IN */
		if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL))
			return NF_ACCEPT;
		offset += cih->ihl * 4;
		cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
		if (cih == NULL)
			return NF_ACCEPT; /* The packet looks wrong, ignore */
		ipip = true;
	}

	pd = ip_vs_proto_data_get(net, cih->protocol);
	if (!pd)
		return NF_ACCEPT;
	pp = pd->pp;

	/* Is the embedded protocol header present? */
	if (unlikely(cih->frag_off & htons(IP_OFFSET) &&
		     pp->dont_defrag))
		return NF_ACCEPT;

	IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset,
		      "Checking incoming ICMP for");

	offset2 = offset;
	ip_vs_fill_ip4hdr(cih, &ciph);
	ciph.len += offset;
	offset = ciph.len;
	/* The embedded headers contain source and dest in reverse order.
	 * For IPIP this is error for request, not for reply.
	 */
	cp = pp->conn_in_get(AF_INET, skb, &ciph, ipip ? 0 : 1);
	if (!cp)
		return NF_ACCEPT;

	verdict = NF_DROP;

	/* Ensure the checksum is correct */
	if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) {
		/* Failed checksum! */
		IP_VS_DBG(1, "Incoming ICMP: failed checksum from %pI4!\n",
			  &iph->saddr);
		goto out;
	}

	if (ipip) {
		__be32 info = ic->un.gateway;
		__u8 type = ic->type;
		__u8 code = ic->code;

		/* Update the MTU */
		if (ic->type == ICMP_DEST_UNREACH &&
		    ic->code == ICMP_FRAG_NEEDED) {
			struct ip_vs_dest *dest = cp->dest;
			u32 mtu = ntohs(ic->un.frag.mtu);
			__be16 frag_off = cih->frag_off;

			/* Strip outer IP and ICMP, go to IPIP header */
			if (pskb_pull(skb, ihl + sizeof(_icmph)) == NULL)
				goto ignore_ipip;
			offset2 -= ihl + sizeof(_icmph);
			skb_reset_network_header(skb);
			IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n",
				&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu);
			ipv4_update_pmtu(skb, dev_net(skb->dev),
					 mtu, 0, 0, 0, 0);
			/* Client uses PMTUD? */
			if (!(frag_off & htons(IP_DF)))
				goto ignore_ipip;
			/* Prefer the resulting PMTU */
			if (dest) {
				struct ip_vs_dest_dst *dest_dst;

				rcu_read_lock();
				dest_dst = rcu_dereference(dest->dest_dst);
				if (dest_dst)
					mtu = dst_mtu(dest_dst->dst_cache);
				rcu_read_unlock();
			}
			if (mtu > 68 + sizeof(struct iphdr))
				mtu -= sizeof(struct iphdr);
			info = htonl(mtu);
		}
		/* Strip outer IP, ICMP and IPIP, go to IP header of
		 * original request.
		 */
		if (pskb_pull(skb, offset2) == NULL)
			goto ignore_ipip;
		skb_reset_network_header(skb);
		IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n",
			&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
			type, code, ntohl(info));
		icmp_send(skb, type, code, info);
		/* ICMP can be shorter but anyways, account it */
		ip_vs_out_stats(cp, skb);

ignore_ipip:
		consume_skb(skb);
		verdict = NF_STOLEN;
		goto out;
	}

	/* do the statistics and put it back */
	ip_vs_in_stats(cp, skb);
	if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol ||
	    IPPROTO_SCTP == cih->protocol)
		offset += 2 * sizeof(__u16);
	verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum, &ciph);

out:
	__ip_vs_conn_put(cp);

	return verdict;
}

#ifdef CONFIG_IP_VS_IPV6
static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related,
			    unsigned int hooknum, struct ip_vs_iphdr *iph)
{
	struct net *net = NULL;
	struct ipv6hdr _ip6h, *ip6h;
	struct icmp6hdr	_icmph, *ic;
	struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */
	struct ip_vs_conn *cp;
	struct ip_vs_protocol *pp;
	struct ip_vs_proto_data *pd;
	unsigned int offs_ciph, writable, verdict;

	*related = 1;

	ic = frag_safe_skb_hp(skb, iph->len, sizeof(_icmph), &_icmph, iph);
	if (ic == NULL)
		return NF_DROP;

	/*
	 * Work through seeing if this is for us.
	 * These checks are supposed to be in an order that means easy
	 * things are checked first to speed up processing.... however
	 * this means that some packets will manage to get a long way
	 * down this stack and then be rejected, but that's life.
	 */
	if (ic->icmp6_type & ICMPV6_INFOMSG_MASK) {
		*related = 0;
		return NF_ACCEPT;
	}
	/* Fragment header that is before ICMP header tells us that:
	 * it's not an error message since they can't be fragmented.
	 */
	if (iph->flags & IP6_FH_F_FRAG)
		return NF_DROP;

	IP_VS_DBG(8, "Incoming ICMPv6 (%d,%d) %pI6c->%pI6c\n",
		  ic->icmp6_type, ntohs(icmpv6_id(ic)),
		  &iph->saddr, &iph->daddr);

	/* Now find the contained IP header */
	ciph.len = iph->len + sizeof(_icmph);
	offs_ciph = ciph.len; /* Save ip header offset */
	ip6h = skb_header_pointer(skb, ciph.len, sizeof(_ip6h), &_ip6h);
	if (ip6h == NULL)
		return NF_ACCEPT; /* The packet looks wrong, ignore */
	ciph.saddr.in6 = ip6h->saddr; /* conn_in_get() handles reverse order */
	ciph.daddr.in6 = ip6h->daddr;
	/* skip possible IPv6 exthdrs of contained IPv6 packet */
	ciph.protocol = ipv6_find_hdr(skb, &ciph.len, -1, &ciph.fragoffs, NULL);
	if (ciph.protocol < 0)
		return NF_ACCEPT; /* Contained IPv6 hdr looks wrong, ignore */

	net = skb_net(skb);
	pd = ip_vs_proto_data_get(net, ciph.protocol);
	if (!pd)
		return NF_ACCEPT;
	pp = pd->pp;

	/* Cannot handle fragmented embedded protocol */
	if (ciph.fragoffs)
		return NF_ACCEPT;

	IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offs_ciph,
		      "Checking incoming ICMPv6 for");

	/* The embedded headers contain source and dest in reverse order
	 * if not from localhost
	 */
	cp = pp->conn_in_get(AF_INET6, skb, &ciph,
			     (hooknum == NF_INET_LOCAL_OUT) ? 0 : 1);

	if (!cp)
		return NF_ACCEPT;
	/* VS/TUN, VS/DR and LOCALNODE just let it go */
	if ((hooknum == NF_INET_LOCAL_OUT) &&
	    (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)) {
		__ip_vs_conn_put(cp);
		return NF_ACCEPT;
	}

	/* do the statistics and put it back */
	ip_vs_in_stats(cp, skb);

	/* Need to mangle contained IPv6 header in ICMPv6 packet */
	writable = ciph.len;
	if (IPPROTO_TCP == ciph.protocol || IPPROTO_UDP == ciph.protocol ||
	    IPPROTO_SCTP == ciph.protocol)
		writable += 2 * sizeof(__u16); /* Also mangle ports */

	verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, writable, hooknum, &ciph);

	__ip_vs_conn_put(cp);

	return verdict;
}
#endif


/*
 *	Check if it's for virtual services, look it up,
 *	and send it on its way...
 */
static unsigned int
ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
{
	struct net *net;
	struct ip_vs_iphdr iph;
	struct ip_vs_protocol *pp;
	struct ip_vs_proto_data *pd;
	struct ip_vs_conn *cp;
	int ret, pkts;
	struct netns_ipvs *ipvs;
	int conn_reuse_mode;

	/* Already marked as IPVS request or reply? */
	if (skb->ipvs_property)
		return NF_ACCEPT;

	/*
	 *	Big tappo:
	 *	- remote client: only PACKET_HOST
	 *	- route: used for struct net when skb->dev is unset
	 */
	if (unlikely((skb->pkt_type != PACKET_HOST &&
		      hooknum != NF_INET_LOCAL_OUT) ||
		     !skb_dst(skb))) {
		ip_vs_fill_iph_skb(af, skb, &iph);
		IP_VS_DBG_BUF(12, "packet type=%d proto=%d daddr=%s"
			      " ignored in hook %u\n",
			      skb->pkt_type, iph.protocol,
			      IP_VS_DBG_ADDR(af, &iph.daddr), hooknum);
		return NF_ACCEPT;
	}
	/* ipvs enabled in this netns ? */
	net = skb_net(skb);
	ipvs = net_ipvs(net);
	if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
		return NF_ACCEPT;

	ip_vs_fill_iph_skb(af, skb, &iph);

	/* Bad... Do not break raw sockets */
	if (unlikely(skb->sk != NULL && hooknum == NF_INET_LOCAL_OUT &&
		     af == AF_INET)) {
		struct sock *sk = skb->sk;
		struct inet_sock *inet = inet_sk(skb->sk);

		if (inet && sk->sk_family == PF_INET && inet->nodefrag)
			return NF_ACCEPT;
	}

#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6) {
		if (unlikely(iph.protocol == IPPROTO_ICMPV6)) {
			int related;
			int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum,
						       &iph);

			if (related)
				return verdict;
		}
	} else
#endif
		if (unlikely(iph.protocol == IPPROTO_ICMP)) {
			int related;
			int verdict = ip_vs_in_icmp(skb, &related, hooknum);

			if (related)
				return verdict;
		}

	/* Protocol supported? */
	pd = ip_vs_proto_data_get(net, iph.protocol);
	if (unlikely(!pd))
		return NF_ACCEPT;
	pp = pd->pp;
	/*
	 * Check if the packet belongs to an existing connection entry
	 */
	cp = pp->conn_in_get(af, skb, &iph, 0);

	conn_reuse_mode = sysctl_conn_reuse_mode(ipvs);
	if (conn_reuse_mode && !iph.fragoffs &&
	    is_new_conn(skb, &iph) && cp &&
	    ((unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest &&
	      unlikely(!atomic_read(&cp->dest->weight))) ||
	     unlikely(is_new_conn_expected(cp, conn_reuse_mode)))) {
		if (!atomic_read(&cp->n_control))
			ip_vs_conn_expire_now(cp);
		__ip_vs_conn_put(cp);
		cp = NULL;
	}

	if (unlikely(!cp) && !iph.fragoffs) {
		/* No (second) fragments need to enter here, as nf_defrag_ipv6
		 * replayed fragment zero will already have created the cp
		 */
		int v;

		/* Schedule and create new connection entry into &cp */
		if (!pp->conn_schedule(af, skb, pd, &v, &cp, &iph))
			return v;
	}

	if (unlikely(!cp)) {
		/* sorry, all this trouble for a no-hit :) */
		IP_VS_DBG_PKT(12, af, pp, skb, 0,
			      "ip_vs_in: packet continues traversal as normal");
		if (iph.fragoffs) {
			/* Fragment that couldn't be mapped to a conn entry
			 * is missing module nf_defrag_ipv6
			 */
			IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n");
			IP_VS_DBG_PKT(7, af, pp, skb, 0, "unhandled fragment");
		}
		return NF_ACCEPT;
	}

	IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet");
	/* Check the server status */
	if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
		/* the destination server is not available */

		if (sysctl_expire_nodest_conn(ipvs)) {
			/* try to expire the connection immediately */
			ip_vs_conn_expire_now(cp);
		}
		/* don't restart its timer, and silently
		   drop the packet. */
		__ip_vs_conn_put(cp);
		return NF_DROP;
	}

	ip_vs_in_stats(cp, skb);
	ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd);
	if (cp->packet_xmit)
		ret = cp->packet_xmit(skb, cp, pp, &iph);
		/* do not touch skb anymore */
	else {
		IP_VS_DBG_RL("warning: packet_xmit is null");
		ret = NF_ACCEPT;
	}

	/* Increase its packet counter and check if it is needed
	 * to be synchronized
	 *
	 * Sync connection if it is about to close to
	 * encorage the standby servers to update the connections timeout
	 *
	 * For ONE_PKT let ip_vs_sync_conn() do the filter work.
	 */

	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
		pkts = sysctl_sync_threshold(ipvs);
	else
		pkts = atomic_add_return(1, &cp->in_pkts);

	if (ipvs->sync_state & IP_VS_STATE_MASTER)
		ip_vs_sync_conn(net, cp, pkts);

	ip_vs_conn_put(cp);
	return ret;
}

/*
 *	AF_INET handler in NF_INET_LOCAL_IN chain
 *	Schedule and forward packets from remote clients
 */
static unsigned int
ip_vs_remote_request4(const struct nf_hook_ops *ops, struct sk_buff *skb,
		      const struct nf_hook_state *state)
{
	return ip_vs_in(ops->hooknum, skb, AF_INET);
}

/*
 *	AF_INET handler in NF_INET_LOCAL_OUT chain
 *	Schedule and forward packets from local clients
 */
static unsigned int
ip_vs_local_request4(const struct nf_hook_ops *ops, struct sk_buff *skb,
		     const struct nf_hook_state *state)
{
	return ip_vs_in(ops->hooknum, skb, AF_INET);
}

#ifdef CONFIG_IP_VS_IPV6

/*
 *	AF_INET6 handler in NF_INET_LOCAL_IN chain
 *	Schedule and forward packets from remote clients
 */
static unsigned int
ip_vs_remote_request6(const struct nf_hook_ops *ops, struct sk_buff *skb,
		      const struct nf_hook_state *state)
{
	return ip_vs_in(ops->hooknum, skb, AF_INET6);
}

/*
 *	AF_INET6 handler in NF_INET_LOCAL_OUT chain
 *	Schedule and forward packets from local clients
 */
static unsigned int
ip_vs_local_request6(const struct nf_hook_ops *ops, struct sk_buff *skb,
		     const struct nf_hook_state *state)
{
	return ip_vs_in(ops->hooknum, skb, AF_INET6);
}

#endif


/*
 *	It is hooked at the NF_INET_FORWARD chain, in order to catch ICMP
 *      related packets destined for 0.0.0.0/0.
 *      When fwmark-based virtual service is used, such as transparent
 *      cache cluster, TCP packets can be marked and routed to ip_vs_in,
 *      but ICMP destined for 0.0.0.0/0 cannot not be easily marked and
 *      sent to ip_vs_in_icmp. So, catch them at the NF_INET_FORWARD chain
 *      and send them to ip_vs_in_icmp.
 */
static unsigned int
ip_vs_forward_icmp(const struct nf_hook_ops *ops, struct sk_buff *skb,
		   const struct nf_hook_state *state)
{
	int r;
	struct net *net;
	struct netns_ipvs *ipvs;

	if (ip_hdr(skb)->protocol != IPPROTO_ICMP)
		return NF_ACCEPT;

	/* ipvs enabled in this netns ? */
	net = skb_net(skb);
	ipvs = net_ipvs(net);
	if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
		return NF_ACCEPT;

	return ip_vs_in_icmp(skb, &r, ops->hooknum);
}

#ifdef CONFIG_IP_VS_IPV6
static unsigned int
ip_vs_forward_icmp_v6(const struct nf_hook_ops *ops, struct sk_buff *skb,
		      const struct nf_hook_state *state)
{
	int r;
	struct net *net;
	struct netns_ipvs *ipvs;
	struct ip_vs_iphdr iphdr;

	ip_vs_fill_iph_skb(AF_INET6, skb, &iphdr);
	if (iphdr.protocol != IPPROTO_ICMPV6)
		return NF_ACCEPT;

	/* ipvs enabled in this netns ? */
	net = skb_net(skb);
	ipvs = net_ipvs(net);
	if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable))
		return NF_ACCEPT;

	return ip_vs_in_icmp_v6(skb, &r, ops->hooknum, &iphdr);
}
#endif


static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
	/* After packet filtering, change source only for VS/NAT */
	{
		.hook		= ip_vs_reply4,
		.owner		= THIS_MODULE,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_LOCAL_IN,
		.priority	= NF_IP_PRI_NAT_SRC - 2,
	},
	/* After packet filtering, forward packet through VS/DR, VS/TUN,
	 * or VS/NAT(change destination), so that filtering rules can be
	 * applied to IPVS. */
	{
		.hook		= ip_vs_remote_request4,
		.owner		= THIS_MODULE,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_LOCAL_IN,
		.priority	= NF_IP_PRI_NAT_SRC - 1,
	},
	/* Before ip_vs_in, change source only for VS/NAT */
	{
		.hook		= ip_vs_local_reply4,
		.owner		= THIS_MODULE,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_LOCAL_OUT,
		.priority	= NF_IP_PRI_NAT_DST + 1,
	},
	/* After mangle, schedule and forward local requests */
	{
		.hook		= ip_vs_local_request4,
		.owner		= THIS_MODULE,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_LOCAL_OUT,
		.priority	= NF_IP_PRI_NAT_DST + 2,
	},
	/* After packet filtering (but before ip_vs_out_icmp), catch icmp
	 * destined for 0.0.0.0/0, which is for incoming IPVS connections */
	{
		.hook		= ip_vs_forward_icmp,
		.owner		= THIS_MODULE,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_FORWARD,
		.priority	= 99,
	},
	/* After packet filtering, change source only for VS/NAT */
	{
		.hook		= ip_vs_reply4,
		.owner		= THIS_MODULE,
		.pf		= NFPROTO_IPV4,
		.hooknum	= NF_INET_FORWARD,
		.priority	= 100,
	},
#ifdef CONFIG_IP_VS_IPV6
	/* After packet filtering, change source only for VS/NAT */
	{
		.hook		= ip_vs_reply6,
		.owner		= THIS_MODULE,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_LOCAL_IN,
		.priority	= NF_IP6_PRI_NAT_SRC - 2,
	},
	/* After packet filtering, forward packet through VS/DR, VS/TUN,
	 * or VS/NAT(change destination), so that filtering rules can be
	 * applied to IPVS. */
	{
		.hook		= ip_vs_remote_request6,
		.owner		= THIS_MODULE,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_LOCAL_IN,
		.priority	= NF_IP6_PRI_NAT_SRC - 1,
	},
	/* Before ip_vs_in, change source only for VS/NAT */
	{
		.hook		= ip_vs_local_reply6,
		.owner		= THIS_MODULE,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_LOCAL_OUT,
		.priority	= NF_IP6_PRI_NAT_DST + 1,
	},
	/* After mangle, schedule and forward local requests */
	{
		.hook		= ip_vs_local_request6,
		.owner		= THIS_MODULE,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_LOCAL_OUT,
		.priority	= NF_IP6_PRI_NAT_DST + 2,
	},
	/* After packet filtering (but before ip_vs_out_icmp), catch icmp
	 * destined for 0.0.0.0/0, which is for incoming IPVS connections */
	{
		.hook		= ip_vs_forward_icmp_v6,
		.owner		= THIS_MODULE,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_FORWARD,
		.priority	= 99,
	},
	/* After packet filtering, change source only for VS/NAT */
	{
		.hook		= ip_vs_reply6,
		.owner		= THIS_MODULE,
		.pf		= NFPROTO_IPV6,
		.hooknum	= NF_INET_FORWARD,
		.priority	= 100,
	},
#endif
};
/*
 *	Initialize IP Virtual Server netns mem.
 */
static int __net_init __ip_vs_init(struct net *net)
{
	struct netns_ipvs *ipvs;

	ipvs = net_generic(net, ip_vs_net_id);
	if (ipvs == NULL)
		return -ENOMEM;

	/* Hold the beast until a service is registerd */
	ipvs->enable = 0;
	ipvs->net = net;
	/* Counters used for creating unique names */
	ipvs->gen = atomic_read(&ipvs_netns_cnt);
	atomic_inc(&ipvs_netns_cnt);
	net->ipvs = ipvs;

	if (ip_vs_estimator_net_init(net) < 0)
		goto estimator_fail;

	if (ip_vs_control_net_init(net) < 0)
		goto control_fail;

	if (ip_vs_protocol_net_init(net) < 0)
		goto protocol_fail;

	if (ip_vs_app_net_init(net) < 0)
		goto app_fail;

	if (ip_vs_conn_net_init(net) < 0)
		goto conn_fail;

	if (ip_vs_sync_net_init(net) < 0)
		goto sync_fail;

	printk(KERN_INFO "IPVS: Creating netns size=%zu id=%d\n",
			 sizeof(struct netns_ipvs), ipvs->gen);
	return 0;
/*
 * Error handling
 */

sync_fail:
	ip_vs_conn_net_cleanup(net);
conn_fail:
	ip_vs_app_net_cleanup(net);
app_fail:
	ip_vs_protocol_net_cleanup(net);
protocol_fail:
	ip_vs_control_net_cleanup(net);
control_fail:
	ip_vs_estimator_net_cleanup(net);
estimator_fail:
	net->ipvs = NULL;
	return -ENOMEM;
}

static void __net_exit __ip_vs_cleanup(struct net *net)
{
	ip_vs_service_net_cleanup(net);	/* ip_vs_flush() with locks */
	ip_vs_conn_net_cleanup(net);
	ip_vs_app_net_cleanup(net);
	ip_vs_protocol_net_cleanup(net);
	ip_vs_control_net_cleanup(net);
	ip_vs_estimator_net_cleanup(net);
	IP_VS_DBG(2, "ipvs netns %d released\n", net_ipvs(net)->gen);
	net->ipvs = NULL;
}

static void __net_exit __ip_vs_dev_cleanup(struct net *net)
{
	EnterFunction(2);
	net_ipvs(net)->enable = 0;	/* Disable packet reception */
	smp_wmb();
	ip_vs_sync_net_cleanup(net);
	LeaveFunction(2);
}

static struct pernet_operations ipvs_core_ops = {
	.init = __ip_vs_init,
	.exit = __ip_vs_cleanup,
	.id   = &ip_vs_net_id,
	.size = sizeof(struct netns_ipvs),
};

static struct pernet_operations ipvs_core_dev_ops = {
	.exit = __ip_vs_dev_cleanup,
};

/*
 *	Initialize IP Virtual Server
 */
static int __init ip_vs_init(void)
{
	int ret;

	ret = ip_vs_control_init();
	if (ret < 0) {
		pr_err("can't setup control.\n");
		goto exit;
	}

	ip_vs_protocol_init();

	ret = ip_vs_conn_init();
	if (ret < 0) {
		pr_err("can't setup connection table.\n");
		goto cleanup_protocol;
	}

	ret = register_pernet_subsys(&ipvs_core_ops);	/* Alloc ip_vs struct */
	if (ret < 0)
		goto cleanup_conn;

	ret = register_pernet_device(&ipvs_core_dev_ops);
	if (ret < 0)
		goto cleanup_sub;

	ret = nf_register_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
	if (ret < 0) {
		pr_err("can't register hooks.\n");
		goto cleanup_dev;
	}

	ret = ip_vs_register_nl_ioctl();
	if (ret < 0) {
		pr_err("can't register netlink/ioctl.\n");
		goto cleanup_hooks;
	}

	pr_info("ipvs loaded.\n");

	return ret;

cleanup_hooks:
	nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
cleanup_dev:
	unregister_pernet_device(&ipvs_core_dev_ops);
cleanup_sub:
	unregister_pernet_subsys(&ipvs_core_ops);
cleanup_conn:
	ip_vs_conn_cleanup();
cleanup_protocol:
	ip_vs_protocol_cleanup();
	ip_vs_control_cleanup();
exit:
	return ret;
}

static void __exit ip_vs_cleanup(void)
{
	ip_vs_unregister_nl_ioctl();
	nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
	unregister_pernet_device(&ipvs_core_dev_ops);
	unregister_pernet_subsys(&ipvs_core_ops);	/* free ip_vs struct */
	ip_vs_conn_cleanup();
	ip_vs_protocol_cleanup();
	ip_vs_control_cleanup();
	pr_info("ipvs unloaded.\n");
}

module_init(ip_vs_init);
module_exit(ip_vs_cleanup);
MODULE_LICENSE("GPL");