summaryrefslogtreecommitdiffstats
path: root/include/net/ip_vs.h
blob: a6cc576fd467f879054c344c24dede5010c72992 (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
/* IP Virtual Server
 * data structure and functionality definitions
 */

#ifndef _NET_IP_VS_H
#define _NET_IP_VS_H

#include <linux/ip_vs.h>                /* definitions shared with userland */

#include <asm/types.h>                  /* for __uXX types */

#include <linux/list.h>                 /* for struct list_head */
#include <linux/spinlock.h>             /* for struct rwlock_t */
#include <linux/atomic.h>               /* for struct atomic_t */
#include <linux/compiler.h>
#include <linux/timer.h>
#include <linux/bug.h>

#include <net/checksum.h>
#include <linux/netfilter.h>		/* for union nf_inet_addr */
#include <linux/ip.h>
#include <linux/ipv6.h>			/* for struct ipv6hdr */
#include <net/ipv6.h>
#if IS_ENABLED(CONFIG_IP_VS_IPV6)
#include <linux/netfilter_ipv6/ip6_tables.h>
#endif
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
#include <net/netfilter/nf_conntrack.h>
#endif
#include <net/net_namespace.h>		/* Netw namespace */

#define IP_VS_HDR_INVERSE	1
#define IP_VS_HDR_ICMP		2

/* Generic access of ipvs struct */
static inline struct netns_ipvs *net_ipvs(struct net* net)
{
	return net->ipvs;
}

/* This one needed for single_open_net since net is stored directly in
 * private not as a struct i.e. seq_file_net can't be used.
 */
static inline struct net *seq_file_single_net(struct seq_file *seq)
{
#ifdef CONFIG_NET_NS
	return (struct net *)seq->private;
#else
	return &init_net;
#endif
}

/* Connections' size value needed by ip_vs_ctl.c */
extern int ip_vs_conn_tab_size;

struct ip_vs_iphdr {
	int hdr_flags;	/* ipvs flags */
	__u32 off;	/* Where IP or IPv4 header starts */
	__u32 len;	/* IPv4 simply where L4 starts
			 * IPv6 where L4 Transport Header starts */
	__u16 fragoffs; /* IPv6 fragment offset, 0 if first frag (or not frag)*/
	__s16 protocol;
	__s32 flags;
	union nf_inet_addr saddr;
	union nf_inet_addr daddr;
};

static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset,
				      int len, void *buffer,
				      const struct ip_vs_iphdr *ipvsh)
{
	return skb_header_pointer(skb, offset, len, buffer);
}

/* This function handles filling *ip_vs_iphdr, both for IPv4 and IPv6.
 * IPv6 requires some extra work, as finding proper header position,
 * depend on the IPv6 extension headers.
 */
static inline int
ip_vs_fill_iph_skb_off(int af, const struct sk_buff *skb, int offset,
		       int hdr_flags, struct ip_vs_iphdr *iphdr)
{
	iphdr->hdr_flags = hdr_flags;
	iphdr->off = offset;

#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6) {
		struct ipv6hdr _iph;
		const struct ipv6hdr *iph = skb_header_pointer(
			skb, offset, sizeof(_iph), &_iph);
		if (!iph)
			return 0;

		iphdr->saddr.in6 = iph->saddr;
		iphdr->daddr.in6 = iph->daddr;
		/* ipv6_find_hdr() updates len, flags */
		iphdr->len	 = offset;
		iphdr->flags	 = 0;
		iphdr->protocol  = ipv6_find_hdr(skb, &iphdr->len, -1,
						 &iphdr->fragoffs,
						 &iphdr->flags);
		if (iphdr->protocol < 0)
			return 0;
	} else
#endif
	{
		struct iphdr _iph;
		const struct iphdr *iph = skb_header_pointer(
			skb, offset, sizeof(_iph), &_iph);
		if (!iph)
			return 0;

		iphdr->len	= offset + iph->ihl * 4;
		iphdr->fragoffs	= 0;
		iphdr->protocol	= iph->protocol;
		iphdr->saddr.ip	= iph->saddr;
		iphdr->daddr.ip	= iph->daddr;
	}

	return 1;
}

static inline int
ip_vs_fill_iph_skb_icmp(int af, const struct sk_buff *skb, int offset,
			bool inverse, struct ip_vs_iphdr *iphdr)
{
	int hdr_flags = IP_VS_HDR_ICMP;

	if (inverse)
		hdr_flags |= IP_VS_HDR_INVERSE;

	return ip_vs_fill_iph_skb_off(af, skb, offset, hdr_flags, iphdr);
}

static inline int
ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, bool inverse,
		   struct ip_vs_iphdr *iphdr)
{
	int hdr_flags = 0;

	if (inverse)
		hdr_flags |= IP_VS_HDR_INVERSE;

	return ip_vs_fill_iph_skb_off(af, skb, skb_network_offset(skb),
				      hdr_flags, iphdr);
}

static inline bool
ip_vs_iph_inverse(const struct ip_vs_iphdr *iph)
{
	return !!(iph->hdr_flags & IP_VS_HDR_INVERSE);
}

static inline bool
ip_vs_iph_icmp(const struct ip_vs_iphdr *iph)
{
	return !!(iph->hdr_flags & IP_VS_HDR_ICMP);
}

static inline void ip_vs_addr_copy(int af, union nf_inet_addr *dst,
				   const union nf_inet_addr *src)
{
#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6)
		dst->in6 = src->in6;
	else
#endif
	dst->ip = src->ip;
}

static inline void ip_vs_addr_set(int af, union nf_inet_addr *dst,
				  const union nf_inet_addr *src)
{
#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6) {
		dst->in6 = src->in6;
		return;
	}
#endif
	dst->ip = src->ip;
	dst->all[1] = 0;
	dst->all[2] = 0;
	dst->all[3] = 0;
}

static inline int ip_vs_addr_equal(int af, const union nf_inet_addr *a,
				   const union nf_inet_addr *b)
{
#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6)
		return ipv6_addr_equal(&a->in6, &b->in6);
#endif
	return a->ip == b->ip;
}

#ifdef CONFIG_IP_VS_DEBUG
#include <linux/net.h>

int ip_vs_get_debug_level(void);

static inline const char *ip_vs_dbg_addr(int af, char *buf, size_t buf_len,
					 const union nf_inet_addr *addr,
					 int *idx)
{
	int len;
#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6)
		len = snprintf(&buf[*idx], buf_len - *idx, "[%pI6c]",
			       &addr->in6) + 1;
	else
#endif
		len = snprintf(&buf[*idx], buf_len - *idx, "%pI4",
			       &addr->ip) + 1;

	*idx += len;
	BUG_ON(*idx > buf_len + 1);
	return &buf[*idx - len];
}

#define IP_VS_DBG_BUF(level, msg, ...)					\
	do {								\
		char ip_vs_dbg_buf[160];				\
		int ip_vs_dbg_idx = 0;					\
		if (level <= ip_vs_get_debug_level())			\
			printk(KERN_DEBUG pr_fmt(msg), ##__VA_ARGS__);	\
	} while (0)
#define IP_VS_ERR_BUF(msg...)						\
	do {								\
		char ip_vs_dbg_buf[160];				\
		int ip_vs_dbg_idx = 0;					\
		pr_err(msg);						\
	} while (0)

/* Only use from within IP_VS_DBG_BUF() or IP_VS_ERR_BUF macros */
#define IP_VS_DBG_ADDR(af, addr)					\
	ip_vs_dbg_addr(af, ip_vs_dbg_buf,				\
		       sizeof(ip_vs_dbg_buf), addr,			\
		       &ip_vs_dbg_idx)

#define IP_VS_DBG(level, msg, ...)					\
	do {								\
		if (level <= ip_vs_get_debug_level())			\
			printk(KERN_DEBUG pr_fmt(msg), ##__VA_ARGS__);	\
	} while (0)
#define IP_VS_DBG_RL(msg, ...)						\
	do {								\
		if (net_ratelimit())					\
			printk(KERN_DEBUG pr_fmt(msg), ##__VA_ARGS__);	\
	} while (0)
#define IP_VS_DBG_PKT(level, af, pp, skb, ofs, msg)			\
	do {								\
		if (level <= ip_vs_get_debug_level())			\
			pp->debug_packet(af, pp, skb, ofs, msg);	\
	} while (0)
#define IP_VS_DBG_RL_PKT(level, af, pp, skb, ofs, msg)			\
	do {								\
		if (level <= ip_vs_get_debug_level() &&			\
		    net_ratelimit())					\
			pp->debug_packet(af, pp, skb, ofs, msg);	\
	} while (0)
#else	/* NO DEBUGGING at ALL */
#define IP_VS_DBG_BUF(level, msg...)  do {} while (0)
#define IP_VS_ERR_BUF(msg...)  do {} while (0)
#define IP_VS_DBG(level, msg...)  do {} while (0)
#define IP_VS_DBG_RL(msg...)  do {} while (0)
#define IP_VS_DBG_PKT(level, af, pp, skb, ofs, msg)	do {} while (0)
#define IP_VS_DBG_RL_PKT(level, af, pp, skb, ofs, msg)	do {} while (0)
#endif

#define IP_VS_BUG() BUG()
#define IP_VS_ERR_RL(msg, ...)						\
	do {								\
		if (net_ratelimit())					\
			pr_err(msg, ##__VA_ARGS__);			\
	} while (0)

#ifdef CONFIG_IP_VS_DEBUG
#define EnterFunction(level)						\
	do {								\
		if (level <= ip_vs_get_debug_level())			\
			printk(KERN_DEBUG				\
			       pr_fmt("Enter: %s, %s line %i\n"),	\
			       __func__, __FILE__, __LINE__);		\
	} while (0)
#define LeaveFunction(level)						\
	do {								\
		if (level <= ip_vs_get_debug_level())			\
			printk(KERN_DEBUG				\
			       pr_fmt("Leave: %s, %s line %i\n"),	\
			       __func__, __FILE__, __LINE__);		\
	} while (0)
#else
#define EnterFunction(level)   do {} while (0)
#define LeaveFunction(level)   do {} while (0)
#endif

/* The port number of FTP service (in network order). */
#define FTPPORT  cpu_to_be16(21)
#define FTPDATA  cpu_to_be16(20)

/* TCP State Values */
enum {
	IP_VS_TCP_S_NONE = 0,
	IP_VS_TCP_S_ESTABLISHED,
	IP_VS_TCP_S_SYN_SENT,
	IP_VS_TCP_S_SYN_RECV,
	IP_VS_TCP_S_FIN_WAIT,
	IP_VS_TCP_S_TIME_WAIT,
	IP_VS_TCP_S_CLOSE,
	IP_VS_TCP_S_CLOSE_WAIT,
	IP_VS_TCP_S_LAST_ACK,
	IP_VS_TCP_S_LISTEN,
	IP_VS_TCP_S_SYNACK,
	IP_VS_TCP_S_LAST
};

/* UDP State Values */
enum {
	IP_VS_UDP_S_NORMAL,
	IP_VS_UDP_S_LAST,
};

/* ICMP State Values */
enum {
	IP_VS_ICMP_S_NORMAL,
	IP_VS_ICMP_S_LAST,
};

/* SCTP State Values */
enum ip_vs_sctp_states {
	IP_VS_SCTP_S_NONE,
	IP_VS_SCTP_S_INIT1,
	IP_VS_SCTP_S_INIT,
	IP_VS_SCTP_S_COOKIE_SENT,
	IP_VS_SCTP_S_COOKIE_REPLIED,
	IP_VS_SCTP_S_COOKIE_WAIT,
	IP_VS_SCTP_S_COOKIE,
	IP_VS_SCTP_S_COOKIE_ECHOED,
	IP_VS_SCTP_S_ESTABLISHED,
	IP_VS_SCTP_S_SHUTDOWN_SENT,
	IP_VS_SCTP_S_SHUTDOWN_RECEIVED,
	IP_VS_SCTP_S_SHUTDOWN_ACK_SENT,
	IP_VS_SCTP_S_REJECTED,
	IP_VS_SCTP_S_CLOSED,
	IP_VS_SCTP_S_LAST
};

/* Delta sequence info structure
 * Each ip_vs_conn has 2 (output AND input seq. changes).
 * Only used in the VS/NAT.
 */
struct ip_vs_seq {
	__u32			init_seq;	/* Add delta from this seq */
	__u32			delta;		/* Delta in sequence numbers */
	__u32			previous_delta;	/* Delta in sequence numbers
						 * before last resized pkt */
};

/* counters per cpu */
struct ip_vs_counters {
	__u64		conns;		/* connections scheduled */
	__u64		inpkts;		/* incoming packets */
	__u64		outpkts;	/* outgoing packets */
	__u64		inbytes;	/* incoming bytes */
	__u64		outbytes;	/* outgoing bytes */
};
/* Stats per cpu */
struct ip_vs_cpu_stats {
	struct ip_vs_counters   cnt;
	struct u64_stats_sync   syncp;
};

/* IPVS statistics objects */
struct ip_vs_estimator {
	struct list_head	list;

	u64			last_inbytes;
	u64			last_outbytes;
	u64			last_conns;
	u64			last_inpkts;
	u64			last_outpkts;

	u64			cps;
	u64			inpps;
	u64			outpps;
	u64			inbps;
	u64			outbps;
};

/*
 * IPVS statistics object, 64-bit kernel version of struct ip_vs_stats_user
 */
struct ip_vs_kstats {
	u64			conns;		/* connections scheduled */
	u64			inpkts;		/* incoming packets */
	u64			outpkts;	/* outgoing packets */
	u64			inbytes;	/* incoming bytes */
	u64			outbytes;	/* outgoing bytes */

	u64			cps;		/* current connection rate */
	u64			inpps;		/* current in packet rate */
	u64			outpps;		/* current out packet rate */
	u64			inbps;		/* current in byte rate */
	u64			outbps;		/* current out byte rate */
};

struct ip_vs_stats {
	struct ip_vs_kstats	kstats;		/* kernel statistics */
	struct ip_vs_estimator	est;		/* estimator */
	struct ip_vs_cpu_stats __percpu	*cpustats;	/* per cpu counters */
	spinlock_t		lock;		/* spin lock */
	struct ip_vs_kstats	kstats0;	/* reset values */
};

struct dst_entry;
struct iphdr;
struct ip_vs_conn;
struct ip_vs_app;
struct sk_buff;
struct ip_vs_proto_data;

struct ip_vs_protocol {
	struct ip_vs_protocol	*next;
	char			*name;
	u16			protocol;
	u16			num_states;
	int			dont_defrag;

	void (*init)(struct ip_vs_protocol *pp);

	void (*exit)(struct ip_vs_protocol *pp);

	int (*init_netns)(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd);

	void (*exit_netns)(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd);

	int (*conn_schedule)(struct netns_ipvs *ipvs,
			     int af, struct sk_buff *skb,
			     struct ip_vs_proto_data *pd,
			     int *verdict, struct ip_vs_conn **cpp,
			     struct ip_vs_iphdr *iph);

	struct ip_vs_conn *
	(*conn_in_get)(struct netns_ipvs *ipvs,
		       int af,
		       const struct sk_buff *skb,
		       const struct ip_vs_iphdr *iph);

	struct ip_vs_conn *
	(*conn_out_get)(struct netns_ipvs *ipvs,
			int af,
			const struct sk_buff *skb,
			const struct ip_vs_iphdr *iph);

	int (*snat_handler)(struct sk_buff *skb, struct ip_vs_protocol *pp,
			    struct ip_vs_conn *cp, struct ip_vs_iphdr *iph);

	int (*dnat_handler)(struct sk_buff *skb, struct ip_vs_protocol *pp,
			    struct ip_vs_conn *cp, struct ip_vs_iphdr *iph);

	int (*csum_check)(int af, struct sk_buff *skb,
			  struct ip_vs_protocol *pp);

	const char *(*state_name)(int state);

	void (*state_transition)(struct ip_vs_conn *cp, int direction,
				 const struct sk_buff *skb,
				 struct ip_vs_proto_data *pd);

	int (*register_app)(struct netns_ipvs *ipvs, struct ip_vs_app *inc);

	void (*unregister_app)(struct netns_ipvs *ipvs, struct ip_vs_app *inc);

	int (*app_conn_bind)(struct ip_vs_conn *cp);

	void (*debug_packet)(int af, struct ip_vs_protocol *pp,
			     const struct sk_buff *skb,
			     int offset,
			     const char *msg);

	void (*timeout_change)(struct ip_vs_proto_data *pd, int flags);
};

/* protocol data per netns */
struct ip_vs_proto_data {
	struct ip_vs_proto_data	*next;
	struct ip_vs_protocol	*pp;
	int			*timeout_table;	/* protocol timeout table */
	atomic_t		appcnt;		/* counter of proto app incs. */
	struct tcp_states_t	*tcp_state_table;
};

struct ip_vs_protocol   *ip_vs_proto_get(unsigned short proto);
struct ip_vs_proto_data *ip_vs_proto_data_get(struct netns_ipvs *ipvs,
					      unsigned short proto);

struct ip_vs_conn_param {
	struct netns_ipvs		*ipvs;
	const union nf_inet_addr	*caddr;
	const union nf_inet_addr	*vaddr;
	__be16				cport;
	__be16				vport;
	__u16				protocol;
	u16				af;

	const struct ip_vs_pe		*pe;
	char				*pe_data;
	__u8				pe_data_len;
};

/* IP_VS structure allocated for each dynamically scheduled connection */
struct ip_vs_conn {
	struct hlist_node	c_list;         /* hashed list heads */
	/* Protocol, addresses and port numbers */
	__be16                  cport;
	__be16                  dport;
	__be16                  vport;
	u16			af;		/* address family */
	union nf_inet_addr      caddr;          /* client address */
	union nf_inet_addr      vaddr;          /* virtual address */
	union nf_inet_addr      daddr;          /* destination address */
	volatile __u32          flags;          /* status flags */
	__u16                   protocol;       /* Which protocol (TCP/UDP) */
	__u16			daf;		/* Address family of the dest */
	struct netns_ipvs	*ipvs;

	/* counter and timer */
	atomic_t		refcnt;		/* reference count */
	struct timer_list	timer;		/* Expiration timer */
	volatile unsigned long	timeout;	/* timeout */

	/* Flags and state transition */
	spinlock_t              lock;           /* lock for state transition */
	volatile __u16          state;          /* state info */
	volatile __u16          old_state;      /* old state, to be used for
						 * state transition triggerd
						 * synchronization
						 */
	__u32			fwmark;		/* Fire wall mark from skb */
	unsigned long		sync_endtime;	/* jiffies + sent_retries */

	/* Control members */
	struct ip_vs_conn       *control;       /* Master control connection */
	atomic_t                n_control;      /* Number of controlled ones */
	struct ip_vs_dest       *dest;          /* real server */
	atomic_t                in_pkts;        /* incoming packet counter */

	/* Packet transmitter for different forwarding methods.  If it
	 * mangles the packet, it must return NF_DROP or better NF_STOLEN,
	 * otherwise this must be changed to a sk_buff **.
	 * NF_ACCEPT can be returned when destination is local.
	 */
	int (*packet_xmit)(struct sk_buff *skb, struct ip_vs_conn *cp,
			   struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);

	/* Note: we can group the following members into a structure,
	 * in order to save more space, and the following members are
	 * only used in VS/NAT anyway
	 */
	struct ip_vs_app        *app;           /* bound ip_vs_app object */
	void                    *app_data;      /* Application private data */
	struct ip_vs_seq        in_seq;         /* incoming seq. struct */
	struct ip_vs_seq        out_seq;        /* outgoing seq. struct */

	const struct ip_vs_pe	*pe;
	char			*pe_data;
	__u8			pe_data_len;

	struct rcu_head		rcu_head;
};

/* Extended internal versions of struct ip_vs_service_user and ip_vs_dest_user
 * for IPv6 support.
 *
 * We need these to conveniently pass around service and destination
 * options, but unfortunately, we also need to keep the old definitions to
 * maintain userspace backwards compatibility for the setsockopt interface.
 */
struct ip_vs_service_user_kern {
	/* virtual service addresses */
	u16			af;
	u16			protocol;
	union nf_inet_addr	addr;		/* virtual ip address */
	__be16			port;
	u32			fwmark;		/* firwall mark of service */

	/* virtual service options */
	char			*sched_name;
	char			*pe_name;
	unsigned int		flags;		/* virtual service flags */
	unsigned int		timeout;	/* persistent timeout in sec */
	__be32			netmask;	/* persistent netmask or plen */
};


struct ip_vs_dest_user_kern {
	/* destination server address */
	union nf_inet_addr	addr;
	__be16			port;

	/* real server options */
	unsigned int		conn_flags;	/* connection flags */
	int			weight;		/* destination weight */

	/* thresholds for active connections */
	u32			u_threshold;	/* upper threshold */
	u32			l_threshold;	/* lower threshold */

	/* Address family of addr */
	u16			af;
};


/*
 * The information about the virtual service offered to the net and the
 * forwarding entries.
 */
struct ip_vs_service {
	struct hlist_node	s_list;   /* for normal service table */
	struct hlist_node	f_list;   /* for fwmark-based service table */
	atomic_t		refcnt;   /* reference counter */

	u16			af;       /* address family */
	__u16			protocol; /* which protocol (TCP/UDP) */
	union nf_inet_addr	addr;	  /* IP address for virtual service */
	__be16			port;	  /* port number for the service */
	__u32                   fwmark;   /* firewall mark of the service */
	unsigned int		flags;	  /* service status flags */
	unsigned int		timeout;  /* persistent timeout in ticks */
	__be32			netmask;  /* grouping granularity, mask/plen */
	struct netns_ipvs	*ipvs;

	struct list_head	destinations;  /* real server d-linked list */
	__u32			num_dests;     /* number of servers */
	struct ip_vs_stats      stats;         /* statistics for the service */

	/* for scheduling */
	struct ip_vs_scheduler __rcu *scheduler; /* bound scheduler object */
	spinlock_t		sched_lock;    /* lock sched_data */
	void			*sched_data;   /* scheduler application data */

	/* alternate persistence engine */
	struct ip_vs_pe __rcu	*pe;

	struct rcu_head		rcu_head;
};

/* Information for cached dst */
struct ip_vs_dest_dst {
	struct dst_entry	*dst_cache;	/* destination cache entry */
	u32			dst_cookie;
	union nf_inet_addr	dst_saddr;
	struct rcu_head		rcu_head;
};

/* The real server destination forwarding entry with ip address, port number,
 * and so on.
 */
struct ip_vs_dest {
	struct list_head	n_list;   /* for the dests in the service */
	struct hlist_node	d_list;   /* for table with all the dests */

	u16			af;		/* address family */
	__be16			port;		/* port number of the server */
	union nf_inet_addr	addr;		/* IP address of the server */
	volatile unsigned int	flags;		/* dest status flags */
	atomic_t		conn_flags;	/* flags to copy to conn */
	atomic_t		weight;		/* server weight */

	atomic_t		refcnt;		/* reference counter */
	struct ip_vs_stats      stats;          /* statistics */
	unsigned long		idle_start;	/* start time, jiffies */

	/* connection counters and thresholds */
	atomic_t		activeconns;	/* active connections */
	atomic_t		inactconns;	/* inactive connections */
	atomic_t		persistconns;	/* persistent connections */
	__u32			u_threshold;	/* upper threshold */
	__u32			l_threshold;	/* lower threshold */

	/* for destination cache */
	spinlock_t		dst_lock;	/* lock of dst_cache */
	struct ip_vs_dest_dst __rcu *dest_dst;	/* cached dst info */

	/* for virtual service */
	struct ip_vs_service __rcu *svc;	/* service it belongs to */
	__u16			protocol;	/* which protocol (TCP/UDP) */
	__be16			vport;		/* virtual port number */
	union nf_inet_addr	vaddr;		/* virtual IP address */
	__u32			vfwmark;	/* firewall mark of service */

	struct list_head	t_list;		/* in dest_trash */
	unsigned int		in_rs_table:1;	/* we are in rs_table */
};

/* The scheduler object */
struct ip_vs_scheduler {
	struct list_head	n_list;		/* d-linked list head */
	char			*name;		/* scheduler name */
	atomic_t		refcnt;		/* reference counter */
	struct module		*module;	/* THIS_MODULE/NULL */

	/* scheduler initializing service */
	int (*init_service)(struct ip_vs_service *svc);
	/* scheduling service finish */
	void (*done_service)(struct ip_vs_service *svc);
	/* dest is linked */
	int (*add_dest)(struct ip_vs_service *svc, struct ip_vs_dest *dest);
	/* dest is unlinked */
	int (*del_dest)(struct ip_vs_service *svc, struct ip_vs_dest *dest);
	/* dest is updated */
	int (*upd_dest)(struct ip_vs_service *svc, struct ip_vs_dest *dest);

	/* selecting a server from the given service */
	struct ip_vs_dest* (*schedule)(struct ip_vs_service *svc,
				       const struct sk_buff *skb,
				       struct ip_vs_iphdr *iph);
};

/* The persistence engine object */
struct ip_vs_pe {
	struct list_head	n_list;		/* d-linked list head */
	char			*name;		/* scheduler name */
	atomic_t		refcnt;		/* reference counter */
	struct module		*module;	/* THIS_MODULE/NULL */

	/* get the connection template, if any */
	int (*fill_param)(struct ip_vs_conn_param *p, struct sk_buff *skb);
	bool (*ct_match)(const struct ip_vs_conn_param *p,
			 struct ip_vs_conn *ct);
	u32 (*hashkey_raw)(const struct ip_vs_conn_param *p, u32 initval,
			   bool inverse);
	int (*show_pe_data)(const struct ip_vs_conn *cp, char *buf);
};

/* The application module object (a.k.a. app incarnation) */
struct ip_vs_app {
	struct list_head	a_list;		/* member in app list */
	int			type;		/* IP_VS_APP_TYPE_xxx */
	char			*name;		/* application module name */
	__u16			protocol;
	struct module		*module;	/* THIS_MODULE/NULL */
	struct list_head	incs_list;	/* list of incarnations */

	/* members for application incarnations */
	struct list_head	p_list;		/* member in proto app list */
	struct ip_vs_app	*app;		/* its real application */
	__be16			port;		/* port number in net order */
	atomic_t		usecnt;		/* usage counter */
	struct rcu_head		rcu_head;

	/* output hook: Process packet in inout direction, diff set for TCP.
	 * Return: 0=Error, 1=Payload Not Mangled/Mangled but checksum is ok,
	 *	   2=Mangled but checksum was not updated
	 */
	int (*pkt_out)(struct ip_vs_app *, struct ip_vs_conn *,
		       struct sk_buff *, int *diff);

	/* input hook: Process packet in outin direction, diff set for TCP.
	 * Return: 0=Error, 1=Payload Not Mangled/Mangled but checksum is ok,
	 *	   2=Mangled but checksum was not updated
	 */
	int (*pkt_in)(struct ip_vs_app *, struct ip_vs_conn *,
		      struct sk_buff *, int *diff);

	/* ip_vs_app initializer */
	int (*init_conn)(struct ip_vs_app *, struct ip_vs_conn *);

	/* ip_vs_app finish */
	int (*done_conn)(struct ip_vs_app *, struct ip_vs_conn *);


	/* not used now */
	int (*bind_conn)(struct ip_vs_app *, struct ip_vs_conn *,
			 struct ip_vs_protocol *);

	void (*unbind_conn)(struct ip_vs_app *, struct ip_vs_conn *);

	int *			timeout_table;
	int *			timeouts;
	int			timeouts_size;

	int (*conn_schedule)(struct sk_buff *skb, struct ip_vs_app *app,
			     int *verdict, struct ip_vs_conn **cpp);

	struct ip_vs_conn *
	(*conn_in_get)(const struct sk_buff *skb, struct ip_vs_app *app,
		       const struct iphdr *iph, int inverse);

	struct ip_vs_conn *
	(*conn_out_get)(const struct sk_buff *skb, struct ip_vs_app *app,
			const struct iphdr *iph, int inverse);

	int (*state_transition)(struct ip_vs_conn *cp, int direction,
				const struct sk_buff *skb,
				struct ip_vs_app *app);

	void (*timeout_change)(struct ip_vs_app *app, int flags);
};

struct ipvs_master_sync_state {
	struct list_head	sync_queue;
	struct ip_vs_sync_buff	*sync_buff;
	unsigned long		sync_queue_len;
	unsigned int		sync_queue_delay;
	struct task_struct	*master_thread;
	struct delayed_work	master_wakeup_work;
	struct netns_ipvs	*ipvs;
};

/* How much time to keep dests in trash */
#define IP_VS_DEST_TRASH_PERIOD		(120 * HZ)

struct ipvs_sync_daemon_cfg {
	union nf_inet_addr	mcast_group;
	int			syncid;
	u16			sync_maxlen;
	u16			mcast_port;
	u8			mcast_af;
	u8			mcast_ttl;
	/* multicast interface name */
	char			mcast_ifn[IP_VS_IFNAME_MAXLEN];
};

/* IPVS in network namespace */
struct netns_ipvs {
	int			gen;		/* Generation */
	int			enable;		/* enable like nf_hooks do */
	/* Hash table: for real service lookups */
	#define IP_VS_RTAB_BITS 4
	#define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS)
	#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)

	struct hlist_head	rs_table[IP_VS_RTAB_SIZE];
	/* ip_vs_app */
	struct list_head	app_list;
	/* ip_vs_proto */
	#define IP_VS_PROTO_TAB_SIZE	32	/* must be power of 2 */
	struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE];
	/* ip_vs_proto_tcp */
#ifdef CONFIG_IP_VS_PROTO_TCP
	#define	TCP_APP_TAB_BITS	4
	#define	TCP_APP_TAB_SIZE	(1 << TCP_APP_TAB_BITS)
	#define	TCP_APP_TAB_MASK	(TCP_APP_TAB_SIZE - 1)
	struct list_head	tcp_apps[TCP_APP_TAB_SIZE];
#endif
	/* ip_vs_proto_udp */
#ifdef CONFIG_IP_VS_PROTO_UDP
	#define	UDP_APP_TAB_BITS	4
	#define	UDP_APP_TAB_SIZE	(1 << UDP_APP_TAB_BITS)
	#define	UDP_APP_TAB_MASK	(UDP_APP_TAB_SIZE - 1)
	struct list_head	udp_apps[UDP_APP_TAB_SIZE];
#endif
	/* ip_vs_proto_sctp */
#ifdef CONFIG_IP_VS_PROTO_SCTP
	#define SCTP_APP_TAB_BITS	4
	#define SCTP_APP_TAB_SIZE	(1 << SCTP_APP_TAB_BITS)
	#define SCTP_APP_TAB_MASK	(SCTP_APP_TAB_SIZE - 1)
	/* Hash table for SCTP application incarnations	 */
	struct list_head	sctp_apps[SCTP_APP_TAB_SIZE];
#endif
	/* ip_vs_conn */
	atomic_t		conn_count;      /* connection counter */

	/* ip_vs_ctl */
	struct ip_vs_stats		tot_stats;  /* Statistics & est. */

	int			num_services;    /* no of virtual services */

	/* Trash for destinations */
	struct list_head	dest_trash;
	spinlock_t		dest_trash_lock;
	struct timer_list	dest_trash_timer; /* expiration timer */
	/* Service counters */
	atomic_t		ftpsvc_counter;
	atomic_t		nullsvc_counter;

#ifdef CONFIG_SYSCTL
	/* 1/rate drop and drop-entry variables */
	struct delayed_work	defense_work;   /* Work handler */
	int			drop_rate;
	int			drop_counter;
	atomic_t		dropentry;
	/* locks in ctl.c */
	spinlock_t		dropentry_lock;  /* drop entry handling */
	spinlock_t		droppacket_lock; /* drop packet handling */
	spinlock_t		securetcp_lock;  /* state and timeout tables */

	/* sys-ctl struct */
	struct ctl_table_header	*sysctl_hdr;
	struct ctl_table	*sysctl_tbl;
#endif

	/* sysctl variables */
	int			sysctl_amemthresh;
	int			sysctl_am_droprate;
	int			sysctl_drop_entry;
	int			sysctl_drop_packet;
	int			sysctl_secure_tcp;
#ifdef CONFIG_IP_VS_NFCT
	int			sysctl_conntrack;
#endif
	int			sysctl_snat_reroute;
	int			sysctl_sync_ver;
	int			sysctl_sync_ports;
	int			sysctl_sync_persist_mode;
	unsigned long		sysctl_sync_qlen_max;
	int			sysctl_sync_sock_size;
	int			sysctl_cache_bypass;
	int			sysctl_expire_nodest_conn;
	int			sysctl_sloppy_tcp;
	int			sysctl_sloppy_sctp;
	int			sysctl_expire_quiescent_template;
	int			sysctl_sync_threshold[2];
	unsigned int		sysctl_sync_refresh_period;
	int			sysctl_sync_retries;
	int			sysctl_nat_icmp_send;
	int			sysctl_pmtu_disc;
	int			sysctl_backup_only;
	int			sysctl_conn_reuse_mode;
	int			sysctl_schedule_icmp;
	int			sysctl_ignore_tunneled;

	/* ip_vs_lblc */
	int			sysctl_lblc_expiration;
	struct ctl_table_header	*lblc_ctl_header;
	struct ctl_table	*lblc_ctl_table;
	/* ip_vs_lblcr */
	int			sysctl_lblcr_expiration;
	struct ctl_table_header	*lblcr_ctl_header;
	struct ctl_table	*lblcr_ctl_table;
	/* ip_vs_est */
	struct list_head	est_list;	/* estimator list */
	spinlock_t		est_lock;
	struct timer_list	est_timer;	/* Estimation timer */
	/* ip_vs_sync */
	spinlock_t		sync_lock;
	struct ipvs_master_sync_state *ms;
	spinlock_t		sync_buff_lock;
	struct task_struct	**backup_threads;
	int			threads_mask;
	volatile int		sync_state;
	struct mutex		sync_mutex;
	struct ipvs_sync_daemon_cfg	mcfg;	/* Master Configuration */
	struct ipvs_sync_daemon_cfg	bcfg;	/* Backup Configuration */
	/* net name space ptr */
	struct net		*net;            /* Needed by timer routines */
	/* Number of heterogeneous destinations, needed becaus heterogeneous
	 * are not supported when synchronization is enabled.
	 */
	unsigned int		mixed_address_family_dests;
};

#define DEFAULT_SYNC_THRESHOLD	3
#define DEFAULT_SYNC_PERIOD	50
#define DEFAULT_SYNC_VER	1
#define DEFAULT_SLOPPY_TCP	0
#define DEFAULT_SLOPPY_SCTP	0
#define DEFAULT_SYNC_REFRESH_PERIOD	(0U * HZ)
#define DEFAULT_SYNC_RETRIES		0
#define IPVS_SYNC_WAKEUP_RATE	8
#define IPVS_SYNC_QLEN_MAX	(IPVS_SYNC_WAKEUP_RATE * 4)
#define IPVS_SYNC_SEND_DELAY	(HZ / 50)
#define IPVS_SYNC_CHECK_PERIOD	HZ
#define IPVS_SYNC_FLUSH_TIME	(HZ * 2)
#define IPVS_SYNC_PORTS_MAX	(1 << 6)

#ifdef CONFIG_SYSCTL

static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
{
	return ipvs->sysctl_sync_threshold[0];
}

static inline int sysctl_sync_period(struct netns_ipvs *ipvs)
{
	return ACCESS_ONCE(ipvs->sysctl_sync_threshold[1]);
}

static inline unsigned int sysctl_sync_refresh_period(struct netns_ipvs *ipvs)
{
	return ACCESS_ONCE(ipvs->sysctl_sync_refresh_period);
}

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

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

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

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

static inline int sysctl_sync_ports(struct netns_ipvs *ipvs)
{
	return ACCESS_ONCE(ipvs->sysctl_sync_ports);
}

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

static inline unsigned long sysctl_sync_qlen_max(struct netns_ipvs *ipvs)
{
	return ipvs->sysctl_sync_qlen_max;
}

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

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

static inline int sysctl_backup_only(struct netns_ipvs *ipvs)
{
	return ipvs->sync_state & IP_VS_STATE_BACKUP &&
	       ipvs->sysctl_backup_only;
}

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

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

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

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

#else

static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
{
	return DEFAULT_SYNC_THRESHOLD;
}

static inline int sysctl_sync_period(struct netns_ipvs *ipvs)
{
	return DEFAULT_SYNC_PERIOD;
}

static inline unsigned int sysctl_sync_refresh_period(struct netns_ipvs *ipvs)
{
	return DEFAULT_SYNC_REFRESH_PERIOD;
}

static inline int sysctl_sync_retries(struct netns_ipvs *ipvs)
{
	return DEFAULT_SYNC_RETRIES & 3;
}

static inline int sysctl_sync_ver(struct netns_ipvs *ipvs)
{
	return DEFAULT_SYNC_VER;
}

static inline int sysctl_sloppy_tcp(struct netns_ipvs *ipvs)
{
	return DEFAULT_SLOPPY_TCP;
}

static inline int sysctl_sloppy_sctp(struct netns_ipvs *ipvs)
{
	return DEFAULT_SLOPPY_SCTP;
}

static inline int sysctl_sync_ports(struct netns_ipvs *ipvs)
{
	return 1;
}

static inline int sysctl_sync_persist_mode(struct netns_ipvs *ipvs)
{
	return 0;
}

static inline unsigned long sysctl_sync_qlen_max(struct netns_ipvs *ipvs)
{
	return IPVS_SYNC_QLEN_MAX;
}

static inline int sysctl_sync_sock_size(struct netns_ipvs *ipvs)
{
	return 0;
}

static inline int sysctl_pmtu_disc(struct netns_ipvs *ipvs)
{
	return 1;
}

static inline int sysctl_backup_only(struct netns_ipvs *ipvs)
{
	return 0;
}

static inline int sysctl_conn_reuse_mode(struct netns_ipvs *ipvs)
{
	return 1;
}

static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs)
{
	return 0;
}

static inline int sysctl_ignore_tunneled(struct netns_ipvs *ipvs)
{
	return 0;
}

static inline int sysctl_cache_bypass(struct netns_ipvs *ipvs)
{
	return 0;
}

#endif

/* IPVS core functions
 * (from ip_vs_core.c)
 */
const char *ip_vs_proto_name(unsigned int proto);
void ip_vs_init_hash_table(struct list_head *table, int rows);
#define IP_VS_INIT_HASH_TABLE(t) ip_vs_init_hash_table((t), ARRAY_SIZE((t)))

#define IP_VS_APP_TYPE_FTP	1

/* ip_vs_conn handling functions
 * (from ip_vs_conn.c)
 */
enum {
	IP_VS_DIR_INPUT = 0,
	IP_VS_DIR_OUTPUT,
	IP_VS_DIR_INPUT_ONLY,
	IP_VS_DIR_LAST,
};

static inline void ip_vs_conn_fill_param(struct netns_ipvs *ipvs, int af, int protocol,
					 const union nf_inet_addr *caddr,
					 __be16 cport,
					 const union nf_inet_addr *vaddr,
					 __be16 vport,
					 struct ip_vs_conn_param *p)
{
	p->ipvs = ipvs;
	p->af = af;
	p->protocol = protocol;
	p->caddr = caddr;
	p->cport = cport;
	p->vaddr = vaddr;
	p->vport = vport;
	p->pe = NULL;
	p->pe_data = NULL;
}

struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p);
struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p);

struct ip_vs_conn * ip_vs_conn_in_get_proto(struct netns_ipvs *ipvs, int af,
					    const struct sk_buff *skb,
					    const struct ip_vs_iphdr *iph);

struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p);

struct ip_vs_conn * ip_vs_conn_out_get_proto(struct netns_ipvs *ipvs, int af,
					     const struct sk_buff *skb,
					     const struct ip_vs_iphdr *iph);

/* Get reference to gain full access to conn.
 * By default, RCU read-side critical sections have access only to
 * conn fields and its PE data, see ip_vs_conn_rcu_free() for reference.
 */
static inline bool __ip_vs_conn_get(struct ip_vs_conn *cp)
{
	return atomic_inc_not_zero(&cp->refcnt);
}

/* put back the conn without restarting its timer */
static inline void __ip_vs_conn_put(struct ip_vs_conn *cp)
{
	smp_mb__before_atomic();
	atomic_dec(&cp->refcnt);
}
void ip_vs_conn_put(struct ip_vs_conn *cp);
void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport);

struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af,
				  const union nf_inet_addr *daddr,
				  __be16 dport, unsigned int flags,
				  struct ip_vs_dest *dest, __u32 fwmark);
void ip_vs_conn_expire_now(struct ip_vs_conn *cp);

const char *ip_vs_state_name(__u16 proto, int state);

void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp);
int ip_vs_check_template(struct ip_vs_conn *ct);
void ip_vs_random_dropentry(struct netns_ipvs *ipvs);
int ip_vs_conn_init(void);
void ip_vs_conn_cleanup(void);

static inline void ip_vs_control_del(struct ip_vs_conn *cp)
{
	struct ip_vs_conn *ctl_cp = cp->control;
	if (!ctl_cp) {
		IP_VS_ERR_BUF("request control DEL for uncontrolled: "
			      "%s:%d to %s:%d\n",
			      IP_VS_DBG_ADDR(cp->af, &cp->caddr),
			      ntohs(cp->cport),
			      IP_VS_DBG_ADDR(cp->af, &cp->vaddr),
			      ntohs(cp->vport));

		return;
	}

	IP_VS_DBG_BUF(7, "DELeting control for: "
		      "cp.dst=%s:%d ctl_cp.dst=%s:%d\n",
		      IP_VS_DBG_ADDR(cp->af, &cp->caddr),
		      ntohs(cp->cport),
		      IP_VS_DBG_ADDR(cp->af, &ctl_cp->caddr),
		      ntohs(ctl_cp->cport));

	cp->control = NULL;
	if (atomic_read(&ctl_cp->n_control) == 0) {
		IP_VS_ERR_BUF("BUG control DEL with n=0 : "
			      "%s:%d to %s:%d\n",
			      IP_VS_DBG_ADDR(cp->af, &cp->caddr),
			      ntohs(cp->cport),
			      IP_VS_DBG_ADDR(cp->af, &cp->vaddr),
			      ntohs(cp->vport));

		return;
	}
	atomic_dec(&ctl_cp->n_control);
}

static inline void
ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp)
{
	if (cp->control) {
		IP_VS_ERR_BUF("request control ADD for already controlled: "
			      "%s:%d to %s:%d\n",
			      IP_VS_DBG_ADDR(cp->af, &cp->caddr),
			      ntohs(cp->cport),
			      IP_VS_DBG_ADDR(cp->af, &cp->vaddr),
			      ntohs(cp->vport));

		ip_vs_control_del(cp);
	}

	IP_VS_DBG_BUF(7, "ADDing control for: "
		      "cp.dst=%s:%d ctl_cp.dst=%s:%d\n",
		      IP_VS_DBG_ADDR(cp->af, &cp->caddr),
		      ntohs(cp->cport),
		      IP_VS_DBG_ADDR(cp->af, &ctl_cp->caddr),
		      ntohs(ctl_cp->cport));

	cp->control = ctl_cp;
	atomic_inc(&ctl_cp->n_control);
}

/* IPVS netns init & cleanup functions */
int ip_vs_estimator_net_init(struct netns_ipvs *ipvs);
int ip_vs_control_net_init(struct netns_ipvs *ipvs);
int ip_vs_protocol_net_init(struct netns_ipvs *ipvs);
int ip_vs_app_net_init(struct netns_ipvs *ipvs);
int ip_vs_conn_net_init(struct netns_ipvs *ipvs);
int ip_vs_sync_net_init(struct netns_ipvs *ipvs);
void ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs);
void ip_vs_app_net_cleanup(struct netns_ipvs *ipvs);
void ip_vs_protocol_net_cleanup(struct netns_ipvs *ipvs);
void ip_vs_control_net_cleanup(struct netns_ipvs *ipvs);
void ip_vs_estimator_net_cleanup(struct netns_ipvs *ipvs);
void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs);
void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs);

/* IPVS application functions
 * (from ip_vs_app.c)
 */
#define IP_VS_APP_MAX_PORTS  8
struct ip_vs_app *register_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app);
void unregister_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app);
int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
void ip_vs_unbind_app(struct ip_vs_conn *cp);
int register_ip_vs_app_inc(struct netns_ipvs *ipvs, struct ip_vs_app *app, __u16 proto,
			   __u16 port);
int ip_vs_app_inc_get(struct ip_vs_app *inc);
void ip_vs_app_inc_put(struct ip_vs_app *inc);

int ip_vs_app_pkt_out(struct ip_vs_conn *, struct sk_buff *skb);
int ip_vs_app_pkt_in(struct ip_vs_conn *, struct sk_buff *skb);

int register_ip_vs_pe(struct ip_vs_pe *pe);
int unregister_ip_vs_pe(struct ip_vs_pe *pe);
struct ip_vs_pe *ip_vs_pe_getbyname(const char *name);
struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name);

/* Use a #define to avoid all of module.h just for these trivial ops */
#define ip_vs_pe_get(pe)			\
	if (pe && pe->module)			\
		__module_get(pe->module);

#define ip_vs_pe_put(pe)			\
	if (pe && pe->module)			\
		module_put(pe->module);

/* IPVS protocol functions (from ip_vs_proto.c) */
int ip_vs_protocol_init(void);
void ip_vs_protocol_cleanup(void);
void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags);
int *ip_vs_create_timeout_table(int *table, int size);
int ip_vs_set_state_timeout(int *table, int num, const char *const *names,
			    const char *name, int to);
void ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp,
			       const struct sk_buff *skb, int offset,
			       const char *msg);

extern struct ip_vs_protocol ip_vs_protocol_tcp;
extern struct ip_vs_protocol ip_vs_protocol_udp;
extern struct ip_vs_protocol ip_vs_protocol_icmp;
extern struct ip_vs_protocol ip_vs_protocol_esp;
extern struct ip_vs_protocol ip_vs_protocol_ah;
extern struct ip_vs_protocol ip_vs_protocol_sctp;

/* Registering/unregistering scheduler functions
 * (from ip_vs_sched.c)
 */
int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
int ip_vs_bind_scheduler(struct ip_vs_service *svc,
			 struct ip_vs_scheduler *scheduler);
void ip_vs_unbind_scheduler(struct ip_vs_service *svc,
			    struct ip_vs_scheduler *sched);
struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name);
void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler);
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);
int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
		struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph);

void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg);

/* IPVS control data and functions (from ip_vs_ctl.c) */
extern struct ip_vs_stats ip_vs_stats;
extern int sysctl_ip_vs_sync_ver;

struct ip_vs_service *
ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u32 fwmark, __u16 protocol,
		  const union nf_inet_addr *vaddr, __be16 vport);

bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol,
			    const union nf_inet_addr *daddr, __be16 dport);

int ip_vs_use_count_inc(void);
void ip_vs_use_count_dec(void);
int ip_vs_register_nl_ioctl(void);
void ip_vs_unregister_nl_ioctl(void);
int ip_vs_control_init(void);
void ip_vs_control_cleanup(void);
struct ip_vs_dest *
ip_vs_find_dest(struct netns_ipvs *ipvs, int svc_af, int dest_af,
		const union nf_inet_addr *daddr, __be16 dport,
		const union nf_inet_addr *vaddr, __be16 vport,
		__u16 protocol, __u32 fwmark, __u32 flags);
void ip_vs_try_bind_dest(struct ip_vs_conn *cp);

static inline void ip_vs_dest_hold(struct ip_vs_dest *dest)
{
	atomic_inc(&dest->refcnt);
}

static inline void ip_vs_dest_put(struct ip_vs_dest *dest)
{
	smp_mb__before_atomic();
	atomic_dec(&dest->refcnt);
}

static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest)
{
	if (atomic_dec_return(&dest->refcnt) < 0)
		kfree(dest);
}

/* IPVS sync daemon data and function prototypes
 * (from ip_vs_sync.c)
 */
int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *cfg,
		      int state);
int stop_sync_thread(struct netns_ipvs *ipvs, int state);
void ip_vs_sync_conn(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts);

/* IPVS rate estimator prototypes (from ip_vs_est.c) */
void ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats);
void ip_vs_stop_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats);
void ip_vs_zero_estimator(struct ip_vs_stats *stats);
void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats);

/* Various IPVS packet transmitters (from ip_vs_xmit.c) */
int ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
		    struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
int ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
		      struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
int ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
		   struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
int ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
		      struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
int ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
		  struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
int ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
		    struct ip_vs_protocol *pp, int offset,
		    unsigned int hooknum, struct ip_vs_iphdr *iph);
void ip_vs_dest_dst_rcu_free(struct rcu_head *head);

#ifdef CONFIG_IP_VS_IPV6
int ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
			 struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
int ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
		      struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
int ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
			 struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
int ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
		     struct ip_vs_protocol *pp, struct ip_vs_iphdr *iph);
int ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
		       struct ip_vs_protocol *pp, int offset,
		       unsigned int hooknum, struct ip_vs_iphdr *iph);
#endif

#ifdef CONFIG_SYSCTL
/* This is a simple mechanism to ignore packets when
 * we are loaded. Just set ip_vs_drop_rate to 'n' and
 * we start to drop 1/rate of the packets
 */
static inline int ip_vs_todrop(struct netns_ipvs *ipvs)
{
	if (!ipvs->drop_rate)
		return 0;
	if (--ipvs->drop_counter > 0)
		return 0;
	ipvs->drop_counter = ipvs->drop_rate;
	return 1;
}
#else
static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { return 0; }
#endif

/* ip_vs_fwd_tag returns the forwarding tag of the connection */
#define IP_VS_FWD_METHOD(cp)  (cp->flags & IP_VS_CONN_F_FWD_MASK)

static inline char ip_vs_fwd_tag(struct ip_vs_conn *cp)
{
	char fwd;

	switch (IP_VS_FWD_METHOD(cp)) {
	case IP_VS_CONN_F_MASQ:
		fwd = 'M'; break;
	case IP_VS_CONN_F_LOCALNODE:
		fwd = 'L'; break;
	case IP_VS_CONN_F_TUNNEL:
		fwd = 'T'; break;
	case IP_VS_CONN_F_DROUTE:
		fwd = 'R'; break;
	case IP_VS_CONN_F_BYPASS:
		fwd = 'B'; break;
	default:
		fwd = '?'; break;
	}
	return fwd;
}

void ip_vs_nat_icmp(struct sk_buff *skb, struct ip_vs_protocol *pp,
		    struct ip_vs_conn *cp, int dir);

#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 dir);
#endif

__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset);

static inline __wsum ip_vs_check_diff4(__be32 old, __be32 new, __wsum oldsum)
{
	__be32 diff[2] = { ~old, new };

	return csum_partial(diff, sizeof(diff), oldsum);
}

#ifdef CONFIG_IP_VS_IPV6
static inline __wsum ip_vs_check_diff16(const __be32 *old, const __be32 *new,
					__wsum oldsum)
{
	__be32 diff[8] = { ~old[3], ~old[2], ~old[1], ~old[0],
			    new[3],  new[2],  new[1],  new[0] };

	return csum_partial(diff, sizeof(diff), oldsum);
}
#endif

static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum)
{
	__be16 diff[2] = { ~old, new };

	return csum_partial(diff, sizeof(diff), oldsum);
}

/* Forget current conntrack (unconfirmed) and attach notrack entry */
static inline void ip_vs_notrack(struct sk_buff *skb)
{
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
	enum ip_conntrack_info ctinfo;
	struct nf_conn *ct = nf_ct_get(skb, &ctinfo);

	if (!ct || !nf_ct_is_untracked(ct)) {
		nf_conntrack_put(skb->nfct);
		skb->nfct = &nf_ct_untracked_get()->ct_general;
		skb->nfctinfo = IP_CT_NEW;
		nf_conntrack_get(skb->nfct);
	}
#endif
}

#ifdef CONFIG_IP_VS_NFCT
/* Netfilter connection tracking
 * (from ip_vs_nfct.c)
 */
static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs)
{
#ifdef CONFIG_SYSCTL
	return ipvs->sysctl_conntrack;
#else
	return 0;
#endif
}

void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp,
			    int outin);
int ip_vs_confirm_conntrack(struct sk_buff *skb);
void ip_vs_nfct_expect_related(struct sk_buff *skb, struct nf_conn *ct,
			       struct ip_vs_conn *cp, u_int8_t proto,
			       const __be16 port, int from_rs);
void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp);

#else

static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs)
{
	return 0;
}

static inline void ip_vs_update_conntrack(struct sk_buff *skb,
					  struct ip_vs_conn *cp, int outin)
{
}

static inline int ip_vs_confirm_conntrack(struct sk_buff *skb)
{
	return NF_ACCEPT;
}

static inline void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp)
{
}
#endif /* CONFIG_IP_VS_NFCT */

/* Really using conntrack? */
static inline bool ip_vs_conn_uses_conntrack(struct ip_vs_conn *cp,
					     struct sk_buff *skb)
{
#ifdef CONFIG_IP_VS_NFCT
	enum ip_conntrack_info ctinfo;
	struct nf_conn *ct;

	if (!(cp->flags & IP_VS_CONN_F_NFCT))
		return false;
	ct = nf_ct_get(skb, &ctinfo);
	if (ct && !nf_ct_is_untracked(ct))
		return true;
#endif
	return false;
}

static inline int
ip_vs_dest_conn_overhead(struct ip_vs_dest *dest)
{
	/* We think the overhead of processing active connections is 256
	 * times higher than that of inactive connections in average. (This
	 * 256 times might not be accurate, we will change it later) We
	 * use the following formula to estimate the overhead now:
	 *		  dest->activeconns*256 + dest->inactconns
	 */
	return (atomic_read(&dest->activeconns) << 8) +
		atomic_read(&dest->inactconns);
}

#endif	/* _NET_IP_VS_H */
OpenPOWER on IntegriCloud