aboutsummaryrefslogtreecommitdiffstats
path: root/include/net/ip_vs.h
blob: b7bbd6c28cfa17dde6fa3a972d33635c5a498312 (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
/*
 *      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 */

/* old ipvsadm versions still include this file directly */
#ifdef __KERNEL__

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

#include <linux/sysctl.h>               /* for ctl_path */
#include <linux/list.h>                 /* for struct list_head */
#include <linux/spinlock.h>             /* for struct rwlock_t */
#include <asm/atomic.h>                 /* for struct atomic_t */
#include <linux/compiler.h>
#include <linux/timer.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>			/* for ipv6_addr_copy */
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
#include <net/netfilter/nf_conntrack.h>
#endif

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


struct ip_vs_iphdr {
	int len;
	__u8 protocol;
	union nf_inet_addr saddr;
	union nf_inet_addr daddr;
};

static inline void
ip_vs_fill_iphdr(int af, const void *nh, struct ip_vs_iphdr *iphdr)
{
#ifdef CONFIG_IP_VS_IPV6
	if (af == AF_INET6) {
		const struct ipv6hdr *iph = nh;
		iphdr->len = sizeof(struct ipv6hdr);
		iphdr->protocol = iph->nexthdr;
		ipv6_addr_copy(&iphdr->saddr.in6, &iph->saddr);
		ipv6_addr_copy(&iphdr->daddr.in6, &iph->daddr);
	} else
#endif
	{
		const struct iphdr *iph = nh;
		iphdr->len = iph->ihl * 4;
		iphdr->protocol = iph->protocol;
		iphdr->saddr.ip = iph->saddr;
		iphdr->daddr.ip = iph->daddr;
	}
}

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)
		ipv6_addr_copy(&dst->in6, &src->in6);
	else
#endif
	dst->ip = src->ip;
}

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>

extern 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, "[%pI6]",
			       &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

#define	IP_VS_WAIT_WHILE(expr)	while (expr) { cpu_relax(); }


/*
 *      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_INIT_CLI,
	IP_VS_SCTP_S_INIT_SER,
	IP_VS_SCTP_S_INIT_ACK_CLI,
	IP_VS_SCTP_S_INIT_ACK_SER,
	IP_VS_SCTP_S_ECHO_CLI,
	IP_VS_SCTP_S_ECHO_SER,
	IP_VS_SCTP_S_ESTABLISHED,
	IP_VS_SCTP_S_SHUT_CLI,
	IP_VS_SCTP_S_SHUT_SER,
	IP_VS_SCTP_S_SHUT_ACK_CLI,
	IP_VS_SCTP_S_SHUT_ACK_SER,
	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 */
};


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

	u64			last_inbytes;
	u64			last_outbytes;
	u32			last_conns;
	u32			last_inpkts;
	u32			last_outpkts;

	u32			cps;
	u32			inpps;
	u32			outpps;
	u32			inbps;
	u32			outbps;
};

struct ip_vs_stats {
	struct ip_vs_stats_user	ustats;         /* statistics */
	struct ip_vs_estimator	est;		/* estimator */

	spinlock_t              lock;           /* spin lock */
};

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

struct ip_vs_protocol {
	struct ip_vs_protocol	*next;
	char			*name;
	u16			protocol;
	u16			num_states;
	int			dont_defrag;
	atomic_t		appcnt;		/* counter of proto app incs */
	int			*timeout_table;	/* protocol timeout table */

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

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

	int (*conn_schedule)(int af, struct sk_buff *skb,
			     struct ip_vs_protocol *pp,
			     int *verdict, struct ip_vs_conn **cpp);

	struct ip_vs_conn *
	(*conn_in_get)(int af,
		       const struct sk_buff *skb,
		       struct ip_vs_protocol *pp,
		       const struct ip_vs_iphdr *iph,
		       unsigned int proto_off,
		       int inverse);

	struct ip_vs_conn *
	(*conn_out_get)(int af,
			const struct sk_buff *skb,
			struct ip_vs_protocol *pp,
			const struct ip_vs_iphdr *iph,
			unsigned int proto_off,
			int inverse);

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

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

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

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

	int (*state_transition)(struct ip_vs_conn *cp, int direction,
				const struct sk_buff *skb,
				struct ip_vs_protocol *pp);

	int (*register_app)(struct ip_vs_app *inc);

	void (*unregister_app)(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_protocol *pp, int flags);

	int (*set_state_timeout)(struct ip_vs_protocol *pp, char *sname, int to);
};

extern struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto);

struct ip_vs_conn_param {
	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 list_head        c_list;         /* hashed list heads */

	/* Protocol, addresses and port numbers */
	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 */
	__be16                   cport;
	__be16                   vport;
	__be16                   dport;
	__u16                   protocol;       /* Which protocol (TCP/UDP) */

	/* 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
						 */

	/* 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);

	/* 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 */

	char			*pe_data;
	__u8			pe_data_len;
};


/*
 *	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 */
	u16			port;
	u32			fwmark;		/* firwall mark of service */

	/* virtual service options */
	char			*sched_name;
	char			*pe_name;
	unsigned		flags;		/* virtual service flags */
	unsigned		timeout;	/* persistent timeout in sec */
	u32			netmask;	/* persistent netmask */
};


struct ip_vs_dest_user_kern {
	/* destination server address */
	union nf_inet_addr	addr;
	u16			port;

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

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


/*
 *	The information about the virtual service offered to the net
 *	and the forwarding entries
 */
struct ip_vs_service {
	struct list_head	s_list;   /* for normal service table */
	struct list_head	f_list;   /* for fwmark-based service table */
	atomic_t		refcnt;   /* reference counter */
	atomic_t		usecnt;   /* use 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		flags;	  /* service status flags */
	unsigned		timeout;  /* persistent timeout in ticks */
	__be32			netmask;  /* grouping granularity */

	struct list_head	destinations;  /* real server d-linked list */
	__u32			num_dests;     /* number of servers */
	struct ip_vs_stats      stats;         /* statistics for the service */
	struct ip_vs_app	*inc;	  /* bind conns to this app inc */

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

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


/*
 *	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 list_head	d_list;   /* for table with all the dests */

	u16			af;		/* address family */
	union nf_inet_addr	addr;		/* IP address of the server */
	__be16			port;		/* port number of the server */
	volatile unsigned	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 */

	/* 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 dst_entry	*dst_cache;	/* destination cache entry */
	u32			dst_rtos;	/* RT_TOS(tos) for dst */
	u32			dst_cookie;
#ifdef CONFIG_IP_VS_IPV6
	struct in6_addr		dst_saddr;
#endif

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


/*
 *	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 */
	int (*done_service)(struct ip_vs_service *svc);
	/* scheduler updating service */
	int (*update_service)(struct ip_vs_service *svc);

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

/* 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 */

	/*
	 * 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, unsigned int proto_off,
		       int inverse);

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


/*
 *      IPVS core functions
 *      (from ip_vs_core.c)
 */
extern const char *ip_vs_proto_name(unsigned proto);
extern 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(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->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(int af, const struct sk_buff *skb,
					    struct ip_vs_protocol *pp,
					    const struct ip_vs_iphdr *iph,
					    unsigned int proto_off,
					    int inverse);

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(int af, const struct sk_buff *skb,
					     struct ip_vs_protocol *pp,
					     const struct ip_vs_iphdr *iph,
					     unsigned int proto_off,
					     int inverse);

/* put back the conn without restarting its timer */
static inline void __ip_vs_conn_put(struct ip_vs_conn *cp)
{
	atomic_dec(&cp->refcnt);
}
extern void ip_vs_conn_put(struct ip_vs_conn *cp);
extern 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,
				  const union nf_inet_addr *daddr,
				  __be16 dport, unsigned flags,
				  struct ip_vs_dest *dest);
extern void ip_vs_conn_expire_now(struct ip_vs_conn *cp);

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

extern void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp);
extern int ip_vs_check_template(struct ip_vs_conn *ct);
extern void ip_vs_random_dropentry(void);
extern int ip_vs_conn_init(void);
extern 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 application functions
 *      (from ip_vs_app.c)
 */
#define IP_VS_APP_MAX_PORTS  8
extern int register_ip_vs_app(struct ip_vs_app *app);
extern void unregister_ip_vs_app(struct ip_vs_app *app);
extern int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
extern void ip_vs_unbind_app(struct ip_vs_conn *cp);
extern int
register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port);
extern int ip_vs_app_inc_get(struct ip_vs_app *inc);
extern void ip_vs_app_inc_put(struct ip_vs_app *inc);

extern int ip_vs_app_pkt_out(struct ip_vs_conn *, struct sk_buff *skb);
extern int ip_vs_app_pkt_in(struct ip_vs_conn *, struct sk_buff *skb);
extern int ip_vs_app_init(void);
extern void ip_vs_app_cleanup(void);

void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe);
void ip_vs_unbind_pe(struct ip_vs_service *svc);
int register_ip_vs_pe(struct ip_vs_pe *pe);
int unregister_ip_vs_pe(struct ip_vs_pe *pe);
extern struct ip_vs_pe *ip_vs_pe_get(const char *name);
extern void ip_vs_pe_put(struct ip_vs_pe *pe);

/*
 *	IPVS protocol functions (from ip_vs_proto.c)
 */
extern int ip_vs_protocol_init(void);
extern void ip_vs_protocol_cleanup(void);
extern void ip_vs_protocol_timeout_change(int flags);
extern int *ip_vs_create_timeout_table(int *table, int size);
extern int
ip_vs_set_state_timeout(int *table, int num, const char *const *names,
			const char *name, int to);
extern 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)
 */
extern int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
extern int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
extern int ip_vs_bind_scheduler(struct ip_vs_service *svc,
				struct ip_vs_scheduler *scheduler);
extern int ip_vs_unbind_scheduler(struct ip_vs_service *svc);
extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name);
extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler);
extern struct ip_vs_conn *
ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
	       struct ip_vs_protocol *pp, int *ignored);
extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
			struct ip_vs_protocol *pp);


/*
 *      IPVS control data and functions (from ip_vs_ctl.c)
 */
extern int sysctl_ip_vs_cache_bypass;
extern int sysctl_ip_vs_expire_nodest_conn;
extern int sysctl_ip_vs_expire_quiescent_template;
extern int sysctl_ip_vs_sync_threshold[2];
extern int sysctl_ip_vs_nat_icmp_send;
extern int sysctl_ip_vs_conntrack;
extern int sysctl_ip_vs_snat_reroute;
extern struct ip_vs_stats ip_vs_stats;
extern const struct ctl_path net_vs_ctl_path[];

extern struct ip_vs_service *
ip_vs_service_get(int af, __u32 fwmark, __u16 protocol,
		  const union nf_inet_addr *vaddr, __be16 vport);

static inline void ip_vs_service_put(struct ip_vs_service *svc)
{
	atomic_dec(&svc->usecnt);
}

extern struct ip_vs_dest *
ip_vs_lookup_real_service(int af, __u16 protocol,
			  const union nf_inet_addr *daddr, __be16 dport);

extern int ip_vs_use_count_inc(void);
extern void ip_vs_use_count_dec(void);
extern int ip_vs_control_init(void);
extern void ip_vs_control_cleanup(void);
extern struct ip_vs_dest *
ip_vs_find_dest(int af, const union nf_inet_addr *daddr, __be16 dport,
		const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol);
extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);


/*
 *      IPVS sync daemon data and function prototypes
 *      (from ip_vs_sync.c)
 */
extern volatile int ip_vs_sync_state;
extern volatile int ip_vs_master_syncid;
extern volatile int ip_vs_backup_syncid;
extern char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
extern char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
extern int start_sync_thread(int state, char *mcast_ifn, __u8 syncid);
extern int stop_sync_thread(int state);
extern void ip_vs_sync_conn(struct ip_vs_conn *cp);


/*
 *      IPVS rate estimator prototypes (from ip_vs_est.c)
 */
extern int ip_vs_estimator_init(void);
extern void ip_vs_estimator_cleanup(void);
extern void ip_vs_new_estimator(struct ip_vs_stats *stats);
extern void ip_vs_kill_estimator(struct ip_vs_stats *stats);
extern void ip_vs_zero_estimator(struct ip_vs_stats *stats);

/*
 *	Various IPVS packet transmitters (from ip_vs_xmit.c)
 */
extern int ip_vs_null_xmit
(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
extern int ip_vs_bypass_xmit
(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
extern int ip_vs_nat_xmit
(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
extern int ip_vs_tunnel_xmit
(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
extern int ip_vs_dr_xmit
(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp);
extern int ip_vs_icmp_xmit
(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, int offset);
extern void ip_vs_dst_reset(struct ip_vs_dest *dest);

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

/*
 *	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
 */
extern int ip_vs_drop_rate;
extern int ip_vs_drop_counter;

static __inline__ int ip_vs_todrop(void)
{
	if (!ip_vs_drop_rate) return 0;
	if (--ip_vs_drop_counter > 0) return 0;
	ip_vs_drop_counter = ip_vs_drop_rate;
	return 1;
}

/*
 *      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;
}

extern 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
extern void ip_vs_nat_icmp_v6(struct sk_buff *skb, struct ip_vs_protocol *pp,
			      struct ip_vs_conn *cp, int dir);
#endif

extern __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 = ct = nf_ct_get(skb, &ctinfo);

	if (!ct || !nf_ct_is_untracked(ct)) {
		nf_reset(skb);
		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(void)
{
	return sysctl_ip_vs_conntrack;
}

extern void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp,
				   int outin);
extern int ip_vs_confirm_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp);
extern 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);
extern void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp);

#else

static inline int ip_vs_conntrack_enabled(void)
{
	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,
					  struct ip_vs_conn *cp)
{
	return NF_ACCEPT;
}

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

#endif /* __KERNEL__ */

#endif	/* _NET_IP_VS_H */