forked from CSL-KU/riscv-linux
-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathip_vs.h
1637 lines (1394 loc) · 46.7 KB
/
ip_vs.h
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
/* SPDX-License-Identifier: GPL-2.0 */
/* 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/refcount.h> /* for struct refcount_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 */
refcount_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 */
refcount_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);
/* create connections for real-server outgoing packets */
struct ip_vs_conn* (*conn_out)(struct ip_vs_service *svc,
struct ip_vs_dest *dest,
struct sk_buff *skb,
const struct ip_vs_iphdr *iph,
__be16 dport, __be16 cport);
};
/* 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;
atomic_t conn_out_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 READ_ONCE(ipvs->sysctl_sync_threshold[1]);
}
static inline unsigned int sysctl_sync_refresh_period(struct netns_ipvs *ipvs)
{
return READ_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)