forked from microsoft/WSL2-Linux-Kernel
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtcp.h
1928 lines (1623 loc) · 55.8 KB
/
tcp.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
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Definitions for the TCP module.
*
* Version: @(#)tcp.h 1.0.5 05/23/93
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#ifndef _TCP_H
#define _TCP_H
#define TCP_DEBUG 1
#define FASTRETRANS_DEBUG 1
/* Cancel timers, when they are not required. */
#undef TCP_CLEAR_TIMERS
#include <linux/config.h>
#include <linux/list.h>
#include <linux/tcp.h>
#include <linux/slab.h>
#include <linux/cache.h>
#include <linux/percpu.h>
#include <net/checksum.h>
#include <net/request_sock.h>
#include <net/sock.h>
#include <net/snmp.h>
#include <net/ip.h>
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
#include <linux/ipv6.h>
#endif
#include <linux/seq_file.h>
/* This is for all connections with a full identity, no wildcards.
* New scheme, half the table is for TIME_WAIT, the other half is
* for the rest. I'll experiment with dynamic table growth later.
*/
struct tcp_ehash_bucket {
rwlock_t lock;
struct hlist_head chain;
} __attribute__((__aligned__(8)));
/* This is for listening sockets, thus all sockets which possess wildcards. */
#define TCP_LHTABLE_SIZE 32 /* Yes, really, this is all you need. */
/* There are a few simple rules, which allow for local port reuse by
* an application. In essence:
*
* 1) Sockets bound to different interfaces may share a local port.
* Failing that, goto test 2.
* 2) If all sockets have sk->sk_reuse set, and none of them are in
* TCP_LISTEN state, the port may be shared.
* Failing that, goto test 3.
* 3) If all sockets are bound to a specific inet_sk(sk)->rcv_saddr local
* address, and none of them are the same, the port may be
* shared.
* Failing this, the port cannot be shared.
*
* The interesting point, is test #2. This is what an FTP server does
* all day. To optimize this case we use a specific flag bit defined
* below. As we add sockets to a bind bucket list, we perform a
* check of: (newsk->sk_reuse && (newsk->sk_state != TCP_LISTEN))
* As long as all sockets added to a bind bucket pass this test,
* the flag bit will be set.
* The resulting situation is that tcp_v[46]_verify_bind() can just check
* for this flag bit, if it is set and the socket trying to bind has
* sk->sk_reuse set, we don't even have to walk the owners list at all,
* we return that it is ok to bind this socket to the requested local port.
*
* Sounds like a lot of work, but it is worth it. In a more naive
* implementation (ie. current FreeBSD etc.) the entire list of ports
* must be walked for each data port opened by an ftp server. Needless
* to say, this does not scale at all. With a couple thousand FTP
* users logged onto your box, isn't it nice to know that new data
* ports are created in O(1) time? I thought so. ;-) -DaveM
*/
struct tcp_bind_bucket {
unsigned short port;
signed short fastreuse;
struct hlist_node node;
struct hlist_head owners;
};
#define tb_for_each(tb, node, head) hlist_for_each_entry(tb, node, head, node)
struct tcp_bind_hashbucket {
spinlock_t lock;
struct hlist_head chain;
};
static inline struct tcp_bind_bucket *__tb_head(struct tcp_bind_hashbucket *head)
{
return hlist_entry(head->chain.first, struct tcp_bind_bucket, node);
}
static inline struct tcp_bind_bucket *tb_head(struct tcp_bind_hashbucket *head)
{
return hlist_empty(&head->chain) ? NULL : __tb_head(head);
}
extern struct tcp_hashinfo {
/* This is for sockets with full identity only. Sockets here will
* always be without wildcards and will have the following invariant:
*
* TCP_ESTABLISHED <= sk->sk_state < TCP_CLOSE
*
* First half of the table is for sockets not in TIME_WAIT, second half
* is for TIME_WAIT sockets only.
*/
struct tcp_ehash_bucket *__tcp_ehash;
/* Ok, let's try this, I give up, we do need a local binding
* TCP hash as well as the others for fast bind/connect.
*/
struct tcp_bind_hashbucket *__tcp_bhash;
int __tcp_bhash_size;
int __tcp_ehash_size;
/* All sockets in TCP_LISTEN state will be in here. This is the only
* table where wildcard'd TCP sockets can exist. Hash function here
* is just local port number.
*/
struct hlist_head __tcp_listening_hash[TCP_LHTABLE_SIZE];
/* All the above members are written once at bootup and
* never written again _or_ are predominantly read-access.
*
* Now align to a new cache line as all the following members
* are often dirty.
*/
rwlock_t __tcp_lhash_lock ____cacheline_aligned;
atomic_t __tcp_lhash_users;
wait_queue_head_t __tcp_lhash_wait;
spinlock_t __tcp_portalloc_lock;
} tcp_hashinfo;
#define tcp_ehash (tcp_hashinfo.__tcp_ehash)
#define tcp_bhash (tcp_hashinfo.__tcp_bhash)
#define tcp_ehash_size (tcp_hashinfo.__tcp_ehash_size)
#define tcp_bhash_size (tcp_hashinfo.__tcp_bhash_size)
#define tcp_listening_hash (tcp_hashinfo.__tcp_listening_hash)
#define tcp_lhash_lock (tcp_hashinfo.__tcp_lhash_lock)
#define tcp_lhash_users (tcp_hashinfo.__tcp_lhash_users)
#define tcp_lhash_wait (tcp_hashinfo.__tcp_lhash_wait)
#define tcp_portalloc_lock (tcp_hashinfo.__tcp_portalloc_lock)
extern kmem_cache_t *tcp_bucket_cachep;
extern struct tcp_bind_bucket *tcp_bucket_create(struct tcp_bind_hashbucket *head,
unsigned short snum);
extern void tcp_bucket_destroy(struct tcp_bind_bucket *tb);
extern void tcp_bucket_unlock(struct sock *sk);
extern int tcp_port_rover;
/* These are AF independent. */
static __inline__ int tcp_bhashfn(__u16 lport)
{
return (lport & (tcp_bhash_size - 1));
}
extern void tcp_bind_hash(struct sock *sk, struct tcp_bind_bucket *tb,
unsigned short snum);
#if (BITS_PER_LONG == 64)
#define TCP_ADDRCMP_ALIGN_BYTES 8
#else
#define TCP_ADDRCMP_ALIGN_BYTES 4
#endif
/* This is a TIME_WAIT bucket. It works around the memory consumption
* problems of sockets in such a state on heavily loaded servers, but
* without violating the protocol specification.
*/
struct tcp_tw_bucket {
/*
* Now struct sock also uses sock_common, so please just
* don't add nothing before this first member (__tw_common) --acme
*/
struct sock_common __tw_common;
#define tw_family __tw_common.skc_family
#define tw_state __tw_common.skc_state
#define tw_reuse __tw_common.skc_reuse
#define tw_bound_dev_if __tw_common.skc_bound_dev_if
#define tw_node __tw_common.skc_node
#define tw_bind_node __tw_common.skc_bind_node
#define tw_refcnt __tw_common.skc_refcnt
volatile unsigned char tw_substate;
unsigned char tw_rcv_wscale;
__u16 tw_sport;
/* Socket demultiplex comparisons on incoming packets. */
/* these five are in inet_sock */
__u32 tw_daddr
__attribute__((aligned(TCP_ADDRCMP_ALIGN_BYTES)));
__u32 tw_rcv_saddr;
__u16 tw_dport;
__u16 tw_num;
/* And these are ours. */
int tw_hashent;
int tw_timeout;
__u32 tw_rcv_nxt;
__u32 tw_snd_nxt;
__u32 tw_rcv_wnd;
__u32 tw_ts_recent;
long tw_ts_recent_stamp;
unsigned long tw_ttd;
struct tcp_bind_bucket *tw_tb;
struct hlist_node tw_death_node;
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
struct in6_addr tw_v6_daddr;
struct in6_addr tw_v6_rcv_saddr;
int tw_v6_ipv6only;
#endif
};
static __inline__ void tw_add_node(struct tcp_tw_bucket *tw,
struct hlist_head *list)
{
hlist_add_head(&tw->tw_node, list);
}
static __inline__ void tw_add_bind_node(struct tcp_tw_bucket *tw,
struct hlist_head *list)
{
hlist_add_head(&tw->tw_bind_node, list);
}
static inline int tw_dead_hashed(struct tcp_tw_bucket *tw)
{
return tw->tw_death_node.pprev != NULL;
}
static __inline__ void tw_dead_node_init(struct tcp_tw_bucket *tw)
{
tw->tw_death_node.pprev = NULL;
}
static __inline__ void __tw_del_dead_node(struct tcp_tw_bucket *tw)
{
__hlist_del(&tw->tw_death_node);
tw_dead_node_init(tw);
}
static __inline__ int tw_del_dead_node(struct tcp_tw_bucket *tw)
{
if (tw_dead_hashed(tw)) {
__tw_del_dead_node(tw);
return 1;
}
return 0;
}
#define tw_for_each(tw, node, head) \
hlist_for_each_entry(tw, node, head, tw_node)
#define tw_for_each_inmate(tw, node, jail) \
hlist_for_each_entry(tw, node, jail, tw_death_node)
#define tw_for_each_inmate_safe(tw, node, safe, jail) \
hlist_for_each_entry_safe(tw, node, safe, jail, tw_death_node)
#define tcptw_sk(__sk) ((struct tcp_tw_bucket *)(__sk))
static inline u32 tcp_v4_rcv_saddr(const struct sock *sk)
{
return likely(sk->sk_state != TCP_TIME_WAIT) ?
inet_sk(sk)->rcv_saddr : tcptw_sk(sk)->tw_rcv_saddr;
}
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
static inline struct in6_addr *__tcp_v6_rcv_saddr(const struct sock *sk)
{
return likely(sk->sk_state != TCP_TIME_WAIT) ?
&inet6_sk(sk)->rcv_saddr : &tcptw_sk(sk)->tw_v6_rcv_saddr;
}
static inline struct in6_addr *tcp_v6_rcv_saddr(const struct sock *sk)
{
return sk->sk_family == AF_INET6 ? __tcp_v6_rcv_saddr(sk) : NULL;
}
#define tcptw_sk_ipv6only(__sk) (tcptw_sk(__sk)->tw_v6_ipv6only)
static inline int tcp_v6_ipv6only(const struct sock *sk)
{
return likely(sk->sk_state != TCP_TIME_WAIT) ?
ipv6_only_sock(sk) : tcptw_sk_ipv6only(sk);
}
#else
# define __tcp_v6_rcv_saddr(__sk) NULL
# define tcp_v6_rcv_saddr(__sk) NULL
# define tcptw_sk_ipv6only(__sk) 0
# define tcp_v6_ipv6only(__sk) 0
#endif
extern kmem_cache_t *tcp_timewait_cachep;
static inline void tcp_tw_put(struct tcp_tw_bucket *tw)
{
if (atomic_dec_and_test(&tw->tw_refcnt)) {
#ifdef INET_REFCNT_DEBUG
printk(KERN_DEBUG "tw_bucket %p released\n", tw);
#endif
kmem_cache_free(tcp_timewait_cachep, tw);
}
}
extern atomic_t tcp_orphan_count;
extern int tcp_tw_count;
extern void tcp_time_wait(struct sock *sk, int state, int timeo);
extern void tcp_tw_deschedule(struct tcp_tw_bucket *tw);
/* Socket demux engine toys. */
#ifdef __BIG_ENDIAN
#define TCP_COMBINED_PORTS(__sport, __dport) \
(((__u32)(__sport)<<16) | (__u32)(__dport))
#else /* __LITTLE_ENDIAN */
#define TCP_COMBINED_PORTS(__sport, __dport) \
(((__u32)(__dport)<<16) | (__u32)(__sport))
#endif
#if (BITS_PER_LONG == 64)
#ifdef __BIG_ENDIAN
#define TCP_V4_ADDR_COOKIE(__name, __saddr, __daddr) \
__u64 __name = (((__u64)(__saddr))<<32)|((__u64)(__daddr));
#else /* __LITTLE_ENDIAN */
#define TCP_V4_ADDR_COOKIE(__name, __saddr, __daddr) \
__u64 __name = (((__u64)(__daddr))<<32)|((__u64)(__saddr));
#endif /* __BIG_ENDIAN */
#define TCP_IPV4_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\
(((*((__u64 *)&(inet_sk(__sk)->daddr)))== (__cookie)) && \
((*((__u32 *)&(inet_sk(__sk)->dport)))== (__ports)) && \
(!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
#define TCP_IPV4_TW_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\
(((*((__u64 *)&(tcptw_sk(__sk)->tw_daddr))) == (__cookie)) && \
((*((__u32 *)&(tcptw_sk(__sk)->tw_dport))) == (__ports)) && \
(!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
#else /* 32-bit arch */
#define TCP_V4_ADDR_COOKIE(__name, __saddr, __daddr)
#define TCP_IPV4_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\
((inet_sk(__sk)->daddr == (__saddr)) && \
(inet_sk(__sk)->rcv_saddr == (__daddr)) && \
((*((__u32 *)&(inet_sk(__sk)->dport)))== (__ports)) && \
(!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
#define TCP_IPV4_TW_MATCH(__sk, __cookie, __saddr, __daddr, __ports, __dif)\
((tcptw_sk(__sk)->tw_daddr == (__saddr)) && \
(tcptw_sk(__sk)->tw_rcv_saddr == (__daddr)) && \
((*((__u32 *)&(tcptw_sk(__sk)->tw_dport))) == (__ports)) && \
(!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
#endif /* 64-bit arch */
#define TCP_IPV6_MATCH(__sk, __saddr, __daddr, __ports, __dif) \
(((*((__u32 *)&(inet_sk(__sk)->dport)))== (__ports)) && \
((__sk)->sk_family == AF_INET6) && \
ipv6_addr_equal(&inet6_sk(__sk)->daddr, (__saddr)) && \
ipv6_addr_equal(&inet6_sk(__sk)->rcv_saddr, (__daddr)) && \
(!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif))))
/* These can have wildcards, don't try too hard. */
static __inline__ int tcp_lhashfn(unsigned short num)
{
return num & (TCP_LHTABLE_SIZE - 1);
}
static __inline__ int tcp_sk_listen_hashfn(struct sock *sk)
{
return tcp_lhashfn(inet_sk(sk)->num);
}
#define MAX_TCP_HEADER (128 + MAX_HEADER)
/*
* Never offer a window over 32767 without using window scaling. Some
* poor stacks do signed 16bit maths!
*/
#define MAX_TCP_WINDOW 32767U
/* Minimal accepted MSS. It is (60+60+8) - (20+20). */
#define TCP_MIN_MSS 88U
/* Minimal RCV_MSS. */
#define TCP_MIN_RCVMSS 536U
/* After receiving this amount of duplicate ACKs fast retransmit starts. */
#define TCP_FASTRETRANS_THRESH 3
/* Maximal reordering. */
#define TCP_MAX_REORDERING 127
/* Maximal number of ACKs sent quickly to accelerate slow-start. */
#define TCP_MAX_QUICKACKS 16U
/* urg_data states */
#define TCP_URG_VALID 0x0100
#define TCP_URG_NOTYET 0x0200
#define TCP_URG_READ 0x0400
#define TCP_RETR1 3 /*
* This is how many retries it does before it
* tries to figure out if the gateway is
* down. Minimal RFC value is 3; it corresponds
* to ~3sec-8min depending on RTO.
*/
#define TCP_RETR2 15 /*
* This should take at least
* 90 minutes to time out.
* RFC1122 says that the limit is 100 sec.
* 15 is ~13-30min depending on RTO.
*/
#define TCP_SYN_RETRIES 5 /* number of times to retry active opening a
* connection: ~180sec is RFC minumum */
#define TCP_SYNACK_RETRIES 5 /* number of times to retry passive opening a
* connection: ~180sec is RFC minumum */
#define TCP_ORPHAN_RETRIES 7 /* number of times to retry on an orphaned
* socket. 7 is ~50sec-16min.
*/
#define TCP_TIMEWAIT_LEN (60*HZ) /* how long to wait to destroy TIME-WAIT
* state, about 60 seconds */
#define TCP_FIN_TIMEOUT TCP_TIMEWAIT_LEN
/* BSD style FIN_WAIT2 deadlock breaker.
* It used to be 3min, new value is 60sec,
* to combine FIN-WAIT-2 timeout with
* TIME-WAIT timer.
*/
#define TCP_DELACK_MAX ((unsigned)(HZ/5)) /* maximal time to delay before sending an ACK */
#if HZ >= 100
#define TCP_DELACK_MIN ((unsigned)(HZ/25)) /* minimal time to delay before sending an ACK */
#define TCP_ATO_MIN ((unsigned)(HZ/25))
#else
#define TCP_DELACK_MIN 4U
#define TCP_ATO_MIN 4U
#endif
#define TCP_RTO_MAX ((unsigned)(120*HZ))
#define TCP_RTO_MIN ((unsigned)(HZ/5))
#define TCP_TIMEOUT_INIT ((unsigned)(3*HZ)) /* RFC 1122 initial RTO value */
#define TCP_RESOURCE_PROBE_INTERVAL ((unsigned)(HZ/2U)) /* Maximal interval between probes
* for local resources.
*/
#define TCP_KEEPALIVE_TIME (120*60*HZ) /* two hours */
#define TCP_KEEPALIVE_PROBES 9 /* Max of 9 keepalive probes */
#define TCP_KEEPALIVE_INTVL (75*HZ)
#define MAX_TCP_KEEPIDLE 32767
#define MAX_TCP_KEEPINTVL 32767
#define MAX_TCP_KEEPCNT 127
#define MAX_TCP_SYNCNT 127
#define TCP_SYNQ_INTERVAL (HZ/5) /* Period of SYNACK timer */
#define TCP_SYNQ_HSIZE 512 /* Size of SYNACK hash table */
#define TCP_PAWS_24DAYS (60 * 60 * 24 * 24)
#define TCP_PAWS_MSL 60 /* Per-host timestamps are invalidated
* after this time. It should be equal
* (or greater than) TCP_TIMEWAIT_LEN
* to provide reliability equal to one
* provided by timewait state.
*/
#define TCP_PAWS_WINDOW 1 /* Replay window for per-host
* timestamps. It must be less than
* minimal timewait lifetime.
*/
#define TCP_TW_RECYCLE_SLOTS_LOG 5
#define TCP_TW_RECYCLE_SLOTS (1<<TCP_TW_RECYCLE_SLOTS_LOG)
/* If time > 4sec, it is "slow" path, no recycling is required,
so that we select tick to get range about 4 seconds.
*/
#if HZ <= 16 || HZ > 4096
# error Unsupported: HZ <= 16 or HZ > 4096
#elif HZ <= 32
# define TCP_TW_RECYCLE_TICK (5+2-TCP_TW_RECYCLE_SLOTS_LOG)
#elif HZ <= 64
# define TCP_TW_RECYCLE_TICK (6+2-TCP_TW_RECYCLE_SLOTS_LOG)
#elif HZ <= 128
# define TCP_TW_RECYCLE_TICK (7+2-TCP_TW_RECYCLE_SLOTS_LOG)
#elif HZ <= 256
# define TCP_TW_RECYCLE_TICK (8+2-TCP_TW_RECYCLE_SLOTS_LOG)
#elif HZ <= 512
# define TCP_TW_RECYCLE_TICK (9+2-TCP_TW_RECYCLE_SLOTS_LOG)
#elif HZ <= 1024
# define TCP_TW_RECYCLE_TICK (10+2-TCP_TW_RECYCLE_SLOTS_LOG)
#elif HZ <= 2048
# define TCP_TW_RECYCLE_TICK (11+2-TCP_TW_RECYCLE_SLOTS_LOG)
#else
# define TCP_TW_RECYCLE_TICK (12+2-TCP_TW_RECYCLE_SLOTS_LOG)
#endif
#define BICTCP_BETA_SCALE 1024 /* Scale factor beta calculation
* max_cwnd = snd_cwnd * beta
*/
#define BICTCP_MAX_INCREMENT 32 /*
* Limit on the amount of
* increment allowed during
* binary search.
*/
#define BICTCP_FUNC_OF_MIN_INCR 11 /*
* log(B/Smin)/log(B/(B-1))+1,
* Smin:min increment
* B:log factor
*/
#define BICTCP_B 4 /*
* In binary search,
* go to point (max+min)/N
*/
/*
* TCP option
*/
#define TCPOPT_NOP 1 /* Padding */
#define TCPOPT_EOL 0 /* End of options */
#define TCPOPT_MSS 2 /* Segment size negotiating */
#define TCPOPT_WINDOW 3 /* Window scaling */
#define TCPOPT_SACK_PERM 4 /* SACK Permitted */
#define TCPOPT_SACK 5 /* SACK Block */
#define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */
/*
* TCP option lengths
*/
#define TCPOLEN_MSS 4
#define TCPOLEN_WINDOW 3
#define TCPOLEN_SACK_PERM 2
#define TCPOLEN_TIMESTAMP 10
/* But this is what stacks really send out. */
#define TCPOLEN_TSTAMP_ALIGNED 12
#define TCPOLEN_WSCALE_ALIGNED 4
#define TCPOLEN_SACKPERM_ALIGNED 4
#define TCPOLEN_SACK_BASE 2
#define TCPOLEN_SACK_BASE_ALIGNED 4
#define TCPOLEN_SACK_PERBLOCK 8
#define TCP_TIME_RETRANS 1 /* Retransmit timer */
#define TCP_TIME_DACK 2 /* Delayed ack timer */
#define TCP_TIME_PROBE0 3 /* Zero window probe timer */
#define TCP_TIME_KEEPOPEN 4 /* Keepalive timer */
/* Flags in tp->nonagle */
#define TCP_NAGLE_OFF 1 /* Nagle's algo is disabled */
#define TCP_NAGLE_CORK 2 /* Socket is corked */
#define TCP_NAGLE_PUSH 4 /* Cork is overriden for already queued data */
/* sysctl variables for tcp */
extern int sysctl_max_syn_backlog;
extern int sysctl_tcp_timestamps;
extern int sysctl_tcp_window_scaling;
extern int sysctl_tcp_sack;
extern int sysctl_tcp_fin_timeout;
extern int sysctl_tcp_tw_recycle;
extern int sysctl_tcp_keepalive_time;
extern int sysctl_tcp_keepalive_probes;
extern int sysctl_tcp_keepalive_intvl;
extern int sysctl_tcp_syn_retries;
extern int sysctl_tcp_synack_retries;
extern int sysctl_tcp_retries1;
extern int sysctl_tcp_retries2;
extern int sysctl_tcp_orphan_retries;
extern int sysctl_tcp_syncookies;
extern int sysctl_tcp_retrans_collapse;
extern int sysctl_tcp_stdurg;
extern int sysctl_tcp_rfc1337;
extern int sysctl_tcp_abort_on_overflow;
extern int sysctl_tcp_max_orphans;
extern int sysctl_tcp_max_tw_buckets;
extern int sysctl_tcp_fack;
extern int sysctl_tcp_reordering;
extern int sysctl_tcp_ecn;
extern int sysctl_tcp_dsack;
extern int sysctl_tcp_mem[3];
extern int sysctl_tcp_wmem[3];
extern int sysctl_tcp_rmem[3];
extern int sysctl_tcp_app_win;
extern int sysctl_tcp_adv_win_scale;
extern int sysctl_tcp_tw_reuse;
extern int sysctl_tcp_frto;
extern int sysctl_tcp_low_latency;
extern int sysctl_tcp_westwood;
extern int sysctl_tcp_vegas_cong_avoid;
extern int sysctl_tcp_vegas_alpha;
extern int sysctl_tcp_vegas_beta;
extern int sysctl_tcp_vegas_gamma;
extern int sysctl_tcp_nometrics_save;
extern int sysctl_tcp_bic;
extern int sysctl_tcp_bic_fast_convergence;
extern int sysctl_tcp_bic_low_window;
extern int sysctl_tcp_bic_beta;
extern int sysctl_tcp_moderate_rcvbuf;
extern int sysctl_tcp_tso_win_divisor;
extern atomic_t tcp_memory_allocated;
extern atomic_t tcp_sockets_allocated;
extern int tcp_memory_pressure;
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
#define TCP_INET_FAMILY(fam) ((fam) == AF_INET)
#else
#define TCP_INET_FAMILY(fam) 1
#endif
/*
* Pointers to address related TCP functions
* (i.e. things that depend on the address family)
*/
struct tcp_func {
int (*queue_xmit) (struct sk_buff *skb,
int ipfragok);
void (*send_check) (struct sock *sk,
struct tcphdr *th,
int len,
struct sk_buff *skb);
int (*rebuild_header) (struct sock *sk);
int (*conn_request) (struct sock *sk,
struct sk_buff *skb);
struct sock * (*syn_recv_sock) (struct sock *sk,
struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst);
int (*remember_stamp) (struct sock *sk);
__u16 net_header_len;
int (*setsockopt) (struct sock *sk,
int level,
int optname,
char __user *optval,
int optlen);
int (*getsockopt) (struct sock *sk,
int level,
int optname,
char __user *optval,
int __user *optlen);
void (*addr2sockaddr) (struct sock *sk,
struct sockaddr *);
int sockaddr_len;
};
/*
* The next routines deal with comparing 32 bit unsigned ints
* and worry about wraparound (automatic with unsigned arithmetic).
*/
static inline int before(__u32 seq1, __u32 seq2)
{
return (__s32)(seq1-seq2) < 0;
}
static inline int after(__u32 seq1, __u32 seq2)
{
return (__s32)(seq2-seq1) < 0;
}
/* is s2<=s1<=s3 ? */
static inline int between(__u32 seq1, __u32 seq2, __u32 seq3)
{
return seq3 - seq2 >= seq1 - seq2;
}
extern struct proto tcp_prot;
DECLARE_SNMP_STAT(struct tcp_mib, tcp_statistics);
#define TCP_INC_STATS(field) SNMP_INC_STATS(tcp_statistics, field)
#define TCP_INC_STATS_BH(field) SNMP_INC_STATS_BH(tcp_statistics, field)
#define TCP_INC_STATS_USER(field) SNMP_INC_STATS_USER(tcp_statistics, field)
#define TCP_DEC_STATS(field) SNMP_DEC_STATS(tcp_statistics, field)
#define TCP_ADD_STATS_BH(field, val) SNMP_ADD_STATS_BH(tcp_statistics, field, val)
#define TCP_ADD_STATS_USER(field, val) SNMP_ADD_STATS_USER(tcp_statistics, field, val)
extern void tcp_put_port(struct sock *sk);
extern void tcp_inherit_port(struct sock *sk, struct sock *child);
extern void tcp_v4_err(struct sk_buff *skb, u32);
extern void tcp_shutdown (struct sock *sk, int how);
extern int tcp_v4_rcv(struct sk_buff *skb);
extern int tcp_v4_remember_stamp(struct sock *sk);
extern int tcp_v4_tw_remember_stamp(struct tcp_tw_bucket *tw);
extern int tcp_sendmsg(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg, size_t size);
extern ssize_t tcp_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags);
extern int tcp_ioctl(struct sock *sk,
int cmd,
unsigned long arg);
extern int tcp_rcv_state_process(struct sock *sk,
struct sk_buff *skb,
struct tcphdr *th,
unsigned len);
extern int tcp_rcv_established(struct sock *sk,
struct sk_buff *skb,
struct tcphdr *th,
unsigned len);
extern void tcp_rcv_space_adjust(struct sock *sk);
enum tcp_ack_state_t
{
TCP_ACK_SCHED = 1,
TCP_ACK_TIMER = 2,
TCP_ACK_PUSHED= 4
};
static inline void tcp_schedule_ack(struct tcp_sock *tp)
{
tp->ack.pending |= TCP_ACK_SCHED;
}
static inline int tcp_ack_scheduled(struct tcp_sock *tp)
{
return tp->ack.pending&TCP_ACK_SCHED;
}
static __inline__ void tcp_dec_quickack_mode(struct tcp_sock *tp)
{
if (tp->ack.quick && --tp->ack.quick == 0) {
/* Leaving quickack mode we deflate ATO. */
tp->ack.ato = TCP_ATO_MIN;
}
}
extern void tcp_enter_quickack_mode(struct tcp_sock *tp);
static __inline__ void tcp_delack_init(struct tcp_sock *tp)
{
memset(&tp->ack, 0, sizeof(tp->ack));
}
static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
{
rx_opt->tstamp_ok = rx_opt->sack_ok = rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
}
enum tcp_tw_status
{
TCP_TW_SUCCESS = 0,
TCP_TW_RST = 1,
TCP_TW_ACK = 2,
TCP_TW_SYN = 3
};
extern enum tcp_tw_status tcp_timewait_state_process(struct tcp_tw_bucket *tw,
struct sk_buff *skb,
struct tcphdr *th,
unsigned len);
extern struct sock * tcp_check_req(struct sock *sk,struct sk_buff *skb,
struct request_sock *req,
struct request_sock **prev);
extern int tcp_child_process(struct sock *parent,
struct sock *child,
struct sk_buff *skb);
extern void tcp_enter_frto(struct sock *sk);
extern void tcp_enter_loss(struct sock *sk, int how);
extern void tcp_clear_retrans(struct tcp_sock *tp);
extern void tcp_update_metrics(struct sock *sk);
extern void tcp_close(struct sock *sk,
long timeout);
extern struct sock * tcp_accept(struct sock *sk, int flags, int *err);
extern unsigned int tcp_poll(struct file * file, struct socket *sock, struct poll_table_struct *wait);
extern int tcp_getsockopt(struct sock *sk, int level,
int optname,
char __user *optval,
int __user *optlen);
extern int tcp_setsockopt(struct sock *sk, int level,
int optname, char __user *optval,
int optlen);
extern void tcp_set_keepalive(struct sock *sk, int val);
extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg,
size_t len, int nonblock,
int flags, int *addr_len);
extern int tcp_listen_start(struct sock *sk);
extern void tcp_parse_options(struct sk_buff *skb,
struct tcp_options_received *opt_rx,
int estab);
/*
* TCP v4 functions exported for the inet6 API
*/
extern int tcp_v4_rebuild_header(struct sock *sk);
extern int tcp_v4_build_header(struct sock *sk,
struct sk_buff *skb);
extern void tcp_v4_send_check(struct sock *sk,
struct tcphdr *th, int len,
struct sk_buff *skb);
extern int tcp_v4_conn_request(struct sock *sk,
struct sk_buff *skb);
extern struct sock * tcp_create_openreq_child(struct sock *sk,
struct request_sock *req,
struct sk_buff *skb);
extern struct sock * tcp_v4_syn_recv_sock(struct sock *sk,
struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst);
extern int tcp_v4_do_rcv(struct sock *sk,
struct sk_buff *skb);
extern int tcp_v4_connect(struct sock *sk,
struct sockaddr *uaddr,
int addr_len);
extern int tcp_connect(struct sock *sk);
extern struct sk_buff * tcp_make_synack(struct sock *sk,
struct dst_entry *dst,
struct request_sock *req);
extern int tcp_disconnect(struct sock *sk, int flags);
extern void tcp_unhash(struct sock *sk);
extern int tcp_v4_hash_connecting(struct sock *sk);
/* From syncookies.c */
extern struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
struct ip_options *opt);
extern __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb,
__u16 *mss);
/* tcp_output.c */
extern int tcp_write_xmit(struct sock *, int nonagle);
extern int tcp_retransmit_skb(struct sock *, struct sk_buff *);
extern void tcp_xmit_retransmit_queue(struct sock *);
extern void tcp_simple_retransmit(struct sock *);
extern int tcp_trim_head(struct sock *, struct sk_buff *, u32);
extern void tcp_send_probe0(struct sock *);
extern void tcp_send_partial(struct sock *);
extern int tcp_write_wakeup(struct sock *);
extern void tcp_send_fin(struct sock *sk);
extern void tcp_send_active_reset(struct sock *sk, int priority);
extern int tcp_send_synack(struct sock *);
extern void tcp_push_one(struct sock *, unsigned mss_now);
extern void tcp_send_ack(struct sock *sk);
extern void tcp_send_delayed_ack(struct sock *sk);
/* tcp_timer.c */
extern void tcp_init_xmit_timers(struct sock *);
extern void tcp_clear_xmit_timers(struct sock *);
extern void tcp_delete_keepalive_timer(struct sock *);
extern void tcp_reset_keepalive_timer(struct sock *, unsigned long);
extern unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu);
extern unsigned int tcp_current_mss(struct sock *sk, int large);
#ifdef TCP_DEBUG
extern const char tcp_timer_bug_msg[];
#endif
/* tcp_diag.c */
extern void tcp_get_info(struct sock *, struct tcp_info *);
/* Read 'sendfile()'-style from a TCP socket */
typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *,
unsigned int, size_t);
extern int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
sk_read_actor_t recv_actor);
static inline void tcp_clear_xmit_timer(struct sock *sk, int what)
{
struct tcp_sock *tp = tcp_sk(sk);
switch (what) {
case TCP_TIME_RETRANS:
case TCP_TIME_PROBE0:
tp->pending = 0;
#ifdef TCP_CLEAR_TIMERS
sk_stop_timer(sk, &tp->retransmit_timer);
#endif
break;
case TCP_TIME_DACK:
tp->ack.blocked = 0;
tp->ack.pending = 0;
#ifdef TCP_CLEAR_TIMERS
sk_stop_timer(sk, &tp->delack_timer);
#endif
break;
default:
#ifdef TCP_DEBUG
printk(tcp_timer_bug_msg);
#endif
return;
};
}
/*
* Reset the retransmission timer
*/
static inline void tcp_reset_xmit_timer(struct sock *sk, int what, unsigned long when)
{
struct tcp_sock *tp = tcp_sk(sk);
if (when > TCP_RTO_MAX) {
#ifdef TCP_DEBUG
printk(KERN_DEBUG "reset_xmit_timer sk=%p %d when=0x%lx, caller=%p\n", sk, what, when, current_text_addr());
#endif
when = TCP_RTO_MAX;
}
switch (what) {
case TCP_TIME_RETRANS:
case TCP_TIME_PROBE0:
tp->pending = what;
tp->timeout = jiffies+when;
sk_reset_timer(sk, &tp->retransmit_timer, tp->timeout);
break;
case TCP_TIME_DACK:
tp->ack.pending |= TCP_ACK_TIMER;
tp->ack.timeout = jiffies+when;
sk_reset_timer(sk, &tp->delack_timer, tp->ack.timeout);
break;
default:
#ifdef TCP_DEBUG
printk(tcp_timer_bug_msg);
#endif
return;
};
}
/* Initialize RCV_MSS value.
* RCV_MSS is an our guess about MSS used by the peer.
* We haven't any direct information about the MSS.
* It's better to underestimate the RCV_MSS rather than overestimate.
* Overestimations make us ACKing less frequently than needed.
* Underestimations are more easy to detect and fix by tcp_measure_rcv_mss().
*/
static inline void tcp_initialize_rcv_mss(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
unsigned int hint = min(tp->advmss, tp->mss_cache_std);
hint = min(hint, tp->rcv_wnd/2);
hint = min(hint, TCP_MIN_RCVMSS);
hint = max(hint, TCP_MIN_MSS);
tp->ack.rcv_mss = hint;
}
static __inline__ void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
{