-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtcp_ipv4.c
executable file
·3049 lines (2654 loc) · 81.6 KB
/
tcp_ipv4.c
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.
*
* Implementation of the Transmission Control Protocol(TCP).
*
* IPv4 specific functions
*
*
* code split from:
* linux/ipv4/tcp.c
* linux/ipv4/tcp_input.c
* linux/ipv4/tcp_output.c
*
* See tcp.c for author information
*
* 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.
*/
/*
* Changes:
* David S. Miller : New socket lookup architecture.
* This code is dedicated to John Dyson.
* David S. Miller : Change semantics of established hash,
* half is devoted to TIME_WAIT sockets
* and the rest go in the other half.
* Andi Kleen : Add support for syncookies and fixed
* some bugs: ip options weren't passed to
* the TCP layer, missed a check for an
* ACK bit.
* Andi Kleen : Implemented fast path mtu discovery.
* Fixed many serious bugs in the
* request_sock handling and moved
* most of it into the af independent code.
* Added tail drop and some other bugfixes.
* Added new listen semantics.
* Mike McLagan : Routing by source
* Juan Jose Ciarlante: ip_dynaddr bits
* Andi Kleen: various fixes.
* Vitaly E. Lavrov : Transparent proxy revived after year
* coma.
* Andi Kleen : Fix new listen.
* Andi Kleen : Fix accept error reporting.
* YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which
* Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind
* a single port at the same time.
*/
#include <linux/bottom_half.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/module.h>
#include <linux/random.h>
#include <linux/cache.h>
#include <linux/jhash.h>
#include <linux/init.h>
#include <linux/times.h>
#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/icmp.h>
#include <net/inet_hashtables.h>
#include <net/tcp.h>
#include <net/transp_v6.h>
#include <net/ipv6.h>
#include <net/inet_common.h>
#include <net/timewait_sock.h>
#include <net/xfrm.h>
#include <net/netdma.h>
#include <linux/inet.h>
#include <linux/ipv6.h>
#include <linux/stddef.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/crypto.h>
#include <linux/scatterlist.h>
int sysctl_tcp_tw_reuse __read_mostly;
int sysctl_tcp_low_latency __read_mostly;
#ifdef CONFIG_TCP_MD5SIG
static struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk,
__be32 addr);
static int tcp_v4_md5_hash_hdr(char *md5_hash, struct tcp_md5sig_key *key,
__be32 daddr, __be32 saddr, struct tcphdr *th);
#else
static inline
struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr)
{
return NULL;
}
#endif
//存放在tcp_prot的h.hashinfo中 //该变量初始化赋值在tcp_init
struct inet_hashinfo tcp_hashinfo;//tcp_prot套接口和IPV6的tcpv6_prot在这个hash表中，tcp套接字的struct sock通过inet_hash加入到该hash中
static inline __u32 tcp_v4_init_sequence(struct sk_buff *skb)
{
return secure_tcp_sequence_number(ip_hdr(skb)->daddr,
ip_hdr(skb)->saddr,
tcp_hdr(skb)->dest,
tcp_hdr(skb)->source);
}
int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
{
const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw);
struct tcp_sock *tp = tcp_sk(sk);
/* With PAWS, it is safe from the viewpoint
of data integrity. Even without PAWS it is safe provided sequence
spaces do not overlap i.e. at data rates <= 80Mbit/sec.
Actually, the idea is close to VJ's one, only timestamp cache is
held not per host, but per port pair and TW bucket is used as state
holder.
If TW bucket has been already destroyed we fall back to VJ's scheme
and use initial timestamp retrieved from peer table.
*/
if (tcptw->tw_ts_recent_stamp &&
(twp == NULL || (sysctl_tcp_tw_reuse &&
get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
if (tp->write_seq == 0)
tp->write_seq = 1;
tp->rx_opt.ts_recent = tcptw->tw_ts_recent;
tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
sock_hold(sktw);
return 1;
}
return 0;
}
EXPORT_SYMBOL_GPL(tcp_twsk_unique);
/* This will initiate an outgoing connection. */
/*
* 在套接字层检测完必要条件，如套接字的状态等之后，传输
* 接口层中还需对传输控制块进行更详细的校验，如地址族的
* 类型，是否获取到有效的路由入口。通过检测后设置传输控
* 制块各字段值，如初始化时间戳，保存目的地址和目的端口
* 等，最后构造并发送SYN段。
*/
int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct inet_sock *inet = inet_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
struct rtable *rt;
__be32 daddr, nexthop;
int tmp;
int err;
if (addr_len < sizeof(struct sockaddr_in))
return -EINVAL;
if (usin->sin_family != AF_INET)
return -EAFNOSUPPORT;
nexthop = daddr = usin->sin_addr.s_addr;//connect的时候s_addr里面对应的是目的地址，即对端ip地址
if (inet->opt && inet->opt->srr) {
if (!daddr)
return -EINVAL;
nexthop = inet->opt->faddr;
}
/*
* 调用ip_route_connect()根据下一跳地址等信息查找目的路由缓存项，如果路由查找命中，则生成一个相应的路由缓存项，这个缓存项不但
* 可以用于当前待发送SYN段，而且对后续的所有数据包都可以起到一个加速路由查找的作用。
*/
tmp = ip_route_connect(&rt, nexthop, inet->inet_saddr,
RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
IPPROTO_TCP,
inet->inet_sport, usin->sin_port, sk, 1);
if (tmp < 0) {
if (tmp == -ENETUNREACH)
IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
return tmp;
}
/*TCP不能使用类型为组播或多播的路由缓存项。*/
if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
ip_rt_put(rt);
return -ENETUNREACH;
}
/* 如果没有启用源路由选项，则使用获取到路由缓存项中的目的地址。*/
if (!inet->opt || !inet->opt->srr)
daddr = rt->rt_dst;
/* 如果还未设置传输控制块中的源地址，则使用路由缓存项中的源地址对其进行设置。*/
//这里说明了客户端在连接的时候可以不用指明本地IP地址，由路由缓存找到对应目的IP的时候，就可以确定本地IP地址了。
if (!inet->inet_saddr)
inet->inet_saddr = rt->rt_src;
inet->inet_rcv_saddr = inet->inet_saddr;
/* 如果传输控制块中的时间戳和目的地址已被使用过，则说明该传输控制块之前已建立连接并进行过通信，需重新初始化相关成员。 */
if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) {
/* Reset inherited state */
tp->rx_opt.ts_recent = 0;
tp->rx_opt.ts_recent_stamp = 0;
tp->write_seq = 0;
}
/* 如果启用了sysctl_tw_recycle并接收过时间戳选项，从对端信息块中获取相应的值来初始化ts_recent_stamp和ts_recent。*/
if (tcp_death_row.sysctl_tw_recycle &&
!tp->rx_opt.ts_recent_stamp && rt->rt_dst == daddr) {
struct inet_peer *peer = rt_get_peer(rt);
/*
* VJ's idea. We save last timestamp seen from
* the destination in peer table, when entering state
* TIME-WAIT * and initialize rx_opt.ts_recent from it,
* when trying new connection.
*/
if (peer != NULL &&
(u32)get_seconds() - peer->tcp_ts_stamp <= TCP_PAWS_MSL) {
tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp;
tp->rx_opt.ts_recent = peer->tcp_ts;
}
}
inet->inet_dport = usin->sin_port;
inet->inet_daddr = daddr;
inet_csk(sk)->icsk_ext_hdr_len = 0;
if (inet->opt)
inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen;
tp->rx_opt.mss_clamp = TCP_MSS_DEFAULT;
/* Socket identity is still unknown (sport may be zero).
* However we set state to SYN-SENT and not releasing socket
* lock select source port, enter ourselves into the hash tables and
* complete initialization after this.
*/
/* 将TCP设置为SYN_SENT，动态绑定一个本地端口，并将传输控制块添加到ehash散列表中。由于在动态分配端口时，如果找到的是已使用的端口，则
* 需在TIME_WAIT状态中进行相应的确认，因此调用inet_hash_connect()时需用timewait传输控制块和参数管理器tcp_death_row作为参数。*/
tcp_set_state(sk, TCP_SYN_SENT);
err = inet_hash_connect(&tcp_death_row, sk);
if (err)
goto failure;
err = ip_route_newports(&rt, IPPROTO_TCP,
inet->inet_sport, inet->inet_dport, sk);
if (err)
goto failure;
/* OK, now commit destination to socket. */
/*
* 设置GSO类型为SKB_GSO_TCPV4，并根据该传输
* 控制块的路由输出设置特性设置传输控制
* 块中目的路由网络设备的特性。
*/
sk->sk_gso_type = SKB_GSO_TCPV4;
sk_setup_caps(sk, &rt->u.dst);
/*
* 如果write_seq字段值为零，则说明该传输控制块还
* 未设置初始序号，因此需调用secure_tcp_sequence_number()，
* 根据双方的地址、端口计算初始序列号，同时根据
* 发送需要和当前时间得到用于设置IP首部ID域的值。
*/
if (!tp->write_seq)
tp->write_seq = secure_tcp_sequence_number(inet->inet_saddr,
inet->inet_daddr,
inet->inet_sport,
usin->sin_port);
inet->inet_id = tp->write_seq ^ jiffies;
/*
* 最后调用tcp_connect()来构造并发送SYN段。
*/
err = tcp_connect(sk);
rt = NULL;
if (err)
goto failure;
return 0;
failure:
/*
* This unhashes the socket and releases the local port,
* if necessary.
*/
tcp_set_state(sk, TCP_CLOSE);
ip_rt_put(rt);
sk->sk_route_caps = 0;
inet->inet_dport = 0;
return err;
}
/*
* This routine does path mtu discovery as defined in RFC1191.
*/
/*
* ICMP模块接收到"需要分片ICMP目的不可达报文"的消息后，
* 根据传输层协议，如果是TCP，则会调用tcp_v4_err()，在该
* 函数中进而根据类型ICMP_DEST_UNREACH和编码ICMP_FRAG_NEEDED
* 调用do_pmtu_discovery()进行路径MTU发现失败处理。
*/
static void do_pmtu_discovery(struct sock *sk, struct iphdr *iph, u32 mtu)
{
struct dst_entry *dst;
struct inet_sock *inet = inet_sk(sk);
/* We are not interested in TCP_LISTEN and open_requests (SYN-ACKs
* send out by Linux are always <576bytes so they should go through
* unfragmented).
*/
/*
* 在监听状态下，不需要进行路径MTU发现，因为在该
* 状态下输出的SYN+ACK段总是小于536B，因此输出的IP
* 数据包不会被分片。
*/
if (sk->sk_state == TCP_LISTEN)
return;
/* We don't check in the destentry if pmtu discovery is forbidden
* on this route. We just assume that no packet_to_big packets
* are send back when pmtu discovery is not active.
* There is a small race when the user changes this flag in the
* route, but I think that's acceptable.
*/
/*
* 检测当前传输控制块的路由缓存项是否可用。如果
* 失效，则不继续处理。
*/
if ((dst = __sk_dst_check(sk, 0)) == NULL)
return;
/*
* 在没有锁定路由缓存项的度量值的情况下，将获取的
* 下一跳MTU更新到与路由相关的路由缓存项的度量值中。
* 如果存储在路由缓存项的度量值中的PTMU大于下一跳的
* MTU，且发送出的IP数据包禁止分片，则需报告相应的
* 错误。
*/
dst->ops->update_pmtu(dst, mtu);
/* Something is about to be wrong... Remember soft error
* for the case, if this connection will not able to recover.
*/
if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst))
sk->sk_err_soft = EMSGSIZE;
mtu = dst_mtu(dst);
/*
* 在允许路径MTU发现的情况下，如果缓存在传输控制块
* 中的路径MTU值大于新的值，则需将新的路径MTU值更新
* 到传输控制块的缓存中，同时更新MSS，最后重传。
*/
if (inet->pmtudisc != IP_PMTUDISC_DONT &&
inet_csk(sk)->icsk_pmtu_cookie > mtu) {
tcp_sync_mss(sk, mtu);
/* Resend the TCP packet because it's
* clear that the old packet has been
* dropped. This is the new "fast" path mtu
* discovery.
*/
tcp_simple_retransmit(sk);
} /* else let the usual retransmit timer handle it */
}
static void do_pmtu_discovery1(struct sock *sk, struct iphdr *iph, u32 mtu)
{
struct dst_entry *dst;
struct inet_sock *inet = inet_sk(sk);
/* We are not interested in TCP_LISTEN and open_requests (SYN-ACKs
* send out by Linux are always <576bytes so they should go through
* unfragmented).
*/
if (sk->sk_state == TCP_LISTEN)
return;
/* We don't check in the destentry if pmtu discovery is forbidden
* on this route. We just assume that no packet_to_big packets
* are send back when pmtu discovery is not active.
* There is a small race when the user changes this flag in the
* route, but I think that's acceptable.
*/
if ((dst = __sk_dst_check(sk, 0)) == NULL)
return;
dst->ops->update_pmtu(dst, mtu);
/* Something is about to be wrong... Remember soft error
* for the case, if this connection will not able to recover.
*/
if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst))
sk->sk_err_soft = EMSGSIZE;
mtu = dst_mtu(dst);
if (inet->pmtudisc != IP_PMTUDISC_DONT &&
inet_csk(sk)->icsk_pmtu_cookie > mtu) {
tcp_sync_mss(sk, mtu);
/* Resend the TCP packet because it's
* clear that the old packet has been
* dropped. This is the new "fast" path mtu
* discovery.
*/
tcp_simple_retransmit(sk);
} /* else let the usual retransmit timer handle it */
}
/*
* This routine is called by the ICMP module when it gets some
* sort of error condition. If err < 0 then the socket should
* be closed and the error returned to the user. If err > 0
* it's just the icmp type << 8 | icmp code. After adjustment
* header points to the first 8 bytes of the tcp header. We need
* to find the appropriate port.
*
* The locking strategy used here is very "optimistic". When
* someone else accesses the socket the ICMP is just dropped
* and for some paths there is no check at all.
* A more general error queue to queue errors for later handling
* is probably better.
*
*/
/*
* 目的不可达、源端被关闭、超时、参数错误这四种类型
* 的差错ICMP报文，都是由同一个函数icmp_unreach()来处理的，
* 对其中目的不可达、源端被关闭这两种类型ICMP报文
* 因要提取某些信息而需作一些特殊的处理，而另外
* 一些则不需要，根据差错报文中的信息直接调用
* 传输层的错误处理例程。参见<Linux内核源码剖析348页>
CMP差错报文的数据部分包括:原始数据报的IP首部再加上前8个字节的数据部分(2字节源端口+2字节目的端口+4字节序号)
*/
void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
{
struct iphdr *iph = (struct iphdr *)icmp_skb->data;
struct tcphdr *th = (struct tcphdr *)(icmp_skb->data + (iph->ihl << 2));
struct inet_connection_sock *icsk;
struct tcp_sock *tp;
struct inet_sock *inet;
const int type = icmp_hdr(icmp_skb)->type;
const int code = icmp_hdr(icmp_skb)->code;
struct sock *sk;
struct sk_buff *skb;
__u32 seq;
__u32 remaining;
int err;
struct net *net = dev_net(icmp_skb->dev);
/*
* 检测ICMP报文长度是否包含了原始IP首部和原始IP数据包中
* 前8字节数据，如果不完整则返回
*/
if (icmp_skb->len < (iph->ihl << 2) + 8) {
ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
return;
}
/*
* 通过从ICMP报文数据中获取的原始TCP首部中源端口号和IP首部
* 中源地址，得到发送该TCP报文的传输控制块。如果获取失败，
* 则说明ICMP报文有误或该套接字已关闭；如果获取传输控制块
* 的TCP状态为TIME_WAIT，则说明套接字即将关闭，这两种情况
* 都无需进一步处理
*/
sk = inet_lookup(net, &tcp_hashinfo, iph->daddr, th->dest,
iph->saddr, th->source, inet_iif(icmp_skb));
if (!sk) {
ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
return;
}
if (sk->sk_state == TCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
return;
}
bh_lock_sock(sk);
/* If too many ICMPs get dropped on busy
* servers this needs to be solved differently.
*//*
* 如果此时该传输控制块被用户进程锁定(如用户进程正在调用
* send等系统调用)，则需累计相关SNMP的统计量
*/
if (sock_owned_by_user(sk))
NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
if (sk->sk_state == TCP_CLOSE)
goto out;
if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) {
NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP);
goto out;
}
/*
* 如果传输控制块不再侦听状态，且序号不再已发送未确认的区间内，则
* ICMP报文异常，无需进一步处理
*/
icsk = inet_csk(sk);
tp = tcp_sk(sk);
seq = ntohl(th->seq);
if (sk->sk_state != TCP_LISTEN &&
!between(seq, tp->snd_una, tp->snd_nxt)) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
switch (type) {
case ICMP_SOURCE_QUENCH:
/* Just silently ignore these. */
goto out;
case ICMP_PARAMETERPROB:
err = EPROTO;
break;
/*
* 处理目的不可达类型，首先检测代码的合法性，然后根据
* 代码具体处理:如果需要分片而设置了不可分片，则调用
* do_pmtu_discovery()探测路径MTU；其他编码，则获取
* 对应的错误码
*/
case ICMP_DEST_UNREACH:
if (code > NR_ICMP_UNREACH)
goto out;
if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */
if (!sock_owned_by_user(sk))
do_pmtu_discovery(sk, iph, info);
goto out;
}
err = icmp_err_convert[code].errno;
/* check if icmp_skb allows revert of backoff
* (see draft-zimmermann-tcp-lcd) */
if (code != ICMP_NET_UNREACH && code != ICMP_HOST_UNREACH)
break;
if (seq != tp->snd_una || !icsk->icsk_retransmits ||
!icsk->icsk_backoff)
break;
if (sock_owned_by_user(sk))
break;
icsk->icsk_backoff--;
inet_csk(sk)->icsk_rto = __tcp_set_rto(tp) <<
icsk->icsk_backoff;
tcp_bound_rto(sk);
skb = tcp_write_queue_head(sk);
BUG_ON(!skb);
remaining = icsk->icsk_rto - min(icsk->icsk_rto,
tcp_time_stamp - TCP_SKB_CB(skb)->when);
if (remaining) {
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
remaining, TCP_RTO_MAX);
} else {
/* RTO revert clocked out retransmission.
* Will retransmit now */
tcp_retransmit_timer(sk);
}
break;
case ICMP_TIME_EXCEEDED:
err = EHOSTUNREACH;
break;
default:
goto out;
}
switch (sk->sk_state) {
struct request_sock *req, **prev;
case TCP_LISTEN:
/*
* 如果传输控制块被用户进程锁定，则不作进一步处理
*/
if (sock_owned_by_user(sk))
goto out;
/*
* 由于处于监听状态，因此根据目的端口号、源地址和目的地址查找
* 正在连接的对端套接字，如果查找失败则不作进一步处理
*/
req = inet_csk_search_req(sk, &prev, th->dest,
iph->daddr, iph->saddr);
if (!req)
goto out;
/* ICMPs are not backlogged, hence we cannot get
an established socket here.
*/
WARN_ON(req->sk);
/*
* 如果发送出去TCP段的序号不等于对端套接字中的发送序号，
* 则说明序号有误，不作进一步处理
*/
if (seq != tcp_rsk(req)->snt_isn) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
/*
* Still in SYN_RECV, just remove it silently.
* There is no good way to pass the error to the newly
* created socket, and POSIX does not want network
* errors returned from accept().
*/
/*
* 删除并释放连接过程中的传输控制块
*/
inet_csk_reqsk_queue_drop(sk, req, prev);
goto out;
case TCP_SYN_SENT:
case TCP_SYN_RECV: /* Cannot happen.
It can f.e. if SYNs crossed.
*//*
* 如果传输控制块没有被用户进程锁定，则将错误码设置到sk_err，
* 调用该套接字的错误报告借口函数，关闭套接字；否则将错误码
* 设置到sk_err_soft，在这种情况下用户进程可使用SO_ERROR套接
* 字选项获取错误码
*/
if (!sock_owned_by_user(sk)) {
sk->sk_err = err;
sk->sk_error_report(sk);
tcp_done(sk);
} else {
sk->sk_err_soft = err;
}
goto out;
}
/* If we've already connected we will keep trying
* until we time out, or the user gives up.
*
* rfc1122 4.2.3.9 allows to consider as hard errors
* only PROTO_UNREACH and PORT_UNREACH (well, FRAG_FAILED too,
* but it is obsoleted by pmtu discovery).
*
* Note, that in modern internet, where routing is unreliable
* and in each dark corner broken firewalls sit, sending random
* errors ordered by their masters even this two messages finally lose
* their original sense (even Linux sends invalid PORT_UNREACHs)
*
* Now we are in compliance with RFCs.
* --ANK (980905)
*/
/*
* 到这一步，则传输控制块一定不再LISTEN、SYN_SENT或SYN_RECV状态，
* 此时如果控制块没有被用户进程锁定，并且允许接收扩展的可靠错误
* 信息，则设置得到的错误码，然后通知错误；否则将错误码设置到sk_err_soft
*/
inet = inet_sk(sk);
if (!sock_owned_by_user(sk) && inet->recverr) {
sk->sk_err = err;
sk->sk_error_report(sk);
} else { /* Only an error on timeout */
sk->sk_err_soft = err;
}
out:
bh_unlock_sock(sk);
sock_put(sk);
}
/*
* 基于TCP用户数据的中间累加和(如果存在数据)，生成TCP包的校验和
*/ //这是TCP输出的时候的校验和tcp_v4_send_check, TCP输入的时候计算校验和用的tcp_v4_checksum_init
static void __tcp_v4_send_check(struct sk_buff *skb,
__be32 saddr, __be32 daddr)
{
struct tcphdr *th = tcp_hdr(skb);
/*
* 如果TCP包本身的校验由硬件来完成，则只执行伪首部校验和
*/
if (skb->ip_summed == CHECKSUM_PARTIAL) {
th->check = ~tcp_v4_check(skb->len, saddr, daddr, 0);
skb->csum_start = skb_transport_header(skb) - skb->head;
skb->csum_offset = offsetof(struct tcphdr, check);
} else {
/*
* 对于用软件完成校验和的操作，则基于TCP用户数据的中间累加和，
* 生成TCP包的校验和
*/
th->check = tcp_v4_check(skb->len, saddr, daddr,
csum_partial(th,
th->doff << 2,
skb->csum));
}
}
/* This routine computes an IPv4 TCP checksum. */
/*
* 基于TCP用户数据的中间累加和(如果存在数据)，生成TCP包的校验和
*///这是TCP输出的时候的校验和tcp_v4_send_check, TCP输入的时候计算校验和用的tcp_v4_checksum_init
void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb)
{
struct inet_sock *inet = inet_sk(sk);
__tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr);
}
int tcp_v4_gso_send_check(struct sk_buff *skb)
{
const struct iphdr *iph;
struct tcphdr *th;
if (!pskb_may_pull(skb, sizeof(*th)))
return -EINVAL;
iph = ip_hdr(skb);
th = tcp_hdr(skb);
th->check = 0;
skb->ip_summed = CHECKSUM_PARTIAL;
__tcp_v4_send_check(skb, iph->saddr, iph->daddr);
return 0;
}
/*
* This routine will send an RST to the other tcp.
*
* Someone asks: why I NEVER use socket parameters (TOS, TTL etc.)
* for reset.
* Answer: if a packet caused RST, it is not for a socket
* existing in our system, if it is matched to a socket,
* it is just duplicate segment or bug in other side's TCP.
* So that we build reply only basing on parameters
* arrived with segment.
* Exception: precedence violation. We do not implement it in any case.
*/
static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
{
struct tcphdr *th = tcp_hdr(skb);
struct {
struct tcphdr th;
#ifdef CONFIG_TCP_MD5SIG
__be32 opt[(TCPOLEN_MD5SIG_ALIGNED >> 2)];
#endif
} rep;
struct ip_reply_arg arg;
#ifdef CONFIG_TCP_MD5SIG
struct tcp_md5sig_key *key;
#endif
struct net *net;
/* Never send a reset in response to a reset. */
if (th->rst)
return;
if (skb_rtable(skb)->rt_type != RTN_LOCAL)
return;
/* Swap the send and the receive. */
memset(&rep, 0, sizeof(rep));
rep.th.dest = th->source;
rep.th.source = th->dest;
rep.th.doff = sizeof(struct tcphdr) / 4;
rep.th.rst = 1;
if (th->ack) {
rep.th.seq = th->ack_seq;
} else {
rep.th.ack = 1;
rep.th.ack_seq = htonl(ntohl(th->seq) + th->syn + th->fin +
skb->len - (th->doff << 2));
}
memset(&arg, 0, sizeof(arg));
arg.iov[0].iov_base = (unsigned char *)&rep;
arg.iov[0].iov_len = sizeof(rep.th);
#ifdef CONFIG_TCP_MD5SIG
key = sk ? tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr) : NULL;
if (key) {
rep.opt[0] = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
(TCPOPT_MD5SIG << 8) |
TCPOLEN_MD5SIG);
/* Update length and the length the header thinks exists */
arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED;
rep.th.doff = arg.iov[0].iov_len / 4;
tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[1],
key, ip_hdr(skb)->saddr,
ip_hdr(skb)->daddr, &rep.th);
}
#endif
arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr,
ip_hdr(skb)->saddr, /* XXX */
arg.iov[0].iov_len, IPPROTO_TCP, 0);
arg.csumoffset = offsetof(struct tcphdr, check) / 2;
arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0;
net = dev_net(skb_dst(skb)->dev);
ip_send_reply(net->ipv4.tcp_sock, skb,
&arg, arg.iov[0].iov_len);
TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
TCP_INC_STATS_BH(net, TCP_MIB_OUTRSTS);
}
/* The code following below sending ACKs in SYN-RECV and TIME-WAIT states
outside socket context is ugly, certainly. What can I do?
*/
static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
u32 win, u32 ts, int oif,
struct tcp_md5sig_key *key,
int reply_flags)
{
struct tcphdr *th = tcp_hdr(skb);
struct {
struct tcphdr th;
__be32 opt[(TCPOLEN_TSTAMP_ALIGNED >> 2)
#ifdef CONFIG_TCP_MD5SIG
+ (TCPOLEN_MD5SIG_ALIGNED >> 2)
#endif
];
} rep;
struct ip_reply_arg arg;
struct net *net = dev_net(skb_dst(skb)->dev);
memset(&rep.th, 0, sizeof(struct tcphdr));
memset(&arg, 0, sizeof(arg));
arg.iov[0].iov_base = (unsigned char *)&rep;
arg.iov[0].iov_len = sizeof(rep.th);
if (ts) {
rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
(TCPOPT_TIMESTAMP << 8) |
TCPOLEN_TIMESTAMP);
rep.opt[1] = htonl(tcp_time_stamp);
rep.opt[2] = htonl(ts);
arg.iov[0].iov_len += TCPOLEN_TSTAMP_ALIGNED;
}
/* Swap the send and the receive. */
rep.th.dest = th->source;
rep.th.source = th->dest;
rep.th.doff = arg.iov[0].iov_len / 4;
rep.th.seq = htonl(seq);
rep.th.ack_seq = htonl(ack);
rep.th.ack = 1;
rep.th.window = htons(win);
#ifdef CONFIG_TCP_MD5SIG
if (key) {
int offset = (ts) ? 3 : 0;
rep.opt[offset++] = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
(TCPOPT_MD5SIG << 8) |
TCPOLEN_MD5SIG);
arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED;
rep.th.doff = arg.iov[0].iov_len/4;
tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[offset],
key, ip_hdr(skb)->saddr,
ip_hdr(skb)->daddr, &rep.th);
}
#endif
arg.flags = reply_flags;
arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr,
ip_hdr(skb)->saddr, /* XXX */
arg.iov[0].iov_len, IPPROTO_TCP, 0);
arg.csumoffset = offsetof(struct tcphdr, check) / 2;
if (oif)
arg.bound_dev_if = oif;
ip_send_reply(net->ipv4.tcp_sock, skb,
&arg, arg.iov[0].iov_len);
TCP_INC_STATS_BH(net, TCP_MIB_OUTSEGS);
}
static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
{
struct inet_timewait_sock *tw = inet_twsk(sk);
struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
tcptw->tw_ts_recent,
tw->tw_bound_dev_if,
tcp_twsk_md5_key(tcptw),
tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0
);
inet_twsk_put(tw);
}
static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
struct request_sock *req)
{
tcp_v4_send_ack(skb, tcp_rsk(req)->snt_isn + 1,
tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd,
req->ts_recent,
0,
tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr),
inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0);
}
/*
* Send a SYN-ACK after having received a SYN.
* This still operates on a request_sock only, not on a big
* socket.
*/
static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
struct request_sock *req,
struct request_values *rvp)
{
const struct inet_request_sock *ireq = inet_rsk(req);
int err = -1;
struct sk_buff * skb;
/* First, grab a route. */
if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL)
return -1;
skb = tcp_make_synack(sk, dst, req, rvp);
if (skb) {
__tcp_v4_send_check(skb, ireq->loc_addr, ireq->rmt_addr);
err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr,
ireq->rmt_addr,
ireq->opt);
err = net_xmit_eval(err);
}
dst_release(dst);
return err;
}
static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req,
struct request_values *rvp)
{
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
return tcp_v4_send_synack(sk, NULL, req, rvp);
}
/*
* IPv4 request_sock destructor.
*/
static void tcp_v4_reqsk_destructor(struct request_sock *req)
{
kfree(inet_rsk(req)->opt);
}
#ifdef CONFIG_SYN_COOKIES
static void syn_flood_warning(struct sk_buff *skb)
{
static unsigned long warntime;
if (time_after(jiffies, (warntime + HZ * 60))) {
warntime = jiffies;
printk(KERN_INFO
"possible SYN flooding on port %d. Sending cookies.\n",
ntohs(tcp_hdr(skb)->dest));
}
}
#endif
/*
* Save and compile IPv4 options into the request_sock if needed.
*/
static struct ip_options *tcp_v4_save_options(struct sock *sk,
struct sk_buff *skb)
{
struct ip_options *opt = &(IPCB(skb)->opt);
struct ip_options *dopt = NULL;
if (opt && opt->optlen) {
int opt_size = optlength(opt);
dopt = kmalloc(opt_size, GFP_ATOMIC);
if (dopt) {
if (ip_options_echo(dopt, skb)) {
kfree(dopt);
dopt = NULL;
}
}