Repository navigation
Expand file tree
/
Copy pathtcp_in.c
More file actions
1569 lines (1443 loc) · 56.8 KB
/
Copy pathtcp_in.c
File metadata and controls
1569 lines (1443 loc) · 56.8 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
10000
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
/**
* @file
* Transmission Control Protocol, incoming traffic
*
* The input processing functions of the TCP layer.
*
* These functions are generally called in the order (ip_input() ->)
* tcp_input() -> * tcp_process() -> tcp_receive() (-> application).
*
*/
/*
* Copyright (c) 2001-2004 Swedish Institute of Computer Science.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without modification,
* are permitted provided that the following conditions are met:
*
* 1. Redistributions of source code must retain the above copyright notice,
* this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright notice,
* this list of conditions and the following disclaimer in the documentation
* and/or other materials provided with the distribution.
* 3. The name of the author may not be used to endorse or promote products
* derived from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT
* SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
* EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT
* OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
* IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY
* OF SUCH DAMAGE.
*
* This file is part of the lwIP TCP/IP stack.
*
* Author: Adam Dunkels <adam@sics.se>
*
*/
#include "lwip/opt.h"
#if LWIP_TCP /* don't build if not configured for use in lwipopts.h */
#include "lwip/tcp_impl.h"
#include "lwip/def.h"
#include "lwip/ip_addr.h"
#include "lwip/netif.h"
#include "lwip/mem.h"
#include "lwip/memp.h"
#include "lwip/inet_chksum.h"
#include "lwip/stats.h"
#include "lwip/snmp.h"
#include "arch/perf.h"
/* These variables are global to all functions involved in the input
processing of TCP segments. They are set by the tcp_input()
function. */
static struct tcp_seg inseg;
static struct tcp_hdr *tcphdr;
static struct ip_hdr *iphdr;
static u32_t seqno, ackno;
static u8_t flags;
static u16_t tcplen;
static u8_t recv_flags;
static struct pbuf *recv_data;
struct tcp_pcb *tcp_input_pcb;
/* Forward declarations. */
static err_t tcp_process(struct tcp_pcb *pcb);
static void tcp_receive(struct tcp_pcb *pcb);
static void tcp_parseopt(struct tcp_pcb *pcb);
static err_t tcp_listen_input(struct tcp_pcb_listen *pcb);
static err_t tcp_timewait_input(struct tcp_pcb *pcb);
/**
* The initial input processing of TCP. It verifies the TCP header, demultiplexes
* the segment between the PCBs and passes it on to tcp_process(), which implements
* the TCP finite state machine. This function is called by the IP layer (in
* ip_input()).
*
* @param p received TCP segment to process (p->payload pointing to the IP header)
* @param inp network interface on which this segment was received
*/
void
tcp_input(struct pbuf *p, struct netif *inp)
{
struct tcp_pcb *pcb, *prev;
struct tcp_pcb_listen *lpcb;
#if SO_REUSE
struct tcp_pcb *lpcb_prev = NULL;
struct tcp_pcb_listen *lpcb_any = NULL;
#endif /* SO_REUSE */
u8_t hdrlen;
err_t err;
PERF_START;
TCP_STATS_INC(tcp.recv);
snmp_inc_tcpinsegs();
iphdr = (struct ip_hdr *)p->payload;
tcphdr = (struct tcp_hdr *)((u8_t *)p->payload + IPH_HL(iphdr) * 4);
#if TCP_INPUT_DEBUG
tcp_debug_print(tcphdr);
#endif
/* remove header from payload */
if (pbuf_header(p, -((s16_t)(IPH_HL(iphdr) * 4))) || (p->tot_len < sizeof(struct tcp_hdr))) {
/* drop short packets */
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("tcp_input: short packet (%"U16_F" bytes) discarded\n", p->tot_len));
TCP_STATS_INC(tcp.lenerr);
TCP_STATS_INC(tcp.drop);
snmp_inc_tcpinerrs();
pbuf_free(p);
return;
}
/* Don't even process incoming broadcasts/multicasts. */
if (ip_addr_isbroadcast(¤t_iphdr_dest, inp) ||
ip_addr_ismulticast(¤t_iphdr_dest)) {
TCP_STATS_INC(tcp.proterr);
TCP_STATS_INC(tcp.drop);
snmp_inc_tcpinerrs();
pbuf_free(p);
return;
}
#if CHECKSUM_CHECK_TCP
/* Verify TCP checksum. */
if (inet_chksum_pseudo(p, ip_current_src_addr(), ip_current_dest_addr(),
IP_PROTO_TCP, p->tot_len) != 0) {
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("tcp_input: packet discarded due to failing checksum 0x%04"X16_F"\n",
inet_chksum_pseudo(p, ip_current_src_addr(), ip_current_dest_addr(),
IP_PROTO_TCP, p->tot_len)));
#if TCP_DEBUG
tcp_debug_print(tcphdr);
#endif /* TCP_DEBUG */
TCP_STATS_INC(tcp.chkerr);
TCP_STATS_INC(tcp.drop);
snmp_inc_tcpinerrs();
pbuf_free(p);
return;
}
#endif
/* Move the payload pointer in the pbuf so that it points to the
TCP data instead of the TCP header. */
hdrlen = TCPH_HDRLEN(tcphdr);
if(pbuf_header(p, -(hdrlen * 4))){
/* drop short packets */
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("tcp_input: short packet\n"));
TCP_STATS_INC(tcp.lenerr);
TCP_STATS_INC(tcp.drop);
snmp_inc_tcpinerrs();
pbuf_free(p);
return;
}
/* Convert fields in TCP header to host byte order. */
tcphdr->src = ntohs(tcphdr->src);
tcphdr->dest = ntohs(tcphdr->dest);
seqno = tcphdr->seqno = ntohl(tcphdr->seqno);
ackno = tcphdr->ackno = ntohl(tcphdr->ackno);
tcphdr->wnd = ntohs(tcphdr->wnd);
flags = TCPH_FLAGS(tcphdr);
tcplen = p->tot_len + ((flags & (TCP_FIN | TCP_SYN)) ? 1 : 0);
/* Demultiplex an incoming segment. First, we check if it is destined
for an active connection. */
prev = NULL;
for(pcb = tcp_active_pcbs; pcb != NULL; pcb = pcb->next) {
LWIP_ASSERT("tcp_input: active pcb->state != CLOSED", pcb->state != CLOSED);
LWIP_ASSERT("tcp_input: active pcb->state != TIME-WAIT", pcb->state != TIME_WAIT);
LWIP_ASSERT("tcp_input: active pcb->state != LISTEN", pcb->state != LISTEN);
if (pcb->remote_port == tcphdr->src &&
pcb->local_port == tcphdr->dest &&
ip_addr_cmp(&(pcb->remote_ip), ¤t_iphdr_src) &&
ip_addr_cmp(&(pcb->local_ip), ¤t_iphdr_dest)) {
/* Move this PCB to the front of the list so that subsequent
lookups will be faster (we exploit locality in TCP segment
arrivals). */
LWIP_ASSERT("tcp_input: pcb->next != pcb (before cache)", pcb->next != pcb);
if (prev != NULL) {
prev->next = pcb->next;
pcb->next = tcp_active_pcbs;
tcp_active_pcbs = pcb;
}
LWIP_ASSERT("tcp_input: pcb->next != pcb (after cache)", pcb->next != pcb);
break;
}
prev = pcb;
}
if (pcb == NULL) {
/* If it did not go to an active connection, we check the connections
in the TIME-WAIT state. */
for(pcb = tcp_tw_pcbs; pcb != NULL; pcb = pcb->next) {
LWIP_ASSERT("tcp_input: TIME-WAIT pcb->state == TIME-WAIT", pcb->state == TIME_WAIT);
if (pcb->remote_port == tcphdr->src &&
pcb->local_port == tcphdr->dest &&
ip_addr_cmp(&(pcb->remote_ip), ¤t_iphdr_src) &&
ip_addr_cmp(&(pcb->local_ip), ¤t_iphdr_dest)) {
/* We don't really care enough to move this PCB to the front
of the list since we are not very likely to receive that
many segments for connections in TIME-WAIT. */
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("tcp_input: packed for TIME_WAITing connection.\n"));
tcp_timewait_input(pcb);
pbuf_free(p);
return;
}
}
/* Finally, if we still did not get a match, we check all PCBs that
are LISTENing for incoming connections. */
prev = NULL;
for(lpcb = tcp_listen_pcbs.listen_pcbs; lpcb != NULL; lpcb = lpcb->next) {
if (lpcb->local_port == tcphdr->dest) {
#if SO_REUSE
if (ip_addr_cmp(&(lpcb->local_ip), ¤t_iphdr_dest)) {
/* found an exact match */
break;
} else if(ip_addr_isany(&(lpcb->local_ip))) {
/* found an ANY-match */
lpcb_any = lpcb;
lpcb_prev = prev;
}
#else /* SO_REUSE */
if (ip_addr_cmp(&(lpcb->local_ip), ¤t_iphdr_dest) ||
ip_addr_isany(&(lpcb->local_ip))) {
/* found a match */
break;
}
#endif /* SO_REUSE */
}
prev = (struct tcp_pcb *)lpcb;
}
#if SO_REUSE
/* first try specific local IP */
if (lpcb == NULL) {
/* only pass to ANY if no specific local IP has been found */
lpcb = lpcb_any;
prev = lpcb_prev;
}
#endif /* SO_REUSE */
if (lpcb != NULL) {
/* Move this PCB to the front of the list so that subsequent
lookups will be faster (we exploit locality in TCP segment
arrivals). */
if (prev != NULL) {
((struct tcp_pcb_listen *)prev)->next = lpcb->next;
/* our successor is the remainder of the listening list */
lpcb->next = tcp_listen_pcbs.listen_pcbs;
/* put this listening pcb at the head of the listening list */
tcp_listen_pcbs.listen_pcbs = lpcb;
}
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("tcp_input: packed for LISTENing connection.\n"));
tcp_listen_input(lpcb);
pbuf_free(p);
return;
}
}
#if TCP_INPUT_DEBUG
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("+-+-+-+-+-+-+-+-+-+-+-+-+-+- tcp_input: flags "));
tcp_debug_print_flags(TCPH_FLAGS(tcphdr));
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("-+-+-+-+-+-+-+-+-+-+-+-+-+-+\n"));
#endif /* TCP_INPUT_DEBUG */
if (pcb != NULL) {
/* The incoming segment belongs to a connection. */
#if TCP_INPUT_DEBUG
#if TCP_DEBUG
tcp_debug_print_state(pcb->state);
#endif /* TCP_DEBUG */
#endif /* TCP_INPUT_DEBUG */
/* Set up a tcp_seg structure. */
inseg.next = NULL;
inseg.len = p->tot_len;
inseg.dataptr = p->payload;
inseg.p = p;
inseg.tcphdr = tcphdr;
recv_data = NULL;
recv_flags = 0;
/* If there is data which was previously "refused" by upper layer */
if (pcb->refused_data != NULL) {
/* Notify again application with data previously received. */
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("tcp_input: notify kept packet\n"));
TCP_EVENT_RECV(pcb, pcb->refused_data, ERR_OK, err);
if (err == ERR_OK) {
pcb->refused_data = NULL;
} else {
/* if err == ERR_ABRT, 'pcb' is already deallocated */
/* drop incoming packets, because pcb is "full" */
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("tcp_input: drop incoming packets, because pcb is \"full\"\n"));
TCP_STATS_INC(tcp.drop);
snmp_inc_tcpinerrs();
pbuf_free(p);
return;
}
}
tcp_input_pcb = pcb;
err = tcp_process(pcb);
/* A return value of ERR_ABRT means that tcp_abort() was called
and that the pcb has been freed. If so, we don't do anything. */
if (err != ERR_ABRT) {
if (recv_flags & TF_RESET) {
/* TF_RESET means that the connection was reset by the other
end. We then call the error callback to inform the
application that the connection is dead before we
deallocate the PCB. */
TCP_EVENT_ERR(pcb->errf, pcb->callback_arg, ERR_RST);
tcp_pcb_remove(&tcp_active_pcbs, pcb);
memp_free(MEMP_TCP_PCB, pcb);
} else if (recv_flags & TF_CLOSED) {
/* The connection has been closed and we will deallocate the
PCB. */
tcp_pcb_remove(&tcp_active_pcbs, pcb);
memp_free(MEMP_TCP_PCB, pcb);
} else {
err = ERR_OK;
/* If the application has registered a "sent" function to be
called when new send buffer space is available, we call it
now. */
if (pcb->acked > 0) {
TCP_EVENT_SENT(pcb, pcb->acked, err);
if (err == ERR_ABRT) {
goto aborted;
}
}
if (recv_data != NULL) {
if (pcb->flags & TF_RXCLOSED) {
/* received data although already closed -> abort (send RST) to
notify the remote host that not all data has been processed */
pbuf_free(recv_data);
tcp_abort(pcb);
goto aborted;
}
if (flags & TCP_PSH) {
recv_data->flags |= PBUF_FLAG_PUSH;
}
/* Notify application that data has been received. */
TCP_EVENT_RECV(pcb, recv_data, ERR_OK, err);
if (err == ERR_ABRT) {
goto aborted;
}
/* If the upper layer can't receive this data, store it */
if (err != ERR_OK) {
pcb->refused_data = recv_data;
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("tcp_input: keep incoming packet, because pcb is \"full\"\n"));
}
}
/* If a FIN segment was received, we call the callback
function with a NULL buffer to indicate EOF. */
if (recv_flags & TF_GOT_FIN) {
/* correct rcv_wnd as the application won't call tcp_recved()
for the FIN's seqno */
if (pcb->rcv_wnd != TCP_WND) {
pcb->rcv_wnd++;
}
TCP_EVENT_CLOSED(pcb, err);
if (err == ERR_ABRT) {
goto aborted;
}
}
tcp_input_pcb = NULL;
/* Try to send something out. */
tcp_output(pcb);
#if TCP_INPUT_DEBUG
#if TCP_DEBUG
tcp_debug_print_state(pcb->state);
#endif /* TCP_DEBUG */
#endif /* TCP_INPUT_DEBUG */
}
}
/* Jump target if pcb has been aborted in a callback (by calling tcp_abort()).
Below this line, 'pcb' may not be dereferenced! */
aborted:
tcp_input_pcb = NULL;
recv_data = NULL;
/* give up our reference to inseg.p */
if (inseg.p != NULL)
{
pbuf_free(inseg.p);
inseg.p = NULL;
}
} else {
/* If no matching PCB was found, send a TCP RST (reset) to the
sender. */
LWIP_DEBUGF(TCP_RST_DEBUG, ("tcp_input: no PCB match found, resetting.\n"));
if (!(TCPH_FLAGS(tcphdr) & TCP_RST)) {
TCP_STATS_INC(tcp.proterr);
TCP_STATS_INC(tcp.drop);
tcp_rst(ackno, seqno + tcplen,
ip_current_dest_addr(), ip_current_src_addr(),
tcphdr->dest, tcphdr->src);
}
pbuf_free(p);
}
LWIP_ASSERT("tcp_input: tcp_pcbs_sane()", tcp_pcbs_sane());
PERF_STOP("tcp_input");
}
/**
* Called by tcp_input() when a segment arrives for a listening
* connection (from tcp_input()).
*
* @param pcb the tcp_pcb_listen for which a segment arrived
* @return ERR_OK if the segment was processed
* another err_t on error
*
* @note the return value is not (yet?) used in tcp_input()
* @note the segment which arrived is saved in global variables, therefore only the pcb
* involved is passed as a parameter to this function
*/
static err_t
tcp_listen_input(struct tcp_pcb_listen *pcb)
{
struct tcp_pcb *npcb;
err_t rc;
/* In the LISTEN state, we check for incoming SYN segments,
creates a new PCB, and responds with a SYN|ACK. */
if (flags & TCP_ACK) {
/* For incoming segments with the ACK flag set, respond with a
RST. */
LWIP_DEBUGF(TCP_RST_DEBUG, ("tcp_listen_input: ACK in LISTEN, sending reset\n"));
tcp_rst(ackno + 1, seqno + tcplen,
ip_current_dest_addr(), ip_current_src_addr(),
tcphdr->dest, tcphdr->src);
} else if (flags & TCP_SYN) {
LWIP_DEBUGF(TCP_DEBUG, ("TCP connection request %"U16_F" -> %"U16_F".\n", tcphdr->src, tcphdr->dest));
#if TCP_LISTEN_BACKLOG
if (pcb->accepts_pending >= pcb->backlog) {
LWIP_DEBUGF(TCP_DEBUG, ("tcp_listen_input: listen backlog exceeded for port %"U16_F"\n", tcphdr->dest));
return ERR_ABRT;
}
#endif /* TCP_LISTEN_BACKLOG */
npcb = tcp_alloc(pcb->prio);
/* If a new PCB could not be created (probably due to lack of memory),
we don't do anything, but rely on the sender will retransmit the
SYN at a time when we have more memory available. */
if (npcb == NULL) {
LWIP_DEBUGF(TCP_DEBUG, ("tcp_listen_input: could not allocate PCB\n"));
TCP_STATS_INC(tcp.memerr);
return ERR_MEM;
}
#if TCP_LISTEN_BACKLOG
pcb->accepts_pending++;
#endif /* TCP_LISTEN_BACKLOG */
/* Set up the new PCB. */
ip_addr_copy(npcb->local_ip, current_iphdr_dest);
npcb->local_port = pcb->local_port;
ip_addr_copy(npcb->remote_ip, current_iphdr_src);
npcb->remote_port = tcphdr->src;
npcb->state = SYN_RCVD;
npcb->rcv_nxt = seqno + 1;
npcb->rcv_ann_right_edge = npcb->rcv_nxt;
npcb->snd_wnd = tcphdr->wnd;
npcb->ssthresh = npcb->snd_wnd;
npcb->snd_wl1 = seqno - 1;/* initialise to seqno-1 to force window update */
npcb->callback_arg = pcb->callback_arg;
#if LWIP_CALLBACK_API
npcb->accept = pcb->accept;
#endif /* LWIP_CALLBACK_API */
/* inherit socket options */
npcb->so_options = pcb->so_options & SOF_INHERITED;
/* Register the new PCB so that we can begin receiving segments
for it. */
TCP_REG(&tcp_active_pcbs, npcb);
/* Parse any options in the SYN. */
tcp_parseopt(npcb);
#if TCP_CALCULATE_EFF_SEND_MSS
npcb->mss = tcp_eff_send_mss(npcb->mss, &(npcb->remote_ip));
#endif /* TCP_CALCULATE_EFF_SEND_MSS */
snmp_inc_tcppassiveopens();
/* Send a SYN|ACK together with the MSS option. */
rc = tcp_enqueue_flags(npcb, TCP_SYN | TCP_ACK);
if (rc != ERR_OK) {
tcp_abandon(npcb, 0);
return rc;
}
return tcp_output(npcb);
}
return ERR_OK;
}
/**
* Called by tcp_input() when a segment arrives for a connection in
* TIME_WAIT.
*
* @param pcb the tcp_pcb for which a segment arrived
*
* @note the segment which arrived is saved in global variables, therefore only the pcb
* involved is passed as a parameter to this function
*/
static err_t
tcp_timewait_input(struct tcp_pcb *pcb)
{
/* RFC 1337: in TIME_WAIT, ignore RST and ACK FINs + any 'acceptable' segments */
/* RFC 793 3.9 Event Processing - Segment Arrives:
* - first check sequence number - we skip that one in TIME_WAIT (always
* acceptable since we only send ACKs)
* - second check the RST bit (... return) */
if (flags & TCP_RST) {
return ERR_OK;
}
/* - fourth, check the SYN bit, */
if (flags & TCP_SYN) {
/* If an incoming segment is not acceptable, an acknowledgment
should be sent in reply */
if (TCP_SEQ_BETWEEN(seqno, pcb->rcv_nxt, pcb->rcv_nxt+pcb->rcv_wnd)) {
/* If the SYN is in the window it is an error, send a reset */
tcp_rst(ackno, seqno + tcplen, ip_current_dest_addr(), ip_current_src_addr(),
tcphdr->dest, tcphdr->src);
return ERR_OK;
}
} else if (flags & TCP_FIN) {
/* - eighth, check the FIN bit: Remain in the TIME-WAIT state.
Restart the 2 MSL time-wait timeout.*/
pcb->tmr = tcp_ticks;
}
if ((tcplen > 0)) {
/* Acknowledge data, FIN or out-of-window SYN */
pcb->flags |= TF_ACK_NOW;
return tcp_output(pcb);
}
return ERR_OK;
}
/**
* Implements the TCP state machine. Called by tcp_input. In some
* states tcp_receive() is called to receive data. The tcp_seg
* argument will be freed by the caller (tcp_input()) unless the
* recv_data pointer in the pcb is set.
*
* @param pcb the tcp_pcb for which a segment arrived
*
* @note the segment which arrived is saved in global variables, therefore only the pcb
* involved is passed as a parameter to this function
*/
static err_t
tcp_process(struct tcp_pcb *pcb)
{
struct tcp_seg *rseg;
u8_t acceptable = 0;
err_t err;
err = ERR_OK;
/* Process incoming RST segments. */
if (flags & TCP_RST) {
/* First, determine if the reset is acceptable. */
if (pcb->state == SYN_SENT) {
if (ackno == pcb->snd_nxt) {
acceptable = 1;
}
} else {
if (TCP_SEQ_BETWEEN(seqno, pcb->rcv_nxt,
pcb->rcv_nxt+pcb->rcv_wnd)) {
acceptable = 1;
}
}
if (acceptable) {
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("tcp_process: Connection RESET\n"));
LWIP_ASSERT("tcp_input: pcb->state != CLOSED", pcb->state != CLOSED);
recv_flags |= TF_RESET;
pcb->flags &= ~TF_ACK_DELAY;
return ERR_RST;
} else {
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("tcp_process: unacceptable reset seqno %"U32_F" rcv_nxt %"U32_F"\n",
seqno, pcb->rcv_nxt));
LWIP_DEBUGF(TCP_DEBUG, ("tcp_process: unacceptable reset seqno %"U32_F" rcv_nxt %"U32_F"\n",
seqno, pcb->rcv_nxt));
return ERR_OK;
}
}
if ((flags & TCP_SYN) && (pcb->state != SYN_SENT && pcb->state != SYN_RCVD)) {
/* Cope with new connection attempt after remote end crashed */
tcp_ack_now(pcb);
return ERR_OK;
}
if ((pcb->flags & TF_RXCLOSED) == 0) {
/* Update the PCB (in)activity timer unless rx is closed (see tcp_shutdown) */
pcb->tmr = tcp_ticks;
}
pcb->keep_cnt_sent = 0;
tcp_parseopt(pcb);
/* Do different things depending on the TCP state. */
switch (pcb->state) {
case SYN_SENT:
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("SYN-SENT: ackno %"U32_F" pcb->snd_nxt %"U32_F" unacked %"U32_F"\n", ackno,
pcb->snd_nxt, ntohl(pcb->unacked->tcphdr->seqno)));
/* received SYN ACK with expected sequence number? */
if ((flags & TCP_ACK) && (flags & TCP_SYN)
&& ackno == ntohl(pcb->unacked->tcphdr->seqno) + 1) {
pcb->snd_buf++;
pcb->rcv_nxt = seqno + 1;
pcb->rcv_ann_right_edge = pcb->rcv_nxt;
pcb->lastack = ackno;
pcb->snd_wnd = tcphdr->wnd;
pcb->snd_wl1 = seqno - 1; /* initialise to seqno - 1 to force window update */
pcb->state = ESTABLISHED;
#if TCP_CALCULATE_EFF_SEND_MSS
pcb->mss = tcp_eff_send_mss(pcb->mss, &(pcb->remote_ip));
#endif /* TCP_CALCULATE_EFF_SEND_MSS */
/* Set ssthresh again after changing pcb->mss (already set in tcp_connect
* but for the default value of pcb->mss) */
pcb->ssthresh = pcb->mss * 10;
pcb->cwnd = ((pcb->cwnd == 1) ? (pcb->mss * 2) : pcb->mss);
LWIP_ASSERT("pcb->snd_queuelen > 0", (pcb->snd_queuelen > 0));
--pcb->snd_queuelen;
LWIP_DEBUGF(TCP_QLEN_DEBUG, ("tcp_process: SYN-SENT --queuelen %"U16_F"\n", (u16_t)pcb->snd_queuelen));
rseg = pcb->unacked;
pcb->unacked = rseg->next;
/* If there's nothing left to acknowledge, stop the retransmit
timer, otherwise reset it to start again */
if(pcb->unacked == NULL)
pcb->rtime = -1;
else {
pcb->rtime = 0;
pcb->nrtx = 0;
}
tcp_seg_free(rseg);
/* Call the user specified function to call when sucessfully
* connected. */
TCP_EVENT_CONNECTED(pcb, ERR_OK, err);
if (err == ERR_ABRT) {
return ERR_ABRT;
}
tcp_ack_now(pcb);
}
/* received ACK? possibly a half-open connection */
else if (flags & TCP_ACK) {
/* send a RST to bring the other side in a non-synchronized state. */
tcp_rst(ackno, seqno + tcplen, ip_current_dest_addr(), ip_current_src_addr(),
tcphdr->dest, tcphdr->src);
}
break;
case SYN_RCVD:
if (flags & TCP_ACK) {
/* expected ACK number? */
if (TCP_SEQ_BETWEEN(ackno, pcb->lastack+1, pcb->snd_nxt)) {
u16_t old_cwnd;
pcb->state = ESTABLISHED;
LWIP_DEBUGF(TCP_DEBUG, ("TCP connection established %"U16_F" -> %"U16_F".\n", inseg.tcphdr->src, inseg.tcphdr->dest));
#if LWIP_CALLBACK_API
LWIP_ASSERT("pcb->accept != NULL", pcb->accept != NULL);
#endif
/* Call the accept function. */
TCP_EVENT_ACCEPT(pcb, ERR_OK, err);
if (err != ERR_OK) {
/* If the accept function returns with an error, we abort
* the connection. */
/* Already aborted? */
if (err != ERR_ABRT) {
tcp_abort(pcb);
}
return ERR_ABRT;
}
old_cwnd = pcb->cwnd;
/* If there was any data contained within this ACK,
* we'd better pass it on to the application as well. */
tcp_receive(pcb);
/* Prevent ACK for SYN to generate a sent event */
if (pcb->acked != 0) {
pcb->acked--;
}
pcb->cwnd = ((old_cwnd == 1) ? (pcb->mss * 2) : pcb->mss);
if (recv_flags & TF_GOT_FIN) {
tcp_ack_now(pcb);
pcb->state = CLOSE_WAIT;
}
} else {
/* incorrect ACK number, send RST */
tcp_rst(ackno, seqno + tcplen, ip_current_dest_addr(), ip_current_src_addr(),
tcphdr->dest, tcphdr->src);
}
} else if ((flags & TCP_SYN) && (seqno == pcb->rcv_nxt - 1)) {
/* Looks like another copy of the SYN - retransmit our SYN-ACK */
tcp_rexmit(pcb);
}
break;
case CLOSE_WAIT:
/* FALLTHROUGH */
case ESTABLISHED:
tcp_receive(pcb);
if (recv_flags & TF_GOT_FIN) { /* passive close */
tcp_ack_now(pcb);
pcb->state = CLOSE_WAIT;
}
break;
case FIN_WAIT_1:
tcp_receive(pcb);
if (recv_flags & TF_GOT_FIN) {
if ((flags & TCP_ACK) && (ackno == pcb->snd_nxt)) {
LWIP_DEBUGF(TCP_DEBUG,
("TCP connection closed: FIN_WAIT_1 %"U16_F" -> %"U16_F".\n", inseg.tcphdr->src, inseg.tcphdr->dest));
tcp_ack_now(pcb);
tcp_pcb_purge(pcb);
TCP_RMV(&tcp_active_pcbs, pcb);
pcb->state = TIME_WAIT;
TCP_REG(&tcp_tw_pcbs, pcb);
} else {
tcp_ack_now(pcb);
pcb->state = CLOSING;
}
} else if ((flags & TCP_ACK) && (ackno == pcb->snd_nxt)) {
pcb->state = FIN_WAIT_2;
}
break;
case FIN_WAIT_2:
tcp_receive(pcb);
if (recv_flags & TF_GOT_FIN) {
LWIP_DEBUGF(TCP_DEBUG, ("TCP connection closed: FIN_WAIT_2 %"U16_F" -> %"U16_F".\n", inseg.tcphdr->src, inseg.tcphdr->dest));
tcp_ack_now(pcb);
tcp_pcb_purge(pcb);
TCP_RMV(&tcp_active_pcbs, pcb);
pcb->state = TIME_WAIT;
TCP_REG(&tcp_tw_pcbs, pcb);
}
break;
case CLOSING:
tcp_receive(pcb);
if (flags & TCP_ACK && ackno == pcb->snd_nxt) {
LWIP_DEBUGF(TCP_DEBUG, ("TCP connection closed: CLOSING %"U16_F" -> %"U16_F".\n", inseg.tcphdr->src, inseg.tcphdr->dest));
tcp_pcb_purge(pcb);
TCP_RMV(&tcp_active_pcbs, pcb);
pcb->state = TIME_WAIT;
TCP_REG(&tcp_tw_pcbs, pcb);
}
break;
case LAST_ACK:
tcp_receive(pcb);
if (flags & TCP_ACK && ackno == pcb->snd_nxt) {
LWIP_DEBUGF(TCP_DEBUG, ("TCP connection closed: LAST_ACK %"U16_F" -> %"U16_F".\n", inseg.tcphdr->src, inseg.tcphdr->dest));
/* bugfix #21699: don't set pcb->state to CLOSED here or we risk leaking segments */
recv_flags |= TF_CLOSED;
}
break;
default:
break;
}
return ERR_OK;
}
#if TCP_QUEUE_OOSEQ
/**
* Insert segment into the list (segments covered with new one will be deleted)
*
* Called from tcp_receive()
*/
static void
tcp_oos_insert_segment(struct tcp_seg *cseg, struct tcp_seg *next)
{
struct tcp_seg *old_seg;
if (TCPH_FLAGS(cseg->tcphdr) & TCP_FIN) {
/* received segment overlaps all following segments */
tcp_segs_free(next);
next = NULL;
}
else {
/* delete some following segments
oos queue may have segments with FIN flag */
while (next &&
TCP_SEQ_GEQ((seqno + cseg->len),
(next->tcphdr->seqno + next->len))) {
/* cseg with FIN already processed */
if (TCPH_FLAGS(next->tcphdr) & TCP_FIN) {
TCPH_SET_FLAG(cseg->tcphdr, TCP_FIN);
}
old_seg = next;
next = next->next;
tcp_seg_free(old_seg);
}
if (next &&
TCP_SEQ_GT(seqno + cseg->len, next->tcphdr->seqno)) {
/* We need to trim the incoming segment. */
cseg->len = (u16_t)(next->tcphdr->seqno - seqno);
pbuf_realloc(cseg->p, cseg->len);
}
}
cseg->next = next;
}
#endif /* TCP_QUEUE_OOSEQ */
/**
* Called by tcp_process. Checks if the given segment is an ACK for outstanding
* data, and if so frees the memory of the buffered data. Next, is places the
* segment on any of the receive queues (pcb->recved or pcb->ooseq). If the segment
* is buffered, the pbuf is referenced by pbuf_ref so that it will not be freed until
* i it has been removed from the buffer.
*
* If the incoming segment constitutes an ACK for a segment that was used for RTT
* estimation, the RTT is estimated here as well.
*
* Called from tcp_process().
*/
static void
tcp_receive(struct tcp_pcb *pcb)
{
struct tcp_seg *next;
#if TCP_QUEUE_OOSEQ
struct tcp_seg *prev, *cseg;
#endif /* TCP_QUEUE_OOSEQ */
struct pbuf *p;
s32_t off;
s16_t m;
u32_t right_wnd_edge;
u16_t new_tot_len;
int found_dupack = 0;
if (flags & TCP_ACK) {
right_wnd_edge = pcb->snd_wnd + pcb->snd_wl2;
/* Update window. */
if (TCP_SEQ_LT(pcb->snd_wl1, seqno) ||
(pcb->snd_wl1 == seqno && TCP_SEQ_LT(pcb->snd_wl2, ackno)) ||
(pcb->snd_wl2 == ackno && tcphdr->wnd > pcb->snd_wnd)) {
pcb->snd_wnd = tcphdr->wnd;
pcb->snd_wl1 = seqno;
pcb->snd_wl2 = ackno;
if (pcb->snd_wnd > 0 && pcb->persist_backoff > 0) {
pcb->persist_backoff = 0;
}
LWIP_DEBUGF(TCP_WND_DEBUG, ("tcp_receive: window update %"U16_F"\n", pcb->snd_wnd));
#if TCP_WND_DEBUG
} else {
if (pcb->snd_wnd != tcphdr->wnd) {
LWIP_DEBUGF(TCP_WND_DEBUG,
("tcp_receive: no window update lastack %"U32_F" ackno %"
U32_F" wl1 %"U32_F" seqno %"U32_F" wl2 %"U32_F"\n",
pcb->lastack, ackno, pcb->snd_wl1, seqno, pcb->snd_wl2));
}
#endif /* TCP_WND_DEBUG */
}
/* (From Stevens TCP/IP Illustrated Vol II, p970.) Its only a
* duplicate ack if:
* 1) It doesn't ACK new data
* 2) length of received packet is zero (i.e. no payload)
* 3) the advertised window hasn't changed
* 4) There is outstanding unacknowledged data (retransmission timer running)
* 5) The ACK is == biggest ACK sequence number so far seen (snd_una)
*
* If it passes all five, should process as a dupack:
* a) dupacks < 3: do nothing
* b) dupacks == 3: fast retransmit
* c) dupacks > 3: increase cwnd
*
* If it only passes 1-3, should reset dupack counter (and add to
* stats, which we don't do in lwIP)
*
* If it only passes 1, should reset dupack counter
*
*/
/* Clause 1 */
if (TCP_SEQ_LEQ(ackno, pcb->lastack)) {
pcb->acked = 0;
/* Clause 2 */
if (tcplen == 0) {
/* Clause 3 */
if (pcb->snd_wl2 + pcb->snd_wnd == right_wnd_edge){
/* Clause 4 */
if (pcb->rtime >= 0) {
/* Clause 5 */
if (pcb->lastack == ackno) {
found_dupack = 1;
if (pcb->dupacks + 1 > pcb->dupacks)
++pcb->dupacks;
if (pcb->dupacks > 3) {
/* Inflate the congestion window, but not if it means that
the value overflows. */
if ((u16_t)(pcb->cwnd + pcb->mss) > pcb->cwnd) {
pcb->cwnd += pcb->mss;
}
} else if (pcb->dupacks == 3) {
/* Do fast retransmit */
tcp_rexmit_fast(pcb);
}
}
}
}
}
/* If Clause (1) or more is true, but not a duplicate ack, reset
* count of consecutive duplicate acks */
if (!found_dupack) {
pcb->dupacks = 0;
}
} else if (TCP_SEQ_BETWEEN(ackno, pcb->lastack+1, pcb->snd_nxt)){
/* We come here when the ACK acknowledges new data. */
/* Reset the "IN Fast Retransmit" flag, since we are no longer
in fast retransmit. Also reset the congestion window to the
slow start threshold. */
if (pcb->flags & TF_INFR) {
pcb->flags &= ~TF_INFR;
pcb->cwnd = pcb->ssthresh;
}
/* Reset the number of retransmissions. */
pcb->nrtx = 0;
/* Reset the retransmission time-out. */
pcb->rto = (pcb->sa >> 3) + pcb->sv;
/* Update the send buffer space. Diff between the two can never exceed 64K? */
pcb->acked = (u16_t)(ackno - pcb->lastack);
pcb->snd_buf += pcb->acked;
/* Reset the fast retransmit variables. */
pcb->dupacks = 0;
pcb->lastack = ackno;
/* Update the congestion control variables (cwnd and
ssthresh). */
if (pcb->state >= ESTABLISHED) {
if (pcb->cwnd < pcb->ssthresh) {
if ((u16_t)(pcb->cwnd + pcb->mss) > pcb->cwnd) {
pcb->cwnd += pcb->mss;
}
LWIP_DEBUGF(TCP_CWND_DEBUG, ("tcp_receive: slow start cwnd %"U16_F"\n", pcb->cwnd));
} else {
u16_t new_cwnd = (pcb->cwnd + pcb->mss * pcb->mss / pcb->cwnd);
if (new_cwnd > pcb->cwnd) {
pcb->cwnd = new_cwnd;
}
LWIP_DEBUGF(TCP_CWND_DEBUG, ("tcp_receive: congestion avoidance cwnd %"U16_F"\n", pcb->cwnd));
}
}
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("tcp_receive: ACK for %"U32_F", unacked->seqno %"U32_F":%"U32_F"\n",
ackno,
pcb->unacked != NULL?
ntohl(pcb->unacked->tcphdr->seqno): 0,
pcb->unacked != NULL?
ntohl(pcb->unacked->tcphdr->seqno) + TCP_TCPLEN(pcb->unacked): 0));
/* Remove segment from the unacknowledged list if the incoming
ACK acknowlegdes them. */
while (pcb->unacked != NULL &&
TCP_SEQ_LEQ(ntohl(pcb->unacked->tcphdr->seqno) +
TCP_TCPLEN(pcb->unacked), ackno)) {
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("tcp_receive: removing %"U32_F":%"U32_F" from pcb->unacked\n",
ntohl(pcb->unacked->tcphdr->seqno),
ntohl(pcb->unacked->tcphdr->seqno) +
TCP_TCPLEN(pcb->unacked)));
next = pcb->unacked;
pcb->unacked = pcb->unacked->next;
LWIP_DEBUGF(TCP_QLEN_DEBUG, ("tcp_receive: queuelen %"U16_F" ... ", (u16_t)pcb->snd_queuelen));
LWIP_ASSERT("pcb->snd_queuelen >= pbuf_clen(next->p)", (pcb->snd_queuelen >= pbuf_clen(next->p)));
/* Prevent ACK for FIN to generate a sent event */
if ((pcb->acked != 0) && ((TCPH_FLAGS(next->tcphdr) & TCP_FIN) != 0)) {
pcb->acked--;