-
Notifications
You must be signed in to change notification settings - Fork 447
/
Copy pathtcp_in.c
2179 lines (2003 loc) · 81.5 KB
/
tcp_in.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
/**
* @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 <[email protected]>
*
*/
#include "lwip/opt.h"
#if LWIP_TCP /* don't build if not configured for use in lwipopts.h */
#include "lwip/priv/tcp_priv.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/ip6.h"
#include "lwip/ip6_addr.h"
#if LWIP_ND6_TCP_REACHABILITY_HINTS
#include "lwip/nd6.h"
#endif /* LWIP_ND6_TCP_REACHABILITY_HINTS */
#include <string.h>
#ifdef LWIP_HOOK_FILENAME
#include LWIP_HOOK_FILENAME
#endif
/** Initial CWND calculation as defined RFC 2581 */
#define LWIP_TCP_CALC_INITIAL_CWND(mss) ((tcpwnd_size_t)LWIP_MIN((4U * (mss)), LWIP_MAX((2U * (mss)), 4380U)))
/* 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 u16_t tcphdr_optlen;
static u16_t tcphdr_opt1len;
static u8_t *tcphdr_opt2;
static u16_t tcp_optidx;
static u32_t seqno, ackno;
static tcpwnd_size_t recv_acked;
static u16_t tcplen;
static u8_t flags;
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 void tcp_listen_input(struct tcp_pcb_listen *pcb);
static void tcp_timewait_input(struct tcp_pcb *pcb);
static int tcp_input_delayed_close(struct tcp_pcb *pcb);
#if LWIP_TCP_SACK_OUT
static void tcp_add_sack(struct tcp_pcb *pcb, u32_t left, u32_t right);
static void tcp_remove_sacks_lt(struct tcp_pcb *pcb, u32_t seq);
#if defined(TCP_OOSEQ_BYTES_LIMIT) || defined(TCP_OOSEQ_PBUFS_LIMIT)
static void tcp_remove_sacks_gt(struct tcp_pcb *pcb, u32_t seq);
#endif /* TCP_OOSEQ_BYTES_LIMIT || TCP_OOSEQ_PBUFS_LIMIT */
#endif /* LWIP_TCP_SACK_OUT */
/**
* 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 TCP 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_bytes;
err_t err;
LWIP_UNUSED_ARG(inp);
LWIP_ASSERT_CORE_LOCKED();
LWIP_ASSERT("tcp_input: invalid pbuf", p != NULL);
PERF_START;
TCP_STATS_INC(tcp.recv);
MIB2_STATS_INC(mib2.tcpinsegs);
tcphdr = (struct tcp_hdr *)p->payload;
#if TCP_INPUT_DEBUG
tcp_debug_print(tcphdr);
#endif
/* Check that TCP header fits in payload */
if (p->len < TCP_HLEN) {
/* 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);
goto dropped;
}
/* Don't even process incoming broadcasts/multicasts. */
if (ip_addr_isbroadcast(ip_current_dest_addr(), ip_current_netif()) ||
ip_addr_ismulticast(ip_current_dest_addr())) {
TCP_STATS_INC(tcp.proterr);
goto dropped;
}
#if CHECKSUM_CHECK_TCP
IF__NETIF_CHECKSUM_ENABLED(inp, NETIF_CHECKSUM_CHECK_TCP) {
/* Verify TCP checksum. */
u16_t chksum = ip_chksum_pseudo(p, IP_PROTO_TCP, p->tot_len,
ip_current_src_addr(), ip_current_dest_addr());
if (chksum != 0) {
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("tcp_input: packet discarded due to failing checksum 0x%04"X16_F"\n",
chksum));
tcp_debug_print(tcphdr);
TCP_STATS_INC(tcp.chkerr);
goto dropped;
}
}
#endif /* CHECKSUM_CHECK_TCP */
/* sanity-check header length */
hdrlen_bytes = TCPH_HDRLEN_BYTES(tcphdr);
if ((hdrlen_bytes < TCP_HLEN) || (hdrlen_bytes > p->tot_len)) {
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("tcp_input: invalid header length (%"U16_F")\n", (u16_t)hdrlen_bytes));
TCP_STATS_INC(tcp.lenerr);
goto dropped;
}
/* Move the payload pointer in the pbuf so that it points to the
TCP data instead of the TCP header. */
tcphdr_optlen = (u16_t)(hdrlen_bytes - TCP_HLEN);
tcphdr_opt2 = NULL;
if (p->len >= hdrlen_bytes) {
/* all options are in the first pbuf */
tcphdr_opt1len = tcphdr_optlen;
pbuf_remove_header(p, hdrlen_bytes); /* cannot fail */
} else {
u16_t opt2len;
/* TCP header fits into first pbuf, options don't - data is in the next pbuf */
/* there must be a next pbuf, due to hdrlen_bytes sanity check above */
LWIP_ASSERT("p->next != NULL", p->next != NULL);
/* advance over the TCP header (cannot fail) */
pbuf_remove_header(p, TCP_HLEN);
/* determine how long the first and second parts of the options are */
tcphdr_opt1len = p->len;
opt2len = (u16_t)(tcphdr_optlen - tcphdr_opt1len);
/* options continue in the next pbuf: set p to zero length and hide the
options in the next pbuf (adjusting p->tot_len) */
pbuf_remove_header(p, tcphdr_opt1len);
/* check that the options fit in the second pbuf */
if (opt2len > p->next->len) {
/* drop short packets */
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("tcp_input: options overflow second pbuf (%"U16_F" bytes)\n", p->next->len));
TCP_STATS_INC(tcp.lenerr);
goto dropped;
}
/* remember the pointer to the second part of the options */
tcphdr_opt2 = (u8_t *)p->next->payload;
/* advance p->next to point after the options, and manually
adjust p->tot_len to keep it consistent with the changed p->next */
pbuf_remove_header(p->next, opt2len);
p->tot_len = (u16_t)(p->tot_len - opt2len);
LWIP_ASSERT("p->len == 0", p->len == 0);
LWIP_ASSERT("p->tot_len == p->next->tot_len", p->tot_len == p->next->tot_len);
}
/* Convert fields in TCP header to host byte order. */
tcphdr->src = lwip_ntohs(tcphdr->src);
tcphdr->dest = lwip_ntohs(tcphdr->dest);
seqno = tcphdr->seqno = lwip_ntohl(tcphdr->seqno);
ackno = tcphdr->ackno = lwip_ntohl(tcphdr->ackno);
tcphdr->wnd = lwip_ntohs(tcphdr->wnd);
flags = TCPH_FLAGS(tcphdr);
tcplen = p->tot_len;
if (flags & (TCP_FIN | TCP_SYN)) {
tcplen++;
if (tcplen < p->tot_len) {
/* u16_t overflow, cannot handle this */
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("tcp_input: length u16_t overflow, cannot handle this\n"));
TCP_STATS_INC(tcp.lenerr);
goto dropped;
}
}
/* 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);
/* check if PCB is bound to specific netif */
if ((pcb->netif_idx != NETIF_NO_INDEX) &&
(pcb->netif_idx != netif_get_index(ip_data.current_input_netif))) {
prev = pcb;
continue;
}
if (pcb->remote_port == tcphdr->src &&
pcb->local_port == tcphdr->dest &&
ip_addr_cmp(&pcb->remote_ip, ip_current_src_addr()) &&
ip_addr_cmp(&pcb->local_ip, ip_current_dest_addr())) {
/* 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;
} else {
TCP_STATS_INC(tcp.cachehit);
}
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);
/* check if PCB is bound to specific netif */
if ((pcb->netif_idx != NETIF_NO_INDEX) &&
(pcb->netif_idx != netif_get_index(ip_data.current_input_netif))) {
continue;
}
if (pcb->remote_port == tcphdr->src &&
pcb->local_port == tcphdr->dest &&
ip_addr_cmp(&pcb->remote_ip, ip_current_src_addr()) &&
ip_addr_cmp(&pcb->local_ip, ip_current_dest_addr())) {
/* 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"));
#ifdef LWIP_HOOK_TCP_INPACKET_PCB
if (LWIP_HOOK_TCP_INPACKET_PCB(pcb, tcphdr, tcphdr_optlen, tcphdr_opt1len,
tcphdr_opt2, p) == ERR_OK)
#endif
{
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) {
/* check if PCB is bound to specific netif */
if ((lpcb->netif_idx != NETIF_NO_INDEX) &&
(lpcb->netif_idx != netif_get_index(ip_data.current_input_netif))) {
prev = (struct tcp_pcb *)lpcb;
continue;
}
if (lpcb->local_port == tcphdr->dest) {
if (IP_IS_ANY_TYPE_VAL(lpcb->local_ip)) {
/* found an ANY TYPE (IPv4/IPv6) match */
#if SO_REUSE
lpcb_any = lpcb;
lpcb_prev = prev;
#else /* SO_REUSE */
break;
#endif /* SO_REUSE */
} else if (IP_ADDR_PCB_VERSION_MATCH_EXACT(lpcb, ip_current_dest_addr())) {
if (ip_addr_cmp(&lpcb->local_ip, ip_current_dest_addr())) {
/* found an exact match */
break;
} else if (ip_addr_isany(&lpcb->local_ip)) {
/* found an ANY-match */
#if SO_REUSE
lpcb_any = lpcb;
lpcb_prev = prev;
#else /* SO_REUSE */
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;
} else {
TCP_STATS_INC(tcp.cachehit);
}
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("tcp_input: packed for LISTENing connection.\n"));
#ifdef LWIP_HOOK_TCP_INPACKET_PCB
if (LWIP_HOOK_TCP_INPACKET_PCB((struct tcp_pcb *)lpcb, tcphdr, tcphdr_optlen,
tcphdr_opt1len, tcphdr_opt2, p) == ERR_OK)
#endif
{
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 */
#ifdef LWIP_HOOK_TCP_INPACKET_PCB
if ((pcb != NULL) && LWIP_HOOK_TCP_INPACKET_PCB(pcb, tcphdr, tcphdr_optlen,
tcphdr_opt1len, tcphdr_opt2, p) != ERR_OK) {
pbuf_free(p);
return;
}
#endif
if (pcb != NULL) {
/* The incoming segment belongs to a connection. */
#if TCP_INPUT_DEBUG
tcp_debug_print_state(pcb->state);
#endif /* TCP_INPUT_DEBUG */
/* Set up a tcp_seg structure. */
inseg.next = NULL;
inseg.len = p->tot_len;
inseg.p = p;
inseg.tcphdr = tcphdr;
recv_data = NULL;
recv_flags = 0;
recv_acked = 0;
if (flags & TCP_PSH) {
p->flags |= PBUF_FLAG_PUSH;
}
/* If there is data which was previously "refused" by upper layer */
if (pcb->refused_data != NULL) {
if ((tcp_process_refused_data(pcb) == ERR_ABRT) ||
((pcb->refused_data != NULL) && (tcplen > 0))) {
/* pcb has been aborted or refused data is still refused and the new
segment contains data */
if (pcb->rcv_ann_wnd == 0) {
/* this is a zero-window probe, we respond to it with current RCV.NXT
and drop the data segment */
tcp_send_empty_ack(pcb);
}
TCP_STATS_INC(tcp.drop);
MIB2_STATS_INC(mib2.tcpinerrs);
goto aborted;
}
}
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->state, pcb->errf, pcb->callback_arg, ERR_RST);
tcp_pcb_remove(&tcp_active_pcbs, pcb);
tcp_free(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 (recv_acked > 0) {
u16_t acked16;
#if LWIP_WND_SCALE
/* recv_acked is u32_t but the sent callback only takes a u16_t,
so we might have to call it multiple times. */
u32_t acked = recv_acked;
while (acked > 0) {
acked16 = (u16_t)LWIP_MIN(acked, 0xffffu);
acked -= acked16;
#else
{
acked16 = recv_acked;
#endif
TCP_EVENT_SENT(pcb, (u16_t)acked16, err);
if (err == ERR_ABRT) {
goto aborted;
}
}
recv_acked = 0;
}
if (tcp_input_delayed_close(pcb)) {
goto aborted;
}
#if TCP_QUEUE_OOSEQ && LWIP_WND_SCALE
while (recv_data != NULL) {
struct pbuf *rest = NULL;
pbuf_split_64k(recv_data, &rest);
#else /* TCP_QUEUE_OOSEQ && LWIP_WND_SCALE */
if (recv_data != NULL) {
#endif /* TCP_QUEUE_OOSEQ && LWIP_WND_SCALE */
LWIP_ASSERT("pcb->refused_data == NULL", pcb->refused_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);
#if TCP_QUEUE_OOSEQ && LWIP_WND_SCALE
if (rest != NULL) {
pbuf_free(rest);
}
#endif /* TCP_QUEUE_OOSEQ && LWIP_WND_SCALE */
tcp_abort(pcb);
goto aborted;
}
/* Notify application that data has been received. */
TCP_EVENT_RECV(pcb, recv_data, ERR_OK, err);
if (err == ERR_ABRT) {
#if TCP_QUEUE_OOSEQ && LWIP_WND_SCALE
if (rest != NULL) {
pbuf_free(rest);
}
#endif /* TCP_QUEUE_OOSEQ && LWIP_WND_SCALE */
goto aborted;
}
/* If the upper layer can't receive this data, store it */
if (err != ERR_OK) {
#if TCP_QUEUE_OOSEQ && LWIP_WND_SCALE
if (rest != NULL) {
pbuf_cat(recv_data, rest);
}
#endif /* TCP_QUEUE_OOSEQ && LWIP_WND_SCALE */
pcb->refused_data = recv_data;
LWIP_DEBUGF(TCP_INPUT_DEBUG, ("tcp_input: keep incoming packet, because pcb is \"full\"\n"));
#if TCP_QUEUE_OOSEQ && LWIP_WND_SCALE
break;
} else {
/* Upper layer received the data, go on with the rest if > 64K */
recv_data = rest;
#endif /* TCP_QUEUE_OOSEQ && LWIP_WND_SCALE */
}
}
/* If a FIN segment was received, we call the callback
function with a NULL buffer to indicate EOF. */
if (recv_flags & TF_GOT_FIN) {
if (pcb->refused_data != NULL) {
/* Delay this if we have refused data. */
pcb->refused_data->flags |= PBUF_FLAG_TCP_FIN;
} else {
/* correct rcv_wnd as the application won't call tcp_recved()
for the FIN's seqno */
if (pcb->rcv_wnd != TCP_WND_MAX(pcb)) {
pcb->rcv_wnd++;
}
TCP_EVENT_CLOSED(pcb, err);
if (err == ERR_ABRT) {
goto aborted;
}
}
}
tcp_input_pcb = NULL;
if (tcp_input_delayed_close(pcb)) {
goto aborted;
}
/* 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(NULL, 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");
return;
dropped:
TCP_STATS_INC(tcp.drop);
MIB2_STATS_INC(mib2.tcpinerrs);
pbuf_free(p);
}
/** Called from tcp_input to check for TF_CLOSED flag. This results in closing
* and deallocating a pcb at the correct place to ensure noone references it
* any more.
* @returns 1 if the pcb has been closed and deallocated, 0 otherwise
*/
static int
tcp_input_delayed_close(struct tcp_pcb *pcb)
{
LWIP_ASSERT("tcp_input_delayed_close: invalid pcb", pcb != NULL);
if (recv_flags & TF_CLOSED) {
/* The connection has been closed and we will deallocate the
PCB. */
if (!(pcb->flags & TF_RXCLOSED)) {
/* Connection closed although the application has only shut down the
tx side: call the PCB's err callback and indicate the closure to
ensure the application doesn't continue using the PCB. */
TCP_EVENT_ERR(pcb->state, pcb->errf, pcb->callback_arg, ERR_CLSD);
}
tcp_pcb_remove(&tcp_active_pcbs, pcb);
tcp_free(pcb);
return 1;
}
return 0;
}
/**
* 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
*
* @note the segment which arrived is saved in global variables, therefore only the pcb
* involved is passed as a parameter to this function
*/
static void
tcp_listen_input(struct tcp_pcb_listen *pcb)
{
struct tcp_pcb *npcb;
u32_t iss;
err_t rc;
if (flags & TCP_RST) {
/* An incoming RST should be ignored. Return. */
return;
}
LWIP_ASSERT("tcp_listen_input: invalid pcb", pcb != NULL);
/* 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((const struct tcp_pcb *)pcb, ackno, 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;
}
#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) {
err_t err;
LWIP_DEBUGF(TCP_DEBUG, ("tcp_listen_input: could not allocate PCB\n"));
TCP_STATS_INC(tcp.memerr);
TCP_EVENT_ACCEPT(pcb, NULL, pcb->callback_arg, ERR_MEM, err);
LWIP_UNUSED_ARG(err); /* err not useful here */
return;
}
#if TCP_LISTEN_BACKLOG
pcb->accepts_pending++;
tcp_set_flags(npcb, TF_BACKLOGPEND);
#endif /* TCP_LISTEN_BACKLOG */
/* Set up the new PCB. */
ip_addr_copy(npcb->local_ip, *ip_current_dest_addr());
ip_addr_copy(npcb->remote_ip, *ip_current_src_addr());
npcb->local_port = pcb->local_port;
npcb->remote_port = tcphdr->src;
npcb->state = SYN_RCVD;
npcb->rcv_nxt = seqno + 1;
npcb->rcv_ann_right_edge = npcb->rcv_nxt;
iss = tcp_next_iss(npcb);
npcb->snd_wl2 = iss;
npcb->snd_nxt = iss;
npcb->lastack = iss;
npcb->snd_lbb = iss;
npcb->snd_wl1 = seqno - 1;/* initialise to seqno-1 to force window update */
npcb->callback_arg = pcb->callback_arg;
#if LWIP_CALLBACK_API || TCP_LISTEN_BACKLOG
npcb->listener = pcb;
#endif /* LWIP_CALLBACK_API || TCP_LISTEN_BACKLOG */
/* inherit socket options */
npcb->so_options = pcb->so_options & SOF_INHERITED;
npcb->netif_idx = pcb->netif_idx;
/* Register the new PCB so that we can begin receiving segments
for it. */
TCP_REG_ACTIVE(npcb);
/* Parse any options in the SYN. */
tcp_parseopt(npcb);
npcb->snd_wnd = tcphdr->wnd;
npcb->snd_wnd_max = npcb->snd_wnd;
#if TCP_CALCULATE_EFF_SEND_MSS
npcb->mss = tcp_eff_send_mss(npcb->mss, &npcb->local_ip, &npcb->remote_ip);
#endif /* TCP_CALCULATE_EFF_SEND_MSS */
MIB2_STATS_INC(mib2.tcppassiveopens);
#if LWIP_TCP_PCB_NUM_EXT_ARGS
if (tcp_ext_arg_invoke_callbacks_passive_open(pcb, npcb) != ERR_OK) {
tcp_abandon(npcb, 0);
return;
}
#endif
/* 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;
}
tcp_output(npcb);
}
return;
}
/**
* 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 void
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;
}
LWIP_ASSERT("tcp_timewait_input: invalid pcb", pcb != NULL);
/* - 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(pcb, ackno, seqno + tcplen, ip_current_dest_addr(),
ip_current_src_addr(), tcphdr->dest, tcphdr->src);
return;
}
} 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 */
tcp_ack_now(pcb);
tcp_output(pcb);
}
return;
}
/**
* 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;
LWIP_ASSERT("tcp_process: invalid pcb", pcb != NULL);
/* Process incoming RST segments. */
if (flags & TCP_RST) {
/* First, determine if the reset is acceptable. */
if (pcb->state == SYN_SENT) {
/* "In the SYN-SENT state (a RST received in response to an initial SYN),
the RST is acceptable if the ACK field acknowledges the SYN." */
if (ackno == pcb->snd_nxt) {
acceptable = 1;
}
} else {
/* "In all states except SYN-SENT, all reset (RST) segments are validated
by checking their SEQ-fields." */
if (seqno == pcb->rcv_nxt) {
acceptable = 1;
} else if (TCP_SEQ_BETWEEN(seqno, pcb->rcv_nxt,
pcb->rcv_nxt + pcb->rcv_wnd)) {
/* If the sequence number is inside the window, we send a challenge ACK
and wait for a re-send with matching sequence number.
This follows RFC 5961 section 3.2 and addresses CVE-2004-0230
(RST spoofing attack), which is present in RFC 793 RST handling. */
tcp_ack_now(pcb);
}
}
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;
tcp_clear_flags(pcb, 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;
pcb->persist_probe = 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 %s %"U32_F"\n",
ackno, pcb->snd_nxt, pcb->unacked ? "" : " empty:",
pcb->unacked ? lwip_ntohl(pcb->unacked->tcphdr->seqno) : 0));
/* received SYN ACK with expected sequence number? */
if ((flags & TCP_ACK) && (flags & TCP_SYN)
&& (ackno == pcb->lastack + 1)) {
pcb->rcv_nxt = seqno + 1;
pcb->rcv_ann_right_edge = pcb->rcv_nxt;
pcb->lastack = ackno;
pcb->snd_wnd = tcphdr->wnd;
pcb->snd_wnd_max = pcb->snd_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->local_ip, &pcb->remote_ip);
#endif /* TCP_CALCULATE_EFF_SEND_MSS */
pcb->cwnd = LWIP_TCP_CALC_INITIAL_CWND(pcb->mss);
LWIP_DEBUGF(TCP_CWND_DEBUG, ("tcp_process (SENT): cwnd %"TCPWNDSIZE_F
" ssthresh %"TCPWNDSIZE_F"\n",
pcb->cwnd, pcb->ssthresh));
LWIP_ASSERT("pcb->snd_queuelen > 0", (pcb->snd_queuelen > 0));
--pcb->snd_queuelen;
LWIP_DEBUGF(TCP_QLEN_DEBUG, ("tcp_process: SYN-SENT --queuelen %"TCPWNDSIZE_F"\n", (tcpwnd_size_t)pcb->snd_queuelen));
rseg = pcb->unacked;
if (rseg == NULL) {
/* might happen if tcp_output fails in tcp_rexmit_rto()
in which case the segment is on the unsent list */
rseg = pcb->unsent;
LWIP_ASSERT("no segment to free", rseg != NULL);
pcb->unsent = rseg->next;
} else {
pcb->unacked = rseg->next;
}
tcp_seg_free(rseg);
/* 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;
}
/* Call the user specified function to call when successfully
* 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(pcb, ackno, seqno + tcplen, ip_current_dest_addr(),
ip_current_src_addr(), tcphdr->dest, tcphdr->src);
/* Resend SYN immediately (don't wait for rto timeout) to establish
connection faster, but do not send more SYNs than we otherwise would
have, or we might get caught in a loop on loopback interfaces. */
if (pcb->nrtx < TCP_SYNMAXRTX) {
pcb->rtime = 0;
tcp_rexmit_rto(pcb);
}
}
break;
case SYN_RCVD:
if (flags & TCP_ACK) {
/* expected ACK number? */
if (TCP_SEQ_BETWEEN(ackno, pcb->lastack + 1, pcb->snd_nxt)) {
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 || TCP_LISTEN_BACKLOG
if (pcb->listener == NULL) {
/* listen pcb might be closed by now */
err = ERR_VAL;
} else
#endif /* LWIP_CALLBACK_API || TCP_LISTEN_BACKLOG */
{
#if LWIP_CALLBACK_API
LWIP_ASSERT("pcb->listener->accept != NULL", pcb->listener->accept != NULL);
#endif
tcp_backlog_accepted(pcb);
/* Call the accept function. */
TCP_EVENT_ACCEPT(pcb->listener, pcb, pcb->callback_arg, 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;
}
/* 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 (recv_acked != 0) {
recv_acked--;
}
pcb->cwnd = LWIP_TCP_CALC_INITIAL_CWND(pcb->mss);
LWIP_DEBUGF(TCP_CWND_DEBUG, ("tcp_process (SYN_RCVD): cwnd %"TCPWNDSIZE_F
" ssthresh %"TCPWNDSIZE_F"\n",
pcb->cwnd, pcb->ssthresh));
if (recv_flags & TF_GOT_FIN) {
tcp_ack_now(pcb);
pcb->state = CLOSE_WAIT;
}
} else {
/* incorrect ACK number, send RST */
tcp_rst(pcb, 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) &&
pcb->unsent == NULL) {
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_ACTIVE(pcb);
pcb->state = TIME_WAIT;
TCP_REG(&tcp_tw_pcbs, pcb);