summaryrefslogtreecommitdiff
path: root/net/netfilter/nf_conntrack_proto_tcp.c
blob: ba94004fe323182b6a527507548a1e54e1099321 (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
/* (C) 1999-2001 Paul `Rusty' Russell
 * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#include <linux/types.h>
#include <linux/timer.h>
#include <linux/module.h>
#include <linux/in.h>
#include <linux/tcp.h>
#include <linux/spinlock.h>
#include <linux/skbuff.h>
#include <linux/ipv6.h>
#include <net/ip6_checksum.h>

#include <net/tcp.h>

#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_ipv6.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
#include <net/netfilter/nf_conntrack_ecache.h>
#include <net/netfilter/nf_log.h>

/* Protects ct->proto.tcp */
static DEFINE_RWLOCK(tcp_lock);

/* "Be conservative in what you do,
    be liberal in what you accept from others."
    If it's non-zero, we mark only out of window RST segments as INVALID. */
static int nf_ct_tcp_be_liberal __read_mostly = 0;

/* If it is set to zero, we disable picking up already established
   connections. */
static int nf_ct_tcp_loose __read_mostly = 1;

/* Max number of the retransmitted packets without receiving an (acceptable)
   ACK from the destination. If this number is reached, a shorter timer
   will be started. */
static int nf_ct_tcp_max_retrans __read_mostly = 3;

  /* FIXME: Examine ipfilter's timeouts and conntrack transitions more
     closely.  They're more complex. --RR */

static const char *const tcp_conntrack_names[] = {
	"NONE",
	"SYN_SENT",
	"SYN_RECV",
	"ESTABLISHED",
	"FIN_WAIT",
	"CLOSE_WAIT",
	"LAST_ACK",
	"TIME_WAIT",
	"CLOSE",
	"LISTEN"
};

#define SECS * HZ
#define MINS * 60 SECS
#define HOURS * 60 MINS
#define DAYS * 24 HOURS

/* RFC1122 says the R2 limit should be at least 100 seconds.
   Linux uses 15 packets as limit, which corresponds
   to ~13-30min depending on RTO. */
static unsigned int nf_ct_tcp_timeout_max_retrans __read_mostly =   5 MINS;

static unsigned int tcp_timeouts[TCP_CONNTRACK_MAX] __read_mostly = {
	[TCP_CONNTRACK_SYN_SENT]	= 2 MINS,
	[TCP_CONNTRACK_SYN_RECV]	= 60 SECS,
	[TCP_CONNTRACK_ESTABLISHED]	= 5 DAYS,
	[TCP_CONNTRACK_FIN_WAIT]	= 2 MINS,
	[TCP_CONNTRACK_CLOSE_WAIT]	= 60 SECS,
	[TCP_CONNTRACK_LAST_ACK]	= 30 SECS,
	[TCP_CONNTRACK_TIME_WAIT]	= 2 MINS,
	[TCP_CONNTRACK_CLOSE]		= 10 SECS,
};

#define sNO TCP_CONNTRACK_NONE
#define sSS TCP_CONNTRACK_SYN_SENT
#define sSR TCP_CONNTRACK_SYN_RECV
#define sES TCP_CONNTRACK_ESTABLISHED
#define sFW TCP_CONNTRACK_FIN_WAIT
#define sCW TCP_CONNTRACK_CLOSE_WAIT
#define sLA TCP_CONNTRACK_LAST_ACK
#define sTW TCP_CONNTRACK_TIME_WAIT
#define sCL TCP_CONNTRACK_CLOSE
#define sLI TCP_CONNTRACK_LISTEN
#define sIV TCP_CONNTRACK_MAX
#define sIG TCP_CONNTRACK_IGNORE

/* What TCP flags are set from RST/SYN/FIN/ACK. */
enum tcp_bit_set {
	TCP_SYN_SET,
	TCP_SYNACK_SET,
	TCP_FIN_SET,
	TCP_ACK_SET,
	TCP_RST_SET,
	TCP_NONE_SET,
};

/*
 * The TCP state transition table needs a few words...
 *
 * We are the man in the middle. All the packets go through us
 * but might get lost in transit to the destination.
 * It is assumed that the destinations can't receive segments
 * we haven't seen.
 *
 * The checked segment is in window, but our windows are *not*
 * equivalent with the ones of the sender/receiver. We always
 * try to guess the state of the current sender.
 *
 * The meaning of the states are:
 *
 * NONE:	initial state
 * SYN_SENT:	SYN-only packet seen
 * SYN_RECV:	SYN-ACK packet seen
 * ESTABLISHED:	ACK packet seen
 * FIN_WAIT:	FIN packet seen
 * CLOSE_WAIT:	ACK seen (after FIN)
 * LAST_ACK:	FIN seen (after FIN)
 * TIME_WAIT:	last ACK seen
 * CLOSE:	closed connection (RST)
 *
 * LISTEN state is not used.
 *
 * Packets marked as IGNORED (sIG):
 *	if they may be either invalid or valid
 *	and the receiver may send back a connection
 *	closing RST or a SYN/ACK.
 *
 * Packets marked as INVALID (sIV):
 *	if they are invalid
 *	or we do not support the request (simultaneous open)
 */
static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = {
	{
/* ORIGINAL */
/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
/*syn*/	   { sSS, sSS, sIG, sIG, sIG, sIG, sIG, sSS, sSS, sIV },
/*
 *	sNO -> sSS	Initialize a new connection
 *	sSS -> sSS	Retransmitted SYN
 *	sSR -> sIG	Late retransmitted SYN?
 *	sES -> sIG	Error: SYNs in window outside the SYN_SENT state
 *			are errors. Receiver will reply with RST
 *			and close the connection.
 *			Or we are not in sync and hold a dead connection.
 *	sFW -> sIG
 *	sCW -> sIG
 *	sLA -> sIG
 *	sTW -> sSS	Reopened connection (RFC 1122).
 *	sCL -> sSS
 */
/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
/*synack*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV },
/*
 * A SYN/ACK from the client is always invalid:
 *	- either it tries to set up a simultaneous open, which is
 *	  not supported;
 *	- or the firewall has just been inserted between the two hosts
 *	  during the session set-up. The SYN will be retransmitted
 *	  by the true client (or it'll time out).
 */
/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
/*fin*/    { sIV, sIV, sFW, sFW, sLA, sLA, sLA, sTW, sCL, sIV },
/*
 *	sNO -> sIV	Too late and no reason to do anything...
 *	sSS -> sIV	Client migth not send FIN in this state:
 *			we enforce waiting for a SYN/ACK reply first.
 *	sSR -> sFW	Close started.
 *	sES -> sFW
 *	sFW -> sLA	FIN seen in both directions, waiting for
 *			the last ACK.
 *			Migth be a retransmitted FIN as well...
 *	sCW -> sLA
 *	sLA -> sLA	Retransmitted FIN. Remain in the same state.
 *	sTW -> sTW
 *	sCL -> sCL
 */
/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
/*ack*/	   { sES, sIV, sES, sES, sCW, sCW, sTW, sTW, sCL, sIV },
/*
 *	sNO -> sES	Assumed.
 *	sSS -> sIV	ACK is invalid: we haven't seen a SYN/ACK yet.
 *	sSR -> sES	Established state is reached.
 *	sES -> sES	:-)
 *	sFW -> sCW	Normal close request answered by ACK.
 *	sCW -> sCW
 *	sLA -> sTW	Last ACK detected.
 *	sTW -> sTW	Retransmitted last ACK. Remain in the same state.
 *	sCL -> sCL
 */
/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
/*rst*/    { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV },
/*none*/   { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV }
	},
	{
/* REPLY */
/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
/*syn*/	   { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV },
/*
 *	sNO -> sIV	Never reached.
 *	sSS -> sIV	Simultaneous open, not supported
 *	sSR -> sIV	Simultaneous open, not supported.
 *	sES -> sIV	Server may not initiate a connection.
 *	sFW -> sIV
 *	sCW -> sIV
 *	sLA -> sIV
 *	sTW -> sIV	Reopened connection, but server may not do it.
 *	sCL -> sIV
 */
/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
/*synack*/ { sIV, sSR, sSR, sIG, sIG, sIG, sIG, sIG, sIG, sIV },
/*
 *	sSS -> sSR	Standard open.
 *	sSR -> sSR	Retransmitted SYN/ACK.
 *	sES -> sIG	Late retransmitted SYN/ACK?
 *	sFW -> sIG	Might be SYN/ACK answering ignored SYN
 *	sCW -> sIG
 *	sLA -> sIG
 *	sTW -> sIG
 *	sCL -> sIG
 */
/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
/*fin*/    { sIV, sIV, sFW, sFW, sLA, sLA, sLA, sTW, sCL, sIV },
/*
 *	sSS -> sIV	Server might not send FIN in this state.
 *	sSR -> sFW	Close started.
 *	sES -> sFW
 *	sFW -> sLA	FIN seen in both directions.
 *	sCW -> sLA
 *	sLA -> sLA	Retransmitted FIN.
 *	sTW -> sTW
 *	sCL -> sCL
 */
/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
/*ack*/	   { sIV, sIG, sSR, sES, sCW, sCW, sTW, sTW, sCL, sIV },
/*
 *	sSS -> sIG	Might be a half-open connection.
 *	sSR -> sSR	Might answer late resent SYN.
 *	sES -> sES	:-)
 *	sFW -> sCW	Normal close request answered by ACK.
 *	sCW -> sCW
 *	sLA -> sTW	Last ACK detected.
 *	sTW -> sTW	Retransmitted last ACK.
 *	sCL -> sCL
 */
/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
/*rst*/    { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV },
/*none*/   { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV }
	}
};

static bool tcp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
			     struct nf_conntrack_tuple *tuple)
{
	const struct tcphdr *hp;
	struct tcphdr _hdr;

	/* Actually only need first 8 bytes. */
	hp = skb_header_pointer(skb, dataoff, 8, &_hdr);
	if (hp == NULL)
		return false;

	tuple->src.u.tcp.port = hp->source;
	tuple->dst.u.tcp.port = hp->dest;

	return true;
}

static bool tcp_invert_tuple(struct nf_conntrack_tuple *tuple,
			     const struct nf_conntrack_tuple *orig)
{
	tuple->src.u.tcp.port = orig->dst.u.tcp.port;
	tuple->dst.u.tcp.port = orig->src.u.tcp.port;
	return true;
}

/* Print out the per-protocol part of the tuple. */
static int tcp_print_tuple(struct seq_file *s,
			   const struct nf_conntrack_tuple *tuple)
{
	return seq_printf(s, "sport=%hu dport=%hu ",
			  ntohs(tuple->src.u.tcp.port),
			  ntohs(tuple->dst.u.tcp.port));
}

/* Print out the private part of the conntrack. */
static int tcp_print_conntrack(struct seq_file *s, const struct nf_conn *ct)
{
	enum tcp_conntrack state;

	read_lock_bh(&tcp_lock);
	state = ct->proto.tcp.state;
	read_unlock_bh(&tcp_lock);

	return seq_printf(s, "%s ", tcp_conntrack_names[state]);
}

static unsigned int get_conntrack_index(const struct tcphdr *tcph)
{
	if (tcph->rst) return TCP_RST_SET;
	else if (tcph->syn) return (tcph->ack ? TCP_SYNACK_SET : TCP_SYN_SET);
	else if (tcph->fin) return TCP_FIN_SET;
	else if (tcph->ack) return TCP_ACK_SET;
	else return TCP_NONE_SET;
}

/* TCP connection tracking based on 'Real Stateful TCP Packet Filtering
   in IP Filter' by Guido van Rooij.

   http://www.nluug.nl/events/sane2000/papers.html
   http://www.iae.nl/users/guido/papers/tcp_filtering.ps.gz

   The boundaries and the conditions are changed according to RFC793:
   the packet must intersect the window (i.e. segments may be
   after the right or before the left edge) and thus receivers may ACK
   segments after the right edge of the window.

	td_maxend = max(sack + max(win,1)) seen in reply packets
	td_maxwin = max(max(win, 1)) + (sack - ack) seen in sent packets
	td_maxwin += seq + len - sender.td_maxend
			if seq + len > sender.td_maxend
	td_end    = max(seq + len) seen in sent packets

   I.   Upper bound for valid data:	seq <= sender.td_maxend
   II.  Lower bound for valid data:	seq + len >= sender.td_end - receiver.td_maxwin
   III.	Upper bound for valid ack:      sack <= receiver.td_end
   IV.	Lower bound for valid ack:	ack >= receiver.td_end - MAXACKWINDOW

   where sack is the highest right edge of sack block found in the packet.

   The upper bound limit for a valid ack is not ignored -
   we doesn't have to deal with fragments.
*/

static inline __u32 segment_seq_plus_len(__u32 seq,
					 size_t len,
					 unsigned int dataoff,
					 const struct tcphdr *tcph)
{
	/* XXX Should I use payload length field in IP/IPv6 header ?
	 * - YK */
	return (seq + len - dataoff - tcph->doff*4
		+ (tcph->syn ? 1 : 0) + (tcph->fin ? 1 : 0));
}

/* Fixme: what about big packets? */
#define MAXACKWINCONST			66000
#define MAXACKWINDOW(sender)						\
	((sender)->td_maxwin > MAXACKWINCONST ? (sender)->td_maxwin	\
					      : MAXACKWINCONST)

/*
 * Simplified tcp_parse_options routine from tcp_input.c
 */
static void tcp_options(const struct sk_buff *skb,
			unsigned int dataoff,
			const struct tcphdr *tcph,
			struct ip_ct_tcp_state *state)
{
	unsigned char buff[(15 * 4) - sizeof(struct tcphdr)];
	const unsigned char *ptr;
	int length = (tcph->doff*4) - sizeof(struct tcphdr);

	if (!length)
		return;

	ptr = skb_header_pointer(skb, dataoff + sizeof(struct tcphdr),
				 length, buff);
	BUG_ON(ptr == NULL);

	state->td_scale =
	state->flags = 0;

	while (length > 0) {
		int opcode=*ptr++;
		int opsize;

		switch (opcode) {
		case TCPOPT_EOL:
			return;
		case TCPOPT_NOP:	/* Ref: RFC 793 section 3.1 */
			length--;
			continue;
		default:
			opsize=*ptr++;
			if (opsize < 2) /* "silly options" */
				return;
			if (opsize > length)
				break;	/* don't parse partial options */

			if (opcode == TCPOPT_SACK_PERM
			    && opsize == TCPOLEN_SACK_PERM)
				state->flags |= IP_CT_TCP_FLAG_SACK_PERM;
			else if (opcode == TCPOPT_WINDOW
				 && opsize == TCPOLEN_WINDOW) {
				state->td_scale = *(u_int8_t *)ptr;

				if (state->td_scale > 14) {
					/* See RFC1323 */
					state->td_scale = 14;
				}
				state->flags |=
					IP_CT_TCP_FLAG_WINDOW_SCALE;
			}
			ptr += opsize - 2;
			length -= opsize;
		}
	}
}

static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff,
                     const struct tcphdr *tcph, __u32 *sack)
{
	unsigned char buff[(15 * 4) - sizeof(struct tcphdr)];
	const unsigned char *ptr;
	int length = (tcph->doff*4) - sizeof(struct tcphdr);
	__u32 tmp;

	if (!length)
		return;

	ptr = skb_header_pointer(skb, dataoff + sizeof(struct tcphdr),
				 length, buff);
	BUG_ON(ptr == NULL);

	/* Fast path for timestamp-only option */
	if (length == TCPOLEN_TSTAMP_ALIGNED*4
	    && *(__be32 *)ptr == htonl((TCPOPT_NOP << 24)
				       | (TCPOPT_NOP << 16)
				       | (TCPOPT_TIMESTAMP << 8)
				       | TCPOLEN_TIMESTAMP))
		return;

	while (length > 0) {
		int opcode = *ptr++;
		int opsize, i;

		switch (opcode) {
		case TCPOPT_EOL:
			return;
		case TCPOPT_NOP:	/* Ref: RFC 793 section 3.1 */
			length--;
			continue;
		default:
			opsize = *ptr++;
			if (opsize < 2) /* "silly options" */
				return;
			if (opsize > length)
				break;	/* don't parse partial options */

			if (opcode == TCPOPT_SACK
			    && opsize >= (TCPOLEN_SACK_BASE
					  + TCPOLEN_SACK_PERBLOCK)
			    && !((opsize - TCPOLEN_SACK_BASE)
				 % TCPOLEN_SACK_PERBLOCK)) {
				for (i = 0;
				     i < (opsize - TCPOLEN_SACK_BASE);
				     i += TCPOLEN_SACK_PERBLOCK) {
					tmp = ntohl(*((__be32 *)(ptr+i)+1));

					if (after(tmp, *sack))
						*sack = tmp;
				}
				return;
			}
			ptr += opsize - 2;
			length -= opsize;
		}
	}
}

static bool tcp_in_window(const struct nf_conn *ct,
			  struct ip_ct_tcp *state,
			  enum ip_conntrack_dir dir,
			  unsigned int index,
			  const struct sk_buff *skb,
			  unsigned int dataoff,
			  const struct tcphdr *tcph,
			  int pf)
{
	struct ip_ct_tcp_state *sender = &state->seen[dir];
	struct ip_ct_tcp_state *receiver = &state->seen[!dir];
	const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple;
	__u32 seq, ack, sack, end, win, swin;
	bool res;

	/*
	 * Get the required data from the packet.
	 */
	seq = ntohl(tcph->seq);
	ack = sack = ntohl(tcph->ack_seq);
	win = ntohs(tcph->window);
	end = segment_seq_plus_len(seq, skb->len, dataoff, tcph);

	if (receiver->flags & IP_CT_TCP_FLAG_SACK_PERM)
		tcp_sack(skb, dataoff, tcph, &sack);

	pr_debug("tcp_in_window: START\n");
	pr_debug("tcp_in_window: ");
	nf_ct_dump_tuple(tuple);
	pr_debug("seq=%u ack=%u sack=%u win=%u end=%u\n",
		 seq, ack, sack, win, end);
	pr_debug("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i "
		 "receiver end=%u maxend=%u maxwin=%u scale=%i\n",
		 sender->td_end, sender->td_maxend, sender->td_maxwin,
		 sender->td_scale,
		 receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
		 receiver->td_scale);

	if (sender->td_end == 0) {
		/*
		 * Initialize sender data.
		 */
		if (tcph->syn && tcph->ack) {
			/*
			 * Outgoing SYN-ACK in reply to a SYN.
			 */
			sender->td_end =
			sender->td_maxend = end;
			sender->td_maxwin = (win == 0 ? 1 : win);

			tcp_options(skb, dataoff, tcph, sender);
			/*
			 * RFC 1323:
			 * Both sides must send the Window Scale option
			 * to enable window scaling in either direction.
			 */
			if (!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE
			      && receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE))
				sender->td_scale =
				receiver->td_scale = 0;
		} else {
			/*
			 * We are in the middle of a connection,
			 * its history is lost for us.
			 * Let's try to use the data from the packet.
			 */
			sender->td_end = end;
			sender->td_maxwin = (win == 0 ? 1 : win);
			sender->td_maxend = end + sender->td_maxwin;
		}
	} else if (((state->state == TCP_CONNTRACK_SYN_SENT
		     && dir == IP_CT_DIR_ORIGINAL)
		   || (state->state == TCP_CONNTRACK_SYN_RECV
		     && dir == IP_CT_DIR_REPLY))
		   && after(end, sender->td_end)) {
		/*
		 * RFC 793: "if a TCP is reinitialized ... then it need
		 * not wait at all; it must only be sure to use sequence
		 * numbers larger than those recently used."
		 */
		sender->td_end =
		sender->td_maxend = end;
		sender->td_maxwin = (win == 0 ? 1 : win);

		tcp_options(skb, dataoff, tcph, sender);
	}

	if (!(tcph->ack)) {
		/*
		 * If there is no ACK, just pretend it was set and OK.
		 */
		ack = sack = receiver->td_end;
	} else if (((tcp_flag_word(tcph) & (TCP_FLAG_ACK|TCP_FLAG_RST)) ==
		    (TCP_FLAG_ACK|TCP_FLAG_RST))
		   && (ack == 0)) {
		/*
		 * Broken TCP stacks, that set ACK in RST packets as well
		 * with zero ack value.
		 */
		ack = sack = receiver->td_end;
	}

	if (seq == end
	    && (!tcph->rst
		|| (seq == 0 && state->state == TCP_CONNTRACK_SYN_SENT)))
		/*
		 * Packets contains no data: we assume it is valid
		 * and check the ack value only.
		 * However RST segments are always validated by their
		 * SEQ number, except when seq == 0 (reset sent answering
		 * SYN.
		 */
		seq = end = sender->td_end;

	pr_debug("tcp_in_window: ");
	nf_ct_dump_tuple(tuple);
	pr_debug("seq=%u ack=%u sack =%u win=%u end=%u\n",
		 seq, ack, sack, win, end);
	pr_debug("tcp_in_window: sender end=%u maxend=%u maxwin=%u scale=%i "
		 "receiver end=%u maxend=%u maxwin=%u scale=%i\n",
		 sender->td_end, sender->td_maxend, sender->td_maxwin,
		 sender->td_scale,
		 receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
		 receiver->td_scale);

	pr_debug("tcp_in_window: I=%i II=%i III=%i IV=%i\n",
		 before(seq, sender->td_maxend + 1),
		 after(end, sender->td_end - receiver->td_maxwin - 1),
		 before(sack, receiver->td_end + 1),
		 after(ack, receiver->td_end - MAXACKWINDOW(sender)));

	if (before(seq, sender->td_maxend + 1) &&
	    after(end, sender->td_end - receiver->td_maxwin - 1) &&
	    before(sack, receiver->td_end + 1) &&
	    after(ack, receiver->td_end - MAXACKWINDOW(sender))) {
		/*
		 * Take into account window scaling (RFC 1323).
		 */
		if (!tcph->syn)
			win <<= sender->td_scale;

		/*
		 * Update sender data.
		 */
		swin = win + (sack - ack);
		if (sender->td_maxwin < swin)
			sender->td_maxwin = swin;
		if (after(end, sender->td_end))
			sender->td_end = end;
		/*
		 * Update receiver data.
		 */
		if (after(end, sender->td_maxend))
			receiver->td_maxwin += end - sender->td_maxend;
		if (after(sack + win, receiver->td_maxend - 1)) {
			receiver->td_maxend = sack + win;
			if (win == 0)
				receiver->td_maxend++;
		}

		/*
		 * Check retransmissions.
		 */
		if (index == TCP_ACK_SET) {
			if (state->last_dir == dir
			    && state->last_seq == seq
			    && state->last_ack == ack
			    && state->last_end == end
			    && state->last_win == win)
				state->retrans++;
			else {
				state->last_dir = dir;
				state->last_seq = seq;
				state->last_ack = ack;
				state->last_end = end;
				state->last_win = win;
				state->retrans = 0;
			}
		}
		res = true;
	} else {
		res = false;
		if (sender->flags & IP_CT_TCP_FLAG_BE_LIBERAL ||
		    nf_ct_tcp_be_liberal)
			res = true;
		if (!res && LOG_INVALID(IPPROTO_TCP))
			nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
			"nf_ct_tcp: %s ",
			before(seq, sender->td_maxend + 1) ?
			after(end, sender->td_end - receiver->td_maxwin - 1) ?
			before(sack, receiver->td_end + 1) ?
			after(ack, receiver->td_end - MAXACKWINDOW(sender)) ? "BUG"
			: "ACK is under the lower bound (possible overly delayed ACK)"
			: "ACK is over the upper bound (ACKed data not seen yet)"
			: "SEQ is under the lower bound (already ACKed data retransmitted)"
			: "SEQ is over the upper bound (over the window of the receiver)");
	}

	pr_debug("tcp_in_window: res=%u sender end=%u maxend=%u maxwin=%u "
		 "receiver end=%u maxend=%u maxwin=%u\n",
		 res, sender->td_end, sender->td_maxend, sender->td_maxwin,
		 receiver->td_end, receiver->td_maxend, receiver->td_maxwin);

	return res;
}

#ifdef CONFIG_NF_NAT_NEEDED
/* Update sender->td_end after NAT successfully mangled the packet */
/* Caller must linearize skb at tcp header. */
void nf_conntrack_tcp_update(const struct sk_buff *skb,
			     unsigned int dataoff,
			     struct nf_conn *ct,
			     int dir)
{
	const struct tcphdr *tcph = (const void *)skb->data + dataoff;
	const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[dir];
	const struct ip_ct_tcp_state *receiver = &ct->proto.tcp.seen[!dir];
	__u32 end;

	end = segment_seq_plus_len(ntohl(tcph->seq), skb->len, dataoff, tcph);

	write_lock_bh(&tcp_lock);
	/*
	 * We have to worry for the ack in the reply packet only...
	 */
	if (after(end, ct->proto.tcp.seen[dir].td_end))
		ct->proto.tcp.seen[dir].td_end = end;
	ct->proto.tcp.last_end = end;
	write_unlock_bh(&tcp_lock);
	pr_debug("tcp_update: sender end=%u maxend=%u maxwin=%u scale=%i "
		 "receiver end=%u maxend=%u maxwin=%u scale=%i\n",
		 sender->td_end, sender->td_maxend, sender->td_maxwin,
		 sender->td_scale,
		 receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
		 receiver->td_scale);
}
EXPORT_SYMBOL_GPL(nf_conntrack_tcp_update);
#endif

#define	TH_FIN	0x01
#define	TH_SYN	0x02
#define	TH_RST	0x04
#define	TH_PUSH	0x08
#define	TH_ACK	0x10
#define	TH_URG	0x20
#define	TH_ECE	0x40
#define	TH_CWR	0x80

/* table of valid flag combinations - PUSH, ECE and CWR are always valid */
static const u8 tcp_valid_flags[(TH_FIN|TH_SYN|TH_RST|TH_ACK|TH_URG) + 1] =
{
	[TH_SYN]			= 1,
	[TH_SYN|TH_URG]			= 1,
	[TH_SYN|TH_ACK]			= 1,
	[TH_RST]			= 1,
	[TH_RST|TH_ACK]			= 1,
	[TH_FIN|TH_ACK]			= 1,
	[TH_FIN|TH_ACK|TH_URG]		= 1,
	[TH_ACK]			= 1,
	[TH_ACK|TH_URG]			= 1,
};

/* Protect conntrack agaist broken packets. Code taken from ipt_unclean.c.  */
static int tcp_error(struct sk_buff *skb,
		     unsigned int dataoff,
		     enum ip_conntrack_info *ctinfo,
		     int pf,
		     unsigned int hooknum)
{
	const struct tcphdr *th;
	struct tcphdr _tcph;
	unsigned int tcplen = skb->len - dataoff;
	u_int8_t tcpflags;

	/* Smaller that minimal TCP header? */
	th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph);
	if (th == NULL) {
		if (LOG_INVALID(IPPROTO_TCP))
			nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
				"nf_ct_tcp: short packet ");
		return -NF_ACCEPT;
	}

	/* Not whole TCP header or malformed packet */
	if (th->doff*4 < sizeof(struct tcphdr) || tcplen < th->doff*4) {
		if (LOG_INVALID(IPPROTO_TCP))
			nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
				"nf_ct_tcp: truncated/malformed packet ");
		return -NF_ACCEPT;
	}

	/* Checksum invalid? Ignore.
	 * We skip checking packets on the outgoing path
	 * because the checksum is assumed to be correct.
	 */
	/* FIXME: Source route IP option packets --RR */
	if (nf_conntrack_checksum && hooknum == NF_INET_PRE_ROUTING &&
	    nf_checksum(skb, hooknum, dataoff, IPPROTO_TCP, pf)) {
		if (LOG_INVALID(IPPROTO_TCP))
			nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
				  "nf_ct_tcp: bad TCP checksum ");
		return -NF_ACCEPT;
	}

	/* Check TCP flags. */
	tcpflags = (((u_int8_t *)th)[13] & ~(TH_ECE|TH_CWR|TH_PUSH));
	if (!tcp_valid_flags[tcpflags]) {
		if (LOG_INVALID(IPPROTO_TCP))
			nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
				  "nf_ct_tcp: invalid TCP flag combination ");
		return -NF_ACCEPT;
	}

	return NF_ACCEPT;
}

/* Returns verdict for packet, or -1 for invalid. */
static int tcp_packet(struct nf_conn *ct,
		      const struct sk_buff *skb,
		      unsigned int dataoff,
		      enum ip_conntrack_info ctinfo,
		      int pf,
		      unsigned int hooknum)
{
	struct nf_conntrack_tuple *tuple;
	enum tcp_conntrack new_state, old_state;
	enum ip_conntrack_dir dir;
	const struct tcphdr *th;
	struct tcphdr _tcph;
	unsigned long timeout;
	unsigned int index;

	th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph);
	BUG_ON(th == NULL);

	write_lock_bh(&tcp_lock);
	old_state = ct->proto.tcp.state;
	dir = CTINFO2DIR(ctinfo);
	index = get_conntrack_index(th);
	new_state = tcp_conntracks[dir][index][old_state];
	tuple = &ct->tuplehash[dir].tuple;

	switch (new_state) {
	case TCP_CONNTRACK_SYN_SENT:
		if (old_state < TCP_CONNTRACK_TIME_WAIT)
			break;
		/* RFC 1122: "When a connection is closed actively,
		 * it MUST linger in TIME-WAIT state for a time 2xMSL
		 * (Maximum Segment Lifetime). However, it MAY accept
		 * a new SYN from the remote TCP to reopen the connection
		 * directly from TIME-WAIT state, if..."
		 * We ignore the conditions because we are in the
		 * TIME-WAIT state anyway.
		 *
		 * Handle aborted connections: we and the server
		 * think there is an existing connection but the client
		 * aborts it and starts a new one.
		 */
		if (((ct->proto.tcp.seen[dir].flags
		      | ct->proto.tcp.seen[!dir].flags)
		     & IP_CT_TCP_FLAG_CLOSE_INIT)
		    || (ct->proto.tcp.last_dir == dir
		        && ct->proto.tcp.last_index == TCP_RST_SET)) {
			/* Attempt to reopen a closed/aborted connection.
			 * Delete this connection and look up again. */
			write_unlock_bh(&tcp_lock);
			if (del_timer(&ct->timeout))
				ct->timeout.function((unsigned long)ct);
			return -NF_REPEAT;
		}
		/* Fall through */
	case TCP_CONNTRACK_IGNORE:
		/* Ignored packets:
		 *
		 * Our connection entry may be out of sync, so ignore
		 * packets which may signal the real connection between
		 * the client and the server.
		 *
		 * a) SYN in ORIGINAL
		 * b) SYN/ACK in REPLY
		 * c) ACK in reply direction after initial SYN in original.
		 *
		 * If the ignored packet is invalid, the receiver will send
		 * a RST we'll catch below.
		 */
		if (index == TCP_SYNACK_SET
		    && ct->proto.tcp.last_index == TCP_SYN_SET
		    && ct->proto.tcp.last_dir != dir
		    && ntohl(th->ack_seq) == ct->proto.tcp.last_end) {
			/* b) This SYN/ACK acknowledges a SYN that we earlier
			 * ignored as invalid. This means that the client and
			 * the server are both in sync, while the firewall is
			 * not. We kill this session and block the SYN/ACK so
			 * that the client cannot but retransmit its SYN and
			 * thus initiate a clean new session.
			 */
			write_unlock_bh(&tcp_lock);
			if (LOG_INVALID(IPPROTO_TCP))
				nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
					  "nf_ct_tcp: killing out of sync session ");
			if (del_timer(&ct->timeout))
				ct->timeout.function((unsigned long)ct);
			return -NF_DROP;
		}
		ct->proto.tcp.last_index = index;
		ct->proto.tcp.last_dir = dir;
		ct->proto.tcp.last_seq = ntohl(th->seq);
		ct->proto.tcp.last_end =
		    segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th);

		write_unlock_bh(&tcp_lock);
		if (LOG_INVALID(IPPROTO_TCP))
			nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
				  "nf_ct_tcp: invalid packet ignored ");
		return NF_ACCEPT;
	case TCP_CONNTRACK_MAX:
		/* Invalid packet */
		pr_debug("nf_ct_tcp: Invalid dir=%i index=%u ostate=%u\n",
			 dir, get_conntrack_index(th), old_state);
		write_unlock_bh(&tcp_lock);
		if (LOG_INVALID(IPPROTO_TCP))
			nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
				  "nf_ct_tcp: invalid state ");
		return -NF_ACCEPT;
	case TCP_CONNTRACK_CLOSE:
		if (index == TCP_RST_SET
		    && ((test_bit(IPS_SEEN_REPLY_BIT, &ct->status)
			 && ct->proto.tcp.last_index == TCP_SYN_SET)
			|| (!test_bit(IPS_ASSURED_BIT, &ct->status)
			    && ct->proto.tcp.last_index == TCP_ACK_SET))
		    && ntohl(th->ack_seq) == ct->proto.tcp.last_end) {
			/* RST sent to invalid SYN or ACK we had let through
			 * at a) and c) above:
			 *
			 * a) SYN was in window then
			 * c) we hold a half-open connection.
			 *
			 * Delete our connection entry.
			 * We skip window checking, because packet might ACK
			 * segments we ignored. */
			goto in_window;
		}
		/* Just fall through */
	default:
		/* Keep compilers happy. */
		break;
	}

	if (!tcp_in_window(ct, &ct->proto.tcp, dir, index,
			   skb, dataoff, th, pf)) {
		write_unlock_bh(&tcp_lock);
		return -NF_ACCEPT;
	}
     in_window:
	/* From now on we have got in-window packets */
	ct->proto.tcp.last_index = index;
	ct->proto.tcp.last_dir = dir;

	pr_debug("tcp_conntracks: ");
	nf_ct_dump_tuple(tuple);
	pr_debug("syn=%i ack=%i fin=%i rst=%i old=%i new=%i\n",
		 (th->syn ? 1 : 0), (th->ack ? 1 : 0),
		 (th->fin ? 1 : 0), (th->rst ? 1 : 0),
		 old_state, new_state);

	ct->proto.tcp.state = new_state;
	if (old_state != new_state
	    && new_state == TCP_CONNTRACK_FIN_WAIT)
		ct->proto.tcp.seen[dir].flags |= IP_CT_TCP_FLAG_CLOSE_INIT;
	timeout = ct->proto.tcp.retrans >= nf_ct_tcp_max_retrans
		  && tcp_timeouts[new_state] > nf_ct_tcp_timeout_max_retrans
		  ? nf_ct_tcp_timeout_max_retrans : tcp_timeouts[new_state];
	write_unlock_bh(&tcp_lock);

	nf_conntrack_event_cache(IPCT_PROTOINFO_VOLATILE, skb);
	if (new_state != old_state)
		nf_conntrack_event_cache(IPCT_PROTOINFO, skb);

	if (!test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
		/* If only reply is a RST, we can consider ourselves not to
		   have an established connection: this is a fairly common
		   problem case, so we can delete the conntrack
		   immediately.  --RR */
		if (th->rst) {
			if (del_timer(&ct->timeout))
				ct->timeout.function((unsigned long)ct);
			return NF_ACCEPT;
		}
	} else if (!test_bit(IPS_ASSURED_BIT, &ct->status)
		   && (old_state == TCP_CONNTRACK_SYN_RECV
		       || old_state == TCP_CONNTRACK_ESTABLISHED)
		   && new_state == TCP_CONNTRACK_ESTABLISHED) {
		/* Set ASSURED if we see see valid ack in ESTABLISHED
		   after SYN_RECV or a valid answer for a picked up
		   connection. */
		set_bit(IPS_ASSURED_BIT, &ct->status);
		nf_conntrack_event_cache(IPCT_STATUS, skb);
	}
	nf_ct_refresh_acct(ct, ctinfo, skb, timeout);

	return NF_ACCEPT;
}

/* Called when a new connection for this protocol found. */
static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,
		    unsigned int dataoff)
{
	enum tcp_conntrack new_state;
	const struct tcphdr *th;
	struct tcphdr _tcph;
	const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[0];
	const struct ip_ct_tcp_state *receiver = &ct->proto.tcp.seen[1];

	th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph);
	BUG_ON(th == NULL);

	/* Don't need lock here: this conntrack not in circulation yet */
	new_state
		= tcp_conntracks[0][get_conntrack_index(th)]
		[TCP_CONNTRACK_NONE];

	/* Invalid: delete conntrack */
	if (new_state >= TCP_CONNTRACK_MAX) {
		pr_debug("nf_ct_tcp: invalid new deleting.\n");
		return false;
	}

	if (new_state == TCP_CONNTRACK_SYN_SENT) {
		/* SYN packet */
		ct->proto.tcp.seen[0].td_end =
			segment_seq_plus_len(ntohl(th->seq), skb->len,
					     dataoff, th);
		ct->proto.tcp.seen[0].td_maxwin = ntohs(th->window);
		if (ct->proto.tcp.seen[0].td_maxwin == 0)
			ct->proto.tcp.seen[0].td_maxwin = 1;
		ct->proto.tcp.seen[0].td_maxend =
			ct->proto.tcp.seen[0].td_end;

		tcp_options(skb, dataoff, th, &ct->proto.tcp.seen[0]);
		ct->proto.tcp.seen[1].flags = 0;
	} else if (nf_ct_tcp_loose == 0) {
		/* Don't try to pick up connections. */
		return false;
	} else {
		/*
		 * We are in the middle of a connection,
		 * its history is lost for us.
		 * Let's try to use the data from the packet.
		 */
		ct->proto.tcp.seen[0].td_end =
			segment_seq_plus_len(ntohl(th->seq), skb->len,
					     dataoff, th);
		ct->proto.tcp.seen[0].td_maxwin = ntohs(th->window);
		if (ct->proto.tcp.seen[0].td_maxwin == 0)
			ct->proto.tcp.seen[0].td_maxwin = 1;
		ct->proto.tcp.seen[0].td_maxend =
			ct->proto.tcp.seen[0].td_end +
			ct->proto.tcp.seen[0].td_maxwin;
		ct->proto.tcp.seen[0].td_scale = 0;

		/* We assume SACK and liberal window checking to handle
		 * window scaling */
		ct->proto.tcp.seen[0].flags =
		ct->proto.tcp.seen[1].flags = IP_CT_TCP_FLAG_SACK_PERM |
					      IP_CT_TCP_FLAG_BE_LIBERAL;
	}

	ct->proto.tcp.seen[1].td_end = 0;
	ct->proto.tcp.seen[1].td_maxend = 0;
	ct->proto.tcp.seen[1].td_maxwin = 1;
	ct->proto.tcp.seen[1].td_scale = 0;

	/* tcp_packet will set them */
	ct->proto.tcp.state = TCP_CONNTRACK_NONE;
	ct->proto.tcp.last_index = TCP_NONE_SET;

	pr_debug("tcp_new: sender end=%u maxend=%u maxwin=%u scale=%i "
		 "receiver end=%u maxend=%u maxwin=%u scale=%i\n",
		 sender->td_end, sender->td_maxend, sender->td_maxwin,
		 sender->td_scale,
		 receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
		 receiver->td_scale);
	return true;
}

#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)

#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_conntrack.h>

static int tcp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
			 const struct nf_conn *ct)
{
	struct nlattr *nest_parms;
	struct nf_ct_tcp_flags tmp = {};

	read_lock_bh(&tcp_lock);
	nest_parms = nla_nest_start(skb, CTA_PROTOINFO_TCP | NLA_F_NESTED);
	if (!nest_parms)
		goto nla_put_failure;

	NLA_PUT_U8(skb, CTA_PROTOINFO_TCP_STATE, ct->proto.tcp.state);

	NLA_PUT_U8(skb, CTA_PROTOINFO_TCP_WSCALE_ORIGINAL,
		   ct->proto.tcp.seen[0].td_scale);

	NLA_PUT_U8(skb, CTA_PROTOINFO_TCP_WSCALE_REPLY,
		   ct->proto.tcp.seen[1].td_scale);

	tmp.flags = ct->proto.tcp.seen[0].flags;
	NLA_PUT(skb, CTA_PROTOINFO_TCP_FLAGS_ORIGINAL,
		sizeof(struct nf_ct_tcp_flags), &tmp);

	tmp.flags = ct->proto.tcp.seen[1].flags;
	NLA_PUT(skb, CTA_PROTOINFO_TCP_FLAGS_REPLY,
		sizeof(struct nf_ct_tcp_flags), &tmp);
	read_unlock_bh(&tcp_lock);

	nla_nest_end(skb, nest_parms);

	return 0;

nla_put_failure:
	read_unlock_bh(&tcp_lock);
	return -1;
}

static const struct nla_policy tcp_nla_policy[CTA_PROTOINFO_TCP_MAX+1] = {
	[CTA_PROTOINFO_TCP_STATE]	    = { .type = NLA_U8 },
	[CTA_PROTOINFO_TCP_WSCALE_ORIGINAL] = { .type = NLA_U8 },
	[CTA_PROTOINFO_TCP_WSCALE_REPLY]    = { .type = NLA_U8 },
	[CTA_PROTOINFO_TCP_FLAGS_ORIGINAL]  = { .len = sizeof(struct nf_ct_tcp_flags) },
	[CTA_PROTOINFO_TCP_FLAGS_REPLY]	    = { .len =  sizeof(struct nf_ct_tcp_flags) },
};

static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct)
{
	struct nlattr *pattr = cda[CTA_PROTOINFO_TCP];
	struct nlattr *tb[CTA_PROTOINFO_TCP_MAX+1];
	int err;

	/* updates could not contain anything about the private
	 * protocol info, in that case skip the parsing */
	if (!pattr)
		return 0;

	err = nla_parse_nested(tb, CTA_PROTOINFO_TCP_MAX, pattr, tcp_nla_policy);
	if (err < 0)
		return err;

	if (tb[CTA_PROTOINFO_TCP_STATE] &&
	    nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]) >= TCP_CONNTRACK_MAX)
		return -EINVAL;

	write_lock_bh(&tcp_lock);
	if (tb[CTA_PROTOINFO_TCP_STATE])
		ct->proto.tcp.state = nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]);

	if (tb[CTA_PROTOINFO_TCP_FLAGS_ORIGINAL]) {
		struct nf_ct_tcp_flags *attr =
			nla_data(tb[CTA_PROTOINFO_TCP_FLAGS_ORIGINAL]);
		ct->proto.tcp.seen[0].flags &= ~attr->mask;
		ct->proto.tcp.seen[0].flags |= attr->flags & attr->mask;
	}

	if (tb[CTA_PROTOINFO_TCP_FLAGS_REPLY]) {
		struct nf_ct_tcp_flags *attr =
			nla_data(tb[CTA_PROTOINFO_TCP_FLAGS_REPLY]);
		ct->proto.tcp.seen[1].flags &= ~attr->mask;
		ct->proto.tcp.seen[1].flags |= attr->flags & attr->mask;
	}

	if (tb[CTA_PROTOINFO_TCP_WSCALE_ORIGINAL] &&
	    tb[CTA_PROTOINFO_TCP_WSCALE_REPLY] &&
	    ct->proto.tcp.seen[0].flags & IP_CT_TCP_FLAG_WINDOW_SCALE &&
	    ct->proto.tcp.seen[1].flags & IP_CT_TCP_FLAG_WINDOW_SCALE) {
		ct->proto.tcp.seen[0].td_scale =
			nla_get_u8(tb[CTA_PROTOINFO_TCP_WSCALE_ORIGINAL]);
		ct->proto.tcp.seen[1].td_scale =
			nla_get_u8(tb[CTA_PROTOINFO_TCP_WSCALE_REPLY]);
	}
	write_unlock_bh(&tcp_lock);

	return 0;
}
#endif

#ifdef CONFIG_SYSCTL
static unsigned int tcp_sysctl_table_users;
static struct ctl_table_header *tcp_sysctl_header;
static struct ctl_table tcp_sysctl_table[] = {
	{
		.procname	= "nf_conntrack_tcp_timeout_syn_sent",
		.data		= &tcp_timeouts[TCP_CONNTRACK_SYN_SENT],
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.procname	= "nf_conntrack_tcp_timeout_syn_recv",
		.data		= &tcp_timeouts[TCP_CONNTRACK_SYN_RECV],
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.procname	= "nf_conntrack_tcp_timeout_established",
		.data		= &tcp_timeouts[TCP_CONNTRACK_ESTABLISHED],
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.procname	= "nf_conntrack_tcp_timeout_fin_wait",
		.data		= &tcp_timeouts[TCP_CONNTRACK_FIN_WAIT],
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.procname	= "nf_conntrack_tcp_timeout_close_wait",
		.data		= &tcp_timeouts[TCP_CONNTRACK_CLOSE_WAIT],
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.procname	= "nf_conntrack_tcp_timeout_last_ack",
		.data		= &tcp_timeouts[TCP_CONNTRACK_LAST_ACK],
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.procname	= "nf_conntrack_tcp_timeout_time_wait",
		.data		= &tcp_timeouts[TCP_CONNTRACK_TIME_WAIT],
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.procname	= "nf_conntrack_tcp_timeout_close",
		.data		= &tcp_timeouts[TCP_CONNTRACK_CLOSE],
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.procname	= "nf_conntrack_tcp_timeout_max_retrans",
		.data		= &nf_ct_tcp_timeout_max_retrans,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.ctl_name	= NET_NF_CONNTRACK_TCP_LOOSE,
		.procname	= "nf_conntrack_tcp_loose",
		.data		= &nf_ct_tcp_loose,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= NET_NF_CONNTRACK_TCP_BE_LIBERAL,
		.procname       = "nf_conntrack_tcp_be_liberal",
		.data           = &nf_ct_tcp_be_liberal,
		.maxlen         = sizeof(unsigned int),
		.mode           = 0644,
		.proc_handler   = &proc_dointvec,
	},
	{
		.ctl_name	= NET_NF_CONNTRACK_TCP_MAX_RETRANS,
		.procname	= "nf_conntrack_tcp_max_retrans",
		.data		= &nf_ct_tcp_max_retrans,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= 0
	}
};

#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT
static struct ctl_table tcp_compat_sysctl_table[] = {
	{
		.procname	= "ip_conntrack_tcp_timeout_syn_sent",
		.data		= &tcp_timeouts[TCP_CONNTRACK_SYN_SENT],
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.procname	= "ip_conntrack_tcp_timeout_syn_recv",
		.data		= &tcp_timeouts[TCP_CONNTRACK_SYN_RECV],
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.procname	= "ip_conntrack_tcp_timeout_established",
		.data		= &tcp_timeouts[TCP_CONNTRACK_ESTABLISHED],
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.procname	= "ip_conntrack_tcp_timeout_fin_wait",
		.data		= &tcp_timeouts[TCP_CONNTRACK_FIN_WAIT],
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.procname	= "ip_conntrack_tcp_timeout_close_wait",
		.data		= &tcp_timeouts[TCP_CONNTRACK_CLOSE_WAIT],
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.procname	= "ip_conntrack_tcp_timeout_last_ack",
		.data		= &tcp_timeouts[TCP_CONNTRACK_LAST_ACK],
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.procname	= "ip_conntrack_tcp_timeout_time_wait",
		.data		= &tcp_timeouts[TCP_CONNTRACK_TIME_WAIT],
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.procname	= "ip_conntrack_tcp_timeout_close",
		.data		= &tcp_timeouts[TCP_CONNTRACK_CLOSE],
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.procname	= "ip_conntrack_tcp_timeout_max_retrans",
		.data		= &nf_ct_tcp_timeout_max_retrans,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.ctl_name	= NET_IPV4_NF_CONNTRACK_TCP_LOOSE,
		.procname	= "ip_conntrack_tcp_loose",
		.data		= &nf_ct_tcp_loose,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= NET_IPV4_NF_CONNTRACK_TCP_BE_LIBERAL,
		.procname	= "ip_conntrack_tcp_be_liberal",
		.data		= &nf_ct_tcp_be_liberal,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= NET_IPV4_NF_CONNTRACK_TCP_MAX_RETRANS,
		.procname	= "ip_conntrack_tcp_max_retrans",
		.data		= &nf_ct_tcp_max_retrans,
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= 0
	}
};
#endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */
#endif /* CONFIG_SYSCTL */

struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 __read_mostly =
{
	.l3proto		= PF_INET,
	.l4proto 		= IPPROTO_TCP,
	.name 			= "tcp",
	.pkt_to_tuple 		= tcp_pkt_to_tuple,
	.invert_tuple 		= tcp_invert_tuple,
	.print_tuple 		= tcp_print_tuple,
	.print_conntrack 	= tcp_print_conntrack,
	.packet 		= tcp_packet,
	.new 			= tcp_new,
	.error			= tcp_error,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
	.to_nlattr		= tcp_to_nlattr,
	.from_nlattr		= nlattr_to_tcp,
	.tuple_to_nlattr	= nf_ct_port_tuple_to_nlattr,
	.nlattr_to_tuple	= nf_ct_port_nlattr_to_tuple,
	.nla_policy		= nf_ct_port_nla_policy,
#endif
#ifdef CONFIG_SYSCTL
	.ctl_table_users	= &tcp_sysctl_table_users,
	.ctl_table_header	= &tcp_sysctl_header,
	.ctl_table		= tcp_sysctl_table,
#ifdef CONFIG_NF_CONNTRACK_PROC_COMPAT
	.ctl_compat_table	= tcp_compat_sysctl_table,
#endif
#endif
};
EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_tcp4);

struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 __read_mostly =
{
	.l3proto		= PF_INET6,
	.l4proto 		= IPPROTO_TCP,
	.name 			= "tcp",
	.pkt_to_tuple 		= tcp_pkt_to_tuple,
	.invert_tuple 		= tcp_invert_tuple,
	.print_tuple 		= tcp_print_tuple,
	.print_conntrack 	= tcp_print_conntrack,
	.packet 		= tcp_packet,
	.new 			= tcp_new,
	.error			= tcp_error,
#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
	.to_nlattr		= tcp_to_nlattr,
	.from_nlattr		= nlattr_to_tcp,
	.tuple_to_nlattr	= nf_ct_port_tuple_to_nlattr,
	.nlattr_to_tuple	= nf_ct_port_nlattr_to_tuple,
	.nla_policy		= nf_ct_port_nla_policy,
#endif
#ifdef CONFIG_SYSCTL
	.ctl_table_users	= &tcp_sysctl_table_users,
	.ctl_table_header	= &tcp_sysctl_header,
	.ctl_table		= tcp_sysctl_table,
#endif
};
EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_tcp6);