Free Electrons

Embedded Linux Experts

  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
/*
 * DCCP connection tracking protocol helper
 *
 * Copyright (c) 2005, 2006, 2008 Patrick McHardy <kaber@trash.net>
 *
 * 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/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/sysctl.h>
#include <linux/spinlock.h>
#include <linux/skbuff.h>
#include <linux/dccp.h>
#include <linux/slab.h>

#include <net/net_namespace.h>
#include <net/netns/generic.h>

#include <linux/netfilter/nfnetlink_conntrack.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>

/* Timeouts are based on values from RFC4340:
 *
 * - REQUEST:
 *
 *   8.1.2. Client Request
 *
 *   A client MAY give up on its DCCP-Requests after some time
 *   (3 minutes, for example).
 *
 * - RESPOND:
 *
 *   8.1.3. Server Response
 *
 *   It MAY also leave the RESPOND state for CLOSED after a timeout of
 *   not less than 4MSL (8 minutes);
 *
 * - PARTOPEN:
 *
 *   8.1.5. Handshake Completion
 *
 *   If the client remains in PARTOPEN for more than 4MSL (8 minutes),
 *   it SHOULD reset the connection with Reset Code 2, "Aborted".
 *
 * - OPEN:
 *
 *   The DCCP timestamp overflows after 11.9 hours. If the connection
 *   stays idle this long the sequence number won't be recognized
 *   as valid anymore.
 *
 * - CLOSEREQ/CLOSING:
 *
 *   8.3. Termination
 *
 *   The retransmission timer should initially be set to go off in two
 *   round-trip times and should back off to not less than once every
 *   64 seconds ...
 *
 * - TIMEWAIT:
 *
 *   4.3. States
 *
 *   A server or client socket remains in this state for 2MSL (4 minutes)
 *   after the connection has been town down, ...
 */

#define DCCP_MSL (2 * 60 * HZ)

static const char * const dccp_state_names[] = {
	[CT_DCCP_NONE]		= "NONE",
	[CT_DCCP_REQUEST]	= "REQUEST",
	[CT_DCCP_RESPOND]	= "RESPOND",
	[CT_DCCP_PARTOPEN]	= "PARTOPEN",
	[CT_DCCP_OPEN]		= "OPEN",
	[CT_DCCP_CLOSEREQ]	= "CLOSEREQ",
	[CT_DCCP_CLOSING]	= "CLOSING",
	[CT_DCCP_TIMEWAIT]	= "TIMEWAIT",
	[CT_DCCP_IGNORE]	= "IGNORE",
	[CT_DCCP_INVALID]	= "INVALID",
};

#define sNO	CT_DCCP_NONE
#define sRQ	CT_DCCP_REQUEST
#define sRS	CT_DCCP_RESPOND
#define sPO	CT_DCCP_PARTOPEN
#define sOP	CT_DCCP_OPEN
#define sCR	CT_DCCP_CLOSEREQ
#define sCG	CT_DCCP_CLOSING
#define sTW	CT_DCCP_TIMEWAIT
#define sIG	CT_DCCP_IGNORE
#define sIV	CT_DCCP_INVALID

/*
 * DCCP state transition table
 *
 * The assumption is the same as for TCP tracking:
 *
 * 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 destination
 * can't receive segments we haven't seen.
 *
 * The following states exist:
 *
 * NONE:	Initial state, expecting Request
 * REQUEST:	Request seen, waiting for Response from server
 * RESPOND:	Response from server seen, waiting for Ack from client
 * PARTOPEN:	Ack after Response seen, waiting for packet other than Response,
 * 		Reset or Sync from server
 * OPEN:	Packet other than Response, Reset or Sync seen
 * CLOSEREQ:	CloseReq from server seen, expecting Close from client
 * CLOSING:	Close seen, expecting Reset
 * TIMEWAIT:	Reset seen
 * IGNORE:	Not determinable whether packet is valid
 *
 * Some states exist only on one side of the connection: REQUEST, RESPOND,
 * PARTOPEN, CLOSEREQ. For the other side these states are equivalent to
 * the one it was in before.
 *
 * Packets are marked as ignored (sIG) if we don't know if they're valid
 * (for example a reincarnation of a connection we didn't notice is dead
 * already) and the server may send back a connection closing Reset or a
 * Response. They're also used for Sync/SyncAck packets, which we don't
 * care about.
 */
static const u_int8_t
dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = {
	[CT_DCCP_ROLE_CLIENT] = {
		[DCCP_PKT_REQUEST] = {
		/*
		 * sNO -> sRQ		Regular Request
		 * sRQ -> sRQ		Retransmitted Request or reincarnation
		 * sRS -> sRS		Retransmitted Request (apparently Response
		 * 			got lost after we saw it) or reincarnation
		 * sPO -> sIG		Ignore, conntrack might be out of sync
		 * sOP -> sIG		Ignore, conntrack might be out of sync
		 * sCR -> sIG		Ignore, conntrack might be out of sync
		 * sCG -> sIG		Ignore, conntrack might be out of sync
		 * sTW -> sRQ		Reincarnation
		 *
		 *	sNO, sRQ, sRS, sPO. sOP, sCR, sCG, sTW, */
			sRQ, sRQ, sRS, sIG, sIG, sIG, sIG, sRQ,
		},
		[DCCP_PKT_RESPONSE] = {
		/*
		 * sNO -> sIV		Invalid
		 * sRQ -> sIG		Ignore, might be response to ignored Request
		 * sRS -> sIG		Ignore, might be response to ignored Request
		 * sPO -> sIG		Ignore, might be response to ignored Request
		 * sOP -> sIG		Ignore, might be response to ignored Request
		 * sCR -> sIG		Ignore, might be response to ignored Request
		 * sCG -> sIG		Ignore, might be response to ignored Request
		 * sTW -> sIV		Invalid, reincarnation in reverse direction
		 *			goes through sRQ
		 *
		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
			sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIV,
		},
		[DCCP_PKT_ACK] = {
		/*
		 * sNO -> sIV		No connection
		 * sRQ -> sIV		No connection
		 * sRS -> sPO		Ack for Response, move to PARTOPEN (8.1.5.)
		 * sPO -> sPO		Retransmitted Ack for Response, remain in PARTOPEN
		 * sOP -> sOP		Regular ACK, remain in OPEN
		 * sCR -> sCR		Ack in CLOSEREQ MAY be processed (8.3.)
		 * sCG -> sCG		Ack in CLOSING MAY be processed (8.3.)
		 * sTW -> sIV
		 *
		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
			sIV, sIV, sPO, sPO, sOP, sCR, sCG, sIV
		},
		[DCCP_PKT_DATA] = {
		/*
		 * sNO -> sIV		No connection
		 * sRQ -> sIV		No connection
		 * sRS -> sIV		No connection
		 * sPO -> sIV		MUST use DataAck in PARTOPEN state (8.1.5.)
		 * sOP -> sOP		Regular Data packet
		 * sCR -> sCR		Data in CLOSEREQ MAY be processed (8.3.)
		 * sCG -> sCG		Data in CLOSING MAY be processed (8.3.)
		 * sTW -> sIV
		 *
		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
			sIV, sIV, sIV, sIV, sOP, sCR, sCG, sIV,
		},
		[DCCP_PKT_DATAACK] = {
		/*
		 * sNO -> sIV		No connection
		 * sRQ -> sIV		No connection
		 * sRS -> sPO		Ack for Response, move to PARTOPEN (8.1.5.)
		 * sPO -> sPO		Remain in PARTOPEN state
		 * sOP -> sOP		Regular DataAck packet in OPEN state
		 * sCR -> sCR		DataAck in CLOSEREQ MAY be processed (8.3.)
		 * sCG -> sCG		DataAck in CLOSING MAY be processed (8.3.)
		 * sTW -> sIV
		 *
		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
			sIV, sIV, sPO, sPO, sOP, sCR, sCG, sIV
		},
		[DCCP_PKT_CLOSEREQ] = {
		/*
		 * CLOSEREQ may only be sent by the server.
		 *
		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
			sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV
		},
		[DCCP_PKT_CLOSE] = {
		/*
		 * sNO -> sIV		No connection
		 * sRQ -> sIV		No connection
		 * sRS -> sIV		No connection
		 * sPO -> sCG		Client-initiated close
		 * sOP -> sCG		Client-initiated close
		 * sCR -> sCG		Close in response to CloseReq (8.3.)
		 * sCG -> sCG		Retransmit
		 * sTW -> sIV		Late retransmit, already in TIME_WAIT
		 *
		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
			sIV, sIV, sIV, sCG, sCG, sCG, sIV, sIV
		},
		[DCCP_PKT_RESET] = {
		/*
		 * sNO -> sIV		No connection
		 * sRQ -> sTW		Sync received or timeout, SHOULD send Reset (8.1.1.)
		 * sRS -> sTW		Response received without Request
		 * sPO -> sTW		Timeout, SHOULD send Reset (8.1.5.)
		 * sOP -> sTW		Connection reset
		 * sCR -> sTW		Connection reset
		 * sCG -> sTW		Connection reset
		 * sTW -> sIG		Ignore (don't refresh timer)
		 *
		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
			sIV, sTW, sTW, sTW, sTW, sTW, sTW, sIG
		},
		[DCCP_PKT_SYNC] = {
		/*
		 * We currently ignore Sync packets
		 *
		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
			sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
		},
		[DCCP_PKT_SYNCACK] = {
		/*
		 * We currently ignore SyncAck packets
		 *
		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
			sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
		},
	},
	[CT_DCCP_ROLE_SERVER] = {
		[DCCP_PKT_REQUEST] = {
		/*
		 * sNO -> sIV		Invalid
		 * sRQ -> sIG		Ignore, conntrack might be out of sync
		 * sRS -> sIG		Ignore, conntrack might be out of sync
		 * sPO -> sIG		Ignore, conntrack might be out of sync
		 * sOP -> sIG		Ignore, conntrack might be out of sync
		 * sCR -> sIG		Ignore, conntrack might be out of sync
		 * sCG -> sIG		Ignore, conntrack might be out of sync
		 * sTW -> sRQ		Reincarnation, must reverse roles
		 *
		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
			sIV, sIG, sIG, sIG, sIG, sIG, sIG, sRQ
		},
		[DCCP_PKT_RESPONSE] = {
		/*
		 * sNO -> sIV		Response without Request
		 * sRQ -> sRS		Response to clients Request
		 * sRS -> sRS		Retransmitted Response (8.1.3. SHOULD NOT)
		 * sPO -> sIG		Response to an ignored Request or late retransmit
		 * sOP -> sIG		Ignore, might be response to ignored Request
		 * sCR -> sIG		Ignore, might be response to ignored Request
		 * sCG -> sIG		Ignore, might be response to ignored Request
		 * sTW -> sIV		Invalid, Request from client in sTW moves to sRQ
		 *
		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
			sIV, sRS, sRS, sIG, sIG, sIG, sIG, sIV
		},
		[DCCP_PKT_ACK] = {
		/*
		 * sNO -> sIV		No connection
		 * sRQ -> sIV		No connection
		 * sRS -> sIV		No connection
		 * sPO -> sOP		Enter OPEN state (8.1.5.)
		 * sOP -> sOP		Regular Ack in OPEN state
		 * sCR -> sIV		Waiting for Close from client
		 * sCG -> sCG		Ack in CLOSING MAY be processed (8.3.)
		 * sTW -> sIV
		 *
		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
			sIV, sIV, sIV, sOP, sOP, sIV, sCG, sIV
		},
		[DCCP_PKT_DATA] = {
		/*
		 * sNO -> sIV		No connection
		 * sRQ -> sIV		No connection
		 * sRS -> sIV		No connection
		 * sPO -> sOP		Enter OPEN state (8.1.5.)
		 * sOP -> sOP		Regular Data packet in OPEN state
		 * sCR -> sIV		Waiting for Close from client
		 * sCG -> sCG		Data in CLOSING MAY be processed (8.3.)
		 * sTW -> sIV
		 *
		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
			sIV, sIV, sIV, sOP, sOP, sIV, sCG, sIV
		},
		[DCCP_PKT_DATAACK] = {
		/*
		 * sNO -> sIV		No connection
		 * sRQ -> sIV		No connection
		 * sRS -> sIV		No connection
		 * sPO -> sOP		Enter OPEN state (8.1.5.)
		 * sOP -> sOP		Regular DataAck in OPEN state
		 * sCR -> sIV		Waiting for Close from client
		 * sCG -> sCG		Data in CLOSING MAY be processed (8.3.)
		 * sTW -> sIV
		 *
		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
			sIV, sIV, sIV, sOP, sOP, sIV, sCG, sIV
		},
		[DCCP_PKT_CLOSEREQ] = {
		/*
		 * sNO -> sIV		No connection
		 * sRQ -> sIV		No connection
		 * sRS -> sIV		No connection
		 * sPO -> sOP -> sCR	Move directly to CLOSEREQ (8.1.5.)
		 * sOP -> sCR		CloseReq in OPEN state
		 * sCR -> sCR		Retransmit
		 * sCG -> sCR		Simultaneous close, client sends another Close
		 * sTW -> sIV		Already closed
		 *
		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
			sIV, sIV, sIV, sCR, sCR, sCR, sCR, sIV
		},
		[DCCP_PKT_CLOSE] = {
		/*
		 * sNO -> sIV		No connection
		 * sRQ -> sIV		No connection
		 * sRS -> sIV		No connection
		 * sPO -> sOP -> sCG	Move direcly to CLOSING
		 * sOP -> sCG		Move to CLOSING
		 * sCR -> sIV		Close after CloseReq is invalid
		 * sCG -> sCG		Retransmit
		 * sTW -> sIV		Already closed
		 *
		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
			sIV, sIV, sIV, sCG, sCG, sIV, sCG, sIV
		},
		[DCCP_PKT_RESET] = {
		/*
		 * sNO -> sIV		No connection
		 * sRQ -> sTW		Reset in response to Request
		 * sRS -> sTW		Timeout, SHOULD send Reset (8.1.3.)
		 * sPO -> sTW		Timeout, SHOULD send Reset (8.1.3.)
		 * sOP -> sTW
		 * sCR -> sTW
		 * sCG -> sTW
		 * sTW -> sIG		Ignore (don't refresh timer)
		 *
		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW, sTW */
			sIV, sTW, sTW, sTW, sTW, sTW, sTW, sTW, sIG
		},
		[DCCP_PKT_SYNC] = {
		/*
		 * We currently ignore Sync packets
		 *
		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
			sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
		},
		[DCCP_PKT_SYNCACK] = {
		/*
		 * We currently ignore SyncAck packets
		 *
		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
			sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
		},
	},
};

/* this module per-net specifics */
static int dccp_net_id __read_mostly;
struct dccp_net {
	int dccp_loose;
	unsigned int dccp_timeout[CT_DCCP_MAX + 1];
#ifdef CONFIG_SYSCTL
	struct ctl_table_header *sysctl_header;
	struct ctl_table *sysctl_table;
#endif
};

static inline struct dccp_net *dccp_pernet(struct net *net)
{
	return net_generic(net, dccp_net_id);
}

static bool dccp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
			      struct nf_conntrack_tuple *tuple)
{
	struct dccp_hdr _hdr, *dh;

	dh = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr);
	if (dh == NULL)
		return false;

	tuple->src.u.dccp.port = dh->dccph_sport;
	tuple->dst.u.dccp.port = dh->dccph_dport;
	return true;
}

static bool dccp_invert_tuple(struct nf_conntrack_tuple *inv,
			      const struct nf_conntrack_tuple *tuple)
{
	inv->src.u.dccp.port = tuple->dst.u.dccp.port;
	inv->dst.u.dccp.port = tuple->src.u.dccp.port;
	return true;
}

static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
		     unsigned int dataoff, unsigned int *timeouts)
{
	struct net *net = nf_ct_net(ct);
	struct dccp_net *dn;
	struct dccp_hdr _dh, *dh;
	const char *msg;
	u_int8_t state;

	dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh);
	BUG_ON(dh == NULL);

	state = dccp_state_table[CT_DCCP_ROLE_CLIENT][dh->dccph_type][CT_DCCP_NONE];
	switch (state) {
	default:
		dn = dccp_pernet(net);
		if (dn->dccp_loose == 0) {
			msg = "nf_ct_dccp: not picking up existing connection ";
			goto out_invalid;
		}
	case CT_DCCP_REQUEST:
		break;
	case CT_DCCP_INVALID:
		msg = "nf_ct_dccp: invalid state transition ";
		goto out_invalid;
	}

	ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_CLIENT;
	ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_SERVER;
	ct->proto.dccp.state = CT_DCCP_NONE;
	ct->proto.dccp.last_pkt = DCCP_PKT_REQUEST;
	ct->proto.dccp.last_dir = IP_CT_DIR_ORIGINAL;
	ct->proto.dccp.handshake_seq = 0;
	return true;

out_invalid:
	if (LOG_INVALID(net, IPPROTO_DCCP))
		nf_log_packet(nf_ct_l3num(ct), 0, skb, NULL, NULL, NULL, msg);
	return false;
}

static u64 dccp_ack_seq(const struct dccp_hdr *dh)
{
	const struct dccp_hdr_ack_bits *dhack;

	dhack = (void *)dh + __dccp_basic_hdr_len(dh);
	return ((u64)ntohs(dhack->dccph_ack_nr_high) << 32) +
		     ntohl(dhack->dccph_ack_nr_low);
}

static unsigned int *dccp_get_timeouts(struct net *net)
{
	return dccp_pernet(net)->dccp_timeout;
}

static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb,
		       unsigned int dataoff, enum ip_conntrack_info ctinfo,
		       u_int8_t pf, unsigned int hooknum,
		       unsigned int *timeouts)
{
	struct net *net = nf_ct_net(ct);
	enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
	struct dccp_hdr _dh, *dh;
	u_int8_t type, old_state, new_state;
	enum ct_dccp_roles role;

	dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh);
	BUG_ON(dh == NULL);
	type = dh->dccph_type;

	if (type == DCCP_PKT_RESET &&
	    !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
		/* Tear down connection immediately if only reply is a RESET */
		nf_ct_kill_acct(ct, ctinfo, skb);
		return NF_ACCEPT;
	}

	spin_lock_bh(&ct->lock);

	role = ct->proto.dccp.role[dir];
	old_state = ct->proto.dccp.state;
	new_state = dccp_state_table[role][type][old_state];

	switch (new_state) {
	case CT_DCCP_REQUEST:
		if (old_state == CT_DCCP_TIMEWAIT &&
		    role == CT_DCCP_ROLE_SERVER) {
			/* Reincarnation in the reverse direction: reopen and
			 * reverse client/server roles. */
			ct->proto.dccp.role[dir] = CT_DCCP_ROLE_CLIENT;
			ct->proto.dccp.role[!dir] = CT_DCCP_ROLE_SERVER;
		}
		break;
	case CT_DCCP_RESPOND:
		if (old_state == CT_DCCP_REQUEST)
			ct->proto.dccp.handshake_seq = dccp_hdr_seq(dh);
		break;
	case CT_DCCP_PARTOPEN:
		if (old_state == CT_DCCP_RESPOND &&
		    type == DCCP_PKT_ACK &&
		    dccp_ack_seq(dh) == ct->proto.dccp.handshake_seq)
			set_bit(IPS_ASSURED_BIT, &ct->status);
		break;
	case CT_DCCP_IGNORE:
		/*
		 * Connection tracking might be out of sync, so we ignore
		 * packets that might establish a new connection and resync
		 * if the server responds with a valid Response.
		 */
		if (ct->proto.dccp.last_dir == !dir &&
		    ct->proto.dccp.last_pkt == DCCP_PKT_REQUEST &&
		    type == DCCP_PKT_RESPONSE) {
			ct->proto.dccp.role[!dir] = CT_DCCP_ROLE_CLIENT;
			ct->proto.dccp.role[dir] = CT_DCCP_ROLE_SERVER;
			ct->proto.dccp.handshake_seq = dccp_hdr_seq(dh);
			new_state = CT_DCCP_RESPOND;
			break;
		}
		ct->proto.dccp.last_dir = dir;
		ct->proto.dccp.last_pkt = type;

		spin_unlock_bh(&ct->lock);
		if (LOG_INVALID(net, IPPROTO_DCCP))
			nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
				      "nf_ct_dccp: invalid packet ignored ");
		return NF_ACCEPT;
	case CT_DCCP_INVALID:
		spin_unlock_bh(&ct->lock);
		if (LOG_INVALID(net, IPPROTO_DCCP))
			nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
				      "nf_ct_dccp: invalid state transition ");
		return -NF_ACCEPT;
	}

	ct->proto.dccp.last_dir = dir;
	ct->proto.dccp.last_pkt = type;
	ct->proto.dccp.state = new_state;
	spin_unlock_bh(&ct->lock);

	if (new_state != old_state)
		nf_conntrack_event_cache(IPCT_PROTOINFO, ct);

	nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]);

	return NF_ACCEPT;
}

static int dccp_error(struct net *net, struct nf_conn *tmpl,
		      struct sk_buff *skb, unsigned int dataoff,
		      enum ip_conntrack_info *ctinfo,
		      u_int8_t pf, unsigned int hooknum)
{
	struct dccp_hdr _dh, *dh;
	unsigned int dccp_len = skb->len - dataoff;
	unsigned int cscov;
	const char *msg;

	dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &dh);
	if (dh == NULL) {
		msg = "nf_ct_dccp: short packet ";
		goto out_invalid;
	}

	if (dh->dccph_doff * 4 < sizeof(struct dccp_hdr) ||
	    dh->dccph_doff * 4 > dccp_len) {
		msg = "nf_ct_dccp: truncated/malformed packet ";
		goto out_invalid;
	}

	cscov = dccp_len;
	if (dh->dccph_cscov) {
		cscov = (dh->dccph_cscov - 1) * 4;
		if (cscov > dccp_len) {
			msg = "nf_ct_dccp: bad checksum coverage ";
			goto out_invalid;
		}
	}

	if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING &&
	    nf_checksum_partial(skb, hooknum, dataoff, cscov, IPPROTO_DCCP,
				pf)) {
		msg = "nf_ct_dccp: bad checksum ";
		goto out_invalid;
	}

	if (dh->dccph_type >= DCCP_PKT_INVALID) {
		msg = "nf_ct_dccp: reserved packet type ";
		goto out_invalid;
	}

	return NF_ACCEPT;

out_invalid:
	if (LOG_INVALID(net, IPPROTO_DCCP))
		nf_log_packet(pf, 0, skb, NULL, NULL, NULL, msg);
	return -NF_ACCEPT;
}

static int dccp_print_tuple(struct seq_file *s,
			    const struct nf_conntrack_tuple *tuple)
{
	return seq_printf(s, "sport=%hu dport=%hu ",
			  ntohs(tuple->src.u.dccp.port),
			  ntohs(tuple->dst.u.dccp.port));
}

static int dccp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
{
	return seq_printf(s, "%s ", dccp_state_names[ct->proto.dccp.state]);
}

#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
static int dccp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
			  struct nf_conn *ct)
{
	struct nlattr *nest_parms;

	spin_lock_bh(&ct->lock);
	nest_parms = nla_nest_start(skb, CTA_PROTOINFO_DCCP | NLA_F_NESTED);
	if (!nest_parms)
		goto nla_put_failure;
	NLA_PUT_U8(skb, CTA_PROTOINFO_DCCP_STATE, ct->proto.dccp.state);
	NLA_PUT_U8(skb, CTA_PROTOINFO_DCCP_ROLE,
		   ct->proto.dccp.role[IP_CT_DIR_ORIGINAL]);
	NLA_PUT_BE64(skb, CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ,
		     cpu_to_be64(ct->proto.dccp.handshake_seq));
	nla_nest_end(skb, nest_parms);
	spin_unlock_bh(&ct->lock);
	return 0;

nla_put_failure:
	spin_unlock_bh(&ct->lock);
	return -1;
}

static const struct nla_policy dccp_nla_policy[CTA_PROTOINFO_DCCP_MAX + 1] = {
	[CTA_PROTOINFO_DCCP_STATE]	= { .type = NLA_U8 },
	[CTA_PROTOINFO_DCCP_ROLE]	= { .type = NLA_U8 },
	[CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ] = { .type = NLA_U64 },
};

static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct)
{
	struct nlattr *attr = cda[CTA_PROTOINFO_DCCP];
	struct nlattr *tb[CTA_PROTOINFO_DCCP_MAX + 1];
	int err;

	if (!attr)
		return 0;

	err = nla_parse_nested(tb, CTA_PROTOINFO_DCCP_MAX, attr,
			       dccp_nla_policy);
	if (err < 0)
		return err;

	if (!tb[CTA_PROTOINFO_DCCP_STATE] ||
	    !tb[CTA_PROTOINFO_DCCP_ROLE] ||
	    nla_get_u8(tb[CTA_PROTOINFO_DCCP_ROLE]) > CT_DCCP_ROLE_MAX ||
	    nla_get_u8(tb[CTA_PROTOINFO_DCCP_STATE]) >= CT_DCCP_IGNORE) {
		return -EINVAL;
	}

	spin_lock_bh(&ct->lock);
	ct->proto.dccp.state = nla_get_u8(tb[CTA_PROTOINFO_DCCP_STATE]);
	if (nla_get_u8(tb[CTA_PROTOINFO_DCCP_ROLE]) == CT_DCCP_ROLE_CLIENT) {
		ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_CLIENT;
		ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_SERVER;
	} else {
		ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_SERVER;
		ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_CLIENT;
	}
	if (tb[CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ]) {
		ct->proto.dccp.handshake_seq =
		be64_to_cpu(nla_get_be64(tb[CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ]));
	}
	spin_unlock_bh(&ct->lock);
	return 0;
}

static int dccp_nlattr_size(void)
{
	return nla_total_size(0)	/* CTA_PROTOINFO_DCCP */
		+ nla_policy_len(dccp_nla_policy, CTA_PROTOINFO_DCCP_MAX + 1);
}

#endif

#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)

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

static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[], void *data)
{
	struct dccp_net *dn = dccp_pernet(&init_net);
	unsigned int *timeouts = data;
	int i;

	/* set default DCCP timeouts. */
	for (i=0; i<CT_DCCP_MAX; i++)
		timeouts[i] = dn->dccp_timeout[i];

	/* there's a 1:1 mapping between attributes and protocol states. */
	for (i=CTA_TIMEOUT_DCCP_UNSPEC+1; i<CTA_TIMEOUT_DCCP_MAX+1; i++) {
		if (tb[i]) {
			timeouts[i] = ntohl(nla_get_be32(tb[i])) * HZ;
		}
	}
	return 0;
}

static int
dccp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data)
{
        const unsigned int *timeouts = data;
	int i;

	for (i=CTA_TIMEOUT_DCCP_UNSPEC+1; i<CTA_TIMEOUT_DCCP_MAX+1; i++)
		NLA_PUT_BE32(skb, i, htonl(timeouts[i] / HZ));

	return 0;

nla_put_failure:
	return -ENOSPC;
}

static const struct nla_policy
dccp_timeout_nla_policy[CTA_TIMEOUT_DCCP_MAX+1] = {
	[CTA_TIMEOUT_DCCP_REQUEST]	= { .type = NLA_U32 },
	[CTA_TIMEOUT_DCCP_RESPOND]	= { .type = NLA_U32 },
	[CTA_TIMEOUT_DCCP_PARTOPEN]	= { .type = NLA_U32 },
	[CTA_TIMEOUT_DCCP_OPEN]		= { .type = NLA_U32 },
	[CTA_TIMEOUT_DCCP_CLOSEREQ]	= { .type = NLA_U32 },
	[CTA_TIMEOUT_DCCP_CLOSING]	= { .type = NLA_U32 },
	[CTA_TIMEOUT_DCCP_TIMEWAIT]	= { .type = NLA_U32 },
};
#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */

#ifdef CONFIG_SYSCTL
/* template, data assigned later */
static struct ctl_table dccp_sysctl_table[] = {
	{
		.procname	= "nf_conntrack_dccp_timeout_request",
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
	},
	{
		.procname	= "nf_conntrack_dccp_timeout_respond",
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
	},
	{
		.procname	= "nf_conntrack_dccp_timeout_partopen",
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
	},
	{
		.procname	= "nf_conntrack_dccp_timeout_open",
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
	},
	{
		.procname	= "nf_conntrack_dccp_timeout_closereq",
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
	},
	{
		.procname	= "nf_conntrack_dccp_timeout_closing",
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
	},
	{
		.procname	= "nf_conntrack_dccp_timeout_timewait",
		.maxlen		= sizeof(unsigned int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec_jiffies,
	},
	{
		.procname	= "nf_conntrack_dccp_loose",
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= proc_dointvec,
	},
	{ }
};
#endif /* CONFIG_SYSCTL */

static struct nf_conntrack_l4proto dccp_proto4 __read_mostly = {
	.l3proto		= AF_INET,
	.l4proto		= IPPROTO_DCCP,
	.name			= "dccp",
	.pkt_to_tuple		= dccp_pkt_to_tuple,
	.invert_tuple		= dccp_invert_tuple,
	.new			= dccp_new,
	.packet			= dccp_packet,
	.get_timeouts		= dccp_get_timeouts,
	.error			= dccp_error,
	.print_tuple		= dccp_print_tuple,
	.print_conntrack	= dccp_print_conntrack,
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
	.to_nlattr		= dccp_to_nlattr,
	.nlattr_size		= dccp_nlattr_size,
	.from_nlattr		= nlattr_to_dccp,
	.tuple_to_nlattr	= nf_ct_port_tuple_to_nlattr,
	.nlattr_tuple_size	= nf_ct_port_nlattr_tuple_size,
	.nlattr_to_tuple	= nf_ct_port_nlattr_to_tuple,
	.nla_policy		= nf_ct_port_nla_policy,
#endif
#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
	.ctnl_timeout		= {
		.nlattr_to_obj	= dccp_timeout_nlattr_to_obj,
		.obj_to_nlattr	= dccp_timeout_obj_to_nlattr,
		.nlattr_max	= CTA_TIMEOUT_DCCP_MAX,
		.obj_size	= sizeof(unsigned int) * CT_DCCP_MAX,
		.nla_policy	= dccp_timeout_nla_policy,
	},
#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
};

static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = {
	.l3proto		= AF_INET6,
	.l4proto		= IPPROTO_DCCP,
	.name			= "dccp",
	.pkt_to_tuple		= dccp_pkt_to_tuple,
	.invert_tuple		= dccp_invert_tuple,
	.new			= dccp_new,
	.packet			= dccp_packet,
	.get_timeouts		= dccp_get_timeouts,
	.error			= dccp_error,
	.print_tuple		= dccp_print_tuple,
	.print_conntrack	= dccp_print_conntrack,
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
	.to_nlattr		= dccp_to_nlattr,
	.nlattr_size		= dccp_nlattr_size,
	.from_nlattr		= nlattr_to_dccp,
	.tuple_to_nlattr	= nf_ct_port_tuple_to_nlattr,
	.nlattr_tuple_size	= nf_ct_port_nlattr_tuple_size,
	.nlattr_to_tuple	= nf_ct_port_nlattr_to_tuple,
	.nla_policy		= nf_ct_port_nla_policy,
#endif
#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
	.ctnl_timeout		= {
		.nlattr_to_obj	= dccp_timeout_nlattr_to_obj,
		.obj_to_nlattr	= dccp_timeout_obj_to_nlattr,
		.nlattr_max	= CTA_TIMEOUT_DCCP_MAX,
		.obj_size	= sizeof(unsigned int) * CT_DCCP_MAX,
		.nla_policy	= dccp_timeout_nla_policy,
	},
#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
};

static __net_init int dccp_net_init(struct net *net)
{
	struct dccp_net *dn = dccp_pernet(net);

	/* default values */
	dn->dccp_loose = 1;
	dn->dccp_timeout[CT_DCCP_REQUEST]	= 2 * DCCP_MSL;
	dn->dccp_timeout[CT_DCCP_RESPOND]	= 4 * DCCP_MSL;
	dn->dccp_timeout[CT_DCCP_PARTOPEN]	= 4 * DCCP_MSL;
	dn->dccp_timeout[CT_DCCP_OPEN]		= 12 * 3600 * HZ;
	dn->dccp_timeout[CT_DCCP_CLOSEREQ]	= 64 * HZ;
	dn->dccp_timeout[CT_DCCP_CLOSING]	= 64 * HZ;
	dn->dccp_timeout[CT_DCCP_TIMEWAIT]	= 2 * DCCP_MSL;

#ifdef CONFIG_SYSCTL
	dn->sysctl_table = kmemdup(dccp_sysctl_table,
			sizeof(dccp_sysctl_table), GFP_KERNEL);
	if (!dn->sysctl_table)
		return -ENOMEM;

	dn->sysctl_table[0].data = &dn->dccp_timeout[CT_DCCP_REQUEST];
	dn->sysctl_table[1].data = &dn->dccp_timeout[CT_DCCP_RESPOND];
	dn->sysctl_table[2].data = &dn->dccp_timeout[CT_DCCP_PARTOPEN];
	dn->sysctl_table[3].data = &dn->dccp_timeout[CT_DCCP_OPEN];
	dn->sysctl_table[4].data = &dn->dccp_timeout[CT_DCCP_CLOSEREQ];
	dn->sysctl_table[5].data = &dn->dccp_timeout[CT_DCCP_CLOSING];
	dn->sysctl_table[6].data = &dn->dccp_timeout[CT_DCCP_TIMEWAIT];
	dn->sysctl_table[7].data = &dn->dccp_loose;

	dn->sysctl_header = register_net_sysctl_table(net,
			nf_net_netfilter_sysctl_path, dn->sysctl_table);
	if (!dn->sysctl_header) {
		kfree(dn->sysctl_table);
		return -ENOMEM;
	}
#endif

	return 0;
}

static __net_exit void dccp_net_exit(struct net *net)
{
	struct dccp_net *dn = dccp_pernet(net);
#ifdef CONFIG_SYSCTL
	unregister_net_sysctl_table(dn->sysctl_header);
	kfree(dn->sysctl_table);
#endif
}

static struct pernet_operations dccp_net_ops = {
	.init = dccp_net_init,
	.exit = dccp_net_exit,
	.id   = &dccp_net_id,
	.size = sizeof(struct dccp_net),
};

static int __init nf_conntrack_proto_dccp_init(void)
{
	int err;

	err = register_pernet_subsys(&dccp_net_ops);
	if (err < 0)
		goto err1;

	err = nf_conntrack_l4proto_register(&dccp_proto4);
	if (err < 0)
		goto err2;

	err = nf_conntrack_l4proto_register(&dccp_proto6);
	if (err < 0)
		goto err3;
	return 0;

err3:
	nf_conntrack_l4proto_unregister(&dccp_proto4);
err2:
	unregister_pernet_subsys(&dccp_net_ops);
err1:
	return err;
}

static void __exit nf_conntrack_proto_dccp_fini(void)
{
	unregister_pernet_subsys(&dccp_net_ops);
	nf_conntrack_l4proto_unregister(&dccp_proto6);
	nf_conntrack_l4proto_unregister(&dccp_proto4);
}

module_init(nf_conntrack_proto_dccp_init);
module_exit(nf_conntrack_proto_dccp_fini);

MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
MODULE_DESCRIPTION("DCCP connection tracking protocol helper");
MODULE_LICENSE("GPL");