aboutsummaryrefslogtreecommitdiff
path: root/net/dccp/ccids/ccid3.c
blob: e7db8a4ee642784485994de139e7eebddad70b3a (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
/*
 *  net/dccp/ccids/ccid3.c
 *
 *  Copyright (c) 2007   The University of Aberdeen, Scotland, UK
 *  Copyright (c) 2005-7 The University of Waikato, Hamilton, New Zealand.
 *  Copyright (c) 2005-7 Ian McDonald <ian.mcdonald@jandi.co.nz>
 *
 *  An implementation of the DCCP protocol
 *
 *  This code has been developed by the University of Waikato WAND
 *  research group. For further information please see http://www.wand.net.nz/
 *
 *  This code also uses code from Lulea University, rereleased as GPL by its
 *  authors:
 *  Copyright (c) 2003 Nils-Erik Mattsson, Joacim Haggmark, Magnus Erixzon
 *
 *  Changes to meet Linux coding standards, to make it meet latest ccid3 draft
 *  and to make it work as a loadable module in the DCCP stack written by
 *  Arnaldo Carvalho de Melo <acme@conectiva.com.br>.
 *
 *  Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br>
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; either version 2 of the License, or
 *  (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; if not, write to the Free Software
 *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */
#include "../dccp.h"
#include "ccid3.h"

#include <asm/unaligned.h>

#ifdef CONFIG_IP_DCCP_CCID3_DEBUG
static int ccid3_debug;
#define ccid3_pr_debug(format, a...)	DCCP_PR_DEBUG(ccid3_debug, format, ##a)
#else
#define ccid3_pr_debug(format, a...)
#endif

/*
 *	Transmitter Half-Connection Routines
 */
#ifdef CONFIG_IP_DCCP_CCID3_DEBUG
static const char *ccid3_tx_state_name(enum ccid3_hc_tx_states state)
{
	static char *ccid3_state_names[] = {
	[TFRC_SSTATE_NO_SENT]  = "NO_SENT",
	[TFRC_SSTATE_NO_FBACK] = "NO_FBACK",
	[TFRC_SSTATE_FBACK]    = "FBACK",
	[TFRC_SSTATE_TERM]     = "TERM",
	};

	return ccid3_state_names[state];
}
#endif

static void ccid3_hc_tx_set_state(struct sock *sk,
				  enum ccid3_hc_tx_states state)
{
	struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk);
	enum ccid3_hc_tx_states oldstate = hctx->state;

	ccid3_pr_debug("%s(%p) %-8.8s -> %s\n",
		       dccp_role(sk), sk, ccid3_tx_state_name(oldstate),
		       ccid3_tx_state_name(state));
	WARN_ON(state == oldstate);
	hctx->state = state;
}

/*
 * Compute the initial sending rate X_init in the manner of RFC 3390:
 *
 *	X_init  =  min(4 * s, max(2 * s, 4380 bytes)) / RTT
 *
 * Note that RFC 3390 uses MSS, RFC 4342 refers to RFC 3390, and rfc3448bis
 * (rev-02) clarifies the use of RFC 3390 with regard to the above formula.
 * For consistency with other parts of the code, X_init is scaled by 2^6.
 */
static inline u64 rfc3390_initial_rate(struct sock *sk)
{
	const struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk);
	const __u32 w_init = clamp_t(__u32, 4380U, 2 * hctx->s, 4 * hctx->s);

	return scaled_div(w_init << 6, hctx->rtt);
}

/**
 * ccid3_update_send_interval  -  Calculate new t_ipi = s / X_inst
 * This respects the granularity of X_inst (64 * bytes/second).
 */
static void ccid3_update_send_interval(struct ccid3_hc_tx_sock *hctx)
{
	hctx->t_ipi = scaled_div32(((u64)hctx->s) << 6, hctx->x);

	ccid3_pr_debug("t_ipi=%u, s=%u, X=%u\n", hctx->t_ipi,
		       hctx->s, (unsigned)(hctx->x >> 6));
}

static u32 ccid3_hc_tx_idle_rtt(struct ccid3_hc_tx_sock *hctx, ktime_t now)
{
	u32 delta = ktime_us_delta(now, hctx->t_last_win_count);

	return delta / hctx->rtt;
}

/**
 * ccid3_hc_tx_update_x  -  Update allowed sending rate X
 * @stamp: most recent time if available - can be left NULL.
 * This function tracks draft rfc3448bis, check there for latest details.
 *
 * Note: X and X_recv are both stored in units of 64 * bytes/second, to support
 *       fine-grained resolution of sending rates. This requires scaling by 2^6
 *       throughout the code. Only X_calc is unscaled (in bytes/second).
 *
 */
static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp)
{
	struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk);
	u64 min_rate = 2 * hctx->x_recv;
	const u64 old_x = hctx->x;
	ktime_t now = stamp ? *stamp : ktime_get_real();

	/*
	 * Handle IDLE periods: do not reduce below RFC3390 initial sending rate
	 * when idling [RFC 4342, 5.1]. Definition of idling is from rfc3448bis:
	 * a sender is idle if it has not sent anything over a 2-RTT-period.
	 * For consistency with X and X_recv, min_rate is also scaled by 2^6.
	 */
	if (ccid3_hc_tx_idle_rtt(hctx, now) >= 2) {
		min_rate = rfc3390_initial_rate(sk);
		min_rate = max(min_rate, 2 * hctx->x_recv);
	}

	if (hctx->p > 0) {

		hctx->x = min(((u64)hctx->x_calc) << 6, min_rate);
		hctx->x = max(hctx->x, (((u64)hctx->s) << 6) / TFRC_T_MBI);

	} else if (ktime_us_delta(now, hctx->t_ld) - (s64)hctx->rtt >= 0) {

		hctx->x = min(2 * hctx->x, min_rate);
		hctx->x = max(hctx->x,
			      scaled_div(((u64)hctx->s) << 6, hctx->rtt));
		hctx->t_ld = now;
	}

	if (hctx->x != old_x) {
		ccid3_pr_debug("X_prev=%u, X_now=%u, X_calc=%u, "
			       "X_recv=%u\n", (unsigned)(old_x >> 6),
			       (unsigned)(hctx->x >> 6), hctx->x_calc,
			       (unsigned)(hctx->x_recv >> 6));

		ccid3_update_send_interval(hctx);
	}
}

/*
 *	Track the mean packet size `s' (cf. RFC 4342, 5.3 and  RFC 3448, 4.1)
 *	@len: DCCP packet payload size in bytes
 */
static inline void ccid3_hc_tx_update_s(struct ccid3_hc_tx_sock *hctx, int len)
{
	const u16 old_s = hctx->s;

	hctx->s = tfrc_ewma(hctx->s, len, 9);

	if (hctx->s != old_s)
		ccid3_update_send_interval(hctx);
}

/*
 *	Update Window Counter using the algorithm from [RFC 4342, 8.1].
 *	As elsewhere, RTT > 0 is assumed by using dccp_sample_rtt().
 */
static inline void ccid3_hc_tx_update_win_count(struct ccid3_hc_tx_sock *hctx,
						ktime_t now)
{
	u32 delta = ktime_us_delta(now, hctx->t_last_win_count),
	    quarter_rtts = (4 * delta) / hctx->rtt;

	if (quarter_rtts > 0) {
		hctx->t_last_win_count = now;
		hctx->last_win_count  += min(quarter_rtts, 5U);
		hctx->last_win_count  &= 0xF;		/* mod 16 */
	}
}

static void ccid3_hc_tx_no_feedback_timer(unsigned long data)
{
	struct sock *sk = (struct sock *)data;
	struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk);
	unsigned long t_nfb = USEC_PER_SEC / 5;

	bh_lock_sock(sk);
	if (sock_owned_by_user(sk)) {
		/* Try again later. */
		/* XXX: set some sensible MIB */
		goto restart_timer;
	}

	ccid3_pr_debug("%s(%p, state=%s) - entry \n", dccp_role(sk), sk,
		       ccid3_tx_state_name(hctx->state));

	if (hctx->state == TFRC_SSTATE_FBACK)
		ccid3_hc_tx_set_state(sk, TFRC_SSTATE_NO_FBACK);
	else if (hctx->state != TFRC_SSTATE_NO_FBACK)
		goto out;

	/*
	 * Determine new allowed sending rate X as per draft rfc3448bis-00, 4.4
	 * RTO is 0 if and only if no feedback has been received yet.
	 */
	if (hctx->t_rto == 0 || hctx->p == 0) {

		/* halve send rate directly */
		hctx->x = max(hctx->x / 2, (((u64)hctx->s) << 6) / TFRC_T_MBI);
		ccid3_update_send_interval(hctx);
	} else {
		/*
		 *  Modify the cached value of X_recv
		 *
		 *  If (X_calc > 2 * X_recv)
		 *    X_recv = max(X_recv / 2, s / (2 * t_mbi));
		 *  Else
		 *    X_recv = X_calc / 4;
		 *
		 *  Note that X_recv is scaled by 2^6 while X_calc is not
		 */
		BUG_ON(hctx->p && !hctx->x_calc);

		if (hctx->x_calc > (hctx->x_recv >> 5))
			hctx->x_recv =
				max(hctx->x_recv / 2,
				    (((__u64)hctx->s) << 6) / (2 * TFRC_T_MBI));
		else {
			hctx->x_recv = hctx->x_calc;
			hctx->x_recv <<= 4;
		}
		ccid3_hc_tx_update_x(sk, NULL);
	}
	ccid3_pr_debug("Reduced X to %llu/64 bytes/sec\n",
			(unsigned long long)hctx->x);

	/*
	 * Set new timeout for the nofeedback timer.
	 * See comments in packet_recv() regarding the value of t_RTO.
	 */
	if (unlikely(hctx->t_rto == 0))		/* no feedback received yet */
		t_nfb = TFRC_INITIAL_TIMEOUT;
	else
		t_nfb = max(hctx->t_rto, 2 * hctx->t_ipi);

restart_timer:
	sk_reset_timer(sk, &hctx->no_feedback_timer,
			   jiffies + usecs_to_jiffies(t_nfb));
out:
	bh_unlock_sock(sk);
	sock_put(sk);
}

/*
 * returns
 *   > 0: delay (in msecs) that should pass before actually sending
 *   = 0: can send immediately
 *   < 0: error condition; do not send packet
 */
static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
{
	struct dccp_sock *dp = dccp_sk(sk);
	struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk);
	ktime_t now = ktime_get_real();
	s64 delay;

	/*
	 * This function is called only for Data and DataAck packets. Sending
	 * zero-sized Data(Ack)s is theoretically possible, but for congestion
	 * control this case is pathological - ignore it.
	 */
	if (unlikely(skb->len == 0))
		return -EBADMSG;

	switch (hctx->state) {
	case TFRC_SSTATE_NO_SENT:
		sk_reset_timer(sk, &hctx->no_feedback_timer, (jiffies +
				usecs_to_jiffies(TFRC_INITIAL_TIMEOUT)));
		hctx->last_win_count   = 0;
		hctx->t_last_win_count = now;

		/* Set t_0 for initial packet */
		hctx->t_nom = now;

		hctx->s = skb->len;

		/*
		 * Use initial RTT sample when available: recommended by erratum
		 * to RFC 4342. This implements the initialisation procedure of
		 * draft rfc3448bis, section 4.2. Remember, X is scaled by 2^6.
		 */
		if (dp->dccps_syn_rtt) {
			ccid3_pr_debug("SYN RTT = %uus\n", dp->dccps_syn_rtt);
			hctx->rtt  = dp->dccps_syn_rtt;
			hctx->x    = rfc3390_initial_rate(sk);
			hctx->t_ld = now;
		} else {
			/*
			 * Sender does not have RTT sample:
			 * - set fallback RTT (RFC 4340, 3.4) since a RTT value
			 *   is needed in several parts (e.g.  window counter);
			 * - set sending rate X_pps = 1pps as per RFC 3448, 4.2.
			 */
			hctx->rtt = DCCP_FALLBACK_RTT;
			hctx->x   = hctx->s;
			hctx->x <<= 6;
		}
		ccid3_update_send_interval(hctx);

		ccid3_hc_tx_set_state(sk, TFRC_SSTATE_NO_FBACK);
		break;
	case TFRC_SSTATE_NO_FBACK:
	case TFRC_SSTATE_FBACK:
		delay = ktime_us_delta(hctx->t_nom, now);
		ccid3_pr_debug("delay=%ld\n", (long)delay);
		/*
		 *	Scheduling of packet transmissions [RFC 3448, 4.6]
		 *
		 * if (t_now > t_nom - delta)
		 *       // send the packet now
		 * else
		 *       // send the packet in (t_nom - t_now) milliseconds.
		 */
		if (delay >= TFRC_T_DELTA)
			return (u32)delay / USEC_PER_MSEC;

		ccid3_hc_tx_update_win_count(hctx, now);
		break;
	case TFRC_SSTATE_TERM:
		DCCP_BUG("%s(%p) - Illegal state TERM", dccp_role(sk), sk);
		return -EINVAL;
	}

	/* prepare to send now (add options etc.) */
	dp->dccps_hc_tx_insert_options = 1;
	DCCP_SKB_CB(skb)->dccpd_ccval  = hctx->last_win_count;

	/* set the nominal send time for the next following packet */
	hctx->t_nom = ktime_add_us(hctx->t_nom, hctx->t_ipi);
	return 0;
}

static void ccid3_hc_tx_packet_sent(struct sock *sk, int more,
				    unsigned int len)
{
	struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk);

	ccid3_hc_tx_update_s(hctx, len);

	if (tfrc_tx_hist_add(&hctx->hist, dccp_sk(sk)->dccps_gss))
		DCCP_CRIT("packet history - out of memory!");
}

static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
{
	struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk);
	struct tfrc_tx_hist_entry *acked;
	ktime_t now;
	unsigned long t_nfb;
	u32 r_sample;

	/* we are only interested in ACKs */
	if (!(DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_ACK ||
	      DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_DATAACK))
		return;
	/* ... and only in the established state */
	if (hctx->state != TFRC_SSTATE_FBACK &&
	    hctx->state != TFRC_SSTATE_NO_FBACK)
		return;

	/*
	 * Locate the acknowledged packet in the TX history.
	 *
	 * Returning "entry not found" here can for instance happen when
	 *  - the host has not sent out anything (e.g. a passive server),
	 *  - the Ack is outdated (packet with higher Ack number was received),
	 *  - it is a bogus Ack (for a packet not sent on this connection).
	 */
	acked = tfrc_tx_hist_find_entry(hctx->hist, dccp_hdr_ack_seq(skb));
	if (acked == NULL)
		return;
	/* For the sake of RTT sampling, ignore/remove all older entries */
	tfrc_tx_hist_purge(&acked->next);

	/* Update the moving average for the RTT estimate (RFC 3448, 4.3) */
	now	  = ktime_get_real();
	r_sample  = dccp_sample_rtt(sk, ktime_us_delta(now, acked->stamp));
	hctx->rtt = tfrc_ewma(hctx->rtt, r_sample, 9);

	/*
	 * Update allowed sending rate X as per draft rfc3448bis-00, 4.2/3
	 */
	if (hctx->state == TFRC_SSTATE_NO_FBACK) {
		ccid3_hc_tx_set_state(sk, TFRC_SSTATE_FBACK);

		if (hctx->t_rto == 0) {
			/*
			 * Initial feedback packet: Larger Initial Windows (4.2)
			 */
			hctx->x    = rfc3390_initial_rate(sk);
			hctx->t_ld = now;

			ccid3_update_send_interval(hctx);

			goto done_computing_x;
		} else if (hctx->p == 0) {
			/*
			 * First feedback after nofeedback timer expiry (4.3)
			 */
			goto done_computing_x;
		}
	}

	/* Update sending rate (step 4 of [RFC 3448, 4.3]) */
	if (hctx->p > 0)
		hctx->x_calc = tfrc_calc_x(hctx->s, hctx->rtt, hctx->p);
	ccid3_hc_tx_update_x(sk, &now);

done_computing_x:
	ccid3_pr_debug("%s(%p), RTT=%uus (sample=%uus), s=%u, "
			       "p=%u, X_calc=%u, X_recv=%u, X=%u\n",
			       dccp_role(sk), sk, hctx->rtt, r_sample,
			       hctx->s, hctx->p, hctx->x_calc,
			       (unsigned)(hctx->x_recv >> 6),
			       (unsigned)(hctx->x >> 6));

	/* unschedule no feedback timer */
	sk_stop_timer(sk, &hctx->no_feedback_timer);

	/*
	 * As we have calculated new ipi, delta, t_nom it is possible
	 * that we now can send a packet, so wake up dccp_wait_for_ccid
	 */
	sk->sk_write_space(sk);

	/*
	 * Update timeout interval for the nofeedback timer.
	 * We use a configuration option to increase the lower bound.
	 * This can help avoid triggering the nofeedback timer too
	 * often ('spinning') on LANs with small RTTs.
	 */
	hctx->t_rto = max_t(u32, 4 * hctx->rtt, (CONFIG_IP_DCCP_CCID3_RTO *
						 (USEC_PER_SEC / 1000)));
	/*
	 * Schedule no feedback timer to expire in
	 * max(t_RTO, 2 * s/X)  =  max(t_RTO, 2 * t_ipi)
	 */
	t_nfb = max(hctx->t_rto, 2 * hctx->t_ipi);

	ccid3_pr_debug("%s(%p), Scheduled no feedback timer to "
		       "expire in %lu jiffies (%luus)\n",
		       dccp_role(sk), sk, usecs_to_jiffies(t_nfb), t_nfb);

	sk_reset_timer(sk, &hctx->no_feedback_timer,
			   jiffies + usecs_to_jiffies(t_nfb));
}

static int ccid3_hc_tx_parse_options(struct sock *sk, u8 packet_type,
				     u8 option, u8 *optval, u8 optlen)
{
	struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk);
	__be32 opt_val;

	switch (option) {
	case TFRC_OPT_RECEIVE_RATE:
	case TFRC_OPT_LOSS_EVENT_RATE:
		/* Must be ignored on Data packets, cf. RFC 4342 8.3 and 8.5 */
		if (packet_type == DCCP_PKT_DATA)
			break;
		if (unlikely(optlen != 4)) {
			DCCP_WARN("%s(%p), invalid len %d for %u\n",
				  dccp_role(sk), sk, optlen, option);
			return -EINVAL;
		}
		opt_val = ntohl(get_unaligned((__be32 *)optval));

		if (option == TFRC_OPT_RECEIVE_RATE) {
			/* Receive Rate is kept in units of 64 bytes/second */
			hctx->x_recv = opt_val;
			hctx->x_recv <<= 6;

			ccid3_pr_debug("%s(%p), RECEIVE_RATE=%u\n",
				       dccp_role(sk), sk, opt_val);
		} else {
			/* Update the fixpoint Loss Event Rate fraction */
			hctx->p = tfrc_invert_loss_event_rate(opt_val);

			ccid3_pr_debug("%s(%p), LOSS_EVENT_RATE=%u\n",
				       dccp_role(sk), sk, opt_val);
		}
	}
	return 0;
}

static int ccid3_hc_tx_init(struct ccid *ccid, struct sock *sk)
{
	struct ccid3_hc_tx_sock *hctx = ccid_priv(ccid);

	hctx->state = TFRC_SSTATE_NO_SENT;
	hctx->hist  = NULL;
	setup_timer(&hctx->no_feedback_timer,
		    ccid3_hc_tx_no_feedback_timer, (unsigned long)sk);
	return 0;
}

static void ccid3_hc_tx_exit(struct sock *sk)
{
	struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk);

	ccid3_hc_tx_set_state(sk, TFRC_SSTATE_TERM);
	sk_stop_timer(sk, &hctx->no_feedback_timer);

	tfrc_tx_hist_purge(&hctx->hist);
}

static void ccid3_hc_tx_get_info(struct sock *sk, struct tcp_info *info)
{
	info->tcpi_rto = ccid3_hc_tx_sk(sk)->t_rto;
	info->tcpi_rtt = ccid3_hc_tx_sk(sk)->rtt;
}

static int ccid3_hc_tx_getsockopt(struct sock *sk, const int optname, int len,
				  u32 __user *optval, int __user *optlen)
{
	const struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk);
	struct tfrc_tx_info tfrc;
	const void *val;

	switch (optname) {
	case DCCP_SOCKOPT_CCID_TX_INFO:
		if (len < sizeof(tfrc))
			return -EINVAL;
		tfrc.tfrctx_x	   = hctx->x;
		tfrc.tfrctx_x_recv = hctx->x_recv;
		tfrc.tfrctx_x_calc = hctx->x_calc;
		tfrc.tfrctx_rtt	   = hctx->rtt;
		tfrc.tfrctx_p	   = hctx->p;
		tfrc.tfrctx_rto	   = hctx->t_rto;
		tfrc.tfrctx_ipi	   = hctx->t_ipi;
		len = sizeof(tfrc);
		val = &tfrc;
		break;
	default:
		return -ENOPROTOOPT;
	}

	if (put_user(len, optlen) || copy_to_user(optval, val, len))
		return -EFAULT;

	return 0;
}

/*
 *	Receiver Half-Connection Routines
 */

/* CCID3 feedback types */
enum ccid3_fback_type {
	CCID3_FBACK_NONE = 0,
	CCID3_FBACK_INITIAL,
	CCID3_FBACK_PERIODIC,
	CCID3_FBACK_PARAM_CHANGE
};

#ifdef CONFIG_IP_DCCP_CCID3_DEBUG
static const char *ccid3_rx_state_name(enum ccid3_hc_rx_states state)
{
	static char *ccid3_rx_state_names[] = {
	[TFRC_RSTATE_NO_DATA] = "NO_DATA",
	[TFRC_RSTATE_DATA]    = "DATA",
	[TFRC_RSTATE_TERM]    = "TERM",
	};

	return ccid3_rx_state_names[state];
}
#endif

static void ccid3_hc_rx_set_state(struct sock *sk,
				  enum ccid3_hc_rx_states state)
{
	struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk);
	enum ccid3_hc_rx_states oldstate = hcrx->state;

	ccid3_pr_debug("%s(%p) %-8.8s -> %s\n",
		       dccp_role(sk), sk, ccid3_rx_state_name(oldstate),
		       ccid3_rx_state_name(state));
	WARN_ON(state == oldstate);
	hcrx->state = state;
}

static void ccid3_hc_rx_send_feedback(struct sock *sk,
				      const struct sk_buff *skb,
				      enum ccid3_fback_type fbtype)
{
	struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk);
	struct dccp_sock *dp = dccp_sk(sk);
	ktime_t now;
	s64 delta = 0;

	if (unlikely(hcrx->state == TFRC_RSTATE_TERM))
		return;

	now = ktime_get_real();

	switch (fbtype) {
	case CCID3_FBACK_INITIAL:
		hcrx->x_recv = 0;
		hcrx->p_inverse = ~0U;   /* see RFC 4342, 8.5 */
		break;
	case CCID3_FBACK_PARAM_CHANGE:
		/*
		 * When parameters change (new loss or p > p_prev), we do not
		 * have a reliable estimate for R_m of [RFC 3448, 6.2] and so
		 * need to  reuse the previous value of X_recv. However, when
		 * X_recv was 0 (due to early loss), this would kill X down to
		 * s/t_mbi (i.e. one packet in 64 seconds).
		 * To avoid such drastic reduction, we approximate X_recv as
		 * the number of bytes since last feedback.
		 * This is a safe fallback, since X is bounded above by X_calc.
		 */
		if (hcrx->x_recv > 0)
			break;
		/* fall through */
	case CCID3_FBACK_PERIODIC:
		delta = ktime_us_delta(now, hcrx->tstamp_last_feedback);
		if (delta <= 0)
			DCCP_BUG("delta (%ld) <= 0", (long)delta);
		else
			hcrx->x_recv = scaled_div32(hcrx->bytes_recv, delta);
		break;
	default:
		return;
	}

	ccid3_pr_debug("Interval %ldusec, X_recv=%u, 1/p=%u\n",
		       (long)delta, hcrx->x_recv, hcrx->p_inverse);

	hcrx->tstamp_last_feedback = now;
	hcrx->last_counter	   = dccp_hdr(skb)->dccph_ccval;
	hcrx->bytes_recv	   = 0;

	dp->dccps_hc_rx_insert_options = 1;
	dccp_send_ack(sk);
}

static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb)
{
	const struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk);
	__be32 x_recv, pinv;

	if (!(sk->sk_state == DCCP_OPEN || sk->sk_state == DCCP_PARTOPEN))
		return 0;

	if (dccp_packet_without_ack(skb))
		return 0;

	x_recv = htonl(hcrx->x_recv);
	pinv   = htonl(hcrx->p_inverse);

	if (dccp_insert_option(sk, skb, TFRC_OPT_LOSS_EVENT_RATE,
			       &pinv, sizeof(pinv)) ||
	    dccp_insert_option(sk, skb, TFRC_OPT_RECEIVE_RATE,
			       &x_recv, sizeof(x_recv)))
		return -1;

	return 0;
}

/** ccid3_first_li  -  Implements [RFC 3448, 6.3.1]
 *
 * Determine the length of the first loss interval via inverse lookup.
 * Assume that X_recv can be computed by the throughput equation
 *		    s
 *	X_recv = --------
 *		 R * fval
 * Find some p such that f(p) = fval; return 1/p (scaled).
 */
static u32 ccid3_first_li(struct sock *sk)
{
	struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk);
	u32 x_recv, p, delta;
	u64 fval;

	if (hcrx->rtt == 0) {
		DCCP_WARN("No RTT estimate available, using fallback RTT\n");
		hcrx->rtt = DCCP_FALLBACK_RTT;
	}

	delta = ktime_to_us(net_timedelta(hcrx->tstamp_last_feedback));
	x_recv = scaled_div32(hcrx->bytes_recv, delta);
	if (x_recv == 0) {		/* would also trigger divide-by-zero */
		DCCP_WARN("X_recv==0\n");
		if (hcrx->x_recv == 0) {
			DCCP_BUG("stored value of X_recv is zero");
			return ~0U;
		}
		x_recv = hcrx->x_recv;
	}

	fval = scaled_div(hcrx->s, hcrx->rtt);
	fval = scaled_div32(fval, x_recv);
	p = tfrc_calc_x_reverse_lookup(fval);

	ccid3_pr_debug("%s(%p), receive rate=%u bytes/s, implied "
		       "loss rate=%u\n", dccp_role(sk), sk, x_recv, p);

	return p == 0 ? ~0U : scaled_div(1, p);
}

static void ccid3_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb)
{
	struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk);
	enum ccid3_fback_type do_feedback = CCID3_FBACK_NONE;
	const u64 ndp = dccp_sk(sk)->dccps_options_received.dccpor_ndp;
	const bool is_data_packet = dccp_data_packet(skb);

	if (unlikely(hcrx->state == TFRC_RSTATE_NO_DATA)) {
		if (is_data_packet) {
			const u32 payload = skb->len - dccp_hdr(skb)->dccph_doff * 4;
			do_feedback = CCID3_FBACK_INITIAL;
			ccid3_hc_rx_set_state(sk, TFRC_RSTATE_DATA);
			hcrx->s = payload;
			/*
			 * Not necessary to update bytes_recv here,
			 * since X_recv = 0 for the first feedback packet (cf.
			 * RFC 3448, 6.3) -- gerrit
			 */
		}
		goto update_records;
	}

	if (tfrc_rx_hist_duplicate(&hcrx->hist, skb))
		return; /* done receiving */

	if (is_data_packet) {
		const u32 payload = skb->len - dccp_hdr(skb)->dccph_doff * 4;
		/*
		 * Update moving-average of s and the sum of received payload bytes
		 */
		hcrx->s = tfrc_ewma(hcrx->s, payload, 9);
		hcrx->bytes_recv += payload;
	}

	/*
	 * Perform loss detection and handle pending losses
	 */
	if (tfrc_rx_handle_loss(&hcrx->hist, &hcrx->li_hist,
				skb, ndp, ccid3_first_li, sk)) {
		do_feedback = CCID3_FBACK_PARAM_CHANGE;
		goto done_receiving;
	}

	if (tfrc_rx_hist_loss_pending(&hcrx->hist))
		return; /* done receiving */

	/*
	 * Handle data packets: RTT sampling and monitoring p
	 */
	if (unlikely(!is_data_packet))
		goto update_records;

	if (!tfrc_lh_is_initialised(&hcrx->li_hist)) {
		const u32 sample = tfrc_rx_hist_sample_rtt(&hcrx->hist, skb);
		/*
		 * Empty loss history: no loss so far, hence p stays 0.
		 * Sample RTT values, since an RTT estimate is required for the
		 * computation of p when the first loss occurs; RFC 3448, 6.3.1.
		 */
		if (sample != 0)
			hcrx->rtt = tfrc_ewma(hcrx->rtt, sample, 9);

	} else if (tfrc_lh_update_i_mean(&hcrx->li_hist, skb)) {
		/*
		 * Step (3) of [RFC 3448, 6.1]: Recompute I_mean and, if I_mean
		 * has decreased (resp. p has increased), send feedback now.
		 */
		do_feedback = CCID3_FBACK_PARAM_CHANGE;
	}

	/*
	 * Check if the periodic once-per-RTT feedback is due; RFC 4342, 10.3
	 */
	if (SUB16(dccp_hdr(skb)->dccph_ccval, hcrx->last_counter) > 3)
		do_feedback = CCID3_FBACK_PERIODIC;

update_records:
	tfrc_rx_hist_add_packet(&hcrx->hist, skb, ndp);

done_receiving:
	if (do_feedback)
		ccid3_hc_rx_send_feedback(sk, skb, do_feedback);
}

static int ccid3_hc_rx_init(struct ccid *ccid, struct sock *sk)
{
	struct ccid3_hc_rx_sock *hcrx = ccid_priv(ccid);

	hcrx->state = TFRC_RSTATE_NO_DATA;
	tfrc_lh_init(&hcrx->li_hist);
	return tfrc_rx_hist_alloc(&hcrx->hist);
}

static void ccid3_hc_rx_exit(struct sock *sk)
{
	struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk);

	ccid3_hc_rx_set_state(sk, TFRC_RSTATE_TERM);

	tfrc_rx_hist_purge(&hcrx->hist);
	tfrc_lh_cleanup(&hcrx->li_hist);
}

static void ccid3_hc_rx_get_info(struct sock *sk, struct tcp_info *info)
{
	info->tcpi_ca_state = ccid3_hc_rx_sk(sk)->state;
	info->tcpi_options  |= TCPI_OPT_TIMESTAMPS;
	info->tcpi_rcv_rtt  = ccid3_hc_rx_sk(sk)->rtt;
}

static int ccid3_hc_rx_getsockopt(struct sock *sk, const int optname, int len,
				  u32 __user *optval, int __user *optlen)
{
	const struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk);
	struct tfrc_rx_info rx_info;
	const void *val;

	switch (optname) {
	case DCCP_SOCKOPT_CCID_RX_INFO:
		if (len < sizeof(rx_info))
			return -EINVAL;
		rx_info.tfrcrx_x_recv = hcrx->x_recv;
		rx_info.tfrcrx_rtt    = hcrx->rtt;
		rx_info.tfrcrx_p      = tfrc_invert_loss_event_rate(hcrx->p_inverse);
		len = sizeof(rx_info);
		val = &rx_info;
		break;
	default:
		return -ENOPROTOOPT;
	}

	if (put_user(len, optlen) || copy_to_user(optval, val, len))
		return -EFAULT;

	return 0;
}

static struct ccid_operations ccid3 = {
	.ccid_id		   = DCCPC_CCID3,
	.ccid_name		   = "TCP-Friendly Rate Control",
	.ccid_owner		   = THIS_MODULE,
	.ccid_hc_tx_obj_size	   = sizeof(struct ccid3_hc_tx_sock),
	.ccid_hc_tx_init	   = ccid3_hc_tx_init,
	.ccid_hc_tx_exit	   = ccid3_hc_tx_exit,
	.ccid_hc_tx_send_packet	   = ccid3_hc_tx_send_packet,
	.ccid_hc_tx_packet_sent	   = ccid3_hc_tx_packet_sent,
	.ccid_hc_tx_packet_recv	   = ccid3_hc_tx_packet_recv,
	.ccid_hc_tx_parse_options  = ccid3_hc_tx_parse_options,
	.ccid_hc_rx_obj_size	   = sizeof(struct ccid3_hc_rx_sock),
	.ccid_hc_rx_init	   = ccid3_hc_rx_init,
	.ccid_hc_rx_exit	   = ccid3_hc_rx_exit,
	.ccid_hc_rx_insert_options = ccid3_hc_rx_insert_options,
	.ccid_hc_rx_packet_recv	   = ccid3_hc_rx_packet_recv,
	.ccid_hc_rx_get_info	   = ccid3_hc_rx_get_info,
	.ccid_hc_tx_get_info	   = ccid3_hc_tx_get_info,
	.ccid_hc_rx_getsockopt	   = ccid3_hc_rx_getsockopt,
	.ccid_hc_tx_getsockopt	   = ccid3_hc_tx_getsockopt,
};

#ifdef CONFIG_IP_DCCP_CCID3_DEBUG
module_param(ccid3_debug, bool, 0644);
MODULE_PARM_DESC(ccid3_debug, "Enable debug messages");
#endif

static __init int ccid3_module_init(void)
{
	return ccid_register(&ccid3);
}
module_init(ccid3_module_init);

static __exit void ccid3_module_exit(void)
{
	ccid_unregister(&ccid3);
}
module_exit(ccid3_module_exit);

MODULE_AUTHOR("Ian McDonald <ian.mcdonald@jandi.co.nz>, "
	      "Arnaldo Carvalho de Melo <acme@ghostprotocols.net>");
MODULE_DESCRIPTION("DCCP TFRC CCID3 CCID");
MODULE_LICENSE("GPL");
MODULE_ALIAS("net-dccp-ccid-3");