summaryrefslogtreecommitdiffstats
path: root/net/dccp/ccids/ccid2.c
blob: c9ea19a4d85e10b0ba8c5a2a4d8c27b2496bc79b (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
/*
 *  net/dccp/ccids/ccid2.c
 *
 *  Copyright (c) 2005, 2006 Andrea Bittau <a.bittau@cs.ucl.ac.uk>
 *
 *  Changes to meet Linux coding standards, and DCCP infrastructure fixes.
 *
 *  Copyright (c) 2006 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.
 */

/*
 * This implementation should follow RFC 4341
 */
#include "../feat.h"
#include "../ccid.h"
#include "../dccp.h"
#include "ccid2.h"


#ifdef CONFIG_IP_DCCP_CCID2_DEBUG
static int ccid2_debug;
#define ccid2_pr_debug(format, a...)	DCCP_PR_DEBUG(ccid2_debug, format, ##a)

static void ccid2_hc_tx_check_sanity(const struct ccid2_hc_tx_sock *hctx)
{
	int len = 0;
	int pipe = 0;
	struct ccid2_seq *seqp = hctx->ccid2hctx_seqh;

	/* there is data in the chain */
	if (seqp != hctx->ccid2hctx_seqt) {
		seqp = seqp->ccid2s_prev;
		len++;
		if (!seqp->ccid2s_acked)
			pipe++;

		while (seqp != hctx->ccid2hctx_seqt) {
			struct ccid2_seq *prev = seqp->ccid2s_prev;

			len++;
			if (!prev->ccid2s_acked)
				pipe++;

			/* packets are sent sequentially */
			BUG_ON(dccp_delta_seqno(seqp->ccid2s_seq,
						prev->ccid2s_seq ) >= 0);
			BUG_ON(time_before(seqp->ccid2s_sent,
					   prev->ccid2s_sent));

			seqp = prev;
		}
	}

	BUG_ON(pipe != hctx->ccid2hctx_pipe);
	ccid2_pr_debug("len of chain=%d\n", len);

	do {
		seqp = seqp->ccid2s_prev;
		len++;
	} while (seqp != hctx->ccid2hctx_seqh);

	ccid2_pr_debug("total len=%d\n", len);
	BUG_ON(len != hctx->ccid2hctx_seqbufc * CCID2_SEQBUF_LEN);
}
#else
#define ccid2_pr_debug(format, a...)
#define ccid2_hc_tx_check_sanity(hctx)
#endif

static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hctx)
{
	struct ccid2_seq *seqp;
	int i;

	/* check if we have space to preserve the pointer to the buffer */
	if (hctx->ccid2hctx_seqbufc >= (sizeof(hctx->ccid2hctx_seqbuf) /
					sizeof(struct ccid2_seq*)))
		return -ENOMEM;

	/* allocate buffer and initialize linked list */
	seqp = kmalloc(CCID2_SEQBUF_LEN * sizeof(struct ccid2_seq), gfp_any());
	if (seqp == NULL)
		return -ENOMEM;

	for (i = 0; i < (CCID2_SEQBUF_LEN - 1); i++) {
		seqp[i].ccid2s_next = &seqp[i + 1];
		seqp[i + 1].ccid2s_prev = &seqp[i];
	}
	seqp[CCID2_SEQBUF_LEN - 1].ccid2s_next = seqp;
	seqp->ccid2s_prev = &seqp[CCID2_SEQBUF_LEN - 1];

	/* This is the first allocation.  Initiate the head and tail.  */
	if (hctx->ccid2hctx_seqbufc == 0)
		hctx->ccid2hctx_seqh = hctx->ccid2hctx_seqt = seqp;
	else {
		/* link the existing list with the one we just created */
		hctx->ccid2hctx_seqh->ccid2s_next = seqp;
		seqp->ccid2s_prev = hctx->ccid2hctx_seqh;

		hctx->ccid2hctx_seqt->ccid2s_prev = &seqp[CCID2_SEQBUF_LEN - 1];
		seqp[CCID2_SEQBUF_LEN - 1].ccid2s_next = hctx->ccid2hctx_seqt;
	}

	/* store the original pointer to the buffer so we can free it */
	hctx->ccid2hctx_seqbuf[hctx->ccid2hctx_seqbufc] = seqp;
	hctx->ccid2hctx_seqbufc++;

	return 0;
}

static int ccid2_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
{
	struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);

	if (hctx->ccid2hctx_pipe < hctx->ccid2hctx_cwnd)
		return 0;

	return 1; /* XXX CCID should dequeue when ready instead of polling */
}

static void ccid2_change_l_ack_ratio(struct sock *sk, u32 val)
{
	struct dccp_sock *dp = dccp_sk(sk);
	u32 max_ratio = DIV_ROUND_UP(ccid2_hc_tx_sk(sk)->ccid2hctx_cwnd, 2);

	/*
	 * Ensure that Ack Ratio does not exceed ceil(cwnd/2), which is (2) from
	 * RFC 4341, 6.1.2. We ignore the statement that Ack Ratio 2 is always
	 * acceptable since this causes starvation/deadlock whenever cwnd < 2.
	 * The same problem arises when Ack Ratio is 0 (ie. Ack Ratio disabled).
	 */
	if (val == 0 || val > max_ratio) {
		DCCP_WARN("Limiting Ack Ratio (%u) to %u\n", val, max_ratio);
		val = max_ratio;
	}
	if (val > DCCPF_ACK_RATIO_MAX)
		val = DCCPF_ACK_RATIO_MAX;

	if (val == dp->dccps_l_ack_ratio)
		return;

	ccid2_pr_debug("changing local ack ratio to %u\n", val);
	dp->dccps_l_ack_ratio = val;
}

static void ccid2_change_srtt(struct ccid2_hc_tx_sock *hctx, long val)
{
	ccid2_pr_debug("change SRTT to %ld\n", val);
	hctx->ccid2hctx_srtt = val;
}

static void ccid2_start_rto_timer(struct sock *sk);

static void ccid2_hc_tx_rto_expire(unsigned long data)
{
	struct sock *sk = (struct sock *)data;
	struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
	long s;

	bh_lock_sock(sk);
	if (sock_owned_by_user(sk)) {
		sk_reset_timer(sk, &hctx->ccid2hctx_rtotimer,
			       jiffies + HZ / 5);
		goto out;
	}

	ccid2_pr_debug("RTO_EXPIRE\n");

	ccid2_hc_tx_check_sanity(hctx);

	/* back-off timer */
	hctx->ccid2hctx_rto <<= 1;

	s = hctx->ccid2hctx_rto / HZ;
	if (s > 60)
		hctx->ccid2hctx_rto = 60 * HZ;

	ccid2_start_rto_timer(sk);

	/* adjust pipe, cwnd etc */
	hctx->ccid2hctx_ssthresh = hctx->ccid2hctx_cwnd / 2;
	if (hctx->ccid2hctx_ssthresh < 2)
		hctx->ccid2hctx_ssthresh = 2;
	hctx->ccid2hctx_cwnd	 = 1;
	hctx->ccid2hctx_pipe	 = 0;

	/* clear state about stuff we sent */
	hctx->ccid2hctx_seqt = hctx->ccid2hctx_seqh;
	hctx->ccid2hctx_packets_acked = 0;

	/* clear ack ratio state. */
	hctx->ccid2hctx_rpseq	 = 0;
	hctx->ccid2hctx_rpdupack = -1;
	ccid2_change_l_ack_ratio(sk, 1);
	ccid2_hc_tx_check_sanity(hctx);
out:
	bh_unlock_sock(sk);
	sock_put(sk);
}

static void ccid2_start_rto_timer(struct sock *sk)
{
	struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);

	ccid2_pr_debug("setting RTO timeout=%ld\n", hctx->ccid2hctx_rto);

	BUG_ON(timer_pending(&hctx->ccid2hctx_rtotimer));
	sk_reset_timer(sk, &hctx->ccid2hctx_rtotimer,
		       jiffies + hctx->ccid2hctx_rto);
}

static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, unsigned int len)
{
	struct dccp_sock *dp = dccp_sk(sk);
	struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
	struct ccid2_seq *next;

	hctx->ccid2hctx_pipe++;

	hctx->ccid2hctx_seqh->ccid2s_seq   = dp->dccps_gss;
	hctx->ccid2hctx_seqh->ccid2s_acked = 0;
	hctx->ccid2hctx_seqh->ccid2s_sent  = jiffies;

	next = hctx->ccid2hctx_seqh->ccid2s_next;
	/* check if we need to alloc more space */
	if (next == hctx->ccid2hctx_seqt) {
		if (ccid2_hc_tx_alloc_seq(hctx)) {
			DCCP_CRIT("packet history - out of memory!");
			/* FIXME: find a more graceful way to bail out */
			return;
		}
		next = hctx->ccid2hctx_seqh->ccid2s_next;
		BUG_ON(next == hctx->ccid2hctx_seqt);
	}
	hctx->ccid2hctx_seqh = next;

	ccid2_pr_debug("cwnd=%d pipe=%d\n", hctx->ccid2hctx_cwnd,
		       hctx->ccid2hctx_pipe);

	/*
	 * FIXME: The code below is broken and the variables have been removed
	 * from the socket struct. The `ackloss' variable was always set to 0,
	 * and with arsent there are several problems:
	 *  (i) it doesn't just count the number of Acks, but all sent packets;
	 *  (ii) it is expressed in # of packets, not # of windows, so the
	 *  comparison below uses the wrong formula: Appendix A of RFC 4341
	 *  comes up with the number K = cwnd / (R^2 - R) of consecutive windows
	 *  of data with no lost or marked Ack packets. If arsent were the # of
	 *  consecutive Acks received without loss, then Ack Ratio needs to be
	 *  decreased by 1 when
	 *	      arsent >=  K * cwnd / R  =  cwnd^2 / (R^3 - R^2)
	 *  where cwnd / R is the number of Acks received per window of data
	 *  (cf. RFC 4341, App. A). The problems are that
	 *  - arsent counts other packets as well;
	 *  - the comparison uses a formula different from RFC 4341;
	 *  - computing a cubic/quadratic equation each time is too complicated.
	 *  Hence a different algorithm is needed.
	 */
#if 0
	/* Ack Ratio.  Need to maintain a concept of how many windows we sent */
	hctx->ccid2hctx_arsent++;
	/* We had an ack loss in this window... */
	if (hctx->ccid2hctx_ackloss) {
		if (hctx->ccid2hctx_arsent >= hctx->ccid2hctx_cwnd) {
			hctx->ccid2hctx_arsent	= 0;
			hctx->ccid2hctx_ackloss	= 0;
		}
	} else {
		/* No acks lost up to now... */
		/* decrease ack ratio if enough packets were sent */
		if (dp->dccps_l_ack_ratio > 1) {
			/* XXX don't calculate denominator each time */
			int denom = dp->dccps_l_ack_ratio * dp->dccps_l_ack_ratio -
				    dp->dccps_l_ack_ratio;

			denom = hctx->ccid2hctx_cwnd * hctx->ccid2hctx_cwnd / denom;

			if (hctx->ccid2hctx_arsent >= denom) {
				ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio - 1);
				hctx->ccid2hctx_arsent = 0;
			}
		} else {
			/* we can't increase ack ratio further [1] */
			hctx->ccid2hctx_arsent = 0; /* or maybe set it to cwnd*/
		}
	}
#endif

	/* setup RTO timer */
	if (!timer_pending(&hctx->ccid2hctx_rtotimer))
		ccid2_start_rto_timer(sk);

#ifdef CONFIG_IP_DCCP_CCID2_DEBUG
	do {
		struct ccid2_seq *seqp = hctx->ccid2hctx_seqt;

		while (seqp != hctx->ccid2hctx_seqh) {
			ccid2_pr_debug("out seq=%llu acked=%d time=%lu\n",
				       (unsigned long long)seqp->ccid2s_seq,
				       seqp->ccid2s_acked, seqp->ccid2s_sent);
			seqp = seqp->ccid2s_next;
		}
	} while (0);
	ccid2_pr_debug("=========\n");
	ccid2_hc_tx_check_sanity(hctx);
#endif
}

/* XXX Lame code duplication!
 * returns -1 if none was found.
 * else returns the next offset to use in the function call.
 */
static int ccid2_ackvector(struct sock *sk, struct sk_buff *skb, int offset,
			   unsigned char **vec, unsigned char *veclen)
{
	const struct dccp_hdr *dh = dccp_hdr(skb);
	unsigned char *options = (unsigned char *)dh + dccp_hdr_len(skb);
	unsigned char *opt_ptr;
	const unsigned char *opt_end = (unsigned char *)dh +
					(dh->dccph_doff * 4);
	unsigned char opt, len;
	unsigned char *value;

	BUG_ON(offset < 0);
	options += offset;
	opt_ptr = options;
	if (opt_ptr >= opt_end)
		return -1;

	while (opt_ptr != opt_end) {
		opt   = *opt_ptr++;
		len   = 0;
		value = NULL;

		/* Check if this isn't a single byte option */
		if (opt > DCCPO_MAX_RESERVED) {
			if (opt_ptr == opt_end)
				goto out_invalid_option;

			len = *opt_ptr++;
			if (len < 3)
				goto out_invalid_option;
			/*
			 * Remove the type and len fields, leaving
			 * just the value size
			 */
			len     -= 2;
			value   = opt_ptr;
			opt_ptr += len;

			if (opt_ptr > opt_end)
				goto out_invalid_option;
		}

		switch (opt) {
		case DCCPO_ACK_VECTOR_0:
		case DCCPO_ACK_VECTOR_1:
			*vec	= value;
			*veclen = len;
			return offset + (opt_ptr - options);
		}
	}

	return -1;

out_invalid_option:
	DCCP_BUG("Invalid option - this should not happen (previous parsing)!");
	return -1;
}

static void ccid2_hc_tx_kill_rto_timer(struct sock *sk)
{
	struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);

	sk_stop_timer(sk, &hctx->ccid2hctx_rtotimer);
	ccid2_pr_debug("deleted RTO timer\n");
}

static inline void ccid2_new_ack(struct sock *sk,
				 struct ccid2_seq *seqp,
				 unsigned int *maxincr)
{
	struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);

	if (hctx->ccid2hctx_cwnd < hctx->ccid2hctx_ssthresh) {
		if (*maxincr > 0 && ++hctx->ccid2hctx_packets_acked == 2) {
			hctx->ccid2hctx_cwnd += 1;
			*maxincr	     -= 1;
			hctx->ccid2hctx_packets_acked = 0;
		}
	} else if (++hctx->ccid2hctx_packets_acked >= hctx->ccid2hctx_cwnd) {
			hctx->ccid2hctx_cwnd += 1;
			hctx->ccid2hctx_packets_acked = 0;
	}

	/* update RTO */
	if (hctx->ccid2hctx_srtt == -1 ||
	    time_after(jiffies, hctx->ccid2hctx_lastrtt + hctx->ccid2hctx_srtt)) {
		unsigned long r = (long)jiffies - (long)seqp->ccid2s_sent;
		int s;

		/* first measurement */
		if (hctx->ccid2hctx_srtt == -1) {
			ccid2_pr_debug("R: %lu Time=%lu seq=%llu\n",
				       r, jiffies,
				       (unsigned long long)seqp->ccid2s_seq);
			ccid2_change_srtt(hctx, r);
			hctx->ccid2hctx_rttvar = r >> 1;
		} else {
			/* RTTVAR */
			long tmp = hctx->ccid2hctx_srtt - r;
			long srtt;

			if (tmp < 0)
				tmp *= -1;

			tmp >>= 2;
			hctx->ccid2hctx_rttvar *= 3;
			hctx->ccid2hctx_rttvar >>= 2;
			hctx->ccid2hctx_rttvar += tmp;

			/* SRTT */
			srtt = hctx->ccid2hctx_srtt;
			srtt *= 7;
			srtt >>= 3;
			tmp = r >> 3;
			srtt += tmp;
			ccid2_change_srtt(hctx, srtt);
		}
		s = hctx->ccid2hctx_rttvar << 2;
		/* clock granularity is 1 when based on jiffies */
		if (!s)
			s = 1;
		hctx->ccid2hctx_rto = hctx->ccid2hctx_srtt + s;

		/* must be at least a second */
		s = hctx->ccid2hctx_rto / HZ;
		/* DCCP doesn't require this [but I like it cuz my code sux] */
#if 1
		if (s < 1)
			hctx->ccid2hctx_rto = HZ;
#endif
		/* max 60 seconds */
		if (s > 60)
			hctx->ccid2hctx_rto = HZ * 60;

		hctx->ccid2hctx_lastrtt = jiffies;

		ccid2_pr_debug("srtt: %ld rttvar: %ld rto: %ld (HZ=%d) R=%lu\n",
			       hctx->ccid2hctx_srtt, hctx->ccid2hctx_rttvar,
			       hctx->ccid2hctx_rto, HZ, r);
	}

	/* we got a new ack, so re-start RTO timer */
	ccid2_hc_tx_kill_rto_timer(sk);
	ccid2_start_rto_timer(sk);
}

static void ccid2_hc_tx_dec_pipe(struct sock *sk)
{
	struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);

	if (hctx->ccid2hctx_pipe == 0)
		DCCP_BUG("pipe == 0");
	else
		hctx->ccid2hctx_pipe--;

	if (hctx->ccid2hctx_pipe == 0)
		ccid2_hc_tx_kill_rto_timer(sk);
}

static void ccid2_congestion_event(struct sock *sk, struct ccid2_seq *seqp)
{
	struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);

	if (time_before(seqp->ccid2s_sent, hctx->ccid2hctx_last_cong)) {
		ccid2_pr_debug("Multiple losses in an RTT---treating as one\n");
		return;
	}

	hctx->ccid2hctx_last_cong = jiffies;

	hctx->ccid2hctx_cwnd     = hctx->ccid2hctx_cwnd / 2 ? : 1U;
	hctx->ccid2hctx_ssthresh = max(hctx->ccid2hctx_cwnd, 2U);

	/* Avoid spurious timeouts resulting from Ack Ratio > cwnd */
	if (dccp_sk(sk)->dccps_l_ack_ratio > hctx->ccid2hctx_cwnd)
		ccid2_change_l_ack_ratio(sk, hctx->ccid2hctx_cwnd);
}

static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
{
	struct dccp_sock *dp = dccp_sk(sk);
	struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
	u64 ackno, seqno;
	struct ccid2_seq *seqp;
	unsigned char *vector;
	unsigned char veclen;
	int offset = 0;
	int done = 0;
	unsigned int maxincr = 0;

	ccid2_hc_tx_check_sanity(hctx);
	/* check reverse path congestion */
	seqno = DCCP_SKB_CB(skb)->dccpd_seq;

	/* XXX this whole "algorithm" is broken.  Need to fix it to keep track
	 * of the seqnos of the dupacks so that rpseq and rpdupack are correct
	 * -sorbo.
	 */
	/* need to bootstrap */
	if (hctx->ccid2hctx_rpdupack == -1) {
		hctx->ccid2hctx_rpdupack = 0;
		hctx->ccid2hctx_rpseq = seqno;
	} else {
		/* check if packet is consecutive */
		if (dccp_delta_seqno(hctx->ccid2hctx_rpseq, seqno) == 1)
			hctx->ccid2hctx_rpseq = seqno;
		/* it's a later packet */
		else if (after48(seqno, hctx->ccid2hctx_rpseq)) {
			hctx->ccid2hctx_rpdupack++;

			/* check if we got enough dupacks */
			if (hctx->ccid2hctx_rpdupack >= NUMDUPACK) {
				hctx->ccid2hctx_rpdupack = -1; /* XXX lame */
				hctx->ccid2hctx_rpseq = 0;

				ccid2_change_l_ack_ratio(sk, 2 * dp->dccps_l_ack_ratio);
			}
		}
	}

	/* check forward path congestion */
	/* still didn't send out new data packets */
	if (hctx->ccid2hctx_seqh == hctx->ccid2hctx_seqt)
		return;

	switch (DCCP_SKB_CB(skb)->dccpd_type) {
	case DCCP_PKT_ACK:
	case DCCP_PKT_DATAACK:
		break;
	default:
		return;
	}

	ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq;
	if (after48(ackno, hctx->ccid2hctx_high_ack))
		hctx->ccid2hctx_high_ack = ackno;

	seqp = hctx->ccid2hctx_seqt;
	while (before48(seqp->ccid2s_seq, ackno)) {
		seqp = seqp->ccid2s_next;
		if (seqp == hctx->ccid2hctx_seqh) {
			seqp = hctx->ccid2hctx_seqh->ccid2s_prev;
			break;
		}
	}

	/*
	 * In slow-start, cwnd can increase up to a maximum of Ack Ratio/2
	 * packets per acknowledgement. Rounding up avoids that cwnd is not
	 * advanced when Ack Ratio is 1 and gives a slight edge otherwise.
	 */
	if (hctx->ccid2hctx_cwnd < hctx->ccid2hctx_ssthresh)
		maxincr = DIV_ROUND_UP(dp->dccps_l_ack_ratio, 2);

	/* go through all ack vectors */
	while ((offset = ccid2_ackvector(sk, skb, offset,
					 &vector, &veclen)) != -1) {
		/* go through this ack vector */
		while (veclen--) {
			const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK;
			u64 ackno_end_rl = SUB48(ackno, rl);

			ccid2_pr_debug("ackvec start:%llu end:%llu\n",
				       (unsigned long long)ackno,
				       (unsigned long long)ackno_end_rl);
			/* if the seqno we are analyzing is larger than the
			 * current ackno, then move towards the tail of our
			 * seqnos.
			 */
			while (after48(seqp->ccid2s_seq, ackno)) {
				if (seqp == hctx->ccid2hctx_seqt) {
					done = 1;
					break;
				}
				seqp = seqp->ccid2s_prev;
			}
			if (done)
				break;

			/* check all seqnos in the range of the vector
			 * run length
			 */
			while (between48(seqp->ccid2s_seq,ackno_end_rl,ackno)) {
				const u8 state = *vector &
						 DCCP_ACKVEC_STATE_MASK;

				/* new packet received or marked */
				if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED &&
				    !seqp->ccid2s_acked) {
					if (state ==
					    DCCP_ACKVEC_STATE_ECN_MARKED) {
						ccid2_congestion_event(sk,
								       seqp);
					} else
						ccid2_new_ack(sk, seqp,
							      &maxincr);

					seqp->ccid2s_acked = 1;
					ccid2_pr_debug("Got ack for %llu\n",
						       (unsigned long long)seqp->ccid2s_seq);
					ccid2_hc_tx_dec_pipe(sk);
				}
				if (seqp == hctx->ccid2hctx_seqt) {
					done = 1;
					break;
				}
				seqp = seqp->ccid2s_prev;
			}
			if (done)
				break;

			ackno = SUB48(ackno_end_rl, 1);
			vector++;
		}
		if (done)
			break;
	}

	/* The state about what is acked should be correct now
	 * Check for NUMDUPACK
	 */
	seqp = hctx->ccid2hctx_seqt;
	while (before48(seqp->ccid2s_seq, hctx->ccid2hctx_high_ack)) {
		seqp = seqp->ccid2s_next;
		if (seqp == hctx->ccid2hctx_seqh) {
			seqp = hctx->ccid2hctx_seqh->ccid2s_prev;
			break;
		}
	}
	done = 0;
	while (1) {
		if (seqp->ccid2s_acked) {
			done++;
			if (done == NUMDUPACK)
				break;
		}
		if (seqp == hctx->ccid2hctx_seqt)
			break;
		seqp = seqp->ccid2s_prev;
	}

	/* If there are at least 3 acknowledgements, anything unacknowledged
	 * below the last sequence number is considered lost
	 */
	if (done == NUMDUPACK) {
		struct ccid2_seq *last_acked = seqp;

		/* check for lost packets */
		while (1) {
			if (!seqp->ccid2s_acked) {
				ccid2_pr_debug("Packet lost: %llu\n",
					       (unsigned long long)seqp->ccid2s_seq);
				/* XXX need to traverse from tail -> head in
				 * order to detect multiple congestion events in
				 * one ack vector.
				 */
				ccid2_congestion_event(sk, seqp);
				ccid2_hc_tx_dec_pipe(sk);
			}
			if (seqp == hctx->ccid2hctx_seqt)
				break;
			seqp = seqp->ccid2s_prev;
		}

		hctx->ccid2hctx_seqt = last_acked;
	}

	/* trim acked packets in tail */
	while (hctx->ccid2hctx_seqt != hctx->ccid2hctx_seqh) {
		if (!hctx->ccid2hctx_seqt->ccid2s_acked)
			break;

		hctx->ccid2hctx_seqt = hctx->ccid2hctx_seqt->ccid2s_next;
	}

	ccid2_hc_tx_check_sanity(hctx);
}

static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk)
{
	struct ccid2_hc_tx_sock *hctx = ccid_priv(ccid);
	struct dccp_sock *dp = dccp_sk(sk);
	u32 max_ratio;

	/* RFC 4341, 5: initialise ssthresh to arbitrarily high (max) value */
	hctx->ccid2hctx_ssthresh  = ~0U;

	/*
	 * RFC 4341, 5: "The cwnd parameter is initialized to at most four
	 * packets for new connections, following the rules from [RFC3390]".
	 * We need to convert the bytes of RFC3390 into the packets of RFC 4341.
	 */
	hctx->ccid2hctx_cwnd = clamp(4380U / dp->dccps_mss_cache, 2U, 4U);

	/* Make sure that Ack Ratio is enabled and within bounds. */
	max_ratio = DIV_ROUND_UP(hctx->ccid2hctx_cwnd, 2);
	if (dp->dccps_l_ack_ratio == 0 || dp->dccps_l_ack_ratio > max_ratio)
		dp->dccps_l_ack_ratio = max_ratio;

	/* XXX init ~ to window size... */
	if (ccid2_hc_tx_alloc_seq(hctx))
		return -ENOMEM;

	hctx->ccid2hctx_rto	 = 3 * HZ;
	ccid2_change_srtt(hctx, -1);
	hctx->ccid2hctx_rttvar	 = -1;
	hctx->ccid2hctx_rpdupack = -1;
	hctx->ccid2hctx_last_cong = jiffies;
	setup_timer(&hctx->ccid2hctx_rtotimer, ccid2_hc_tx_rto_expire,
			(unsigned long)sk);

	ccid2_hc_tx_check_sanity(hctx);
	return 0;
}

static void ccid2_hc_tx_exit(struct sock *sk)
{
	struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
	int i;

	ccid2_hc_tx_kill_rto_timer(sk);

	for (i = 0; i < hctx->ccid2hctx_seqbufc; i++)
		kfree(hctx->ccid2hctx_seqbuf[i]);
	hctx->ccid2hctx_seqbufc = 0;
}

static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb)
{
	const struct dccp_sock *dp = dccp_sk(sk);
	struct ccid2_hc_rx_sock *hcrx = ccid2_hc_rx_sk(sk);

	switch (DCCP_SKB_CB(skb)->dccpd_type) {
	case DCCP_PKT_DATA:
	case DCCP_PKT_DATAACK:
		hcrx->ccid2hcrx_data++;
		if (hcrx->ccid2hcrx_data >= dp->dccps_r_ack_ratio) {
			dccp_send_ack(sk);
			hcrx->ccid2hcrx_data = 0;
		}
		break;
	}
}

static struct ccid_operations ccid2 = {
	.ccid_id		= DCCPC_CCID2,
	.ccid_name		= "TCP-like",
	.ccid_owner		= THIS_MODULE,
	.ccid_hc_tx_obj_size	= sizeof(struct ccid2_hc_tx_sock),
	.ccid_hc_tx_init	= ccid2_hc_tx_init,
	.ccid_hc_tx_exit	= ccid2_hc_tx_exit,
	.ccid_hc_tx_send_packet	= ccid2_hc_tx_send_packet,
	.ccid_hc_tx_packet_sent	= ccid2_hc_tx_packet_sent,
	.ccid_hc_tx_packet_recv	= ccid2_hc_tx_packet_recv,
	.ccid_hc_rx_obj_size	= sizeof(struct ccid2_hc_rx_sock),
	.ccid_hc_rx_packet_recv	= ccid2_hc_rx_packet_recv,
};

#ifdef CONFIG_IP_DCCP_CCID2_DEBUG
module_param(ccid2_debug, bool, 0644);
MODULE_PARM_DESC(ccid2_debug, "Enable debug messages");
#endif

static __init int ccid2_module_init(void)
{
	return ccid_register(&ccid2);
}
module_init(ccid2_module_init);

static __exit void ccid2_module_exit(void)
{
	ccid_unregister(&ccid2);
}
module_exit(ccid2_module_exit);

MODULE_AUTHOR("Andrea Bittau <a.bittau@cs.ucl.ac.uk>");
MODULE_DESCRIPTION("DCCP TCP-Like (CCID2) CCID");
MODULE_LICENSE("GPL");
MODULE_ALIAS("net-dccp-ccid-2");
OpenPOWER on IntegriCloud