summaryrefslogtreecommitdiff
path: root/net/dccp/ackvec.c
blob: 64408253b14ea67cfb50a045239d236eedd4f081 (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
/*
 *  net/dccp/ackvec.c
 *
 *  An implementation of the DCCP protocol
 *  Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
 *
 *      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; version 2 of the License;
 */

#include "ackvec.h"
#include "dccp.h"

#include <linux/dccp.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/slab.h>

#include <net/sock.h>

static kmem_cache_t *dccp_ackvec_slab;

int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb)
{
	struct dccp_sock *dp = dccp_sk(sk);
#ifdef CONFIG_IP_DCCP_DEBUG
	const char *debug_prefix = dp->dccps_role == DCCP_ROLE_CLIENT ?
				"CLIENT tx: " : "server tx: ";
#endif
	struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec;
	int len = av->dccpav_vec_len + 2;
	struct timeval now;
	u32 elapsed_time;
	unsigned char *to, *from;

	dccp_timestamp(sk, &now);
	elapsed_time = timeval_delta(&now, &av->dccpav_time) / 10;

	if (elapsed_time != 0)
		dccp_insert_option_elapsed_time(sk, skb, elapsed_time);

	if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN)
		return -1;

	/*
	 * XXX: now we have just one ack vector sent record, so
	 * we have to wait for it to be cleared.
	 *
	 * Of course this is not acceptable, but this is just for
	 * basic testing now.
	 */
	if (av->dccpav_ack_seqno != DCCP_MAX_SEQNO + 1)
		return -1;

	DCCP_SKB_CB(skb)->dccpd_opt_len += len;

	to    = skb_push(skb, len);
	*to++ = DCCPO_ACK_VECTOR_0;
	*to++ = len;

	len  = av->dccpav_vec_len;
	from = av->dccpav_buf + av->dccpav_buf_head;

	/* Check if buf_head wraps */
	if ((int)av->dccpav_buf_head + len > av->dccpav_vec_len) {
		const u32 tailsize = av->dccpav_vec_len - av->dccpav_buf_head;

		memcpy(to, from, tailsize);
		to   += tailsize;
		len  -= tailsize;
		from = av->dccpav_buf;
	}

	memcpy(to, from, len);
	/*
	 *	From draft-ietf-dccp-spec-11.txt:
	 *
	 *	For each acknowledgement it sends, the HC-Receiver will add an
	 *	acknowledgement record.  ack_seqno will equal the HC-Receiver
	 *	sequence number it used for the ack packet; ack_ptr will equal
	 *	buf_head; ack_ackno will equal buf_ackno; and ack_nonce will
	 *	equal buf_nonce.
	 *
	 * This implemention uses just one ack record for now.
	 */
	av->dccpav_ack_seqno = DCCP_SKB_CB(skb)->dccpd_seq;
	av->dccpav_ack_ptr   = av->dccpav_buf_head;
	av->dccpav_ack_ackno = av->dccpav_buf_ackno;
	av->dccpav_ack_nonce = av->dccpav_buf_nonce;
	av->dccpav_sent_len  = av->dccpav_vec_len;

	dccp_pr_debug("%sACK Vector 0, len=%d, ack_seqno=%llu, "
		      "ack_ackno=%llu\n",
		      debug_prefix, av->dccpav_sent_len,
		      (unsigned long long)av->dccpav_ack_seqno,
		      (unsigned long long)av->dccpav_ack_ackno);
	return -1;
}

struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority)
{
	struct dccp_ackvec *av = kmem_cache_alloc(dccp_ackvec_slab, priority);

	if (av != NULL) {
		av->dccpav_buf_head	=
			av->dccpav_buf_tail = DCCP_MAX_ACKVEC_LEN - 1;
		av->dccpav_buf_ackno	=
			av->dccpav_ack_ackno = av->dccpav_ack_seqno = ~0LLU;
		av->dccpav_buf_nonce = av->dccpav_buf_nonce = 0;
		av->dccpav_ack_ptr	= 0;
		av->dccpav_time.tv_sec	= 0;
		av->dccpav_time.tv_usec	= 0;
		av->dccpav_sent_len	= av->dccpav_vec_len = 0;
	}

	return av;
}

void dccp_ackvec_free(struct dccp_ackvec *av)
{
	kmem_cache_free(dccp_ackvec_slab, av);
}

static inline u8 dccp_ackvec_state(const struct dccp_ackvec *av,
				   const u8 index)
{
	return av->dccpav_buf[index] & DCCP_ACKVEC_STATE_MASK;
}

static inline u8 dccp_ackvec_len(const struct dccp_ackvec *av,
				 const u8 index)
{
	return av->dccpav_buf[index] & DCCP_ACKVEC_LEN_MASK;
}

/*
 * If several packets are missing, the HC-Receiver may prefer to enter multiple
 * bytes with run length 0, rather than a single byte with a larger run length;
 * this simplifies table updates if one of the missing packets arrives.
 */
static inline int dccp_ackvec_set_buf_head_state(struct dccp_ackvec *av,
						 const unsigned int packets,
						 const unsigned char state)
{
	unsigned int gap;
	long new_head;

	if (av->dccpav_vec_len + packets > DCCP_MAX_ACKVEC_LEN)
		return -ENOBUFS;

	gap	 = packets - 1;
	new_head = av->dccpav_buf_head - packets;

	if (new_head < 0) {
		if (gap > 0) {
			memset(av->dccpav_buf, DCCP_ACKVEC_STATE_NOT_RECEIVED,
			       gap + new_head + 1);
			gap = -new_head;
		}
		new_head += DCCP_MAX_ACKVEC_LEN;
	} 

	av->dccpav_buf_head = new_head;

	if (gap > 0)
		memset(av->dccpav_buf + av->dccpav_buf_head + 1,
		       DCCP_ACKVEC_STATE_NOT_RECEIVED, gap);

	av->dccpav_buf[av->dccpav_buf_head] = state;
	av->dccpav_vec_len += packets;
	return 0;
}

/*
 * Implements the draft-ietf-dccp-spec-11.txt Appendix A
 */
int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk,
		    const u64 ackno, const u8 state)
{
	/*
	 * Check at the right places if the buffer is full, if it is, tell the
	 * caller to start dropping packets till the HC-Sender acks our ACK
	 * vectors, when we will free up space in dccpav_buf.
	 *
	 * We may well decide to do buffer compression, etc, but for now lets
	 * just drop.
	 *
	 * From Appendix A:
	 *
	 *	Of course, the circular buffer may overflow, either when the
	 *	HC-Sender is sending data at a very high rate, when the
	 *	HC-Receiver's acknowledgements are not reaching the HC-Sender,
	 *	or when the HC-Sender is forgetting to acknowledge those acks
	 *	(so the HC-Receiver is unable to clean up old state). In this
	 *	case, the HC-Receiver should either compress the buffer (by
	 *	increasing run lengths when possible), transfer its state to
	 *	a larger buffer, or, as a last resort, drop all received
	 *	packets, without processing them whatsoever, until its buffer
	 *	shrinks again.
	 */

	/* See if this is the first ackno being inserted */
	if (av->dccpav_vec_len == 0) {
		av->dccpav_buf[av->dccpav_buf_head] = state;
		av->dccpav_vec_len = 1;
	} else if (after48(ackno, av->dccpav_buf_ackno)) {
		const u64 delta = dccp_delta_seqno(av->dccpav_buf_ackno,
						   ackno);

		/*
		 * Look if the state of this packet is the same as the
		 * previous ackno and if so if we can bump the head len.
		 */
		if (delta == 1 &&
		    dccp_ackvec_state(av, av->dccpav_buf_head) == state &&
		    (dccp_ackvec_len(av, av->dccpav_buf_head) <
		     DCCP_ACKVEC_LEN_MASK))
			av->dccpav_buf[av->dccpav_buf_head]++;
		else if (dccp_ackvec_set_buf_head_state(av, delta, state))
			return -ENOBUFS;
	} else {
		/*
		 * A.1.2.  Old Packets
		 *
		 *	When a packet with Sequence Number S arrives, and
		 *	S <= buf_ackno, the HC-Receiver will scan the table
		 *	for the byte corresponding to S. (Indexing structures
		 *	could reduce the complexity of this scan.)
		 */
		u64 delta = dccp_delta_seqno(ackno, av->dccpav_buf_ackno);
		u8 index = av->dccpav_buf_head;

		while (1) {
			const u8 len = dccp_ackvec_len(av, index);
			const u8 state = dccp_ackvec_state(av, index);
			/*
			 * valid packets not yet in dccpav_buf have a reserved
			 * entry, with a len equal to 0.
			 */
			if (state == DCCP_ACKVEC_STATE_NOT_RECEIVED &&
			    len == 0 && delta == 0) { /* Found our
							 reserved seat! */
				dccp_pr_debug("Found %llu reserved seat!\n",
					      (unsigned long long)ackno);
				av->dccpav_buf[index] = state;
				goto out;
			}
			/* len == 0 means one packet */
			if (delta < len + 1)
				goto out_duplicate;

			delta -= len + 1;
			if (++index == DCCP_MAX_ACKVEC_LEN)
				index = 0;
		}
	}

	av->dccpav_buf_ackno = ackno;
	dccp_timestamp(sk, &av->dccpav_time);
out:
	dccp_pr_debug("");
	return 0;

out_duplicate:
	/* Duplicate packet */
	dccp_pr_debug("Received a dup or already considered lost "
		      "packet: %llu\n", (unsigned long long)ackno);
	return -EILSEQ;
}

#ifdef CONFIG_IP_DCCP_DEBUG
void dccp_ackvector_print(const u64 ackno, const unsigned char *vector, int len)
{
	if (!dccp_debug)
		return;

	printk("ACK vector len=%d, ackno=%llu |", len,
	       (unsigned long long)ackno);

	while (len--) {
		const u8 state = (*vector & DCCP_ACKVEC_STATE_MASK) >> 6;
		const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK;

		printk("%d,%d|", state, rl);
		++vector;
	}

	printk("\n");
}

void dccp_ackvec_print(const struct dccp_ackvec *av)
{
	dccp_ackvector_print(av->dccpav_buf_ackno,
			     av->dccpav_buf + av->dccpav_buf_head,
			     av->dccpav_vec_len);
}
#endif

static void dccp_ackvec_throw_away_ack_record(struct dccp_ackvec *av)
{
	/*
	 * As we're keeping track of the ack vector size (dccpav_vec_len) and
	 * the sent ack vector size (dccpav_sent_len) we don't need
	 * dccpav_buf_tail at all, but keep this code here as in the future
	 * we'll implement a vector of ack records, as suggested in
	 * draft-ietf-dccp-spec-11.txt Appendix A. -acme
	 */
#if 0
	u32 new_buf_tail = av->dccpav_ack_ptr + 1;
	if (new_buf_tail >= av->dccpav_vec_len)
		new_buf_tail -= av->dccpav_vec_len;
	av->dccpav_buf_tail = new_buf_tail;
#endif
	av->dccpav_vec_len -= av->dccpav_sent_len;
}

void dccp_ackvec_check_rcv_ackno(struct dccp_ackvec *av, struct sock *sk,
				 const u64 ackno)
{
	/* Check if we actually sent an ACK vector */
	if (av->dccpav_ack_seqno == DCCP_MAX_SEQNO + 1)
		return;

	if (ackno == av->dccpav_ack_seqno) {
#ifdef CONFIG_IP_DCCP_DEBUG
		struct dccp_sock *dp = dccp_sk(sk);
		const char *debug_prefix = dp->dccps_role == DCCP_ROLE_CLIENT ?
					"CLIENT rx ack: " : "server rx ack: ";
#endif
		dccp_pr_debug("%sACK packet 0, len=%d, ack_seqno=%llu, "
			      "ack_ackno=%llu, ACKED!\n",
			      debug_prefix, 1,
			      (unsigned long long)av->dccpav_ack_seqno,
			      (unsigned long long)av->dccpav_ack_ackno);
		dccp_ackvec_throw_away_ack_record(av);
		av->dccpav_ack_seqno = DCCP_MAX_SEQNO + 1;
	}
}

static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av,
					    struct sock *sk, u64 ackno,
					    const unsigned char len,
					    const unsigned char *vector)
{
	unsigned char i;

	/* Check if we actually sent an ACK vector */
	if (av->dccpav_ack_seqno == DCCP_MAX_SEQNO + 1)
		return;
	/*
	 * We're in the receiver half connection, so if the received an ACK
	 * vector ackno (e.g. 50) before dccpav_ack_seqno (e.g. 52), we're
	 * not interested.
	 *
	 * Extra explanation with example:
	 * 
	 * if we received an ACK vector with ackno 50, it can only be acking
	 * 50, 49, 48, etc, not 52 (the seqno for the ACK vector we sent).
	 */
	/* dccp_pr_debug("is %llu < %llu? ", ackno, av->dccpav_ack_seqno); */
	if (before48(ackno, av->dccpav_ack_seqno)) {
		/* dccp_pr_debug_cat("yes\n"); */
		return;
	}
	/* dccp_pr_debug_cat("no\n"); */

	i = len;
	while (i--) {
		const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK;
		u64 ackno_end_rl;

		dccp_set_seqno(&ackno_end_rl, ackno - rl);

		/*
		 * dccp_pr_debug("is %llu <= %llu <= %llu? ", ackno_end_rl,
		 * av->dccpav_ack_seqno, ackno);
		 */
		if (between48(av->dccpav_ack_seqno, ackno_end_rl, ackno)) {
			const u8 state = (*vector &
					  DCCP_ACKVEC_STATE_MASK) >> 6;
			/* dccp_pr_debug_cat("yes\n"); */

			if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED) {
#ifdef CONFIG_IP_DCCP_DEBUG
				struct dccp_sock *dp = dccp_sk(sk);
				const char *debug_prefix =
					dp->dccps_role == DCCP_ROLE_CLIENT ?
					"CLIENT rx ack: " : "server rx ack: ";
#endif
				dccp_pr_debug("%sACK vector 0, len=%d, "
					      "ack_seqno=%llu, ack_ackno=%llu, "
					      "ACKED!\n",
					      debug_prefix, len,
					      (unsigned long long)
					      av->dccpav_ack_seqno,
					      (unsigned long long)
					      av->dccpav_ack_ackno);
				dccp_ackvec_throw_away_ack_record(av);
			}
			/*
			 * If dccpav_ack_seqno was not received, no problem
			 * we'll send another ACK vector.
			 */
			av->dccpav_ack_seqno = DCCP_MAX_SEQNO + 1;
			break;
		}
		/* dccp_pr_debug_cat("no\n"); */

		dccp_set_seqno(&ackno, ackno_end_rl - 1);
		++vector;
	}
}

int dccp_ackvec_parse(struct sock *sk, const struct sk_buff *skb,
		      const u8 opt, const u8 *value, const u8 len)
{
	if (len > DCCP_MAX_ACKVEC_LEN)
		return -1;

	/* dccp_ackvector_print(DCCP_SKB_CB(skb)->dccpd_ack_seq, value, len); */
	dccp_ackvec_check_rcv_ackvector(dccp_sk(sk)->dccps_hc_rx_ackvec, sk,
					DCCP_SKB_CB(skb)->dccpd_ack_seq,
				        len, value);
	return 0;
}

static char dccp_ackvec_slab_msg[] __initdata =
	KERN_CRIT "DCCP: Unable to create ack vectors slab cache\n";

int __init dccp_ackvec_init(void)
{
	dccp_ackvec_slab = kmem_cache_create("dccp_ackvec",
					     sizeof(struct dccp_ackvec), 0,
					     SLAB_HWCACHE_ALIGN, NULL, NULL);
	if (dccp_ackvec_slab == NULL) {
		printk(dccp_ackvec_slab_msg);
		return -ENOBUFS;
	}

	return 0;
}

void dccp_ackvec_exit(void)
{
	if (dccp_ackvec_slab != NULL) {
		kmem_cache_destroy(dccp_ackvec_slab);
		dccp_ackvec_slab = NULL;
	}
}