summaryrefslogtreecommitdiffstats
path: root/net/dccp/ackvec.c
blob: af976fca407ab38d38999c08e09a31c485f17aed (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
/*
 *  net/dccp/ackvec.c
 *
 *  An implementation of Ack Vectors for the DCCP protocol
 *  Copyright (c) 2007 University of Aberdeen, Scotland, UK
 *  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/init.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/slab.h>

#include <net/sock.h>

static struct kmem_cache *dccp_ackvec_slab;
static struct kmem_cache *dccp_ackvec_record_slab;

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

	if (av != NULL) {
		av->av_buf_head	= DCCPAV_MAX_ACKVEC_LEN - 1;
		INIT_LIST_HEAD(&av->av_records);
	}
	return av;
}

static void dccp_ackvec_purge_records(struct dccp_ackvec *av)
{
	struct dccp_ackvec_record *cur, *next;

	list_for_each_entry_safe(cur, next, &av->av_records, avr_node)
		kmem_cache_free(dccp_ackvec_record_slab, cur);
	INIT_LIST_HEAD(&av->av_records);
}

void dccp_ackvec_free(struct dccp_ackvec *av)
{
	if (likely(av != NULL)) {
		dccp_ackvec_purge_records(av);
		kmem_cache_free(dccp_ackvec_slab, av);
	}
}

/**
 * dccp_ackvec_update_records  -  Record information about sent Ack Vectors
 * @av:		Ack Vector records to update
 * @seqno:	Sequence number of the packet carrying the Ack Vector just sent
 * @nonce_sum:	The sum of all buffer nonces contained in the Ack Vector
 */
int dccp_ackvec_update_records(struct dccp_ackvec *av, u64 seqno, u8 nonce_sum)
{
	struct dccp_ackvec_record *avr;

	avr = kmem_cache_alloc(dccp_ackvec_record_slab, GFP_ATOMIC);
	if (avr == NULL)
		return -ENOBUFS;

	avr->avr_ack_seqno  = seqno;
	avr->avr_ack_ptr    = av->av_buf_head;
	avr->avr_ack_ackno  = av->av_buf_ackno;
	avr->avr_ack_nonce  = nonce_sum;
	avr->avr_ack_runlen = dccp_ackvec_runlen(av->av_buf + av->av_buf_head);
	/*
	 * Since GSS is incremented for each packet, the list is automatically
	 * arranged in descending order of @ack_seqno.
	 */
	list_add(&avr->avr_node, &av->av_records);

	dccp_pr_debug("Added Vector, ack_seqno=%llu, ack_ackno=%llu (rl=%u)\n",
		      (unsigned long long)avr->avr_ack_seqno,
		      (unsigned long long)avr->avr_ack_ackno,
		      avr->avr_ack_runlen);
	return 0;
}

/*
 * 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)
{
	long gap;
	long new_head;

	if (av->av_vec_len + packets > DCCPAV_MAX_ACKVEC_LEN)
		return -ENOBUFS;

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

	if (new_head < 0) {
		if (gap > 0) {
			memset(av->av_buf, DCCPAV_NOT_RECEIVED,
			       gap + new_head + 1);
			gap = -new_head;
		}
		new_head += DCCPAV_MAX_ACKVEC_LEN;
	}

	av->av_buf_head = new_head;

	if (gap > 0)
		memset(av->av_buf + av->av_buf_head + 1,
		       DCCPAV_NOT_RECEIVED, gap);

	av->av_buf[av->av_buf_head] = state;
	av->av_vec_len += packets;
	return 0;
}

/*
 * Implements the RFC 4340, Appendix A
 */
int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk,
		    const u64 ackno, const u8 state)
{
	u8 *cur_head = av->av_buf + av->av_buf_head,
	   *buf_end  = av->av_buf + DCCPAV_MAX_ACKVEC_LEN;
	/*
	 * 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 av_buf.
	 *
	 * We may well decide to do buffer compression, etc, but for now lets
	 * just drop.
	 *
	 * From Appendix A.1.1 (`New Packets'):
	 *
	 *	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->av_vec_len == 0) {
		*cur_head = state;
		av->av_vec_len = 1;
	} else if (after48(ackno, av->av_buf_ackno)) {
		const u64 delta = dccp_delta_seqno(av->av_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(cur_head) == state &&
		    dccp_ackvec_runlen(cur_head) < DCCPAV_MAX_RUNLEN)
			*cur_head += 1;
		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 <= buf_ackno
		 *	arrives, 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->av_buf_ackno);

		while (1) {
			const u8 len = dccp_ackvec_runlen(cur_head);
			/*
			 * valid packets not yet in av_buf have a reserved
			 * entry, with a len equal to 0.
			 */
			if (*cur_head == DCCPAV_NOT_RECEIVED && delta == 0) {
				dccp_pr_debug("Found %llu reserved seat!\n",
					      (unsigned long long)ackno);
				*cur_head = state;
				goto out;
			}
			/* len == 0 means one packet */
			if (delta < len + 1)
				goto out_duplicate;

			delta -= len + 1;
			if (++cur_head == buf_end)
				cur_head = av->av_buf;
		}
	}

	av->av_buf_ackno = ackno;
out:
	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;
}

static void dccp_ackvec_throw_record(struct dccp_ackvec *av,
				     struct dccp_ackvec_record *avr)
{
	struct dccp_ackvec_record *next;

	/* sort out vector length */
	if (av->av_buf_head <= avr->avr_ack_ptr)
		av->av_vec_len = avr->avr_ack_ptr - av->av_buf_head;
	else
		av->av_vec_len = DCCPAV_MAX_ACKVEC_LEN - 1 -
				 av->av_buf_head + avr->avr_ack_ptr;

	/* free records */
	list_for_each_entry_safe_from(avr, next, &av->av_records, avr_node) {
		list_del(&avr->avr_node);
		kmem_cache_free(dccp_ackvec_record_slab, avr);
	}
}

void dccp_ackvec_check_rcv_ackno(struct dccp_ackvec *av, struct sock *sk,
				 const u64 ackno)
{
	struct dccp_ackvec_record *avr;

	/*
	 * If we traverse backwards, it should be faster when we have large
	 * windows. We will be receiving ACKs for stuff we sent a while back
	 * -sorbo.
	 */
	list_for_each_entry_reverse(avr, &av->av_records, avr_node) {
		if (ackno == avr->avr_ack_seqno) {
			dccp_pr_debug("%s ACK packet 0, len=%d, ack_seqno=%llu, "
				      "ack_ackno=%llu, ACKED!\n",
				      dccp_role(sk), avr->avr_ack_runlen,
				      (unsigned long long)avr->avr_ack_seqno,
				      (unsigned long long)avr->avr_ack_ackno);
			dccp_ackvec_throw_record(av, avr);
			break;
		} else if (avr->avr_ack_seqno > ackno)
			break; /* old news */
	}
}

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;
	struct dccp_ackvec_record *avr;

	/* Check if we actually sent an ACK vector */
	if (list_empty(&av->av_records))
		return;

	i = len;
	/*
	 * XXX
	 * I think it might be more efficient to work backwards. See comment on
	 * rcv_ackno. -sorbo.
	 */
	avr = list_entry(av->av_records.next, struct dccp_ackvec_record, avr_node);
	while (i--) {
		const u8 rl = dccp_ackvec_runlen(vector);
		u64 ackno_end_rl;

		dccp_set_seqno(&ackno_end_rl, *ackno - rl);

		/*
		 * If our AVR sequence number is greater than the ack, go
		 * forward in the AVR list until it is not so.
		 */
		list_for_each_entry_from(avr, &av->av_records, avr_node) {
			if (!after48(avr->avr_ack_seqno, *ackno))
				goto found;
		}
		/* End of the av_records list, not found, exit */
		break;
found:
		if (between48(avr->avr_ack_seqno, ackno_end_rl, *ackno)) {
			if (dccp_ackvec_state(vector) != DCCPAV_NOT_RECEIVED) {
				dccp_pr_debug("%s ACK vector 0, len=%d, "
					      "ack_seqno=%llu, ack_ackno=%llu, "
					      "ACKED!\n",
					      dccp_role(sk), len,
					      (unsigned long long)
					      avr->avr_ack_seqno,
					      (unsigned long long)
					      avr->avr_ack_ackno);
				dccp_ackvec_throw_record(av, avr);
				break;
			}
			/*
			 * If it wasn't received, continue scanning... we might
			 * find another one.
			 */
		}

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

int dccp_ackvec_parse(struct sock *sk, const struct sk_buff *skb,
		      u64 *ackno, const u8 opt, const u8 *value, const u8 len)
{
	if (len > DCCP_SINGLE_OPT_MAXLEN)
		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,
					ackno, len, value);
	return 0;
}

int __init dccp_ackvec_init(void)
{
	dccp_ackvec_slab = kmem_cache_create("dccp_ackvec",
					     sizeof(struct dccp_ackvec), 0,
					     SLAB_HWCACHE_ALIGN, NULL);
	if (dccp_ackvec_slab == NULL)
		goto out_err;

	dccp_ackvec_record_slab = kmem_cache_create("dccp_ackvec_record",
					     sizeof(struct dccp_ackvec_record),
					     0, SLAB_HWCACHE_ALIGN, NULL);
	if (dccp_ackvec_record_slab == NULL)
		goto out_destroy_slab;

	return 0;

out_destroy_slab:
	kmem_cache_destroy(dccp_ackvec_slab);
	dccp_ackvec_slab = NULL;
out_err:
	DCCP_CRIT("Unable to create Ack Vector slab cache");
	return -ENOBUFS;
}

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