outqueue.c 52 KB
Newer Older
1
/* SCTP kernel implementation
Linus Torvalds's avatar
Linus Torvalds committed
2
3
4
5
6
 * (C) Copyright IBM Corp. 2001, 2004
 * Copyright (c) 1999-2000 Cisco, Inc.
 * Copyright (c) 1999-2001 Motorola, Inc.
 * Copyright (c) 2001-2003 Intel Corp.
 *
7
 * This file is part of the SCTP kernel implementation
Linus Torvalds's avatar
Linus Torvalds committed
8
9
10
11
 *
 * These functions implement the sctp_outq class.   The outqueue handles
 * bundling and queueing of outgoing SCTP chunks.
 *
12
 * This SCTP implementation is free software;
Linus Torvalds's avatar
Linus Torvalds committed
13
14
15
16
17
 * 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, or (at your option)
 * any later version.
 *
18
 * This SCTP implementation is distributed in the hope that it
Linus Torvalds's avatar
Linus Torvalds committed
19
20
21
22
23
24
 * 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
25
26
 * along with GNU CC; see the file COPYING.  If not, see
 * <http://www.gnu.org/licenses/>.
Linus Torvalds's avatar
Linus Torvalds committed
27
28
29
 *
 * Please send any bug reports or fixes you make to the
 * email address(es):
30
 *    lksctp developers <linux-sctp@vger.kernel.org>
Linus Torvalds's avatar
Linus Torvalds committed
31
32
33
34
35
36
37
38
39
40
41
 *
 * Written or modified by:
 *    La Monte H.P. Yarroll <piggy@acm.org>
 *    Karl Knutson          <karl@athena.chicago.il.us>
 *    Perry Melange         <pmelange@null.cc.uic.edu>
 *    Xingang Guo           <xingang.guo@intel.com>
 *    Hui Huang 	    <hui.huang@nokia.com>
 *    Sridhar Samudrala     <sri@us.ibm.com>
 *    Jon Grimm             <jgrimm@us.ibm.com>
 */

42
43
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

Linus Torvalds's avatar
Linus Torvalds committed
44
45
46
47
#include <linux/types.h>
#include <linux/list.h>   /* For struct list_head */
#include <linux/socket.h>
#include <linux/ip.h>
48
#include <linux/slab.h>
Linus Torvalds's avatar
Linus Torvalds committed
49
50
51
52
53
54
55
56
57
58
#include <net/sock.h>	  /* For skb_set_owner_w */

#include <net/sctp/sctp.h>
#include <net/sctp/sm.h>

/* Declare internal functions here.  */
static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn);
static void sctp_check_transmitted(struct sctp_outq *q,
				   struct list_head *transmitted_queue,
				   struct sctp_transport *transport,
59
				   union sctp_addr *saddr,
Linus Torvalds's avatar
Linus Torvalds committed
60
				   struct sctp_sackhdr *sack,
61
				   __u32 *highest_new_tsn);
Linus Torvalds's avatar
Linus Torvalds committed
62
63
64
65
66
67
68
69
70

static void sctp_mark_missing(struct sctp_outq *q,
			      struct list_head *transmitted_queue,
			      struct sctp_transport *transport,
			      __u32 highest_new_tsn,
			      int count_of_newacks);

static void sctp_generate_fwdtsn(struct sctp_outq *q, __u32 sack_ctsn);

71
72
static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout);

Linus Torvalds's avatar
Linus Torvalds committed
73
74
75
76
/* Add data to the front of the queue. */
static inline void sctp_outq_head_data(struct sctp_outq *q,
					struct sctp_chunk *ch)
{
77
	list_add(&ch->list, &q->out_chunk_list);
Linus Torvalds's avatar
Linus Torvalds committed
78
79
80
81
82
83
	q->out_qlen += ch->skb->len;
}

/* Take data from the front of the queue. */
static inline struct sctp_chunk *sctp_outq_dequeue_data(struct sctp_outq *q)
{
84
85
86
87
88
89
90
	struct sctp_chunk *ch = NULL;

	if (!list_empty(&q->out_chunk_list)) {
		struct list_head *entry = q->out_chunk_list.next;

		ch = list_entry(entry, struct sctp_chunk, list);
		list_del_init(entry);
Linus Torvalds's avatar
Linus Torvalds committed
91
		q->out_qlen -= ch->skb->len;
92
	}
Linus Torvalds's avatar
Linus Torvalds committed
93
94
95
96
97
98
	return ch;
}
/* Add data chunk to the end of the queue. */
static inline void sctp_outq_tail_data(struct sctp_outq *q,
				       struct sctp_chunk *ch)
{
99
	list_add_tail(&ch->list, &q->out_chunk_list);
Linus Torvalds's avatar
Linus Torvalds committed
100
101
102
103
104
105
106
107
108
109
110
111
112
	q->out_qlen += ch->skb->len;
}

/*
 * SFR-CACC algorithm:
 * D) If count_of_newacks is greater than or equal to 2
 * and t was not sent to the current primary then the
 * sender MUST NOT increment missing report count for t.
 */
static inline int sctp_cacc_skip_3_1_d(struct sctp_transport *primary,
				       struct sctp_transport *transport,
				       int count_of_newacks)
{
113
	if (count_of_newacks >= 2 && transport != primary)
Linus Torvalds's avatar
Linus Torvalds committed
114
115
116
117
118
119
120
121
122
123
124
125
126
127
		return 1;
	return 0;
}

/*
 * SFR-CACC algorithm:
 * F) If count_of_newacks is less than 2, let d be the
 * destination to which t was sent. If cacc_saw_newack
 * is 0 for destination d, then the sender MUST NOT
 * increment missing report count for t.
 */
static inline int sctp_cacc_skip_3_1_f(struct sctp_transport *transport,
				       int count_of_newacks)
{
128
129
	if (count_of_newacks < 2 &&
			(transport && !transport->cacc.cacc_saw_newack))
Linus Torvalds's avatar
Linus Torvalds committed
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
		return 1;
	return 0;
}

/*
 * SFR-CACC algorithm:
 * 3.1) If CYCLING_CHANGEOVER is 0, the sender SHOULD
 * execute steps C, D, F.
 *
 * C has been implemented in sctp_outq_sack
 */
static inline int sctp_cacc_skip_3_1(struct sctp_transport *primary,
				     struct sctp_transport *transport,
				     int count_of_newacks)
{
	if (!primary->cacc.cycling_changeover) {
		if (sctp_cacc_skip_3_1_d(primary, transport, count_of_newacks))
			return 1;
		if (sctp_cacc_skip_3_1_f(transport, count_of_newacks))
			return 1;
		return 0;
	}
	return 0;
}

/*
 * SFR-CACC algorithm:
 * 3.2) Else if CYCLING_CHANGEOVER is 1, and t is less
 * than next_tsn_at_change of the current primary, then
 * the sender MUST NOT increment missing report count
 * for t.
 */
static inline int sctp_cacc_skip_3_2(struct sctp_transport *primary, __u32 tsn)
{
	if (primary->cacc.cycling_changeover &&
	    TSN_lt(tsn, primary->cacc.next_tsn_at_change))
		return 1;
	return 0;
}

/*
 * SFR-CACC algorithm:
 * 3) If the missing report count for TSN t is to be
 * incremented according to [RFC2960] and
 * [SCTP_STEWART-2002], and CHANGEOVER_ACTIVE is set,
Lucas De Marchi's avatar
Lucas De Marchi committed
175
 * then the sender MUST further execute steps 3.1 and
Linus Torvalds's avatar
Linus Torvalds committed
176
177
178
179
180
 * 3.2 to determine if the missing report count for
 * TSN t SHOULD NOT be incremented.
 *
 * 3.3) If 3.1 and 3.2 do not dictate that the missing
 * report count for t should not be incremented, then
Lucas De Marchi's avatar
Lucas De Marchi committed
181
 * the sender SHOULD increment missing report count for
Linus Torvalds's avatar
Linus Torvalds committed
182
183
184
185
186
187
188
189
 * t (according to [RFC2960] and [SCTP_STEWART_2002]).
 */
static inline int sctp_cacc_skip(struct sctp_transport *primary,
				 struct sctp_transport *transport,
				 int count_of_newacks,
				 __u32 tsn)
{
	if (primary->cacc.changeover_active &&
190
191
	    (sctp_cacc_skip_3_1(primary, transport, count_of_newacks) ||
	     sctp_cacc_skip_3_2(primary, tsn)))
Linus Torvalds's avatar
Linus Torvalds committed
192
193
194
195
196
197
198
199
200
201
		return 1;
	return 0;
}

/* Initialize an existing sctp_outq.  This does the boring stuff.
 * You still need to define handlers if you really want to DO
 * something with this structure...
 */
void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q)
{
202
203
	memset(q, 0, sizeof(struct sctp_outq));

Linus Torvalds's avatar
Linus Torvalds committed
204
	q->asoc = asoc;
205
206
	INIT_LIST_HEAD(&q->out_chunk_list);
	INIT_LIST_HEAD(&q->control_chunk_list);
Linus Torvalds's avatar
Linus Torvalds committed
207
208
209
210
211
212
213
	INIT_LIST_HEAD(&q->retransmit);
	INIT_LIST_HEAD(&q->sacked);
	INIT_LIST_HEAD(&q->abandoned);
}

/* Free the outqueue structure and any related pending chunks.
 */
214
static void __sctp_outq_teardown(struct sctp_outq *q)
Linus Torvalds's avatar
Linus Torvalds committed
215
216
{
	struct sctp_transport *transport;
217
	struct list_head *lchunk, *temp;
218
	struct sctp_chunk *chunk, *tmp;
Linus Torvalds's avatar
Linus Torvalds committed
219
220

	/* Throw away unacknowledged chunks. */
221
222
	list_for_each_entry(transport, &q->asoc->peer.transport_addr_list,
			transports) {
Linus Torvalds's avatar
Linus Torvalds committed
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
		while ((lchunk = sctp_list_dequeue(&transport->transmitted)) != NULL) {
			chunk = list_entry(lchunk, struct sctp_chunk,
					   transmitted_list);
			/* Mark as part of a failed message. */
			sctp_chunk_fail(chunk, q->error);
			sctp_chunk_free(chunk);
		}
	}

	/* Throw away chunks that have been gap ACKed.  */
	list_for_each_safe(lchunk, temp, &q->sacked) {
		list_del_init(lchunk);
		chunk = list_entry(lchunk, struct sctp_chunk,
				   transmitted_list);
		sctp_chunk_fail(chunk, q->error);
		sctp_chunk_free(chunk);
	}

	/* Throw away any chunks in the retransmit queue. */
	list_for_each_safe(lchunk, temp, &q->retransmit) {
		list_del_init(lchunk);
		chunk = list_entry(lchunk, struct sctp_chunk,
				   transmitted_list);
		sctp_chunk_fail(chunk, q->error);
		sctp_chunk_free(chunk);
	}

	/* Throw away any chunks that are in the abandoned queue. */
	list_for_each_safe(lchunk, temp, &q->abandoned) {
		list_del_init(lchunk);
		chunk = list_entry(lchunk, struct sctp_chunk,
				   transmitted_list);
		sctp_chunk_fail(chunk, q->error);
		sctp_chunk_free(chunk);
	}

	/* Throw away any leftover data chunks. */
	while ((chunk = sctp_outq_dequeue_data(q)) != NULL) {

		/* Mark as send failure. */
		sctp_chunk_fail(chunk, q->error);
		sctp_chunk_free(chunk);
	}

	/* Throw away any leftover control chunks. */
268
269
	list_for_each_entry_safe(chunk, tmp, &q->control_chunk_list, list) {
		list_del_init(&chunk->list);
Linus Torvalds's avatar
Linus Torvalds committed
270
		sctp_chunk_free(chunk);
271
	}
Linus Torvalds's avatar
Linus Torvalds committed
272
273
}

274
275
276
277
278
279
void sctp_outq_teardown(struct sctp_outq *q)
{
	__sctp_outq_teardown(q);
	sctp_outq_init(q->asoc, q);
}

Linus Torvalds's avatar
Linus Torvalds committed
280
281
282
283
/* Free the outqueue structure and any related pending chunks.  */
void sctp_outq_free(struct sctp_outq *q)
{
	/* Throw away leftover chunks. */
284
	__sctp_outq_teardown(q);
Linus Torvalds's avatar
Linus Torvalds committed
285
286
287
288
289
}

/* Put a new chunk in an sctp_outq.  */
int sctp_outq_tail(struct sctp_outq *q, struct sctp_chunk *chunk)
{
290
	struct net *net = sock_net(q->asoc->base.sk);
Linus Torvalds's avatar
Linus Torvalds committed
291
292
	int error = 0;

293
294
295
296
	pr_debug("%s: outq:%p, chunk:%p[%s]\n", __func__, q, chunk,
		 chunk && chunk->chunk_hdr ?
		 sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) :
		 "illegal chunk");
Linus Torvalds's avatar
Linus Torvalds committed
297
298
299
300

	/* If it is data, queue it up, otherwise, send it
	 * immediately.
	 */
301
	if (sctp_chunk_is_data(chunk)) {
Linus Torvalds's avatar
Linus Torvalds committed
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
		/* Is it OK to queue data chunks?  */
		/* From 9. Termination of Association
		 *
		 * When either endpoint performs a shutdown, the
		 * association on each peer will stop accepting new
		 * data from its user and only deliver data in queue
		 * at the time of sending or receiving the SHUTDOWN
		 * chunk.
		 */
		switch (q->asoc->state) {
		case SCTP_STATE_CLOSED:
		case SCTP_STATE_SHUTDOWN_PENDING:
		case SCTP_STATE_SHUTDOWN_SENT:
		case SCTP_STATE_SHUTDOWN_RECEIVED:
		case SCTP_STATE_SHUTDOWN_ACK_SENT:
			/* Cannot send after transport endpoint shutdown */
			error = -ESHUTDOWN;
			break;

		default:
322
323
324
325
			pr_debug("%s: outqueueing: outq:%p, chunk:%p[%s])\n",
				 __func__, q, chunk, chunk && chunk->chunk_hdr ?
				 sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) :
				 "illegal chunk");
Linus Torvalds's avatar
Linus Torvalds committed
326

327
			sctp_chunk_hold(chunk);
Linus Torvalds's avatar
Linus Torvalds committed
328
329
			sctp_outq_tail_data(q, chunk);
			if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED)
330
				SCTP_INC_STATS(net, SCTP_MIB_OUTUNORDERCHUNKS);
Linus Torvalds's avatar
Linus Torvalds committed
331
			else
332
				SCTP_INC_STATS(net, SCTP_MIB_OUTORDERCHUNKS);
Linus Torvalds's avatar
Linus Torvalds committed
333
			break;
334
		}
Linus Torvalds's avatar
Linus Torvalds committed
335
	} else {
336
		list_add_tail(&chunk->list, &q->control_chunk_list);
337
		SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS);
Linus Torvalds's avatar
Linus Torvalds committed
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
	}

	if (error < 0)
		return error;

	if (!q->cork)
		error = sctp_outq_flush(q, 0);

	return error;
}

/* Insert a chunk into the sorted list based on the TSNs.  The retransmit list
 * and the abandoned list are in ascending order.
 */
static void sctp_insert_list(struct list_head *head, struct list_head *new)
{
	struct list_head *pos;
	struct sctp_chunk *nchunk, *lchunk;
	__u32 ntsn, ltsn;
	int done = 0;

	nchunk = list_entry(new, struct sctp_chunk, transmitted_list);
	ntsn = ntohl(nchunk->subh.data_hdr->tsn);

	list_for_each(pos, head) {
		lchunk = list_entry(pos, struct sctp_chunk, transmitted_list);
		ltsn = ntohl(lchunk->subh.data_hdr->tsn);
		if (TSN_lt(ntsn, ltsn)) {
			list_add(new, pos->prev);
			done = 1;
			break;
		}
	}
	if (!done)
372
		list_add_tail(new, head);
Linus Torvalds's avatar
Linus Torvalds committed
373
374
375
376
377
}

/* Mark all the eligible packets on a transport for retransmission.  */
void sctp_retransmit_mark(struct sctp_outq *q,
			  struct sctp_transport *transport,
378
			  __u8 reason)
Linus Torvalds's avatar
Linus Torvalds committed
379
380
381
382
383
384
385
386
387
388
389
390
391
{
	struct list_head *lchunk, *ltemp;
	struct sctp_chunk *chunk;

	/* Walk through the specified transmitted queue.  */
	list_for_each_safe(lchunk, ltemp, &transport->transmitted) {
		chunk = list_entry(lchunk, struct sctp_chunk,
				   transmitted_list);

		/* If the chunk is abandoned, move it to abandoned list. */
		if (sctp_chunk_abandoned(chunk)) {
			list_del_init(lchunk);
			sctp_insert_list(&q->abandoned, lchunk);
392
393
394
395
396
397
398

			/* If this chunk has not been previousely acked,
			 * stop considering it 'outstanding'.  Our peer
			 * will most likely never see it since it will
			 * not be retransmitted
			 */
			if (!chunk->tsn_gap_acked) {
399
400
401
				if (chunk->transport)
					chunk->transport->flight_size -=
							sctp_data_size(chunk);
402
				q->outstanding_bytes -= sctp_data_size(chunk);
403
				q->asoc->peer.rwnd += sctp_data_size(chunk);
404
			}
Linus Torvalds's avatar
Linus Torvalds committed
405
406
407
			continue;
		}

408
409
410
		/* If we are doing  retransmission due to a timeout or pmtu
		 * discovery, only the  chunks that are not yet acked should
		 * be added to the retransmit queue.
Linus Torvalds's avatar
Linus Torvalds committed
411
		 */
412
		if ((reason == SCTP_RTXR_FAST_RTX  &&
413
			    (chunk->fast_retransmit == SCTP_NEED_FRTX)) ||
414
		    (reason != SCTP_RTXR_FAST_RTX  && !chunk->tsn_gap_acked)) {
Linus Torvalds's avatar
Linus Torvalds committed
415
416
417
418
419
420
421
422
			/* RFC 2960 6.2.1 Processing a Received SACK
			 *
			 * C) Any time a DATA chunk is marked for
			 * retransmission (via either T3-rtx timer expiration
			 * (Section 6.3.3) or via fast retransmit
			 * (Section 7.2.4)), add the data size of those
			 * chunks to the rwnd.
			 */
423
			q->asoc->peer.rwnd += sctp_data_size(chunk);
Linus Torvalds's avatar
Linus Torvalds committed
424
			q->outstanding_bytes -= sctp_data_size(chunk);
425
426
			if (chunk->transport)
				transport->flight_size -= sctp_data_size(chunk);
Linus Torvalds's avatar
Linus Torvalds committed
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445

			/* sctpimpguide-05 Section 2.8.2
			 * M5) If a T3-rtx timer expires, the
			 * 'TSN.Missing.Report' of all affected TSNs is set
			 * to 0.
			 */
			chunk->tsn_missing_report = 0;

			/* If a chunk that is being used for RTT measurement
			 * has to be retransmitted, we cannot use this chunk
			 * anymore for RTT measurements. Reset rto_pending so
			 * that a new RTT measurement is started when a new
			 * data chunk is sent.
			 */
			if (chunk->rtt_in_progress) {
				chunk->rtt_in_progress = 0;
				transport->rto_pending = 0;
			}

446
447
			chunk->resent = 1;

Linus Torvalds's avatar
Linus Torvalds committed
448
449
450
451
452
453
454
455
			/* Move the chunk to the retransmit queue. The chunks
			 * on the retransmit queue are always kept in order.
			 */
			list_del_init(lchunk);
			sctp_insert_list(&q->retransmit, lchunk);
		}
	}

456
457
458
459
	pr_debug("%s: transport:%p, reason:%d, cwnd:%d, ssthresh:%d, "
		 "flight_size:%d, pba:%d\n", __func__, transport, reason,
		 transport->cwnd, transport->ssthresh, transport->flight_size,
		 transport->partial_bytes_acked);
Linus Torvalds's avatar
Linus Torvalds committed
460
461
462
463
464
465
466
467
}

/* Mark all the eligible packets on a transport for retransmission and force
 * one packet out.
 */
void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport,
		     sctp_retransmit_reason_t reason)
{
468
	struct net *net = sock_net(q->asoc->base.sk);
Linus Torvalds's avatar
Linus Torvalds committed
469
470
	int error = 0;

471
	switch (reason) {
Linus Torvalds's avatar
Linus Torvalds committed
472
	case SCTP_RTXR_T3_RTX:
473
		SCTP_INC_STATS(net, SCTP_MIB_T3_RETRANSMITS);
Linus Torvalds's avatar
Linus Torvalds committed
474
475
476
477
478
479
		sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_T3_RTX);
		/* Update the retran path if the T3-rtx timer has expired for
		 * the current retran path.
		 */
		if (transport == transport->asoc->peer.retran_path)
			sctp_assoc_update_retran_path(transport->asoc);
480
481
		transport->asoc->rtx_data_chunks +=
			transport->asoc->unack_data;
Linus Torvalds's avatar
Linus Torvalds committed
482
483
		break;
	case SCTP_RTXR_FAST_RTX:
484
		SCTP_INC_STATS(net, SCTP_MIB_FAST_RETRANSMITS);
Linus Torvalds's avatar
Linus Torvalds committed
485
		sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_FAST_RTX);
486
		q->fast_rtx = 1;
Linus Torvalds's avatar
Linus Torvalds committed
487
488
		break;
	case SCTP_RTXR_PMTUD:
489
		SCTP_INC_STATS(net, SCTP_MIB_PMTUD_RETRANSMITS);
Linus Torvalds's avatar
Linus Torvalds committed
490
		break;
491
	case SCTP_RTXR_T1_RTX:
492
		SCTP_INC_STATS(net, SCTP_MIB_T1_RETRANSMITS);
493
		transport->asoc->init_retries++;
494
		break;
495
496
	default:
		BUG();
Linus Torvalds's avatar
Linus Torvalds committed
497
498
	}

499
	sctp_retransmit_mark(q, transport, reason);
Linus Torvalds's avatar
Linus Torvalds committed
500
501
502
503
504

	/* PR-SCTP A5) Any time the T3-rtx timer expires, on any destination,
	 * the sender SHOULD try to advance the "Advanced.Peer.Ack.Point" by
	 * following the procedures outlined in C1 - C5.
	 */
505
506
	if (reason == SCTP_RTXR_T3_RTX)
		sctp_generate_fwdtsn(q, q->asoc->ctsn_ack_point);
Linus Torvalds's avatar
Linus Torvalds committed
507

508
509
510
511
512
513
	/* Flush the queues only on timeout, since fast_rtx is only
	 * triggered during sack processing and the queue
	 * will be flushed at the end.
	 */
	if (reason != SCTP_RTXR_FAST_RTX)
		error = sctp_outq_flush(q, /* rtx_timeout */ 1);
Linus Torvalds's avatar
Linus Torvalds committed
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533

	if (error)
		q->asoc->base.sk->sk_err = -error;
}

/*
 * Transmit DATA chunks on the retransmit queue.  Upon return from
 * sctp_outq_flush_rtx() the packet 'pkt' may contain chunks which
 * need to be transmitted by the caller.
 * We assume that pkt->transport has already been set.
 *
 * The return value is a normal kernel error return value.
 */
static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
			       int rtx_timeout, int *start_timer)
{
	struct list_head *lqueue;
	struct sctp_transport *transport = pkt->transport;
	sctp_xmit_t status;
	struct sctp_chunk *chunk, *chunk1;
534
	int fast_rtx;
Linus Torvalds's avatar
Linus Torvalds committed
535
	int error = 0;
536
	int timer = 0;
537
	int done = 0;
Linus Torvalds's avatar
Linus Torvalds committed
538
539

	lqueue = &q->retransmit;
540
	fast_rtx = q->fast_rtx;
Linus Torvalds's avatar
Linus Torvalds committed
541

542
543
544
545
	/* This loop handles time-out retransmissions, fast retransmissions,
	 * and retransmissions due to opening of whindow.
	 *
	 * RFC 2960 6.3.3 Handle T3-rtx Expiration
Linus Torvalds's avatar
Linus Torvalds committed
546
547
548
549
550
551
552
553
554
555
556
557
558
559
	 *
	 * E3) Determine how many of the earliest (i.e., lowest TSN)
	 * outstanding DATA chunks for the address for which the
	 * T3-rtx has expired will fit into a single packet, subject
	 * to the MTU constraint for the path corresponding to the
	 * destination transport address to which the retransmission
	 * is being sent (this may be different from the address for
	 * which the timer expires [see Section 6.4]). Call this value
	 * K. Bundle and retransmit those K DATA chunks in a single
	 * packet to the destination endpoint.
	 *
	 * [Just to be painfully clear, if we are retransmitting
	 * because a timeout just happened, we should send only ONE
	 * packet of retransmitted data.]
560
561
562
563
	 *
	 * For fast retransmissions we also send only ONE packet.  However,
	 * if we are just flushing the queue due to open window, we'll
	 * try to send as much as possible.
Linus Torvalds's avatar
Linus Torvalds committed
564
	 */
565
	list_for_each_entry_safe(chunk, chunk1, lqueue, transmitted_list) {
566
567
568
569
570
571
572
		/* If the chunk is abandoned, move it to abandoned list. */
		if (sctp_chunk_abandoned(chunk)) {
			list_del_init(&chunk->transmitted_list);
			sctp_insert_list(&q->abandoned,
					 &chunk->transmitted_list);
			continue;
		}
Linus Torvalds's avatar
Linus Torvalds committed
573
574
575
576
577
578
579

		/* Make sure that Gap Acked TSNs are not retransmitted.  A
		 * simple approach is just to move such TSNs out of the
		 * way and into a 'transmitted' queue and skip to the
		 * next chunk.
		 */
		if (chunk->tsn_gap_acked) {
580
581
			list_move_tail(&chunk->transmitted_list,
				       &transport->transmitted);
Linus Torvalds's avatar
Linus Torvalds committed
582
583
584
			continue;
		}

585
586
587
588
589
590
		/* If we are doing fast retransmit, ignore non-fast_rtransmit
		 * chunks
		 */
		if (fast_rtx && !chunk->fast_retransmit)
			continue;

591
redo:
Linus Torvalds's avatar
Linus Torvalds committed
592
593
594
595
596
		/* Attempt to append this chunk to the packet. */
		status = sctp_packet_append_chunk(pkt, chunk);

		switch (status) {
		case SCTP_XMIT_PMTU_FULL:
597
598
599
600
601
602
603
604
605
606
607
			if (!pkt->has_data && !pkt->has_cookie_echo) {
				/* If this packet did not contain DATA then
				 * retransmission did not happen, so do it
				 * again.  We'll ignore the error here since
				 * control chunks are already freed so there
				 * is nothing we can do.
				 */
				sctp_packet_transmit(pkt);
				goto redo;
			}

Linus Torvalds's avatar
Linus Torvalds committed
608
			/* Send this packet.  */
609
			error = sctp_packet_transmit(pkt);
Linus Torvalds's avatar
Linus Torvalds committed
610
611
612

			/* If we are retransmitting, we should only
			 * send a single packet.
613
			 * Otherwise, try appending this chunk again.
Linus Torvalds's avatar
Linus Torvalds committed
614
			 */
615
616
			if (rtx_timeout || fast_rtx)
				done = 1;
617
618
			else
				goto redo;
Linus Torvalds's avatar
Linus Torvalds committed
619

620
			/* Bundle next chunk in the next round.  */
Linus Torvalds's avatar
Linus Torvalds committed
621
622
623
			break;

		case SCTP_XMIT_RWND_FULL:
624
			/* Send this packet. */
625
			error = sctp_packet_transmit(pkt);
Linus Torvalds's avatar
Linus Torvalds committed
626
627
628
629

			/* Stop sending DATA as there is no more room
			 * at the receiver.
			 */
630
			done = 1;
Linus Torvalds's avatar
Linus Torvalds committed
631
632
			break;

633
		case SCTP_XMIT_DELAY:
634
			/* Send this packet. */
635
			error = sctp_packet_transmit(pkt);
Linus Torvalds's avatar
Linus Torvalds committed
636
637

			/* Stop sending DATA because of nagle delay. */
638
			done = 1;
Linus Torvalds's avatar
Linus Torvalds committed
639
640
641
642
643
644
			break;

		default:
			/* The append was successful, so add this chunk to
			 * the transmitted list.
			 */
645
646
			list_move_tail(&chunk->transmitted_list,
				       &transport->transmitted);
Linus Torvalds's avatar
Linus Torvalds committed
647

648
			/* Mark the chunk as ineligible for fast retransmit
Linus Torvalds's avatar
Linus Torvalds committed
649
650
			 * after it is retransmitted.
			 */
651
652
			if (chunk->fast_retransmit == SCTP_NEED_FRTX)
				chunk->fast_retransmit = SCTP_DONT_FRTX;
Linus Torvalds's avatar
Linus Torvalds committed
653

654
			q->asoc->stats.rtxchunks++;
Linus Torvalds's avatar
Linus Torvalds committed
655
			break;
656
		}
Linus Torvalds's avatar
Linus Torvalds committed
657

658
659
660
661
		/* Set the timer if there were no errors */
		if (!error && !timer)
			timer = 1;

662
663
664
665
666
667
668
669
670
671
672
		if (done)
			break;
	}

	/* If we are here due to a retransmit timeout or a fast
	 * retransmit and if there are any chunks left in the retransmit
	 * queue that could not fit in the PMTU sized packet, they need
	 * to be marked as ineligible for a subsequent fast retransmit.
	 */
	if (rtx_timeout || fast_rtx) {
		list_for_each_entry(chunk1, lqueue, transmitted_list) {
673
674
			if (chunk1->fast_retransmit == SCTP_NEED_FRTX)
				chunk1->fast_retransmit = SCTP_DONT_FRTX;
Linus Torvalds's avatar
Linus Torvalds committed
675
676
677
		}
	}

678
679
680
681
682
683
	*start_timer = timer;

	/* Clear fast retransmit hint */
	if (fast_rtx)
		q->fast_rtx = 0;

Linus Torvalds's avatar
Linus Torvalds committed
684
685
686
687
688
689
	return error;
}

/* Cork the outqueue so queued chunks are really queued. */
int sctp_outq_uncork(struct sctp_outq *q)
{
690
	if (q->cork)
Linus Torvalds's avatar
Linus Torvalds committed
691
		q->cork = 0;
692
693

	return sctp_outq_flush(q, 0);
Linus Torvalds's avatar
Linus Torvalds committed
694
695
}

696

Linus Torvalds's avatar
Linus Torvalds committed
697
698
699
700
701
702
703
704
705
/*
 * Try to flush an outqueue.
 *
 * Description: Send everything in q which we legally can, subject to
 * congestion limitations.
 * * Note: This function can be called from multiple contexts so appropriate
 * locking concerns must be made.  Today we use the sock lock to protect
 * this function.
 */
706
static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout)
Linus Torvalds's avatar
Linus Torvalds committed
707
708
709
710
711
712
713
714
715
{
	struct sctp_packet *packet;
	struct sctp_packet singleton;
	struct sctp_association *asoc = q->asoc;
	__u16 sport = asoc->base.bind_addr.port;
	__u16 dport = asoc->peer.port;
	__u32 vtag = asoc->peer.i.init_tag;
	struct sctp_transport *transport = NULL;
	struct sctp_transport *new_transport;
716
	struct sctp_chunk *chunk, *tmp;
Linus Torvalds's avatar
Linus Torvalds committed
717
718
719
	sctp_xmit_t status;
	int error = 0;
	int start_timer = 0;
720
	int one_packet = 0;
Linus Torvalds's avatar
Linus Torvalds committed
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738

	/* These transports have chunks to send. */
	struct list_head transport_list;
	struct list_head *ltransport;

	INIT_LIST_HEAD(&transport_list);
	packet = NULL;

	/*
	 * 6.10 Bundling
	 *   ...
	 *   When bundling control chunks with DATA chunks, an
	 *   endpoint MUST place control chunks first in the outbound
	 *   SCTP packet.  The transmitter MUST transmit DATA chunks
	 *   within a SCTP packet in increasing order of TSN.
	 *   ...
	 */

739
	list_for_each_entry_safe(chunk, tmp, &q->control_chunk_list, list) {
740
741
742
743
744
745
746
747
748
749
		/* RFC 5061, 5.3
		 * F1) This means that until such time as the ASCONF
		 * containing the add is acknowledged, the sender MUST
		 * NOT use the new IP address as a source for ANY SCTP
		 * packet except on carrying an ASCONF Chunk.
		 */
		if (asoc->src_out_of_asoc_ok &&
		    chunk->chunk_hdr->type != SCTP_CID_ASCONF)
			continue;

750
751
		list_del_init(&chunk->list);

Linus Torvalds's avatar
Linus Torvalds committed
752
753
754
755
		/* Pick the right transport to use. */
		new_transport = chunk->transport;

		if (!new_transport) {
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
			/*
			 * If we have a prior transport pointer, see if
			 * the destination address of the chunk
			 * matches the destination address of the
			 * current transport.  If not a match, then
			 * try to look up the transport with a given
			 * destination address.  We do this because
			 * after processing ASCONFs, we may have new
			 * transports created.
			 */
			if (transport &&
			    sctp_cmp_addr_exact(&chunk->dest,
						&transport->ipaddr))
					new_transport = transport;
			else
				new_transport = sctp_assoc_lookup_paddr(asoc,
								&chunk->dest);

			/* if we still don't have a new transport, then
			 * use the current active path.
			 */
			if (!new_transport)
				new_transport = asoc->peer.active_path;
779
		} else if ((new_transport->state == SCTP_INACTIVE) ||
780
781
			   (new_transport->state == SCTP_UNCONFIRMED) ||
			   (new_transport->state == SCTP_PF)) {
782
783
			/* If the chunk is Heartbeat or Heartbeat Ack,
			 * send it to chunk->transport, even if it's
Linus Torvalds's avatar
Linus Torvalds committed
784
785
786
			 * inactive.
			 *
			 * 3.3.6 Heartbeat Acknowledgement:
787
			 * ...
Linus Torvalds's avatar
Linus Torvalds committed
788
789
790
			 * A HEARTBEAT ACK is always sent to the source IP
			 * address of the IP datagram containing the
			 * HEARTBEAT chunk to which this ack is responding.
791
			 * ...
792
793
			 *
			 * ASCONF_ACKs also must be sent to the source.
Linus Torvalds's avatar
Linus Torvalds committed
794
795
			 */
			if (chunk->chunk_hdr->type != SCTP_CID_HEARTBEAT &&
796
797
			    chunk->chunk_hdr->type != SCTP_CID_HEARTBEAT_ACK &&
			    chunk->chunk_hdr->type != SCTP_CID_ASCONF_ACK)
Linus Torvalds's avatar
Linus Torvalds committed
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
				new_transport = asoc->peer.active_path;
		}

		/* Are we switching transports?
		 * Take care of transport locks.
		 */
		if (new_transport != transport) {
			transport = new_transport;
			if (list_empty(&transport->send_ready)) {
				list_add_tail(&transport->send_ready,
					      &transport_list);
			}
			packet = &transport->packet;
			sctp_packet_config(packet, vtag,
					   asoc->peer.ecn_capable);
		}

		switch (chunk->chunk_hdr->type) {
		/*
		 * 6.10 Bundling
		 *   ...
		 *   An endpoint MUST NOT bundle INIT, INIT ACK or SHUTDOWN
		 *   COMPLETE with any other chunks.  [Send them immediately.]
		 */
		case SCTP_CID_INIT:
		case SCTP_CID_INIT_ACK:
		case SCTP_CID_SHUTDOWN_COMPLETE:
			sctp_packet_init(&singleton, transport, sport, dport);
			sctp_packet_config(&singleton, vtag, 0);
			sctp_packet_append_chunk(&singleton, chunk);
			error = sctp_packet_transmit(&singleton);
			if (error < 0)
				return error;
			break;

		case SCTP_CID_ABORT:
834
835
836
			if (sctp_test_T_bit(chunk)) {
				packet->vtag = asoc->c.my_vtag;
			}
837
838
839
840
841
		/* The following chunks are "response" chunks, i.e.
		 * they are generated in response to something we
		 * received.  If we are sending these, then we can
		 * send only 1 packet containing these chunks.
		 */
Linus Torvalds's avatar
Linus Torvalds committed
842
843
844
		case SCTP_CID_HEARTBEAT_ACK:
		case SCTP_CID_SHUTDOWN_ACK:
		case SCTP_CID_COOKIE_ACK:
845
846
		case SCTP_CID_COOKIE_ECHO:
		case SCTP_CID_ERROR:
Linus Torvalds's avatar
Linus Torvalds committed
847
848
		case SCTP_CID_ECN_CWR:
		case SCTP_CID_ASCONF_ACK:
849
			one_packet = 1;
Lucas De Marchi's avatar
Lucas De Marchi committed
850
			/* Fall through */
851
852
853
854
855
856

		case SCTP_CID_SACK:
		case SCTP_CID_HEARTBEAT:
		case SCTP_CID_SHUTDOWN:
		case SCTP_CID_ECN_ECNE:
		case SCTP_CID_ASCONF:
Linus Torvalds's avatar
Linus Torvalds committed
857
		case SCTP_CID_FWD_TSN:
858
859
860
861
862
			status = sctp_packet_transmit_chunk(packet, chunk,
							    one_packet);
			if (status  != SCTP_XMIT_OK) {
				/* put the chunk back */
				list_add(&chunk->list, &q->control_chunk_list);
863
864
			} else {
				asoc->stats.octrlchunks++;
865
866
867
868
				/* PR-SCTP C5) If a FORWARD TSN is sent, the
				 * sender MUST assure that at least one T3-rtx
				 * timer is running.
				 */
869
870
				if (chunk->chunk_hdr->type == SCTP_CID_FWD_TSN)
					sctp_transport_reset_timers(transport);
871
			}
Linus Torvalds's avatar
Linus Torvalds committed
872
873
874
875
876
			break;

		default:
			/* We built a chunk with an illegal type! */
			BUG();
877
		}
Linus Torvalds's avatar
Linus Torvalds committed
878
879
	}

880
881
882
	if (q->asoc->src_out_of_asoc_ok)
		goto sctp_flush_out;

Linus Torvalds's avatar
Linus Torvalds committed
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
	/* Is it OK to send data chunks?  */
	switch (asoc->state) {
	case SCTP_STATE_COOKIE_ECHOED:
		/* Only allow bundling when this packet has a COOKIE-ECHO
		 * chunk.
		 */
		if (!packet || !packet->has_cookie_echo)
			break;

		/* fallthru */
	case SCTP_STATE_ESTABLISHED:
	case SCTP_STATE_SHUTDOWN_PENDING:
	case SCTP_STATE_SHUTDOWN_RECEIVED:
		/*
		 * RFC 2960 6.1  Transmission of DATA Chunks
		 *
		 * C) When the time comes for the sender to transmit,
		 * before sending new DATA chunks, the sender MUST
		 * first transmit any outstanding DATA chunks which
		 * are marked for retransmission (limited by the
		 * current cwnd).
		 */
		if (!list_empty(&q->retransmit)) {
906
907
			if (asoc->peer.retran_path->state == SCTP_UNCONFIRMED)
				goto sctp_flush_out;
Linus Torvalds's avatar
Linus Torvalds committed
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
			if (transport == asoc->peer.retran_path)
				goto retran;

			/* Switch transports & prepare the packet.  */

			transport = asoc->peer.retran_path;

			if (list_empty(&transport->send_ready)) {
				list_add_tail(&transport->send_ready,
					      &transport_list);
			}

			packet = &transport->packet;
			sctp_packet_config(packet, vtag,
					   asoc->peer.ecn_capable);
		retran:
			error = sctp_outq_flush_rtx(q, packet,
						    rtx_timeout, &start_timer);

			if (start_timer)
928
				sctp_transport_reset_timers(transport);
Linus Torvalds's avatar
Linus Torvalds committed
929
930
931
932
933
934
935
936
937
938
939
940
941
942

			/* This can happen on COOKIE-ECHO resend.  Only
			 * one chunk can get bundled with a COOKIE-ECHO.
			 */
			if (packet->has_cookie_echo)
				goto sctp_flush_out;

			/* Don't send new data if there is still data
			 * waiting to retransmit.
			 */
			if (!list_empty(&q->retransmit))
				goto sctp_flush_out;
		}

943
944
945
946
947
948
949
950
		/* Apply Max.Burst limitation to the current transport in
		 * case it will be used for new data.  We are going to
		 * rest it before we return, but we want to apply the limit
		 * to the currently queued data.
		 */
		if (transport)
			sctp_transport_burst_limited(transport);

Linus Torvalds's avatar
Linus Torvalds committed
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
		/* Finally, transmit new packets.  */
		while ((chunk = sctp_outq_dequeue_data(q)) != NULL) {
			/* RFC 2960 6.5 Every DATA chunk MUST carry a valid
			 * stream identifier.
			 */
			if (chunk->sinfo.sinfo_stream >=
			    asoc->c.sinit_num_ostreams) {

				/* Mark as failed send. */
				sctp_chunk_fail(chunk, SCTP_ERROR_INV_STRM);
				sctp_chunk_free(chunk);
				continue;
			}

			/* Has this chunk expired? */
			if (sctp_chunk_abandoned(chunk)) {
				sctp_chunk_fail(chunk, 0);
				sctp_chunk_free(chunk);
				continue;
			}

			/* If there is a specified transport, use it.
			 * Otherwise, we want to use the active path.
			 */
			new_transport = chunk->transport;
976
			if (!new_transport ||
977
			    ((new_transport->state == SCTP_INACTIVE) ||
978
979
			     (new_transport->state == SCTP_UNCONFIRMED) ||
			     (new_transport->state == SCTP_PF)))
Linus Torvalds's avatar
Linus Torvalds committed
980
				new_transport = asoc->peer.active_path;
981
982
			if (new_transport->state == SCTP_UNCONFIRMED)
				continue;
Linus Torvalds's avatar
Linus Torvalds committed
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998

			/* Change packets if necessary.  */
			if (new_transport != transport) {
				transport = new_transport;

				/* Schedule to have this transport's
				 * packet flushed.
				 */
				if (list_empty(&transport->send_ready)) {
					list_add_tail(&transport->send_ready,
						      &transport_list);
				}

				packet = &transport->packet;
				sctp_packet_config(packet, vtag,
						   asoc->peer.ecn_capable);
999
1000
1001
1002
				/* We've switched transports, so apply the
				 * Burst limit to the new transport.
				 */
				sctp_transport_burst_limited(transport);
Linus Torvalds's avatar
Linus Torvalds committed
1003
1004
			}

1005
1006
1007
1008
1009
1010
1011
			pr_debug("%s: outq:%p, chunk:%p[%s], tx-tsn:0x%x skb->head:%p "
				 "skb->users:%d\n",
				 __func__, q, chunk, chunk && chunk->chunk_hdr ?
				 sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) :
				 "illegal chunk", ntohl(chunk->subh.data_hdr->tsn),
				 chunk->skb ? chunk->skb->head : NULL, chunk->skb ?
				 atomic_read(&chunk->skb->users) : -1);
Linus Torvalds's avatar
Linus Torvalds committed
1012
1013

			/* Add the chunk to the packet.  */
1014
			status = sctp_packet_transmit_chunk(packet, chunk, 0);
Linus Torvalds's avatar
Linus Torvalds committed
1015
1016
1017
1018

			switch (status) {
			case SCTP_XMIT_PMTU_FULL:
			case SCTP_XMIT_RWND_FULL:
1019
			case SCTP_XMIT_DELAY:
Linus Torvalds's avatar
Linus Torvalds committed
1020
1021
1022
				/* We could not append this chunk, so put
				 * the chunk back on the output queue.
				 */
1023
1024
1025
1026
				pr_debug("%s: could not transmit tsn:0x%x, status:%d\n",
					 __func__, ntohl(chunk->subh.data_hdr->tsn),
					 status);

Linus Torvalds's avatar
Linus Torvalds committed
1027
1028
1029
1030
				sctp_outq_head_data(q, chunk);
				goto sctp_flush_out;

			case SCTP_XMIT_OK:
1031
1032
1033
1034
1035
1036
				/* The sender is in the SHUTDOWN-PENDING state,
				 * The sender MAY set the I-bit in the DATA
				 * chunk header.
				 */
				if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING)
					chunk->chunk_hdr->flags |= SCTP_DATA_SACK_IMM;
1037
1038
1039
1040
				if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED)
					asoc->stats.ouodchunks++;
				else
					asoc->stats.oodchunks++;
1041

Linus Torvalds's avatar
Linus Torvalds committed
1042
1043
1044
1045
1046
1047
				break;

			default:
				BUG();
			}

1048
			/* BUG: We assume that the sctp_packet_transmit()
Linus Torvalds's avatar
Linus Torvalds committed
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
			 * call below will succeed all the time and add the
			 * chunk to the transmitted list and restart the
			 * timers.
			 * It is possible that the call can fail under OOM
			 * conditions.
			 *
			 * Is this really a problem?  Won't this behave
			 * like a lost TSN?
			 */
			list_add_tail(&chunk->transmitted_list,
				      &transport->transmitted);

1061
			sctp_transport_reset_timers(transport);
Linus Torvalds's avatar
Linus Torvalds committed
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084

			/* Only let one DATA chunk get bundled with a
			 * COOKIE-ECHO chunk.
			 */
			if (packet->has_cookie_echo)
				goto sctp_flush_out;
		}
		break;

	default:
		/* Do nothing.  */
		break;
	}

sctp_flush_out:

	/* Before returning, examine all the transports touched in
	 * this call.  Right now, we bluntly force clear all the
	 * transports.  Things might change after we implement Nagle.
	 * But such an examination is still required.
	 *
	 * --xguo
	 */
1085
	while ((ltransport = sctp_list_dequeue(&transport_list)) != NULL) {
Linus Torvalds's avatar
Linus Torvalds committed
1086
1087
1088
1089
1090
1091
		struct sctp_transport *t = list_entry(ltransport,
						      struct sctp_transport,
						      send_ready);
		packet = &t->packet;
		if (!sctp_packet_empty(packet))
			error = sctp_packet_transmit(packet);
1092
1093
1094

		/* Clear the burst limited state, if any */
		sctp_transport_burst_reset(t);
Linus Torvalds's avatar
Linus Torvalds committed
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
	}

	return error;
}

/* Update unack_data based on the incoming SACK chunk */
static void sctp_sack_update_unack_data(struct sctp_association *assoc,
					struct sctp_sackhdr *sack)
{
	sctp_sack_variable_t *frags;
	__u16 unack_data;
	int i;

	unack_data = assoc->next_tsn - assoc->ctsn_ack_point - 1;

	frags = sack->variable;
	for (i = 0; i < ntohs(sack->num_gap_ack_blocks); i++) {
		unack_data -= ((ntohs(frags[i].gab.end) -
				ntohs(frags[i].gab.start) + 1));
	}

	assoc->unack_data = unack_data;
}

/* This is where we REALLY process a SACK.
 *
 * Process the SACK against the outqueue.  Mostly, this just frees
 * things off the transmitted queue.
 */
1124
int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk)
Linus Torvalds's avatar
Linus Torvalds committed
1125
1126
{
	struct sctp_association *asoc = q->asoc;
1127
	struct sctp_sackhdr *sack = chunk->subh.sack_hdr;
Linus Torvalds's avatar
Linus Torvalds committed
1128
1129
	struct sctp_transport *transport;
	struct sctp_chunk *tchunk = NULL;
1130
	struct list_head *lchunk, *transport_list, *temp;
Linus Torvalds's avatar
Linus Torvalds committed
1131
1132
1133
1134
	sctp_sack_variable_t *frags = sack->variable;
	__u32 sack_ctsn, ctsn, tsn;
	__u32 highest_tsn, highest_new_tsn;
	__u32 sack_a_rwnd;
1135
	unsigned int outstanding;
Linus Torvalds's avatar
Linus Torvalds committed
1136
1137
	struct sctp_transport *primary = asoc->peer.primary_path;
	int count_of_newacks = 0;
1138
	int gap_ack_blocks;
1139
	u8 accum_moved = 0;
Linus Torvalds's avatar
Linus Torvalds committed
1140
1141
1142
1143
1144

	/* Grab the association's destination address list. */
	transport_list = &asoc->peer.transport_addr_list;

	sack_ctsn = ntohl(sack->cum_tsn_ack);
1145
	gap_ack_blocks = ntohs(sack->num_gap_ack_blocks);
1146
	asoc->stats.gapcnt += gap_ack_blocks;
Linus Torvalds's avatar
Linus Torvalds committed
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
	/*
	 * SFR-CACC algorithm:
	 * On receipt of a SACK the sender SHOULD execute the
	 * following statements.
	 *
	 * 1) If the cumulative ack in the SACK passes next tsn_at_change
	 * on the current primary, the CHANGEOVER_ACTIVE flag SHOULD be
	 * cleared. The CYCLING_CHANGEOVER flag SHOULD also be cleared for
	 * all destinations.
	 * 2) If the SACK contains gap acks and the flag CHANGEOVER_ACTIVE
	 * is set the receiver of the SACK MUST take the following actions:
	 *
	 * A) Initialize the cacc_saw_newack to 0 for all destination
	 * addresses.
1161
1162
1163
	 *
	 * Only bother if changeover_active is set. Otherwise, this is
	 * totally suboptimal to do on every SACK.
Linus Torvalds's avatar
Linus Torvalds committed
1164
	 */
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
	if (primary->cacc.changeover_active) {
		u8 clear_cycling = 0;

		if (TSN_lte(primary->cacc.next_tsn_at_change, sack_ctsn)) {
			primary->cacc.changeover_active = 0;
			clear_cycling = 1;
		}

		if (clear_cycling || gap_ack_blocks) {
			list_for_each_entry(transport, transport_list,
					transports) {
				if (clear_cycling)
					transport->cacc.cycling_changeover = 0;
				if (gap_ack_blocks)
					transport->cacc.cacc_saw_newack = 0;
			}
Linus Torvalds's avatar
Linus Torvalds committed
1181
1182
1183
1184
1185
		}
	}

	/* Get the highest TSN in the sack. */
	highest_tsn = sack_ctsn;
1186
1187
	if (gap_ack_blocks)
		highest_tsn += ntohs(frags[gap_ack_blocks - 1].gab.end);
Linus Torvalds's avatar
Linus Torvalds committed
1188

1189
	if (TSN_lt(asoc->highest_sacked, highest_tsn))
Linus Torvalds's avatar
Linus Torvalds committed
1190
1191
		asoc->highest_sacked = highest_tsn;

1192
	highest_new_tsn = sack_ctsn;
1193

Linus Torvalds's avatar
Linus Torvalds committed
1194
1195
1196
	/* Run through the retransmit queue.  Credit bytes received
	 * and free those chunks that we can.
	 */
1197
	sctp_check_transmitted(q, &q->retransmit, NULL, NULL, sack, &highest_new_tsn);
Linus Torvalds's avatar
Linus Torvalds committed
1198
1199
1200
1201
1202
1203

	/* Run through the transmitted queue.
	 * Credit bytes received and free those chunks which we can.
	 *
	 * This is a MASSIVE candidate for optimization.
	 */
1204
	list_for_each_entry(transport, transport_list, transports) {
Linus Torvalds's avatar
Linus Torvalds committed
1205
		sctp_check_transmitted(q, &transport->transmitted,
1206
1207
				       transport, &chunk->source, sack,
				       &highest_new_tsn);
Linus Torvalds's avatar
Linus Torvalds committed
1208
1209
1210
1211
1212
1213
		/*
		 * SFR-CACC algorithm:
		 * C) Let count_of_newacks be the number of
		 * destinations for which cacc_saw_newack is set.
		 */
		if (transport->cacc.cacc_saw_newack)
1214
			count_of_newacks++;
Linus Torvalds's avatar
Linus Torvalds committed
1215
1216
	}

1217
1218
1219
1220
1221
1222
	/* Move the Cumulative TSN Ack Point if appropriate.  */
	if (TSN_lt(asoc->ctsn_ack_point, sack_ctsn)) {
		asoc->ctsn_ack_point = sack_ctsn;
		accum_moved = 1;
	}

1223
	if (gap_ack_blocks) {
1224
1225
1226
1227

		if (asoc->fast_recovery && accum_moved)
			highest_new_tsn = highest_tsn;

1228
1229
1230
		list_for_each_entry(transport, transport_list, transports)
			sctp_mark_missing(q, &transport->transmitted, transport,
					  highest_new_tsn, count_of_newacks);
Linus Torvalds's avatar
Linus Torvalds committed
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
	}

	/* Update unack_data field in the assoc. */
	sctp_sack_update_unack_data(asoc, sack);

	ctsn = asoc->ctsn_ack_point;

	/* Throw away stuff rotting on the sack queue.  */
	list_for_each_safe(lchunk, temp, &q->sacked) {
		tchunk = list_entry(lchunk, struct sctp_chunk,
				    transmitted_list);
		tsn = ntohl(tchunk->subh.data_hdr->tsn);
1243
1244
		if (TSN_lte(tsn, ctsn)) {
			list_del_init(&tchunk->transmitted_list);
Linus Torvalds's avatar
Linus Torvalds committed
1245
			sctp_chunk_free(tchunk);
1246
		}
Linus Torvalds's avatar
Linus Torvalds committed
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
	}

	/* ii) Set rwnd equal to the newly received a_rwnd minus the
	 *     number of bytes still outstanding after processing the
	 *     Cumulative TSN Ack and the Gap Ack Blocks.
	 */

	sack_a_rwnd = ntohl(sack->a_rwnd);
	outstanding = q->outstanding_bytes;

	if (outstanding < sack_a_rwnd)
		sack_a_rwnd -= outstanding;
	else
		sack_a_rwnd = 0;

	asoc->peer.rwnd = sack_a_rwnd;

	sctp_generate_fwdtsn(q, sack_ctsn);

1266
1267
1268
1269
	pr_debug("%s: sack cumulative tsn ack:0x%x\n", __func__, sack_ctsn);
	pr_debug("%s: cumulative tsn ack of assoc:%p is 0x%x, "
		 "advertised peer ack point:0x%x\n", __func__, asoc, ctsn,
		 asoc->adv_peer_ack_point);
Linus Torvalds's avatar
Linus Torvalds committed
1270

1271
	return sctp_outq_is_empty(q);
Linus Torvalds's avatar
Linus Torvalds committed
1272
1273
}

1274
1275
1276
1277
/* Is the outqueue empty?
 * The queue is empty when we have not pending data, no in-flight data
 * and nothing pending retransmissions.
 */
Linus Torvalds's avatar
Linus Torvalds committed
1278
1279
int sctp_outq_is_empty(const struct sctp_outq *q)
{
1280
1281
	return q->out_qlen == 0 && q->outstanding_bytes == 0 &&
	       list_empty(&q->retransmit);
Linus Torvalds's avatar
Linus Torvalds committed
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
}

/********************************************************************
 * 2nd Level Abstractions
 ********************************************************************/

/* Go through a transport's transmitted list or the association's retransmit
 * list and move chunks that are acked by the Cumulative TSN Ack to q->sacked.
 * The retransmit list will not have an associated transport.
 *
 * I added coherent debug information output.	--xguo
 *
 * Instead of printing 'sacked' or 'kept' for each TSN on the
 * transmitted_queue, we print a range: SACKED: TSN1-TSN2, TSN3, TSN4-TSN5.
 * KEPT TSN6-TSN7, etc.
 */
static void sctp_check_transmitted(struct sctp_outq *q,
				   struct list_head *transmitted_queue,
				   struct sctp_transport *transport,
1301
				   union sctp_addr *saddr,
Linus Torvalds's avatar
Linus Torvalds committed
1302
				   struct sctp_sackhdr *sack,
1303
				   __u32 *highest_new_tsn_in_sack)
Linus Torvalds's avatar
Linus Torvalds committed
1304
1305
1306
1307
1308
1309
1310
1311
1312
{
	struct list_head *lchunk;
	struct sctp_chunk *tchunk;
	struct list_head tlist;
	__u32 tsn;
	__u32 sack_ctsn;
	__u32 rtt;
	__u8 restart_timer = 0;
	int bytes_acked = 0;
1313
	int migrate_bytes = 0;
1314
	bool forward_progress = false;
Linus Torvalds's avatar
Linus Torvalds committed
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327

	sack_ctsn = ntohl(sack->cum_tsn_ack);

	INIT_LIST_HEAD(&tlist);

	/* The while loop will skip empty transmitted queues. */
	while (NULL != (lchunk = sctp_list_dequeue(transmitted_queue))) {
		tchunk = list_entry(lchunk, struct sctp_chunk,
				    transmitted_list);

		if (sctp_chunk_abandoned(tchunk)) {
			/* Move the chunk to abandoned list. */
			sctp_insert_list(&q->abandoned, lchunk);
1328
1329
1330
1331
1332

			/* If this chunk has not been acked, stop
			 * considering it as 'outstanding'.
			 */
			if (!tchunk->tsn_gap_acked) {
1333
1334
1335
				if (tchunk->transport)
					tchunk->transport->flight_size -=
							sctp_data_size(tchunk);
1336
1337
				q->outstanding_bytes -= sctp_data_size(tchunk);
			}
Linus Torvalds's avatar
Linus Torvalds committed
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
			continue;
		}

		tsn = ntohl(tchunk->subh.data_hdr->tsn);
		if (sctp_acked(sack, tsn)) {
			/* If this queue is the retransmit queue, the
			 * retransmit timer has already reclaimed
			 * the outstanding bytes for this chunk, so only
			 * count bytes associated with a transport.
			 */
			if (transport) {
				/* If this chunk is being used for RTT
				 * measurement, calculate the RTT and update
				 * the RTO using this value.
				 *
				 * 6.3.1 C5) Karn's algorithm: RTT measurements
				 * MUST NOT be made using packets that were
				 * retransmitted (and thus for which it is
				 * ambiguous whether the reply was for the
				 * first instance of the packet or a later
				 * instance).
				 */
1360
				if (!tchunk->tsn_gap_acked &&
1361
				    !tchunk->resent &&
Linus Torvalds's avatar
Linus Torvalds committed
1362
				    tchunk->rtt_in_progress) {
1363
					tchunk->rtt_in_progress = 0;
Linus Torvalds's avatar
Linus Torvalds committed
1364
1365
1366
1367
1368
					rtt = jiffies - tchunk->sent_at;
					sctp_transport_update_rto(transport,
								  rtt);
				}
			}
1369
1370
1371
1372
1373
1374
1375
1376
1377

			/* If the chunk hasn't been marked as ACKED,
			 * mark it and account bytes_acked if the
			 * chunk had a valid transport (it will not
			 * have a transport if ASCONF had deleted it
			 * while DATA was outstanding).
			 */
			if (!tchunk->tsn_gap_acked) {
				tchunk->tsn_gap_acked = 1;
1378
1379
				if (TSN_lt(*highest_new_tsn_in_sack, tsn))
					*highest_new_tsn_in_sack = tsn;
1380
1381
1382
				bytes_acked += sctp_data_size(tchunk);
				if (!tchunk->transport)
					migrate_bytes += sctp_data_size(tchunk);
1383
				forward_progress = true;
1384
1385
			}

1386
			if (TSN_lte(tsn, sack_ctsn)) {
Linus Torvalds's avatar
Linus Torvalds committed
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
				/* RFC 2960  6.3.2 Retransmission Timer Rules
				 *
				 * R3) Whenever a SACK is received
				 * that acknowledges the DATA chunk
				 * with the earliest outstanding TSN
				 * for that address, restart T3-rtx
				 * timer for that address with its
				 * current RTO.
				 */
				restart_timer = 1;
1397
				forward_progress = true;
Linus Torvalds's avatar
Linus Torvalds committed
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442

				if (!tchunk->tsn_gap_acked) {
					/*
					 * SFR-CACC algorithm:
					 * 2) If the SACK contains gap acks
					 * and the flag CHANGEOVER_ACTIVE is
					 * set the receiver of the SACK MUST
					 * take the following action:
					 *
					 * B) For each TSN t being acked that
					 * has not been acked in any SACK so
					 * far, set cacc_saw_newack to 1 for
					 * the destination that the TSN was
					 * sent to.
					 */
					if (transport &&
					    sack->num_gap_ack_blocks &&
					    q->asoc->peer.primary_path->cacc.
					    changeover_active)
						transport->cacc.cacc_saw_newack
							= 1;
				}

				list_add_tail(&tchunk->transmitted_list,
					      &q->sacked);
			} else {
				/* RFC2960 7.2.4, sctpimpguide-05 2.8.2
				 * M2) Each time a SACK arrives reporting
				 * 'Stray DATA chunk(s)' record the highest TSN
				 * reported as newly acknowledged, call this
				 * value 'HighestTSNinSack'. A newly
				 * acknowledged DATA chunk is one not
				 * previously acknowledged in a SACK.
				 *
				 * When the SCTP sender of data receives a SACK
				 * chunk that acknowledges, for the first time,
				 * the receipt of a DATA chunk, all the still
				 * unacknowledged DATA chunks whose TSN is
				 * older than that newly acknowledged DATA
				 * chunk, are qualified as 'Stray DATA chunks'.
				 */
				list_add_tail(lchunk, &tlist);
			}
		} else {
			if (tchunk->tsn_gap_acked) {
1443
1444
1445
				pr_debug("%s: receiver reneged on data TSN:0x%x\n",
					 __func__, tsn);

Linus Torvalds's avatar
Linus Torvalds committed
1446
1447
				tchunk->tsn_gap_acked = 0;

1448
1449
				if (tchunk->transport)
					bytes_acked -= sctp_data_size(tchunk);
Linus Torvalds's avatar
Linus Torvalds committed
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468

				/* RFC 2960 6.3.2 Retransmission Timer Rules
				 *
				 * R4) Whenever a SACK is received missing a
				 * TSN that was previously acknowledged via a
				 * Gap Ack Block, start T3-rtx for the
				 * destination address to which the DATA
				 * chunk was originally
				 * transmitted if it is not already running.
				 */
				restart_timer = 1;
			}

			list_add_tail(lchunk, &tlist);
		}
	}

	if (transport) {
		if (bytes_acked) {
1469
1470
			struct sctp_association *asoc = transport->asoc;

1471
1472
1473
1474
1475
1476
1477
1478
			/* We may have counted DATA that was migrated
			 * to this transport due to DEL-IP operation.
			 * Subtract those bytes, since the were never
			 * send on this transport and shouldn't be
			 * credited to this transport.
			 */
			bytes_acked -= migrate_bytes;

Linus Torvalds's avatar
Linus Torvalds committed
1479
1480
1481
1482
1483
1484
1485
1486
1487
			/* 8.2. When an outstanding TSN is acknowledged,
			 * the endpoint shall clear the error counter of
			 * the destination transport address to which the
			 * DATA chunk was last sent.
			 * The association's overall error counter is
			 * also cleared.
			 */
			transport->error_count = 0;
			transport->asoc->overall_error_count = 0;
1488
			forward_progress = true;
Linus Torvalds's avatar
Linus Torvalds committed
1489

1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
			/*
			 * While in SHUTDOWN PENDING, we may have started
			 * the T5 shutdown guard timer after reaching the
			 * retransmission limit. Stop that timer as soon
			 * as the receiver acknowledged any data.
			 */
			if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING &&
			    del_timer(&asoc->timers
				[SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD]))
					sctp_association_put(asoc);

Linus Torvalds's avatar
Linus Torvalds committed
1501
1502
1503
			/* Mark the destination transport address as
			 * active if it is not so marked.
			 */
1504
1505
1506
			if ((transport->state == SCTP_INACTIVE ||
			     transport->state == SCTP_UNCONFIRMED) &&
			    sctp_cmp_addr_exact(&transport->ipaddr, saddr)) {
Linus Torvalds's avatar
Linus Torvalds committed
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
				sctp_assoc_control_transport(
					transport->asoc,
					transport,
					SCTP_TRANSPORT_UP,
					SCTP_RECEIVED_SACK);
			}

			sctp_transport_raise_cwnd(transport, sack_ctsn,
						  bytes_acked);

			transport->flight_size -= bytes_acked;
1518
1519
			if (transport->flight_size == 0)
				transport->partial_bytes_acked = 0;
1520
			q->outstanding_bytes -= bytes_acked + migrate_bytes;
Linus Torvalds's avatar
Linus Torvalds committed
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
		} else {
			/* RFC 2960 6.1, sctpimpguide-06 2.15.2
			 * When a sender is doing zero window probing, it
			 * should not timeout the association if it continues
			 * to receive new packets from the receiver. The
			 * reason is that the receiver MAY keep its window
			 * closed for an indefinite time.
			 * A sender is doing zero window probing when the
			 * receiver's advertised window is zero, and there is
			 * only one data chunk in flight to the receiver.
1531
1532
1533
1534
			 *
			 * Allow the association to timeout while in SHUTDOWN
			 * PENDING or SHUTDOWN RECEIVED in case the receiver
			 * stays in zero window mode forever.
Linus Torvalds's avatar
Linus Torvalds committed
1535
1536
1537
			 */
			if (!q->asoc->peer.rwnd &&
			    !list_empty(&tlist) &&
1538
1539
			    (sack_ctsn+2 == q->asoc->next_tsn) &&
			    q->asoc->state < SCTP_STATE_SHUTDOWN_PENDING) {
1540
1541
1542
				pr_debug("%s: sack received for zero window "
					 "probe:%u\n", __func__, sack_ctsn);

Linus Torvalds's avatar
Linus Torvalds committed
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
				q->asoc->overall_error_count = 0;
				transport->error_count = 0;
			}
		}

		/* RFC 2960 6.3.2 Retransmission Timer Rules
		 *
		 * R2) Whenever all outstanding data sent to an address have
		 * been acknowledged, turn off the T3-rtx timer of that
		 * address.
		 */
		if (!transport->flight_size) {
1555
			if (del_timer(&transport->T3_rtx_timer))
Linus Torvalds's avatar
Linus Torvalds committed
1556
1557
1558
1559
1560
1561
				sctp_transport_put(transport);
		} else if (restart_timer) {
			if (!mod_timer(&transport->T3_rtx_timer,
				       jiffies + transport->rto))
				sctp_transport_hold(transport);
		}
1562
1563
1564
1565
1566

		if (forward_progress) {
			if (transport->dst)
				dst_confirm(transport->dst);
		}
Linus Torvalds's avatar
Linus Torvalds committed
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
	}

	list_splice(&tlist, transmitted_queue);
}

/* Mark chunks as missing and consequently may get retransmitted. */
static void sctp_mark_missing(struct sctp_outq *q,
			      struct list_head *transmitted_queue,
			      struct sctp_transport *transport,
			      __u32 highest_new_tsn_in_sack,
			      int count_of_newacks)
{
	struct sctp_chunk *chunk;
	__u32 tsn;
	char do_fast_retransmit = 0;
1582
1583
	struct sctp_association *asoc = q->asoc;
	struct sctp_transport *primary = asoc->peer.primary_path;
Linus Torvalds's avatar
Linus Torvalds committed
1584

1585
	list_for_each_entry(chunk, transmitted_queue, transmitted_list) {
Linus Torvalds's avatar
Linus Torvalds committed
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595

		tsn = ntohl(chunk->subh.data_hdr->tsn);

		/* RFC 2960 7.2.4, sctpimpguide-05 2.8.2 M3) Examine all
		 * 'Unacknowledged TSN's', if the TSN number of an
		 * 'Unacknowledged TSN' is smaller than the 'HighestTSNinSack'
		 * value, increment the 'TSN.Missing.Report' count on that
		 * chunk if it has NOT been fast retransmitted or marked for
		 * fast retransmit already.
		 */
1596
		if (chunk->fast_retransmit == SCTP_CAN_FRTX &&
Linus Torvalds's avatar
Linus Torvalds committed
1597
1598
1599
1600
1601
1602
		    !chunk->tsn_gap_acked &&
		    TSN_lt(tsn, highest_new_tsn_in_sack)) {

			/* SFR-CACC may require us to skip marking
			 * this chunk as missing.
			 */
Vlad Yasevich's avatar