aboutsummaryrefslogtreecommitdiff
path: root/sys/netinet/cc/cc_newreno.c
blob: 8f939ad70695d5e1ca6cfe19ece38bd5cc9e116b (plain) (blame)
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
/*-
 * SPDX-License-Identifier: BSD-2-Clause-FreeBSD
 *
 * Copyright (c) 1982, 1986, 1988, 1990, 1993, 1994, 1995
 *	The Regents of the University of California.
 * Copyright (c) 2007-2008,2010,2014
 *	Swinburne University of Technology, Melbourne, Australia.
 * Copyright (c) 2009-2010 Lawrence Stewart <lstewart@freebsd.org>
 * Copyright (c) 2010 The FreeBSD Foundation
 * All rights reserved.
 *
 * This software was developed at the Centre for Advanced Internet
 * Architectures, Swinburne University of Technology, by Lawrence Stewart, James
 * Healy and David Hayes, made possible in part by a grant from the Cisco
 * University Research Program Fund at Community Foundation Silicon Valley.
 *
 * Portions of this software were developed at the Centre for Advanced
 * Internet Architectures, Swinburne University of Technology, Melbourne,
 * Australia by David Hayes under sponsorship from the FreeBSD Foundation.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 */

/*
 * This software was first released in 2007 by James Healy and Lawrence Stewart
 * whilst working on the NewTCP research project at Swinburne University of
 * Technology's Centre for Advanced Internet Architectures, Melbourne,
 * Australia, which was made possible in part by a grant from the Cisco
 * University Research Program Fund at Community Foundation Silicon Valley.
 * More details are available at:
 *   http://caia.swin.edu.au/urp/newtcp/
 *
 * Dec 2014 garmitage@swin.edu.au
 * Borrowed code fragments from cc_cdg.c to add modifiable beta
 * via sysctls.
 *
 */

#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");

#include <sys/param.h>
#include <sys/kernel.h>
#include <sys/malloc.h>
#include <sys/module.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/sysctl.h>
#include <sys/systm.h>

#include <net/vnet.h>

#include <netinet/tcp.h>
#include <netinet/tcp_seq.h>
#include <netinet/tcp_var.h>
#include <netinet/cc/cc.h>
#include <netinet/cc/cc_module.h>
#include <netinet/cc/cc_newreno.h>

static MALLOC_DEFINE(M_NEWRENO, "newreno data",
	"newreno beta values");

static void	newreno_cb_destroy(struct cc_var *ccv);
static void	newreno_ack_received(struct cc_var *ccv, uint16_t type);
static void	newreno_after_idle(struct cc_var *ccv);
static void	newreno_cong_signal(struct cc_var *ccv, uint32_t type);
static void	newreno_post_recovery(struct cc_var *ccv);
static int newreno_ctl_output(struct cc_var *ccv, struct sockopt *sopt, void *buf);

VNET_DEFINE(uint32_t, newreno_beta) = 50;
VNET_DEFINE(uint32_t, newreno_beta_ecn) = 80;
#define V_newreno_beta VNET(newreno_beta)
#define V_newreno_beta_ecn VNET(newreno_beta_ecn)

struct cc_algo newreno_cc_algo = {
	.name = "newreno",
	.cb_destroy = newreno_cb_destroy,
	.ack_received = newreno_ack_received,
	.after_idle = newreno_after_idle,
	.cong_signal = newreno_cong_signal,
	.post_recovery = newreno_post_recovery,
	.ctl_output = newreno_ctl_output,
};

static inline struct newreno *
newreno_malloc(struct cc_var *ccv)
{
	struct newreno *nreno;

	nreno = malloc(sizeof(struct newreno), M_NEWRENO, M_NOWAIT);
	if (nreno != NULL) {
		/* NB: nreno is not zeroed, so initialise all fields. */
		nreno->beta = V_newreno_beta;
		nreno->beta_ecn = V_newreno_beta_ecn;
		nreno->newreno_flags = 0;
		ccv->cc_data = nreno;
	}

	return (nreno);
}

static void
newreno_cb_destroy(struct cc_var *ccv)
{
	free(ccv->cc_data, M_NEWRENO);
}

static void
newreno_ack_received(struct cc_var *ccv, uint16_t type)
{
	if (type == CC_ACK && !IN_RECOVERY(CCV(ccv, t_flags)) &&
	    (ccv->flags & CCF_CWND_LIMITED)) {
		u_int cw = CCV(ccv, snd_cwnd);
		u_int incr = CCV(ccv, t_maxseg);

		/*
		 * Regular in-order ACK, open the congestion window.
		 * Method depends on which congestion control state we're
		 * in (slow start or cong avoid) and if ABC (RFC 3465) is
		 * enabled.
		 *
		 * slow start: cwnd <= ssthresh
		 * cong avoid: cwnd > ssthresh
		 *
		 * slow start and ABC (RFC 3465):
		 *   Grow cwnd exponentially by the amount of data
		 *   ACKed capping the max increment per ACK to
		 *   (abc_l_var * maxseg) bytes.
		 *
		 * slow start without ABC (RFC 5681):
		 *   Grow cwnd exponentially by maxseg per ACK.
		 *
		 * cong avoid and ABC (RFC 3465):
		 *   Grow cwnd linearly by maxseg per RTT for each
		 *   cwnd worth of ACKed data.
		 *
		 * cong avoid without ABC (RFC 5681):
		 *   Grow cwnd linearly by approximately maxseg per RTT using
		 *   maxseg^2 / cwnd per ACK as the increment.
		 *   If cwnd > maxseg^2, fix the cwnd increment at 1 byte to
		 *   avoid capping cwnd.
		 */
		if (cw > CCV(ccv, snd_ssthresh)) {
			if (V_tcp_do_rfc3465) {
				if (ccv->flags & CCF_ABC_SENTAWND)
					ccv->flags &= ~CCF_ABC_SENTAWND;
				else
					incr = 0;
			} else
				incr = max((incr * incr / cw), 1);
		} else if (V_tcp_do_rfc3465) {
			/*
			 * In slow-start with ABC enabled and no RTO in sight?
			 * (Must not use abc_l_var > 1 if slow starting after
			 * an RTO. On RTO, snd_nxt = snd_una, so the
			 * snd_nxt == snd_max check is sufficient to
			 * handle this).
			 *
			 * XXXLAS: Find a way to signal SS after RTO that
			 * doesn't rely on tcpcb vars.
			 */
			uint16_t abc_val;

			if (ccv->flags & CCF_USE_LOCAL_ABC)
				abc_val = ccv->labc;
			else
				abc_val = V_tcp_abc_l_var;
			if (CCV(ccv, snd_nxt) == CCV(ccv, snd_max))
				incr = min(ccv->bytes_this_ack,
				    ccv->nsegs * abc_val *
				    CCV(ccv, t_maxseg));
			else
				incr = min(ccv->bytes_this_ack, CCV(ccv, t_maxseg));
		}
		/* ABC is on by default, so incr equals 0 frequently. */
		if (incr > 0)
			CCV(ccv, snd_cwnd) = min(cw + incr,
			    TCP_MAXWIN << CCV(ccv, snd_scale));
	}
}

static void
newreno_after_idle(struct cc_var *ccv)
{
	uint32_t rw;

	/*
	 * If we've been idle for more than one retransmit timeout the old
	 * congestion window is no longer current and we have to reduce it to
	 * the restart window before we can transmit again.
	 *
	 * The restart window is the initial window or the last CWND, whichever
	 * is smaller.
	 *
	 * This is done to prevent us from flooding the path with a full CWND at
	 * wirespeed, overloading router and switch buffers along the way.
	 *
	 * See RFC5681 Section 4.1. "Restarting Idle Connections".
	 *
	 * In addition, per RFC2861 Section 2, the ssthresh is set to the
	 * maximum of the former ssthresh or 3/4 of the old cwnd, to
	 * not exit slow-start prematurely.
	 */
	rw = tcp_compute_initwnd(tcp_maxseg(ccv->ccvc.tcp));

	CCV(ccv, snd_ssthresh) = max(CCV(ccv, snd_ssthresh),
	    CCV(ccv, snd_cwnd)-(CCV(ccv, snd_cwnd)>>2));

	CCV(ccv, snd_cwnd) = min(rw, CCV(ccv, snd_cwnd));
}

/*
 * Perform any necessary tasks before we enter congestion recovery.
 */
static void
newreno_cong_signal(struct cc_var *ccv, uint32_t type)
{
	struct newreno *nreno;
	uint32_t beta, beta_ecn, cwin, factor;
	u_int mss;

	cwin = CCV(ccv, snd_cwnd);
	mss = tcp_fixed_maxseg(ccv->ccvc.tcp);
	/*
	 * Other TCP congestion controls use newreno_cong_signal(), but
	 * with their own private cc_data. Make sure the cc_data is used
	 * correctly.
	 */
	nreno = (CC_ALGO(ccv->ccvc.tcp) == &newreno_cc_algo) ? ccv->cc_data : NULL;
	beta = (nreno == NULL) ? V_newreno_beta : nreno->beta;
	beta_ecn = (nreno == NULL) ? V_newreno_beta_ecn : nreno->beta_ecn;

	/*
	 * Note that we only change the backoff for ECN if the
	 * global sysctl V_cc_do_abe is set <or> the stack itself
	 * has set a flag in our newreno_flags (due to pacing) telling
	 * us to use the lower valued back-off.
	 */
	if ((type == CC_ECN) &&
	    (V_cc_do_abe ||
	    ((nreno != NULL) && (nreno->newreno_flags & CC_NEWRENO_BETA_ECN))))
		factor = beta_ecn;
	else
		factor = beta;

	/* Catch algos which mistakenly leak private signal types. */
	KASSERT((type & CC_SIGPRIVMASK) == 0,
	    ("%s: congestion signal type 0x%08x is private\n", __func__, type));

	cwin = max(((uint64_t)cwin * (uint64_t)factor) / (100ULL * (uint64_t)mss),
	    2) * mss;

	switch (type) {
	case CC_NDUPACK:
		if (!IN_FASTRECOVERY(CCV(ccv, t_flags))) {
			if (IN_CONGRECOVERY(CCV(ccv, t_flags) &&
			    V_cc_do_abe && V_cc_abe_frlossreduce)) {
				CCV(ccv, snd_ssthresh) =
				    ((uint64_t)CCV(ccv, snd_ssthresh) *
				     (uint64_t)beta) / (uint64_t)beta_ecn;
			}
			if (!IN_CONGRECOVERY(CCV(ccv, t_flags)))
				CCV(ccv, snd_ssthresh) = cwin;
			ENTER_RECOVERY(CCV(ccv, t_flags));
		}
		break;
	case CC_ECN:
		if (!IN_CONGRECOVERY(CCV(ccv, t_flags))) {
			CCV(ccv, snd_ssthresh) = cwin;
			CCV(ccv, snd_cwnd) = cwin;
			ENTER_CONGRECOVERY(CCV(ccv, t_flags));
		}
		break;
	case CC_RTO:
		CCV(ccv, snd_ssthresh) = max(min(CCV(ccv, snd_wnd),
						 CCV(ccv, snd_cwnd)) / 2 / mss,
					     2) * mss;
		CCV(ccv, snd_cwnd) = mss;
		break;
	}
}

/*
 * Perform any necessary tasks before we exit congestion recovery.
 */
static void
newreno_post_recovery(struct cc_var *ccv)
{
	int pipe;

	if (IN_FASTRECOVERY(CCV(ccv, t_flags))) {
		/*
		 * Fast recovery will conclude after returning from this
		 * function. Window inflation should have left us with
		 * approximately snd_ssthresh outstanding data. But in case we
		 * would be inclined to send a burst, better to do it via the
		 * slow start mechanism.
		 *
		 * XXXLAS: Find a way to do this without needing curack
		 */
		if (V_tcp_do_newsack)
			pipe = tcp_compute_pipe(ccv->ccvc.tcp);
		else
			pipe = CCV(ccv, snd_max) - ccv->curack;

		if (pipe < CCV(ccv, snd_ssthresh))
			/*
			 * Ensure that cwnd does not collapse to 1 MSS under
			 * adverse conditons. Implements RFC6582
			 */
			CCV(ccv, snd_cwnd) = max(pipe, CCV(ccv, t_maxseg)) +
			    CCV(ccv, t_maxseg);
		else
			CCV(ccv, snd_cwnd) = CCV(ccv, snd_ssthresh);
	}
}

static int
newreno_ctl_output(struct cc_var *ccv, struct sockopt *sopt, void *buf)
{
	struct newreno *nreno;
	struct cc_newreno_opts *opt;

	if (sopt->sopt_valsize != sizeof(struct cc_newreno_opts))
		return (EMSGSIZE);

	if (CC_ALGO(ccv->ccvc.tcp) != &newreno_cc_algo)
		return (ENOPROTOOPT);

	nreno = ccv->cc_data;
	opt = buf;

	switch (sopt->sopt_dir) {
	case SOPT_SET:
		/* We cannot set without cc_data memory. */
		if (nreno == NULL) {
			nreno = newreno_malloc(ccv);
			if (nreno == NULL)
				return (ENOMEM);
		}
		switch (opt->name) {
		case CC_NEWRENO_BETA:
			nreno->beta = opt->val;
			break;
		case CC_NEWRENO_BETA_ECN:
			if ((!V_cc_do_abe) && ((nreno->newreno_flags & CC_NEWRENO_BETA_ECN) == 0))
				return (EACCES);
			nreno->beta_ecn = opt->val;
			break;
		default:
			return (ENOPROTOOPT);
		}
		break;
	case SOPT_GET:
		switch (opt->name) {
		case CC_NEWRENO_BETA:
			opt->val = (nreno == NULL) ?
			    V_newreno_beta : nreno->beta;
			break;
		case CC_NEWRENO_BETA_ECN:
			opt->val = (nreno == NULL) ?
			    V_newreno_beta_ecn : nreno->beta_ecn;
			break;
		default:
			return (ENOPROTOOPT);
		}
		break;
	default:
		return (EINVAL);
	}

	return (0);
}

static int
newreno_beta_handler(SYSCTL_HANDLER_ARGS)
{
	int error;
	uint32_t new;

	new = *(uint32_t *)arg1;
	error = sysctl_handle_int(oidp, &new, 0, req);
	if (error == 0 && req->newptr != NULL ) {
		if (arg1 == &VNET_NAME(newreno_beta_ecn) && !V_cc_do_abe)
			error = EACCES;
		else if (new == 0 || new > 100)
			error = EINVAL;
		else
			*(uint32_t *)arg1 = new;
	}

	return (error);
}

SYSCTL_DECL(_net_inet_tcp_cc_newreno);
SYSCTL_NODE(_net_inet_tcp_cc, OID_AUTO, newreno,
    CTLFLAG_RW | CTLFLAG_MPSAFE, NULL,
    "New Reno related settings");

SYSCTL_PROC(_net_inet_tcp_cc_newreno, OID_AUTO, beta,
    CTLFLAG_VNET | CTLTYPE_UINT | CTLFLAG_RW | CTLFLAG_NEEDGIANT,
    &VNET_NAME(newreno_beta), 3, &newreno_beta_handler, "IU",
    "New Reno beta, specified as number between 1 and 100");

SYSCTL_PROC(_net_inet_tcp_cc_newreno, OID_AUTO, beta_ecn,
    CTLFLAG_VNET | CTLTYPE_UINT | CTLFLAG_RW | CTLFLAG_NEEDGIANT,
    &VNET_NAME(newreno_beta_ecn), 3, &newreno_beta_handler, "IU",
    "New Reno beta ecn, specified as number between 1 and 100");

DECLARE_CC_MODULE(newreno, &newreno_cc_algo);
MODULE_VERSION(newreno, 1);