summaryrefslogtreecommitdiffstats
path: root/drivers/cpufreq/cpufreq_governor.c
blob: 47e24b5384b37978cde5ce1f0e2eeb440e6ea04b (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
/*
 * drivers/cpufreq/cpufreq_governor.c
 *
 * CPUFREQ governors common code
 *
 * Copyright	(C) 2001 Russell King
 *		(C) 2003 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>.
 *		(C) 2003 Jun Nakajima <jun.nakajima@intel.com>
 *		(C) 2009 Alexander Clouter <alex@digriz.org.uk>
 *		(c) 2012 Viresh Kumar <viresh.kumar@linaro.org>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/export.h>
#include <linux/kernel_stat.h>
#include <linux/slab.h>

#include "cpufreq_governor.h"

static DEFINE_PER_CPU(struct cpu_dbs_info, cpu_dbs);

static DEFINE_MUTEX(gov_dbs_data_mutex);

/* Common sysfs tunables */
/**
 * store_sampling_rate - update sampling rate effective immediately if needed.
 *
 * If new rate is smaller than the old, simply updating
 * dbs.sampling_rate might not be appropriate. For example, if the
 * original sampling_rate was 1 second and the requested new sampling rate is 10
 * ms because the user needs immediate reaction from ondemand governor, but not
 * sure if higher frequency will be required or not, then, the governor may
 * change the sampling rate too late; up to 1 second later. Thus, if we are
 * reducing the sampling rate, we need to make the new value effective
 * immediately.
 *
 * This must be called with dbs_data->mutex held, otherwise traversing
 * policy_dbs_list isn't safe.
 */
ssize_t store_sampling_rate(struct gov_attr_set *attr_set, const char *buf,
			    size_t count)
{
	struct dbs_data *dbs_data = to_dbs_data(attr_set);
	struct policy_dbs_info *policy_dbs;
	unsigned int rate;
	int ret;
	ret = sscanf(buf, "%u", &rate);
	if (ret != 1)
		return -EINVAL;

	dbs_data->sampling_rate = max(rate, dbs_data->min_sampling_rate);

	/*
	 * We are operating under dbs_data->mutex and so the list and its
	 * entries can't be freed concurrently.
	 */
	list_for_each_entry(policy_dbs, &attr_set->policy_list, list) {
		mutex_lock(&policy_dbs->update_mutex);
		/*
		 * On 32-bit architectures this may race with the
		 * sample_delay_ns read in dbs_update_util_handler(), but that
		 * really doesn't matter.  If the read returns a value that's
		 * too big, the sample will be skipped, but the next invocation
		 * of dbs_update_util_handler() (when the update has been
		 * completed) will take a sample.
		 *
		 * If this runs in parallel with dbs_work_handler(), we may end
		 * up overwriting the sample_delay_ns value that it has just
		 * written, but it will be corrected next time a sample is
		 * taken, so it shouldn't be significant.
		 */
		gov_update_sample_delay(policy_dbs, 0);
		mutex_unlock(&policy_dbs->update_mutex);
	}

	return count;
}
EXPORT_SYMBOL_GPL(store_sampling_rate);

/**
 * gov_update_cpu_data - Update CPU load data.
 * @dbs_data: Top-level governor data pointer.
 *
 * Update CPU load data for all CPUs in the domain governed by @dbs_data
 * (that may be a single policy or a bunch of them if governor tunables are
 * system-wide).
 *
 * Call under the @dbs_data mutex.
 */
void gov_update_cpu_data(struct dbs_data *dbs_data)
{
	struct policy_dbs_info *policy_dbs;

	list_for_each_entry(policy_dbs, &dbs_data->attr_set.policy_list, list) {
		unsigned int j;

		for_each_cpu(j, policy_dbs->policy->cpus) {
			struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);

			j_cdbs->prev_cpu_idle = get_cpu_idle_time(j, &j_cdbs->prev_update_time,
								  dbs_data->io_is_busy);
			if (dbs_data->ignore_nice_load)
				j_cdbs->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
		}
	}
}
EXPORT_SYMBOL_GPL(gov_update_cpu_data);

unsigned int dbs_update(struct cpufreq_policy *policy)
{
	struct policy_dbs_info *policy_dbs = policy->governor_data;
	struct dbs_data *dbs_data = policy_dbs->dbs_data;
	unsigned int ignore_nice = dbs_data->ignore_nice_load;
	unsigned int max_load = 0, idle_periods = UINT_MAX;
	unsigned int sampling_rate, io_busy, j;

	/*
	 * Sometimes governors may use an additional multiplier to increase
	 * sample delays temporarily.  Apply that multiplier to sampling_rate
	 * so as to keep the wake-up-from-idle detection logic a bit
	 * conservative.
	 */
	sampling_rate = dbs_data->sampling_rate * policy_dbs->rate_mult;
	/*
	 * For the purpose of ondemand, waiting for disk IO is an indication
	 * that you're performance critical, and not that the system is actually
	 * idle, so do not add the iowait time to the CPU idle time then.
	 */
	io_busy = dbs_data->io_is_busy;

	/* Get Absolute Load */
	for_each_cpu(j, policy->cpus) {
		struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);
		u64 update_time, cur_idle_time;
		unsigned int idle_time, time_elapsed;
		unsigned int load;

		cur_idle_time = get_cpu_idle_time(j, &update_time, io_busy);

		time_elapsed = update_time - j_cdbs->prev_update_time;
		j_cdbs->prev_update_time = update_time;

		idle_time = cur_idle_time - j_cdbs->prev_cpu_idle;
		j_cdbs->prev_cpu_idle = cur_idle_time;

		if (ignore_nice) {
			u64 cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];

			idle_time += div_u64(cur_nice - j_cdbs->prev_cpu_nice, NSEC_PER_USEC);
			j_cdbs->prev_cpu_nice = cur_nice;
		}

		if (unlikely(!time_elapsed)) {
			/*
			 * That can only happen when this function is called
			 * twice in a row with a very short interval between the
			 * calls, so the previous load value can be used then.
			 */
			load = j_cdbs->prev_load;
		} else if (unlikely(time_elapsed > 2 * sampling_rate &&
				    j_cdbs->prev_load)) {
			/*
			 * If the CPU had gone completely idle and a task has
			 * just woken up on this CPU now, it would be unfair to
			 * calculate 'load' the usual way for this elapsed
			 * time-window, because it would show near-zero load,
			 * irrespective of how CPU intensive that task actually
			 * was. This is undesirable for latency-sensitive bursty
			 * workloads.
			 *
			 * To avoid this, reuse the 'load' from the previous
			 * time-window and give this task a chance to start with
			 * a reasonably high CPU frequency. However, that
			 * shouldn't be over-done, lest we get stuck at a high
			 * load (high frequency) for too long, even when the
			 * current system load has actually dropped down, so
			 * clear prev_load to guarantee that the load will be
			 * computed again next time.
			 *
			 * Detecting this situation is easy: the governor's
			 * utilization update handler would not have run during
			 * CPU-idle periods.  Hence, an unusually large
			 * 'time_elapsed' (as compared to the sampling rate)
			 * indicates this scenario.
			 */
			load = j_cdbs->prev_load;
			j_cdbs->prev_load = 0;
		} else {
			if (time_elapsed >= idle_time) {
				load = 100 * (time_elapsed - idle_time) / time_elapsed;
			} else {
				/*
				 * That can happen if idle_time is returned by
				 * get_cpu_idle_time_jiffy().  In that case
				 * idle_time is roughly equal to the difference
				 * between time_elapsed and "busy time" obtained
				 * from CPU statistics.  Then, the "busy time"
				 * can end up being greater than time_elapsed
				 * (for example, if jiffies_64 and the CPU
				 * statistics are updated by different CPUs),
				 * so idle_time may in fact be negative.  That
				 * means, though, that the CPU was busy all
				 * the time (on the rough average) during the
				 * last sampling interval and 100 can be
				 * returned as the load.
				 */
				load = (int)idle_time < 0 ? 100 : 0;
			}
			j_cdbs->prev_load = load;
		}

		if (time_elapsed > 2 * sampling_rate) {
			unsigned int periods = time_elapsed / sampling_rate;

			if (periods < idle_periods)
				idle_periods = periods;
		}

		if (load > max_load)
			max_load = load;
	}

	policy_dbs->idle_periods = idle_periods;

	return max_load;
}
EXPORT_SYMBOL_GPL(dbs_update);

static void dbs_work_handler(struct work_struct *work)
{
	struct policy_dbs_info *policy_dbs;
	struct cpufreq_policy *policy;
	struct dbs_governor *gov;

	policy_dbs = container_of(work, struct policy_dbs_info, work);
	policy = policy_dbs->policy;
	gov = dbs_governor_of(policy);

	/*
	 * Make sure cpufreq_governor_limits() isn't evaluating load or the
	 * ondemand governor isn't updating the sampling rate in parallel.
	 */
	mutex_lock(&policy_dbs->update_mutex);
	gov_update_sample_delay(policy_dbs, gov->gov_dbs_update(policy));
	mutex_unlock(&policy_dbs->update_mutex);

	/* Allow the utilization update handler to queue up more work. */
	atomic_set(&policy_dbs->work_count, 0);
	/*
	 * If the update below is reordered with respect to the sample delay
	 * modification, the utilization update handler may end up using a stale
	 * sample delay value.
	 */
	smp_wmb();
	policy_dbs->work_in_progress = false;
}

static void dbs_irq_work(struct irq_work *irq_work)
{
	struct policy_dbs_info *policy_dbs;

	policy_dbs = container_of(irq_work, struct policy_dbs_info, irq_work);
	schedule_work_on(smp_processor_id(), &policy_dbs->work);
}

static void dbs_update_util_handler(struct update_util_data *data, u64 time,
				    unsigned int flags)
{
	struct cpu_dbs_info *cdbs = container_of(data, struct cpu_dbs_info, update_util);
	struct policy_dbs_info *policy_dbs = cdbs->policy_dbs;
	u64 delta_ns, lst;

	/*
	 * The work may not be allowed to be queued up right now.
	 * Possible reasons:
	 * - Work has already been queued up or is in progress.
	 * - It is too early (too little time from the previous sample).
	 */
	if (policy_dbs->work_in_progress)
		return;

	/*
	 * If the reads below are reordered before the check above, the value
	 * of sample_delay_ns used in the computation may be stale.
	 */
	smp_rmb();
	lst = READ_ONCE(policy_dbs->last_sample_time);
	delta_ns = time - lst;
	if ((s64)delta_ns < policy_dbs->sample_delay_ns)
		return;

	/*
	 * If the policy is not shared, the irq_work may be queued up right away
	 * at this point.  Otherwise, we need to ensure that only one of the
	 * CPUs sharing the policy will do that.
	 */
	if (policy_dbs->is_shared) {
		if (!atomic_add_unless(&policy_dbs->work_count, 1, 1))
			return;

		/*
		 * If another CPU updated last_sample_time in the meantime, we
		 * shouldn't be here, so clear the work counter and bail out.
		 */
		if (unlikely(lst != READ_ONCE(policy_dbs->last_sample_time))) {
			atomic_set(&policy_dbs->work_count, 0);
			return;
		}
	}

	policy_dbs->last_sample_time = time;
	policy_dbs->work_in_progress = true;
	irq_work_queue(&policy_dbs->irq_work);
}

static void gov_set_update_util(struct policy_dbs_info *policy_dbs,
				unsigned int delay_us)
{
	struct cpufreq_policy *policy = policy_dbs->policy;
	int cpu;

	gov_update_sample_delay(policy_dbs, delay_us);
	policy_dbs->last_sample_time = 0;

	for_each_cpu(cpu, policy->cpus) {
		struct cpu_dbs_info *cdbs = &per_cpu(cpu_dbs, cpu);

		cpufreq_add_update_util_hook(cpu, &cdbs->update_util,
					     dbs_update_util_handler);
	}
}

static inline void gov_clear_update_util(struct cpufreq_policy *policy)
{
	int i;

	for_each_cpu(i, policy->cpus)
		cpufreq_remove_update_util_hook(i);

	synchronize_sched();
}

static struct policy_dbs_info *alloc_policy_dbs_info(struct cpufreq_policy *policy,
						     struct dbs_governor *gov)
{
	struct policy_dbs_info *policy_dbs;
	int j;

	/* Allocate memory for per-policy governor data. */
	policy_dbs = gov->alloc();
	if (!policy_dbs)
		return NULL;

	policy_dbs->policy = policy;
	mutex_init(&policy_dbs->update_mutex);
	atomic_set(&policy_dbs->work_count, 0);
	init_irq_work(&policy_dbs->irq_work, dbs_irq_work);
	INIT_WORK(&policy_dbs->work, dbs_work_handler);

	/* Set policy_dbs for all CPUs, online+offline */
	for_each_cpu(j, policy->related_cpus) {
		struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);

		j_cdbs->policy_dbs = policy_dbs;
	}
	return policy_dbs;
}

static void free_policy_dbs_info(struct policy_dbs_info *policy_dbs,
				 struct dbs_governor *gov)
{
	int j;

	mutex_destroy(&policy_dbs->update_mutex);

	for_each_cpu(j, policy_dbs->policy->related_cpus) {
		struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);

		j_cdbs->policy_dbs = NULL;
		j_cdbs->update_util.func = NULL;
	}
	gov->free(policy_dbs);
}

int cpufreq_dbs_governor_init(struct cpufreq_policy *policy)
{
	struct dbs_governor *gov = dbs_governor_of(policy);
	struct dbs_data *dbs_data;
	struct policy_dbs_info *policy_dbs;
	unsigned int latency;
	int ret = 0;

	/* State should be equivalent to EXIT */
	if (policy->governor_data)
		return -EBUSY;

	policy_dbs = alloc_policy_dbs_info(policy, gov);
	if (!policy_dbs)
		return -ENOMEM;

	/* Protect gov->gdbs_data against concurrent updates. */
	mutex_lock(&gov_dbs_data_mutex);

	dbs_data = gov->gdbs_data;
	if (dbs_data) {
		if (WARN_ON(have_governor_per_policy())) {
			ret = -EINVAL;
			goto free_policy_dbs_info;
		}
		policy_dbs->dbs_data = dbs_data;
		policy->governor_data = policy_dbs;

		gov_attr_set_get(&dbs_data->attr_set, &policy_dbs->list);
		goto out;
	}

	dbs_data = kzalloc(sizeof(*dbs_data), GFP_KERNEL);
	if (!dbs_data) {
		ret = -ENOMEM;
		goto free_policy_dbs_info;
	}

	gov_attr_set_init(&dbs_data->attr_set, &policy_dbs->list);

	ret = gov->init(dbs_data);
	if (ret)
		goto free_policy_dbs_info;

	/* policy latency is in ns. Convert it to us first */
	latency = policy->cpuinfo.transition_latency / 1000;
	if (latency == 0)
		latency = 1;

	/* Bring kernel and HW constraints together */
	dbs_data->min_sampling_rate = max(dbs_data->min_sampling_rate,
					  MIN_LATENCY_MULTIPLIER * latency);
	dbs_data->sampling_rate = max(dbs_data->min_sampling_rate,
				      LATENCY_MULTIPLIER * latency);

	if (!have_governor_per_policy())
		gov->gdbs_data = dbs_data;

	policy_dbs->dbs_data = dbs_data;
	policy->governor_data = policy_dbs;

	gov->kobj_type.sysfs_ops = &governor_sysfs_ops;
	ret = kobject_init_and_add(&dbs_data->attr_set.kobj, &gov->kobj_type,
				   get_governor_parent_kobj(policy),
				   "%s", gov->gov.name);
	if (!ret)
		goto out;

	/* Failure, so roll back. */
	pr_err("initialization failed (dbs_data kobject init error %d)\n", ret);

	policy->governor_data = NULL;

	if (!have_governor_per_policy())
		gov->gdbs_data = NULL;
	gov->exit(dbs_data);
	kfree(dbs_data);

free_policy_dbs_info:
	free_policy_dbs_info(policy_dbs, gov);

out:
	mutex_unlock(&gov_dbs_data_mutex);
	return ret;
}
EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_init);

void cpufreq_dbs_governor_exit(struct cpufreq_policy *policy)
{
	struct dbs_governor *gov = dbs_governor_of(policy);
	struct policy_dbs_info *policy_dbs = policy->governor_data;
	struct dbs_data *dbs_data = policy_dbs->dbs_data;
	unsigned int count;

	/* Protect gov->gdbs_data against concurrent updates. */
	mutex_lock(&gov_dbs_data_mutex);

	count = gov_attr_set_put(&dbs_data->attr_set, &policy_dbs->list);

	policy->governor_data = NULL;

	if (!count) {
		if (!have_governor_per_policy())
			gov->gdbs_data = NULL;

		gov->exit(dbs_data);
		kfree(dbs_data);
	}

	free_policy_dbs_info(policy_dbs, gov);

	mutex_unlock(&gov_dbs_data_mutex);
}
EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_exit);

int cpufreq_dbs_governor_start(struct cpufreq_policy *policy)
{
	struct dbs_governor *gov = dbs_governor_of(policy);
	struct policy_dbs_info *policy_dbs = policy->governor_data;
	struct dbs_data *dbs_data = policy_dbs->dbs_data;
	unsigned int sampling_rate, ignore_nice, j;
	unsigned int io_busy;

	if (!policy->cur)
		return -EINVAL;

	policy_dbs->is_shared = policy_is_shared(policy);
	policy_dbs->rate_mult = 1;

	sampling_rate = dbs_data->sampling_rate;
	ignore_nice = dbs_data->ignore_nice_load;
	io_busy = dbs_data->io_is_busy;

	for_each_cpu(j, policy->cpus) {
		struct cpu_dbs_info *j_cdbs = &per_cpu(cpu_dbs, j);

		j_cdbs->prev_cpu_idle = get_cpu_idle_time(j, &j_cdbs->prev_update_time, io_busy);
		/*
		 * Make the first invocation of dbs_update() compute the load.
		 */
		j_cdbs->prev_load = 0;

		if (ignore_nice)
			j_cdbs->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
	}

	gov->start(policy);

	gov_set_update_util(policy_dbs, sampling_rate);
	return 0;
}
EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_start);

void cpufreq_dbs_governor_stop(struct cpufreq_policy *policy)
{
	struct policy_dbs_info *policy_dbs = policy->governor_data;

	gov_clear_update_util(policy_dbs->policy);
	irq_work_sync(&policy_dbs->irq_work);
	cancel_work_sync(&policy_dbs->work);
	atomic_set(&policy_dbs->work_count, 0);
	policy_dbs->work_in_progress = false;
}
EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_stop);

void cpufreq_dbs_governor_limits(struct cpufreq_policy *policy)
{
	struct policy_dbs_info *policy_dbs = policy->governor_data;

	mutex_lock(&policy_dbs->update_mutex);
	cpufreq_policy_apply_limits(policy);
	gov_update_sample_delay(policy_dbs, 0);

	mutex_unlock(&policy_dbs->update_mutex);
}
EXPORT_SYMBOL_GPL(cpufreq_dbs_governor_limits);
OpenPOWER on IntegriCloud