summaryrefslogtreecommitdiffstats
path: root/drivers/base/power/domain_governor.c
blob: 282a3a135827ceeded2695b4a94b969f0eff6876 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * drivers/base/power/domain_governor.c - Governors for device PM domains.
 *
 * Copyright (C) 2011 Rafael J. Wysocki <rjw@sisk.pl>, Renesas Electronics Corp.
 */
#include <linux/kernel.h>
#include <linux/pm_domain.h>
#include <linux/pm_qos.h>
#include <linux/hrtimer.h>
#include <linux/cpuidle.h>
#include <linux/cpumask.h>
#include <linux/ktime.h>

static int dev_update_qos_constraint(struct device *dev, void *data)
{
	s64 *constraint_ns_p = data;
	s64 constraint_ns;

	if (dev->power.subsys_data && dev->power.subsys_data->domain_data) {
		struct gpd_timing_data *td = dev_gpd_data(dev)->td;

		/*
		 * Only take suspend-time QoS constraints of devices into
		 * account, because constraints updated after the device has
		 * been suspended are not guaranteed to be taken into account
		 * anyway.  In order for them to take effect, the device has to
		 * be resumed and suspended again.
		 */
		constraint_ns = td ? td->effective_constraint_ns :
				PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS;
	} else {
		/*
		 * The child is not in a domain and there's no info on its
		 * suspend/resume latencies, so assume them to be negligible and
		 * take its current PM QoS constraint (that's the only thing
		 * known at this point anyway).
		 */
		constraint_ns = dev_pm_qos_read_value(dev, DEV_PM_QOS_RESUME_LATENCY);
		constraint_ns *= NSEC_PER_USEC;
	}

	if (constraint_ns < *constraint_ns_p)
		*constraint_ns_p = constraint_ns;

	return 0;
}

/**
 * default_suspend_ok - Default PM domain governor routine to suspend devices.
 * @dev: Device to check.
 */
static bool default_suspend_ok(struct device *dev)
{
	struct gpd_timing_data *td = dev_gpd_data(dev)->td;
	unsigned long flags;
	s64 constraint_ns;

	dev_dbg(dev, "%s()\n", __func__);

	spin_lock_irqsave(&dev->power.lock, flags);

	if (!td->constraint_changed) {
		bool ret = td->cached_suspend_ok;

		spin_unlock_irqrestore(&dev->power.lock, flags);
		return ret;
	}
	td->constraint_changed = false;
	td->cached_suspend_ok = false;
	td->effective_constraint_ns = 0;
	constraint_ns = __dev_pm_qos_resume_latency(dev);

	spin_unlock_irqrestore(&dev->power.lock, flags);

	if (constraint_ns == 0)
		return false;

	constraint_ns *= NSEC_PER_USEC;
	/*
	 * We can walk the children without any additional locking, because
	 * they all have been suspended at this point and their
	 * effective_constraint_ns fields won't be modified in parallel with us.
	 */
	if (!dev->power.ignore_children)
		device_for_each_child(dev, &constraint_ns,
				      dev_update_qos_constraint);

	if (constraint_ns == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS) {
		/* "No restriction", so the device is allowed to suspend. */
		td->effective_constraint_ns = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS;
		td->cached_suspend_ok = true;
	} else if (constraint_ns == 0) {
		/*
		 * This triggers if one of the children that don't belong to a
		 * domain has a zero PM QoS constraint and it's better not to
		 * suspend then.  effective_constraint_ns is zero already and
		 * cached_suspend_ok is false, so bail out.
		 */
		return false;
	} else {
		constraint_ns -= td->suspend_latency_ns +
				td->resume_latency_ns;
		/*
		 * effective_constraint_ns is zero already and cached_suspend_ok
		 * is false, so if the computed value is not positive, return
		 * right away.
		 */
		if (constraint_ns <= 0)
			return false;

		td->effective_constraint_ns = constraint_ns;
		td->cached_suspend_ok = true;
	}

	/*
	 * The children have been suspended already, so we don't need to take
	 * their suspend latencies into account here.
	 */
	return td->cached_suspend_ok;
}

static void update_domain_next_wakeup(struct generic_pm_domain *genpd, ktime_t now)
{
	ktime_t domain_wakeup = KTIME_MAX;
	ktime_t next_wakeup;
	struct pm_domain_data *pdd;
	struct gpd_link *link;

	if (!(genpd->flags & GENPD_FLAG_MIN_RESIDENCY))
		return;

	/*
	 * Devices that have a predictable wakeup pattern, may specify
	 * their next wakeup. Let's find the next wakeup from all the
	 * devices attached to this domain and from all the sub-domains.
	 * It is possible that component's a next wakeup may have become
	 * stale when we read that here. We will ignore to ensure the domain
	 * is able to enter its optimal idle state.
	 */
	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
		next_wakeup = to_gpd_data(pdd)->td->next_wakeup;
		if (next_wakeup != KTIME_MAX && !ktime_before(next_wakeup, now))
			if (ktime_before(next_wakeup, domain_wakeup))
				domain_wakeup = next_wakeup;
	}

	list_for_each_entry(link, &genpd->parent_links, parent_node) {
		struct genpd_governor_data *cgd = link->child->gd;

		next_wakeup = cgd ? cgd->next_wakeup : KTIME_MAX;
		if (next_wakeup != KTIME_MAX && !ktime_before(next_wakeup, now))
			if (ktime_before(next_wakeup, domain_wakeup))
				domain_wakeup = next_wakeup;
	}

	genpd->gd->next_wakeup = domain_wakeup;
}

static bool next_wakeup_allows_state(struct generic_pm_domain *genpd,
				     unsigned int state, ktime_t now)
{
	ktime_t domain_wakeup = genpd->gd->next_wakeup;
	s64 idle_time_ns, min_sleep_ns;

	min_sleep_ns = genpd->states[state].power_off_latency_ns +
		       genpd->states[state].residency_ns;

	idle_time_ns = ktime_to_ns(ktime_sub(domain_wakeup, now));

	return idle_time_ns >= min_sleep_ns;
}

static bool __default_power_down_ok(struct dev_pm_domain *pd,
				     unsigned int state)
{
	struct generic_pm_domain *genpd = pd_to_genpd(pd);
	struct gpd_link *link;
	struct pm_domain_data *pdd;
	s64 min_off_time_ns;
	s64 off_on_time_ns;

	off_on_time_ns = genpd->states[state].power_off_latency_ns +
		genpd->states[state].power_on_latency_ns;

	min_off_time_ns = -1;
	/*
	 * Check if subdomains can be off for enough time.
	 *
	 * All subdomains have been powered off already at this point.
	 */
	list_for_each_entry(link, &genpd->parent_links, parent_node) {
		struct genpd_governor_data *cgd = link->child->gd;

		s64 sd_max_off_ns = cgd ? cgd->max_off_time_ns : -1;

		if (sd_max_off_ns < 0)
			continue;

		/*
		 * Check if the subdomain is allowed to be off long enough for
		 * the current domain to turn off and on (that's how much time
		 * it will have to wait worst case).
		 */
		if (sd_max_off_ns <= off_on_time_ns)
			return false;

		if (min_off_time_ns > sd_max_off_ns || min_off_time_ns < 0)
			min_off_time_ns = sd_max_off_ns;
	}

	/*
	 * Check if the devices in the domain can be off enough time.
	 */
	list_for_each_entry(pdd, &genpd->dev_list, list_node) {
		struct gpd_timing_data *td;
		s64 constraint_ns;

		/*
		 * Check if the device is allowed to be off long enough for the
		 * domain to turn off and on (that's how much time it will
		 * have to wait worst case).
		 */
		td = to_gpd_data(pdd)->td;
		constraint_ns = td->effective_constraint_ns;
		/*
		 * Zero means "no suspend at all" and this runs only when all
		 * devices in the domain are suspended, so it must be positive.
		 */
		if (constraint_ns == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS)
			continue;

		if (constraint_ns <= off_on_time_ns)
			return false;

		if (min_off_time_ns > constraint_ns || min_off_time_ns < 0)
			min_off_time_ns = constraint_ns;
	}

	/*
	 * If the computed minimum device off time is negative, there are no
	 * latency constraints, so the domain can spend arbitrary time in the
	 * "off" state.
	 */
	if (min_off_time_ns < 0)
		return true;

	/*
	 * The difference between the computed minimum subdomain or device off
	 * time and the time needed to turn the domain on is the maximum
	 * theoretical time this domain can spend in the "off" state.
	 */
	genpd->gd->max_off_time_ns = min_off_time_ns -
		genpd->states[state].power_on_latency_ns;
	return true;
}

/**
 * _default_power_down_ok - Default generic PM domain power off governor routine.
 * @pd: PM domain to check.
 * @now: current ktime.
 *
 * This routine must be executed under the PM domain's lock.
 */
static bool _default_power_down_ok(struct dev_pm_domain *pd, ktime_t now)
{
	struct generic_pm_domain *genpd = pd_to_genpd(pd);
	struct genpd_governor_data *gd = genpd->gd;
	int state_idx = genpd->state_count - 1;
	struct gpd_link *link;

	/*
	 * Find the next wakeup from devices that can determine their own wakeup
	 * to find when the domain would wakeup and do it for every device down
	 * the hierarchy. It is not worth while to sleep if the state's residency
	 * cannot be met.
	 */
	update_domain_next_wakeup(genpd, now);
	if ((genpd->flags & GENPD_FLAG_MIN_RESIDENCY) && (gd->next_wakeup != KTIME_MAX)) {
		/* Let's find out the deepest domain idle state, the devices prefer */
		while (state_idx >= 0) {
			if (next_wakeup_allows_state(genpd, state_idx, now)) {
				gd->max_off_time_changed = true;
				break;
			}
			state_idx--;
		}

		if (state_idx < 0) {
			state_idx = 0;
			gd->cached_power_down_ok = false;
			goto done;
		}
	}

	if (!gd->max_off_time_changed) {
		genpd->state_idx = gd->cached_power_down_state_idx;
		return gd->cached_power_down_ok;
	}

	/*
	 * We have to invalidate the cached results for the parents, so
	 * use the observation that default_power_down_ok() is not
	 * going to be called for any parent until this instance
	 * returns.
	 */
	list_for_each_entry(link, &genpd->child_links, child_node) {
		struct genpd_governor_data *pgd = link->parent->gd;

		if (pgd)
			pgd->max_off_time_changed = true;
	}

	gd->max_off_time_ns = -1;
	gd->max_off_time_changed = false;
	gd->cached_power_down_ok = true;

	/*
	 * Find a state to power down to, starting from the state
	 * determined by the next wakeup.
	 */
	while (!__default_power_down_ok(pd, state_idx)) {
		if (state_idx == 0) {
			gd->cached_power_down_ok = false;
			break;
		}
		state_idx--;
	}

done:
	genpd->state_idx = state_idx;
	gd->cached_power_down_state_idx = genpd->state_idx;
	return gd->cached_power_down_ok;
}

static bool default_power_down_ok(struct dev_pm_domain *pd)
{
	return _default_power_down_ok(pd, ktime_get());
}

#ifdef CONFIG_CPU_IDLE
static bool cpu_power_down_ok(struct dev_pm_domain *pd)
{
	struct generic_pm_domain *genpd = pd_to_genpd(pd);
	struct cpuidle_device *dev;
	ktime_t domain_wakeup, next_hrtimer;
	ktime_t now = ktime_get();
	s64 idle_duration_ns;
	int cpu, i;

	/* Validate dev PM QoS constraints. */
	if (!_default_power_down_ok(pd, now))
		return false;

	if (!(genpd->flags & GENPD_FLAG_CPU_DOMAIN))
		return true;

	/*
	 * Find the next wakeup for any of the online CPUs within the PM domain
	 * and its subdomains. Note, we only need the genpd->cpus, as it already
	 * contains a mask of all CPUs from subdomains.
	 */
	domain_wakeup = ktime_set(KTIME_SEC_MAX, 0);
	for_each_cpu_and(cpu, genpd->cpus, cpu_online_mask) {
		dev = per_cpu(cpuidle_devices, cpu);
		if (dev) {
			next_hrtimer = READ_ONCE(dev->next_hrtimer);
			if (ktime_before(next_hrtimer, domain_wakeup))
				domain_wakeup = next_hrtimer;
		}
	}

	/* The minimum idle duration is from now - until the next wakeup. */
	idle_duration_ns = ktime_to_ns(ktime_sub(domain_wakeup, now));
	if (idle_duration_ns <= 0)
		return false;

	/*
	 * Find the deepest idle state that has its residency value satisfied
	 * and by also taking into account the power off latency for the state.
	 * Start at the state picked by the dev PM QoS constraint validation.
	 */
	i = genpd->state_idx;
	do {
		if (idle_duration_ns >= (genpd->states[i].residency_ns +
		    genpd->states[i].power_off_latency_ns)) {
			genpd->state_idx = i;
			return true;
		}
	} while (--i >= 0);

	return false;
}

struct dev_power_governor pm_domain_cpu_gov = {
	.suspend_ok = default_suspend_ok,
	.power_down_ok = cpu_power_down_ok,
};
#endif

struct dev_power_governor simple_qos_governor = {
	.suspend_ok = default_suspend_ok,
	.power_down_ok = default_power_down_ok,
};

/**
 * pm_genpd_gov_always_on - A governor implementing an always-on policy
 */
struct dev_power_governor pm_domain_always_on_gov = {
	.suspend_ok = default_suspend_ok,
};