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
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
|
/*
* drivers/cpufreq/cpufreq_interactive.c
*
* Copyright (C) 2010 Google, Inc.
*
* This software is licensed under the terms of the GNU General Public
* License version 2, as published by the Free Software Foundation, and
* may be copied, distributed, and modified under those terms.
*
* This program is distributed in the hope that it 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.
*
* Author: Mike Chan (mike@android.com)
*
*/
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/cpufreq.h>
#include <linux/mutex.h>
#include <linux/sched.h>
#include <linux/tick.h>
#include <linux/timer.h>
#include <linux/workqueue.h>
#include <linux/kthread.h>
#include <asm/cputime.h>
static atomic_t active_count = ATOMIC_INIT(0);
struct cpufreq_interactive_cpuinfo {
struct timer_list cpu_timer;
int timer_idlecancel;
u64 time_in_idle;
u64 idle_exit_time;
u64 timer_run_time;
int idling;
u64 freq_change_time;
u64 freq_change_time_in_idle;
struct cpufreq_policy *policy;
struct cpufreq_frequency_table *freq_table;
unsigned int target_freq;
int governor_enabled;
};
static DEFINE_PER_CPU(struct cpufreq_interactive_cpuinfo, cpuinfo);
/* Workqueues handle frequency scaling */
static struct task_struct *up_task;
static struct workqueue_struct *down_wq;
static struct work_struct freq_scale_down_work;
static cpumask_t up_cpumask;
static spinlock_t up_cpumask_lock;
static cpumask_t down_cpumask;
static spinlock_t down_cpumask_lock;
/* Go to max speed when CPU load at or above this value. */
#define DEFAULT_GO_MAXSPEED_LOAD 85
static unsigned long go_maxspeed_load;
/*
* The minimum amount of time to spend at a frequency before we can ramp down.
*/
#define DEFAULT_MIN_SAMPLE_TIME 80000;
static unsigned long min_sample_time;
/*
* The sample rate of the timer used to increase frequency
*/
#define DEFAULT_TIMER_RATE 30000;
static unsigned long timer_rate;
static int cpufreq_governor_interactive(struct cpufreq_policy *policy,
unsigned int event);
#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE
static
#endif
struct cpufreq_governor cpufreq_gov_interactive = {
.name = "interactive",
.governor = cpufreq_governor_interactive,
.max_transition_latency = 10000000,
.owner = THIS_MODULE,
};
static void cpufreq_interactive_timer(unsigned long data)
{
unsigned int delta_idle;
unsigned int delta_time;
int cpu_load;
int load_since_change;
u64 time_in_idle;
u64 idle_exit_time;
struct cpufreq_interactive_cpuinfo *pcpu =
&per_cpu(cpuinfo, data);
u64 now_idle;
unsigned int new_freq;
unsigned int index;
unsigned long flags;
smp_rmb();
if (!pcpu->governor_enabled)
goto exit;
/*
* Once pcpu->timer_run_time is updated to >= pcpu->idle_exit_time,
* this lets idle exit know the current idle time sample has
* been processed, and idle exit can generate a new sample and
* re-arm the timer. This prevents a concurrent idle
* exit on that CPU from writing a new set of info at the same time
* the timer function runs (the timer function can't use that info
* until more time passes).
*/
time_in_idle = pcpu->time_in_idle;
idle_exit_time = pcpu->idle_exit_time;
now_idle = get_cpu_idle_time_us(data, &pcpu->timer_run_time);
smp_wmb();
/* If we raced with cancelling a timer, skip. */
if (!idle_exit_time)
goto exit;
delta_idle = (unsigned int) cputime64_sub(now_idle, time_in_idle);
delta_time = (unsigned int) cputime64_sub(pcpu->timer_run_time,
idle_exit_time);
/*
* If timer ran less than 1ms after short-term sample started, retry.
*/
if (delta_time < 1000)
goto rearm;
if (delta_idle > delta_time)
cpu_load = 0;
else
cpu_load = 100 * (delta_time - delta_idle) / delta_time;
delta_idle = (unsigned int) cputime64_sub(now_idle,
pcpu->freq_change_time_in_idle);
delta_time = (unsigned int) cputime64_sub(pcpu->timer_run_time,
pcpu->freq_change_time);
if (delta_idle > delta_time)
load_since_change = 0;
else
load_since_change =
100 * (delta_time - delta_idle) / delta_time;
/*
* Choose greater of short-term load (since last idle timer
* started or timer function re-armed itself) or long-term load
* (since last frequency change).
*/
if (load_since_change > cpu_load)
cpu_load = load_since_change;
if (cpu_load >= go_maxspeed_load)
new_freq = pcpu->policy->max;
else
new_freq = pcpu->policy->max * cpu_load / 100;
if (cpufreq_frequency_table_target(pcpu->policy, pcpu->freq_table,
new_freq, CPUFREQ_RELATION_H,
&index)) {
pr_warn_once("timer %d: cpufreq_frequency_table_target error\n",
(int) data);
goto rearm;
}
new_freq = pcpu->freq_table[index].frequency;
if (pcpu->target_freq == new_freq)
goto rearm_if_notmax;
/*
* Do not scale down unless we have been at this frequency for the
* minimum sample time.
*/
if (new_freq < pcpu->target_freq) {
if (cputime64_sub(pcpu->timer_run_time, pcpu->freq_change_time) <
min_sample_time)
goto rearm;
}
if (new_freq < pcpu->target_freq) {
pcpu->target_freq = new_freq;
spin_lock_irqsave(&down_cpumask_lock, flags);
cpumask_set_cpu(data, &down_cpumask);
spin_unlock_irqrestore(&down_cpumask_lock, flags);
queue_work(down_wq, &freq_scale_down_work);
} else {
pcpu->target_freq = new_freq;
spin_lock_irqsave(&up_cpumask_lock, flags);
cpumask_set_cpu(data, &up_cpumask);
spin_unlock_irqrestore(&up_cpumask_lock, flags);
wake_up_process(up_task);
}
rearm_if_notmax:
/*
* Already set max speed and don't see a need to change that,
* wait until next idle to re-evaluate, don't need timer.
*/
if (pcpu->target_freq == pcpu->policy->max)
goto exit;
rearm:
if (!timer_pending(&pcpu->cpu_timer)) {
/*
* If already at min: if that CPU is idle, don't set timer.
* Else cancel the timer if that CPU goes idle. We don't
* need to re-evaluate speed until the next idle exit.
*/
if (pcpu->target_freq == pcpu->policy->min) {
smp_rmb();
if (pcpu->idling)
goto exit;
pcpu->timer_idlecancel = 1;
}
pcpu->time_in_idle = get_cpu_idle_time_us(
data, &pcpu->idle_exit_time);
mod_timer(&pcpu->cpu_timer, jiffies + usecs_to_jiffies(timer_rate));
}
exit:
return;
}
static void cpufreq_interactive_idle_start(void)
{
struct cpufreq_interactive_cpuinfo *pcpu =
&per_cpu(cpuinfo, smp_processor_id());
int pending;
if (!pcpu->governor_enabled) {
return;
}
pcpu->idling = 1;
smp_wmb();
pending = timer_pending(&pcpu->cpu_timer);
if (pcpu->target_freq != pcpu->policy->min) {
#ifdef CONFIG_SMP
/*
* Entering idle while not at lowest speed. On some
* platforms this can hold the other CPU(s) at that speed
* even though the CPU is idle. Set a timer to re-evaluate
* speed so this idle CPU doesn't hold the other CPUs above
* min indefinitely. This should probably be a quirk of
* the CPUFreq driver.
*/
if (!pending) {
pcpu->time_in_idle = get_cpu_idle_time_us(
smp_processor_id(), &pcpu->idle_exit_time);
pcpu->timer_idlecancel = 0;
mod_timer(&pcpu->cpu_timer, jiffies + usecs_to_jiffies(timer_rate));
}
#endif
} else {
/*
* If at min speed and entering idle after load has
* already been evaluated, and a timer has been set just in
* case the CPU suddenly goes busy, cancel that timer. The
* CPU didn't go busy; we'll recheck things upon idle exit.
*/
if (pending && pcpu->timer_idlecancel) {
del_timer(&pcpu->cpu_timer);
/*
* Ensure last timer run time is after current idle
* sample start time, so next idle exit will always
* start a new idle sampling period.
*/
pcpu->idle_exit_time = 0;
pcpu->timer_idlecancel = 0;
}
}
}
static void cpufreq_interactive_idle_end(void)
{
struct cpufreq_interactive_cpuinfo *pcpu =
&per_cpu(cpuinfo, smp_processor_id());
pcpu->idling = 0;
smp_wmb();
/*
* Arm the timer for 1-2 ticks later if not already, and if the timer
* function has already processed the previous load sampling
* interval. (If the timer is not pending but has not processed
* the previous interval, it is probably racing with us on another
* CPU. Let it compute load based on the previous sample and then
* re-arm the timer for another interval when it's done, rather
* than updating the interval start time to be "now", which doesn't
* give the timer function enough time to make a decision on this
* run.)
*/
if (timer_pending(&pcpu->cpu_timer) == 0 &&
pcpu->timer_run_time >= pcpu->idle_exit_time &&
pcpu->governor_enabled) {
pcpu->time_in_idle =
get_cpu_idle_time_us(smp_processor_id(),
&pcpu->idle_exit_time);
pcpu->timer_idlecancel = 0;
mod_timer(&pcpu->cpu_timer, jiffies + usecs_to_jiffies(timer_rate));
}
}
static int cpufreq_interactive_up_task(void *data)
{
unsigned int cpu;
cpumask_t tmp_mask;
unsigned long flags;
struct cpufreq_interactive_cpuinfo *pcpu;
while (1) {
set_current_state(TASK_INTERRUPTIBLE);
spin_lock_irqsave(&up_cpumask_lock, flags);
if (cpumask_empty(&up_cpumask)) {
spin_unlock_irqrestore(&up_cpumask_lock, flags);
schedule();
if (kthread_should_stop())
break;
spin_lock_irqsave(&up_cpumask_lock, flags);
}
set_current_state(TASK_RUNNING);
tmp_mask = up_cpumask;
cpumask_clear(&up_cpumask);
spin_unlock_irqrestore(&up_cpumask_lock, flags);
for_each_cpu(cpu, &tmp_mask) {
pcpu = &per_cpu(cpuinfo, cpu);
smp_rmb();
if (!pcpu->governor_enabled)
continue;
__cpufreq_driver_target(pcpu->policy,
pcpu->target_freq,
CPUFREQ_RELATION_H);
pcpu->freq_change_time_in_idle =
get_cpu_idle_time_us(cpu,
&pcpu->freq_change_time);
}
}
return 0;
}
static void cpufreq_interactive_freq_down(struct work_struct *work)
{
unsigned int cpu;
cpumask_t tmp_mask;
unsigned long flags;
struct cpufreq_interactive_cpuinfo *pcpu;
spin_lock_irqsave(&down_cpumask_lock, flags);
tmp_mask = down_cpumask;
cpumask_clear(&down_cpumask);
spin_unlock_irqrestore(&down_cpumask_lock, flags);
for_each_cpu(cpu, &tmp_mask) {
pcpu = &per_cpu(cpuinfo, cpu);
smp_rmb();
if (!pcpu->governor_enabled)
continue;
__cpufreq_driver_target(pcpu->policy,
pcpu->target_freq,
CPUFREQ_RELATION_H);
pcpu->freq_change_time_in_idle =
get_cpu_idle_time_us(cpu,
&pcpu->freq_change_time);
}
}
static ssize_t show_go_maxspeed_load(struct kobject *kobj,
struct attribute *attr, char *buf)
{
return sprintf(buf, "%lu\n", go_maxspeed_load);
}
static ssize_t store_go_maxspeed_load(struct kobject *kobj,
struct attribute *attr, const char *buf, size_t count)
{
int ret;
unsigned long val;
ret = strict_strtoul(buf, 0, &val);
if (ret < 0)
return ret;
go_maxspeed_load = val;
return count;
}
static struct global_attr go_maxspeed_load_attr = __ATTR(go_maxspeed_load, 0644,
show_go_maxspeed_load, store_go_maxspeed_load);
static ssize_t show_min_sample_time(struct kobject *kobj,
struct attribute *attr, char *buf)
{
return sprintf(buf, "%lu\n", min_sample_time);
}
static ssize_t store_min_sample_time(struct kobject *kobj,
struct attribute *attr, const char *buf, size_t count)
{
int ret;
unsigned long val;
ret = strict_strtoul(buf, 0, &val);
if (ret < 0)
return ret;
min_sample_time = val;
return count;
}
static struct global_attr min_sample_time_attr = __ATTR(min_sample_time, 0644,
show_min_sample_time, store_min_sample_time);
static ssize_t show_timer_rate(struct kobject *kobj,
struct attribute *attr, char *buf)
{
return sprintf(buf, "%lu\n", timer_rate);
}
static ssize_t store_timer_rate(struct kobject *kobj,
struct attribute *attr, const char *buf, size_t count)
{
int ret;
unsigned long val;
ret = strict_strtoul(buf, 0, &val);
if (ret < 0)
return ret;
timer_rate = val;
return count;
}
static struct global_attr timer_rate_attr = __ATTR(timer_rate, 0644,
show_timer_rate, store_timer_rate);
static struct attribute *interactive_attributes[] = {
&go_maxspeed_load_attr.attr,
&min_sample_time_attr.attr,
&timer_rate_attr.attr,
NULL,
};
static struct attribute_group interactive_attr_group = {
.attrs = interactive_attributes,
.name = "interactive",
};
static int cpufreq_governor_interactive(struct cpufreq_policy *policy,
unsigned int event)
{
int rc;
unsigned int j;
struct cpufreq_interactive_cpuinfo *pcpu;
struct cpufreq_frequency_table *freq_table;
switch (event) {
case CPUFREQ_GOV_START:
if (!cpu_online(policy->cpu))
return -EINVAL;
freq_table =
cpufreq_frequency_get_table(policy->cpu);
for_each_cpu(j, policy->cpus) {
pcpu = &per_cpu(cpuinfo, j);
pcpu->policy = policy;
pcpu->target_freq = policy->cur;
pcpu->freq_table = freq_table;
pcpu->freq_change_time_in_idle =
get_cpu_idle_time_us(j,
&pcpu->freq_change_time);
pcpu->governor_enabled = 1;
smp_wmb();
}
/*
* Do not register the idle hook and create sysfs
* entries if we have already done so.
*/
if (atomic_inc_return(&active_count) > 1)
return 0;
rc = sysfs_create_group(cpufreq_global_kobject,
&interactive_attr_group);
if (rc)
return rc;
break;
case CPUFREQ_GOV_STOP:
for_each_cpu(j, policy->cpus) {
pcpu = &per_cpu(cpuinfo, j);
pcpu->governor_enabled = 0;
smp_wmb();
del_timer_sync(&pcpu->cpu_timer);
/*
* Reset idle exit time since we may cancel the timer
* before it can run after the last idle exit time,
* to avoid tripping the check in idle exit for a timer
* that is trying to run.
*/
pcpu->idle_exit_time = 0;
}
flush_work(&freq_scale_down_work);
if (atomic_dec_return(&active_count) > 0)
return 0;
sysfs_remove_group(cpufreq_global_kobject,
&interactive_attr_group);
break;
case CPUFREQ_GOV_LIMITS:
if (policy->max < policy->cur)
__cpufreq_driver_target(policy,
policy->max, CPUFREQ_RELATION_H);
else if (policy->min > policy->cur)
__cpufreq_driver_target(policy,
policy->min, CPUFREQ_RELATION_L);
break;
}
return 0;
}
static int cpufreq_interactive_idle_notifier(struct notifier_block *nb,
unsigned long val,
void *data)
{
switch (val) {
case IDLE_START:
cpufreq_interactive_idle_start();
break;
case IDLE_END:
cpufreq_interactive_idle_end();
break;
}
return 0;
}
static struct notifier_block cpufreq_interactive_idle_nb = {
.notifier_call = cpufreq_interactive_idle_notifier,
};
static int __init cpufreq_interactive_init(void)
{
unsigned int i;
struct cpufreq_interactive_cpuinfo *pcpu;
struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
go_maxspeed_load = DEFAULT_GO_MAXSPEED_LOAD;
min_sample_time = DEFAULT_MIN_SAMPLE_TIME;
timer_rate = DEFAULT_TIMER_RATE;
/* Initalize per-cpu timers */
for_each_possible_cpu(i) {
pcpu = &per_cpu(cpuinfo, i);
init_timer(&pcpu->cpu_timer);
pcpu->cpu_timer.function = cpufreq_interactive_timer;
pcpu->cpu_timer.data = i;
}
up_task = kthread_create(cpufreq_interactive_up_task, NULL,
"kinteractiveup");
if (IS_ERR(up_task))
return PTR_ERR(up_task);
sched_setscheduler_nocheck(up_task, SCHED_FIFO, ¶m);
get_task_struct(up_task);
/* No rescuer thread, bind to CPU queuing the work for possibly
warm cache (probably doesn't matter much). */
down_wq = alloc_workqueue("knteractive_down", 0, 1);
if (! down_wq)
goto err_freeuptask;
INIT_WORK(&freq_scale_down_work,
cpufreq_interactive_freq_down);
spin_lock_init(&up_cpumask_lock);
spin_lock_init(&down_cpumask_lock);
idle_notifier_register(&cpufreq_interactive_idle_nb);
return cpufreq_register_governor(&cpufreq_gov_interactive);
err_freeuptask:
put_task_struct(up_task);
return -ENOMEM;
}
#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_INTERACTIVE
fs_initcall(cpufreq_interactive_init);
#else
module_init(cpufreq_interactive_init);
#endif
static void __exit cpufreq_interactive_exit(void)
{
cpufreq_unregister_governor(&cpufreq_gov_interactive);
kthread_stop(up_task);
put_task_struct(up_task);
destroy_workqueue(down_wq);
}
module_exit(cpufreq_interactive_exit);
MODULE_AUTHOR("Mike Chan <mike@android.com>");
MODULE_DESCRIPTION("'cpufreq_interactive' - A cpufreq governor for "
"Latency sensitive workloads");
MODULE_LICENSE("GPL");
|