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
|
/*
* 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 struct attribute_group *get_sysfs_attr(struct dbs_data *dbs_data)
{
if (have_governor_per_policy())
return dbs_data->cdata->attr_group_gov_pol;
else
return dbs_data->cdata->attr_group_gov_sys;
}
void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
{
struct cpu_dbs_common_info *cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
struct od_dbs_tuners *od_tuners = dbs_data->tuners;
struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
struct cpufreq_policy *policy;
unsigned int sampling_rate;
unsigned int max_load = 0;
unsigned int ignore_nice;
unsigned int j;
if (dbs_data->cdata->governor == GOV_ONDEMAND) {
struct od_cpu_dbs_info_s *od_dbs_info =
dbs_data->cdata->get_cpu_dbs_info_s(cpu);
/*
* Sometimes, the ondemand governor uses an additional
* multiplier to give long delays. So apply this multiplier to
* the 'sampling_rate', so as to keep the wake-up-from-idle
* detection logic a bit conservative.
*/
sampling_rate = od_tuners->sampling_rate;
sampling_rate *= od_dbs_info->rate_mult;
ignore_nice = od_tuners->ignore_nice_load;
} else {
sampling_rate = cs_tuners->sampling_rate;
ignore_nice = cs_tuners->ignore_nice_load;
}
policy = cdbs->cur_policy;
/* Get Absolute Load */
for_each_cpu(j, policy->cpus) {
struct cpu_dbs_common_info *j_cdbs;
u64 cur_wall_time, cur_idle_time;
unsigned int idle_time, wall_time;
unsigned int load;
int io_busy = 0;
j_cdbs = dbs_data->cdata->get_cpu_cdbs(j);
/*
* 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.
*/
if (dbs_data->cdata->governor == GOV_ONDEMAND)
io_busy = od_tuners->io_is_busy;
cur_idle_time = get_cpu_idle_time(j, &cur_wall_time, io_busy);
wall_time = (unsigned int)
(cur_wall_time - j_cdbs->prev_cpu_wall);
j_cdbs->prev_cpu_wall = cur_wall_time;
idle_time = (unsigned int)
(cur_idle_time - j_cdbs->prev_cpu_idle);
j_cdbs->prev_cpu_idle = cur_idle_time;
if (ignore_nice) {
u64 cur_nice;
unsigned long cur_nice_jiffies;
cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE] -
cdbs->prev_cpu_nice;
/*
* Assumption: nice time between sampling periods will
* be less than 2^32 jiffies for 32 bit sys
*/
cur_nice_jiffies = (unsigned long)
cputime64_to_jiffies64(cur_nice);
cdbs->prev_cpu_nice =
kcpustat_cpu(j).cpustat[CPUTIME_NICE];
idle_time += jiffies_to_usecs(cur_nice_jiffies);
}
if (unlikely(!wall_time || wall_time < idle_time))
continue;
/*
* If the CPU had gone completely idle, and a task just woke up
* on this CPU now, it would be unfair to calculate 'load' the
* usual way for this elapsed time-window, because it will show
* near-zero load, irrespective of how CPU intensive that task
* actually is. This is undesirable for latency-sensitive bursty
* workloads.
*
* To avoid this, we reuse the 'load' from the previous
* time-window and give this task a chance to start with a
* reasonably high CPU frequency. (However, we shouldn't over-do
* this copy, lest we get stuck at a high load (high frequency)
* for too long, even when the current system load has actually
* dropped down. So we perform the copy only once, upon the
* first wake-up from idle.)
*
* Detecting this situation is easy: the governor's deferrable
* timer would not have fired during CPU-idle periods. Hence
* an unusually large 'wall_time' (as compared to the sampling
* rate) indicates this scenario.
*
* prev_load can be zero in two cases and we must recalculate it
* for both cases:
* - during long idle intervals
* - explicitly set to zero
*/
if (unlikely(wall_time > (2 * sampling_rate) &&
j_cdbs->prev_load)) {
load = j_cdbs->prev_load;
/*
* Perform a destructive copy, to ensure that we copy
* the previous load only once, upon the first wake-up
* from idle.
*/
j_cdbs->prev_load = 0;
} else {
load = 100 * (wall_time - idle_time) / wall_time;
j_cdbs->prev_load = load;
}
if (load > max_load)
max_load = load;
}
dbs_data->cdata->gov_check_cpu(cpu, max_load);
}
EXPORT_SYMBOL_GPL(dbs_check_cpu);
static inline void __gov_queue_work(int cpu, struct dbs_data *dbs_data,
unsigned int delay)
{
struct cpu_dbs_common_info *cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
mod_delayed_work_on(cpu, system_wq, &cdbs->work, delay);
}
void gov_queue_work(struct dbs_data *dbs_data, struct cpufreq_policy *policy,
unsigned int delay, bool all_cpus)
{
int i;
mutex_lock(&cpufreq_governor_lock);
if (!policy->governor_enabled)
goto out_unlock;
if (!all_cpus) {
/*
* Use raw_smp_processor_id() to avoid preemptible warnings.
* We know that this is only called with all_cpus == false from
* works that have been queued with *_work_on() functions and
* those works are canceled during CPU_DOWN_PREPARE so they
* can't possibly run on any other CPU.
*/
__gov_queue_work(raw_smp_processor_id(), dbs_data, delay);
} else {
for_each_cpu(i, policy->cpus)
__gov_queue_work(i, dbs_data, delay);
}
out_unlock:
mutex_unlock(&cpufreq_governor_lock);
}
EXPORT_SYMBOL_GPL(gov_queue_work);
static inline void gov_cancel_work(struct dbs_data *dbs_data,
struct cpufreq_policy *policy)
{
struct cpu_dbs_common_info *cdbs;
int i;
for_each_cpu(i, policy->cpus) {
cdbs = dbs_data->cdata->get_cpu_cdbs(i);
cancel_delayed_work_sync(&cdbs->work);
}
}
/* Will return if we need to evaluate cpu load again or not */
bool need_load_eval(struct cpu_dbs_common_info *cdbs,
unsigned int sampling_rate)
{
if (policy_is_shared(cdbs->cur_policy)) {
ktime_t time_now = ktime_get();
s64 delta_us = ktime_us_delta(time_now, cdbs->time_stamp);
/* Do nothing if we recently have sampled */
if (delta_us < (s64)(sampling_rate / 2))
return false;
else
cdbs->time_stamp = time_now;
}
return true;
}
EXPORT_SYMBOL_GPL(need_load_eval);
static void set_sampling_rate(struct dbs_data *dbs_data,
unsigned int sampling_rate)
{
if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
cs_tuners->sampling_rate = sampling_rate;
} else {
struct od_dbs_tuners *od_tuners = dbs_data->tuners;
od_tuners->sampling_rate = sampling_rate;
}
}
int cpufreq_governor_dbs(struct cpufreq_policy *policy,
struct common_dbs_data *cdata, unsigned int event)
{
struct dbs_data *dbs_data;
struct od_cpu_dbs_info_s *od_dbs_info = NULL;
struct cs_cpu_dbs_info_s *cs_dbs_info = NULL;
struct od_ops *od_ops = NULL;
struct od_dbs_tuners *od_tuners = NULL;
struct cs_dbs_tuners *cs_tuners = NULL;
struct cpu_dbs_common_info *cpu_cdbs;
unsigned int sampling_rate, latency, ignore_nice, j, cpu = policy->cpu;
int io_busy = 0;
int rc;
if (have_governor_per_policy())
dbs_data = policy->governor_data;
else
dbs_data = cdata->gdbs_data;
WARN_ON(!dbs_data && (event != CPUFREQ_GOV_POLICY_INIT));
switch (event) {
case CPUFREQ_GOV_POLICY_INIT:
if (have_governor_per_policy()) {
WARN_ON(dbs_data);
} else if (dbs_data) {
dbs_data->usage_count++;
policy->governor_data = dbs_data;
return 0;
}
dbs_data = kzalloc(sizeof(*dbs_data), GFP_KERNEL);
if (!dbs_data) {
pr_err("%s: POLICY_INIT: kzalloc failed\n", __func__);
return -ENOMEM
|