summaryrefslogtreecommitdiffstats
path: root/drivers/cpufreq/cpufreq_ondemand.c
blob: c631f27a3dcc754aa8ebe97ab7ef0a351b55a776 (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
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
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
/*
 *  drivers/cpufreq/cpufreq_ondemand.c
 *
 *  Copyright (C)  2001 Russell King
 *            (C)  2003 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>.
 *                      Jun Nakajima <jun.nakajima@intel.com>
 *
 * 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.
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/cpufreq.h>
#include <linux/cpu.h>
#include <linux/jiffies.h>
#include <linux/kernel_stat.h>
#include <linux/mutex.h>
#include <linux/hrtimer.h>
#include <linux/tick.h>
#include <linux/ktime.h>
#include <linux/sched.h>

/*
 * dbs is used in this file as a shortform for demandbased switching
 * It helps to keep variable names smaller, simpler
 */

#define DEF_FREQUENCY_DOWN_DIFFERENTIAL		(10)
#define DEF_FREQUENCY_UP_THRESHOLD		(80)
#define DEF_SAMPLING_DOWN_FACTOR		(1)
#define MAX_SAMPLING_DOWN_FACTOR		(100000)
#define MICRO_FREQUENCY_DOWN_DIFFERENTIAL	(3)
#define MICRO_FREQUENCY_UP_THRESHOLD		(95)
#define MICRO_FREQUENCY_MIN_SAMPLE_RATE		(10000)
#define MIN_FREQUENCY_UP_THRESHOLD		(11)
#define MAX_FREQUENCY_UP_THRESHOLD		(100)

/*
 * The polling frequency of this governor depends on the capability of
 * the processor. Default polling frequency is 1000 times the transition
 * latency of the processor. The governor will work on any processor with
 * transition latency <= 10mS, using appropriate sampling
 * rate.
 * For CPUs with transition latency > 10mS (mostly drivers with CPUFREQ_ETERNAL)
 * this governor will not work.
 * All times here are in uS.
 */
#define MIN_SAMPLING_RATE_RATIO			(2)

static unsigned int min_sampling_rate;

#define LATENCY_MULTIPLIER			(1000)
#define MIN_LATENCY_MULTIPLIER			(100)
#define TRANSITION_LATENCY_LIMIT		(10 * 1000 * 1000)

static void do_dbs_timer(struct work_struct *work);
static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
				unsigned int event);

#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
static
#endif
struct cpufreq_governor cpufreq_gov_ondemand = {
       .name                   = "ondemand",
       .governor               = cpufreq_governor_dbs,
       .max_transition_latency = TRANSITION_LATENCY_LIMIT,
       .owner                  = THIS_MODULE,
};

/* Sampling types */
enum {DBS_NORMAL_SAMPLE, DBS_SUB_SAMPLE};

struct cpu_dbs_info_s {
	cputime64_t prev_cpu_idle;
	cputime64_t prev_cpu_iowait;
	cputime64_t prev_cpu_wall;
	cputime64_t prev_cpu_nice;
	struct cpufreq_policy *cur_policy;
	struct delayed_work work;
	struct cpufreq_frequency_table *freq_table;
	unsigned int freq_lo;
	unsigned int freq_lo_jiffies;
	unsigned int freq_hi_jiffies;
	unsigned int rate_mult;
	int cpu;
	unsigned int sample_type:1;
	/*
	 * percpu mutex that serializes governor limit change with
	 * do_dbs_timer invocation. We do not want do_dbs_timer to run
	 * when user is changing the governor or limits.
	 */
	struct mutex timer_mutex;
};
static DEFINE_PER_CPU(struct cpu_dbs_info_s, od_cpu_dbs_info);

static unsigned int dbs_enable;	/* number of CPUs using this policy */

/*
 * dbs_mutex protects data in dbs_tuners_ins from concurrent changes on
 * different CPUs. It protects dbs_enable in governor start/stop.
 */
static DEFINE_MUTEX(dbs_mutex);

static struct workqueue_struct	*kondemand_wq;

static struct dbs_tuners {
	unsigned int sampling_rate;
	unsigned int up_threshold;
	unsigned int down_differential;
	unsigned int ignore_nice;
	unsigned int sampling_down_factor;
	unsigned int powersave_bias;
	unsigned int io_is_busy;
} dbs_tuners_ins = {
	.up_threshold = DEF_FREQUENCY_UP_THRESHOLD,
	.sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR,
	.down_differential = DEF_FREQUENCY_DOWN_DIFFERENTIAL,
	.ignore_nice = 0,
	.powersave_bias = 0,
};

static inline cputime64_t get_cpu_idle_time_jiffy(unsigned int cpu,
							cputime64_t *wall)
{
	cputime64_t idle_time;
	cputime64_t cur_wall_time;
	cputime64_t busy_time;

	cur_wall_time = jiffies64_to_cputime64(get_jiffies_64());
	busy_time = cputime64_add(kstat_cpu(cpu).cpustat.user,
			kstat_cpu(cpu).cpustat.system);

	busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.irq);
	busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.softirq);
	busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.steal);
	busy_time = cputime64_add(busy_time, kstat_cpu(cpu).cpustat.nice);

	idle_time = cputime64_sub(cur_wall_time, busy_time);
	if (wall)
		*wall = (cputime64_t)jiffies_to_usecs(cur_wall_time);

	return (cputime64_t)jiffies_to_usecs(idle_time);
}

static inline cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall)
{
	u64 idle_time = get_cpu_idle_time_us(cpu, wall);

	if (idle_time == -1ULL)
		return get_cpu_idle_time_jiffy(cpu, wall);

	return idle_time;
}

static inline cputime64_t get_cpu_iowait_time(unsigned int cpu, cputime64_t *wall)
{
	u64 iowait_time = get_cpu_iowait_time_us(cpu, wall);

	if (iowait_time == -1ULL)
		return 0;

	return iowait_time;
}

/*
 * Find right freq to be set now with powersave_bias on.
 * Returns the freq_hi to be used right now and will set freq_hi_jiffies,
 * freq_lo, and freq_lo_jiffies in percpu area for averaging freqs.
 */
static unsigned int powersave_bias_target(struct cpufreq_policy *policy,
					  unsigned int freq_next,
					  unsigned int relation)
{
	unsigned int freq_req, freq_reduc, freq_avg;
	unsigned int freq_hi, freq_lo;
	unsigned int index = 0;
	unsigned int jiffies_total, jiffies_hi, jiffies_lo;
	struct cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
						   policy->cpu);

	if (!dbs_info->freq_table) {
		dbs_info->freq_lo = 0;
		dbs_info->freq_lo_jiffies = 0;
		return freq_next;
	}

	cpufreq_frequency_table_target(policy, dbs_info->freq_table, freq_next,
			relation, &index);
	freq_req = dbs_info->freq_table[index].frequency;
	freq_reduc = freq_req * dbs_tuners_ins.powersave_bias / 1000;
	freq_avg = freq_req - freq_reduc;

	/* Find freq bounds for freq_avg in freq_table */
	index = 0;
	cpufreq_frequency_table_target(policy, dbs_info->freq_table, freq_avg,
			CPUFREQ_RELATION_H, &index);
	freq_lo = dbs_info->freq_table[index].frequency;
	index = 0;
	cpufreq_frequency_table_target(policy, dbs_info->freq_table, freq_avg,
			CPUFREQ_RELATION_L, &index);
	freq_hi = dbs_info->freq_table[index].frequency;

	/* Find out how long we have to be in hi and lo freqs */
	if (freq_hi == freq_lo) {
		dbs_info->freq_lo = 0;
		dbs_info->freq_lo_jiffies = 0;
		return freq_lo;
	}
	jiffies_total = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
	jiffies_hi = (freq_avg - freq_lo) * jiffies_total;
	jiffies_hi += ((freq_hi - freq_lo) / 2);
	jiffies_hi /= (freq_hi - freq_lo);
	jiffies_lo = jiffies_total - jiffies_hi;
	dbs_info->freq_lo = freq_lo;
	dbs_info->freq_lo_jiffies = jiffies_lo;
	dbs_info->freq_hi_jiffies = jiffies_hi;
	return freq_hi;
}

static void ondemand_powersave_bias_init_cpu(int cpu)
{
	struct cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
	dbs_info->freq_table = cpufreq_frequency_get_table(cpu);
	dbs_info->freq_lo = 0;
}

static void ondemand_powersave_bias_init(void)
{
	int i;
	for_each_online_cpu(i) {
		ondemand_powersave_bias_init_cpu(i);
	}
}

/************************** sysfs interface ************************/

static ssize_t show_sampling_rate_max(struct kobject *kobj,
				      struct attribute *attr, char *buf)
{
	printk_once(KERN_INFO "CPUFREQ: ondemand sampling_rate_max "
	       "sysfs file is deprecated - used by: %s\n", current->comm);
	return sprintf(buf, "%u\n", -1U);
}

static ssize_t show_sampling_rate_min(struct kobject *kobj,
				      struct attribute *attr, char *buf)
{
	return sprintf(buf, "%u\n", min_sampling_rate);
}

define_one_global_ro(sampling_rate_max);
define_one_global_ro(sampling_rate_min);

/* cpufreq_ondemand Governor Tunables */
#define show_one(file_name, object)					\
static ssize_t show_##file_name						\
(struct kobject *kobj, struct attribute *attr, char *buf)              \
{									\
	return sprintf(buf, "%u\n", dbs_tuners_ins.object);		\
}
show_one(sampling_rate, sampling_rate);
show_one(io_is_busy, io_is_busy);
show_one(up_threshold, up_threshold);
show_one(sampling_down_factor, sampling_down_factor);
show_one(ignore_nice_load, ignore_nice);
show_one(powersave_bias, powersave_bias);

/*** delete after deprecation time ***/

#define DEPRECATION_MSG(file_name)					\
	printk_once(KERN_INFO "CPUFREQ: Per core ondemand sysfs "	\
		    "interface is deprecated - " #file_name "\n");

#define show_one_old(file_name)						\
static ssize_t show_##file_name##_old					\
(struct cpufreq_policy *unused, char *buf)				\
{									\
	printk_once(KERN_INFO "CPUFREQ: Per core ondemand sysfs "	\
		    "interface is deprecated - " #file_name "\n");	\
	return show_##file_name(NULL, NULL, buf);			\
}
show_one_old(sampling_rate);
show_one_old(up_threshold);
show_one_old(ignore_nice_load);
show_one_old(powersave_bias);
show_one_old(sampling_rate_min);
show_one_old(sampling_rate_max);

cpufreq_freq_attr_ro_old(sampling_rate_min);
cpufreq_freq_attr_ro_old(sampling_rate_max);

/*** delete after deprecation time ***/

static ssize_t store_sampling_rate(struct kobject *a, struct attribute *b,
				   const char *buf, size_t count)
{
	unsigned int input;
	int ret;
	ret = sscanf(buf, "%u", &input);
	if (ret != 1)
		return -EINVAL;

	mutex_lock(&dbs_mutex);
	dbs_tuners_ins.sampling_rate = max(input, min_sampling_rate);
	mutex_unlock(&dbs_mutex);

	return count;
}

static ssize_t store_io_is_busy(struct kobject *a, struct attribute *b,
				   const char *buf, size_t count)
{
	unsigned int input;
	int ret;

	ret = sscanf(buf, "%u", &input);
	if (ret != 1)
		return -EINVAL;

	mutex_lock(&dbs_mutex);
	dbs_tuners_ins.io_is_busy = !!input;
	mutex_unlock(&dbs_mutex);

	return count;
}

static ssize_t store_up_threshold(struct kobject *a, struct attribute *b,
				  const char *buf, size_t count)
{
	unsigned int input;
	int ret;
	ret = sscanf(buf, "%u", &input);

	if (ret != 1 || input > MAX_FREQUENCY_UP_THRESHOLD ||
			input < MIN_FREQUENCY_UP_THRESHOLD) {
		return -EINVAL;
	}

	mutex_lock(&dbs_mutex);
	dbs_tuners_ins.up_threshold = input;
	mutex_unlock(&dbs_mutex);

	return count;
}

static ssize_t store_sampling_down_factor(struct kobject *a,
			struct attribute *b, const char *buf, size_t count)
{
	unsigned int input, j;
	int ret;
	ret = sscanf(buf, "%u", &input);

	if (ret != 1 || input > MAX_SAMPLING_DOWN_FACTOR || input < 1)
		return -EINVAL;
	mutex_lock(&dbs_mutex);
	dbs_tuners_ins.sampling_down_factor = input;

	/* Reset down sampling multiplier in case it was active */
	for_each_online_cpu(j) {
		struct cpu_dbs_info_s *dbs_info;
		dbs_info = &per_cpu(od_cpu_dbs_info, j);
		dbs_info->rate_mult = 1;
	}
	mutex_unlock(&dbs_mutex);

	return count;
}

static ssize_t store_ignore_nice_load(struct kobject *a, struct attribute *b,
				      const char *buf, size_t count)
{
	unsigned int input;
	int ret;

	unsigned int j;

	ret = sscanf(buf, "%u", &input);
	if (ret != 1)
		return -EINVAL;

	if (input > 1)
		input = 1;

	mutex_lock(&dbs_mutex);
	if (input == dbs_tuners_ins.ignore_nice) { /* nothing to do */
		mutex_unlock(&dbs_mutex);
		return count;
	}
	dbs_tuners_ins.ignore_nice = input;

	/* we need to re-evaluate prev_cpu_idle */
	for_each_online_cpu(j) {
		struct cpu_dbs_info_s *dbs_info;
		dbs_info = &per_cpu(od_cpu_dbs_info, j);
		dbs_info->prev_cpu_idle = get_cpu_idle_time(j,
						&dbs_info->prev_cpu_wall);
		if (dbs_tuners_ins.ignore_nice)
			dbs_info->prev_cpu_nice = kstat_cpu(j).cpustat.nice;

	}
	mutex_unlock(&dbs_mutex);

	return count;
}

static ssize_t store_powersave_bias(struct kobject *a, struct attribute *b,
				    const char *buf, size_t count)
{
	unsigned int input;
	int ret;
	ret = sscanf(buf, "%u", &input);

	if (ret != 1)
		return -EINVAL;

	if (input > 1000)
		input = 1000;

	mutex_lock(&dbs_mutex);
	dbs_tuners_ins.powersave_bias = input;
	ondemand_powersave_bias_init();
	mutex_unlock(&dbs_mutex);

	return count;
}

define_one_global_rw(sampling_rate);
define_one_global_rw(io_is_busy);
define_one_global_rw(up_threshold);
define_one_global_rw(sampling_down_factor);
define_one_global_rw(ignore_nice_load);
define_one_global_rw(powersave_bias);

static struct attribute *dbs_attributes[] = {
	&sampling_rate_max.attr,
	&sampling_rate_min.attr,
	&sampling_rate.attr,
	&up_threshold.attr,
	&sampling_down_factor.attr,
	&ignore_nice_load.attr,
	&powersave_bias.attr,
	&io_is_busy.attr,
	NULL
};

static struct attribute_group dbs_attr_group = {
	.attrs = dbs_attributes,
	.name = "ondemand",
};

/*** delete after deprecation time ***/

#define write_one_old(file_name)					\
static ssize_t store_##file_name##_old					\
(struct cpufreq_policy *unused, const char *buf, size_t count)		\
{									\
       printk_once(KERN_INFO "CPUFREQ: Per core ondemand sysfs "	\
		   "interface is deprecated - " #file_name "\n");	\
       return store_##file_name(NULL, NULL, buf, count);		\
}
write_one_old(sampling_rate);
write_one_old(up_threshold);
write_one_old(ignore_nice_load);
write_one_old(powersave_bias);

cpufreq_freq_attr_rw_old(sampling_rate);
cpufreq_freq_attr_rw_old(up_threshold);
cpufreq_freq_attr_rw_old(ignore_nice_load);
cpufreq_freq_attr_rw_old(powersave_bias);

static struct attribute *dbs_attributes_old[] = {
       &sampling_rate_max_old.attr,
       &sampling_rate_min_old.attr,
       &sampling_rate_old.attr,
       &up_threshold_old.attr,
       &ignore_nice_load_old.attr,
       &powersave_bias_old.attr,
       NULL
};

static struct attribute_group dbs_attr_group_old = {
       .attrs = dbs_attributes_old,
       .name = "ondemand",
};

/*** delete after deprecation time ***/

/************************** sysfs end ************************/

static void dbs_freq_increase(struct cpufreq_policy *p, unsigned int freq)
{
	if (dbs_tuners_ins.powersave_bias)
		freq = powersave_bias_target(p, freq, CPUFREQ_RELATION_H);
	else if (p->cur == p->max)
		return;

	__cpufreq_driver_target(p, freq, dbs_tuners_ins.powersave_bias ?
			CPUFREQ_RELATION_L : CPUFREQ_RELATION_H);
}

static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
{
	unsigned int max_load_freq;

	struct cpufreq_policy *policy;
	unsigned int j;

	this_dbs_info->freq_lo = 0;
	policy = this_dbs_info->cur_policy;

	/*
	 * Every sampling_rate, we check, if current idle time is less
	 * than 20% (default), then we try to increase frequency
	 * Every sampling_rate, we look for a the lowest
	 * frequency which can sustain the load while keeping idle time over
	 * 30%. If such a frequency exist, we try to decrease to this frequency.
	 *
	 * Any frequency increase takes it to the maximum frequency.
	 * Frequency reduction happens at minimum steps of
	 * 5% (default) of current frequency
	 */

	/* Get Absolute Load - in terms of freq */
	max_load_freq = 0;

	for_each_cpu(j, policy->cpus) {
		struct cpu_dbs_info_s *j_dbs_info;
		cputime64_t cur_wall_time, cur_idle_time, cur_iowait_time;
		unsigned int idle_time, wall_time, iowait_time;
		unsigned int load, load_freq;
		int freq_avg;

		j_dbs_info = &per_cpu(od_cpu_dbs_info, j);

		cur_idle_time = get_cpu_idle_time(j, &cur_wall_time);
		cur_iowait_time = get_cpu_iowait_time(j, &cur_wall_time);

		wall_time = (unsigned int) cputime64_sub(cur_wall_time,
				j_dbs_info->prev_cpu_wall);
		j_dbs_info->prev_cpu_wall = cur_wall_time;

		idle_time = (unsigned int) cputime64_sub(cur_idle_time,
				j_dbs_info->prev_cpu_idle);
		j_dbs_info->prev_cpu_idle = cur_idle_time;

		iowait_time = (unsigned int) cputime64_sub(cur_iowait_time,
				j_dbs_info->prev_cpu_iowait);
		j_dbs_info->prev_cpu_iowait = cur_iowait_time;

		if (dbs_tuners_ins.ignore_nice) {
			cputime64_t cur_nice;
			unsigned long cur_nice_jiffies;

			cur_nice = cputime64_sub(kstat_cpu(j).cpustat.nice,
					 j_dbs_info->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);

			j_dbs_info->prev_cpu_nice = kstat_cpu(j).cpustat.nice;
			idle_time += jiffies_to_usecs(cur_nice_jiffies);
		}

		/*
		 * 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 subtract the iowait time
		 * from the cpu idle time.
		 */

		if (dbs_tuners_ins.io_is_busy && idle_time >= iowait_time)
			idle_time -= iowait_time;

		if (unlikely(!wall_time || wall_time < idle_time))
			continue;

		load = 100 * (wall_time - idle_time) / wall_time;

		freq_avg = __cpufreq_driver_getavg(policy, j);
		if (freq_avg <= 0)
			freq_avg = policy->cur;

		load_freq = load * freq_avg;
		if (load_freq > max_load_freq)
			max_load_freq = load_freq;
	}

	/* Check for frequency increase */
	if (max_load_freq > dbs_tuners_ins.up_threshold * policy->cur) {
		/* If switching to max speed, apply sampling_down_factor */
		if (policy->cur < policy->max)
			this_dbs_info->rate_mult =
				dbs_tuners_ins.sampling_down_factor;
		dbs_freq_increase(policy, policy->max);
		return;
	}

	/* Check for frequency decrease */
	/* if we cannot reduce the frequency anymore, break out early */
	if (policy->cur == policy->min)
		return;

	/*
	 * The optimal frequency is the frequency that is the lowest that
	 * can support the current CPU usage without triggering the up
	 * policy. To be safe, we focus 10 points under the threshold.
	 */
	if (max_load_freq <
	    (dbs_tuners_ins.up_threshold - dbs_tuners_ins.down_differential) *
	     policy->cur) {
		unsigned int freq_next;
		freq_next = max_load_freq /
				(dbs_tuners_ins.up_threshold -
				 dbs_tuners_ins.down_differential);

		/* No longer fully busy, reset rate_mult */
		this_dbs_info->rate_mult = 1;

		if (freq_next < policy->min)
			freq_next = policy->min;

		if (!dbs_tuners_ins.powersave_bias) {
			__cpufreq_driver_target(policy, freq_next,
					CPUFREQ_RELATION_L);
		} else {
			int freq = powersave_bias_target(policy, freq_next,
					CPUFREQ_RELATION_L);
			__cpufreq_driver_target(policy, freq,
				CPUFREQ_RELATION_L);
		}
	}
}

static void do_dbs_timer(struct work_struct *work)
{
	struct cpu_dbs_info_s *dbs_info =
		container_of(work, struct cpu_dbs_info_s, work.work);
	unsigned int cpu = dbs_info->cpu;
	int sample_type = dbs_info->sample_type;

	/* We want all CPUs to do sampling nearly on same jiffy */
	int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate
		* dbs_info->rate_mult);

	if (num_online_cpus() > 1)
		delay -= jiffies % delay;

	mutex_lock(&dbs_info->timer_mutex);

	/* Common NORMAL_SAMPLE setup */
	dbs_info->sample_type = DBS_NORMAL_SAMPLE;
	if (!dbs_tuners_ins.powersave_bias ||
	    sample_type == DBS_NORMAL_SAMPLE) {
		dbs_check_cpu(dbs_info);
		if (dbs_info->freq_lo) {
			/* Setup timer for SUB_SAMPLE */
			dbs_info->sample_type = DBS_SUB_SAMPLE;
			delay = dbs_info->freq_hi_jiffies;
		}
	} else {
		__cpufreq_driver_target(dbs_info->cur_policy,
			dbs_info->freq_lo, CPUFREQ_RELATION_H);
	}
	queue_delayed_work_on(cpu, kondemand_wq, &dbs_info->work, delay);
	mutex_unlock(&dbs_info->timer_mutex);
}

static inline void dbs_timer_init(struct cpu_dbs_info_s *dbs_info)
{
	/* We want all CPUs to do sampling nearly on same jiffy */
	int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);

	if (num_online_cpus() > 1)
		delay -= jiffies % delay;

	dbs_info->sample_type = DBS_NORMAL_SAMPLE;
	INIT_DELAYED_WORK_DEFERRABLE(&dbs_info->work, do_dbs_timer);
	queue_delayed_work_on(dbs_info->cpu, kondemand_wq, &dbs_info->work,
		delay);
}

static inline void dbs_timer_exit(struct cpu_dbs_info_s *dbs_info)
{
	cancel_delayed_work_sync(&dbs_info->work);
}

/*
 * Not all CPUs want IO time to be accounted as busy; this dependson how
 * efficient idling at a higher frequency/voltage is.
 * Pavel Machek says this is not so for various generations of AMD and old
 * Intel systems.
 * Mike Chan (androidlcom) calis this is also not true for ARM.
 * Because of this, whitelist specific known (series) of CPUs by default, and
 * leave all others up to the user.
 */
static int should_io_be_busy(void)
{
#if defined(CONFIG_X86)
	/*
	 * For Intel, Core 2 (model 15) andl later have an efficient idle.
	 */
	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
	    boot_cpu_data.x86 == 6 &&
	    boot_cpu_data.x86_model >= 15)
		return 1;
#endif
	return 0;
}

static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
				   unsigned int event)
{
	unsigned int cpu = policy->cpu;
	struct cpu_dbs_info_s *this_dbs_info;
	unsigned int j;
	int rc;

	this_dbs_info = &per_cpu(od_cpu_dbs_info, cpu);

	switch (event) {
	case CPUFREQ_GOV_START:
		if ((!cpu_online(cpu)) || (!policy->cur))
			return -EINVAL;

		mutex_lock(&dbs_mutex);

		rc = sysfs_create_group(&policy->kobj, &dbs_attr_group_old);
		if (rc) {
			mutex_unlock(&dbs_mutex);
			return rc;
		}

		dbs_enable++;
		for_each_cpu(j, policy->cpus) {
			struct cpu_dbs_info_s *j_dbs_info;
			j_dbs_info = &per_cpu(od_cpu_dbs_info, j);
			j_dbs_info->cur_policy = policy;

			j_dbs_info->prev_cpu_idle = get_cpu_idle_time(j,
						&j_dbs_info->prev_cpu_wall);
			if (dbs_tuners_ins.ignore_nice) {
				j_dbs_info->prev_cpu_nice =
						kstat_cpu(j).cpustat.nice;
			}
		}
		this_dbs_info->cpu = cpu;
		this_dbs_info->rate_mult = 1;
		ondemand_powersave_bias_init_cpu(cpu);
		/*
		 * Start the timerschedule work, when this governor
		 * is used for first time
		 */
		if (dbs_enable == 1) {
			unsigned int latency;

			rc = sysfs_create_group(cpufreq_global_kobject,
						&dbs_attr_group);
			if (rc) {
				mutex_unlock(&dbs_mutex);
				return rc;
			}

			/* 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 */
			min_sampling_rate = max(min_sampling_rate,
					MIN_LATENCY_MULTIPLIER * latency);
			dbs_tuners_ins.sampling_rate =
				max(min_sampling_rate,
				    latency * LATENCY_MULTIPLIER);
			dbs_tuners_ins.io_is_busy = should_io_be_busy();
		}
		mutex_unlock(&dbs_mutex);

		mutex_init(&this_dbs_info->timer_mutex);
		dbs_timer_init(this_dbs_info);
		break;

	case CPUFREQ_GOV_STOP:
		dbs_timer_exit(this_dbs_info);

		mutex_lock(&dbs_mutex);
		sysfs_remove_group(&policy->kobj, &dbs_attr_group_old);
		mutex_destroy(&this_dbs_info->timer_mutex);
		dbs_enable--;
		mutex_unlock(&dbs_mutex);
		if (!dbs_enable)
			sysfs_remove_group(cpufreq_global_kobject,
					   &dbs_attr_group);

		break;

	case CPUFREQ_GOV_LIMITS:
		mutex_lock(&this_dbs_info->timer_mutex);
		if (policy->max < this_dbs_info->cur_policy->cur)
			__cpufreq_driver_target(this_dbs_info->cur_policy,
				policy->max, CPUFREQ_RELATION_H);
		else if (policy->min > this_dbs_info->cur_policy->cur)
			__cpufreq_driver_target(this_dbs_info->cur_policy,
				policy->min, CPUFREQ_RELATION_L);
		mutex_unlock(&this_dbs_info->timer_mutex);
		break;
	}
	return 0;
}

static int __init cpufreq_gov_dbs_init(void)
{
	int err;
	cputime64_t wall;
	u64 idle_time;
	int cpu = get_cpu();

	idle_time = get_cpu_idle_time_us(cpu, &wall);
	put_cpu();
	if (idle_time != -1ULL) {
		/* Idle micro accounting is supported. Use finer thresholds */
		dbs_tuners_ins.up_threshold = MICRO_FREQUENCY_UP_THRESHOLD;
		dbs_tuners_ins.down_differential =
					MICRO_FREQUENCY_DOWN_DIFFERENTIAL;
		/*
		 * In no_hz/micro accounting case we set the minimum frequency
		 * not depending on HZ, but fixed (very low). The deferred
		 * timer might skip some samples if idle/sleeping as needed.
		*/
		min_sampling_rate = MICRO_FREQUENCY_MIN_SAMPLE_RATE;
	} else {
		/* For correct statistics, we need 10 ticks for each measure */
		min_sampling_rate =
			MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10);
	}

	kondemand_wq = create_workqueue("kondemand");
	if (!kondemand_wq) {
		printk(KERN_ERR "Creation of kondemand failed\n");
		return -EFAULT;
	}
	err = cpufreq_register_governor(&cpufreq_gov_ondemand);
	if (err)
		destroy_workqueue(kondemand_wq);

	return err;
}

static void __exit cpufreq_gov_dbs_exit(void)
{
	cpufreq_unregister_governor(&cpufreq_gov_ondemand);
	destroy_workqueue(kondemand_wq);
}


MODULE_AUTHOR("Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>");
MODULE_AUTHOR("Alexey Starikovskiy <alexey.y.starikovskiy@intel.com>");
MODULE_DESCRIPTION("'cpufreq_ondemand' - A dynamic cpufreq governor for "
	"Low Latency Frequency Transition capable processors");
MODULE_LICENSE("GPL");

#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
fs_initcall(cpufreq_gov_dbs_init);
#else
module_init(cpufreq_gov_dbs_init);
#endif
module_exit(cpufreq_gov_dbs_exit);