summaryrefslogtreecommitdiffstats
path: root/kernel/sched/cpufreq_schedutil.c
blob: 5e39da0ae0868756819d096717422e67ccda7998 (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
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
// SPDX-License-Identifier: GPL-2.0
/*
 * CPUFreq governor based on scheduler-provided CPU utilization data.
 *
 * Copyright (C) 2016, Intel Corporation
 * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include "sched.h"

#include <linux/sched/cpufreq.h>
#include <trace/events/power.h>

#define IOWAIT_BOOST_MIN	(SCHED_CAPACITY_SCALE / 8)

struct sugov_tunables {
	struct gov_attr_set	attr_set;
	unsigned int		rate_limit_us;
};

struct sugov_policy {
	struct cpufreq_policy	*policy;

	struct sugov_tunables	*tunables;
	struct list_head	tunables_hook;

	raw_spinlock_t		update_lock;	/* For shared policies */
	u64			last_freq_update_time;
	s64			freq_update_delay_ns;
	unsigned int		next_freq;
	unsigned int		cached_raw_freq;

	/* The next fields are only needed if fast switch cannot be used: */
	struct			irq_work irq_work;
	struct			kthread_work work;
	struct			mutex work_lock;
	struct			kthread_worker worker;
	struct task_struct	*thread;
	bool			work_in_progress;

	bool			limits_changed;
	bool			need_freq_update;
};

struct sugov_cpu {
	struct update_util_data	update_util;
	struct sugov_policy	*sg_policy;
	unsigned int		cpu;

	bool			iowait_boost_pending;
	unsigned int		iowait_boost;
	u64			last_update;

	unsigned long		bw_dl;
	unsigned long		max;

	/* The field below is for single-CPU policies only: */
#ifdef CONFIG_NO_HZ_COMMON
	unsigned long		saved_idle_calls;
#endif
};

static DEFINE_PER_CPU(struct sugov_cpu, sugov_cpu);

/************************ Governor internals ***********************/

static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
{
	s64 delta_ns;

	/*
	 * Since cpufreq_update_util() is called with rq->lock held for
	 * the @target_cpu, our per-CPU data is fully serialized.
	 *
	 * However, drivers cannot in general deal with cross-CPU
	 * requests, so while get_next_freq() will work, our
	 * sugov_update_commit() call may not for the fast switching platforms.
	 *
	 * Hence stop here for remote requests if they aren't supported
	 * by the hardware, as calculating the frequency is pointless if
	 * we cannot in fact act on it.
	 *
	 * This is needed on the slow switching platforms too to prevent CPUs
	 * going offline from leaving stale IRQ work items behind.
	 */
	if (!cpufreq_this_cpu_can_update(sg_policy->policy))
		return false;

	if (unlikely(sg_policy->limits_changed)) {
		sg_policy->limits_changed = false;
		sg_policy->need_freq_update = true;
		return true;
	}

	delta_ns = time - sg_policy->last_freq_update_time;

	return delta_ns >= sg_policy->freq_update_delay_ns;
}

static bool sugov_update_next_freq(struct sugov_policy *sg_policy, u64 time,
				   unsigned int next_freq)
{
	if (!sg_policy->need_freq_update) {
		if (sg_policy->next_freq == next_freq)
			return false;
	} else {
		sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);
	}

	sg_policy->next_freq = next_freq;
	sg_policy->last_freq_update_time = time;

	return true;
}

static void sugov_fast_switch(struct sugov_policy *sg_policy, u64 time,
			      unsigned int next_freq)
{
	if (sugov_update_next_freq(sg_policy, time, next_freq))
		cpufreq_driver_fast_switch(sg_policy->policy, next_freq);
}

static void sugov_deferred_update(struct sugov_policy *sg_policy, u64 time,
				  unsigned int next_freq)
{
	if (!sugov_update_next_freq(sg_policy, time, next_freq))
		return;

	if (!sg_policy->work_in_progress) {
		sg_policy->work_in_progress = true;
		irq_work_queue(&sg_policy->irq_work);
	}
}

/**
 * get_next_freq - Compute a new frequency for a given cpufreq policy.
 * @sg_policy: schedutil policy object to compute the new frequency for.
 * @util: Current CPU utilization.
 * @max: CPU capacity.
 *
 * If the utilization is frequency-invariant, choose the new frequency to be
 * proportional to it, that is
 *
 * next_freq = C * max_freq * util / max
 *
 * Otherwise, approximate the would-be frequency-invariant utilization by
 * util_raw * (curr_freq / max_freq) which leads to
 *
 * next_freq = C * curr_freq * util_raw / max
 *
 * Take C = 1.25 for the frequency tipping point at (util / max) = 0.8.
 *
 * The lowest driver-supported frequency which is equal or greater than the raw
 * next_freq (as calculated above) is returned, subject to policy min/max and
 * cpufreq driver limitations.
 */
static unsigned int get_next_freq(struct sugov_policy *sg_policy,
				  unsigned long util, unsigned long max)
{
	struct cpufreq_policy *policy = sg_policy->policy;
	unsigned int freq = arch_scale_freq_invariant() ?
				policy->cpuinfo.max_freq : policy->cur;

	freq = map_util_freq(util, freq, max);

	if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)
		return sg_policy->next_freq;

	sg_policy->cached_raw_freq = freq;
	return cpufreq_driver_resolve_freq(policy, freq);
}

/*
 * This function computes an effective utilization for the given CPU, to be
 * used for frequency selection given the linear relation: f = u * f_max.
 *
 * The scheduler tracks the following metrics:
 *
 *   cpu_util_{cfs,rt,dl,irq}()
 *   cpu_bw_dl()
 *
 * Where the cfs,rt and dl util numbers are tracked with the same metric and
 * synchronized windows and are thus directly comparable.
 *
 * The cfs,rt,dl utilization are the running times measured with rq->clock_task
 * which excludes things like IRQ and steal-time. These latter are then accrued
 * in the irq utilization.
 *
 * The DL bandwidth number otoh is not a measured metric but a value computed
 * based on the task model parameters and gives the minimal utilization
 * required to meet deadlines.
 */
unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
				 unsigned long max, enum schedutil_type type,
				 struct task_struct *p)
{
	unsigned long dl_util, util, irq;
	struct rq *rq = cpu_rq(cpu);

	if (!uclamp_is_used() &&
	    type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) {
		return max;
	}

	/*
	 * Early check to see if IRQ/steal time saturates the CPU, can be
	 * because of inaccuracies in how we track these -- see
	 * update_irq_load_avg().
	 */
	irq = cpu_util_irq(rq);
	if (unlikely(irq >= max))
		return max;

	/*
	 * Because the time spend on RT/DL tasks is visible as 'lost' time to
	 * CFS tasks and we use the same metric to track the effective
	 * utilization (PELT windows are synchronized) we can directly add them
	 * to obtain the CPU's actual utilization.
	 *
	 * CFS and RT utilization can be boosted or capped, depending on
	 * utilization clamp constraints requested by currently RUNNABLE
	 * tasks.
	 * When there are no CFS RUNNABLE tasks, clamps are released and
	 * frequency will be gracefully reduced with the utilization decay.
	 */
	util = util_cfs + cpu_util_rt(rq);
	if (type == FREQUENCY_UTIL)
		util = uclamp_rq_util_with(rq, util, p);

	dl_util = cpu_util_dl(rq);

	/*
	 * For frequency selection we do not make cpu_util_dl() a permanent part
	 * of this sum because we want to use cpu_bw_dl() later on, but we need
	 * to check if the CFS+RT+DL sum is saturated (ie. no idle time) such
	 * that we select f_max when there is no idle time.
	 *
	 * NOTE: numerical errors or stop class might cause us to not quite hit
	 * saturation when we should -- something for later.
	 */
	if (util + dl_util >= max)
		return max;

	/*
	 * OTOH, for energy computation we need the estimated running time, so
	 * include util_dl and ignore dl_bw.
	 */
	if (type == ENERGY_UTIL)
		util += dl_util;

	/*
	 * There is still idle time; further improve the number by using the
	 * irq metric. Because IRQ/steal time is hidden from the task clock we
	 * need to scale the task numbers:
	 *
	 *              max - irq
	 *   U' = irq + --------- * U
	 *                 max
	 */
	util = scale_irq_capacity(util, irq, max);
	util += irq;

	/*
	 * Bandwidth required by DEADLINE must always be granted while, for
	 * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism
	 * to gracefully reduce the frequency when no tasks show up for longer
	 * periods of time.
	 *
	 * Ideally we would like to set bw_dl as min/guaranteed freq and util +
	 * bw_dl as requested freq. However, cpufreq is not yet ready for such
	 * an interface. So, we only do the latter for now.
	 */
	if (type == FREQUENCY_UTIL)
		util += cpu_bw_dl(rq);

	return min(max, util);
}

static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
{
	struct rq *rq = cpu_rq(sg_cpu->cpu);
	unsigned long util = cpu_util_cfs(rq);
	unsigned long max = arch_scale_cpu_capacity(sg_cpu->cpu);

	sg_cpu->max = max;
	sg_cpu->bw_dl = cpu_bw_dl(rq);

	return schedutil_cpu_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL, NULL);
}

/**
 * sugov_iowait_reset() - Reset the IO boost status of a CPU.
 * @sg_cpu: the sugov data for the CPU to boost
 * @time: the update time from the caller
 * @set_iowait_boost: true if an IO boost has been requested
 *
 * The IO wait boost of a task is disabled after a tick since the last update
 * of a CPU. If a new IO wait boost is requested after more then a tick, then
 * we enable the boost starting from IOWAIT_BOOST_MIN, which improves energy
 * efficiency by ignoring sporadic wakeups from IO.
 */
static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time,
			       bool set_iowait_boost)
{
	s64 delta_ns = time - sg_cpu->last_update;

	/* Reset boost only if a tick has elapsed since last request */
	if (delta_ns <= TICK_NSEC)
		return false;

	sg_cpu->iowait_boost = set_iowait_boost ? IOWAIT_BOOST_MIN : 0;
	sg_cpu->iowait_boost_pending = set_iowait_boost;

	return true;
}

/**
 * sugov_iowait_boost() - Updates the IO boost status of a CPU.
 * @sg_cpu: the sugov data for the CPU to boost
 * @time: the update time from the caller
 * @flags: SCHED_CPUFREQ_IOWAIT if the task is waking up after an IO wait
 *
 * Each time a task wakes up after an IO operation, the CPU utilization can be
 * boosted to a certain utilization which doubles at each "frequent and
 * successive" wakeup from IO, ranging from IOWAIT_BOOST_MIN to the utilization
 * of the maximum OPP.
 *
 * To keep doubling, an IO boost has to be requested at least once per tick,
 * otherwise we restart from the utilization of the minimum OPP.
 */
static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
			       unsigned int flags)
{
	bool set_iowait_boost = flags & SCHED_CPUFREQ_IOWAIT;

	/* Reset boost if the CPU appears to have been idle enough */
	if (sg_cpu->iowait_boost &&
	    sugov_iowait_reset(sg_cpu, time, set_iowait_boost))
		return;

	/* Boost only tasks waking up after IO */
	if (!set_iowait_boost)
		return;

	/* Ensure boost doubles only one time at each request */
	if (sg_cpu->iowait_boost_pending)
		return;
	sg_cpu->iowait_boost_pending = true;

	/* Double the boost at each request */
	if (sg_cpu->iowait_boost) {
		sg_cpu->iowait_boost =
			min_t(unsigned int, sg_cpu->iowait_boost << 1, SCHED_CAPACITY_SCALE);
		return;
	}

	/* First wakeup after IO: start with minimum boost */
	sg_cpu->iowait_boost = IOWAIT_BOOST_MIN;
}

/**
 * sugov_iowait_apply() - Apply the IO boost to a CPU.
 * @sg_cpu: the sugov data for the cpu to boost
 * @time: the update time from the caller
 * @util: the utilization to (eventually) boost
 * @max: the maximum value the utilization can be boosted to
 *
 * A CPU running a task which woken up after an IO operation can have its
 * utilization boosted to speed up the completion of those IO operations.
 * The IO boost value is increased each time a task wakes up from IO, in
 * sugov_iowait_apply(), and it's instead decreased by this function,
 * each time an increase has not been requested (!iowait_boost_pending).
 *
 * A CPU which also appears to have been idle for at least one tick has also
 * its IO boost utilization reset.
 *
 * This mechanism is designed to boost high frequently IO waiting tasks, while
 * being more conservative on tasks which does sporadic IO operations.
 */
static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
					unsigned long util, unsigned long max)
{
	unsigned long boost;

	/* No boost currently required */
	if (!sg_cpu->iowait_boost)
		return util;

	/* Reset boost if the CPU appears to have been idle enough */
	if (sugov_iowait_reset(sg_cpu, time, false))
		return util;

	if (!sg_cpu->iowait_boost_pending) {
		/*
		 * No boost pending; reduce the boost value.
		 */
		sg_cpu->iowait_boost >>= 1;
		if (sg_cpu->iowait_boost < IOWAIT_BOOST_MIN) {
			sg_cpu->iowait_boost = 0;
			return util;
		}
	}

	sg_cpu->iowait_boost_pending = false;

	/*
	 * @util is already in capacity scale; convert iowait_boost
	 * into the same scale so we can compare.
	 */
	boost = (sg_cpu->iowait_boost * max) >> SCHED_CAPACITY_SHIFT;
	return max(boost, util);
}

#ifdef CONFIG_NO_HZ_COMMON
static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu)
{
	unsigned long idle_calls = tick_nohz_get_idle_calls_cpu(sg_cpu->cpu);
	bool ret = idle_calls == sg_cpu->saved_idle_calls;

	sg_cpu->saved_idle_calls = idle_calls;
	return ret;
}
#else
static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
#endif /* CONFIG_NO_HZ_COMMON */

/*
 * Make sugov_should_update_freq() ignore the rate limit when DL
 * has increased the utilization.
 */
static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy)
{
	if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
		sg_policy->limits_changed = true;
}

static void sugov_update_single(struct update_util_data *hook, u64 time,
				unsigned int flags)
{
	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
	unsigned long util, max;
	unsigned int next_f;
	unsigned int cached_freq = sg_policy->cached_raw_freq;

	sugov_iowait_boost(sg_cpu, time, flags);
	sg_cpu->last_update = time;

	ignore_dl_rate_limit(sg_cpu, sg_policy);

	if (!sugov_should_update_freq(sg_policy, time))
		return;

	util = sugov_get_util(sg_cpu);
	max = sg_cpu->max;
	util = sugov_iowait_apply(sg_cpu, time, util, max);
	next_f = get_next_freq(sg_policy, util, max);
	/*
	 * Do not reduce the frequency if the CPU has not been idle
	 * recently, as the reduction is likely to be premature then.
	 */
	if (sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
		next_f = sg_policy->next_freq;

		/* Restore cached freq as next_freq has changed */
		sg_policy->cached_raw_freq = cached_freq;
	}

	/*
	 * This code runs under rq->lock for the target CPU, so it won't run
	 * concurrently on two different CPUs for the same target and it is not
	 * necessary to acquire the lock in the fast switch case.
	 */
	if (sg_policy->policy->fast_switch_enabled) {
		sugov_fast_switch(sg_policy, time, next_f);
	} else {
		raw_spin_lock(&sg_policy->update_lock);
		sugov_deferred_update(sg_policy, time, next_f);
		raw_spin_unlock(&sg_policy->update_lock);
	}
}

static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
{
	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
	struct cpufreq_policy *policy = sg_policy->policy;
	unsigned long util = 0, max = 1;
	unsigned int j;

	for_each_cpu(j, policy->cpus) {
		struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
		unsigned long j_util, j_max;

		j_util = sugov_get_util(j_sg_cpu);
		j_max = j_sg_cpu->max;
		j_util = sugov_iowait_apply(j_sg_cpu, time, j_util, j_max);

		if (j_util * max > j_max * util) {
			util = j_util;
			max = j_max;
		}
	}

	return get_next_freq(sg_policy, util, max);
}

static void
sugov_update_shared(struct update_util_data *hook, u64 time, unsigned int flags)
{
	struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
	struct sugov_policy *sg_policy = sg_cpu->sg_policy;
	unsigned int next_f;

	raw_spin_lock(&sg_policy->update_lock);

	sugov_iowait_boost(sg_cpu, time, flags);
	sg_cpu->last_update = time;

	ignore_dl_rate_limit(sg_cpu, sg_policy);

	if (sugov_should_update_freq(sg_policy, time)) {
		next_f = sugov_next_freq_shared(sg_cpu, time);

		if (sg_policy->policy->fast_switch_enabled)
			sugov_fast_switch(sg_policy, time, next_f);
		else
			sugov_deferred_update(sg_policy, time, next_f);
	}

	raw_spin_unlock(&sg_policy->update_lock);
}

static void sugov_work(struct kthread_work *work)
{
	struct sugov_policy *sg_policy = container_of(work, struct sugov_policy, work);
	unsigned int freq;
	unsigned long flags;

	/*
	 * Hold sg_policy->update_lock shortly to handle the case where:
	 * incase sg_policy->next_freq is read here, and then updated by
	 * sugov_deferred_update() just before work_in_progress is set to false
	 * here, we may miss queueing the new update.
	 *
	 * Note: If a work was queued after the update_lock is released,
	 * sugov_work() will just be called again by kthread_work code; and the
	 * request will be proceed before the sugov thread sleeps.
	 */
	raw_spin_lock_irqsave(&sg_policy->update_lock, flags);
	freq = sg_policy->next_freq;
	sg_policy->work_in_progress = false;
	raw_spin_unlock_irqrestore(&sg_policy->update_lock, flags);

	mutex_lock(&sg_policy->work_lock);
	__cpufreq_driver_target(sg_policy->policy, freq, CPUFREQ_RELATION_L);
	mutex_unlock(&sg_policy->work_lock);
}

static void sugov_irq_work(struct irq_work *irq_work)
{
	struct sugov_policy *sg_policy;

	sg_policy = container_of(irq_work, struct sugov_policy, irq_work);

	kthread_queue_work(&sg_policy->worker, &sg_policy->work);
}

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

static struct sugov_tunables *global_tunables;
static DEFINE_MUTEX(global_tunables_lock);

static inline struct sugov_tunables *to_sugov_tunables(struct gov_attr_set *attr_set)
{
	return container_of(attr_set, struct sugov_tunables, attr_set);
}

static ssize_t rate_limit_us_show(struct gov_attr_set *attr_set, char *buf)
{
	struct sugov_tunables *tunables = to_sugov_tunables(attr_set);

	return sprintf(buf, "%u\n", tunables->rate_limit_us);
}

static ssize_t
rate_limit_us_store(struct gov_attr_set *attr_set, const char *buf, size_t count)
{
	struct sugov_tunables *tunables = to_sugov_tunables(attr_set);
	struct sugov_policy *sg_policy;
	unsigned int rate_limit_us;

	if (kstrtouint(buf, 10, &rate_limit_us))
		return -EINVAL;

	tunables->rate_limit_us = rate_limit_us;

	list_for_each_entry(sg_policy, &attr_set->policy_list, tunables_hook)
		sg_policy->freq_update_delay_ns = rate_limit_us * NSEC_PER_USEC;

	return count;
}

static struct governor_attr rate_limit_us = __ATTR_RW(rate_limit_us);

static struct attribute *sugov_attrs[] = {
	&rate_limit_us.attr,
	NULL
};
ATTRIBUTE_GROUPS(sugov);

static void sugov_tunables_free(struct kobject *kobj)
{
	struct gov_attr_set *attr_set = container_of(kobj, struct gov_attr_set, kobj);

	kfree(to_sugov_tunables(attr_set));
}

static struct kobj_type sugov_tunables_ktype = {
	.default_groups = sugov_groups,
	.sysfs_ops = &governor_sysfs_ops,
	.release = &sugov_tunables_free,
};

/********************** cpufreq governor interface *********************/

struct cpufreq_governor schedutil_gov;

static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy)
{
	struct sugov_policy *sg_policy;

	sg_policy = kzalloc(sizeof(*sg_policy), GFP_KERNEL);
	if (!sg_policy)
		return NULL;

	sg_policy->policy = policy;
	raw_spin_lock_init(&sg_policy->update_lock);
	return sg_policy;
}

static void sugov_policy_free(struct sugov_policy *sg_policy)
{
	kfree(sg_policy);
}

static int sugov_kthread_create(struct sugov_policy *sg_policy)
{
	struct task_struct *thread;
	struct sched_attr attr = {
		.size		= sizeof(struct sched_attr),
		.sched_policy	= SCHED_DEADLINE,
		.sched_flags	= SCHED_FLAG_SUGOV,
		.sched_nice	= 0,
		.sched_priority	= 0,
		/*
		 * Fake (unused) bandwidth; workaround to "fix"
		 * priority inheritance.
		 */
		.sched_runtime	=  1000000,
		.sched_deadline = 10000000,
		.sched_period	= 10000000,
	};
	struct cpufreq_policy *policy = sg_policy->policy;
	int ret;

	/* kthread only required for slow path */
	if (policy->fast_switch_enabled)
		return 0;

	kthread_init_work(&sg_policy->work, sugov_work);
	kthread_init_worker(&sg_policy->worker);
	thread = kthread_create(kthread_worker_fn, &sg_policy->worker,
				"sugov:%d",
				cpumask_first(policy->related_cpus));
	if (IS_ERR(thread)) {
		pr_err("failed to create sugov thread: %ld\n", PTR_ERR(thread));
		return PTR_ERR(thread);
	}

	ret = sched_setattr_nocheck(thread, &attr);
	if (ret) {
		kthread_stop(thread);
		pr_warn("%s: failed to set SCHED_DEADLINE\n", __func__);
		return ret;
	}

	sg_policy->thread = thread;
	kthread_bind_mask(thread, policy->related_cpus);
	init_irq_work(&sg_policy->irq_work, sugov_irq_work);
	mutex_init(&sg_policy->work_lock);

	wake_up_process(thread);

	return 0;
}

static void sugov_kthread_stop(struct sugov_policy *sg_policy)
{
	/* kthread only required for slow path */
	if (sg_policy->policy->fast_switch_enabled)
		return;

	kthread_flush_worker(&sg_policy->worker);
	kthread_stop(sg_policy->thread);
	mutex_destroy(&sg_policy->work_lock);
}

static struct sugov_tunables *sugov_tunables_alloc(struct sugov_policy *sg_policy)
{
	struct sugov_tunables *tunables;

	tunables = kzalloc(sizeof(*tunables), GFP_KERNEL);
	if (tunables) {
		gov_attr_set_init(&tunables->attr_set, &sg_policy->tunables_hook);
		if (!have_governor_per_policy())
			global_tunables = tunables;
	}
	return tunables;
}

static void sugov_clear_global_tunables(void)
{
	if (!have_governor_per_policy())
		global_tunables = NULL;
}

static int sugov_init(struct cpufreq_policy *policy)
{
	struct sugov_policy *sg_policy;
	struct sugov_tunables *tunables;
	int ret = 0;

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

	cpufreq_enable_fast_switch(policy);

	sg_policy = sugov_policy_alloc(policy);
	if (!sg_policy) {
		ret = -ENOMEM;
		goto disable_fast_switch;
	}

	ret = sugov_kthread_create(sg_policy);
	if (ret)
		goto free_sg_policy;

	mutex_lock(&global_tunables_lock);

	if (global_tunables) {
		if (WARN_ON(have_governor_per_policy())) {
			ret = -EINVAL;
			goto stop_kthread;
		}
		policy->governor_data = sg_policy;
		sg_policy->tunables = global_tunables;

		gov_attr_set_get(&global_tunables->attr_set, &sg_policy->tunables_hook);
		goto out;
	}

	tunables = sugov_tunables_alloc(sg_policy);
	if (!tunables) {
		ret = -ENOMEM;
		goto stop_kthread;
	}

	tunables->rate_limit_us = cpufreq_policy_transition_delay_us(policy);

	policy->governor_data = sg_policy;
	sg_policy->tunables = tunables;

	ret = kobject_init_and_add(&tunables->attr_set.kobj, &sugov_tunables_ktype,
				   get_governor_parent_kobj(policy), "%s",
				   schedutil_gov.name);
	if (ret)
		goto fail;

out:
	mutex_unlock(&global_tunables_lock);
	return 0;

fail:
	kobject_put(&tunables->attr_set.kobj);
	policy->governor_data = NULL;
	sugov_clear_global_tunables();

stop_kthread:
	sugov_kthread_stop(sg_policy);
	mutex_unlock(&global_tunables_lock);

free_sg_policy:
	sugov_policy_free(sg_policy);

disable_fast_switch:
	cpufreq_disable_fast_switch(policy);

	pr_err("initialization failed (error %d)\n", ret);
	return ret;
}

static void sugov_exit(struct cpufreq_policy *policy)
{
	struct sugov_policy *sg_policy = policy->governor_data;
	struct sugov_tunables *tunables = sg_policy->tunables;
	unsigned int count;

	mutex_lock(&global_tunables_lock);

	count = gov_attr_set_put(&tunables->attr_set, &sg_policy->tunables_hook);
	policy->governor_data = NULL;
	if (!count)
		sugov_clear_global_tunables();

	mutex_unlock(&global_tunables_lock);

	sugov_kthread_stop(sg_policy);
	sugov_policy_free(sg_policy);
	cpufreq_disable_fast_switch(policy);
}

static int sugov_start(struct cpufreq_policy *policy)
{
	struct sugov_policy *sg_policy = policy->governor_data;
	unsigned int cpu;

	sg_policy->freq_update_delay_ns	= sg_policy->tunables->rate_limit_us * NSEC_PER_USEC;
	sg_policy->last_freq_update_time	= 0;
	sg_policy->next_freq			= 0;
	sg_policy->work_in_progress		= false;
	sg_policy->limits_changed		= false;
	sg_policy->cached_raw_freq		= 0;

	sg_policy->need_freq_update = cpufreq_driver_test_flags(CPUFREQ_NEED_UPDATE_LIMITS);

	for_each_cpu(cpu, policy->cpus) {
		struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);

		memset(sg_cpu, 0, sizeof(*sg_cpu));
		sg_cpu->cpu			= cpu;
		sg_cpu->sg_policy		= sg_policy;
	}

	for_each_cpu(cpu, policy->cpus) {
		struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu);

		cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util,
					     policy_is_shared(policy) ?
							sugov_update_shared :
							sugov_update_single);
	}
	return 0;
}

static void sugov_stop(struct cpufreq_policy *policy)
{
	struct sugov_policy *sg_policy = policy->governor_data;
	unsigned int cpu;

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

	synchronize_rcu();

	if (!policy->fast_switch_enabled) {
		irq_work_sync(&sg_policy->irq_work);
		kthread_cancel_work_sync(&sg_policy->work);
	}
}

static void sugov_limits(struct cpufreq_policy *policy)
{
	struct sugov_policy *sg_policy = policy->governor_data;

	if (!policy->fast_switch_enabled) {
		mutex_lock(&sg_policy->work_lock);
		cpufreq_policy_apply_limits(policy);
		mutex_unlock(&sg_policy->work_lock);
	}

	sg_policy->limits_changed = true;
}

struct cpufreq_governor schedutil_gov = {
	.name			= "schedutil",
	.owner			= THIS_MODULE,
	.flags			= CPUFREQ_GOV_DYNAMIC_SWITCHING,
	.init			= sugov_init,
	.exit			= sugov_exit,
	.start			= sugov_start,
	.stop			= sugov_stop,
	.limits			= sugov_limits,
};

#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL
struct cpufreq_governor *cpufreq_default_governor(void)
{
	return &schedutil_gov;
}
#endif

cpufreq_governor_init(schedutil_gov);

#ifdef CONFIG_ENERGY_MODEL
extern bool sched_energy_update;
extern struct mutex sched_energy_mutex;

static void rebuild_sd_workfn(struct work_struct *work)
{
	mutex_lock(&sched_energy_mutex);
	sched_energy_update = true;
	rebuild_sched_domains();
	sched_energy_update = false;
	mutex_unlock(&sched_energy_mutex);
}
static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn);

/*
 * EAS shouldn't be attempted without sugov, so rebuild the sched_domains
 * on governor changes to make sure the scheduler knows about it.
 */
void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
				  struct cpufreq_governor *old_gov)
{
	if (old_gov == &schedutil_gov || policy->governor == &schedutil_gov) {
		/*
		 * When called from the cpufreq_register_driver() path, the
		 * cpu_hotplug_lock is already held, so use a work item to
		 * avoid nested locking in rebuild_sched_domains().
		 */
		schedule_work(&rebuild_sd_work);
	}

}
#endif