-
Notifications
You must be signed in to change notification settings - Fork 53.5k
/
cpufreq.c
1939 lines (1614 loc) · 48.5 KB
/
cpufreq.c
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
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* linux/drivers/cpufreq/cpufreq.c
*
* Copyright (C) 2001 Russell King
* (C) 2002 - 2003 Dominik Brodowski <[email protected]>
*
* Oct 2005 - Ashok Raj <[email protected]>
* Added handling for CPU hotplug
* Feb 2006 - Jacob Shin <[email protected]>
* Fix handling for CPU hotplug -- affected CPUs
*
* 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/notifier.h>
#include <linux/cpufreq.h>
#include <linux/delay.h>
#include <linux/interrupt.h>
#include <linux/spinlock.h>
#include <linux/device.h>
#include <linux/slab.h>
#include <linux/cpu.h>
#include <linux/completion.h>
#include <linux/mutex.h>
#include <linux/syscore_ops.h>
#include <trace/events/power.h>
/**
* The "cpufreq driver" - the arch- or hardware-dependent low
* level driver of CPUFreq support, and its spinlock. This lock
* also protects the cpufreq_cpu_data array.
*/
static struct cpufreq_driver *cpufreq_driver;
static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
#ifdef CONFIG_HOTPLUG_CPU
/* This one keeps track of the previously set governor of a removed CPU */
static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor);
#endif
static DEFINE_SPINLOCK(cpufreq_driver_lock);
/*
* cpu_policy_rwsem is a per CPU reader-writer semaphore designed to cure
* all cpufreq/hotplug/workqueue/etc related lock issues.
*
* The rules for this semaphore:
* - Any routine that wants to read from the policy structure will
* do a down_read on this semaphore.
* - Any routine that will write to the policy structure and/or may take away
* the policy altogether (eg. CPU hotplug), will hold this lock in write
* mode before doing so.
*
* Additional rules:
* - All holders of the lock should check to make sure that the CPU they
* are concerned with are online after they get the lock.
* - Governor routines that can be called in cpufreq hotplug path should not
* take this sem as top level hotplug notifier handler takes this.
* - Lock should not be held across
* __cpufreq_governor(data, CPUFREQ_GOV_STOP);
*/
static DEFINE_PER_CPU(int, cpufreq_policy_cpu);
static DEFINE_PER_CPU(struct rw_semaphore, cpu_policy_rwsem);
#define lock_policy_rwsem(mode, cpu) \
static int lock_policy_rwsem_##mode \
(int cpu) \
{ \
int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu); \
BUG_ON(policy_cpu == -1); \
down_##mode(&per_cpu(cpu_policy_rwsem, policy_cpu)); \
if (unlikely(!cpu_online(cpu))) { \
up_##mode(&per_cpu(cpu_policy_rwsem, policy_cpu)); \
return -1; \
} \
\
return 0; \
}
lock_policy_rwsem(read, cpu);
lock_policy_rwsem(write, cpu);
static void unlock_policy_rwsem_read(int cpu)
{
int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu);
BUG_ON(policy_cpu == -1);
up_read(&per_cpu(cpu_policy_rwsem, policy_cpu));
}
static void unlock_policy_rwsem_write(int cpu)
{
int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu);
BUG_ON(policy_cpu == -1);
up_write(&per_cpu(cpu_policy_rwsem, policy_cpu));
}
/* internal prototypes */
static int __cpufreq_governor(struct cpufreq_policy *policy,
unsigned int event);
static unsigned int __cpufreq_get(unsigned int cpu);
static void handle_update(struct work_struct *work);
/**
* Two notifier lists: the "policy" list is involved in the
* validation process for a new CPU frequency policy; the
* "transition" list for kernel code that needs to handle
* changes to devices when the CPU clock speed changes.
* The mutex locks both lists.
*/
static BLOCKING_NOTIFIER_HEAD(cpufreq_policy_notifier_list);
static struct srcu_notifier_head cpufreq_transition_notifier_list;
static bool init_cpufreq_transition_notifier_list_called;
static int __init init_cpufreq_transition_notifier_list(void)
{
srcu_init_notifier_head(&cpufreq_transition_notifier_list);
init_cpufreq_transition_notifier_list_called = true;
return 0;
}
pure_initcall(init_cpufreq_transition_notifier_list);
static int off __read_mostly;
int cpufreq_disabled(void)
{
return off;
}
void disable_cpufreq(void)
{
off = 1;
}
static LIST_HEAD(cpufreq_governor_list);
static DEFINE_MUTEX(cpufreq_governor_mutex);
struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
{
struct cpufreq_policy *data;
unsigned long flags;
if (cpu >= nr_cpu_ids)
goto err_out;
/* get the cpufreq driver */
spin_lock_irqsave(&cpufreq_driver_lock, flags);
if (!cpufreq_driver)
goto err_out_unlock;
if (!try_module_get(cpufreq_driver->owner))
goto err_out_unlock;
/* get the CPU */
data = per_cpu(cpufreq_cpu_data, cpu);
if (!data)
goto err_out_put_module;
if (!kobject_get(&data->kobj))
goto err_out_put_module;
spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
return data;
err_out_put_module:
module_put(cpufreq_driver->owner);
err_out_unlock:
spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
err_out:
return NULL;
}
EXPORT_SYMBOL_GPL(cpufreq_cpu_get);
void cpufreq_cpu_put(struct cpufreq_policy *data)
{
kobject_put(&data->kobj);
module_put(cpufreq_driver->owner);
}
EXPORT_SYMBOL_GPL(cpufreq_cpu_put);
/*********************************************************************
* EXTERNALLY AFFECTING FREQUENCY CHANGES *
*********************************************************************/
/**
* adjust_jiffies - adjust the system "loops_per_jiffy"
*
* This function alters the system "loops_per_jiffy" for the clock
* speed change. Note that loops_per_jiffy cannot be updated on SMP
* systems as each CPU might be scaled differently. So, use the arch
* per-CPU loops_per_jiffy value wherever possible.
*/
#ifndef CONFIG_SMP
static unsigned long l_p_j_ref;
static unsigned int l_p_j_ref_freq;
static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci)
{
if (ci->flags & CPUFREQ_CONST_LOOPS)
return;
if (!l_p_j_ref_freq) {
l_p_j_ref = loops_per_jiffy;
l_p_j_ref_freq = ci->old;
pr_debug("saving %lu as reference value for loops_per_jiffy; "
"freq is %u kHz\n", l_p_j_ref, l_p_j_ref_freq);
}
if ((val == CPUFREQ_POSTCHANGE && ci->old != ci->new) ||
(val == CPUFREQ_RESUMECHANGE || val == CPUFREQ_SUSPENDCHANGE)) {
loops_per_jiffy = cpufreq_scale(l_p_j_ref, l_p_j_ref_freq,
ci->new);
pr_debug("scaling loops_per_jiffy to %lu "
"for frequency %u kHz\n", loops_per_jiffy, ci->new);
}
}
#else
static inline void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci)
{
return;
}
#endif
/**
* cpufreq_notify_transition - call notifier chain and adjust_jiffies
* on frequency transition.
*
* This function calls the transition notifiers and the "adjust_jiffies"
* function. It is called twice on all CPU frequency changes that have
* external effects.
*/
void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state)
{
struct cpufreq_policy *policy;
BUG_ON(irqs_disabled());
freqs->flags = cpufreq_driver->flags;
pr_debug("notification %u of frequency transition to %u kHz\n",
state, freqs->new);
policy = per_cpu(cpufreq_cpu_data, freqs->cpu);
switch (state) {
case CPUFREQ_PRECHANGE:
/* detect if the driver reported a value as "old frequency"
* which is not equal to what the cpufreq core thinks is
* "old frequency".
*/
if (!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) {
if ((policy) && (policy->cpu == freqs->cpu) &&
(policy->cur) && (policy->cur != freqs->old)) {
pr_debug("Warning: CPU frequency is"
" %u, cpufreq assumed %u kHz.\n",
freqs->old, policy->cur);
freqs->old = policy->cur;
}
}
srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
CPUFREQ_PRECHANGE, freqs);
adjust_jiffies(CPUFREQ_PRECHANGE, freqs);
break;
case CPUFREQ_POSTCHANGE:
adjust_jiffies(CPUFREQ_POSTCHANGE, freqs);
pr_debug("FREQ: %lu - CPU: %lu", (unsigned long)freqs->new,
(unsigned long)freqs->cpu);
trace_power_frequency(POWER_PSTATE, freqs->new, freqs->cpu);
trace_cpu_frequency(freqs->new, freqs->cpu);
srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
CPUFREQ_POSTCHANGE, freqs);
if (likely(policy) && likely(policy->cpu == freqs->cpu))
policy->cur = freqs->new;
break;
}
}
EXPORT_SYMBOL_GPL(cpufreq_notify_transition);
/*********************************************************************
* SYSFS INTERFACE *
*********************************************************************/
static struct cpufreq_governor *__find_governor(const char *str_governor)
{
struct cpufreq_governor *t;
list_for_each_entry(t, &cpufreq_governor_list, governor_list)
if (!strnicmp(str_governor, t->name, CPUFREQ_NAME_LEN))
return t;
return NULL;
}
/**
* cpufreq_parse_governor - parse a governor string
*/
static int cpufreq_parse_governor(char *str_governor, unsigned int *policy,
struct cpufreq_governor **governor)
{
int err = -EINVAL;
if (!cpufreq_driver)
goto out;
if (cpufreq_driver->setpolicy) {
if (!strnicmp(str_governor, "performance", CPUFREQ_NAME_LEN)) {
*policy = CPUFREQ_POLICY_PERFORMANCE;
err = 0;
} else if (!strnicmp(str_governor, "powersave",
CPUFREQ_NAME_LEN)) {
*policy = CPUFREQ_POLICY_POWERSAVE;
err = 0;
}
} else if (cpufreq_driver->target) {
struct cpufreq_governor *t;
mutex_lock(&cpufreq_governor_mutex);
t = __find_governor(str_governor);
if (t == NULL) {
int ret;
mutex_unlock(&cpufreq_governor_mutex);
ret = request_module("cpufreq_%s", str_governor);
mutex_lock(&cpufreq_governor_mutex);
if (ret == 0)
t = __find_governor(str_governor);
}
if (t != NULL) {
*governor = t;
err = 0;
}
mutex_unlock(&cpufreq_governor_mutex);
}
out:
return err;
}
/**
* cpufreq_per_cpu_attr_read() / show_##file_name() -
* print out cpufreq information
*
* Write out information from cpufreq_driver->policy[cpu]; object must be
* "unsigned int".
*/
#define show_one(file_name, object) \
static ssize_t show_##file_name \
(struct cpufreq_policy *policy, char *buf) \
{ \
return sprintf(buf, "%u\n", policy->object); \
}
show_one(cpuinfo_min_freq, cpuinfo.min_freq);
show_one(cpuinfo_max_freq, cpuinfo.max_freq);
show_one(cpuinfo_transition_latency, cpuinfo.transition_latency);
show_one(scaling_min_freq, min);
show_one(scaling_max_freq, max);
show_one(scaling_cur_freq, cur);
static int __cpufreq_set_policy(struct cpufreq_policy *data,
struct cpufreq_policy *policy);
/**
* cpufreq_per_cpu_attr_write() / store_##file_name() - sysfs write access
*/
#define store_one(file_name, object) \
static ssize_t store_##file_name \
(struct cpufreq_policy *policy, const char *buf, size_t count) \
{ \
unsigned int ret = -EINVAL; \
struct cpufreq_policy new_policy; \
\
ret = cpufreq_get_policy(&new_policy, policy->cpu); \
if (ret) \
return -EINVAL; \
\
ret = sscanf(buf, "%u", &new_policy.object); \
if (ret != 1) \
return -EINVAL; \
\
ret = __cpufreq_set_policy(policy, &new_policy); \
policy->user_policy.object = policy->object; \
\
return ret ? ret : count; \
}
store_one(scaling_min_freq, min);
store_one(scaling_max_freq, max);
/**
* show_cpuinfo_cur_freq - current CPU frequency as detected by hardware
*/
static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy,
char *buf)
{
unsigned int cur_freq = __cpufreq_get(policy->cpu);
if (!cur_freq)
return sprintf(buf, "<unknown>");
return sprintf(buf, "%u\n", cur_freq);
}
/**
* show_scaling_governor - show the current policy for the specified CPU
*/
static ssize_t show_scaling_governor(struct cpufreq_policy *policy, char *buf)
{
if (policy->policy == CPUFREQ_POLICY_POWERSAVE)
return sprintf(buf, "powersave\n");
else if (policy->policy == CPUFREQ_POLICY_PERFORMANCE)
return sprintf(buf, "performance\n");
else if (policy->governor)
return scnprintf(buf, CPUFREQ_NAME_LEN, "%s\n",
policy->governor->name);
return -EINVAL;
}
/**
* store_scaling_governor - store policy for the specified CPU
*/
static ssize_t store_scaling_governor(struct cpufreq_policy *policy,
const char *buf, size_t count)
{
unsigned int ret = -EINVAL;
char str_governor[16];
struct cpufreq_policy new_policy;
ret = cpufreq_get_policy(&new_policy, policy->cpu);
if (ret)
return ret;
ret = sscanf(buf, "%15s", str_governor);
if (ret != 1)
return -EINVAL;
if (cpufreq_parse_governor(str_governor, &new_policy.policy,
&new_policy.governor))
return -EINVAL;
/* Do not use cpufreq_set_policy here or the user_policy.max
will be wrongly overridden */
ret = __cpufreq_set_policy(policy, &new_policy);
policy->user_policy.policy = policy->policy;
policy->user_policy.governor = policy->governor;
if (ret)
return ret;
else
return count;
}
/**
* show_scaling_driver - show the cpufreq driver currently loaded
*/
static ssize_t show_scaling_driver(struct cpufreq_policy *policy, char *buf)
{
return scnprintf(buf, CPUFREQ_NAME_LEN, "%s\n", cpufreq_driver->name);
}
/**
* show_scaling_available_governors - show the available CPUfreq governors
*/
static ssize_t show_scaling_available_governors(struct cpufreq_policy *policy,
char *buf)
{
ssize_t i = 0;
struct cpufreq_governor *t;
if (!cpufreq_driver->target) {
i += sprintf(buf, "performance powersave");
goto out;
}
list_for_each_entry(t, &cpufreq_governor_list, governor_list) {
if (i >= (ssize_t) ((PAGE_SIZE / sizeof(char))
- (CPUFREQ_NAME_LEN + 2)))
goto out;
i += scnprintf(&buf[i], CPUFREQ_NAME_LEN, "%s ", t->name);
}
out:
i += sprintf(&buf[i], "\n");
return i;
}
static ssize_t show_cpus(const struct cpumask *mask, char *buf)
{
ssize_t i = 0;
unsigned int cpu;
for_each_cpu(cpu, mask) {
if (i)
i += scnprintf(&buf[i], (PAGE_SIZE - i - 2), " ");
i += scnprintf(&buf[i], (PAGE_SIZE - i - 2), "%u", cpu);
if (i >= (PAGE_SIZE - 5))
break;
}
i += sprintf(&buf[i], "\n");
return i;
}
/**
* show_related_cpus - show the CPUs affected by each transition even if
* hw coordination is in use
*/
static ssize_t show_related_cpus(struct cpufreq_policy *policy, char *buf)
{
if (cpumask_empty(policy->related_cpus))
return show_cpus(policy->cpus, buf);
return show_cpus(policy->related_cpus, buf);
}
/**
* show_affected_cpus - show the CPUs affected by each transition
*/
static ssize_t show_affected_cpus(struct cpufreq_policy *policy, char *buf)
{
return show_cpus(policy->cpus, buf);
}
static ssize_t store_scaling_setspeed(struct cpufreq_policy *policy,
const char *buf, size_t count)
{
unsigned int freq = 0;
unsigned int ret;
if (!policy->governor || !policy->governor->store_setspeed)
return -EINVAL;
ret = sscanf(buf, "%u", &freq);
if (ret != 1)
return -EINVAL;
policy->governor->store_setspeed(policy, freq);
return count;
}
static ssize_t show_scaling_setspeed(struct cpufreq_policy *policy, char *buf)
{
if (!policy->governor || !policy->governor->show_setspeed)
return sprintf(buf, "<unsupported>\n");
return policy->governor->show_setspeed(policy, buf);
}
/**
* show_scaling_driver - show the current cpufreq HW/BIOS limitation
*/
static ssize_t show_bios_limit(struct cpufreq_policy *policy, char *buf)
{
unsigned int limit;
int ret;
if (cpufreq_driver->bios_limit) {
ret = cpufreq_driver->bios_limit(policy->cpu, &limit);
if (!ret)
return sprintf(buf, "%u\n", limit);
}
return sprintf(buf, "%u\n", policy->cpuinfo.max_freq);
}
cpufreq_freq_attr_ro_perm(cpuinfo_cur_freq, 0400);
cpufreq_freq_attr_ro(cpuinfo_min_freq);
cpufreq_freq_attr_ro(cpuinfo_max_freq);
cpufreq_freq_attr_ro(cpuinfo_transition_latency);
cpufreq_freq_attr_ro(scaling_available_governors);
cpufreq_freq_attr_ro(scaling_driver);
cpufreq_freq_attr_ro(scaling_cur_freq);
cpufreq_freq_attr_ro(bios_limit);
cpufreq_freq_attr_ro(related_cpus);
cpufreq_freq_attr_ro(affected_cpus);
cpufreq_freq_attr_rw(scaling_min_freq);
cpufreq_freq_attr_rw(scaling_max_freq);
cpufreq_freq_attr_rw(scaling_governor);
cpufreq_freq_attr_rw(scaling_setspeed);
static struct attribute *default_attrs[] = {
&cpuinfo_min_freq.attr,
&cpuinfo_max_freq.attr,
&cpuinfo_transition_latency.attr,
&scaling_min_freq.attr,
&scaling_max_freq.attr,
&affected_cpus.attr,
&related_cpus.attr,
&scaling_governor.attr,
&scaling_driver.attr,
&scaling_available_governors.attr,
&scaling_setspeed.attr,
NULL
};
struct kobject *cpufreq_global_kobject;
EXPORT_SYMBOL(cpufreq_global_kobject);
#define to_policy(k) container_of(k, struct cpufreq_policy, kobj)
#define to_attr(a) container_of(a, struct freq_attr, attr)
static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
{
struct cpufreq_policy *policy = to_policy(kobj);
struct freq_attr *fattr = to_attr(attr);
ssize_t ret = -EINVAL;
policy = cpufreq_cpu_get(policy->cpu);
if (!policy)
goto no_policy;
if (lock_policy_rwsem_read(policy->cpu) < 0)
goto fail;
if (fattr->show)
ret = fattr->show(policy, buf);
else
ret = -EIO;
unlock_policy_rwsem_read(policy->cpu);
fail:
cpufreq_cpu_put(policy);
no_policy:
return ret;
}
static ssize_t store(struct kobject *kobj, struct attribute *attr,
const char *buf, size_t count)
{
struct cpufreq_policy *policy = to_policy(kobj);
struct freq_attr *fattr = to_attr(attr);
ssize_t ret = -EINVAL;
policy = cpufreq_cpu_get(policy->cpu);
if (!policy)
goto no_policy;
if (lock_policy_rwsem_write(policy->cpu) < 0)
goto fail;
if (fattr->store)
ret = fattr->store(policy, buf, count);
else
ret = -EIO;
unlock_policy_rwsem_write(policy->cpu);
fail:
cpufreq_cpu_put(policy);
no_policy:
return ret;
}
static void cpufreq_sysfs_release(struct kobject *kobj)
{
struct cpufreq_policy *policy = to_policy(kobj);
pr_debug("last reference is dropped\n");
complete(&policy->kobj_unregister);
}
static const struct sysfs_ops sysfs_ops = {
.show = show,
.store = store,
};
static struct kobj_type ktype_cpufreq = {
.sysfs_ops = &sysfs_ops,
.default_attrs = default_attrs,
.release = cpufreq_sysfs_release,
};
/*
* Returns:
* Negative: Failure
* 0: Success
* Positive: When we have a managed CPU and the sysfs got symlinked
*/
static int cpufreq_add_dev_policy(unsigned int cpu,
struct cpufreq_policy *policy,
struct device *dev)
{
int ret = 0;
#ifdef CONFIG_SMP
unsigned long flags;
unsigned int j;
#ifdef CONFIG_HOTPLUG_CPU
struct cpufreq_governor *gov;
gov = __find_governor(per_cpu(cpufreq_cpu_governor, cpu));
if (gov) {
policy->governor = gov;
pr_debug("Restoring governor %s for cpu %d\n",
policy->governor->name, cpu);
}
#endif
for_each_cpu(j, policy->cpus) {
struct cpufreq_policy *managed_policy;
if (cpu == j)
continue;
/* Check for existing affected CPUs.
* They may not be aware of it due to CPU Hotplug.
* cpufreq_cpu_put is called when the device is removed
* in __cpufreq_remove_dev()
*/
managed_policy = cpufreq_cpu_get(j);
if (unlikely(managed_policy)) {
/* Set proper policy_cpu */
unlock_policy_rwsem_write(cpu);
per_cpu(cpufreq_policy_cpu, cpu) = managed_policy->cpu;
if (lock_policy_rwsem_write(cpu) < 0) {
/* Should not go through policy unlock path */
if (cpufreq_driver->exit)
cpufreq_driver->exit(policy);
cpufreq_cpu_put(managed_policy);
return -EBUSY;
}
spin_lock_irqsave(&cpufreq_driver_lock, flags);
cpumask_copy(managed_policy->cpus, policy->cpus);
per_cpu(cpufreq_cpu_data, cpu) = managed_policy;
spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
pr_debug("CPU already managed, adding link\n");
ret = sysfs_create_link(&dev->kobj,
&managed_policy->kobj,
"cpufreq");
if (ret)
cpufreq_cpu_put(managed_policy);
/*
* Success. We only needed to be added to the mask.
* Call driver->exit() because only the cpu parent of
* the kobj needed to call init().
*/
if (cpufreq_driver->exit)
cpufreq_driver->exit(policy);
if (!ret)
return 1;
else
return ret;
}
}
#endif
return ret;
}
/* symlink affected CPUs */
static int cpufreq_add_dev_symlink(unsigned int cpu,
struct cpufreq_policy *policy)
{
unsigned int j;
int ret = 0;
for_each_cpu(j, policy->cpus) {
struct cpufreq_policy *managed_policy;
struct device *cpu_dev;
if (j == cpu)
continue;
if (!cpu_online(j))
continue;
pr_debug("CPU %u already managed, adding link\n", j);
managed_policy = cpufreq_cpu_get(cpu);
cpu_dev = get_cpu_device(j);
ret = sysfs_create_link(&cpu_dev->kobj, &policy->kobj,
"cpufreq");
if (ret) {
cpufreq_cpu_put(managed_policy);
return ret;
}
}
return ret;
}
static int cpufreq_add_dev_interface(unsigned int cpu,
struct cpufreq_policy *policy,
struct device *dev)
{
struct cpufreq_policy new_policy;
struct freq_attr **drv_attr;
unsigned long flags;
int ret = 0;
unsigned int j;
/* prepare interface data */
ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq,
&dev->kobj, "cpufreq");
if (ret)
return ret;
/* set up files for this cpu device */
drv_attr = cpufreq_driver->attr;
while ((drv_attr) && (*drv_attr)) {
ret = sysfs_create_file(&policy->kobj, &((*drv_attr)->attr));
if (ret)
goto err_out_kobj_put;
drv_attr++;
}
if (cpufreq_driver->get) {
ret = sysfs_create_file(&policy->kobj, &cpuinfo_cur_freq.attr);
if (ret)
goto err_out_kobj_put;
}
if (cpufreq_driver->target) {
ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr);
if (ret)
goto err_out_kobj_put;
}
if (cpufreq_driver->bios_limit) {
ret = sysfs_create_file(&policy->kobj, &bios_limit.attr);
if (ret)
goto err_out_kobj_put;
}
spin_lock_irqsave(&cpufreq_driver_lock, flags);
for_each_cpu(j, policy->cpus) {
if (!cpu_online(j))
continue;
per_cpu(cpufreq_cpu_data, j) = policy;
per_cpu(cpufreq_policy_cpu, j) = policy->cpu;
}
spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
ret = cpufreq_add_dev_symlink(cpu, policy);
if (ret)
goto err_out_kobj_put;
memcpy(&new_policy, policy, sizeof(struct cpufreq_policy));
/* assure that the starting sequence is run in __cpufreq_set_policy */
policy->governor = NULL;
/* set default policy */
ret = __cpufreq_set_policy(policy, &new_policy);
policy->user_policy.policy = policy->policy;
policy->user_policy.governor = policy->governor;
if (ret) {
pr_debug("setting policy failed\n");
if (cpufreq_driver->exit)
cpufreq_driver->exit(policy);
}
return ret;
err_out_kobj_put:
kobject_put(&policy->kobj);
wait_for_completion(&policy->kobj_unregister);
return ret;
}
/**
* cpufreq_add_dev - add a CPU device
*
* Adds the cpufreq interface for a CPU device.
*
* The Oracle says: try running cpufreq registration/unregistration concurrently
* with with cpu hotplugging and all hell will break loose. Tried to clean this
* mess up, but more thorough testing is needed. - Mathieu
*/
static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
{
unsigned int cpu = dev->id;
int ret = 0, found = 0;
struct cpufreq_policy *policy;
unsigned long flags;
unsigned int j;
#ifdef CONFIG_HOTPLUG_CPU
int sibling;
#endif
if (cpu_is_offline(cpu))
return 0;
pr_debug("adding CPU %u\n", cpu);
#ifdef CONFIG_SMP
/* check whether a different CPU already registered this
* CPU because it is in the same boat. */
policy = cpufreq_cpu_get(cpu);
if (unlikely(policy)) {
cpufreq_cpu_put(policy);
return 0;
}
#endif
if (!try_module_get(cpufreq_driver->owner)) {
ret = -EINVAL;
goto module_out;
}
ret = -ENOMEM;
policy = kzalloc(sizeof(struct cpufreq_policy), GFP_KERNEL);
if (!policy)
goto nomem_out;
if (!alloc_cpumask_var(&policy->cpus, GFP_KERNEL))
goto err_free_policy;
if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL))
goto err_free_cpumask;
policy->cpu = cpu;
cpumask_copy(policy->cpus, cpumask_of(cpu));
/* Initially set CPU itself as the policy_cpu */
per_cpu(cpufreq_policy_cpu, cpu) = cpu;
ret = (lock_policy_rwsem_write(cpu) < 0);
WARN_ON(ret);
init_completion(&policy->kobj_unregister);
INIT_WORK(&policy->update, handle_update);
/* Set governor before ->init, so that driver could check it */
#ifdef CONFIG_HOTPLUG_CPU
for_each_online_cpu(sibling) {
struct cpufreq_policy *cp = per_cpu(cpufreq_cpu_data, sibling);
if (cp && cp->governor &&
(cpumask_test_cpu(cpu, cp->related_cpus))) {
policy->governor = cp->governor;
found = 1;
break;
}
}
#endif
if (!found)
policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
/* call driver. From then on the cpufreq must be able
* to accept all calls to ->verify and ->setpolicy for this CPU
*/
ret = cpufreq_driver->init(policy);
if (ret) {
pr_debug("initialization failed\n");
goto err_unlock_policy;
}
policy->user_policy.min = policy->min;
policy->user_policy.max = policy->max;
blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
CPUFREQ_START, policy);
ret = cpufreq_add_dev_policy(cpu, policy, dev);
if (ret) {
if (ret > 0)
/* This is a managed cpu, symlink created,
exit with 0 */
ret = 0;
goto err_unlock_policy;
}
ret = cpufreq_add_dev_interface(cpu, policy, dev);
if (ret)
goto err_out_unregister;
unlock_policy_rwsem_write(cpu);
kobject_uevent(&policy->kobj, KOBJ_ADD);
module_put(cpufreq_driver->owner);
pr_debug("initialization complete\n");
return 0;
err_out_unregister:
spin_lock_irqsave(&cpufreq_driver_lock, flags);
for_each_cpu(j, policy->cpus)
per_cpu(cpufreq_cpu_data, j) = NULL;
spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
kobject_put(&policy->kobj);
wait_for_completion(&policy->kobj_unregister);
err_unlock_policy:
unlock_policy_rwsem_write(cpu);
free_cpumask_var(policy->related_cpus);
err_free_cpumask:
free_cpumask_var(policy->cpus);
err_free_policy:
kfree(policy);
nomem_out:
module_put(cpufreq_driver->owner);
module_out:
return ret;
}