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
|
/*
* Thermal throttle event support code (such as syslog messaging and rate
* limiting) that was factored out from x86_64 (mce_intel.c) and i386 (p4.c).
*
* This allows consistent reporting of CPU thermal throttle events.
*
* Maintains a counter in /sys that keeps track of the number of thermal
* events, such that the user knows how bad the thermal problem might be
* (since the logging to syslog is rate limited).
*
* Author: Dmitriy Zavin (dmitriyz@google.com)
*
* Credits: Adapted from Zwane Mwaikambo's original code in mce_intel.c.
* Inspired by Ross Biro's and Al Borchers' counter code.
*/
#include <linux/interrupt.h>
#include <linux/notifier.h>
#include <linux/jiffies.h>
#include <linux/kernel.h>
#include <linux/percpu.h>
#include <linux/export.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/smp.h>
#include <linux/cpu.h>
#include <asm/processor.h>
#include <asm/apic.h>
#include <asm/mce.h>
#include <asm/msr.h>
#include <asm/trace/irq_vectors.h>
/* How long to wait between reporting thermal events */
#define CHECK_INTERVAL (300 * HZ)
#define THERMAL_THROTTLING_EVENT 0
#define POWER_LIMIT_EVENT 1
/*
* Current thermal event state:
*/
struct _thermal_state {
bool new_event;
int event;
u64 next_check;
unsigned long count;
unsigned long last_count;
};
struct thermal_state {
struct _thermal_state core_throttle;
struct _thermal_state core_power_limit;
struct _thermal_state package_throttle;
struct _thermal_state package_power_limit;
struct _thermal_state core_thresh0;
struct _thermal_state core_thresh1;
struct _thermal_state pkg_thresh0;
struct _thermal_state pkg_thresh1;
};
/* Callback to handle core threshold interrupts */
int (*platform_thermal_notify)(__u64 msr_val);
EXPORT_SYMBOL(platform_thermal_notify);
/* Callback to handle core package threshold_interrupts */
int (*platform_thermal_package_notify)(__u64 msr_val);
EXPORT_SYMBOL_GPL(platform_thermal_package_notify);
/* Callback support of rate control, return true, if
* callback has rate control */
bool (*platform_thermal_package_rate_control)(void);
EXPORT_SYMBOL_GPL(platform_thermal_package_rate_control);
static DEFINE_PER_CPU(struct thermal_state, thermal_state);
static atomic_t therm_throt_en = ATOMIC_INIT(0);
static u32 lvtthmr_init __read_mostly;
#ifdef CONFIG_SYSFS
#define define_therm_throt_device_one_ro(_name) \
static DEVICE_ATTR(_name, 0444, \
therm_throt_device_show_##_name, \
NULL) \
#define define_therm_throt_device_show_func(event, name) \
\
static ssize_t therm_throt_device_show_##event##_##name( \
struct device *dev, \
struct device_attribute *attr, \
char *buf) \
{ \
unsigned int cpu = dev->id; \
ssize_t ret; \
\
preempt_disable(); /* CPU hotplug */ \
if (cpu_online(cpu)) { \
ret = sprintf(buf, "%lu\n", \
per_cpu(thermal_state, cpu).event.name); \
} else \
ret = 0; \
preempt_enable(); \
\
return ret; \
}
define_therm_throt_device_show_func(core_throttle, count);
define_therm_throt_device_one_ro(core_throttle_count);
define_therm_throt_device_show_func(core_power_limit, count);
define_therm_throt_device_one_ro(core_power_limit_count);
define_therm_throt_device_show_func(package_throttle, count);
define_therm_throt_device_one_ro(package_throttle_count);
define_therm_throt_device_show_func(package_power_limit, count);
define_therm_throt_device_one_ro(package_power_limit_count);
static struct attribute *thermal_throttle_attrs[] = {
&dev_attr_core_throttle_count.attr,
NULL
};
static const struct attribute_group thermal_attr_group = {
.attrs = thermal_throttle_attrs,
.name = "thermal_throttle"
};
#endif /* CONFIG_SYSFS */
#define CORE_LEVEL 0
#define PACKAGE_LEVEL 1
/***
* therm_throt_process - Process thermal throttling event from interrupt
* @curr: Whether the condition is current or not (boolean), since the
* thermal interrupt normally gets called both when the thermal
* event begins and once the event has ended.
*
* This function is called by the thermal interrupt after the
* IRQ has been acknowledged.
*
* It will take care of rate limiting and printing messages to the syslog.
*/
static void therm_throt_process(bool new_event, int event, int level)
{
struct _thermal_state *state;
unsigned int this_cpu = smp_processor_id();
bool old_event;
u64 now;
struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu);
now = get_jiffies_64();
if (level == CORE_LEVEL) {
if (event == THERMAL_THROTTLING_EVENT)
state = &pstate->core_throttle;
else if (event == POWER_LIMIT_EVENT)
state = &pstate->core_power_limit;
else
return;
} else if (level == PACKAGE_LEVEL) {
if (event == THERMAL_THROTTLING_EVENT)
state = &pstate->package_throttle;
else if (event == POWER_LIMIT_EVENT)
state = &pstate->package_power_limit;
else
return;
} else
return;
old_event = state->new_event;
state->new_event = new_event;
if (new_event)
state->count++;
if (time_before64(now, state->next_check) &&
state->count != state->last_count)
return;
state->next_check = now + CHECK_INTERVAL;
state->last_count = state->count;
/* if we just entered the thermal event */
if (new_event) {
if (event == THERMAL_THROTTLING_EVENT)
pr_crit("CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n",
this_cpu,
level == CORE_LEVEL ? "Core" : "Package",
state->count);
return;
}
if (old_event) {
if (event == THERMAL_THROTTLING_EVENT)
pr_info("CPU%d: %s temperature/speed normal\n", this_cpu,
level == CORE_LEVEL ? "Core" : "Package");
return;
}
}
static int thresh_event_valid(int level, int event)
{
struct _thermal_state *state;
unsigned int this_cpu = smp_processor_id();
struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu);
u64 now = get_jiffies_64();
if (level == PACKAGE_LEVEL)
state = (event == 0) ? &pstate->pkg_thresh0 :
&pstate->pkg_thresh1;
else
state = (event == 0) ? &pstate->core_thresh0 :
&pstate->core_thresh1;
if (time_before64(now, state->next_check))
return 0;
state->next_check = now + CHECK_INTERVAL;
return 1;
}
static bool int_pln_enable;
static int __init int_pln_enable_setup(char *s)
{
int_pln_enable = true;
return 1;
}
__setup("int_pln_enable", int_pln_enable_setup);
#ifdef CONFIG_SYSFS
/* Add/Remove thermal_throttle interface for CPU device: */
static int thermal_throttle_add_dev(struct device *dev, unsigned int cpu)
{
int err;
struct cpuinfo_x86 *c = &cpu_data(cpu);
err = sysfs_create_group(&dev->kobj, &thermal_attr_group);
if (err)
return err;
if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable)
err = sysfs_add_file_to_group(&dev->kobj,
&dev_attr_core_power_limit_count.attr,
thermal_attr_group.name);
if (cpu_has(c, X86_FEATURE_PTS)) {
err = sysfs_add_file_to_group(&dev->kobj,
&dev_attr_package_throttle_count.attr,
thermal_attr_group.name);
if (cpu_has(c, X86_FEATURE_PLN) && int_pln_enable)
err = sysfs_add_file_to_group(&dev->kobj,
&dev_attr_package_power_limit_count.attr,
thermal_attr_group.name);
}
return err;
}
static void thermal_throttle_remove_dev(struct device *dev)
{
sysfs_remove_group(&dev->kobj, &thermal_attr_group);
}
/* Get notified when a cpu comes on/off. Be hotplug friendly. */
static int thermal_throttle_online(unsigned int cpu)
{
struct device *dev = get_cpu_device(cpu);
return thermal_throttle_add_dev(dev, cpu);
}
static int thermal_throttle_offline(unsigned int cpu)
{
struct device *dev = get_cpu_device(cpu);
thermal_throttle_remove_dev(dev);
return 0;
}
static __init int thermal_throttle_init_device(void)
{
int ret;
if (!atomic_read(&therm_throt_en))
return 0;
ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/therm:online",
thermal_throttle_online,
thermal_throttle_offline);
re
|