summaryrefslogtreecommitdiff
path: root/arch/x86/events/intel/cstate.c
blob: 9ba4e4136a1539ba791052b726c12343694ea85f (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
/*
 * perf_event_intel_cstate.c: support cstate residency counters
 *
 * Copyright (C) 2015, Intel Corp.
 * Author: Kan Liang (kan.liang@intel.com)
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Library General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Library General Public License for more details.
 *
 */

/*
 * This file export cstate related free running (read-only) counters
 * for perf. These counters may be use simultaneously by other tools,
 * such as turbostat. However, it still make sense to implement them
 * in perf. Because we can conveniently collect them together with
 * other events, and allow to use them from tools without special MSR
 * access code.
 *
 * The events only support system-wide mode counting. There is no
 * sampling support because it is not supported by the hardware.
 *
 * According to counters' scope and category, two PMUs are registered
 * with the perf_event core subsystem.
 *  - 'cstate_core': The counter is available for each physical core.
 *    The counters include CORE_C*_RESIDENCY.
 *  - 'cstate_pkg': The counter is available for each physical package.
 *    The counters include PKG_C*_RESIDENCY.
 *
 * All of these counters are specified in the Intel® 64 and IA-32
 * Architectures Software Developer.s Manual Vol3b.
 *
 * Model specific counters:
 *	MSR_CORE_C1_RES: CORE C1 Residency Counter
 *			 perf code: 0x00
 *			 Available model: SLM,AMT
 *			 Scope: Core (each processor core has a MSR)
 *	MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
 *			       perf code: 0x01
 *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL
 *			       Scope: Core
 *	MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
 *			       perf code: 0x02
 *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL
 *			       Scope: Core
 *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
 *			       perf code: 0x03
 *			       Available model: SNB,IVB,HSW,BDW,SKL
 *			       Scope: Core
 *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
 *			       perf code: 0x00
 *			       Available model: SNB,IVB,HSW,BDW,SKL
 *			       Scope: Package (physical package)
 *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
 *			       perf code: 0x01
 *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL
 *			       Scope: Package (physical package)
 *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
 *			       perf code: 0x02
 *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL
 *			       Scope: Package (physical package)
 *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
 *			       perf code: 0x03
 *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL
 *			       Scope: Package (physical package)
 *	MSR_PKG_C8_RESIDENCY:  Package C8 Residency Counter.
 *			       perf code: 0x04
 *			       Available model: HSW ULT only
 *			       Scope: Package (physical package)
 *	MSR_PKG_C9_RESIDENCY:  Package C9 Residency Counter.
 *			       perf code: 0x05
 *			       Available model: HSW ULT only
 *			       Scope: Package (physical package)
 *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
 *			       perf code: 0x06
 *			       Available model: HSW ULT only
 *			       Scope: Package (physical package)
 *
 */

#include <linux/module.h>
#include <linux/slab.h>
#include <linux/perf_event.h>
#include <asm/cpu_device_id.h>
#include "../perf_event.h"

MODULE_LICENSE("GPL");

#define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format)		\
static ssize_t __cstate_##_var##_show(struct kobject *kobj,	\
				struct kobj_attribute *attr,	\
				char *page)			\
{								\
	BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE);		\
	return sprintf(page, _format "\n");			\
}								\
static struct kobj_attribute format_attr_##_var =		\
	__ATTR(_name, 0444, __cstate_##_var##_show, NULL)

static ssize_t cstate_get_attr_cpumask(struct device *dev,
				       struct device_attribute *attr,
				       char *buf);

/* Model -> events mapping */
struct cstate_model {
	unsigned long		core_events;
	unsigned long		pkg_events;
	unsigned long		quirks;
};

/* Quirk flags */
#define SLM_PKG_C6_USE_C7_MSR	(1UL << 0)

struct perf_cstate_msr {
	u64	msr;
	struct	perf_pmu_events_attr *attr;
};


/* cstate_core PMU */
static struct pmu cstate_core_pmu;
static bool has_cstate_core;

enum perf_cstate_core_events {
	PERF_CSTATE_CORE_C1_RES = 0,
	PERF_CSTATE_CORE_C3_RES,
	PERF_CSTATE_CORE_C6_RES,
	PERF_CSTATE_CORE_C7_RES,

	PERF_CSTATE_CORE_EVENT_MAX,
};

PMU_EVENT_ATTR_STRING(c1-residency, evattr_cstate_core_c1, "event=0x00");
PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_core_c3, "event=0x01");
PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_core_c6, "event=0x02");
PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_core_c7, "event=0x03");

static struct perf_cstate_msr core_msr[] = {
	[PERF_CSTATE_CORE_C1_RES] = { MSR_CORE_C1_RES,		&evattr_cstate_core_c1 },
	[PERF_CSTATE_CORE_C3_RES] = { MSR_CORE_C3_RESIDENCY,	&evattr_cstate_core_c3 },
	[PERF_CSTATE_CORE_C6_RES] = { MSR_CORE_C6_RESIDENCY,	&evattr_cstate_core_c6 },
	[PERF_CSTATE_CORE_C7_RES] = { MSR_CORE_C7_RESIDENCY,	&evattr_cstate_core_c7 },
};

static struct attribute *core_events_attrs[PERF_CSTATE_CORE_EVENT_MAX + 1] = {
	NULL,
};

static struct attribute_group core_events_attr_group = {
	.name = "events",
	.attrs = core_events_attrs,
};

DEFINE_CSTATE_FORMAT_ATTR(core_event, event, "config:0-63");
static struct attribute *core_format_attrs[] = {
	&format_attr_core_event.attr,
	NULL,
};

static struct attribute_group core_format_attr_group = {
	.name = "format",
	.attrs = core_format_attrs,
};

static cpumask_t cstate_core_cpu_mask;
static DEVICE_ATTR(cpumask, S_IRUGO, cstate_get_attr_cpumask, NULL);

static struct attribute *cstate_cpumask_attrs[] = {
	&dev_attr_cpumask.attr,
	NULL,
};

static struct attribute_group cpumask_attr_group = {
	.attrs = cstate_cpumask_attrs,
};

static const struct attribute_group *core_attr_groups[] = {
	&core_events_attr_group,
	&core_format_attr_group,
	&cpumask_attr_group,
	NULL,
};

/* cstate_pkg PMU */
static struct pmu cstate_pkg_pmu;
static bool has_cstate_pkg;

enum perf_cstate_pkg_events {
	PERF_CSTATE_PKG_C2_RES = 0,
	PERF_CSTATE_PKG_C3_RES,
	PERF_CSTATE_PKG_C6_RES,
	PERF_CSTATE_PKG_C7_RES,
	PERF_CSTATE_PKG_C8_RES,
	PERF_CSTATE_PKG_C9_RES,
	PERF_CSTATE_PKG_C10_RES,

	PERF_CSTATE_PKG_EVENT_MAX,
};

PMU_EVENT_ATTR_STRING(c2-residency, evattr_cstate_pkg_c2, "event=0x00");
PMU_EVENT_ATTR_STRING(c3-residency, evattr_cstate_pkg_c3, "event=0x01");
PMU_EVENT_ATTR_STRING(c6-residency, evattr_cstate_pkg_c6, "event=0x02");
PMU_EVENT_ATTR_STRING(c7-residency, evattr_cstate_pkg_c7, "event=0x03");
PMU_EVENT_ATTR_STRING(c8-residency, evattr_cstate_pkg_c8, "event=0x04");
PMU_EVENT_ATTR_STRING(c9-residency, evattr_cstate_pkg_c9, "event=0x05");
PMU_EVENT_ATTR_STRING(c10-residency, evattr_cstate_pkg_c10, "event=0x06");

static struct perf_cstate_msr pkg_msr[] = {
	[PERF_CSTATE_PKG_C2_RES] = { MSR_PKG_C2_RESIDENCY,	&evattr_cstate_pkg_c2 },
	[PERF_CSTATE_PKG_C3_RES] = { MSR_PKG_C3_RESIDENCY,	&evattr_cstate_pkg_c3 },
	[PERF_CSTATE_PKG_C6_RES] = { MSR_PKG_C6_RESIDENCY,	&evattr_cstate_pkg_c6 },
	[PERF_CSTATE_PKG_C7_RES] = { MSR_PKG_C7_RESIDENCY,	&evattr_cstate_pkg_c7 },
	[PERF_CSTATE_PKG_C8_RES] = { MSR_PKG_C8_RESIDENCY,	&evattr_cstate_pkg_c8 },
	[PERF_CSTATE_PKG_C9_RES] = { MSR_PKG_C9_RESIDENCY,	&evattr_cstate_pkg_c9 },
	[PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY,	&evattr_cstate_pkg_c10 },
};

static struct attribute *pkg_events_attrs[PERF_CSTATE_PKG_EVENT_MAX + 1] = {
	NULL,
};

static struct attribute_group pkg_events_attr_group = {
	.name = "events",
	.attrs = pkg_events_attrs,
};

DEFINE_CSTATE_FORMAT_ATTR(pkg_event, event, "config:0-63");
static struct attribute *pkg_format_attrs[] = {
	&format_attr_pkg_event.attr,
	NULL,
};
static struct attribute_group pkg_format_attr_group = {
	.name = "format",
	.attrs = pkg_format_attrs,
};

static cpumask_t cstate_pkg_cpu_mask;

static const struct attribute_group *pkg_attr_groups[] = {
	&pkg_events_attr_group,
	&pkg_format_attr_group,
	&cpumask_attr_group,
	NULL,
};

static ssize_t cstate_get_attr_cpumask(struct device *dev,
				       struct device_attribute *attr,
				       char *buf)
{
	struct pmu *pmu = dev_get_drvdata(dev);

	if (pmu == &cstate_core_pmu)
		return cpumap_print_to_pagebuf(true, buf, &cstate_core_cpu_mask);
	else if (pmu == &cstate_pkg_pmu)
		return cpumap_print_to_pagebuf(true, buf, &cstate_pkg_cpu_mask);
	else
		return 0;
}

static int cstate_pmu_event_init(struct perf_event *event)
{
	u64 cfg = event->attr.config;
	int cpu;

	if (event->attr.type != event->pmu->type)
		return -ENOENT;

	/* unsupported modes and filters */
	if (event->attr.exclude_user   ||
	    event->attr.exclude_kernel ||
	    event->attr.exclude_hv     ||
	    event->attr.exclude_idle   ||
	    event->attr.exclude_host   ||
	    event->attr.exclude_guest  ||
	    event->attr.sample_period) /* no sampling */
		return -EINVAL;

	if (event->cpu < 0)
		return -EINVAL;

	if (event->pmu == &cstate_core_pmu) {
		if (cfg >= PERF_CSTATE_CORE_EVENT_MAX)
			return -EINVAL;
		if (!core_msr[cfg].attr)
			return -EINVAL;
		event->hw.event_base = core_msr[cfg].msr;
		cpu = cpumask_any_and(&cstate_core_cpu_mask,
				      topology_sibling_cpumask(event->cpu));
	} else if (event->pmu == &cstate_pkg_pmu) {
		if (cfg >= PERF_CSTATE_PKG_EVENT_MAX)
			return -EINVAL;
		if (!pkg_msr[cfg].attr)
			return -EINVAL;
		event->hw.event_base = pkg_msr[cfg].msr;
		cpu = cpumask_any_and(&cstate_pkg_cpu_mask,
				      topology_core_cpumask(event->cpu));
	} else {
		return -ENOENT;
	}

	if (cpu >= nr_cpu_ids)
		return -ENODEV;

	event->cpu = cpu;
	event->hw.config = cfg;
	event->hw.idx = -1;
	return 0;
}

static inline u64 cstate_pmu_read_counter(struct perf_event *event)
{
	u64 val;

	rdmsrl(event->hw.event_base, val);
	return val;
}

static void cstate_pmu_event_update(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;
	u64 prev_raw_count, new_raw_count;

again:
	prev_raw_count = local64_read(&hwc->prev_count);
	new_raw_count = cstate_pmu_read_counter(event);

	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
			    new_raw_count) != prev_raw_count)
		goto again;

	local64_add(new_raw_count - prev_raw_count, &event->count);
}

static void cstate_pmu_event_start(struct perf_event *event, int mode)
{
	local64_set(&event->hw.prev_count, cstate_pmu_read_counter(event));
}

static void cstate_pmu_event_stop(struct perf_event *event, int mode)
{
	cstate_pmu_event_update(event);
}

static void cstate_pmu_event_del(struct perf_event *event, int mode)
{
	cstate_pmu_event_stop(event, PERF_EF_UPDATE);
}

static int cstate_pmu_event_add(struct perf_event *event, int mode)
{
	if (mode & PERF_EF_START)
		cstate_pmu_event_start(event, mode);

	return 0;
}

/*
 * Check if exiting cpu is the designated reader. If so migrate the
 * events when there is a valid target available
 */
static void cstate_cpu_exit(int cpu)
{
	unsigned int target;

	if (has_cstate_core &&
	    cpumask_test_and_clear_cpu(cpu, &cstate_core_cpu_mask)) {

		target = cpumask_any_but(topology_sibling_cpumask(cpu), cpu);
		/* Migrate events if there is a valid target */
		if (target < nr_cpu_ids) {
			cpumask_set_cpu(target, &cstate_core_cpu_mask);
			perf_pmu_migrate_context(&cstate_core_pmu, cpu, target);
		}
	}

	if (has_cstate_pkg &&
	    cpumask_test_and_clear_cpu(cpu, &cstate_pkg_cpu_mask)) {

		target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
		/* Migrate events if there is a valid target */
		if (target < nr_cpu_ids) {
			cpumask_set_cpu(target, &cstate_pkg_cpu_mask);
			perf_pmu_migrate_context(&cstate_pkg_pmu, cpu, target);
		}
	}
}

static void cstate_cpu_init(int cpu)
{
	unsigned int target;

	/*
	 * If this is the first online thread of that core, set it in
	 * the core cpu mask as the designated reader.
	 */
	target = cpumask_any_and(&cstate_core_cpu_mask,
				 topology_sibling_cpumask(cpu));

	if (has_cstate_core && target >= nr_cpu_ids)
		cpumask_set_cpu(cpu, &cstate_core_cpu_mask);

	/*
	 * If this is the first online thread of that package, set it
	 * in the package cpu mask as the designated reader.
	 */
	target = cpumask_any_and(&cstate_pkg_cpu_mask,
				 topology_core_cpumask(cpu));
	if (has_cstate_pkg && target >= nr_cpu_ids)
		cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask);
}

static int cstate_cpu_notifier(struct notifier_block *self,
			       unsigned long action, void *hcpu)
{
	unsigned int cpu = (long)hcpu;

	switch (action & ~CPU_TASKS_FROZEN) {
	case CPU_STARTING:
		cstate_cpu_init(cpu);
		break;
	case CPU_DOWN_PREPARE:
		cstate_cpu_exit(cpu);
		break;
	default:
		break;
	}
	return NOTIFY_OK;
}

static struct notifier_block cstate_cpu_nb = {
	.notifier_call	= cstate_cpu_notifier,
	.priority       = CPU_PRI_PERF + 1,
};

static struct pmu cstate_core_pmu = {
	.attr_groups	= core_attr_groups,
	.name		= "cstate_core",
	.task_ctx_nr	= perf_invalid_context,
	.event_init	= cstate_pmu_event_init,
	.add		= cstate_pmu_event_add,
	.del		= cstate_pmu_event_del,
	.start		= cstate_pmu_event_start,
	.stop		= cstate_pmu_event_stop,
	.read		= cstate_pmu_event_update,
	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT,
};

static struct pmu cstate_pkg_pmu = {
	.attr_groups	= pkg_attr_groups,
	.name		= "cstate_pkg",
	.task_ctx_nr	= perf_invalid_context,
	.event_init	= cstate_pmu_event_init,
	.add		= cstate_pmu_event_add,
	.del		= cstate_pmu_event_del,
	.start		= cstate_pmu_event_start,
	.stop		= cstate_pmu_event_stop,
	.read		= cstate_pmu_event_update,
	.capabilities	= PERF_PMU_CAP_NO_INTERRUPT,
};

static const struct cstate_model nhm_cstates __initconst = {
	.core_events		= BIT(PERF_CSTATE_CORE_C3_RES) |
				  BIT(PERF_CSTATE_CORE_C6_RES),

	.pkg_events		= BIT(PERF_CSTATE_PKG_C3_RES) |
				  BIT(PERF_CSTATE_PKG_C6_RES) |
				  BIT(PERF_CSTATE_PKG_C7_RES),
};

static const struct cstate_model snb_cstates __initconst = {
	.core_events		= BIT(PERF_CSTATE_CORE_C3_RES) |
				  BIT(PERF_CSTATE_CORE_C6_RES) |
				  BIT(PERF_CSTATE_CORE_C7_RES),

	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
				  BIT(PERF_CSTATE_PKG_C3_RES) |
				  BIT(PERF_CSTATE_PKG_C6_RES) |
				  BIT(PERF_CSTATE_PKG_C7_RES),
};

static const struct cstate_model hswult_cstates __initconst = {
	.core_events		= BIT(PERF_CSTATE_CORE_C3_RES) |
				  BIT(PERF_CSTATE_CORE_C6_RES) |
				  BIT(PERF_CSTATE_CORE_C7_RES),

	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
				  BIT(PERF_CSTATE_PKG_C3_RES) |
				  BIT(PERF_CSTATE_PKG_C6_RES) |
				  BIT(PERF_CSTATE_PKG_C7_RES) |
				  BIT(PERF_CSTATE_PKG_C8_RES) |
				  BIT(PERF_CSTATE_PKG_C9_RES) |
				  BIT(PERF_CSTATE_PKG_C10_RES),
};

static const struct cstate_model slm_cstates __initconst = {
	.core_events		= BIT(PERF_CSTATE_CORE_C1_RES) |
				  BIT(PERF_CSTATE_CORE_C6_RES),

	.pkg_events		= BIT(PERF_CSTATE_PKG_C6_RES),
	.quirks			= SLM_PKG_C6_USE_C7_MSR,
};

#define X86_CSTATES_MODEL(model, states)				\
	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) }

static const struct x86_cpu_id intel_cstates_match[] __initconst = {
	X86_CSTATES_MODEL(30, nhm_cstates),    /* 45nm Nehalem              */
	X86_CSTATES_MODEL(26, nhm_cstates),    /* 45nm Nehalem-EP           */
	X86_CSTATES_MODEL(46, nhm_cstates),    /* 45nm Nehalem-EX           */

	X86_CSTATES_MODEL(37, nhm_cstates),    /* 32nm Westmere             */
	X86_CSTATES_MODEL(44, nhm_cstates),    /* 32nm Westmere-EP          */
	X86_CSTATES_MODEL(47, nhm_cstates),    /* 32nm Westmere-EX          */

	X86_CSTATES_MODEL(42, snb_cstates),    /* 32nm SandyBridge          */
	X86_CSTATES_MODEL(45, snb_cstates),    /* 32nm SandyBridge-E/EN/EP  */

	X86_CSTATES_MODEL(58, snb_cstates),    /* 22nm IvyBridge            */
	X86_CSTATES_MODEL(62, snb_cstates),    /* 22nm IvyBridge-EP/EX      */

	X86_CSTATES_MODEL(60, snb_cstates),    /* 22nm Haswell Core         */
	X86_CSTATES_MODEL(63, snb_cstates),    /* 22nm Haswell Server       */
	X86_CSTATES_MODEL(70, snb_cstates),    /* 22nm Haswell + GT3e       */

	X86_CSTATES_MODEL(69, hswult_cstates), /* 22nm Haswell ULT          */

	X86_CSTATES_MODEL(55, slm_cstates),    /* 22nm Atom Silvermont      */
	X86_CSTATES_MODEL(77, slm_cstates),    /* 22nm Atom Avoton/Rangely  */
	X86_CSTATES_MODEL(76, slm_cstates),    /* 22nm Atom Airmont         */

	X86_CSTATES_MODEL(61, snb_cstates),    /* 14nm Broadwell Core-M     */
	X86_CSTATES_MODEL(86, snb_cstates),    /* 14nm Broadwell Xeon D     */
	X86_CSTATES_MODEL(71, snb_cstates),    /* 14nm Broadwell + GT3e     */
	X86_CSTATES_MODEL(79, snb_cstates),    /* 14nm Broadwell Server     */

	X86_CSTATES_MODEL(78, snb_cstates),    /* 14nm Skylake Mobile       */
	X86_CSTATES_MODEL(94, snb_cstates),    /* 14nm Skylake Desktop      */
	{ },
};
MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);

/*
 * Probe the cstate events and insert the available one into sysfs attrs
 * Return false if there are no available events.
 */
static bool __init cstate_probe_msr(const unsigned long evmsk, int max,
                                   struct perf_cstate_msr *msr,
                                   struct attribute **attrs)
{
	bool found = false;
	unsigned int bit;
	u64 val;

	for (bit = 0; bit < max; bit++) {
		if (test_bit(bit, &evmsk) && !rdmsrl_safe(msr[bit].msr, &val)) {
			*attrs++ = &msr[bit].attr->attr.attr;
			found = true;
		} else {
			msr[bit].attr = NULL;
		}
	}
	*attrs = NULL;

	return found;
}

static int __init cstate_probe(const struct cstate_model *cm)
{
	/* SLM has different MSR for PKG C6 */
	if (cm->quirks & SLM_PKG_C6_USE_C7_MSR)
		pkg_msr[PERF_CSTATE_PKG_C6_RES].msr = MSR_PKG_C7_RESIDENCY;

	has_cstate_core = cstate_probe_msr(cm->core_events,
					   PERF_CSTATE_CORE_EVENT_MAX,
					   core_msr, core_events_attrs);

	has_cstate_pkg = cstate_probe_msr(cm->pkg_events,
					  PERF_CSTATE_PKG_EVENT_MAX,
					  pkg_msr, pkg_events_attrs);

	return (has_cstate_core || has_cstate_pkg) ? 0 : -ENODEV;
}

static inline void cstate_cleanup(void)
{
	if (has_cstate_core)
		perf_pmu_unregister(&cstate_core_pmu);

	if (has_cstate_pkg)
		perf_pmu_unregister(&cstate_pkg_pmu);
}

static int __init cstate_init(void)
{
	int cpu, err;

	cpu_notifier_register_begin();
	for_each_online_cpu(cpu)
		cstate_cpu_init(cpu);

	if (has_cstate_core) {
		err = perf_pmu_register(&cstate_core_pmu, cstate_core_pmu.name, -1);
		if (err) {
			has_cstate_core = false;
			pr_info("Failed to register cstate core pmu\n");
			goto out;
		}
	}

	if (has_cstate_pkg) {
		err = perf_pmu_register(&cstate_pkg_pmu, cstate_pkg_pmu.name, -1);
		if (err) {
			has_cstate_pkg = false;
			pr_info("Failed to register cstate pkg pmu\n");
			cstate_cleanup();
			goto out;
		}
	}
	__register_cpu_notifier(&cstate_cpu_nb);
out:
	cpu_notifier_register_done();
	return err;
}

static int __init cstate_pmu_init(void)
{
	const struct x86_cpu_id *id;
	int err;

	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
		return -ENODEV;

	id = x86_match_cpu(intel_cstates_match);
	if (!id)
		return -ENODEV;

	err = cstate_probe((const struct cstate_model *) id->driver_data);
	if (err)
		return err;

	return cstate_init();
}
module_init(cstate_pmu_init);

static void __exit cstate_pmu_exit(void)
{
	cpu_notifier_register_begin();
	__unregister_cpu_notifier(&cstate_cpu_nb);
	cstate_cleanup();
	cpu_notifier_register_done();
}
module_exit(cstate_pmu_exit);