summaryrefslogtreecommitdiffstats
path: root/arch/arm/kernel/perf_event.c
blob: a6bc431cde701037ca6146d6931a56aa96838cb1 (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
#undef DEBUG

/*
 * ARM performance counter support.
 *
 * Copyright (C) 2009 picoChip Designs, Ltd., Jamie Iles
 * Copyright (C) 2010 ARM Ltd., Will Deacon <will.deacon@arm.com>
 *
 * This code is based on the sparc64 perf event code, which is in turn based
 * on the x86 code. Callchain code is based on the ARM OProfile backtrace
 * code.
 */
#define pr_fmt(fmt) "hw perfevents: " fmt

#include <linux/kernel.h>
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
#include <linux/uaccess.h>
#include <linux/irq.h>
#include <linux/irqdesc.h>

#include <asm/irq_regs.h>
#include <asm/pmu.h>
#include <asm/stacktrace.h>

static int
armpmu_map_cache_event(const unsigned (*cache_map)
				      [PERF_COUNT_HW_CACHE_MAX]
				      [PERF_COUNT_HW_CACHE_OP_MAX]
				      [PERF_COUNT_HW_CACHE_RESULT_MAX],
		       u64 config)
{
	unsigned int cache_type, cache_op, cache_result, ret;

	cache_type = (config >>  0) & 0xff;
	if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
		return -EINVAL;

	cache_op = (config >>  8) & 0xff;
	if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
		return -EINVAL;

	cache_result = (config >> 16) & 0xff;
	if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
		return -EINVAL;

	ret = (int)(*cache_map)[cache_type][cache_op][cache_result];

	if (ret == CACHE_OP_UNSUPPORTED)
		return -ENOENT;

	return ret;
}

static int
armpmu_map_hw_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config)
{
	int mapping;

	if (config >= PERF_COUNT_HW_MAX)
		return -EINVAL;

	mapping = (*event_map)[config];
	return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping;
}

static int
armpmu_map_raw_event(u32 raw_event_mask, u64 config)
{
	return (int)(config & raw_event_mask);
}

int
armpmu_map_event(struct perf_event *event,
		 const unsigned (*event_map)[PERF_COUNT_HW_MAX],
		 const unsigned (*cache_map)
				[PERF_COUNT_HW_CACHE_MAX]
				[PERF_COUNT_HW_CACHE_OP_MAX]
				[PERF_COUNT_HW_CACHE_RESULT_MAX],
		 u32 raw_event_mask)
{
	u64 config = event->attr.config;

	switch (event->attr.type) {
	case PERF_TYPE_HARDWARE:
		return armpmu_map_hw_event(event_map, config);
	case PERF_TYPE_HW_CACHE:
		return armpmu_map_cache_event(cache_map, config);
	case PERF_TYPE_RAW:
		return armpmu_map_raw_event(raw_event_mask, config);
	}

	return -ENOENT;
}

int armpmu_event_set_period(struct perf_event *event)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
	struct hw_perf_event *hwc = &event->hw;
	s64 left = local64_read(&hwc->period_left);
	s64 period = hwc->sample_period;
	int ret = 0;

	if (unlikely(left <= -period)) {
		left = period;
		local64_set(&hwc->period_left, left);
		hwc->last_period = period;
		ret = 1;
	}

	if (unlikely(left <= 0)) {
		left += period;
		local64_set(&hwc->period_left, left);
		hwc->last_period = period;
		ret = 1;
	}

	if (left > (s64)armpmu->max_period)
		left = armpmu->max_period;

	local64_set(&hwc->prev_count, (u64)-left);

	armpmu->write_counter(event, (u64)(-left) & 0xffffffff);

	perf_event_update_userpage(event);

	return ret;
}

u64 armpmu_event_update(struct perf_event *event)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
	struct hw_perf_event *hwc = &event->hw;
	u64 delta, prev_raw_count, new_raw_count;

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

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

	delta = (new_raw_count - prev_raw_count) & armpmu->max_period;

	local64_add(delta, &event->count);
	local64_sub(delta, &hwc->period_left);

	return new_raw_count;
}

static void
armpmu_read(struct perf_event *event)
{
	armpmu_event_update(event);
}

static void
armpmu_stop(struct perf_event *event, int flags)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
	struct hw_perf_event *hwc = &event->hw;

	/*
	 * ARM pmu always has to update the counter, so ignore
	 * PERF_EF_UPDATE, see comments in armpmu_start().
	 */
	if (!(hwc->state & PERF_HES_STOPPED)) {
		armpmu->disable(event);
		armpmu_event_update(event);
		hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
	}
}

static void armpmu_start(struct perf_event *event, int flags)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
	struct hw_perf_event *hwc = &event->hw;

	/*
	 * ARM pmu always has to reprogram the period, so ignore
	 * PERF_EF_RELOAD, see the comment below.
	 */
	if (flags & PERF_EF_RELOAD)
		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));

	hwc->state = 0;
	/*
	 * Set the period again. Some counters can't be stopped, so when we
	 * were stopped we simply disabled the IRQ source and the counter
	 * may have been left counting. If we don't do this step then we may
	 * get an interrupt too soon or *way* too late if the overflow has
	 * happened since disabling.
	 */
	armpmu_event_set_period(event);
	armpmu->enable(event);
}

static void
armpmu_del(struct perf_event *event, int flags)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
	struct pmu_hw_events *hw_events = armpmu->get_hw_events();
	struct hw_perf_event *hwc = &event->hw;
	int idx = hwc->idx;

	armpmu_stop(event, PERF_EF_UPDATE);
	hw_events->events[idx] = NULL;
	clear_bit(idx, hw_events->used_mask);
	if (armpmu->clear_event_idx)
		armpmu->clear_event_idx(hw_events, event);

	perf_event_update_userpage(event);
}

static int
armpmu_add(struct perf_event *event, int flags)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
	struct pmu_hw_events *hw_events = armpmu->get_hw_events();
	struct hw_perf_event *hwc = &event->hw;
	int idx;
	int err = 0;

	perf_pmu_disable(event->pmu);

	/* If we don't have a space for the counter then finish early. */
	idx = armpmu->get_event_idx(hw_events, event);
	if (idx < 0) {
		err = idx;
		goto out;
	}

	/*
	 * If there is an event in the counter we are going to use then make
	 * sure it is disabled.
	 */
	event->hw.idx = idx;
	armpmu->disable(event);
	hw_events->events[idx] = event;

	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
	if (flags & PERF_EF_START)
		armpmu_start(event, PERF_EF_RELOAD);

	/* Propagate our changes to the userspace mapping. */
	perf_event_update_userpage(event);

out:
	perf_pmu_enable(event->pmu);
	return err;
}

static int
validate_event(struct pmu_hw_events *hw_events,
	       struct perf_event *event)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);

	if (is_software_event(event))
		return 1;

	if (event->state < PERF_EVENT_STATE_OFF)
		return 1;

	if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
		return 1;

	return armpmu->get_event_idx(hw_events, event) >= 0;
}

static int
validate_group(struct perf_event *event)
{
	struct perf_event *sibling, *leader = event->group_leader;
	struct pmu_hw_events fake_pmu;
	DECLARE_BITMAP(fake_used_mask, ARMPMU_MAX_HWEVENTS);

	/*
	 * Initialise the fake PMU. We only need to populate the
	 * used_mask for the purposes of validation.
	 */
	memset(fake_used_mask, 0, sizeof(fake_used_mask));
	fake_pmu.used_mask = fake_used_mask;

	if (!validate_event(&fake_pmu, leader))
		return -EINVAL;

	list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
		if (!validate_event(&fake_pmu, sibling))
			return -EINVAL;
	}

	if (!validate_event(&fake_pmu, event))
		return -EINVAL;

	return 0;
}

static irqreturn_t armpmu_dispatch_irq(int irq, void *dev)
{
	struct arm_pmu *armpmu;
	struct platform_device *plat_device;
	struct arm_pmu_platdata *plat;
	int ret;
	u64 start_clock, finish_clock;

	if (irq_is_percpu(irq))
		dev = *(void **)dev;
	armpmu = dev;
	plat_device = armpmu->plat_device;
	plat = dev_get_platdata(&plat_device->dev);

	start_clock = sched_clock();
	if (plat && plat->handle_irq)
		ret = plat->handle_irq(irq, dev, armpmu->handle_irq);
	else
		ret = armpmu->handle_irq(irq, dev);
	finish_clock = sched_clock();

	perf_sample_event_took(finish_clock - start_clock);
	return ret;
}

static void
armpmu_release_hardware(struct arm_pmu *armpmu)
{
	armpmu->free_irq(armpmu);
	pm_runtime_put_sync(&armpmu->plat_device->dev);
}

static int
armpmu_reserve_hardware(struct arm_pmu *armpmu)
{
	int err;
	struct platform_device *pmu_device = armpmu->plat_device;

	if (!pmu_device)
		return -ENODEV;

	pm_runtime_get_sync(&pmu_device->dev);
	err = armpmu->request_irq(armpmu, armpmu_dispatch_irq);
	if (err) {
		armpmu_release_hardware(armpmu);
		return err;
	}

	return 0;
}

static void
hw_perf_event_destroy(struct perf_event *event)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
	atomic_t *active_events	 = &armpmu->active_events;
	struct mutex *pmu_reserve_mutex = &armpmu->reserve_mutex;

	if (atomic_dec_and_mutex_lock(active_events, pmu_reserve_mutex)) {
		armpmu_release_hardware(armpmu);
		mutex_unlock(pmu_reserve_mutex);
	}
}

static int
event_requires_mode_exclusion(struct perf_event_attr *attr)
{
	return attr->exclude_idle || attr->exclude_user ||
	       attr->exclude_kernel || attr->exclude_hv;
}

static int
__hw_perf_event_init(struct perf_event *event)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
	struct hw_perf_event *hwc = &event->hw;
	int mapping;

	mapping = armpmu->map_event(event);

	if (mapping < 0) {
		pr_debug("event %x:%llx not supported\n", event->attr.type,
			 event->attr.config);
		return mapping;
	}

	/*
	 * We don't assign an index until we actually place the event onto
	 * hardware. Use -1 to signify that we haven't decided where to put it
	 * yet. For SMP systems, each core has it's own PMU so we can't do any
	 * clever allocation or constraints checking at this point.
	 */
	hwc->idx		= -1;
	hwc->config_base	= 0;
	hwc->config		= 0;
	hwc->event_base		= 0;

	/*
	 * Check whether we need to exclude the counter from certain modes.
	 */
	if ((!armpmu->set_event_filter ||
	     armpmu->set_event_filter(hwc, &event->attr)) &&
	     event_requires_mode_exclusion(&event->attr)) {
		pr_debug("ARM performance counters do not support "
			 "mode exclusion\n");
		return -EOPNOTSUPP;
	}

	/*
	 * Store the event encoding into the config_base field.
	 */
	hwc->config_base	    |= (unsigned long)mapping;

	if (!hwc->sample_period) {
		/*
		 * For non-sampling runs, limit the sample_period to half
		 * of the counter width. That way, the new counter value
		 * is far less likely to overtake the previous one unless
		 * you have some serious IRQ latency issues.
		 */
		hwc->sample_period  = armpmu->max_period >> 1;
		hwc->last_period    = hwc->sample_period;
		local64_set(&hwc->period_left, hwc->sample_period);
	}

	if (event->group_leader != event) {
		if (validate_group(event) != 0)
			return -EINVAL;
	}

	return 0;
}

static int armpmu_event_init(struct perf_event *event)
{
	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
	int err = 0;
	atomic_t *active_events = &armpmu->active_events;

	/* does not support taken branch sampling */
	if (has_branch_stack(event))
		return -EOPNOTSUPP;

	if (armpmu->map_event(event) == -ENOENT)
		return -ENOENT;

	event->destroy = hw_perf_event_destroy;

	if (!atomic_inc_not_zero(active_events)) {
		mutex_lock(&armpmu->reserve_mutex);
		if (atomic_read(active_events) == 0)
			err = armpmu_reserve_hardware(armpmu);

		if (!err)
			atomic_inc(active_events);
		mutex_unlock(&armpmu->reserve_mutex);
	}

	if (err)
		return err;

	err = __hw_perf_event_init(event);
	if (err)
		hw_perf_event_destroy(event);

	return err;
}

static void armpmu_enable(struct pmu *pmu)
{
	struct arm_pmu *armpmu = to_arm_pmu(pmu);
	struct pmu_hw_events *hw_events = armpmu->get_hw_events();
	int enabled = bitmap_weight(hw_events->used_mask, armpmu->num_events);

	if (enabled)
		armpmu->start(armpmu);
}

static void armpmu_disable(struct pmu *pmu)
{
	struct arm_pmu *armpmu = to_arm_pmu(pmu);
	armpmu->stop(armpmu);
}

#ifdef CONFIG_PM_RUNTIME
static int armpmu_runtime_resume(struct device *dev)
{
	struct arm_pmu_platdata *plat = dev_get_platdata(dev);

	if (plat && plat->runtime_resume)
		return plat->runtime_resume(dev);

	return 0;
}

static int armpmu_runtime_suspend(struct device *dev)
{
	struct arm_pmu_platdata *plat = dev_get_platdata(dev);

	if (plat && plat->runtime_suspend)
		return plat->runtime_suspend(dev);

	return 0;
}
#endif

const struct dev_pm_ops armpmu_dev_pm_ops = {
	SET_RUNTIME_PM_OPS(armpmu_runtime_suspend, armpmu_runtime_resume, NULL)
};

static void armpmu_init(struct arm_pmu *armpmu)
{
	atomic_set(&armpmu->active_events, 0);
	mutex_init(&armpmu->reserve_mutex);

	armpmu->pmu = (struct pmu) {
		.pmu_enable	= armpmu_enable,
		.pmu_disable	= armpmu_disable,
		.event_init	= armpmu_event_init,
		.add		= armpmu_add,
		.del		= armpmu_del,
		.start		= armpmu_start,
		.stop		= armpmu_stop,
		.read		= armpmu_read,
	};
}

int armpmu_register(struct arm_pmu *armpmu, int type)
{
	armpmu_init(armpmu);
	pm_runtime_enable(&armpmu->plat_device->dev);
	pr_info("enabled with %s PMU driver, %d counters available\n",
			armpmu->name, armpmu->num_events);
	return perf_pmu_register(&armpmu->pmu, armpmu->name, type);
}

/*
 * Callchain handling code.
 */

/*
 * The registers we're interested in are at the end of the variable
 * length saved register structure. The fp points at the end of this
 * structure so the address of this struct is:
 * (struct frame_tail *)(xxx->fp)-1
 *
 * This code has been adapted from the ARM OProfile support.
 */
struct frame_tail {
	struct frame_tail __user *fp;
	unsigned long sp;
	unsigned long lr;
} __attribute__((packed));

/*
 * Get the return address for a single stackframe and return a pointer to the
 * next frame tail.
 */
static struct frame_tail __user *
user_backtrace(struct frame_tail __user *tail,
	       struct perf_callchain_entry *entry)
{
	struct frame_tail buftail;

	/* Also check accessibility of one struct frame_tail beyond */
	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
		return NULL;
	if (__copy_from_user_inatomic(&buftail, tail, sizeof(buftail)))
		return NULL;

	perf_callchain_store(entry, buftail.lr);

	/*
	 * Frame pointers should strictly progress back up the stack
	 * (towards higher addresses).
	 */
	if (tail + 1 >= buftail.fp)
		return NULL;

	return buftail.fp - 1;
}

void
perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
{
	struct frame_tail __user *tail;

	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
		/* We don't support guest os callchain now */
		return;
	}

	perf_callchain_store(entry, regs->ARM_pc);
	tail = (struct frame_tail __user *)regs->ARM_fp - 1;

	while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
	       tail && !((unsigned long)tail & 0x3))
		tail = user_backtrace(tail, entry);
}

/*
 * Gets called by walk_stackframe() for every stackframe. This will be called
 * whist unwinding the stackframe and is like a subroutine return so we use
 * the PC.
 */
static int
callchain_trace(struct stackframe *fr,
		void *data)
{
	struct perf_callchain_entry *entry = data;
	perf_callchain_store(entry, fr->pc);
	return 0;
}

void
perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
{
	struct stackframe fr;

	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
		/* We don't support guest os callchain now */
		return;
	}

	fr.fp = regs->ARM_fp;
	fr.sp = regs->ARM_sp;
	fr.lr = regs->ARM_lr;
	fr.pc = regs->ARM_pc;
	walk_stackframe(&fr, callchain_trace, entry);
}

unsigned long perf_instruction_pointer(struct pt_regs *regs)
{
	if (perf_guest_cbs && perf_guest_cbs->is_in_guest())
		return perf_guest_cbs->get_guest_ip();

	return instruction_pointer(regs);
}

unsigned long perf_misc_flags(struct pt_regs *regs)
{
	int misc = 0;

	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
		if (perf_guest_cbs->is_user_mode())
			misc |= PERF_RECORD_MISC_GUEST_USER;
		else
			misc |= PERF_RECORD_MISC_GUEST_KERNEL;
	} else {
		if (user_mode(regs))
			misc |= PERF_RECORD_MISC_USER;
		else
			misc |= PERF_RECORD_MISC_KERNEL;
	}

	return misc;
}
OpenPOWER on IntegriCloud