summaryrefslogtreecommitdiff
path: root/arch/mips/kernel/perf_event.c
blob: 2b7f3f703b83cbeb86f48926517f1e0887f07496 (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
/*
 * Linux performance counter support for MIPS.
 *
 * Copyright (C) 2010 MIPS Technologies, Inc.
 * Author: Deng-Cheng Zhu
 *
 * This code is based on the implementation for ARM, which is in turn
 * based on the sparc64 perf event code and the x86 code. Performance
 * counter access is based on the MIPS Oprofile code. And the callchain
 * support references the code of MIPS stacktrace.c.
 *
 * 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/cpumask.h>
#include <linux/interrupt.h>
#include <linux/smp.h>
#include <linux/kernel.h>
#include <linux/perf_event.h>
#include <linux/uaccess.h>

#include <asm/irq.h>
#include <asm/irq_regs.h>
#include <asm/stacktrace.h>
#include <asm/time.h> /* For perf_irq */

/* These are for 32bit counters. For 64bit ones, define them accordingly. */
#define MAX_PERIOD	((1ULL << 32) - 1)
#define VALID_COUNT	0x7fffffff
#define TOTAL_BITS	32
#define HIGHEST_BIT	31

#define MIPS_MAX_HWEVENTS 4

struct cpu_hw_events {
	/* Array of events on this cpu. */
	struct perf_event	*events[MIPS_MAX_HWEVENTS];

	/*
	 * Set the bit (indexed by the counter number) when the counter
	 * is used for an event.
	 */
	unsigned long		used_mask[BITS_TO_LONGS(MIPS_MAX_HWEVENTS)];

	/*
	 * The borrowed MSB for the performance counter. A MIPS performance
	 * counter uses its bit 31 (for 32bit counters) or bit 63 (for 64bit
	 * counters) as a factor of determining whether a counter overflow
	 * should be signaled. So here we use a separate MSB for each
	 * counter to make things easy.
	 */
	unsigned long		msbs[BITS_TO_LONGS(MIPS_MAX_HWEVENTS)];

	/*
	 * Software copy of the control register for each performance counter.
	 * MIPS CPUs vary in performance counters. They use this differently,
	 * and even may not use it.
	 */
	unsigned int		saved_ctrl[MIPS_MAX_HWEVENTS];
};
DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
	.saved_ctrl = {0},
};

/* The description of MIPS performance events. */
struct mips_perf_event {
	unsigned int event_id;
	/*
	 * MIPS performance counters are indexed starting from 0.
	 * CNTR_EVEN indicates the indexes of the counters to be used are
	 * even numbers.
	 */
	unsigned int cntr_mask;
	#define CNTR_EVEN	0x55555555
	#define CNTR_ODD	0xaaaaaaaa
#ifdef CONFIG_MIPS_MT_SMP
	enum {
		T  = 0,
		V  = 1,
		P  = 2,
	} range;
#else
	#define T
	#define V
	#define P
#endif
};

static struct mips_perf_event raw_event;
static DEFINE_MUTEX(raw_event_mutex);

#define UNSUPPORTED_PERF_EVENT_ID 0xffffffff
#define C(x) PERF_COUNT_HW_CACHE_##x

struct mips_pmu {
	const char	*name;
	int		irq;
	irqreturn_t	(*handle_irq)(int irq, void *dev);
	int		(*handle_shared_irq)(void);
	void		(*start)(void);
	void		(*stop)(void);
	int		(*alloc_counter)(struct cpu_hw_events *cpuc,
					struct hw_perf_event *hwc);
	u64		(*read_counter)(unsigned int idx);
	void		(*write_counter)(unsigned int idx, u64 val);
	void		(*enable_event)(struct hw_perf_event *evt, int idx);
	void		(*disable_event)(int idx);
	const struct mips_perf_event *(*map_raw_event)(u64 config);
	const struct mips_perf_event (*general_event_map)[PERF_COUNT_HW_MAX];
	const struct mips_perf_event (*cache_event_map)
				[PERF_COUNT_HW_CACHE_MAX]
				[PERF_COUNT_HW_CACHE_OP_MAX]
				[PERF_COUNT_HW_CACHE_RESULT_MAX];
	unsigned int	num_counters;
};

static const struct mips_pmu *mipspmu;

static int
mipspmu_event_set_period(struct perf_event *event,
			struct hw_perf_event *hwc,
			int idx)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	s64 left = local64_read(&hwc->period_left);
	s64 period = hwc->sample_period;
	int ret = 0;
	u64 uleft;
	unsigned long flags;

	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)MAX_PERIOD)
		left = MAX_PERIOD;

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

	local_irq_save(flags);
	uleft = (u64)(-left) & MAX_PERIOD;
	uleft > VALID_COUNT ?
		set_bit(idx, cpuc->msbs) : clear_bit(idx, cpuc->msbs);
	mipspmu->write_counter(idx, (u64)(-left) & VALID_COUNT);
	local_irq_restore(flags);

	perf_event_update_userpage(event);

	return ret;
}

static int mipspmu_enable(struct perf_event *event)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	struct hw_perf_event *hwc = &event->hw;
	int idx;
	int err = 0;

	/* To look for a free counter for this event. */
	idx = mipspmu->alloc_counter(cpuc, hwc);
	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;
	mipspmu->disable_event(idx);
	cpuc->events[idx] = event;

	/* Set the period for the event. */
	mipspmu_event_set_period(event, hwc, idx);

	/* Enable the event. */
	mipspmu->enable_event(hwc, idx);

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

out:
	return err;
}

static void mipspmu_event_update(struct perf_event *event,
			struct hw_perf_event *hwc,
			int idx)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	unsigned long flags;
	int shift = 64 - TOTAL_BITS;
	s64 prev_raw_count, new_raw_count;
	s64 delta;

again:
	prev_raw_count = local64_read(&hwc->prev_count);
	local_irq_save(flags);
	/* Make the counter value be a "real" one. */
	new_raw_count = mipspmu->read_counter(idx);
	if (new_raw_count & (test_bit(idx, cpuc->msbs) << HIGHEST_BIT)) {
		new_raw_count &= VALID_COUNT;
		clear_bit(idx, cpuc->msbs);
	} else
		new_raw_count |= (test_bit(idx, cpuc->msbs) << HIGHEST_BIT);
	local_irq_restore(flags);

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

	delta = (new_raw_count << shift) - (prev_raw_count << shift);
	delta >>= shift;

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

	return;
}

static void mipspmu_disable(struct perf_event *event)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	struct hw_perf_event *hwc = &event->hw;
	int idx = hwc->idx;


	WARN_ON(idx < 0 || idx >= mipspmu->num_counters);

	/* We are working on a local event. */
	mipspmu->disable_event(idx);

	barrier();

	mipspmu_event_update(event, hwc, idx);
	cpuc->events[idx] = NULL;
	clear_bit(idx, cpuc->used_mask);

	perf_event_update_userpage(event);
}

static void mipspmu_unthrottle(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;

	mipspmu->enable_event(hwc, hwc->idx);
}

static void mipspmu_read(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;

	/* Don't read disabled counters! */
	if (hwc->idx < 0)
		return;

	mipspmu_event_update(event, hwc, hwc->idx);
}

static struct pmu pmu = {
	.enable		= mipspmu_enable,
	.disable	= mipspmu_disable,
	.unthrottle	= mipspmu_unthrottle,
	.read		= mipspmu_read,
};

static atomic_t active_events = ATOMIC_INIT(0);
static DEFINE_MUTEX(pmu_reserve_mutex);
static int (*save_perf_irq)(void);

static int mipspmu_get_irq(void)
{
	int err;

	if (mipspmu->irq >= 0) {
		/* Request my own irq handler. */
		err = request_irq(mipspmu->irq, mipspmu->handle_irq,
			IRQF_DISABLED | IRQF_NOBALANCING,
			"mips_perf_pmu", NULL);
		if (err) {
			pr_warning("Unable to request IRQ%d for MIPS "
			   "performance counters!\n", mipspmu->irq);
		}
	} else if (cp0_perfcount_irq < 0) {
		/*
		 * We are sharing the irq number with the timer interrupt.
		 */
		save_perf_irq = perf_irq;
		perf_irq = mipspmu->handle_shared_irq;
		err = 0;
	} else {
		pr_warning("The platform hasn't properly defined its "
			"interrupt controller.\n");
		err = -ENOENT;
	}

	return err;
}

static void mipspmu_free_irq(void)
{
	if (mipspmu->irq >= 0)
		free_irq(mipspmu->irq, NULL);
	else if (cp0_perfcount_irq < 0)
		perf_irq = save_perf_irq;
}

static inline unsigned int
mipspmu_perf_event_encode(const struct mips_perf_event *pev)
{
/*
 * Top 8 bits for range, next 16 bits for cntr_mask, lowest 8 bits for
 * event_id.
 */
#ifdef CONFIG_MIPS_MT_SMP
	return ((unsigned int)pev->range << 24) |
		(pev->cntr_mask & 0xffff00) |
		(pev->event_id & 0xff);
#else
	return (pev->cntr_mask & 0xffff00) |
		(pev->event_id & 0xff);
#endif
}

static const struct mips_perf_event *
mipspmu_map_general_event(int idx)
{
	const struct mips_perf_event *pev;

	pev = ((*mipspmu->general_event_map)[idx].event_id ==
		UNSUPPORTED_PERF_EVENT_ID ? ERR_PTR(-EOPNOTSUPP) :
		&(*mipspmu->general_event_map)[idx]);

	return pev;
}

static const struct mips_perf_event *
mipspmu_map_cache_event(u64 config)
{
	unsigned int cache_type, cache_op, cache_result;
	const struct mips_perf_event *pev;

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

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

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

	pev = &((*mipspmu->cache_event_map)
					[cache_type]
					[cache_op]
					[cache_result]);

	if (pev->event_id == UNSUPPORTED_PERF_EVENT_ID)
		return ERR_PTR(-EOPNOTSUPP);

	return pev;

}

static int validate_event(struct cpu_hw_events *cpuc,
	       struct perf_event *event)
{
	struct hw_perf_event fake_hwc = event->hw;

	if (event->pmu && event->pmu != &pmu)
		return 0;

	return mipspmu->alloc_counter(cpuc, &fake_hwc) >= 0;
}

static int validate_group(struct perf_event *event)
{
	struct perf_event *sibling, *leader = event->group_leader;
	struct cpu_hw_events fake_cpuc;

	memset(&fake_cpuc, 0, sizeof(fake_cpuc));

	if (!validate_event(&fake_cpuc, leader))
		return -ENOSPC;

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

	if (!validate_event(&fake_cpuc, event))
		return -ENOSPC;

	return 0;
}

/*
 * mipsxx/rm9000/loongson2 have different performance counters, they have
 * specific low-level init routines.
 */
static void reset_counters(void *arg);
static int __hw_perf_event_init(struct perf_event *event);

static void hw_perf_event_destroy(struct perf_event *event)
{
	if (atomic_dec_and_mutex_lock(&active_events,
				&pmu_reserve_mutex)) {
		/*
		 * We must not call the destroy function with interrupts
		 * disabled.
		 */
		on_each_cpu(reset_counters,
			(void *)(long)mipspmu->num_counters, 1);
		mipspmu_free_irq();
		mutex_unlock(&pmu_reserve_mutex);
	}
}

const struct pmu *hw_perf_event_init(struct perf_event *event)
{
	int err = 0;

	if (!mipspmu || event->cpu >= nr_cpumask_bits ||
		(event->cpu >= 0 && !cpu_online(event->cpu)))
		return ERR_PTR(-ENODEV);

	if (!atomic_inc_not_zero(&active_events)) {
		if (atomic_read(&active_events) > MIPS_MAX_HWEVENTS) {
			atomic_dec(&active_events);
			return ERR_PTR(-ENOSPC);
		}

		mutex_lock(&pmu_reserve_mutex);
		if (atomic_read(&active_events) == 0)
			err = mipspmu_get_irq();

		if (!err)
			atomic_inc(&active_events);
		mutex_unlock(&pmu_reserve_mutex);
	}

	if (err)
		return ERR_PTR(err);

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

	return err ? ERR_PTR(err) : &pmu;
}

void hw_perf_enable(void)
{
	if (mipspmu)
		mipspmu->start();
}

void hw_perf_disable(void)
{
	if (mipspmu)
		mipspmu->stop();
}

/* This is needed by specific irq handlers in perf_event_*.c */
static void
handle_associated_event(struct cpu_hw_events *cpuc,
	int idx, struct perf_sample_data *data, struct pt_regs *regs)
{
	struct perf_event *event = cpuc->events[idx];
	struct hw_perf_event *hwc = &event->hw;

	mipspmu_event_update(event, hwc, idx);
	data->period = event->hw.last_period;
	if (!mipspmu_event_set_period(event, hwc, idx))
		return;

	if (perf_event_overflow(event, 0, data, regs))
		mipspmu->disable_event(idx);
}

#include "perf_event_mipsxx.c"

/* Callchain handling code. */
static inline void
callchain_store(struct perf_callchain_entry *entry,
		u64 ip)
{
	if (entry->nr < PERF_MAX_STACK_DEPTH)
		entry->ip[entry->nr++] = ip;
}

/*
 * Leave userspace callchain empty for now. When we find a way to trace
 * the user stack callchains, we add here.
 */
static void
perf_callchain_user(struct pt_regs *regs,
		    struct perf_callchain_entry *entry)
{
}

static void save_raw_perf_callchain(struct perf_callchain_entry *entry,
	unsigned long reg29)
{
	unsigned long *sp = (unsigned long *)reg29;
	unsigned long addr;

	while (!kstack_end(sp)) {
		addr = *sp++;
		if (__kernel_text_address(addr)) {
			callchain_store(entry, addr);
			if (entry->nr >= PERF_MAX_STACK_DEPTH)
				break;
		}
	}
}

static void
perf_callchain_kernel(struct pt_regs *regs,
		      struct perf_callchain_entry *entry)
{
	unsigned long sp = regs->regs[29];
#ifdef CONFIG_KALLSYMS
	unsigned long ra = regs->regs[31];
	unsigned long pc = regs->cp0_epc;

	callchain_store(entry, PERF_CONTEXT_KERNEL);
	if (raw_show_trace || !__kernel_text_address(pc)) {
		unsigned long stack_page =
			(unsigned long)task_stack_page(current);
		if (stack_page && sp >= stack_page &&
		    sp <= stack_page + THREAD_SIZE - 32)
			save_raw_perf_callchain(entry, sp);
		return;
	}
	do {
		callchain_store(entry, pc);
		if (entry->nr >= PERF_MAX_STACK_DEPTH)
			break;
		pc = unwind_stack(current, &sp, pc, &ra);
	} while (pc);
#else
	callchain_store(entry, PERF_CONTEXT_KERNEL);
	save_raw_perf_callchain(entry, sp);
#endif
}

static void
perf_do_callchain(struct pt_regs *regs,
		  struct perf_callchain_entry *entry)
{
	int is_user;

	if (!regs)
		return;

	is_user = user_mode(regs);

	if (!current || !current->pid)
		return;

	if (is_user && current->state != TASK_RUNNING)
		return;

	if (!is_user) {
		perf_callchain_kernel(regs, entry);
		if (current->mm)
			regs = task_pt_regs(current);
		else
			regs = NULL;
	}
	if (regs)
		perf_callchain_user(regs, entry);
}

static DEFINE_PER_CPU(struct perf_callchain_entry, pmc_irq_entry);

struct perf_callchain_entry *
perf_callchain(struct pt_regs *regs)
{
	struct perf_callchain_entry *entry = &__get_cpu_var(pmc_irq_entry);

	entry->nr = 0;
	perf_do_callchain(regs, entry);
	return entry;
}