aboutsummaryrefslogtreecommitdiffstats
path: root/arch/arc/kernel/perf_event.c
blob: 8aec462d90fbe8f0aa88847272d02004a863f2db (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
/*
 * Linux performance counter support for ARC700 series
 *
 * Copyright (C) 2013-2015 Synopsys, Inc. (www.synopsys.com)
 *
 * This code is inspired by the perf support of various other architectures.
 *
 * 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/errno.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/of.h>
#include <linux/perf_event.h>
#include <linux/platform_device.h>
#include <asm/arcregs.h>
#include <asm/stacktrace.h>

struct arc_pmu {
	struct pmu	pmu;
	unsigned int	irq;
	int		n_counters;
	u64		max_period;
	int		ev_hw_idx[PERF_COUNT_ARC_HW_MAX];
};

struct arc_pmu_cpu {
	/*
	 * A 1 bit for an index indicates that the counter is being used for
	 * an event. A 0 means that the counter can be used.
	 */
	unsigned long	used_mask[BITS_TO_LONGS(ARC_PERF_MAX_COUNTERS)];

	/*
	 * The events that are active on the PMU for the given index.
	 */
	struct perf_event *act_counter[ARC_PERF_MAX_COUNTERS];
};

struct arc_callchain_trace {
	int depth;
	void *perf_stuff;
};

static int callchain_trace(unsigned int addr, void *data)
{
	struct arc_callchain_trace *ctrl = data;
	struct perf_callchain_entry_ctx *entry = ctrl->perf_stuff;
	perf_callchain_store(entry, addr);

	if (ctrl->depth++ < 3)
		return 0;

	return -1;
}

void
perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
	struct arc_callchain_trace ctrl = {
		.depth = 0,
		.perf_stuff = entry,
	};

	arc_unwind_core(NULL, regs, callchain_trace, &ctrl);
}

void
perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
{
	/*
	 * User stack can't be unwound trivially with kernel dwarf unwinder
	 * So for now just record the user PC
	 */
	perf_callchain_store(entry, instruction_pointer(regs));
}

static struct arc_pmu *arc_pmu;
static DEFINE_PER_CPU(struct arc_pmu_cpu, arc_pmu_cpu);

/* read counter #idx; note that counter# != event# on ARC! */
static uint64_t arc_pmu_read_counter(int idx)
{
	uint32_t tmp;
	uint64_t result;

	/*
	 * ARC supports making 'snapshots' of the counters, so we don't
	 * need to care about counters wrapping to 0 underneath our feet
	 */
	write_aux_reg(ARC_REG_PCT_INDEX, idx);
	tmp = read_aux_reg(ARC_REG_PCT_CONTROL);
	write_aux_reg(ARC_REG_PCT_CONTROL, tmp | ARC_REG_PCT_CONTROL_SN);
	result = (uint64_t) (read_aux_reg(ARC_REG_PCT_SNAPH)) << 32;
	result |= read_aux_reg(ARC_REG_PCT_SNAPL);

	return result;
}

static void arc_perf_event_update(struct perf_event *event,
				  struct hw_perf_event *hwc, int idx)
{
	uint64_t prev_raw_count = local64_read(&hwc->prev_count);
	uint64_t new_raw_count = arc_pmu_read_counter(idx);
	int64_t delta = new_raw_count - prev_raw_count;

	/*
	 * We aren't afraid of hwc->prev_count changing beneath our feet
	 * because there's no way for us to re-enter this function anytime.
	 */
	local64_set(&hwc->prev_count, new_raw_count);
	local64_add(delta, &event->count);
	local64_sub(delta, &hwc->period_left);
}

static void arc_pmu_read(struct perf_event *event)
{
	arc_perf_event_update(event, &event->hw, event->hw.idx);
}

static int arc_pmu_cache_event(u64 config)
{
	unsigned int cache_type, cache_op, cache_result;
	int ret;

	cache_type	= (config >>  0) & 0xff;
	cache_op	= (config >>  8) & 0xff;
	cache_result	= (config >> 16) & 0xff;
	if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
		return -EINVAL;
	if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
		return -EINVAL;
	if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
		return -EINVAL;

	ret = arc_pmu_cache_map[cache_type][cache_op][cache_result];

	if (ret == CACHE_OP_UNSUPPORTED)
		return -ENOENT;

	pr_debug("init cache event: type/op/result %d/%d/%d with h/w %d \'%s\'\n",
		 cache_type, cache_op, cache_result, ret,
		 arc_pmu_ev_hw_map[ret]);

	return ret;
}

/* initializes hw_perf_event structure if event is supported */
static int arc_pmu_event_init(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;
	int ret;

	if (!is_sampling_event(event)) {
		hwc->sample_period  = arc_pmu->max_period;
		hwc->last_period = hwc->sample_period;
		local64_set(&hwc->period_left, hwc->sample_period);
	}

	hwc->config = 0;

	if (is_isa_arcv2()) {
		/* "exclude user" means "count only kernel" */
		if (event->attr.exclude_user)
			hwc->config |= ARC_REG_PCT_CONFIG_KERN;

		/* "exclude kernel" means "count only user" */
		if (event->attr.exclude_kernel)
			hwc->config |= ARC_REG_PCT_CONFIG_USER;
	}

	switch (event->attr.type) {
	case PERF_TYPE_HARDWARE:
		if (event->attr.config >= PERF_COUNT_HW_MAX)
			return -ENOENT;
		if (arc_pmu->ev_hw_idx[event->attr.config] < 0)
			return -ENOENT;
		hwc->config |= arc_pmu->ev_hw_idx[event->attr.config];
		pr_debug("init event %d with h/w %08x \'%s\'\n",
			 (int)event->attr.config, (int)hwc->config,
			 arc_pmu_ev_hw_map[event->attr.config]);
		return 0;

	case PERF_TYPE_HW_CACHE:
		ret = arc_pmu_cache_event(event->attr.config);
		if (ret < 0)
			return ret;
		hwc->config |= arc_pmu->ev_hw_idx[ret];
		pr_debug("init cache event with h/w %08x \'%s\'\n",
			 (int)hwc->config, arc_pmu_ev_hw_map[ret]);
		return 0;
	default:
		return -ENOENT;
	}
}

/* starts all counters */
static void arc_pmu_enable(struct pmu *pmu)
{
	uint32_t tmp;
	tmp = read_aux_reg(ARC_REG_PCT_CONTROL);
	write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x1);
}

/* stops all counters */
static void arc_pmu_disable(struct pmu *pmu)
{
	uint32_t tmp;
	tmp = read_aux_reg(ARC_REG_PCT_CONTROL);
	write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x0);
}

static int arc_pmu_event_set_period(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;
	s64 left = local64_read(&hwc->period_left);
	s64 period = hwc->sample_period;
	int idx = hwc->idx;
	int overflow = 0;
	u64 value;

	if (unlikely(left <= -period)) {
		/* left underflowed by more than period. */
		left = period;
		local64_set(&hwc->period_left, left);
		hwc->last_period = period;
		overflow = 1;
	} else	if (unlikely(left <= 0)) {
		/* left underflowed by less than period. */
		left += period;
		local64_set(&hwc->period_left, left);
		hwc->last_period = period;
		overflow = 1;
	}

	if (left > arc_pmu->max_period)
		left = arc_pmu->max_period;

	value = arc_pmu->max_period - left;
	local64_set(&hwc->prev_count, value);

	/* Select counter */
	write_aux_reg(ARC_REG_PCT_INDEX, idx);

	/* Write value */
	write_aux_reg(ARC_REG_PCT_COUNTL, (u32)value);
	write_aux_reg(ARC_REG_PCT_COUNTH, (value >> 32));

	perf_event_update_userpage(event);

	return overflow;
}

/*
 * Assigns hardware counter to hardware condition.
 * Note that there is no separate start/stop mechanism;
 * stopping is achieved by assigning the 'never' condition
 */
static void arc_pmu_start(struct perf_event *event, int flags)
{
	struct hw_perf_event *hwc = &event->hw;
	int idx = hwc->idx;

	if (WARN_ON_ONCE(idx == -1))
		return;

	if (flags & PERF_EF_RELOAD)
		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));

	hwc->state = 0;

	arc_pmu_event_set_period(event);

	/* Enable interrupt for this counter */
	if (is_sampling_event(event))
		write_aux_reg(ARC_REG_PCT_INT_CTRL,
			      read_aux_reg(ARC_REG_PCT_INT_CTRL) | (1 << idx));

	/* enable ARC pmu here */
	write_aux_reg(ARC_REG_PCT_INDEX, idx);		/* counter # */
	write_aux_reg(ARC_REG_PCT_CONFIG, hwc->config);	/* condition */
}

static void arc_pmu_stop(struct perf_event *event, int flags)
{
	struct hw_perf_event *hwc = &event->hw;
	int idx = hwc->idx;

	/* Disable interrupt for this counter */
	if (is_sampling_event(event)) {
		/*
		 * Reset interrupt flag by writing of 1. This is required
		 * to make sure pending interrupt was not left.
		 */
		write_aux_reg(ARC_REG_PCT_INT_ACT, 1 << idx);
		write_aux_reg(ARC_REG_PCT_INT_CTRL,
			      read_aux_reg(ARC_REG_PCT_INT_CTRL) & ~(1 << idx));
	}

	if (!(event->hw.state & PERF_HES_STOPPED)) {
		/* stop ARC pmu here */
		write_aux_reg(ARC_REG_PCT_INDEX, idx);

		/* condition code #0 is always "never" */
		write_aux_reg(ARC_REG_PCT_CONFIG, 0);

		event->hw.state |= PERF_HES_STOPPED;
	}

	if ((flags & PERF_EF_UPDATE) &&
	    !(event->hw.state & PERF_HES_UPTODATE)) {
		arc_perf_event_update(event, &event->hw, idx);
		event->hw.state |= PERF_HES_UPTODATE;
	}
}

static void arc_pmu_del(struct perf_event *event, int flags)
{
	struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu);

	arc_pmu_stop(event, PERF_EF_UPDATE);
	__clear_bit(event->hw.idx, pmu_cpu->used_mask);

	pmu_cpu->act_counter[event->hw.idx] = 0;

	perf_event_update_userpage(event);
}

/* allocate hardware counter and optionally start counting */
static int arc_pmu_add(struct perf_event *event, int flags)
{
	struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu);
	struct hw_perf_event *hwc = &event->hw;
	int idx = hwc->idx;

	idx = ffz(pmu_cpu->used_mask[0]);
	if (idx == arc_pmu->n_counters)
		return -EAGAIN;

	__set_bit(idx, pmu_cpu->used_mask);
	hwc->idx = idx;

	write_aux_reg(ARC_REG_PCT_INDEX, idx);

	pmu_cpu->act_counter[idx] = event;

	if (is_sampling_event(event)) {
		/* Mimic full counter overflow as other arches do */
		write_aux_reg(ARC_REG_PCT_INT_CNTL, (u32)arc_pmu->max_period);
		write_aux_reg(ARC_REG_PCT_INT_CNTH,
			      (arc_pmu->max_period >> 32));
	}

	write_aux_reg(ARC_REG_PCT_CONFIG, 0);
	write_aux_reg(ARC_REG_PCT_COUNTL, 0);
	write_aux_reg(ARC_REG_PCT_COUNTH, 0);
	local64_set(&hwc->prev_count, 0);

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

	perf_event_update_userpage(event);

	return 0;
}

#ifdef CONFIG_ISA_ARCV2
static irqreturn_t arc_pmu_intr(int irq, void *dev)
{
	struct perf_sample_data data;
	struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu);
	struct pt_regs *regs;
	unsigned int active_ints;
	int idx;

	arc_pmu_disable(&arc_pmu->pmu);

	active_ints = read_aux_reg(ARC_REG_PCT_INT_ACT);
	if (!active_ints)
		goto done;

	regs = get_irq_regs();

	do {
		struct perf_event *event;
		struct hw_perf_event *hwc;

		idx = __ffs(active_ints);

		/* Reset interrupt flag by writing of 1 */
		write_aux_reg(ARC_REG_PCT_INT_ACT, 1 << idx);

		/*
		 * On reset of "interrupt active" bit corresponding
		 * "interrupt enable" bit gets automatically reset as well.
		 * Now we need to re-enable interrupt for the counter.
		 */
		write_aux_reg(ARC_REG_PCT_INT_CTRL,
			read_aux_reg(ARC_REG_PCT_INT_CTRL) | (1 << idx));

		event = pmu_cpu->act_counter[idx];
		hwc = &event->hw;

		WARN_ON_ONCE(hwc->idx != idx);

		arc_perf_event_update(event, &event->hw, event->hw.idx);
		perf_sample_data_init(&data, 0, hwc->last_period);
		if (arc_pmu_event_set_period(event)) {
			if (perf_event_overflow(event, &data, regs))
				arc_pmu_stop(event, 0);
		}

		active_ints &= ~(1U << idx);
	} while (active_ints);

done:
	arc_pmu_enable(&arc_pmu->pmu);

	return IRQ_HANDLED;
}
#else

static irqreturn_t arc_pmu_intr(int irq, void *dev)
{
	return IRQ_NONE;
}

#endif /* CONFIG_ISA_ARCV2 */

static void arc_cpu_pmu_irq_init(void *data)
{
	int irq = *(int *)data;

	enable_percpu_irq(irq, IRQ_TYPE_NONE);

	/* Clear all pending interrupt flags */
	write_aux_reg(ARC_REG_PCT_INT_ACT, 0xffffffff);
}

static int arc_pmu_device_probe(struct platform_device *pdev)
{
	struct arc_reg_pct_build pct_bcr;
	struct arc_reg_cc_build cc_bcr;
	int i, j, has_interrupts;
	int counter_size;	/* in bits */

	union cc_name {
		struct {
			uint32_t word0, word1;
			char sentinel;
		} indiv;
		char str[9];
	} cc_name;


	READ_BCR(ARC_REG_PCT_BUILD, pct_bcr);
	if (!pct_bcr.v) {
		pr_err("This core does not have performance counters!\n");
		return -ENODEV;
	}
	BUILD_BUG_ON(ARC_PERF_MAX_COUNTERS > 32);
	BUG_ON(pct_bcr.c > ARC_PERF_MAX_COUNTERS);

	READ_BCR(ARC_REG_CC_BUILD, cc_bcr);
	BUG_ON(!cc_bcr.v); /* Counters exist but No countable conditions ? */

	arc_pmu = devm_kzalloc(&pdev->dev, sizeof(struct arc_pmu), GFP_KERNEL);
	if (!arc_pmu)
		return -ENOMEM;

	has_interrupts = is_isa_arcv2() ? pct_bcr.i : 0;

	arc_pmu->n_counters = pct_bcr.c;
	counter_size = 32 + (pct_bcr.s << 4);

	arc_pmu->max_period = (1ULL << counter_size) / 2 - 1ULL;

	pr_info("ARC perf\t: %d counters (%d bits), %d conditions%s\n",
		arc_pmu->n_counters, counter_size, cc_bcr.c,
		has_interrupts ? ", [overflow IRQ support]":"");

	cc_name.str[8] = 0;
	for (i = 0; i < PERF_COUNT_ARC_HW_MAX; i++)
		arc_pmu->ev_hw_idx[i] = -1;

	/* loop thru all available h/w condition indexes */
	for (j = 0; j < cc_bcr.c; j++) {
		write_aux_reg(ARC_REG_CC_INDEX, j);
		cc_name.indiv.word0 = read_aux_reg(ARC_REG_CC_NAME0);
		cc_name.indiv.word1 = read_aux_reg(ARC_REG_CC_NAME1);

		/* See if it has been mapped to a perf event_id */
		for (i = 0; i < ARRAY_SIZE(arc_pmu_ev_hw_map); i++) {
			if (arc_pmu_ev_hw_map[i] &&
			    !strcmp(arc_pmu_ev_hw_map[i], cc_name.str) &&
			    strlen(arc_pmu_ev_hw_map[i])) {
				pr_debug("mapping perf event %2d to h/w event \'%8s\' (idx %d)\n",
					 i, cc_name.str, j);
				arc_pmu->ev_hw_idx[i] = j;
			}
		}
	}

	arc_pmu->pmu = (struct pmu) {
		.pmu_enable	= arc_pmu_enable,
		.pmu_disable	= arc_pmu_disable,
		.event_init	= arc_pmu_event_init,
		.add		= arc_pmu_add,
		.del		= arc_pmu_del,
		.start		= arc_pmu_start,
		.stop		= arc_pmu_stop,
		.read		= arc_pmu_read,
	};

	if (has_interrupts) {
		int irq = platform_get_irq(pdev, 0);

		if (irq < 0) {
			pr_err("Cannot get IRQ number for the platform\n");
			return -ENODEV;
		}

		arc_pmu->irq = irq;

		/* intc map function ensures irq_set_percpu_devid() called */
		request_percpu_irq(irq, arc_pmu_intr, "ARC perf counters",
				   this_cpu_ptr(&arc_pmu_cpu));

		on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1);

	} else
		arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;

	return perf_pmu_register(&arc_pmu->pmu, pdev->name, PERF_TYPE_RAW);
}

#ifdef CONFIG_OF
static const struct of_device_id arc_pmu_match[] = {
	{ .compatible = "snps,arc700-pct" },
	{ .compatible = "snps,archs-pct" },
	{},
};
MODULE_DEVICE_TABLE(of, arc_pmu_match);
#endif

static struct platform_driver arc_pmu_driver = {
	.driver	= {
		.name		= "arc-pct",
		.of_match_table = of_match_ptr(arc_pmu_match),
	},
	.probe		= arc_pmu_device_probe,
};

module_platform_driver(arc_pmu_driver);

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Mischa Jonker <mjonker@synopsys.com>");
MODULE_DESCRIPTION("ARC PMU driver");