summaryrefslogtreecommitdiff
path: root/arch/riscv/kernel/perf_event.c
blob: b0e10c4e9f7745beea96cac0c96d20a6b738a77c (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
/* SPDX-License-Identifier: GPL-2.0 */
/*
 * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
 * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
 * Copyright (C) 2009 Jaswinder Singh Rajput
 * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
 * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
 * Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
 * Copyright (C) 2009 Google, Inc., Stephane Eranian
 * Copyright 2014 Tilera Corporation. All Rights Reserved.
 * Copyright (C) 2018 Andes Technology Corporation
 *
 * Perf_events support for RISC-V platforms.
 *
 * Since the spec. (as of now, Priv-Spec 1.10) does not provide enough
 * functionality for perf event to fully work, this file provides
 * the very basic framework only.
 *
 * For platform portings, please check Documentations/riscv/pmu.txt.
 *
 * The Copyright line includes x86 and tile ones.
 */

#include <linux/kprobes.h>
#include <linux/kernel.h>
#include <linux/kdebug.h>
#include <linux/mutex.h>
#include <linux/bitmap.h>
#include <linux/irq.h>
#include <linux/interrupt.h>
#include <linux/perf_event.h>
#include <linux/atomic.h>
#include <linux/of.h>
#include <asm/perf_event.h>

static const struct riscv_pmu *riscv_pmu __read_mostly;
static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);

/*
 * Hardware & cache maps and their methods
 */

static const int riscv_hw_event_map[] = {
	[PERF_COUNT_HW_CPU_CYCLES]		= RISCV_PMU_CYCLE,
	[PERF_COUNT_HW_INSTRUCTIONS]		= RISCV_PMU_INSTRET,
	[PERF_COUNT_HW_CACHE_REFERENCES]	= RISCV_OP_UNSUPP,
	[PERF_COUNT_HW_CACHE_MISSES]		= RISCV_OP_UNSUPP,
	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= RISCV_OP_UNSUPP,
	[PERF_COUNT_HW_BRANCH_MISSES]		= RISCV_OP_UNSUPP,
	[PERF_COUNT_HW_BUS_CYCLES]		= RISCV_OP_UNSUPP,
};

#define C(x) PERF_COUNT_HW_CACHE_##x
static const int riscv_cache_event_map[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
	[C(L1D)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
		},
	},
	[C(L1I)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
		},
	},
	[C(LL)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
		},
	},
	[C(DTLB)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)] =  RISCV_OP_UNSUPP,
			[C(RESULT_MISS)] =  RISCV_OP_UNSUPP,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
		},
	},
	[C(ITLB)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
		},
	},
	[C(BPU)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)] = RISCV_OP_UNSUPP,
			[C(RESULT_MISS)] = RISCV_OP_UNSUPP,
		},
	},
};

static int riscv_map_hw_event(u64 config)
{
	if (config >= riscv_pmu->max_events)
		return -EINVAL;

	return riscv_pmu->hw_events[config];
}

int riscv_map_cache_decode(u64 config, unsigned int *type,
			   unsigned int *op, unsigned int *result)
{
	return -ENOENT;
}

static int riscv_map_cache_event(u64 config)
{
	unsigned int type, op, result;
	int err = -ENOENT;
		int code;

	err = riscv_map_cache_decode(config, &type, &op, &result);
	if (!riscv_pmu->cache_events || err)
		return err;

	if (type >= PERF_COUNT_HW_CACHE_MAX ||
	    op >= PERF_COUNT_HW_CACHE_OP_MAX ||
	    result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
		return -EINVAL;

	code = (*riscv_pmu->cache_events)[type][op][result];
	if (code == RISCV_OP_UNSUPP)
		return -EINVAL;

	return code;
}

/*
 * Low-level functions: reading/writing counters
 */

static inline u64 read_counter(int idx)
{
	u64 val = 0;

	switch (idx) {
	case RISCV_PMU_CYCLE:
		val = csr_read(cycle);
		break;
	case RISCV_PMU_INSTRET:
		val = csr_read(instret);
		break;
	default:
		WARN_ON_ONCE(idx < 0 ||	idx > RISCV_MAX_COUNTERS);
		return -EINVAL;
	}

	return val;
}

static inline void write_counter(int idx, u64 value)
{
	/* currently not supported */
	WARN_ON_ONCE(1);
}

/*
 * pmu->read: read and update the counter
 *
 * Other architectures' implementation often have a xxx_perf_event_update
 * routine, which can return counter values when called in the IRQ, but
 * return void when being called by the pmu->read method.
 */
static void riscv_pmu_read(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;
	u64 prev_raw_count, new_raw_count;
	u64 oldval;
	int idx = hwc->idx;
	u64 delta;

	do {
		prev_raw_count = local64_read(&hwc->prev_count);
		new_raw_count = read_counter(idx);

		oldval = local64_cmpxchg(&hwc->prev_count, prev_raw_count,
					 new_raw_count);
	} while (oldval != prev_raw_count);

	/*
	 * delta is the value to update the counter we maintain in the kernel.
	 */
	delta = (new_raw_count - prev_raw_count) &
		((1ULL << riscv_pmu->counter_width) - 1);
	local64_add(delta, &event->count);
	/*
	 * Something like local64_sub(delta, &hwc->period_left) here is
	 * needed if there is an interrupt for perf.
	 */
}

/*
 * State transition functions:
 *
 * stop()/start() & add()/del()
 */

/*
 * pmu->stop: stop the counter
 */
static void riscv_pmu_stop(struct perf_event *event, int flags)
{
	struct hw_perf_event *hwc = &event->hw;

	WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
	hwc->state |= PERF_HES_STOPPED;

	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
		riscv_pmu->pmu->read(event);
		hwc->state |= PERF_HES_UPTODATE;
	}
}

/*
 * pmu->start: start the event.
 */
static void riscv_pmu_start(struct perf_event *event, int flags)
{
	struct hw_perf_event *hwc = &event->hw;

	if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
		return;

	if (flags & PERF_EF_RELOAD) {
		WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));

		/*
		 * Set the counter to the period to the next interrupt here,
		 * if you have any.
		 */
	}

	hwc->state = 0;
	perf_event_update_userpage(event);

	/*
	 * Since we cannot write to counters, this serves as an initialization
	 * to the delta-mechanism in pmu->read(); otherwise, the delta would be
	 * wrong when pmu->read is called for the first time.
	 */
	local64_set(&hwc->prev_count, read_counter(hwc->idx));
}

/*
 * pmu->add: add the event to PMU.
 */
static int riscv_pmu_add(struct perf_event *event, int flags)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	struct hw_perf_event *hwc = &event->hw;

	if (cpuc->n_events == riscv_pmu->num_counters)
		return -ENOSPC;

	/*
	 * We don't have general conunters, so no binding-event-to-counter
	 * process here.
	 *
	 * Indexing using hwc->config generally not works, since config may
	 * contain extra information, but here the only info we have in
	 * hwc->config is the event index.
	 */
	hwc->idx = hwc->config;
	cpuc->events[hwc->idx] = event;
	cpuc->n_events++;

	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;

	if (flags & PERF_EF_START)
		riscv_pmu->pmu->start(event, PERF_EF_RELOAD);

	return 0;
}

/*
 * pmu->del: delete the event from PMU.
 */
static void riscv_pmu_del(struct perf_event *event, int flags)
{
	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
	struct hw_perf_event *hwc = &event->hw;

	cpuc->events[hwc->idx] = NULL;
	cpuc->n_events--;
	riscv_pmu->pmu->stop(event, PERF_EF_UPDATE);
	perf_event_update_userpage(event);
}

/*
 * Interrupt: a skeletion for reference.
 */

static DEFINE_MUTEX(pmc_reserve_mutex);

irqreturn_t riscv_base_pmu_handle_irq(int irq_num, void *dev)
{
	return IRQ_NONE;
}

static int reserve_pmc_hardware(void)
{
	int err = 0;

	mutex_lock(&pmc_reserve_mutex);
	if (riscv_pmu->irq >= 0 && riscv_pmu->handle_irq) {
		err = request_irq(riscv_pmu->irq, riscv_pmu->handle_irq,
				  IRQF_PERCPU, "riscv-base-perf", NULL);
	}
	mutex_unlock(&pmc_reserve_mutex);

	return err;
}

void release_pmc_hardware(void)
{
	mutex_lock(&pmc_reserve_mutex);
	if (riscv_pmu->irq >= 0)
		free_irq(riscv_pmu->irq, NULL);
	mutex_unlock(&pmc_reserve_mutex);
}

/*
 * Event Initialization/Finalization
 */

static atomic_t riscv_active_events = ATOMIC_INIT(0);

static void riscv_event_destroy(struct perf_event *event)
{
	if (atomic_dec_return(&riscv_active_events) == 0)
		release_pmc_hardware();
}

static int riscv_event_init(struct perf_event *event)
{
	struct perf_event_attr *attr = &event->attr;
	struct hw_perf_event *hwc = &event->hw;
	int err;
	int code;

	if (atomic_inc_return(&riscv_active_events) == 1) {
		err = reserve_pmc_hardware();

		if (err) {
			pr_warn("PMC hardware not available\n");
			atomic_dec(&riscv_active_events);
			return -EBUSY;
		}
	}

	switch (event->attr.type) {
	case PERF_TYPE_HARDWARE:
		code = riscv_pmu->map_hw_event(attr->config);
		break;
	case PERF_TYPE_HW_CACHE:
		code = riscv_pmu->map_cache_event(attr->config);
		break;
	case PERF_TYPE_RAW:
		return -EOPNOTSUPP;
	default:
		return -ENOENT;
	}

	event->destroy = riscv_event_destroy;
	if (code < 0) {
		event->destroy(event);
		return code;
	}

	/*
	 * idx is set to -1 because the index of a general event should not be
	 * decided until binding to some counter in pmu->add().
	 *
	 * But since we don't have such support, later in pmu->add(), we just
	 * use hwc->config as the index instead.
	 */
	hwc->config = code;
	hwc->idx = -1;

	return 0;
}

/*
 * Initialization
 */

static struct pmu min_pmu = {
	.name		= "riscv-base",
	.event_init	= riscv_event_init,
	.add		= riscv_pmu_add,
	.del		= riscv_pmu_del,
	.start		= riscv_pmu_start,
	.stop		= riscv_pmu_stop,
	.read		= riscv_pmu_read,
};

static const struct riscv_pmu riscv_base_pmu = {
	.pmu = &min_pmu,
	.max_events = ARRAY_SIZE(riscv_hw_event_map),
	.map_hw_event = riscv_map_hw_event,
	.hw_events = riscv_hw_event_map,
	.map_cache_event = riscv_map_cache_event,
	.cache_events = &riscv_cache_event_map,
	.counter_width = 63,
	.num_counters = RISCV_BASE_COUNTERS + 0,
	.handle_irq = &riscv_base_pmu_handle_irq,

	/* This means this PMU has no IRQ. */
	.irq = -1,
};

static const struct of_device_id riscv_pmu_of_ids[] = {
	{.compatible = "riscv,base-pmu",	.data = &riscv_base_pmu},
	{ /* sentinel value */ }
};

int __init init_hw_perf_events(void)
{
	struct device_node *node = of_find_node_by_type(NULL, "pmu");
	const struct of_device_id *of_id;

	riscv_pmu = &riscv_base_pmu;

	if (node) {
		of_id = of_match_node(riscv_pmu_of_ids, node);

		if (of_id)
			riscv_pmu = of_id->data;
	}

	perf_pmu_register(riscv_pmu->pmu, "cpu", PERF_TYPE_RAW);
	return 0;
}
arch_initcall(init_hw_perf_events);