summaryrefslogtreecommitdiff
path: root/drivers/perf/riscv_pmu.c
blob: 0dda70e1ef90a19017c902689f970dea684b4f4c (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
// SPDX-License-Identifier: GPL-2.0
/*
 * RISC-V performance counter support.
 *
 * Copyright (C) 2021 Western Digital Corporation or its affiliates.
 *
 * This implementation is based on old RISC-V perf and ARM perf event code
 * which are in turn based on sparc64 and x86 code.
 */

#include <linux/cpumask.h>
#include <linux/irq.h>
#include <linux/irqdesc.h>
#include <linux/perf/riscv_pmu.h>
#include <linux/printk.h>
#include <linux/smp.h>
#include <linux/sched_clock.h>

#include <asm/sbi.h>

static bool riscv_perf_user_access(struct perf_event *event)
{
	return ((event->attr.type == PERF_TYPE_HARDWARE) ||
		(event->attr.type == PERF_TYPE_HW_CACHE) ||
		(event->attr.type == PERF_TYPE_RAW)) &&
		!!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT) &&
		(event->hw.idx != -1);
}

void arch_perf_update_userpage(struct perf_event *event,
			       struct perf_event_mmap_page *userpg, u64 now)
{
	struct clock_read_data *rd;
	unsigned int seq;
	u64 ns;

	userpg->cap_user_time = 0;
	userpg->cap_user_time_zero = 0;
	userpg->cap_user_time_short = 0;
	userpg->cap_user_rdpmc = riscv_perf_user_access(event);

#ifdef CONFIG_RISCV_PMU
	/*
	 * The counters are 64-bit but the priv spec doesn't mandate all the
	 * bits to be implemented: that's why, counter width can vary based on
	 * the cpu vendor.
	 */
	if (userpg->cap_user_rdpmc)
		userpg->pmc_width = to_riscv_pmu(event->pmu)->ctr_get_width(event->hw.idx) + 1;
#endif

	do {
		rd = sched_clock_read_begin(&seq);

		userpg->time_mult = rd->mult;
		userpg->time_shift = rd->shift;
		userpg->time_zero = rd->epoch_ns;
		userpg->time_cycles = rd->epoch_cyc;
		userpg->time_mask = rd->sched_clock_mask;

		/*
		 * Subtract the cycle base, such that software that
		 * doesn't know about cap_user_time_short still 'works'
		 * assuming no wraps.
		 */
		ns = mul_u64_u32_shr(rd->epoch_cyc, rd->mult, rd->shift);
		userpg->time_zero -= ns;

	} while (sched_clock_read_retry(seq));

	userpg->time_offset = userpg->time_zero - now;

	/*
	 * time_shift is not expected to be greater than 31 due to
	 * the original published conversion algorithm shifting a
	 * 32-bit value (now specifies a 64-bit value) - refer
	 * perf_event_mmap_page documentation in perf_event.h.
	 */
	if (userpg->time_shift == 32) {
		userpg->time_shift = 31;
		userpg->time_mult >>= 1;
	}

	/*
	 * Internal timekeeping for enabled/running/stopped times
	 * is always computed with the sched_clock.
	 */
	userpg->cap_user_time = 1;
	userpg->cap_user_time_zero = 1;
	userpg->cap_user_time_short = 1;
}

static unsigned long csr_read_num(int csr_num)
{
#define switchcase_csr_read(__csr_num, __val)		{\
	case __csr_num:					\
		__val = csr_read(__csr_num);		\
		break; }
#define switchcase_csr_read_2(__csr_num, __val)		{\
	switchcase_csr_read(__csr_num + 0, __val)	 \
	switchcase_csr_read(__csr_num + 1, __val)}
#define switchcase_csr_read_4(__csr_num, __val)		{\
	switchcase_csr_read_2(__csr_num + 0, __val)	 \
	switchcase_csr_read_2(__csr_num + 2, __val)}
#define switchcase_csr_read_8(__csr_num, __val)		{\
	switchcase_csr_read_4(__csr_num + 0, __val)	 \
	switchcase_csr_read_4(__csr_num + 4, __val)}
#define switchcase_csr_read_16(__csr_num, __val)	{\
	switchcase_csr_read_8(__csr_num + 0, __val)	 \
	switchcase_csr_read_8(__csr_num + 8, __val)}
#define switchcase_csr_read_32(__csr_num, __val)	{\
	switchcase_csr_read_16(__csr_num + 0, __val)	 \
	switchcase_csr_read_16(__csr_num + 16, __val)}

	unsigned long ret = 0;

	switch (csr_num) {
	switchcase_csr_read_32(CSR_CYCLE, ret)
	switchcase_csr_read_32(CSR_CYCLEH, ret)
	default :
		break;
	}

	return ret;
#undef switchcase_csr_read_32
#undef switchcase_csr_read_16
#undef switchcase_csr_read_8
#undef switchcase_csr_read_4
#undef switchcase_csr_read_2
#undef switchcase_csr_read
}

/*
 * Read the CSR of a corresponding counter.
 */
unsigned long riscv_pmu_ctr_read_csr(unsigned long csr)
{
	if (csr < CSR_CYCLE || csr > CSR_HPMCOUNTER31H ||
	   (csr > CSR_HPMCOUNTER31 && csr < CSR_CYCLEH)) {
		pr_err("Invalid performance counter csr %lx\n", csr);
		return -EINVAL;
	}

	return csr_read_num(csr);
}

u64 riscv_pmu_ctr_get_width_mask(struct perf_event *event)
{
	int cwidth;
	struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
	struct hw_perf_event *hwc = &event->hw;

	if (!rvpmu->ctr_get_width)
	/**
	 * If the pmu driver doesn't support counter width, set it to default
	 * maximum allowed by the specification.
	 */
		cwidth = 63;
	else {
		if (hwc->idx == -1)
			/* Handle init case where idx is not initialized yet */
			cwidth = rvpmu->ctr_get_width(0);
		else
			cwidth = rvpmu->ctr_get_width(hwc->idx);
	}

	return GENMASK_ULL(cwidth, 0);
}

u64 riscv_pmu_event_update(struct perf_event *event)
{
	struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
	struct hw_perf_event *hwc = &event->hw;
	u64 prev_raw_count, new_raw_count;
	unsigned long cmask;
	u64 oldval, delta;

	if (!rvpmu->ctr_read)
		return 0;

	cmask = riscv_pmu_ctr_get_width_mask(event);

	do {
		prev_raw_count = local64_read(&hwc->prev_count);
		new_raw_count = rvpmu->ctr_read(event);
		oldval = local64_cmpxchg(&hwc->prev_count, prev_raw_count,
					 new_raw_count);
	} while (oldval != prev_raw_count);

	delta = (new_raw_count - prev_raw_count) & cmask;
	local64_add(delta, &event->count);
	local64_sub(delta, &hwc->period_left);

	return delta;
}

void riscv_pmu_stop(struct perf_event *event, int flags)
{
	struct hw_perf_event *hwc = &event->hw;
	struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);

	WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);

	if (!(hwc->state & PERF_HES_STOPPED)) {
		if (rvpmu->ctr_stop) {
			rvpmu->ctr_stop(event, 0);
			hwc->state |= PERF_HES_STOPPED;
		}
		riscv_pmu_event_update(event);
		hwc->state |= PERF_HES_UPTODATE;
	}
}

int riscv_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 overflow = 0;
	uint64_t max_period = riscv_pmu_ctr_get_width_mask(event);

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

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

	/*
	 * Limit the maximum period to prevent the counter value
	 * from overtaking the one we are about to program. In
	 * effect we are reducing max_period to account for
	 * interrupt latency (and we are being very conservative).
	 */
	if (left > (max_period >> 1))
		left = (max_period >> 1);

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

	perf_event_update_userpage(event);

	return overflow;
}

void riscv_pmu_start(struct perf_event *event, int flags)
{
	struct hw_perf_event *hwc = &event->hw;
	struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
	uint64_t max_period = riscv_pmu_ctr_get_width_mask(event);
	u64 init_val;

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

	hwc->state = 0;
	riscv_pmu_event_set_period(event);
	init_val = local64_read(&hwc->prev_count) & max_period;
	rvpmu->ctr_start(event, init_val);
	perf_event_update_userpage(event);
}

static int riscv_pmu_add(struct perf_event *event, int flags)
{
	struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
	struct cpu_hw_events *cpuc = this_cpu_ptr(rvpmu->hw_events);
	struct hw_perf_event *hwc = &event->hw;
	int idx;

	idx = rvpmu->ctr_get_idx(event);
	if (idx < 0)
		return idx;

	hwc->idx = idx;
	cpuc->events[idx] = event;
	cpuc->n_events++;
	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
	if (flags & PERF_EF_START)
		riscv_pmu_start(event, PERF_EF_RELOAD);

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

	return 0;
}

static void riscv_pmu_del(struct perf_event *event, int flags)
{
	struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
	struct cpu_hw_events *cpuc = this_cpu_ptr(rvpmu->hw_events);
	struct hw_perf_event *hwc = &event->hw;

	riscv_pmu_stop(event, PERF_EF_UPDATE);
	cpuc->events[hwc->idx] = NULL;
	/* The firmware need to reset the counter mapping */
	if (rvpmu->ctr_stop)
		rvpmu->ctr_stop(event, RISCV_PMU_STOP_FLAG_RESET);
	cpuc->n_events--;
	if (rvpmu->ctr_clear_idx)
		rvpmu->ctr_clear_idx(event);
	perf_event_update_userpage(event);
	hwc->idx = -1;
}

static void riscv_pmu_read(struct perf_event *event)
{
	riscv_pmu_event_update(event);
}

static int riscv_pmu_event_init(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;
	struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);
	int mapped_event;
	u64 event_config = 0;
	uint64_t cmask;

	hwc->flags = 0;
	mapped_event = rvpmu->event_map(event, &event_config);
	if (mapped_event < 0) {
		pr_debug("event %x:%llx not supported\n", event->attr.type,
			 event->attr.config);
		return mapped_event;
	}

	/*
	 * idx is set to -1 because the index of a general event should not be
	 * decided until binding to some counter in pmu->add().
	 * config will contain the information about counter CSR
	 * the idx will contain the counter index
	 */
	hwc->config = event_config;
	hwc->idx = -1;
	hwc->event_base = mapped_event;

	if (rvpmu->event_init)
		rvpmu->event_init(event);

	if (!is_sampling_event(event)) {
		/*
		 * 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.
		 */
		cmask = riscv_pmu_ctr_get_width_mask(event);
		hwc->sample_period  =  cmask >> 1;
		hwc->last_period    = hwc->sample_period;
		local64_set(&hwc->period_left, hwc->sample_period);
	}

	return 0;
}

static int riscv_pmu_event_idx(struct perf_event *event)
{
	struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);

	if (!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT))
		return 0;

	if (rvpmu->csr_index)
		return rvpmu->csr_index(event) + 1;

	return 0;
}

static void riscv_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm)
{
	struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);

	if (rvpmu->event_mapped) {
		rvpmu->event_mapped(event, mm);
		perf_event_update_userpage(event);
	}
}

static void riscv_pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm)
{
	struct riscv_pmu *rvpmu = to_riscv_pmu(event->pmu);

	if (rvpmu->event_unmapped) {
		rvpmu->event_unmapped(event, mm);
		perf_event_update_userpage(event);
	}
}

struct riscv_pmu *riscv_pmu_alloc(void)
{
	struct riscv_pmu *pmu;
	int cpuid, i;
	struct cpu_hw_events *cpuc;

	pmu = kzalloc(sizeof(*pmu), GFP_KERNEL);
	if (!pmu)
		goto out;

	pmu->hw_events = alloc_percpu_gfp(struct cpu_hw_events, GFP_KERNEL);
	if (!pmu->hw_events) {
		pr_info("failed to allocate per-cpu PMU data.\n");
		goto out_free_pmu;
	}

	for_each_possible_cpu(cpuid) {
		cpuc = per_cpu_ptr(pmu->hw_events, cpuid);
		cpuc->n_events = 0;
		for (i = 0; i < RISCV_MAX_COUNTERS; i++)
			cpuc->events[i] = NULL;
	}
	pmu->pmu = (struct pmu) {
		.event_init	= riscv_pmu_event_init,
		.event_mapped	= riscv_pmu_event_mapped,
		.event_unmapped	= riscv_pmu_event_unmapped,
		.event_idx	= riscv_pmu_event_idx,
		.add		= riscv_pmu_add,
		.del		= riscv_pmu_del,
		.start		= riscv_pmu_start,
		.stop		= riscv_pmu_stop,
		.read		= riscv_pmu_read,
	};

	return pmu;

out_free_pmu:
	kfree(pmu);
out:
	return NULL;
}