summaryrefslogtreecommitdiffstats
path: root/tools/lib/perf/evsel.c
blob: c07160953224adf7e7b291f6a47ab33743d20b94 (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
// SPDX-License-Identifier: GPL-2.0
#include <errno.h>
#include <unistd.h>
#include <sys/syscall.h>
#include <perf/evsel.h>
#include <perf/cpumap.h>
#include <perf/threadmap.h>
#include <linux/list.h>
#include <internal/evsel.h>
#include <linux/zalloc.h>
#include <stdlib.h>
#include <internal/xyarray.h>
#include <internal/cpumap.h>
#include <internal/mmap.h>
#include <internal/threadmap.h>
#include <internal/lib.h>
#include <linux/string.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
#include <asm/bug.h>

void perf_evsel__init(struct perf_evsel *evsel, struct perf_event_attr *attr,
		      int idx)
{
	INIT_LIST_HEAD(&evsel->node);
	evsel->attr = *attr;
	evsel->idx  = idx;
	evsel->leader = evsel;
}

struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr)
{
	struct perf_evsel *evsel = zalloc(sizeof(*evsel));

	if (evsel != NULL)
		perf_evsel__init(evsel, attr, 0);

	return evsel;
}

void perf_evsel__delete(struct perf_evsel *evsel)
{
	free(evsel);
}

#define FD(_evsel, _cpu_map_idx, _thread)				\
	((int *)xyarray__entry(_evsel->fd, _cpu_map_idx, _thread))
#define MMAP(_evsel, _cpu_map_idx, _thread)				\
	(_evsel->mmap ? ((struct perf_mmap *) xyarray__entry(_evsel->mmap, _cpu_map_idx, _thread)) \
		      : NULL)

int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
{
	evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));

	if (evsel->fd) {
		int idx, thread;

		for (idx = 0; idx < ncpus; idx++) {
			for (thread = 0; thread < nthreads; thread++) {
				int *fd = FD(evsel, idx, thread);

				if (fd)
					*fd = -1;
			}
		}
	}

	return evsel->fd != NULL ? 0 : -ENOMEM;
}

static int perf_evsel__alloc_mmap(struct perf_evsel *evsel, int ncpus, int nthreads)
{
	evsel->mmap = xyarray__new(ncpus, nthreads, sizeof(struct perf_mmap));

	return evsel->mmap != NULL ? 0 : -ENOMEM;
}

static int
sys_perf_event_open(struct perf_event_attr *attr,
		    pid_t pid, struct perf_cpu cpu, int group_fd,
		    unsigned long flags)
{
	return syscall(__NR_perf_event_open, attr, pid, cpu.cpu, group_fd, flags);
}

static int get_group_fd(struct perf_evsel *evsel, int cpu_map_idx, int thread, int *group_fd)
{
	struct perf_evsel *leader = evsel->leader;
	int *fd;

	if (evsel == leader) {
		*group_fd = -1;
		return 0;
	}

	/*
	 * Leader must be already processed/open,
	 * if not it's a bug.
	 */
	if (!leader->fd)
		return -ENOTCONN;

	fd = FD(leader, cpu_map_idx, thread);
	if (fd == NULL || *fd == -1)
		return -EBADF;

	*group_fd = *fd;

	return 0;
}

int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
		     struct perf_thread_map *threads)
{
	struct perf_cpu cpu;
	int idx, thread, err = 0;

	if (cpus == NULL) {
		static struct perf_cpu_map *empty_cpu_map;

		if (empty_cpu_map == NULL) {
			empty_cpu_map = perf_cpu_map__new_any_cpu();
			if (empty_cpu_map == NULL)
				return -ENOMEM;
		}

		cpus = empty_cpu_map;
	}

	if (threads == NULL) {
		static struct perf_thread_map *empty_thread_map;

		if (empty_thread_map == NULL) {
			empty_thread_map = perf_thread_map__new_dummy();
			if (empty_thread_map == NULL)
				return -ENOMEM;
		}

		threads = empty_thread_map;
	}

	if (evsel->fd == NULL &&
	    perf_evsel__alloc_fd(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0)
		return -ENOMEM;

	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
		for (thread = 0; thread < threads->nr; thread++) {
			int fd, group_fd, *evsel_fd;

			evsel_fd = FD(evsel, idx, thread);
			if (evsel_fd == NULL) {
				err = -EINVAL;
				goto out;
			}

			err = get_group_fd(evsel, idx, thread, &group_fd);
			if (err < 0)
				goto out;

			fd = sys_perf_event_open(&evsel->attr,
						 threads->map[thread].pid,
						 cpu, group_fd, 0);

			if (fd < 0) {
				err = -errno;
				goto out;
			}

			*evsel_fd = fd;
		}
	}
out:
	if (err)
		perf_evsel__close(evsel);

	return err;
}

static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu_map_idx)
{
	int thread;

	for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) {
		int *fd = FD(evsel, cpu_map_idx, thread);

		if (fd && *fd >= 0) {
			close(*fd);
			*fd = -1;
		}
	}
}

void perf_evsel__close_fd(struct perf_evsel *evsel)
{
	for (int idx = 0; idx < xyarray__max_x(evsel->fd); idx++)
		perf_evsel__close_fd_cpu(evsel, idx);
}

void perf_evsel__free_fd(struct perf_evsel *evsel)
{
	xyarray__delete(evsel->fd);
	evsel->fd = NULL;
}

void perf_evsel__close(struct perf_evsel *evsel)
{
	if (evsel->fd == NULL)
		return;

	perf_evsel__close_fd(evsel);
	perf_evsel__free_fd(evsel);
}

void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx)
{
	if (evsel->fd == NULL)
		return;

	perf_evsel__close_fd_cpu(evsel, cpu_map_idx);
}

void perf_evsel__munmap(struct perf_evsel *evsel)
{
	int idx, thread;

	if (evsel->fd == NULL || evsel->mmap == NULL)
		return;

	for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) {
		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
			int *fd = FD(evsel, idx, thread);

			if (fd == NULL || *fd < 0)
				continue;

			perf_mmap__munmap(MMAP(evsel, idx, thread));
		}
	}

	xyarray__delete(evsel->mmap);
	evsel->mmap = NULL;
}

int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
{
	int ret, idx, thread;
	struct perf_mmap_param mp = {
		.prot = PROT_READ | PROT_WRITE,
		.mask = (pages * page_size) - 1,
	};

	if (evsel->fd == NULL || evsel->mmap)
		return -EINVAL;

	if (perf_evsel__alloc_mmap(evsel, xyarray__max_x(evsel->fd), xyarray__max_y(evsel->fd)) < 0)
		return -ENOMEM;

	for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) {
		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
			int *fd = FD(evsel, idx, thread);
			struct perf_mmap *map;
			struct perf_cpu cpu = perf_cpu_map__cpu(evsel->cpus, idx);

			if (fd == NULL || *fd < 0)
				continue;

			map = MMAP(evsel, idx, thread);
			perf_mmap__init(map, NULL, false, NULL);

			ret = perf_mmap__mmap(map, &mp, *fd, cpu);
			if (ret) {
				perf_evsel__munmap(evsel);
				return ret;
			}
		}
	}

	return 0;
}

void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread)
{
	int *fd = FD(evsel, cpu_map_idx, thread);

	if (fd == NULL || *fd < 0 || MMAP(evsel, cpu_map_idx, thread) == NULL)
		return NULL;

	return MMAP(evsel, cpu_map_idx, thread)->base;
}

int perf_evsel__read_size(struct perf_evsel *evsel)
{
	u64 read_format = evsel->attr.read_format;
	int entry = sizeof(u64); /* value */
	int size = 0;
	int nr = 1;

	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
		size += sizeof(u64);

	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
		size += sizeof(u64);

	if (read_format & PERF_FORMAT_ID)
		entry += sizeof(u64);

	if (read_format & PERF_FORMAT_LOST)
		entry += sizeof(u64);

	if (read_format & PERF_FORMAT_GROUP) {
		nr = evsel->nr_members;
		size += sizeof(u64);
	}

	size += entry * nr;
	return size;
}

/* This only reads values for the leader */
static int perf_evsel__read_group(struct perf_evsel *evsel, int cpu_map_idx,
				  int thread, struct perf_counts_values *count)
{
	size_t size = perf_evsel__read_size(evsel);
	int *fd = FD(evsel, cpu_map_idx, thread);
	u64 read_format = evsel->attr.read_format;
	u64 *data;
	int idx = 1;

	if (fd == NULL || *fd < 0)
		return -EINVAL;

	data = calloc(1, size);
	if (data == NULL)
		return -ENOMEM;

	if (readn(*fd, data, size) <= 0) {
		free(data);
		return -errno;
	}

	/*
	 * This reads only the leader event intentionally since we don't have
	 * perf counts values for sibling events.
	 */
	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
		count->ena = data[idx++];
	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
		count->run = data[idx++];

	/* value is always available */
	count->val = data[idx++];
	if (read_format & PERF_FORMAT_ID)
		count->id = data[idx++];
	if (read_format & PERF_FORMAT_LOST)
		count->lost = data[idx++];

	free(data);
	return 0;
}

/*
 * The perf read format is very flexible.  It needs to set the proper
 * values according to the read format.
 */
static void perf_evsel__adjust_values(struct perf_evsel *evsel, u64 *buf,
				      struct perf_counts_values *count)
{
	u64 read_format = evsel->attr.read_format;
	int n = 0;

	count->val = buf[n++];

	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
		count->ena = buf[n++];

	if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
		count->run = buf[n++];

	if (read_format & PERF_FORMAT_ID)
		count->id = buf[n++];

	if (read_format & PERF_FORMAT_LOST)
		count->lost = buf[n++];
}

int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread,
		     struct perf_counts_values *count)
{
	size_t size = perf_evsel__read_size(evsel);
	int *fd = FD(evsel, cpu_map_idx, thread);
	u64 read_format = evsel->attr.read_format;
	struct perf_counts_values buf;

	memset(count, 0, sizeof(*count));

	if (fd == NULL || *fd < 0)
		return -EINVAL;

	if (read_format & PERF_FORMAT_GROUP)
		return perf_evsel__read_group(evsel, cpu_map_idx, thread, count);

	if (MMAP(evsel, cpu_map_idx, thread) &&
	    !(read_format & (PERF_FORMAT_ID | PERF_FORMAT_LOST)) &&
	    !perf_mmap__read_self(MMAP(evsel, cpu_map_idx, thread), count))
		return 0;

	if (readn(*fd, buf.values, size) <= 0)
		return -errno;

	perf_evsel__adjust_values(evsel, buf.values, count);
	return 0;
}

static int perf_evsel__ioctl(struct perf_evsel *evsel, int ioc, void *arg,
			     int cpu_map_idx, int thread)
{
	int *fd = FD(evsel, cpu_map_idx, thread);

	if (fd == NULL || *fd < 0)
		return -1;

	return ioctl(*fd, ioc, arg);
}

static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
				 int ioc,  void *arg,
				 int cpu_map_idx)
{
	int thread;

	for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
		int err = perf_evsel__ioctl(evsel, ioc, arg, cpu_map_idx, thread);

		if (err)
			return err;
	}

	return 0;
}

int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx)
{
	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu_map_idx);
}

int perf_evsel__enable_thread(struct perf_evsel *evsel, int thread)
{
	struct perf_cpu cpu __maybe_unused;
	int idx;
	int err;

	perf_cpu_map__for_each_cpu(cpu, idx, evsel->cpus) {
		err = perf_evsel__ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, idx, thread);
		if (err)
			return err;
	}

	return 0;
}

int perf_evsel__enable(struct perf_evsel *evsel)
{
	int i;
	int err = 0;

	for (i = 0; i < xyarray__max_x(evsel->fd) && !err; i++)
		err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, i);
	return err;
}

int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx)
{
	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu_map_idx);
}

int perf_evsel__disable(struct perf_evsel *evsel)
{
	int i;
	int err = 0;

	for (i = 0; i < xyarray__max_x(evsel->fd) && !err; i++)
		err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, i);
	return err;
}

int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter)
{
	int err = 0, i;

	for (i = 0; i < perf_cpu_map__nr(evsel->cpus) && !err; i++)
		err = perf_evsel__run_ioctl(evsel,
				     PERF_EVENT_IOC_SET_FILTER,
				     (void *)filter, i);
	return err;
}

struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
{
	return evsel->cpus;
}

struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel)
{
	return evsel->threads;
}

struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel)
{
	return &evsel->attr;
}

int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
{
	if (ncpus == 0 || nthreads == 0)
		return 0;

	evsel->sample_id = xyarray__new(ncpus, nthreads, sizeof(struct perf_sample_id));
	if (evsel->sample_id == NULL)
		return -ENOMEM;

	evsel->id = zalloc(ncpus * nthreads * sizeof(u64));
	if (evsel->id == NULL) {
		xyarray__delete(evsel->sample_id);
		evsel->sample_id = NULL;
		return -ENOMEM;
	}

	return 0;
}

void perf_evsel__free_id(struct perf_evsel *evsel)
{
	xyarray__delete(evsel->sample_id);
	evsel->sample_id = NULL;
	zfree(&evsel->id);
	evsel->ids = 0;
}

void perf_counts_values__scale(struct perf_counts_values *count,
			       bool scale, __s8 *pscaled)
{
	s8 scaled = 0;

	if (scale) {
		if (count->run == 0) {
			scaled = -1;
			count->val = 0;
		} else if (count->run < count->ena) {
			scaled = 1;
			count->val = (u64)((double)count->val * count->ena / count->run);
		}
	}

	if (pscaled)
		*pscaled = scaled;
}