summaryrefslogtreecommitdiffstats
path: root/tools/perf/util/stat.c
blob: ee6f0348121514220df185ec7e19c4afb548850e (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
// SPDX-License-Identifier: GPL-2.0
#include <errno.h>
#include <inttypes.h>
#include <math.h>
#include <string.h>
#include "counts.h"
#include "cpumap.h"
#include "debug.h"
#include "header.h"
#include "stat.h"
#include "session.h"
#include "target.h"
#include "evlist.h"
#include "evsel.h"
#include "thread_map.h"
#include "hashmap.h"
#include <linux/zalloc.h>

void update_stats(struct stats *stats, u64 val)
{
	double delta;

	stats->n++;
	delta = val - stats->mean;
	stats->mean += delta / stats->n;
	stats->M2 += delta*(val - stats->mean);

	if (val > stats->max)
		stats->max = val;

	if (val < stats->min)
		stats->min = val;
}

double avg_stats(struct stats *stats)
{
	return stats->mean;
}

/*
 * http://en.wikipedia.org/wiki/Algorithms_for_calculating_variance
 *
 *       (\Sum n_i^2) - ((\Sum n_i)^2)/n
 * s^2 = -------------------------------
 *                  n - 1
 *
 * http://en.wikipedia.org/wiki/Stddev
 *
 * The std dev of the mean is related to the std dev by:
 *
 *             s
 * s_mean = -------
 *          sqrt(n)
 *
 */
double stddev_stats(struct stats *stats)
{
	double variance, variance_mean;

	if (stats->n < 2)
		return 0.0;

	variance = stats->M2 / (stats->n - 1);
	variance_mean = variance / stats->n;

	return sqrt(variance_mean);
}

double rel_stddev_stats(double stddev, double avg)
{
	double pct = 0.0;

	if (avg)
		pct = 100.0 * stddev/avg;

	return pct;
}

bool __perf_stat_evsel__is(struct evsel *evsel, enum perf_stat_evsel_id id)
{
	struct perf_stat_evsel *ps = evsel->stats;

	return ps->id == id;
}

#define ID(id, name) [PERF_STAT_EVSEL_ID__##id] = #name
static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
	ID(NONE,		x),
	ID(CYCLES_IN_TX,	cpu/cycles-t/),
	ID(TRANSACTION_START,	cpu/tx-start/),
	ID(ELISION_START,	cpu/el-start/),
	ID(CYCLES_IN_TX_CP,	cpu/cycles-ct/),
	ID(TOPDOWN_TOTAL_SLOTS, topdown-total-slots),
	ID(TOPDOWN_SLOTS_ISSUED, topdown-slots-issued),
	ID(TOPDOWN_SLOTS_RETIRED, topdown-slots-retired),
	ID(TOPDOWN_FETCH_BUBBLES, topdown-fetch-bubbles),
	ID(TOPDOWN_RECOVERY_BUBBLES, topdown-recovery-bubbles),
	ID(TOPDOWN_RETIRING, topdown-retiring),
	ID(TOPDOWN_BAD_SPEC, topdown-bad-spec),
	ID(TOPDOWN_FE_BOUND, topdown-fe-bound),
	ID(TOPDOWN_BE_BOUND, topdown-be-bound),
	ID(TOPDOWN_HEAVY_OPS, topdown-heavy-ops),
	ID(TOPDOWN_BR_MISPREDICT, topdown-br-mispredict),
	ID(TOPDOWN_FETCH_LAT, topdown-fetch-lat),
	ID(TOPDOWN_MEM_BOUND, topdown-mem-bound),
	ID(SMI_NUM, msr/smi/),
	ID(APERF, msr/aperf/),
};
#undef ID

static void perf_stat_evsel_id_init(struct evsel *evsel)
{
	struct perf_stat_evsel *ps = evsel->stats;
	int i;

	/* ps->id is 0 hence PERF_STAT_EVSEL_ID__NONE by default */

	for (i = 0; i < PERF_STAT_EVSEL_ID__MAX; i++) {
		if (!strcmp(evsel__name(evsel), id_str[i])) {
			ps->id = i;
			break;
		}
	}
}

static void evsel__reset_stat_priv(struct evsel *evsel)
{
	int i;
	struct perf_stat_evsel *ps = evsel->stats;

	for (i = 0; i < 3; i++)
		init_stats(&ps->res_stats[i]);

	perf_stat_evsel_id_init(evsel);
}

static int evsel__alloc_stat_priv(struct evsel *evsel)
{
	evsel->stats = zalloc(sizeof(struct perf_stat_evsel));
	if (evsel->stats == NULL)
		return -ENOMEM;
	evsel__reset_stat_priv(evsel);
	return 0;
}

static void evsel__free_stat_priv(struct evsel *evsel)
{
	struct perf_stat_evsel *ps = evsel->stats;

	if (ps)
		zfree(&ps->group_data);
	zfree(&evsel->stats);
}

static int evsel__alloc_prev_raw_counts(struct evsel *evsel)
{
	int cpu_map_nr = evsel__nr_cpus(evsel);
	int nthreads = perf_thread_map__nr(evsel->core.threads);
	struct perf_counts *counts;

	counts = perf_counts__new(cpu_map_nr, nthreads);
	if (counts)
		evsel->prev_raw_counts = counts;

	return counts ? 0 : -ENOMEM;
}

static void evsel__free_prev_raw_counts(struct evsel *evsel)
{
	perf_counts__delete(evsel->prev_raw_counts);
	evsel->prev_raw_counts = NULL;
}

static void evsel__reset_prev_raw_counts(struct evsel *evsel)
{
	if (evsel->prev_raw_counts)
		perf_counts__reset(evsel->prev_raw_counts);
}

static int evsel__alloc_stats(struct evsel *evsel, bool alloc_raw)
{
	if (evsel__alloc_stat_priv(evsel) < 0 ||
	    evsel__alloc_counts(evsel) < 0 ||
	    (alloc_raw && evsel__alloc_prev_raw_counts(evsel) < 0))
		return -ENOMEM;

	return 0;
}

int evlist__alloc_stats(struct evlist *evlist, bool alloc_raw)
{
	struct evsel *evsel;

	evlist__for_each_entry(evlist, evsel) {
		if (evsel__alloc_stats(evsel, alloc_raw))
			goto out_free;
	}

	return 0;

out_free:
	evlist__free_stats(evlist);
	return -1;
}

void evlist__free_stats(struct evlist *evlist)
{
	struct evsel *evsel;

	evlist__for_each_entry(evlist, evsel) {
		evsel__free_stat_priv(evsel);
		evsel__free_counts(evsel);
		evsel__free_prev_raw_counts(evsel);
	}
}

void evlist__reset_stats(struct evlist *evlist)
{
	struct evsel *evsel;

	evlist__for_each_entry(evlist, evsel) {
		evsel__reset_stat_priv(evsel);
		evsel__reset_counts(evsel);
	}
}

void evlist__reset_prev_raw_counts(struct evlist *evlist)
{
	struct evsel *evsel;

	evlist__for_each_entry(evlist, evsel)
		evsel__reset_prev_raw_counts(evsel);
}

static void evsel__copy_prev_raw_counts(struct evsel *evsel)
{
	int ncpus = evsel__nr_cpus(evsel);
	int nthreads = perf_thread_map__nr(evsel->core.threads);

	for (int thread = 0; thread < nthreads; thread++) {
		for (int cpu = 0; cpu < ncpus; cpu++) {
			*perf_counts(evsel->counts, cpu, thread) =
				*perf_counts(evsel->prev_raw_counts, cpu,
					     thread);
		}
	}

	evsel->counts->aggr = evsel->prev_raw_counts->aggr;
}

void evlist__copy_prev_raw_counts(struct evlist *evlist)
{
	struct evsel *evsel;

	evlist__for_each_entry(evlist, evsel)
		evsel__copy_prev_raw_counts(evsel);
}

void evlist__save_aggr_prev_raw_counts(struct evlist *evlist)
{
	struct evsel *evsel;

	/*
	 * To collect the overall statistics for interval mode,
	 * we copy the counts from evsel->prev_raw_counts to
	 * evsel->counts. The perf_stat_process_counter creates
	 * aggr values from per cpu values, but the per cpu values
	 * are 0 for AGGR_GLOBAL. So we use a trick that saves the
	 * previous aggr value to the first member of perf_counts,
	 * then aggr calculation in process_counter_values can work
	 * correctly.
	 */
	evlist__for_each_entry(evlist, evsel) {
		*perf_counts(evsel->prev_raw_counts, 0, 0) =
			evsel->prev_raw_counts->aggr;
	}
}

static size_t pkg_id_hash(const void *__key, void *ctx __maybe_unused)
{
	uint64_t *key = (uint64_t *) __key;

	return *key & 0xffffffff;
}

static bool pkg_id_equal(const void *__key1, const void *__key2,
			 void *ctx __maybe_unused)
{
	uint64_t *key1 = (uint64_t *) __key1;
	uint64_t *key2 = (uint64_t *) __key2;

	return *key1 == *key2;
}

static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals,
			 int cpu_map_idx, bool *skip)
{
	struct hashmap *mask = counter->per_pkg_mask;
	struct perf_cpu_map *cpus = evsel__cpus(counter);
	struct perf_cpu cpu = perf_cpu_map__cpu(cpus, cpu_map_idx);
	int s, d, ret = 0;
	uint64_t *key;

	*skip = false;

	if (!counter->per_pkg)
		return 0;

	if (perf_cpu_map__empty(cpus))
		return 0;

	if (!mask) {
		mask = hashmap__new(pkg_id_hash, pkg_id_equal, NULL);
		if (!mask)
			return -ENOMEM;

		counter->per_pkg_mask = mask;
	}

	/*
	 * we do not consider an event that has not run as a good
	 * instance to mark a package as used (skip=1). Otherwise
	 * we may run into a situation where the first CPU in a package
	 * is not running anything, yet the second is, and this function
	 * would mark the package as used after the first CPU and would
	 * not read the values from the second CPU.
	 */
	if (!(vals->run && vals->ena))
		return 0;

	s = cpu__get_socket_id(cpu);
	if (s < 0)
		return -1;

	/*
	 * On multi-die system, die_id > 0. On no-die system, die_id = 0.
	 * We use hashmap(socket, die) to check the used socket+die pair.
	 */
	d = cpu__get_die_id(cpu);
	if (d < 0)
		return -1;

	key = malloc(sizeof(*key));
	if (!key)
		return -ENOMEM;

	*key = (uint64_t)d << 32 | s;
	if (hashmap__find(mask, (void *)key, NULL)) {
		*skip = true;
		free(key);
	} else
		ret = hashmap__add(mask, (void *)key, (void *)1);

	return ret;
}

static int
process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
		       int cpu_map_idx, int thread,
		       struct perf_counts_values *count)
{
	struct perf_counts_values *aggr = &evsel->counts->aggr;
	static struct perf_counts_values zero;
	bool skip = false;

	if (check_per_pkg(evsel, count, cpu_map_idx, &skip)) {
		pr_err("failed to read per-pkg counter\n");
		return -1;
	}

	if (skip)
		count = &zero;

	switch (config->aggr_mode) {
	case AGGR_THREAD:
	case AGGR_CORE:
	case AGGR_DIE:
	case AGGR_SOCKET:
	case AGGR_NODE:
	case AGGR_NONE:
		if (!evsel->snapshot)
			evsel__compute_deltas(evsel, cpu_map_idx, thread, count);
		perf_counts_values__scale(count, config->scale, NULL);
		if ((config->aggr_mode == AGGR_NONE) && (!evsel->percore)) {
			perf_stat__update_shadow_stats(evsel, count->val,
						       cpu_map_idx, &rt_stat);
		}

		if (config->aggr_mode == AGGR_THREAD) {
			if (config->stats)
				perf_stat__update_shadow_stats(evsel,
					count->val, 0, &config->stats[thread]);
			else
				perf_stat__update_shadow_stats(evsel,
					count->val, 0, &rt_stat);
		}
		break;
	case AGGR_GLOBAL:
		aggr->val += count->val;
		aggr->ena += count->ena;
		aggr->run += count->run;
	case AGGR_UNSET:
	default:
		break;
	}

	return 0;
}

static int process_counter_maps(struct perf_stat_config *config,
				struct evsel *counter)
{
	int nthreads = perf_thread_map__nr(counter->core.threads);
	int ncpus = evsel__nr_cpus(counter);
	int idx, thread;

	if (counter->core.system_wide)
		nthreads = 1;

	for (thread = 0; thread < nthreads; thread++) {
		for (idx = 0; idx < ncpus; idx++) {
			if (process_counter_values(config, counter, idx, thread,
						   perf_counts(counter->counts, idx, thread)))
				return -1;
		}
	}

	return 0;
}

int perf_stat_process_counter(struct perf_stat_config *config,
			      struct evsel *counter)
{
	struct perf_counts_values *aggr = &counter->counts->aggr;
	struct perf_stat_evsel *ps = counter->stats;
	u64 *count = counter->counts->aggr.values;
	int i, ret;

	aggr->val = aggr->ena = aggr->run = 0;

	if (counter->per_pkg)
		evsel__zero_per_pkg(counter);

	ret = process_counter_maps(config, counter);
	if (ret)
		return ret;

	if (config->aggr_mode != AGGR_GLOBAL)
		return 0;

	if (!counter->snapshot)
		evsel__compute_deltas(counter, -1, -1, aggr);
	perf_counts_values__scale(aggr, config->scale, &counter->counts->scaled);

	for (i = 0; i < 3; i++)
		update_stats(&ps->res_stats[i], count[i]);

	if (verbose > 0) {
		fprintf(config->output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
			evsel__name(counter), count[0], count[1], count[2]);
	}

	/*
	 * Save the full runtime - to allow normalization during printout:
	 */
	perf_stat__update_shadow_stats(counter, *count, 0, &rt_stat);

	return 0;
}

int perf_event__process_stat_event(struct perf_session *session,
				   union perf_event *event)
{
	struct perf_counts_values count;
	struct perf_record_stat *st = &event->stat;
	struct evsel *counter;

	count.val = st->val;
	count.ena = st->ena;
	count.run = st->run;

	counter = evlist__id2evsel(session->evlist, st->id);
	if (!counter) {
		pr_err("Failed to resolve counter for stat event.\n");
		return -EINVAL;
	}

	*perf_counts(counter->counts, st->cpu, st->thread) = count;
	counter->supported = true;
	return 0;
}

size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp)
{
	struct perf_record_stat *st = (struct perf_record_stat *)event;
	size_t ret;

	ret  = fprintf(fp, "\n... id %" PRI_lu64 ", cpu %d, thread %d\n",
		       st->id, st->cpu, st->thread);
	ret += fprintf(fp, "... value %" PRI_lu64 ", enabled %" PRI_lu64 ", running %" PRI_lu64 "\n",
		       st->val, st->ena, st->run);

	return ret;
}

size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp)
{
	struct perf_record_stat_round *rd = (struct perf_record_stat_round *)event;
	size_t ret;

	ret = fprintf(fp, "\n... time %" PRI_lu64 ", type %s\n", rd->time,
		      rd->type == PERF_STAT_ROUND_TYPE__FINAL ? "FINAL" : "INTERVAL");

	return ret;
}

size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp)
{
	struct perf_stat_config sc;
	size_t ret;

	perf_event__read_stat_config(&sc, &event->stat_config);

	ret  = fprintf(fp, "\n");
	ret += fprintf(fp, "... aggr_mode %d\n", sc.aggr_mode);
	ret += fprintf(fp, "... scale     %d\n", sc.scale);
	ret += fprintf(fp, "... interval  %u\n", sc.interval);

	return ret;
}

int create_perf_stat_counter(struct evsel *evsel,
			     struct perf_stat_config *config,
			     struct target *target,
			     int cpu_map_idx)
{
	struct perf_event_attr *attr = &evsel->core.attr;
	struct evsel *leader = evsel__leader(evsel);

	attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
			    PERF_FORMAT_TOTAL_TIME_RUNNING;

	/*
	 * The event is part of non trivial group, let's enable
	 * the group read (for leader) and ID retrieval for all
	 * members.
	 */
	if (leader->core.nr_members > 1)
		attr->read_format |= PERF_FORMAT_ID|PERF_FORMAT_GROUP;

	attr->inherit = !config->no_inherit && list_empty(&evsel->bpf_counter_list);

	/*
	 * Some events get initialized with sample_(period/type) set,
	 * like tracepoints. Clear it up for counting.
	 */
	attr->sample_period = 0;

	if (config->identifier)
		attr->sample_type = PERF_SAMPLE_IDENTIFIER;

	if (config->all_user) {
		attr->exclude_kernel = 1;
		attr->exclude_user   = 0;
	}

	if (config->all_kernel) {
		attr->exclude_kernel = 0;
		attr->exclude_user   = 1;
	}

	/*
	 * Disabling all counters initially, they will be enabled
	 * either manually by us or by kernel via enable_on_exec
	 * set later.
	 */
	if (evsel__is_group_leader(evsel)) {
		attr->disabled = 1;

		/*
		 * In case of initial_delay we enable tracee
		 * events manually.
		 */
		if (target__none(target) && !config->initial_delay)
			attr->enable_on_exec = 1;
	}

	if (target__has_cpu(target) && !target__has_per_thread(target))
		return evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu_map_idx);

	return evsel__open_per_thread(evsel, evsel->core.threads);
}