evsel.c 53.8 KB
Newer Older
1 2 3 4 5 6 7 8 9
/*
 * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
 *
 * Parts came from builtin-{top,stat,record}.c, see those files for further
 * copyright notes.
 *
 * Released under the GPL v2. (and only v2, not any later version)
 */

10
#include <byteswap.h>
11
#include <linux/bitops.h>
12
#include <api/fs/debugfs.h>
13 14 15
#include <traceevent/event-parse.h>
#include <linux/hw_breakpoint.h>
#include <linux/perf_event.h>
16
#include <sys/resource.h>
17
#include "asm/bug.h"
18
#include "callchain.h"
19
#include "cgroup.h"
20
#include "evsel.h"
21
#include "evlist.h"
22
#include "util.h"
23
#include "cpumap.h"
24
#include "thread_map.h"
25
#include "target.h"
26
#include "perf_regs.h"
A
Adrian Hunter 已提交
27
#include "debug.h"
28
#include "trace-event.h"
29
#include "stat.h"
30

31 32 33
static struct {
	bool sample_id_all;
	bool exclude_guest;
34
	bool mmap2;
35
	bool cloexec;
36 37
	bool clockid;
	bool clockid_wrong;
38 39
} perf_missing_features;

40 41
static clockid_t clockid;

A
Arnaldo Carvalho de Melo 已提交
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
static int perf_evsel__no_extra_init(struct perf_evsel *evsel __maybe_unused)
{
	return 0;
}

static void perf_evsel__no_extra_fini(struct perf_evsel *evsel __maybe_unused)
{
}

static struct {
	size_t	size;
	int	(*init)(struct perf_evsel *evsel);
	void	(*fini)(struct perf_evsel *evsel);
} perf_evsel__object = {
	.size = sizeof(struct perf_evsel),
	.init = perf_evsel__no_extra_init,
	.fini = perf_evsel__no_extra_fini,
};

int perf_evsel__object_config(size_t object_size,
			      int (*init)(struct perf_evsel *evsel),
			      void (*fini)(struct perf_evsel *evsel))
{

	if (object_size == 0)
		goto set_methods;

	if (perf_evsel__object.size > object_size)
		return -EINVAL;

	perf_evsel__object.size = object_size;

set_methods:
	if (init != NULL)
		perf_evsel__object.init = init;

	if (fini != NULL)
		perf_evsel__object.fini = fini;

	return 0;
}

84 85
#define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))

86
int __perf_evsel__sample_size(u64 sample_type)
87 88 89 90 91 92 93 94 95 96 97 98 99 100 101
{
	u64 mask = sample_type & PERF_SAMPLE_MASK;
	int size = 0;
	int i;

	for (i = 0; i < 64; i++) {
		if (mask & (1ULL << i))
			size++;
	}

	size *= sizeof(u64);

	return size;
}

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
/**
 * __perf_evsel__calc_id_pos - calculate id_pos.
 * @sample_type: sample type
 *
 * This function returns the position of the event id (PERF_SAMPLE_ID or
 * PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of struct
 * sample_event.
 */
static int __perf_evsel__calc_id_pos(u64 sample_type)
{
	int idx = 0;

	if (sample_type & PERF_SAMPLE_IDENTIFIER)
		return 0;

	if (!(sample_type & PERF_SAMPLE_ID))
		return -1;

	if (sample_type & PERF_SAMPLE_IP)
		idx += 1;

	if (sample_type & PERF_SAMPLE_TID)
		idx += 1;

	if (sample_type & PERF_SAMPLE_TIME)
		idx += 1;

	if (sample_type & PERF_SAMPLE_ADDR)
		idx += 1;

	return idx;
}

/**
 * __perf_evsel__calc_is_pos - calculate is_pos.
 * @sample_type: sample type
 *
 * This function returns the position (counting backwards) of the event id
 * (PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if
 * sample_id_all is used there is an id sample appended to non-sample events.
 */
static int __perf_evsel__calc_is_pos(u64 sample_type)
{
	int idx = 1;

	if (sample_type & PERF_SAMPLE_IDENTIFIER)
		return 1;

	if (!(sample_type & PERF_SAMPLE_ID))
		return -1;

	if (sample_type & PERF_SAMPLE_CPU)
		idx += 1;

	if (sample_type & PERF_SAMPLE_STREAM_ID)
		idx += 1;

	return idx;
}

void perf_evsel__calc_id_pos(struct perf_evsel *evsel)
{
	evsel->id_pos = __perf_evsel__calc_id_pos(evsel->attr.sample_type);
	evsel->is_pos = __perf_evsel__calc_is_pos(evsel->attr.sample_type);
}

168 169 170 171 172 173
void __perf_evsel__set_sample_bit(struct perf_evsel *evsel,
				  enum perf_event_sample_format bit)
{
	if (!(evsel->attr.sample_type & bit)) {
		evsel->attr.sample_type |= bit;
		evsel->sample_size += sizeof(u64);
174
		perf_evsel__calc_id_pos(evsel);
175 176 177 178 179 180 181 182 183
	}
}

void __perf_evsel__reset_sample_bit(struct perf_evsel *evsel,
				    enum perf_event_sample_format bit)
{
	if (evsel->attr.sample_type & bit) {
		evsel->attr.sample_type &= ~bit;
		evsel->sample_size -= sizeof(u64);
184
		perf_evsel__calc_id_pos(evsel);
185 186 187
	}
}

188 189
void perf_evsel__set_sample_id(struct perf_evsel *evsel,
			       bool can_sample_identifier)
190
{
191 192 193 194 195 196
	if (can_sample_identifier) {
		perf_evsel__reset_sample_bit(evsel, ID);
		perf_evsel__set_sample_bit(evsel, IDENTIFIER);
	} else {
		perf_evsel__set_sample_bit(evsel, ID);
	}
197 198 199
	evsel->attr.read_format |= PERF_FORMAT_ID;
}

200 201 202 203
void perf_evsel__init(struct perf_evsel *evsel,
		      struct perf_event_attr *attr, int idx)
{
	evsel->idx	   = idx;
204
	evsel->tracking	   = !idx;
205
	evsel->attr	   = *attr;
206
	evsel->leader	   = evsel;
207 208
	evsel->unit	   = "";
	evsel->scale	   = 1.0;
209
	INIT_LIST_HEAD(&evsel->node);
210
	INIT_LIST_HEAD(&evsel->config_terms);
A
Arnaldo Carvalho de Melo 已提交
211
	perf_evsel__object.init(evsel);
212
	evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
213
	perf_evsel__calc_id_pos(evsel);
214
	evsel->cmdline_group_boundary = false;
215 216
}

217
struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
218
{
A
Arnaldo Carvalho de Melo 已提交
219
	struct perf_evsel *evsel = zalloc(perf_evsel__object.size);
220

221 222
	if (evsel != NULL)
		perf_evsel__init(evsel, attr, idx);
223 224 225 226

	return evsel;
}

227
struct perf_evsel *perf_evsel__newtp_idx(const char *sys, const char *name, int idx)
228
{
A
Arnaldo Carvalho de Melo 已提交
229
	struct perf_evsel *evsel = zalloc(perf_evsel__object.size);
230 231 232

	if (evsel != NULL) {
		struct perf_event_attr attr = {
233 234 235
			.type	       = PERF_TYPE_TRACEPOINT,
			.sample_type   = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME |
					  PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD),
236 237
		};

238 239 240
		if (asprintf(&evsel->name, "%s:%s", sys, name) < 0)
			goto out_free;

241
		evsel->tp_format = trace_event__tp_format(sys, name);
242 243 244
		if (evsel->tp_format == NULL)
			goto out_free;

245
		event_attr_init(&attr);
246
		attr.config = evsel->tp_format->id;
247
		attr.sample_period = 1;
248 249 250 251 252 253
		perf_evsel__init(evsel, &attr, idx);
	}

	return evsel;

out_free:
254
	zfree(&evsel->name);
255 256 257 258
	free(evsel);
	return NULL;
}

259
const char *perf_evsel__hw_names[PERF_COUNT_HW_MAX] = {
260 261 262 263 264 265 266 267 268 269 270 271
	"cycles",
	"instructions",
	"cache-references",
	"cache-misses",
	"branches",
	"branch-misses",
	"bus-cycles",
	"stalled-cycles-frontend",
	"stalled-cycles-backend",
	"ref-cycles",
};

272
static const char *__perf_evsel__hw_name(u64 config)
273 274 275 276 277 278 279
{
	if (config < PERF_COUNT_HW_MAX && perf_evsel__hw_names[config])
		return perf_evsel__hw_names[config];

	return "unknown-hardware";
}

280
static int perf_evsel__add_modifiers(struct perf_evsel *evsel, char *bf, size_t size)
281
{
282
	int colon = 0, r = 0;
283 284 285 286 287
	struct perf_event_attr *attr = &evsel->attr;
	bool exclude_guest_default = false;

#define MOD_PRINT(context, mod)	do {					\
		if (!attr->exclude_##context) {				\
288
			if (!colon) colon = ++r;			\
289 290 291 292 293 294 295 296 297 298 299 300
			r += scnprintf(bf + r, size - r, "%c", mod);	\
		} } while(0)

	if (attr->exclude_kernel || attr->exclude_user || attr->exclude_hv) {
		MOD_PRINT(kernel, 'k');
		MOD_PRINT(user, 'u');
		MOD_PRINT(hv, 'h');
		exclude_guest_default = true;
	}

	if (attr->precise_ip) {
		if (!colon)
301
			colon = ++r;
302 303 304 305 306 307 308 309 310 311
		r += scnprintf(bf + r, size - r, "%.*s", attr->precise_ip, "ppp");
		exclude_guest_default = true;
	}

	if (attr->exclude_host || attr->exclude_guest == exclude_guest_default) {
		MOD_PRINT(host, 'H');
		MOD_PRINT(guest, 'G');
	}
#undef MOD_PRINT
	if (colon)
312
		bf[colon - 1] = ':';
313 314 315
	return r;
}

316 317 318 319 320 321
static int perf_evsel__hw_name(struct perf_evsel *evsel, char *bf, size_t size)
{
	int r = scnprintf(bf, size, "%s", __perf_evsel__hw_name(evsel->attr.config));
	return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
}

322
const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX] = {
323 324 325 326
	"cpu-clock",
	"task-clock",
	"page-faults",
	"context-switches",
327
	"cpu-migrations",
328 329 330 331
	"minor-faults",
	"major-faults",
	"alignment-faults",
	"emulation-faults",
332
	"dummy",
333 334
};

335
static const char *__perf_evsel__sw_name(u64 config)
336 337 338 339 340 341 342 343 344 345 346 347
{
	if (config < PERF_COUNT_SW_MAX && perf_evsel__sw_names[config])
		return perf_evsel__sw_names[config];
	return "unknown-software";
}

static int perf_evsel__sw_name(struct perf_evsel *evsel, char *bf, size_t size)
{
	int r = scnprintf(bf, size, "%s", __perf_evsel__sw_name(evsel->attr.config));
	return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
}

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
static int __perf_evsel__bp_name(char *bf, size_t size, u64 addr, u64 type)
{
	int r;

	r = scnprintf(bf, size, "mem:0x%" PRIx64 ":", addr);

	if (type & HW_BREAKPOINT_R)
		r += scnprintf(bf + r, size - r, "r");

	if (type & HW_BREAKPOINT_W)
		r += scnprintf(bf + r, size - r, "w");

	if (type & HW_BREAKPOINT_X)
		r += scnprintf(bf + r, size - r, "x");

	return r;
}

static int perf_evsel__bp_name(struct perf_evsel *evsel, char *bf, size_t size)
{
	struct perf_event_attr *attr = &evsel->attr;
	int r = __perf_evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type);
	return r + perf_evsel__add_modifiers(evsel, bf + r, size - r);
}

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
const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX]
				[PERF_EVSEL__MAX_ALIASES] = {
 { "L1-dcache",	"l1-d",		"l1d",		"L1-data",		},
 { "L1-icache",	"l1-i",		"l1i",		"L1-instruction",	},
 { "LLC",	"L2",							},
 { "dTLB",	"d-tlb",	"Data-TLB",				},
 { "iTLB",	"i-tlb",	"Instruction-TLB",			},
 { "branch",	"branches",	"bpu",		"btb",		"bpc",	},
 { "node",								},
};

const char *perf_evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX]
				   [PERF_EVSEL__MAX_ALIASES] = {
 { "load",	"loads",	"read",					},
 { "store",	"stores",	"write",				},
 { "prefetch",	"prefetches",	"speculative-read", "speculative-load",	},
};

const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX]
				       [PERF_EVSEL__MAX_ALIASES] = {
 { "refs",	"Reference",	"ops",		"access",		},
 { "misses",	"miss",							},
};

#define C(x)		PERF_COUNT_HW_CACHE_##x
#define CACHE_READ	(1 << C(OP_READ))
#define CACHE_WRITE	(1 << C(OP_WRITE))
#define CACHE_PREFETCH	(1 << C(OP_PREFETCH))
#define COP(x)		(1 << x)

/*
 * cache operartion stat
 * L1I : Read and prefetch only
 * ITLB and BPU : Read-only
 */
static unsigned long perf_evsel__hw_cache_stat[C(MAX)] = {
 [C(L1D)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
 [C(L1I)]	= (CACHE_READ | CACHE_PREFETCH),
 [C(LL)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
 [C(DTLB)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
 [C(ITLB)]	= (CACHE_READ),
 [C(BPU)]	= (CACHE_READ),
 [C(NODE)]	= (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH),
};

bool perf_evsel__is_cache_op_valid(u8 type, u8 op)
{
	if (perf_evsel__hw_cache_stat[type] & COP(op))
		return true;	/* valid */
	else
		return false;	/* invalid */
}

int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
					    char *bf, size_t size)
{
	if (result) {
		return scnprintf(bf, size, "%s-%s-%s", perf_evsel__hw_cache[type][0],
				 perf_evsel__hw_cache_op[op][0],
				 perf_evsel__hw_cache_result[result][0]);
	}

	return scnprintf(bf, size, "%s-%s", perf_evsel__hw_cache[type][0],
			 perf_evsel__hw_cache_op[op][1]);
}

439
static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size)
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
{
	u8 op, result, type = (config >>  0) & 0xff;
	const char *err = "unknown-ext-hardware-cache-type";

	if (type > PERF_COUNT_HW_CACHE_MAX)
		goto out_err;

	op = (config >>  8) & 0xff;
	err = "unknown-ext-hardware-cache-op";
	if (op > PERF_COUNT_HW_CACHE_OP_MAX)
		goto out_err;

	result = (config >> 16) & 0xff;
	err = "unknown-ext-hardware-cache-result";
	if (result > PERF_COUNT_HW_CACHE_RESULT_MAX)
		goto out_err;

	err = "invalid-cache";
	if (!perf_evsel__is_cache_op_valid(type, op))
		goto out_err;

	return __perf_evsel__hw_cache_type_op_res_name(type, op, result, bf, size);
out_err:
	return scnprintf(bf, size, "%s", err);
}

static int perf_evsel__hw_cache_name(struct perf_evsel *evsel, char *bf, size_t size)
{
	int ret = __perf_evsel__hw_cache_name(evsel->attr.config, bf, size);
	return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
}

472 473 474 475 476 477
static int perf_evsel__raw_name(struct perf_evsel *evsel, char *bf, size_t size)
{
	int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->attr.config);
	return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
}

478
const char *perf_evsel__name(struct perf_evsel *evsel)
479
{
480
	char bf[128];
481

482 483
	if (evsel->name)
		return evsel->name;
484 485 486

	switch (evsel->attr.type) {
	case PERF_TYPE_RAW:
487
		perf_evsel__raw_name(evsel, bf, sizeof(bf));
488 489 490
		break;

	case PERF_TYPE_HARDWARE:
491
		perf_evsel__hw_name(evsel, bf, sizeof(bf));
492
		break;
493 494

	case PERF_TYPE_HW_CACHE:
495
		perf_evsel__hw_cache_name(evsel, bf, sizeof(bf));
496 497
		break;

498
	case PERF_TYPE_SOFTWARE:
499
		perf_evsel__sw_name(evsel, bf, sizeof(bf));
500 501
		break;

502
	case PERF_TYPE_TRACEPOINT:
503
		scnprintf(bf, sizeof(bf), "%s", "unknown tracepoint");
504 505
		break;

506 507 508 509
	case PERF_TYPE_BREAKPOINT:
		perf_evsel__bp_name(evsel, bf, sizeof(bf));
		break;

510
	default:
511 512
		scnprintf(bf, sizeof(bf), "unknown attr type: %d",
			  evsel->attr.type);
513
		break;
514 515
	}

516 517 518
	evsel->name = strdup(bf);

	return evsel->name ?: "unknown";
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
const char *perf_evsel__group_name(struct perf_evsel *evsel)
{
	return evsel->group_name ?: "anon group";
}

int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
{
	int ret;
	struct perf_evsel *pos;
	const char *group_name = perf_evsel__group_name(evsel);

	ret = scnprintf(buf, size, "%s", group_name);

	ret += scnprintf(buf + ret, size - ret, " { %s",
			 perf_evsel__name(evsel));

	for_each_group_member(pos, evsel)
		ret += scnprintf(buf + ret, size - ret, ", %s",
				 perf_evsel__name(pos));

	ret += scnprintf(buf + ret, size - ret, " }");

	return ret;
}

546
static void
547
perf_evsel__config_callgraph(struct perf_evsel *evsel,
548 549
			     struct record_opts *opts,
			     struct callchain_param *param)
550 551 552 553 554 555
{
	bool function = perf_evsel__is_function_event(evsel);
	struct perf_event_attr *attr = &evsel->attr;

	perf_evsel__set_sample_bit(evsel, CALLCHAIN);

556
	if (param->record_mode == CALLCHAIN_LBR) {
557 558 559 560 561 562 563 564 565 566 567 568 569 570 571
		if (!opts->branch_stack) {
			if (attr->exclude_user) {
				pr_warning("LBR callstack option is only available "
					   "to get user callchain information. "
					   "Falling back to framepointers.\n");
			} else {
				perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
				attr->branch_sample_type = PERF_SAMPLE_BRANCH_USER |
							PERF_SAMPLE_BRANCH_CALL_STACK;
			}
		} else
			 pr_warning("Cannot use LBR callstack with branch stack. "
				    "Falling back to framepointers.\n");
	}

572
	if (param->record_mode == CALLCHAIN_DWARF) {
573 574 575 576
		if (!function) {
			perf_evsel__set_sample_bit(evsel, REGS_USER);
			perf_evsel__set_sample_bit(evsel, STACK_USER);
			attr->sample_regs_user = PERF_REGS_MASK;
577
			attr->sample_stack_user = param->dump_size;
578 579 580 581 582 583 584 585 586 587 588 589 590
			attr->exclude_callchain_user = 1;
		} else {
			pr_info("Cannot use DWARF unwind for function trace event,"
				" falling back to framepointers.\n");
		}
	}

	if (function) {
		pr_info("Disabling user space callchains for function trace event.\n");
		attr->exclude_callchain_user = 1;
	}
}

K
Kan Liang 已提交
591
static void apply_config_terms(struct perf_evsel *evsel)
592 593
{
	struct perf_evsel_config_term *term;
K
Kan Liang 已提交
594 595
	struct list_head *config_terms = &evsel->config_terms;
	struct perf_event_attr *attr = &evsel->attr;
596 597 598

	list_for_each_entry(term, config_terms, list) {
		switch (term->type) {
599 600
		case PERF_EVSEL__CONFIG_TERM_PERIOD:
			attr->sample_period = term->val.period;
601
			attr->freq = 0;
K
Kan Liang 已提交
602 603 604 605 606 607 608
			break;
		case PERF_EVSEL__CONFIG_TERM_TIME:
			if (term->val.time)
				perf_evsel__set_sample_bit(evsel, TIME);
			else
				perf_evsel__reset_sample_bit(evsel, TIME);
			break;
609 610 611 612 613 614
		default:
			break;
		}
	}
}

615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642
/*
 * The enable_on_exec/disabled value strategy:
 *
 *  1) For any type of traced program:
 *    - all independent events and group leaders are disabled
 *    - all group members are enabled
 *
 *     Group members are ruled by group leaders. They need to
 *     be enabled, because the group scheduling relies on that.
 *
 *  2) For traced programs executed by perf:
 *     - all independent events and group leaders have
 *       enable_on_exec set
 *     - we don't specifically enable or disable any event during
 *       the record command
 *
 *     Independent events and group leaders are initially disabled
 *     and get enabled by exec. Group members are ruled by group
 *     leaders as stated in 1).
 *
 *  3) For traced programs attached by perf (pid/tid):
 *     - we specifically enable or disable all events during
 *       the record command
 *
 *     When attaching events to already running traced we
 *     enable/disable events specifically, as there's no
 *     initial traced exec call.
 */
643
void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
644
{
645
	struct perf_evsel *leader = evsel->leader;
646
	struct perf_event_attr *attr = &evsel->attr;
647
	int track = evsel->tracking;
648
	bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread;
649

650
	attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
651 652
	attr->inherit	    = !opts->no_inherit;

653 654
	perf_evsel__set_sample_bit(evsel, IP);
	perf_evsel__set_sample_bit(evsel, TID);
655

656 657 658 659 660 661 662
	if (evsel->sample_read) {
		perf_evsel__set_sample_bit(evsel, READ);

		/*
		 * We need ID even in case of single event, because
		 * PERF_SAMPLE_READ process ID specific data.
		 */
663
		perf_evsel__set_sample_id(evsel, false);
664 665 666 667 668 669 670 671 672 673 674

		/*
		 * Apply group format only if we belong to group
		 * with more than one members.
		 */
		if (leader->nr_members > 1) {
			attr->read_format |= PERF_FORMAT_GROUP;
			attr->inherit = 0;
		}
	}

675
	/*
676
	 * We default some events to have a default interval. But keep
677 678
	 * it a weak assumption overridable by the user.
	 */
679
	if (!attr->sample_period || (opts->user_freq != UINT_MAX ||
680 681
				     opts->user_interval != ULLONG_MAX)) {
		if (opts->freq) {
682
			perf_evsel__set_sample_bit(evsel, PERIOD);
683 684 685 686 687 688 689
			attr->freq		= 1;
			attr->sample_freq	= opts->freq;
		} else {
			attr->sample_period = opts->default_interval;
		}
	}

690 691 692 693 694 695 696 697 698
	/*
	 * Disable sampling for all group members other
	 * than leader in case leader 'leads' the sampling.
	 */
	if ((leader != evsel) && leader->sample_read) {
		attr->sample_freq   = 0;
		attr->sample_period = 0;
	}

699 700 701 702 703 704 705
	if (opts->no_samples)
		attr->sample_freq = 0;

	if (opts->inherit_stat)
		attr->inherit_stat = 1;

	if (opts->sample_address) {
706
		perf_evsel__set_sample_bit(evsel, ADDR);
707 708 709
		attr->mmap_data = track;
	}

710 711 712 713 714 715 716 717
	/*
	 * We don't allow user space callchains for  function trace
	 * event, due to issues with page faults while tracing page
	 * fault handler and its overall trickiness nature.
	 */
	if (perf_evsel__is_function_event(evsel))
		evsel->attr.exclude_callchain_user = 1;

718
	if (callchain_param.enabled && !evsel->no_aux_samples)
719
		perf_evsel__config_callgraph(evsel, opts, &callchain_param);
720

721 722 723 724 725
	if (opts->sample_intr_regs) {
		attr->sample_regs_intr = PERF_REGS_MASK;
		perf_evsel__set_sample_bit(evsel, REGS_INTR);
	}

726
	if (target__has_cpu(&opts->target))
727
		perf_evsel__set_sample_bit(evsel, CPU);
728

729
	if (opts->period)
730
		perf_evsel__set_sample_bit(evsel, PERIOD);
731

732 733 734 735 736
	/*
	 * When the user explicitely disabled time don't force it here.
	 */
	if (opts->sample_time &&
	    (!perf_missing_features.sample_id_all &&
737 738
	    (!opts->no_inherit || target__has_cpu(&opts->target) || per_cpu ||
	     opts->sample_time_set)))
739
		perf_evsel__set_sample_bit(evsel, TIME);
740

741
	if (opts->raw_samples && !evsel->no_aux_samples) {
742 743 744
		perf_evsel__set_sample_bit(evsel, TIME);
		perf_evsel__set_sample_bit(evsel, RAW);
		perf_evsel__set_sample_bit(evsel, CPU);
745 746
	}

747
	if (opts->sample_address)
748
		perf_evsel__set_sample_bit(evsel, DATA_SRC);
749

750
	if (opts->no_buffering) {
751 752 753
		attr->watermark = 0;
		attr->wakeup_events = 1;
	}
754
	if (opts->branch_stack && !evsel->no_aux_samples) {
755
		perf_evsel__set_sample_bit(evsel, BRANCH_STACK);
756 757
		attr->branch_sample_type = opts->branch_stack;
	}
758

759
	if (opts->sample_weight)
760
		perf_evsel__set_sample_bit(evsel, WEIGHT);
761

762
	attr->task  = track;
763
	attr->mmap  = track;
764
	attr->mmap2 = track && !perf_missing_features.mmap2;
765
	attr->comm  = track;
766

767 768 769
	if (opts->record_switch_events)
		attr->context_switch = track;

770
	if (opts->sample_transaction)
771
		perf_evsel__set_sample_bit(evsel, TRANSACTION);
772

773 774 775 776 777 778
	if (opts->running_time) {
		evsel->attr.read_format |=
			PERF_FORMAT_TOTAL_TIME_ENABLED |
			PERF_FORMAT_TOTAL_TIME_RUNNING;
	}

779 780 781 782 783 784
	/*
	 * XXX see the function comment above
	 *
	 * Disabling only independent events or group leaders,
	 * keeping group members enabled.
	 */
785
	if (perf_evsel__is_group_leader(evsel))
786 787 788 789 790 791
		attr->disabled = 1;

	/*
	 * Setting enable_on_exec for independent events and
	 * group leaders for traced executed by perf.
	 */
792 793
	if (target__none(&opts->target) && perf_evsel__is_group_leader(evsel) &&
		!opts->initial_delay)
794
		attr->enable_on_exec = 1;
795 796 797 798 799

	if (evsel->immediate) {
		attr->disabled = 0;
		attr->enable_on_exec = 0;
	}
800 801 802 803 804 805

	clockid = opts->clockid;
	if (opts->use_clockid) {
		attr->use_clockid = 1;
		attr->clockid = opts->clockid;
	}
806 807 808 809 810

	/*
	 * Apply event specific term settings,
	 * it overloads any global configuration.
	 */
K
Kan Liang 已提交
811
	apply_config_terms(evsel);
812 813
}

814
static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
815
{
816
	int cpu, thread;
817 818 819 820

	if (evsel->system_wide)
		nthreads = 1;

821
	evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
822 823 824 825 826 827 828 829 830

	if (evsel->fd) {
		for (cpu = 0; cpu < ncpus; cpu++) {
			for (thread = 0; thread < nthreads; thread++) {
				FD(evsel, cpu, thread) = -1;
			}
		}
	}

831 832 833
	return evsel->fd != NULL ? 0 : -ENOMEM;
}

834 835
static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthreads,
			  int ioc,  void *arg)
836 837 838
{
	int cpu, thread;

839 840 841
	if (evsel->system_wide)
		nthreads = 1;

842 843 844
	for (cpu = 0; cpu < ncpus; cpu++) {
		for (thread = 0; thread < nthreads; thread++) {
			int fd = FD(evsel, cpu, thread),
845
			    err = ioctl(fd, ioc, arg);
846 847 848 849 850 851 852 853 854

			if (err)
				return err;
		}
	}

	return 0;
}

855 856
int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
			     const char *filter)
857 858 859 860 861 862
{
	return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
				     PERF_EVENT_IOC_SET_FILTER,
				     (void *)filter);
}

863 864 865 866 867 868 869 870 871 872 873 874 875
int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter)
{
	char *new_filter = strdup(filter);

	if (new_filter != NULL) {
		free(evsel->filter);
		evsel->filter = new_filter;
		return 0;
	}

	return -1;
}

876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892
int perf_evsel__append_filter(struct perf_evsel *evsel,
			      const char *op, const char *filter)
{
	char *new_filter;

	if (evsel->filter == NULL)
		return perf_evsel__set_filter(evsel, filter);

	if (asprintf(&new_filter,"(%s) %s (%s)", evsel->filter, op, filter) > 0) {
		free(evsel->filter);
		evsel->filter = new_filter;
		return 0;
	}

	return -1;
}

893 894 895 896 897 898 899
int perf_evsel__enable(struct perf_evsel *evsel, int ncpus, int nthreads)
{
	return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
				     PERF_EVENT_IOC_ENABLE,
				     0);
}

900 901
int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads)
{
902 903 904
	if (ncpus == 0 || nthreads == 0)
		return 0;

905 906 907
	if (evsel->system_wide)
		nthreads = 1;

908 909 910 911 912 913 914 915 916 917 918 919
	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;
920 921
}

922
static void perf_evsel__free_fd(struct perf_evsel *evsel)
923 924 925 926 927
{
	xyarray__delete(evsel->fd);
	evsel->fd = NULL;
}

928
static void perf_evsel__free_id(struct perf_evsel *evsel)
929
{
930 931
	xyarray__delete(evsel->sample_id);
	evsel->sample_id = NULL;
932
	zfree(&evsel->id);
933 934
}

935 936 937 938 939 940 941 942 943 944
static void perf_evsel__free_config_terms(struct perf_evsel *evsel)
{
	struct perf_evsel_config_term *term, *h;

	list_for_each_entry_safe(term, h, &evsel->config_terms, list) {
		list_del(&term->list);
		free(term);
	}
}

945 946 947 948
void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
{
	int cpu, thread;

949 950 951
	if (evsel->system_wide)
		nthreads = 1;

952 953 954 955 956 957 958
	for (cpu = 0; cpu < ncpus; cpu++)
		for (thread = 0; thread < nthreads; ++thread) {
			close(FD(evsel, cpu, thread));
			FD(evsel, cpu, thread) = -1;
		}
}

959
void perf_evsel__exit(struct perf_evsel *evsel)
960 961
{
	assert(list_empty(&evsel->node));
962 963
	perf_evsel__free_fd(evsel);
	perf_evsel__free_id(evsel);
964
	perf_evsel__free_config_terms(evsel);
965
	close_cgroup(evsel->cgrp);
966
	cpu_map__put(evsel->cpus);
967
	thread_map__put(evsel->threads);
968 969
	zfree(&evsel->group_name);
	zfree(&evsel->name);
A
Arnaldo Carvalho de Melo 已提交
970
	perf_evsel__object.fini(evsel);
971 972 973 974 975
}

void perf_evsel__delete(struct perf_evsel *evsel)
{
	perf_evsel__exit(evsel);
976 977
	free(evsel);
}
978

979
void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread,
980
				struct perf_counts_values *count)
981 982 983 984 985 986 987 988 989 990
{
	struct perf_counts_values tmp;

	if (!evsel->prev_raw_counts)
		return;

	if (cpu == -1) {
		tmp = evsel->prev_raw_counts->aggr;
		evsel->prev_raw_counts->aggr = *count;
	} else {
991 992
		tmp = *perf_counts(evsel->prev_raw_counts, cpu, thread);
		*perf_counts(evsel->prev_raw_counts, cpu, thread) = *count;
993 994 995 996 997 998 999
	}

	count->val = count->val - tmp.val;
	count->ena = count->ena - tmp.ena;
	count->run = count->run - tmp.run;
}

1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019
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 + 0.5);
		}
	} else
		count->ena = count->run = 0;

	if (pscaled)
		*pscaled = scaled;
}

1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033
int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
		     struct perf_counts_values *count)
{
	memset(count, 0, sizeof(*count));

	if (FD(evsel, cpu, thread) < 0)
		return -EINVAL;

	if (readn(FD(evsel, cpu, thread), count, sizeof(*count)) < 0)
		return -errno;

	return 0;
}

1034 1035 1036 1037 1038 1039 1040 1041 1042
int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
			      int cpu, int thread, bool scale)
{
	struct perf_counts_values count;
	size_t nv = scale ? 3 : 1;

	if (FD(evsel, cpu, thread) < 0)
		return -EINVAL;

1043
	if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0)
1044 1045
		return -ENOMEM;

1046 1047 1048
	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
		return -errno;

1049
	perf_evsel__compute_deltas(evsel, cpu, thread, &count);
1050
	perf_counts_values__scale(&count, scale, NULL);
1051
	*perf_counts(evsel->counts, cpu, thread) = count;
1052 1053 1054
	return 0;
}

1055 1056 1057 1058 1059
static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread)
{
	struct perf_evsel *leader = evsel->leader;
	int fd;

1060
	if (perf_evsel__is_group_leader(evsel))
1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074
		return -1;

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

	fd = FD(leader, cpu, thread);
	BUG_ON(fd == -1);

	return fd;
}

1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121
struct bit_names {
	int bit;
	const char *name;
};

static void __p_bits(char *buf, size_t size, u64 value, struct bit_names *bits)
{
	bool first_bit = true;
	int i = 0;

	do {
		if (value & bits[i].bit) {
			buf += scnprintf(buf, size, "%s%s", first_bit ? "" : "|", bits[i].name);
			first_bit = false;
		}
	} while (bits[++i].name != NULL);
}

static void __p_sample_type(char *buf, size_t size, u64 value)
{
#define bit_name(n) { PERF_SAMPLE_##n, #n }
	struct bit_names bits[] = {
		bit_name(IP), bit_name(TID), bit_name(TIME), bit_name(ADDR),
		bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU),
		bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
		bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
		bit_name(IDENTIFIER), bit_name(REGS_INTR),
		{ .name = NULL, }
	};
#undef bit_name
	__p_bits(buf, size, value, bits);
}

static void __p_read_format(char *buf, size_t size, u64 value)
{
#define bit_name(n) { PERF_FORMAT_##n, #n }
	struct bit_names bits[] = {
		bit_name(TOTAL_TIME_ENABLED), bit_name(TOTAL_TIME_RUNNING),
		bit_name(ID), bit_name(GROUP),
		{ .name = NULL, }
	};
#undef bit_name
	__p_bits(buf, size, value, bits);
}

#define BUF_SIZE		1024

1122
#define p_hex(val)		snprintf(buf, BUF_SIZE, "%#"PRIx64, (uint64_t)(val))
1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175
#define p_unsigned(val)		snprintf(buf, BUF_SIZE, "%"PRIu64, (uint64_t)(val))
#define p_signed(val)		snprintf(buf, BUF_SIZE, "%"PRId64, (int64_t)(val))
#define p_sample_type(val)	__p_sample_type(buf, BUF_SIZE, val)
#define p_read_format(val)	__p_read_format(buf, BUF_SIZE, val)

#define PRINT_ATTRn(_n, _f, _p)				\
do {							\
	if (attr->_f) {					\
		_p(attr->_f);				\
		ret += attr__fprintf(fp, _n, buf, priv);\
	}						\
} while (0)

#define PRINT_ATTRf(_f, _p)	PRINT_ATTRn(#_f, _f, _p)

int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
			     attr__fprintf_f attr__fprintf, void *priv)
{
	char buf[BUF_SIZE];
	int ret = 0;

	PRINT_ATTRf(type, p_unsigned);
	PRINT_ATTRf(size, p_unsigned);
	PRINT_ATTRf(config, p_hex);
	PRINT_ATTRn("{ sample_period, sample_freq }", sample_period, p_unsigned);
	PRINT_ATTRf(sample_type, p_sample_type);
	PRINT_ATTRf(read_format, p_read_format);

	PRINT_ATTRf(disabled, p_unsigned);
	PRINT_ATTRf(inherit, p_unsigned);
	PRINT_ATTRf(pinned, p_unsigned);
	PRINT_ATTRf(exclusive, p_unsigned);
	PRINT_ATTRf(exclude_user, p_unsigned);
	PRINT_ATTRf(exclude_kernel, p_unsigned);
	PRINT_ATTRf(exclude_hv, p_unsigned);
	PRINT_ATTRf(exclude_idle, p_unsigned);
	PRINT_ATTRf(mmap, p_unsigned);
	PRINT_ATTRf(comm, p_unsigned);
	PRINT_ATTRf(freq, p_unsigned);
	PRINT_ATTRf(inherit_stat, p_unsigned);
	PRINT_ATTRf(enable_on_exec, p_unsigned);
	PRINT_ATTRf(task, p_unsigned);
	PRINT_ATTRf(watermark, p_unsigned);
	PRINT_ATTRf(precise_ip, p_unsigned);
	PRINT_ATTRf(mmap_data, p_unsigned);
	PRINT_ATTRf(sample_id_all, p_unsigned);
	PRINT_ATTRf(exclude_host, p_unsigned);
	PRINT_ATTRf(exclude_guest, p_unsigned);
	PRINT_ATTRf(exclude_callchain_kernel, p_unsigned);
	PRINT_ATTRf(exclude_callchain_user, p_unsigned);
	PRINT_ATTRf(mmap2, p_unsigned);
	PRINT_ATTRf(comm_exec, p_unsigned);
	PRINT_ATTRf(use_clockid, p_unsigned);
1176
	PRINT_ATTRf(context_switch, p_unsigned);
1177 1178 1179 1180 1181 1182 1183 1184 1185

	PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
	PRINT_ATTRf(bp_type, p_unsigned);
	PRINT_ATTRn("{ bp_addr, config1 }", bp_addr, p_hex);
	PRINT_ATTRn("{ bp_len, config2 }", bp_len, p_hex);
	PRINT_ATTRf(sample_regs_user, p_hex);
	PRINT_ATTRf(sample_stack_user, p_unsigned);
	PRINT_ATTRf(clockid, p_signed);
	PRINT_ATTRf(sample_regs_intr, p_hex);
1186
	PRINT_ATTRf(aux_watermark, p_unsigned);
A
Adrian Hunter 已提交
1187 1188 1189 1190

	return ret;
}

1191 1192 1193 1194 1195 1196
static int __open_attr__fprintf(FILE *fp, const char *name, const char *val,
				void *priv __attribute__((unused)))
{
	return fprintf(fp, "  %-32s %s\n", name, val);
}

1197
static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
1198
			      struct thread_map *threads)
1199
{
1200
	int cpu, thread, nthreads;
1201
	unsigned long flags = PERF_FLAG_FD_CLOEXEC;
1202
	int pid = -1, err;
1203
	enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE;
1204

1205 1206 1207 1208 1209
	if (evsel->system_wide)
		nthreads = 1;
	else
		nthreads = threads->nr;

1210
	if (evsel->fd == NULL &&
1211
	    perf_evsel__alloc_fd(evsel, cpus->nr, nthreads) < 0)
1212
		return -ENOMEM;
1213

S
Stephane Eranian 已提交
1214
	if (evsel->cgrp) {
1215
		flags |= PERF_FLAG_PID_CGROUP;
S
Stephane Eranian 已提交
1216 1217 1218
		pid = evsel->cgrp->fd;
	}

1219
fallback_missing_features:
1220 1221 1222 1223 1224 1225
	if (perf_missing_features.clockid_wrong)
		evsel->attr.clockid = CLOCK_MONOTONIC; /* should always work */
	if (perf_missing_features.clockid) {
		evsel->attr.use_clockid = 0;
		evsel->attr.clockid = 0;
	}
1226 1227
	if (perf_missing_features.cloexec)
		flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC;
1228 1229
	if (perf_missing_features.mmap2)
		evsel->attr.mmap2 = 0;
1230 1231 1232 1233 1234 1235
	if (perf_missing_features.exclude_guest)
		evsel->attr.exclude_guest = evsel->attr.exclude_host = 0;
retry_sample_id:
	if (perf_missing_features.sample_id_all)
		evsel->attr.sample_id_all = 0;

1236 1237 1238 1239 1240 1241
	if (verbose >= 2) {
		fprintf(stderr, "%.60s\n", graph_dotted_line);
		fprintf(stderr, "perf_event_attr:\n");
		perf_event_attr__fprintf(stderr, &evsel->attr, __open_attr__fprintf, NULL);
		fprintf(stderr, "%.60s\n", graph_dotted_line);
	}
A
Adrian Hunter 已提交
1242

1243
	for (cpu = 0; cpu < cpus->nr; cpu++) {
1244

1245
		for (thread = 0; thread < nthreads; thread++) {
1246
			int group_fd;
S
Stephane Eranian 已提交
1247

1248
			if (!evsel->cgrp && !evsel->system_wide)
1249
				pid = thread_map__pid(threads, thread);
S
Stephane Eranian 已提交
1250

1251
			group_fd = get_group_fd(evsel, cpu, thread);
1252
retry_open:
1253
			pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx\n",
A
Adrian Hunter 已提交
1254 1255
				  pid, cpus->map[cpu], group_fd, flags);

1256
			FD(evsel, cpu, thread) = sys_perf_event_open(&evsel->attr,
S
Stephane Eranian 已提交
1257
								     pid,
1258
								     cpus->map[cpu],
S
Stephane Eranian 已提交
1259
								     group_fd, flags);
1260 1261
			if (FD(evsel, cpu, thread) < 0) {
				err = -errno;
1262
				pr_debug2("sys_perf_event_open failed, error %d\n",
1263
					  err);
1264
				goto try_fallback;
1265
			}
1266
			set_rlimit = NO_CHANGE;
1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277

			/*
			 * If we succeeded but had to kill clockid, fail and
			 * have perf_evsel__open_strerror() print us a nice
			 * error.
			 */
			if (perf_missing_features.clockid ||
			    perf_missing_features.clockid_wrong) {
				err = -EINVAL;
				goto out_close;
			}
1278
		}
1279 1280 1281 1282
	}

	return 0;

1283
try_fallback:
1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307
	/*
	 * perf stat needs between 5 and 22 fds per CPU. When we run out
	 * of them try to increase the limits.
	 */
	if (err == -EMFILE && set_rlimit < INCREASED_MAX) {
		struct rlimit l;
		int old_errno = errno;

		if (getrlimit(RLIMIT_NOFILE, &l) == 0) {
			if (set_rlimit == NO_CHANGE)
				l.rlim_cur = l.rlim_max;
			else {
				l.rlim_cur = l.rlim_max + 1000;
				l.rlim_max = l.rlim_cur;
			}
			if (setrlimit(RLIMIT_NOFILE, &l) == 0) {
				set_rlimit++;
				errno = old_errno;
				goto retry_open;
			}
		}
		errno = old_errno;
	}

1308 1309 1310
	if (err != -EINVAL || cpu > 0 || thread > 0)
		goto out_close;

1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321
	/*
	 * Must probe features in the order they were added to the
	 * perf_event_attr interface.
	 */
	if (!perf_missing_features.clockid_wrong && evsel->attr.use_clockid) {
		perf_missing_features.clockid_wrong = true;
		goto fallback_missing_features;
	} else if (!perf_missing_features.clockid && evsel->attr.use_clockid) {
		perf_missing_features.clockid = true;
		goto fallback_missing_features;
	} else if (!perf_missing_features.cloexec && (flags & PERF_FLAG_FD_CLOEXEC)) {
1322 1323 1324
		perf_missing_features.cloexec = true;
		goto fallback_missing_features;
	} else if (!perf_missing_features.mmap2 && evsel->attr.mmap2) {
1325 1326 1327 1328
		perf_missing_features.mmap2 = true;
		goto fallback_missing_features;
	} else if (!perf_missing_features.exclude_guest &&
		   (evsel->attr.exclude_guest || evsel->attr.exclude_host)) {
1329 1330 1331 1332 1333 1334 1335
		perf_missing_features.exclude_guest = true;
		goto fallback_missing_features;
	} else if (!perf_missing_features.sample_id_all) {
		perf_missing_features.sample_id_all = true;
		goto retry_sample_id;
	}

1336
out_close:
1337 1338 1339 1340 1341
	do {
		while (--thread >= 0) {
			close(FD(evsel, cpu, thread));
			FD(evsel, cpu, thread) = -1;
		}
1342
		thread = nthreads;
1343
	} while (--cpu >= 0);
1344 1345 1346 1347 1348 1349 1350 1351 1352 1353
	return err;
}

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

	perf_evsel__close_fd(evsel, ncpus, nthreads);
	perf_evsel__free_fd(evsel);
1354 1355
}

1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371
static struct {
	struct cpu_map map;
	int cpus[1];
} empty_cpu_map = {
	.map.nr	= 1,
	.cpus	= { -1, },
};

static struct {
	struct thread_map map;
	int threads[1];
} empty_thread_map = {
	.map.nr	 = 1,
	.threads = { -1, },
};

1372
int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
1373
		     struct thread_map *threads)
1374
{
1375 1376 1377
	if (cpus == NULL) {
		/* Work around old compiler warnings about strict aliasing */
		cpus = &empty_cpu_map.map;
1378 1379
	}

1380 1381
	if (threads == NULL)
		threads = &empty_thread_map.map;
1382

1383
	return __perf_evsel__open(evsel, cpus, threads);
1384 1385
}

1386
int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
1387
			     struct cpu_map *cpus)
1388
{
1389
	return __perf_evsel__open(evsel, cpus, &empty_thread_map.map);
1390
}
1391

1392
int perf_evsel__open_per_thread(struct perf_evsel *evsel,
1393
				struct thread_map *threads)
1394
{
1395
	return __perf_evsel__open(evsel, &empty_cpu_map.map, threads);
1396
}
1397

1398 1399 1400
static int perf_evsel__parse_id_sample(const struct perf_evsel *evsel,
				       const union perf_event *event,
				       struct perf_sample *sample)
1401
{
1402
	u64 type = evsel->attr.sample_type;
1403
	const u64 *array = event->sample.array;
1404
	bool swapped = evsel->needs_swap;
1405
	union u64_swap u;
1406 1407 1408 1409

	array += ((event->header.size -
		   sizeof(event->header)) / sizeof(u64)) - 1;

1410 1411 1412 1413 1414
	if (type & PERF_SAMPLE_IDENTIFIER) {
		sample->id = *array;
		array--;
	}

1415
	if (type & PERF_SAMPLE_CPU) {
1416 1417 1418 1419 1420 1421 1422 1423
		u.val64 = *array;
		if (swapped) {
			/* undo swap of u64, then swap on individual u32s */
			u.val64 = bswap_64(u.val64);
			u.val32[0] = bswap_32(u.val32[0]);
		}

		sample->cpu = u.val32[0];
1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442
		array--;
	}

	if (type & PERF_SAMPLE_STREAM_ID) {
		sample->stream_id = *array;
		array--;
	}

	if (type & PERF_SAMPLE_ID) {
		sample->id = *array;
		array--;
	}

	if (type & PERF_SAMPLE_TIME) {
		sample->time = *array;
		array--;
	}

	if (type & PERF_SAMPLE_TID) {
1443 1444 1445 1446 1447 1448 1449 1450 1451 1452
		u.val64 = *array;
		if (swapped) {
			/* undo swap of u64, then swap on individual u32s */
			u.val64 = bswap_64(u.val64);
			u.val32[0] = bswap_32(u.val32[0]);
			u.val32[1] = bswap_32(u.val32[1]);
		}

		sample->pid = u.val32[0];
		sample->tid = u.val32[1];
1453
		array--;
1454 1455 1456 1457 1458
	}

	return 0;
}

1459 1460
static inline bool overflow(const void *endp, u16 max_size, const void *offset,
			    u64 size)
1461
{
1462 1463
	return size > max_size || offset + size > endp;
}
1464

1465 1466 1467 1468 1469
#define OVERFLOW_CHECK(offset, size, max_size)				\
	do {								\
		if (overflow(endp, (max_size), (offset), (size)))	\
			return -EFAULT;					\
	} while (0)
1470

1471 1472
#define OVERFLOW_CHECK_u64(offset) \
	OVERFLOW_CHECK(offset, sizeof(u64), sizeof(u64))
1473

1474
int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
1475
			     struct perf_sample *data)
1476
{
1477
	u64 type = evsel->attr.sample_type;
1478
	bool swapped = evsel->needs_swap;
1479
	const u64 *array;
1480 1481 1482
	u16 max_size = event->header.size;
	const void *endp = (void *)event + max_size;
	u64 sz;
1483

1484 1485 1486 1487
	/*
	 * used for cross-endian analysis. See git commit 65014ab3
	 * for why this goofiness is needed.
	 */
1488
	union u64_swap u;
1489

1490
	memset(data, 0, sizeof(*data));
1491 1492
	data->cpu = data->pid = data->tid = -1;
	data->stream_id = data->id = data->time = -1ULL;
1493
	data->period = evsel->attr.sample_period;
1494
	data->weight = 0;
1495 1496

	if (event->header.type != PERF_RECORD_SAMPLE) {
1497
		if (!evsel->attr.sample_id_all)
1498
			return 0;
1499
		return perf_evsel__parse_id_sample(evsel, event, data);
1500 1501 1502 1503
	}

	array = event->sample.array;

1504 1505 1506 1507 1508
	/*
	 * The evsel's sample_size is based on PERF_SAMPLE_MASK which includes
	 * up to PERF_SAMPLE_PERIOD.  After that overflow() must be used to
	 * check the format does not go past the end of the event.
	 */
1509
	if (evsel->sample_size + sizeof(event->header) > event->header.size)
1510 1511
		return -EFAULT;

1512 1513 1514 1515 1516 1517
	data->id = -1ULL;
	if (type & PERF_SAMPLE_IDENTIFIER) {
		data->id = *array;
		array++;
	}

1518
	if (type & PERF_SAMPLE_IP) {
1519
		data->ip = *array;
1520 1521 1522 1523
		array++;
	}

	if (type & PERF_SAMPLE_TID) {
1524 1525 1526 1527 1528 1529 1530 1531 1532 1533
		u.val64 = *array;
		if (swapped) {
			/* undo swap of u64, then swap on individual u32s */
			u.val64 = bswap_64(u.val64);
			u.val32[0] = bswap_32(u.val32[0]);
			u.val32[1] = bswap_32(u.val32[1]);
		}

		data->pid = u.val32[0];
		data->tid = u.val32[1];
1534 1535 1536 1537 1538 1539 1540 1541
		array++;
	}

	if (type & PERF_SAMPLE_TIME) {
		data->time = *array;
		array++;
	}

1542
	data->addr = 0;
1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558
	if (type & PERF_SAMPLE_ADDR) {
		data->addr = *array;
		array++;
	}

	if (type & PERF_SAMPLE_ID) {
		data->id = *array;
		array++;
	}

	if (type & PERF_SAMPLE_STREAM_ID) {
		data->stream_id = *array;
		array++;
	}

	if (type & PERF_SAMPLE_CPU) {
1559 1560 1561 1562 1563 1564 1565 1566 1567

		u.val64 = *array;
		if (swapped) {
			/* undo swap of u64, then swap on individual u32s */
			u.val64 = bswap_64(u.val64);
			u.val32[0] = bswap_32(u.val32[0]);
		}

		data->cpu = u.val32[0];
1568 1569 1570 1571 1572 1573 1574 1575 1576
		array++;
	}

	if (type & PERF_SAMPLE_PERIOD) {
		data->period = *array;
		array++;
	}

	if (type & PERF_SAMPLE_READ) {
1577 1578
		u64 read_format = evsel->attr.read_format;

1579
		OVERFLOW_CHECK_u64(array);
1580 1581 1582 1583 1584 1585 1586 1587
		if (read_format & PERF_FORMAT_GROUP)
			data->read.group.nr = *array;
		else
			data->read.one.value = *array;

		array++;

		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
1588
			OVERFLOW_CHECK_u64(array);
1589 1590 1591 1592 1593
			data->read.time_enabled = *array;
			array++;
		}

		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
1594
			OVERFLOW_CHECK_u64(array);
1595 1596 1597 1598 1599 1600
			data->read.time_running = *array;
			array++;
		}

		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
		if (read_format & PERF_FORMAT_GROUP) {
1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611
			const u64 max_group_nr = UINT64_MAX /
					sizeof(struct sample_read_value);

			if (data->read.group.nr > max_group_nr)
				return -EFAULT;
			sz = data->read.group.nr *
			     sizeof(struct sample_read_value);
			OVERFLOW_CHECK(array, sz, max_size);
			data->read.group.values =
					(struct sample_read_value *)array;
			array = (void *)array + sz;
1612
		} else {
1613
			OVERFLOW_CHECK_u64(array);
1614 1615 1616
			data->read.one.id = *array;
			array++;
		}
1617 1618 1619
	}

	if (type & PERF_SAMPLE_CALLCHAIN) {
1620
		const u64 max_callchain_nr = UINT64_MAX / sizeof(u64);
1621

1622 1623 1624
		OVERFLOW_CHECK_u64(array);
		data->callchain = (struct ip_callchain *)array++;
		if (data->callchain->nr > max_callchain_nr)
1625
			return -EFAULT;
1626 1627 1628
		sz = data->callchain->nr * sizeof(u64);
		OVERFLOW_CHECK(array, sz, max_size);
		array = (void *)array + sz;
1629 1630 1631
	}

	if (type & PERF_SAMPLE_RAW) {
1632
		OVERFLOW_CHECK_u64(array);
1633 1634 1635 1636 1637 1638 1639 1640 1641
		u.val64 = *array;
		if (WARN_ONCE(swapped,
			      "Endianness of raw data not corrected!\n")) {
			/* undo swap of u64, then swap on individual u32s */
			u.val64 = bswap_64(u.val64);
			u.val32[0] = bswap_32(u.val32[0]);
			u.val32[1] = bswap_32(u.val32[1]);
		}
		data->raw_size = u.val32[0];
1642
		array = (void *)array + sizeof(u32);
1643

1644 1645 1646
		OVERFLOW_CHECK(array, data->raw_size, max_size);
		data->raw_data = (void *)array;
		array = (void *)array + data->raw_size;
1647 1648
	}

1649
	if (type & PERF_SAMPLE_BRANCH_STACK) {
1650 1651
		const u64 max_branch_nr = UINT64_MAX /
					  sizeof(struct branch_entry);
1652

1653 1654
		OVERFLOW_CHECK_u64(array);
		data->branch_stack = (struct branch_stack *)array++;
1655

1656 1657
		if (data->branch_stack->nr > max_branch_nr)
			return -EFAULT;
1658
		sz = data->branch_stack->nr * sizeof(struct branch_entry);
1659 1660
		OVERFLOW_CHECK(array, sz, max_size);
		array = (void *)array + sz;
1661
	}
1662 1663

	if (type & PERF_SAMPLE_REGS_USER) {
1664
		OVERFLOW_CHECK_u64(array);
1665 1666
		data->user_regs.abi = *array;
		array++;
1667

1668
		if (data->user_regs.abi) {
1669
			u64 mask = evsel->attr.sample_regs_user;
1670

1671
			sz = hweight_long(mask) * sizeof(u64);
1672
			OVERFLOW_CHECK(array, sz, max_size);
1673
			data->user_regs.mask = mask;
1674
			data->user_regs.regs = (u64 *)array;
1675
			array = (void *)array + sz;
1676 1677 1678 1679
		}
	}

	if (type & PERF_SAMPLE_STACK_USER) {
1680 1681
		OVERFLOW_CHECK_u64(array);
		sz = *array++;
1682 1683 1684 1685

		data->user_stack.offset = ((char *)(array - 1)
					  - (char *) event);

1686
		if (!sz) {
1687 1688
			data->user_stack.size = 0;
		} else {
1689
			OVERFLOW_CHECK(array, sz, max_size);
1690
			data->user_stack.data = (char *)array;
1691 1692
			array = (void *)array + sz;
			OVERFLOW_CHECK_u64(array);
1693
			data->user_stack.size = *array++;
1694 1695 1696
			if (WARN_ONCE(data->user_stack.size > sz,
				      "user stack dump failure\n"))
				return -EFAULT;
1697 1698 1699
		}
	}

1700 1701
	data->weight = 0;
	if (type & PERF_SAMPLE_WEIGHT) {
1702
		OVERFLOW_CHECK_u64(array);
1703 1704 1705 1706
		data->weight = *array;
		array++;
	}

1707 1708
	data->data_src = PERF_MEM_DATA_SRC_NONE;
	if (type & PERF_SAMPLE_DATA_SRC) {
1709
		OVERFLOW_CHECK_u64(array);
1710 1711 1712 1713
		data->data_src = *array;
		array++;
	}

1714 1715
	data->transaction = 0;
	if (type & PERF_SAMPLE_TRANSACTION) {
1716
		OVERFLOW_CHECK_u64(array);
1717 1718 1719 1720
		data->transaction = *array;
		array++;
	}

1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737
	data->intr_regs.abi = PERF_SAMPLE_REGS_ABI_NONE;
	if (type & PERF_SAMPLE_REGS_INTR) {
		OVERFLOW_CHECK_u64(array);
		data->intr_regs.abi = *array;
		array++;

		if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) {
			u64 mask = evsel->attr.sample_regs_intr;

			sz = hweight_long(mask) * sizeof(u64);
			OVERFLOW_CHECK(array, sz, max_size);
			data->intr_regs.mask = mask;
			data->intr_regs.regs = (u64 *)array;
			array = (void *)array + sz;
		}
	}

1738 1739
	return 0;
}
1740

1741
size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
1742
				     u64 read_format)
1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807
{
	size_t sz, result = sizeof(struct sample_event);

	if (type & PERF_SAMPLE_IDENTIFIER)
		result += sizeof(u64);

	if (type & PERF_SAMPLE_IP)
		result += sizeof(u64);

	if (type & PERF_SAMPLE_TID)
		result += sizeof(u64);

	if (type & PERF_SAMPLE_TIME)
		result += sizeof(u64);

	if (type & PERF_SAMPLE_ADDR)
		result += sizeof(u64);

	if (type & PERF_SAMPLE_ID)
		result += sizeof(u64);

	if (type & PERF_SAMPLE_STREAM_ID)
		result += sizeof(u64);

	if (type & PERF_SAMPLE_CPU)
		result += sizeof(u64);

	if (type & PERF_SAMPLE_PERIOD)
		result += sizeof(u64);

	if (type & PERF_SAMPLE_READ) {
		result += sizeof(u64);
		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
			result += sizeof(u64);
		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
			result += sizeof(u64);
		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
		if (read_format & PERF_FORMAT_GROUP) {
			sz = sample->read.group.nr *
			     sizeof(struct sample_read_value);
			result += sz;
		} else {
			result += sizeof(u64);
		}
	}

	if (type & PERF_SAMPLE_CALLCHAIN) {
		sz = (sample->callchain->nr + 1) * sizeof(u64);
		result += sz;
	}

	if (type & PERF_SAMPLE_RAW) {
		result += sizeof(u32);
		result += sample->raw_size;
	}

	if (type & PERF_SAMPLE_BRANCH_STACK) {
		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
		sz += sizeof(u64);
		result += sz;
	}

	if (type & PERF_SAMPLE_REGS_USER) {
		if (sample->user_regs.abi) {
			result += sizeof(u64);
1808
			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829
			result += sz;
		} else {
			result += sizeof(u64);
		}
	}

	if (type & PERF_SAMPLE_STACK_USER) {
		sz = sample->user_stack.size;
		result += sizeof(u64);
		if (sz) {
			result += sz;
			result += sizeof(u64);
		}
	}

	if (type & PERF_SAMPLE_WEIGHT)
		result += sizeof(u64);

	if (type & PERF_SAMPLE_DATA_SRC)
		result += sizeof(u64);

1830 1831 1832
	if (type & PERF_SAMPLE_TRANSACTION)
		result += sizeof(u64);

1833 1834 1835 1836 1837 1838 1839 1840 1841 1842
	if (type & PERF_SAMPLE_REGS_INTR) {
		if (sample->intr_regs.abi) {
			result += sizeof(u64);
			sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
			result += sz;
		} else {
			result += sizeof(u64);
		}
	}

1843 1844 1845
	return result;
}

1846
int perf_event__synthesize_sample(union perf_event *event, u64 type,
1847
				  u64 read_format,
1848 1849 1850 1851
				  const struct perf_sample *sample,
				  bool swapped)
{
	u64 *array;
1852
	size_t sz;
1853 1854 1855 1856
	/*
	 * used for cross-endian analysis. See git commit 65014ab3
	 * for why this goofiness is needed.
	 */
1857
	union u64_swap u;
1858 1859 1860

	array = event->sample.array;

1861 1862 1863 1864 1865
	if (type & PERF_SAMPLE_IDENTIFIER) {
		*array = sample->id;
		array++;
	}

1866
	if (type & PERF_SAMPLE_IP) {
1867
		*array = sample->ip;
1868 1869 1870 1871 1872 1873 1874 1875
		array++;
	}

	if (type & PERF_SAMPLE_TID) {
		u.val32[0] = sample->pid;
		u.val32[1] = sample->tid;
		if (swapped) {
			/*
1876
			 * Inverse of what is done in perf_evsel__parse_sample
1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910
			 */
			u.val32[0] = bswap_32(u.val32[0]);
			u.val32[1] = bswap_32(u.val32[1]);
			u.val64 = bswap_64(u.val64);
		}

		*array = u.val64;
		array++;
	}

	if (type & PERF_SAMPLE_TIME) {
		*array = sample->time;
		array++;
	}

	if (type & PERF_SAMPLE_ADDR) {
		*array = sample->addr;
		array++;
	}

	if (type & PERF_SAMPLE_ID) {
		*array = sample->id;
		array++;
	}

	if (type & PERF_SAMPLE_STREAM_ID) {
		*array = sample->stream_id;
		array++;
	}

	if (type & PERF_SAMPLE_CPU) {
		u.val32[0] = sample->cpu;
		if (swapped) {
			/*
1911
			 * Inverse of what is done in perf_evsel__parse_sample
1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924
			 */
			u.val32[0] = bswap_32(u.val32[0]);
			u.val64 = bswap_64(u.val64);
		}
		*array = u.val64;
		array++;
	}

	if (type & PERF_SAMPLE_PERIOD) {
		*array = sample->period;
		array++;
	}

1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987
	if (type & PERF_SAMPLE_READ) {
		if (read_format & PERF_FORMAT_GROUP)
			*array = sample->read.group.nr;
		else
			*array = sample->read.one.value;
		array++;

		if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) {
			*array = sample->read.time_enabled;
			array++;
		}

		if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) {
			*array = sample->read.time_running;
			array++;
		}

		/* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */
		if (read_format & PERF_FORMAT_GROUP) {
			sz = sample->read.group.nr *
			     sizeof(struct sample_read_value);
			memcpy(array, sample->read.group.values, sz);
			array = (void *)array + sz;
		} else {
			*array = sample->read.one.id;
			array++;
		}
	}

	if (type & PERF_SAMPLE_CALLCHAIN) {
		sz = (sample->callchain->nr + 1) * sizeof(u64);
		memcpy(array, sample->callchain, sz);
		array = (void *)array + sz;
	}

	if (type & PERF_SAMPLE_RAW) {
		u.val32[0] = sample->raw_size;
		if (WARN_ONCE(swapped,
			      "Endianness of raw data not corrected!\n")) {
			/*
			 * Inverse of what is done in perf_evsel__parse_sample
			 */
			u.val32[0] = bswap_32(u.val32[0]);
			u.val32[1] = bswap_32(u.val32[1]);
			u.val64 = bswap_64(u.val64);
		}
		*array = u.val64;
		array = (void *)array + sizeof(u32);

		memcpy(array, sample->raw_data, sample->raw_size);
		array = (void *)array + sample->raw_size;
	}

	if (type & PERF_SAMPLE_BRANCH_STACK) {
		sz = sample->branch_stack->nr * sizeof(struct branch_entry);
		sz += sizeof(u64);
		memcpy(array, sample->branch_stack, sz);
		array = (void *)array + sz;
	}

	if (type & PERF_SAMPLE_REGS_USER) {
		if (sample->user_regs.abi) {
			*array++ = sample->user_regs.abi;
1988
			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015
			memcpy(array, sample->user_regs.regs, sz);
			array = (void *)array + sz;
		} else {
			*array++ = 0;
		}
	}

	if (type & PERF_SAMPLE_STACK_USER) {
		sz = sample->user_stack.size;
		*array++ = sz;
		if (sz) {
			memcpy(array, sample->user_stack.data, sz);
			array = (void *)array + sz;
			*array++ = sz;
		}
	}

	if (type & PERF_SAMPLE_WEIGHT) {
		*array = sample->weight;
		array++;
	}

	if (type & PERF_SAMPLE_DATA_SRC) {
		*array = sample->data_src;
		array++;
	}

2016 2017 2018 2019 2020
	if (type & PERF_SAMPLE_TRANSACTION) {
		*array = sample->transaction;
		array++;
	}

2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031
	if (type & PERF_SAMPLE_REGS_INTR) {
		if (sample->intr_regs.abi) {
			*array++ = sample->intr_regs.abi;
			sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
			memcpy(array, sample->intr_regs.regs, sz);
			array = (void *)array + sz;
		} else {
			*array++ = 0;
		}
	}

2032 2033
	return 0;
}
2034

2035 2036 2037 2038 2039
struct format_field *perf_evsel__field(struct perf_evsel *evsel, const char *name)
{
	return pevent_find_field(evsel->tp_format, name);
}

2040
void *perf_evsel__rawptr(struct perf_evsel *evsel, struct perf_sample *sample,
2041 2042
			 const char *name)
{
2043
	struct format_field *field = perf_evsel__field(evsel, name);
2044 2045
	int offset;

2046 2047
	if (!field)
		return NULL;
2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061

	offset = field->offset;

	if (field->flags & FIELD_IS_DYNAMIC) {
		offset = *(int *)(sample->raw_data + field->offset);
		offset &= 0xffff;
	}

	return sample->raw_data + offset;
}

u64 perf_evsel__intval(struct perf_evsel *evsel, struct perf_sample *sample,
		       const char *name)
{
2062
	struct format_field *field = perf_evsel__field(evsel, name);
2063 2064
	void *ptr;
	u64 value;
2065

2066 2067
	if (!field)
		return 0;
2068

2069
	ptr = sample->raw_data + field->offset;
2070

2071 2072 2073 2074 2075 2076 2077 2078 2079 2080
	switch (field->size) {
	case 1:
		return *(u8 *)ptr;
	case 2:
		value = *(u16 *)ptr;
		break;
	case 4:
		value = *(u32 *)ptr;
		break;
	case 8:
2081
		memcpy(&value, ptr, sizeof(u64));
2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101
		break;
	default:
		return 0;
	}

	if (!evsel->needs_swap)
		return value;

	switch (field->size) {
	case 2:
		return bswap_16(value);
	case 4:
		return bswap_32(value);
	case 8:
		return bswap_64(value);
	default:
		return 0;
	}

	return 0;
2102
}
2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121

static int comma_fprintf(FILE *fp, bool *first, const char *fmt, ...)
{
	va_list args;
	int ret = 0;

	if (!*first) {
		ret += fprintf(fp, ",");
	} else {
		ret += fprintf(fp, ":");
		*first = false;
	}

	va_start(args, fmt);
	ret += vfprintf(fp, fmt, args);
	va_end(args);
	return ret;
}

2122
static int __print_attr__fprintf(FILE *fp, const char *name, const char *val, void *priv)
2123
{
2124
	return comma_fprintf(fp, (bool *)priv, " %s: %s", name, val);
2125 2126
}

2127 2128 2129 2130
int perf_evsel__fprintf(struct perf_evsel *evsel,
			struct perf_attr_details *details, FILE *fp)
{
	bool first = true;
N
Namhyung Kim 已提交
2131 2132
	int printed = 0;

2133
	if (details->event_group) {
N
Namhyung Kim 已提交
2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151
		struct perf_evsel *pos;

		if (!perf_evsel__is_group_leader(evsel))
			return 0;

		if (evsel->nr_members > 1)
			printed += fprintf(fp, "%s{", evsel->group_name ?: "");

		printed += fprintf(fp, "%s", perf_evsel__name(evsel));
		for_each_group_member(pos, evsel)
			printed += fprintf(fp, ",%s", perf_evsel__name(pos));

		if (evsel->nr_members > 1)
			printed += fprintf(fp, "}");
		goto out;
	}

	printed += fprintf(fp, "%s", perf_evsel__name(evsel));
2152

2153 2154 2155 2156
	if (details->verbose) {
		printed += perf_event_attr__fprintf(fp, &evsel->attr,
						    __print_attr__fprintf, &first);
	} else if (details->freq) {
2157 2158 2159
		printed += comma_fprintf(fp, &first, " sample_freq=%" PRIu64,
					 (u64)evsel->attr.sample_freq);
	}
N
Namhyung Kim 已提交
2160
out:
2161 2162 2163
	fputc('\n', fp);
	return ++printed;
}
2164 2165 2166 2167

bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
			  char *msg, size_t msgsize)
{
2168
	if ((err == ENOENT || err == ENXIO || err == ENODEV) &&
2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184
	    evsel->attr.type   == PERF_TYPE_HARDWARE &&
	    evsel->attr.config == PERF_COUNT_HW_CPU_CYCLES) {
		/*
		 * If it's cycles then fall back to hrtimer based
		 * cpu-clock-tick sw counter, which is always available even if
		 * no PMU support.
		 *
		 * PPC returns ENXIO until 2.6.37 (behavior changed with commit
		 * b0a873e).
		 */
		scnprintf(msg, msgsize, "%s",
"The cycles event is not supported, trying to fall back to cpu-clock-ticks");

		evsel->attr.type   = PERF_TYPE_SOFTWARE;
		evsel->attr.config = PERF_COUNT_SW_CPU_CLOCK;

2185
		zfree(&evsel->name);
2186 2187 2188 2189 2190
		return true;
	}

	return false;
}
2191

2192
int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
2193 2194
			      int err, char *msg, size_t size)
{
2195 2196
	char sbuf[STRERR_BUFSIZE];

2197 2198 2199
	switch (err) {
	case EPERM:
	case EACCES:
2200
		return scnprintf(msg, size,
2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213
		 "You may not have permission to collect %sstats.\n"
		 "Consider tweaking /proc/sys/kernel/perf_event_paranoid:\n"
		 " -1 - Not paranoid at all\n"
		 "  0 - Disallow raw tracepoint access for unpriv\n"
		 "  1 - Disallow cpu events for unpriv\n"
		 "  2 - Disallow kernel profiling for unpriv",
				 target->system_wide ? "system-wide " : "");
	case ENOENT:
		return scnprintf(msg, size, "The %s event is not supported.",
				 perf_evsel__name(evsel));
	case EMFILE:
		return scnprintf(msg, size, "%s",
			 "Too many events are opened.\n"
2214 2215 2216
			 "Probably the maximum number of open file descriptors has been reached.\n"
			 "Hint: Try again after reducing the number of events.\n"
			 "Hint: Try increasing the limit with 'ulimit -n <limit>'");
2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232
	case ENODEV:
		if (target->cpu_list)
			return scnprintf(msg, size, "%s",
	 "No such device - did you specify an out-of-range profile CPU?\n");
		break;
	case EOPNOTSUPP:
		if (evsel->attr.precise_ip)
			return scnprintf(msg, size, "%s",
	"\'precise\' request may not be supported. Try removing 'p' modifier.");
#if defined(__i386__) || defined(__x86_64__)
		if (evsel->attr.type == PERF_TYPE_HARDWARE)
			return scnprintf(msg, size, "%s",
	"No hardware sampling interrupt available.\n"
	"No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.");
#endif
		break;
2233 2234 2235 2236 2237 2238
	case EBUSY:
		if (find_process("oprofiled"))
			return scnprintf(msg, size,
	"The PMU counters are busy/taken by another profiler.\n"
	"We found oprofile daemon running, please stop it and try again.");
		break;
2239 2240 2241 2242 2243 2244
	case EINVAL:
		if (perf_missing_features.clockid)
			return scnprintf(msg, size, "clockid feature not supported.");
		if (perf_missing_features.clockid_wrong)
			return scnprintf(msg, size, "wrong clockid (%d).", clockid);
		break;
2245 2246 2247 2248 2249
	default:
		break;
	}

	return scnprintf(msg, size,
2250
	"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
2251 2252
	"/bin/dmesg may provide additional information.\n"
	"No CONFIG_PERF_EVENTS=y kernel support configured?\n",
2253 2254
			 err, strerror_r(err, sbuf, sizeof(sbuf)),
			 perf_evsel__name(evsel));
2255
}