builtin-trace.c 62.5 KB
Newer Older
1
#include <traceevent/event-parse.h>
A
Arnaldo Carvalho de Melo 已提交
2
#include "builtin.h"
3
#include "util/color.h"
4
#include "util/debug.h"
A
Arnaldo Carvalho de Melo 已提交
5
#include "util/evlist.h"
6
#include "util/machine.h"
7
#include "util/session.h"
8
#include "util/thread.h"
A
Arnaldo Carvalho de Melo 已提交
9
#include "util/parse-options.h"
10
#include "util/strlist.h"
11
#include "util/intlist.h"
A
Arnaldo Carvalho de Melo 已提交
12
#include "util/thread_map.h"
13
#include "util/stat.h"
A
Arnaldo Carvalho de Melo 已提交
14 15 16

#include <libaudit.h>
#include <stdlib.h>
17
#include <sys/eventfd.h>
18
#include <sys/mman.h>
19
#include <linux/futex.h>
A
Arnaldo Carvalho de Melo 已提交
20

21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37
/* For older distros: */
#ifndef MAP_STACK
# define MAP_STACK		0x20000
#endif

#ifndef MADV_HWPOISON
# define MADV_HWPOISON		100
#endif

#ifndef MADV_MERGEABLE
# define MADV_MERGEABLE		12
#endif

#ifndef MADV_UNMERGEABLE
# define MADV_UNMERGEABLE	13
#endif

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
struct tp_field {
	int offset;
	union {
		u64 (*integer)(struct tp_field *field, struct perf_sample *sample);
		void *(*pointer)(struct tp_field *field, struct perf_sample *sample);
	};
};

#define TP_UINT_FIELD(bits) \
static u64 tp_field__u##bits(struct tp_field *field, struct perf_sample *sample) \
{ \
	return *(u##bits *)(sample->raw_data + field->offset); \
}

TP_UINT_FIELD(8);
TP_UINT_FIELD(16);
TP_UINT_FIELD(32);
TP_UINT_FIELD(64);

#define TP_UINT_FIELD__SWAPPED(bits) \
static u64 tp_field__swapped_u##bits(struct tp_field *field, struct perf_sample *sample) \
{ \
	u##bits value = *(u##bits *)(sample->raw_data + field->offset); \
	return bswap_##bits(value);\
}

TP_UINT_FIELD__SWAPPED(16);
TP_UINT_FIELD__SWAPPED(32);
TP_UINT_FIELD__SWAPPED(64);

static int tp_field__init_uint(struct tp_field *field,
			       struct format_field *format_field,
			       bool needs_swap)
{
	field->offset = format_field->offset;

	switch (format_field->size) {
	case 1:
		field->integer = tp_field__u8;
		break;
	case 2:
		field->integer = needs_swap ? tp_field__swapped_u16 : tp_field__u16;
		break;
	case 4:
		field->integer = needs_swap ? tp_field__swapped_u32 : tp_field__u32;
		break;
	case 8:
		field->integer = needs_swap ? tp_field__swapped_u64 : tp_field__u64;
		break;
	default:
		return -1;
	}

	return 0;
}

static void *tp_field__ptr(struct tp_field *field, struct perf_sample *sample)
{
	return sample->raw_data + field->offset;
}

static int tp_field__init_ptr(struct tp_field *field, struct format_field *format_field)
{
	field->offset = format_field->offset;
	field->pointer = tp_field__ptr;
	return 0;
}

struct syscall_tp {
	struct tp_field id;
	union {
		struct tp_field args, ret;
	};
};

static int perf_evsel__init_tp_uint_field(struct perf_evsel *evsel,
					  struct tp_field *field,
					  const char *name)
{
	struct format_field *format_field = perf_evsel__field(evsel, name);

	if (format_field == NULL)
		return -1;

	return tp_field__init_uint(field, format_field, evsel->needs_swap);
}

#define perf_evsel__init_sc_tp_uint_field(evsel, name) \
	({ struct syscall_tp *sc = evsel->priv;\
	   perf_evsel__init_tp_uint_field(evsel, &sc->name, #name); })

static int perf_evsel__init_tp_ptr_field(struct perf_evsel *evsel,
					 struct tp_field *field,
					 const char *name)
{
	struct format_field *format_field = perf_evsel__field(evsel, name);

	if (format_field == NULL)
		return -1;

	return tp_field__init_ptr(field, format_field);
}

#define perf_evsel__init_sc_tp_ptr_field(evsel, name) \
	({ struct syscall_tp *sc = evsel->priv;\
	   perf_evsel__init_tp_ptr_field(evsel, &sc->name, #name); })

static void perf_evsel__delete_priv(struct perf_evsel *evsel)
{
	free(evsel->priv);
	evsel->priv = NULL;
	perf_evsel__delete(evsel);
}

152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170
static int perf_evsel__init_syscall_tp(struct perf_evsel *evsel, void *handler)
{
	evsel->priv = malloc(sizeof(struct syscall_tp));
	if (evsel->priv != NULL) {
		if (perf_evsel__init_sc_tp_uint_field(evsel, id))
			goto out_delete;

		evsel->handler = handler;
		return 0;
	}

	return -ENOMEM;

out_delete:
	free(evsel->priv);
	evsel->priv = NULL;
	return -ENOENT;
}

171
static struct perf_evsel *perf_evsel__syscall_newtp(const char *direction, void *handler)
172
{
173
	struct perf_evsel *evsel = perf_evsel__newtp("raw_syscalls", direction);
174 175

	if (evsel) {
176
		if (perf_evsel__init_syscall_tp(evsel, handler))
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
			goto out_delete;
	}

	return evsel;

out_delete:
	perf_evsel__delete_priv(evsel);
	return NULL;
}

#define perf_evsel__sc_tp_uint(evsel, name, sample) \
	({ struct syscall_tp *fields = evsel->priv; \
	   fields->name.integer(&fields->name, sample); })

#define perf_evsel__sc_tp_ptr(evsel, name, sample) \
	({ struct syscall_tp *fields = evsel->priv; \
	   fields->name.pointer(&fields->name, sample); })

static int perf_evlist__add_syscall_newtp(struct perf_evlist *evlist,
					  void *sys_enter_handler,
					  void *sys_exit_handler)
{
	int ret = -1;
	struct perf_evsel *sys_enter, *sys_exit;

202
	sys_enter = perf_evsel__syscall_newtp("sys_enter", sys_enter_handler);
203 204 205 206 207 208
	if (sys_enter == NULL)
		goto out;

	if (perf_evsel__init_sc_tp_ptr_field(sys_enter, args))
		goto out_delete_sys_enter;

209
	sys_exit = perf_evsel__syscall_newtp("sys_exit", sys_exit_handler);
210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230
	if (sys_exit == NULL)
		goto out_delete_sys_enter;

	if (perf_evsel__init_sc_tp_uint_field(sys_exit, ret))
		goto out_delete_sys_exit;

	perf_evlist__add(evlist, sys_enter);
	perf_evlist__add(evlist, sys_exit);

	ret = 0;
out:
	return ret;

out_delete_sys_exit:
	perf_evsel__delete_priv(sys_exit);
out_delete_sys_enter:
	perf_evsel__delete_priv(sys_enter);
	goto out;
}


231 232
struct syscall_arg {
	unsigned long val;
233 234
	struct thread *thread;
	struct trace  *trace;
235
	void	      *parm;
236 237 238 239
	u8	      idx;
	u8	      mask;
};

240
struct strarray {
241
	int	    offset;
242 243 244 245 246 247 248 249 250
	int	    nr_entries;
	const char **entries;
};

#define DEFINE_STRARRAY(array) struct strarray strarray__##array = { \
	.nr_entries = ARRAY_SIZE(array), \
	.entries = array, \
}

251 252 253 254 255 256
#define DEFINE_STRARRAY_OFFSET(array, off) struct strarray strarray__##array = { \
	.offset	    = off, \
	.nr_entries = ARRAY_SIZE(array), \
	.entries = array, \
}

257 258 259
static size_t __syscall_arg__scnprintf_strarray(char *bf, size_t size,
						const char *intfmt,
					        struct syscall_arg *arg)
260 261
{
	struct strarray *sa = arg->parm;
262
	int idx = arg->val - sa->offset;
263 264

	if (idx < 0 || idx >= sa->nr_entries)
265
		return scnprintf(bf, size, intfmt, arg->val);
266 267 268 269

	return scnprintf(bf, size, "%s", sa->entries[idx]);
}

270 271 272 273 274 275
static size_t syscall_arg__scnprintf_strarray(char *bf, size_t size,
					      struct syscall_arg *arg)
{
	return __syscall_arg__scnprintf_strarray(bf, size, "%d", arg);
}

276 277
#define SCA_STRARRAY syscall_arg__scnprintf_strarray

278 279 280 281 282 283 284 285
static size_t syscall_arg__scnprintf_strhexarray(char *bf, size_t size,
						 struct syscall_arg *arg)
{
	return __syscall_arg__scnprintf_strarray(bf, size, "%#x", arg);
}

#define SCA_STRHEXARRAY syscall_arg__scnprintf_strhexarray

286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308
static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
					struct syscall_arg *arg);

#define SCA_FD syscall_arg__scnprintf_fd

static size_t syscall_arg__scnprintf_fd_at(char *bf, size_t size,
					   struct syscall_arg *arg)
{
	int fd = arg->val;

	if (fd == AT_FDCWD)
		return scnprintf(bf, size, "CWD");

	return syscall_arg__scnprintf_fd(bf, size, arg);
}

#define SCA_FDAT syscall_arg__scnprintf_fd_at

static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
					      struct syscall_arg *arg);

#define SCA_CLOSE_FD syscall_arg__scnprintf_close_fd

309
static size_t syscall_arg__scnprintf_hex(char *bf, size_t size,
310
					 struct syscall_arg *arg)
311
{
312
	return scnprintf(bf, size, "%#lx", arg->val);
313 314
}

315 316
#define SCA_HEX syscall_arg__scnprintf_hex

317
static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
318
					       struct syscall_arg *arg)
319
{
320
	int printed = 0, prot = arg->val;
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

	if (prot == PROT_NONE)
		return scnprintf(bf, size, "NONE");
#define	P_MMAP_PROT(n) \
	if (prot & PROT_##n) { \
		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
		prot &= ~PROT_##n; \
	}

	P_MMAP_PROT(EXEC);
	P_MMAP_PROT(READ);
	P_MMAP_PROT(WRITE);
#ifdef PROT_SEM
	P_MMAP_PROT(SEM);
#endif
	P_MMAP_PROT(GROWSDOWN);
	P_MMAP_PROT(GROWSUP);
#undef P_MMAP_PROT

	if (prot)
		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", prot);

	return printed;
}

#define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot

348
static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
349
						struct syscall_arg *arg)
350
{
351
	int printed = 0, flags = arg->val;
352 353 354 355 356 357 358 359 360

#define	P_MMAP_FLAG(n) \
	if (flags & MAP_##n) { \
		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
		flags &= ~MAP_##n; \
	}

	P_MMAP_FLAG(SHARED);
	P_MMAP_FLAG(PRIVATE);
361
#ifdef MAP_32BIT
362
	P_MMAP_FLAG(32BIT);
363
#endif
364 365 366 367 368 369
	P_MMAP_FLAG(ANONYMOUS);
	P_MMAP_FLAG(DENYWRITE);
	P_MMAP_FLAG(EXECUTABLE);
	P_MMAP_FLAG(FILE);
	P_MMAP_FLAG(FIXED);
	P_MMAP_FLAG(GROWSDOWN);
370
#ifdef MAP_HUGETLB
371
	P_MMAP_FLAG(HUGETLB);
372
#endif
373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390
	P_MMAP_FLAG(LOCKED);
	P_MMAP_FLAG(NONBLOCK);
	P_MMAP_FLAG(NORESERVE);
	P_MMAP_FLAG(POPULATE);
	P_MMAP_FLAG(STACK);
#ifdef MAP_UNINITIALIZED
	P_MMAP_FLAG(UNINITIALIZED);
#endif
#undef P_MMAP_FLAG

	if (flags)
		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);

	return printed;
}

#define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags

391
static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
392
						      struct syscall_arg *arg)
393
{
394
	int behavior = arg->val;
395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411

	switch (behavior) {
#define	P_MADV_BHV(n) case MADV_##n: return scnprintf(bf, size, #n)
	P_MADV_BHV(NORMAL);
	P_MADV_BHV(RANDOM);
	P_MADV_BHV(SEQUENTIAL);
	P_MADV_BHV(WILLNEED);
	P_MADV_BHV(DONTNEED);
	P_MADV_BHV(REMOVE);
	P_MADV_BHV(DONTFORK);
	P_MADV_BHV(DOFORK);
	P_MADV_BHV(HWPOISON);
#ifdef MADV_SOFT_OFFLINE
	P_MADV_BHV(SOFT_OFFLINE);
#endif
	P_MADV_BHV(MERGEABLE);
	P_MADV_BHV(UNMERGEABLE);
412
#ifdef MADV_HUGEPAGE
413
	P_MADV_BHV(HUGEPAGE);
414 415
#endif
#ifdef MADV_NOHUGEPAGE
416
	P_MADV_BHV(NOHUGEPAGE);
417
#endif
418 419 420 421 422 423 424 425 426 427 428 429 430 431 432
#ifdef MADV_DONTDUMP
	P_MADV_BHV(DONTDUMP);
#endif
#ifdef MADV_DODUMP
	P_MADV_BHV(DODUMP);
#endif
#undef P_MADV_PHV
	default: break;
	}

	return scnprintf(bf, size, "%#x", behavior);
}

#define SCA_MADV_BHV syscall_arg__scnprintf_madvise_behavior

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
static size_t syscall_arg__scnprintf_flock(char *bf, size_t size,
					   struct syscall_arg *arg)
{
	int printed = 0, op = arg->val;

	if (op == 0)
		return scnprintf(bf, size, "NONE");
#define	P_CMD(cmd) \
	if ((op & LOCK_##cmd) == LOCK_##cmd) { \
		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #cmd); \
		op &= ~LOCK_##cmd; \
	}

	P_CMD(SH);
	P_CMD(EX);
	P_CMD(NB);
	P_CMD(UN);
	P_CMD(MAND);
	P_CMD(RW);
	P_CMD(READ);
	P_CMD(WRITE);
#undef P_OP

	if (op)
		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", op);

	return printed;
}

#define SCA_FLOCK syscall_arg__scnprintf_flock

464
static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, struct syscall_arg *arg)
465 466 467 468 469 470 471 472 473
{
	enum syscall_futex_args {
		SCF_UADDR   = (1 << 0),
		SCF_OP	    = (1 << 1),
		SCF_VAL	    = (1 << 2),
		SCF_TIMEOUT = (1 << 3),
		SCF_UADDR2  = (1 << 4),
		SCF_VAL3    = (1 << 5),
	};
474
	int op = arg->val;
475 476 477 478 479
	int cmd = op & FUTEX_CMD_MASK;
	size_t printed = 0;

	switch (cmd) {
#define	P_FUTEX_OP(n) case FUTEX_##n: printed = scnprintf(bf, size, #n);
480 481 482 483 484 485
	P_FUTEX_OP(WAIT);	    arg->mask |= SCF_VAL3|SCF_UADDR2;		  break;
	P_FUTEX_OP(WAKE);	    arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
	P_FUTEX_OP(FD);		    arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
	P_FUTEX_OP(REQUEUE);	    arg->mask |= SCF_VAL3|SCF_TIMEOUT;	          break;
	P_FUTEX_OP(CMP_REQUEUE);    arg->mask |= SCF_TIMEOUT;			  break;
	P_FUTEX_OP(CMP_REQUEUE_PI); arg->mask |= SCF_TIMEOUT;			  break;
486
	P_FUTEX_OP(WAKE_OP);							  break;
487 488 489 490 491
	P_FUTEX_OP(LOCK_PI);	    arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
	P_FUTEX_OP(UNLOCK_PI);	    arg->mask |= SCF_VAL3|SCF_UADDR2|SCF_TIMEOUT; break;
	P_FUTEX_OP(TRYLOCK_PI);	    arg->mask |= SCF_VAL3|SCF_UADDR2;		  break;
	P_FUTEX_OP(WAIT_BITSET);    arg->mask |= SCF_UADDR2;			  break;
	P_FUTEX_OP(WAKE_BITSET);    arg->mask |= SCF_UADDR2;			  break;
492 493 494 495 496 497 498 499 500 501 502 503 504
	P_FUTEX_OP(WAIT_REQUEUE_PI);						  break;
	default: printed = scnprintf(bf, size, "%#x", cmd);			  break;
	}

	if (op & FUTEX_PRIVATE_FLAG)
		printed += scnprintf(bf + printed, size - printed, "|PRIV");

	if (op & FUTEX_CLOCK_REALTIME)
		printed += scnprintf(bf + printed, size - printed, "|CLKRT");

	return printed;
}

505 506
#define SCA_FUTEX_OP  syscall_arg__scnprintf_futex_op

507 508
static const char *epoll_ctl_ops[] = { "ADD", "DEL", "MOD", };
static DEFINE_STRARRAY_OFFSET(epoll_ctl_ops, 1);
509

510 511 512
static const char *itimers[] = { "REAL", "VIRTUAL", "PROF", };
static DEFINE_STRARRAY(itimers);

513 514 515 516 517 518 519 520 521
static const char *whences[] = { "SET", "CUR", "END",
#ifdef SEEK_DATA
"DATA",
#endif
#ifdef SEEK_HOLE
"HOLE",
#endif
};
static DEFINE_STRARRAY(whences);
522

523 524 525 526 527 528 529 530
static const char *fcntl_cmds[] = {
	"DUPFD", "GETFD", "SETFD", "GETFL", "SETFL", "GETLK", "SETLK",
	"SETLKW", "SETOWN", "GETOWN", "SETSIG", "GETSIG", "F_GETLK64",
	"F_SETLK64", "F_SETLKW64", "F_SETOWN_EX", "F_GETOWN_EX",
	"F_GETOWNER_UIDS",
};
static DEFINE_STRARRAY(fcntl_cmds);

531 532 533 534 535 536 537
static const char *rlimit_resources[] = {
	"CPU", "FSIZE", "DATA", "STACK", "CORE", "RSS", "NPROC", "NOFILE",
	"MEMLOCK", "AS", "LOCKS", "SIGPENDING", "MSGQUEUE", "NICE", "RTPRIO",
	"RTTIME",
};
static DEFINE_STRARRAY(rlimit_resources);

538 539 540
static const char *sighow[] = { "BLOCK", "UNBLOCK", "SETMASK", };
static DEFINE_STRARRAY(sighow);

541 542 543 544 545 546
static const char *clockid[] = {
	"REALTIME", "MONOTONIC", "PROCESS_CPUTIME_ID", "THREAD_CPUTIME_ID",
	"MONOTONIC_RAW", "REALTIME_COARSE", "MONOTONIC_COARSE",
};
static DEFINE_STRARRAY(clockid);

547 548 549 550 551 552 553 554 555 556
static const char *socket_families[] = {
	"UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM",
	"BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI",
	"SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC",
	"RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC",
	"BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF",
	"ALG", "NFC", "VSOCK",
};
static DEFINE_STRARRAY(socket_families);

557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603
#ifndef SOCK_TYPE_MASK
#define SOCK_TYPE_MASK 0xf
#endif

static size_t syscall_arg__scnprintf_socket_type(char *bf, size_t size,
						      struct syscall_arg *arg)
{
	size_t printed;
	int type = arg->val,
	    flags = type & ~SOCK_TYPE_MASK;

	type &= SOCK_TYPE_MASK;
	/*
 	 * Can't use a strarray, MIPS may override for ABI reasons.
 	 */
	switch (type) {
#define	P_SK_TYPE(n) case SOCK_##n: printed = scnprintf(bf, size, #n); break;
	P_SK_TYPE(STREAM);
	P_SK_TYPE(DGRAM);
	P_SK_TYPE(RAW);
	P_SK_TYPE(RDM);
	P_SK_TYPE(SEQPACKET);
	P_SK_TYPE(DCCP);
	P_SK_TYPE(PACKET);
#undef P_SK_TYPE
	default:
		printed = scnprintf(bf, size, "%#x", type);
	}

#define	P_SK_FLAG(n) \
	if (flags & SOCK_##n) { \
		printed += scnprintf(bf + printed, size - printed, "|%s", #n); \
		flags &= ~SOCK_##n; \
	}

	P_SK_FLAG(CLOEXEC);
	P_SK_FLAG(NONBLOCK);
#undef P_SK_FLAG

	if (flags)
		printed += scnprintf(bf + printed, size - printed, "|%#x", flags);

	return printed;
}

#define SCA_SK_TYPE syscall_arg__scnprintf_socket_type

604 605 606
#ifndef MSG_PROBE
#define MSG_PROBE	     0x10
#endif
607 608 609
#ifndef MSG_WAITFORONE
#define MSG_WAITFORONE	0x10000
#endif
610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660
#ifndef MSG_SENDPAGE_NOTLAST
#define MSG_SENDPAGE_NOTLAST 0x20000
#endif
#ifndef MSG_FASTOPEN
#define MSG_FASTOPEN	     0x20000000
#endif

static size_t syscall_arg__scnprintf_msg_flags(char *bf, size_t size,
					       struct syscall_arg *arg)
{
	int printed = 0, flags = arg->val;

	if (flags == 0)
		return scnprintf(bf, size, "NONE");
#define	P_MSG_FLAG(n) \
	if (flags & MSG_##n) { \
		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
		flags &= ~MSG_##n; \
	}

	P_MSG_FLAG(OOB);
	P_MSG_FLAG(PEEK);
	P_MSG_FLAG(DONTROUTE);
	P_MSG_FLAG(TRYHARD);
	P_MSG_FLAG(CTRUNC);
	P_MSG_FLAG(PROBE);
	P_MSG_FLAG(TRUNC);
	P_MSG_FLAG(DONTWAIT);
	P_MSG_FLAG(EOR);
	P_MSG_FLAG(WAITALL);
	P_MSG_FLAG(FIN);
	P_MSG_FLAG(SYN);
	P_MSG_FLAG(CONFIRM);
	P_MSG_FLAG(RST);
	P_MSG_FLAG(ERRQUEUE);
	P_MSG_FLAG(NOSIGNAL);
	P_MSG_FLAG(MORE);
	P_MSG_FLAG(WAITFORONE);
	P_MSG_FLAG(SENDPAGE_NOTLAST);
	P_MSG_FLAG(FASTOPEN);
	P_MSG_FLAG(CMSG_CLOEXEC);
#undef P_MSG_FLAG

	if (flags)
		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);

	return printed;
}

#define SCA_MSG_FLAGS syscall_arg__scnprintf_msg_flags

661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687
static size_t syscall_arg__scnprintf_access_mode(char *bf, size_t size,
						 struct syscall_arg *arg)
{
	size_t printed = 0;
	int mode = arg->val;

	if (mode == F_OK) /* 0 */
		return scnprintf(bf, size, "F");
#define	P_MODE(n) \
	if (mode & n##_OK) { \
		printed += scnprintf(bf + printed, size - printed, "%s", #n); \
		mode &= ~n##_OK; \
	}

	P_MODE(R);
	P_MODE(W);
	P_MODE(X);
#undef P_MODE

	if (mode)
		printed += scnprintf(bf + printed, size - printed, "|%#x", mode);

	return printed;
}

#define SCA_ACCMODE syscall_arg__scnprintf_access_mode

688
static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
689
					       struct syscall_arg *arg)
690
{
691
	int printed = 0, flags = arg->val;
692 693

	if (!(flags & O_CREAT))
694
		arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */
695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743

	if (flags == 0)
		return scnprintf(bf, size, "RDONLY");
#define	P_FLAG(n) \
	if (flags & O_##n) { \
		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
		flags &= ~O_##n; \
	}

	P_FLAG(APPEND);
	P_FLAG(ASYNC);
	P_FLAG(CLOEXEC);
	P_FLAG(CREAT);
	P_FLAG(DIRECT);
	P_FLAG(DIRECTORY);
	P_FLAG(EXCL);
	P_FLAG(LARGEFILE);
	P_FLAG(NOATIME);
	P_FLAG(NOCTTY);
#ifdef O_NONBLOCK
	P_FLAG(NONBLOCK);
#elif O_NDELAY
	P_FLAG(NDELAY);
#endif
#ifdef O_PATH
	P_FLAG(PATH);
#endif
	P_FLAG(RDWR);
#ifdef O_DSYNC
	if ((flags & O_SYNC) == O_SYNC)
		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", "SYNC");
	else {
		P_FLAG(DSYNC);
	}
#else
	P_FLAG(SYNC);
#endif
	P_FLAG(TRUNC);
	P_FLAG(WRONLY);
#undef P_FLAG

	if (flags)
		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);

	return printed;
}

#define SCA_OPEN_FLAGS syscall_arg__scnprintf_open_flags

744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769
static size_t syscall_arg__scnprintf_eventfd_flags(char *bf, size_t size,
						   struct syscall_arg *arg)
{
	int printed = 0, flags = arg->val;

	if (flags == 0)
		return scnprintf(bf, size, "NONE");
#define	P_FLAG(n) \
	if (flags & EFD_##n) { \
		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
		flags &= ~EFD_##n; \
	}

	P_FLAG(SEMAPHORE);
	P_FLAG(CLOEXEC);
	P_FLAG(NONBLOCK);
#undef P_FLAG

	if (flags)
		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);

	return printed;
}

#define SCA_EFD_FLAGS syscall_arg__scnprintf_eventfd_flags

770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792
static size_t syscall_arg__scnprintf_pipe_flags(char *bf, size_t size,
						struct syscall_arg *arg)
{
	int printed = 0, flags = arg->val;

#define	P_FLAG(n) \
	if (flags & O_##n) { \
		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
		flags &= ~O_##n; \
	}

	P_FLAG(CLOEXEC);
	P_FLAG(NONBLOCK);
#undef P_FLAG

	if (flags)
		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);

	return printed;
}

#define SCA_PIPE_FLAGS syscall_arg__scnprintf_pipe_flags

793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837
static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg)
{
	int sig = arg->val;

	switch (sig) {
#define	P_SIGNUM(n) case SIG##n: return scnprintf(bf, size, #n)
	P_SIGNUM(HUP);
	P_SIGNUM(INT);
	P_SIGNUM(QUIT);
	P_SIGNUM(ILL);
	P_SIGNUM(TRAP);
	P_SIGNUM(ABRT);
	P_SIGNUM(BUS);
	P_SIGNUM(FPE);
	P_SIGNUM(KILL);
	P_SIGNUM(USR1);
	P_SIGNUM(SEGV);
	P_SIGNUM(USR2);
	P_SIGNUM(PIPE);
	P_SIGNUM(ALRM);
	P_SIGNUM(TERM);
	P_SIGNUM(STKFLT);
	P_SIGNUM(CHLD);
	P_SIGNUM(CONT);
	P_SIGNUM(STOP);
	P_SIGNUM(TSTP);
	P_SIGNUM(TTIN);
	P_SIGNUM(TTOU);
	P_SIGNUM(URG);
	P_SIGNUM(XCPU);
	P_SIGNUM(XFSZ);
	P_SIGNUM(VTALRM);
	P_SIGNUM(PROF);
	P_SIGNUM(WINCH);
	P_SIGNUM(IO);
	P_SIGNUM(PWR);
	P_SIGNUM(SYS);
	default: break;
	}

	return scnprintf(bf, size, "%#x", sig);
}

#define SCA_SIGNUM syscall_arg__scnprintf_signum

838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859
#define TCGETS		0x5401

static const char *tioctls[] = {
	"TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW",
	"TCSETAF", "TCSBRK", "TCXONC", "TCFLSH", "TIOCEXCL", "TIOCNXCL",
	"TIOCSCTTY", "TIOCGPGRP", "TIOCSPGRP", "TIOCOUTQ", "TIOCSTI",
	"TIOCGWINSZ", "TIOCSWINSZ", "TIOCMGET", "TIOCMBIS", "TIOCMBIC",
	"TIOCMSET", "TIOCGSOFTCAR", "TIOCSSOFTCAR", "FIONREAD", "TIOCLINUX",
	"TIOCCONS", "TIOCGSERIAL", "TIOCSSERIAL", "TIOCPKT", "FIONBIO",
	"TIOCNOTTY", "TIOCSETD", "TIOCGETD", "TCSBRKP", [0x27] = "TIOCSBRK",
	"TIOCCBRK", "TIOCGSID", "TCGETS2", "TCSETS2", "TCSETSW2", "TCSETSF2",
	"TIOCGRS485", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK",
	"TIOCGDEV||TCGETX", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG",
	"TIOCVHANGUP", "TIOCGPKT", "TIOCGPTLCK", "TIOCGEXCL",
	[0x50] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG",
	"TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS",
	"TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI",
	"TIOCMIWAIT", "TIOCGICOUNT", [0x60] = "FIOQSIZE",
};

static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401);

860 861 862 863
#define STRARRAY(arg, name, array) \
	  .arg_scnprintf = { [arg] = SCA_STRARRAY, }, \
	  .arg_parm	 = { [arg] = &strarray__##array, }

A
Arnaldo Carvalho de Melo 已提交
864 865
static struct syscall_fmt {
	const char *name;
866
	const char *alias;
867
	size_t	   (*arg_scnprintf[6])(char *bf, size_t size, struct syscall_arg *arg);
868
	void	   *arg_parm[6];
A
Arnaldo Carvalho de Melo 已提交
869 870
	bool	   errmsg;
	bool	   timeout;
871
	bool	   hexret;
A
Arnaldo Carvalho de Melo 已提交
872
} syscall_fmts[] = {
873 874
	{ .name	    = "access",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_ACCMODE, /* mode */ }, },
875
	{ .name	    = "arch_prctl", .errmsg = true, .alias = "prctl", },
876 877
	{ .name	    = "brk",	    .hexret = true,
	  .arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, },
878
	{ .name     = "clock_gettime",  .errmsg = true, STRARRAY(0, clk_id, clockid), },
879 880
	{ .name	    = "close",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, }, 
881
	{ .name	    = "connect",    .errmsg = true, },
882 883 884 885 886 887
	{ .name	    = "dup",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
	{ .name	    = "dup2",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
	{ .name	    = "dup3",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
888
	{ .name	    = "epoll_ctl",  .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), },
889 890
	{ .name	    = "eventfd2",   .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, },
891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912
	{ .name	    = "faccessat",  .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
	{ .name	    = "fadvise64",  .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
	{ .name	    = "fallocate",  .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
	{ .name	    = "fchdir",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
	{ .name	    = "fchmod",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
	{ .name	    = "fchmodat",   .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
	{ .name	    = "fchown",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
	{ .name	    = "fchownat",   .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
	{ .name	    = "fcntl",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
			     [1] = SCA_STRARRAY, /* cmd */ },
	  .arg_parm	 = { [1] = &strarray__fcntl_cmds, /* cmd */ }, },
	{ .name	    = "fdatasync",  .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
913
	{ .name	    = "flock",	    .errmsg = true,
914 915 916 917 918 919 920 921 922 923 924 925 926 927
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
			     [1] = SCA_FLOCK, /* cmd */ }, },
	{ .name	    = "fsetxattr",  .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
	{ .name	    = "fstat",	    .errmsg = true, .alias = "newfstat",
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
	{ .name	    = "fstatat",    .errmsg = true, .alias = "newfstatat",
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
	{ .name	    = "fstatfs",    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
	{ .name	    = "fsync",    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
	{ .name	    = "ftruncate", .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
928 929
	{ .name	    = "futex",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, },
930 931 932 933 934 935
	{ .name	    = "futimesat", .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
	{ .name	    = "getdents",   .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
	{ .name	    = "getdents64", .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
936 937
	{ .name	    = "getitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
	{ .name	    = "getrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
938
	{ .name	    = "ioctl",	    .errmsg = true,
939
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ 
940 941 942
			     [1] = SCA_STRHEXARRAY, /* cmd */
			     [2] = SCA_HEX, /* arg */ },
	  .arg_parm	 = { [1] = &strarray__tioctls, /* cmd */ }, },
943 944
	{ .name	    = "kill",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
945 946 947 948 949 950
	{ .name	    = "linkat",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
	{ .name	    = "lseek",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */
			     [2] = SCA_STRARRAY, /* whence */ },
	  .arg_parm	 = { [2] = &strarray__whences, /* whence */ }, },
951
	{ .name	    = "lstat",	    .errmsg = true, .alias = "newlstat", },
952 953 954
	{ .name     = "madvise",    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_HEX,	 /* start */
			     [2] = SCA_MADV_BHV, /* behavior */ }, },
955 956 957 958
	{ .name	    = "mkdirat",    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
	{ .name	    = "mknodat",    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
959 960 961 962
	{ .name	    = "mlock",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
	{ .name	    = "mlockall",   .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
963
	{ .name	    = "mmap",	    .hexret = true,
964
	  .arg_scnprintf = { [0] = SCA_HEX,	  /* addr */
965
			     [2] = SCA_MMAP_PROT, /* prot */
966 967
			     [3] = SCA_MMAP_FLAGS, /* flags */
			     [4] = SCA_FD, 	  /* fd */ }, },
968
	{ .name	    = "mprotect",   .errmsg = true,
969 970 971 972 973
	  .arg_scnprintf = { [0] = SCA_HEX, /* start */
			     [2] = SCA_MMAP_PROT, /* prot */ }, },
	{ .name	    = "mremap",	    .hexret = true,
	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */
			     [4] = SCA_HEX, /* new_addr */ }, },
974 975
	{ .name	    = "munlock",    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
976 977
	{ .name	    = "munmap",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
978 979 980 981
	{ .name	    = "name_to_handle_at", .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
	{ .name	    = "newfstatat", .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
982 983
	{ .name	    = "open",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, },
984
	{ .name	    = "open_by_handle_at", .errmsg = true,
985 986
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
			     [2] = SCA_OPEN_FLAGS, /* flags */ }, },
987
	{ .name	    = "openat",	    .errmsg = true,
988 989
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
			     [2] = SCA_OPEN_FLAGS, /* flags */ }, },
990 991
	{ .name	    = "pipe2",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, },
992 993
	{ .name	    = "poll",	    .errmsg = true, .timeout = true, },
	{ .name	    = "ppoll",	    .errmsg = true, .timeout = true, },
994 995 996 997
	{ .name	    = "pread",	    .errmsg = true, .alias = "pread64",
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
	{ .name	    = "preadv",	    .errmsg = true, .alias = "pread",
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
998
	{ .name	    = "prlimit64",  .errmsg = true, STRARRAY(1, resource, rlimit_resources), },
999 1000 1001 1002 1003 1004 1005 1006 1007 1008
	{ .name	    = "pwrite",	    .errmsg = true, .alias = "pwrite64",
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
	{ .name	    = "pwritev",    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
	{ .name	    = "read",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
	{ .name	    = "readlinkat", .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
	{ .name	    = "readv",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
1009 1010 1011 1012 1013 1014
	{ .name	    = "recvfrom",   .errmsg = true,
	  .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
	{ .name	    = "recvmmsg",   .errmsg = true,
	  .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
	{ .name	    = "recvmsg",    .errmsg = true,
	  .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
1015 1016
	{ .name	    = "renameat",   .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
1017 1018
	{ .name	    = "rt_sigaction", .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, },
1019
	{ .name	    = "rt_sigprocmask",  .errmsg = true, STRARRAY(0, how, sighow), },
1020 1021 1022 1023
	{ .name	    = "rt_sigqueueinfo", .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
	{ .name	    = "rt_tgsigqueueinfo", .errmsg = true,
	  .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
1024
	{ .name	    = "select",	    .errmsg = true, .timeout = true, },
1025 1026 1027 1028 1029 1030
	{ .name	    = "sendmmsg",    .errmsg = true,
	  .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
	{ .name	    = "sendmsg",    .errmsg = true,
	  .arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
	{ .name	    = "sendto",	    .errmsg = true,
	  .arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
1031 1032
	{ .name	    = "setitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
	{ .name	    = "setrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
1033 1034
	{ .name	    = "shutdown",   .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
1035
	{ .name	    = "socket",	    .errmsg = true,
1036 1037
	  .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
			     [1] = SCA_SK_TYPE, /* type */ },
1038 1039 1040 1041
	  .arg_parm	 = { [0] = &strarray__socket_families, /* family */ }, },
	{ .name	    = "socketpair", .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
			     [1] = SCA_SK_TYPE, /* type */ },
1042
	  .arg_parm	 = { [0] = &strarray__socket_families, /* family */ }, },
1043
	{ .name	    = "stat",	    .errmsg = true, .alias = "newstat", },
1044 1045
	{ .name	    = "symlinkat",  .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
1046 1047 1048 1049
	{ .name	    = "tgkill",	    .errmsg = true,
	  .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
	{ .name	    = "tkill",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
1050
	{ .name	    = "uname",	    .errmsg = true, .alias = "newuname", },
1051 1052 1053 1054 1055 1056 1057 1058
	{ .name	    = "unlinkat",   .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
	{ .name	    = "utimensat",  .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */ }, },
	{ .name	    = "write",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
	{ .name	    = "writev",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
A
Arnaldo Carvalho de Melo 已提交
1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075
};

static int syscall_fmt__cmp(const void *name, const void *fmtp)
{
	const struct syscall_fmt *fmt = fmtp;
	return strcmp(name, fmt->name);
}

static struct syscall_fmt *syscall_fmt__find(const char *name)
{
	const int nmemb = ARRAY_SIZE(syscall_fmts);
	return bsearch(name, syscall_fmts, nmemb, sizeof(struct syscall_fmt), syscall_fmt__cmp);
}

struct syscall {
	struct event_format *tp_format;
	const char	    *name;
1076
	bool		    filtered;
A
Arnaldo Carvalho de Melo 已提交
1077
	struct syscall_fmt  *fmt;
1078
	size_t		    (**arg_scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
1079
	void		    **arg_parm;
A
Arnaldo Carvalho de Melo 已提交
1080 1081
};

1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092
static size_t fprintf_duration(unsigned long t, FILE *fp)
{
	double duration = (double)t / NSEC_PER_MSEC;
	size_t printed = fprintf(fp, "(");

	if (duration >= 1.0)
		printed += color_fprintf(fp, PERF_COLOR_RED, "%6.3f ms", duration);
	else if (duration >= 0.01)
		printed += color_fprintf(fp, PERF_COLOR_YELLOW, "%6.3f ms", duration);
	else
		printed += color_fprintf(fp, PERF_COLOR_NORMAL, "%6.3f ms", duration);
1093
	return printed + fprintf(fp, "): ");
1094 1095
}

1096 1097 1098 1099
struct thread_trace {
	u64		  entry_time;
	u64		  exit_time;
	bool		  entry_pending;
1100
	unsigned long	  nr_events;
1101
	char		  *entry_str;
1102
	double		  runtime_ms;
1103 1104 1105 1106
	struct {
		int	  max;
		char	  **table;
	} paths;
1107 1108

	struct intlist *syscall_stats;
1109 1110 1111 1112
};

static struct thread_trace *thread_trace__new(void)
{
1113 1114 1115 1116 1117
	struct thread_trace *ttrace =  zalloc(sizeof(struct thread_trace));

	if (ttrace)
		ttrace->paths.max = -1;

1118 1119
	ttrace->syscall_stats = intlist__new(NULL);

1120
	return ttrace;
1121 1122
}

1123
static struct thread_trace *thread__trace(struct thread *thread, FILE *fp)
1124
{
1125 1126
	struct thread_trace *ttrace;

1127 1128 1129 1130 1131
	if (thread == NULL)
		goto fail;

	if (thread->priv == NULL)
		thread->priv = thread_trace__new();
1132
		
1133 1134 1135
	if (thread->priv == NULL)
		goto fail;

1136 1137 1138 1139
	ttrace = thread->priv;
	++ttrace->nr_events;

	return ttrace;
1140
fail:
1141
	color_fprintf(fp, PERF_COLOR_RED,
1142 1143 1144 1145
		      "WARNING: not enough memory, dropping samples!\n");
	return NULL;
}

A
Arnaldo Carvalho de Melo 已提交
1146
struct trace {
1147
	struct perf_tool	tool;
1148 1149 1150 1151
	struct {
		int		machine;
		int		open_id;
	}			audit;
A
Arnaldo Carvalho de Melo 已提交
1152 1153 1154 1155 1156
	struct {
		int		max;
		struct syscall  *table;
	} syscalls;
	struct perf_record_opts opts;
1157
	struct machine		*host;
1158
	u64			base_time;
1159
	bool			full_time;
1160
	FILE			*output;
1161
	unsigned long		nr_events;
1162 1163
	struct strlist		*ev_qualifier;
	bool			not_ev_qualifier;
1164
	bool			live;
1165
	const char 		*last_vfs_getname;
1166 1167
	struct intlist		*tid_list;
	struct intlist		*pid_list;
1168
	bool			sched;
1169
	bool			multiple_threads;
1170
	bool			summary;
D
David Ahern 已提交
1171
	bool			summary_only;
1172
	bool			show_comm;
1173
	bool			show_tool_stats;
1174
	double			duration_filter;
1175
	double			runtime_ms;
1176 1177 1178
	struct {
		u64		vfs_getname, proc_getname;
	} stats;
A
Arnaldo Carvalho de Melo 已提交
1179 1180
};

1181
static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206
{
	struct thread_trace *ttrace = thread->priv;

	if (fd > ttrace->paths.max) {
		char **npath = realloc(ttrace->paths.table, (fd + 1) * sizeof(char *));

		if (npath == NULL)
			return -1;

		if (ttrace->paths.max != -1) {
			memset(npath + ttrace->paths.max + 1, 0,
			       (fd - ttrace->paths.max) * sizeof(char *));
		} else {
			memset(npath, 0, (fd + 1) * sizeof(char *));
		}

		ttrace->paths.table = npath;
		ttrace->paths.max   = fd;
	}

	ttrace->paths.table[fd] = strdup(pathname);

	return ttrace->paths.table[fd] != NULL ? 0 : -1;
}

1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232
static int thread__read_fd_path(struct thread *thread, int fd)
{
	char linkname[PATH_MAX], pathname[PATH_MAX];
	struct stat st;
	int ret;

	if (thread->pid_ == thread->tid) {
		scnprintf(linkname, sizeof(linkname),
			  "/proc/%d/fd/%d", thread->pid_, fd);
	} else {
		scnprintf(linkname, sizeof(linkname),
			  "/proc/%d/task/%d/fd/%d", thread->pid_, thread->tid, fd);
	}

	if (lstat(linkname, &st) < 0 || st.st_size + 1 > (off_t)sizeof(pathname))
		return -1;

	ret = readlink(linkname, pathname, sizeof(pathname));

	if (ret < 0 || ret > st.st_size)
		return -1;

	pathname[ret] = '\0';
	return trace__set_fd_pathname(thread, fd, pathname);
}

1233 1234
static const char *thread__fd_path(struct thread *thread, int fd,
				   struct trace *trace)
1235 1236 1237 1238 1239 1240 1241 1242 1243
{
	struct thread_trace *ttrace = thread->priv;

	if (ttrace == NULL)
		return NULL;

	if (fd < 0)
		return NULL;

1244 1245 1246 1247 1248 1249 1250
	if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL))
		if (!trace->live)
			return NULL;
		++trace->stats.proc_getname;
		if (thread__read_fd_path(thread, fd)) {
			return NULL;
	}
1251 1252 1253 1254 1255 1256 1257 1258 1259

	return ttrace->paths.table[fd];
}

static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
					struct syscall_arg *arg)
{
	int fd = arg->val;
	size_t printed = scnprintf(bf, size, "%d", fd);
1260
	const char *path = thread__fd_path(arg->thread, fd, arg->trace);
1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282

	if (path)
		printed += scnprintf(bf + printed, size - printed, "<%s>", path);

	return printed;
}

static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
					      struct syscall_arg *arg)
{
	int fd = arg->val;
	size_t printed = syscall_arg__scnprintf_fd(bf, size, arg);
	struct thread_trace *ttrace = arg->thread->priv;

	if (ttrace && fd >= 0 && fd <= ttrace->paths.max) {
		free(ttrace->paths.table[fd]);
		ttrace->paths.table[fd] = NULL;
	}

	return printed;
}

1283 1284 1285 1286 1287
static bool trace__filter_duration(struct trace *trace, double t)
{
	return t < (trace->duration_filter * NSEC_PER_MSEC);
}

1288 1289 1290 1291
static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
{
	double ts = (double)(tstamp - trace->base_time) / NSEC_PER_MSEC;

1292
	return fprintf(fp, "%10.3f ", ts);
1293 1294
}

1295
static bool done = false;
1296
static bool interrupted = false;
1297

1298
static void sig_handler(int sig)
1299 1300
{
	done = true;
1301
	interrupted = sig == SIGINT;
1302 1303
}

1304
static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
1305
					u64 duration, u64 tstamp, FILE *fp)
1306 1307
{
	size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
1308
	printed += fprintf_duration(duration, fp);
1309

1310 1311
	if (trace->multiple_threads) {
		if (trace->show_comm)
1312
			printed += fprintf(fp, "%.14s/", thread__comm_str(thread));
1313
		printed += fprintf(fp, "%d ", thread->tid);
1314
	}
1315 1316 1317 1318

	return printed;
}

1319
static int trace__process_event(struct trace *trace, struct machine *machine,
1320
				union perf_event *event, struct perf_sample *sample)
1321 1322 1323 1324 1325
{
	int ret = 0;

	switch (event->header.type) {
	case PERF_RECORD_LOST:
1326
		color_fprintf(trace->output, PERF_COLOR_RED,
1327
			      "LOST %" PRIu64 " events!\n", event->lost.lost);
1328
		ret = machine__process_lost_event(machine, event, sample);
1329
	default:
1330
		ret = machine__process_event(machine, event, sample);
1331 1332 1333 1334 1335 1336
		break;
	}

	return ret;
}

1337
static int trace__tool_process(struct perf_tool *tool,
1338
			       union perf_event *event,
1339
			       struct perf_sample *sample,
1340 1341
			       struct machine *machine)
{
1342
	struct trace *trace = container_of(tool, struct trace, tool);
1343
	return trace__process_event(trace, machine, event, sample);
1344 1345 1346 1347 1348 1349 1350 1351 1352
}

static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
{
	int err = symbol__init();

	if (err)
		return err;

1353 1354 1355
	trace->host = machine__new_host();
	if (trace->host == NULL)
		return -ENOMEM;
1356

1357 1358
	err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
					    evlist->threads, trace__tool_process, false);
1359 1360 1361 1362 1363 1364
	if (err)
		symbol__exit();

	return err;
}

1365 1366 1367 1368 1369 1370 1371 1372 1373
static int syscall__set_arg_fmts(struct syscall *sc)
{
	struct format_field *field;
	int idx = 0;

	sc->arg_scnprintf = calloc(sc->tp_format->format.nr_fields - 1, sizeof(void *));
	if (sc->arg_scnprintf == NULL)
		return -1;

1374 1375 1376
	if (sc->fmt)
		sc->arg_parm = sc->fmt->arg_parm;

1377
	for (field = sc->tp_format->format.fields->next; field; field = field->next) {
1378 1379 1380
		if (sc->fmt && sc->fmt->arg_scnprintf[idx])
			sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx];
		else if (field->flags & FIELD_IS_POINTER)
1381 1382 1383 1384 1385 1386 1387
			sc->arg_scnprintf[idx] = syscall_arg__scnprintf_hex;
		++idx;
	}

	return 0;
}

A
Arnaldo Carvalho de Melo 已提交
1388 1389 1390 1391
static int trace__read_syscall_info(struct trace *trace, int id)
{
	char tp_name[128];
	struct syscall *sc;
1392
	const char *name = audit_syscall_to_name(id, trace->audit.machine);
1393 1394 1395

	if (name == NULL)
		return -1;
A
Arnaldo Carvalho de Melo 已提交
1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414

	if (id > trace->syscalls.max) {
		struct syscall *nsyscalls = realloc(trace->syscalls.table, (id + 1) * sizeof(*sc));

		if (nsyscalls == NULL)
			return -1;

		if (trace->syscalls.max != -1) {
			memset(nsyscalls + trace->syscalls.max + 1, 0,
			       (id - trace->syscalls.max) * sizeof(*sc));
		} else {
			memset(nsyscalls, 0, (id + 1) * sizeof(*sc));
		}

		trace->syscalls.table = nsyscalls;
		trace->syscalls.max   = id;
	}

	sc = trace->syscalls.table + id;
1415
	sc->name = name;
1416

1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427
	if (trace->ev_qualifier) {
		bool in = strlist__find(trace->ev_qualifier, name) != NULL;

		if (!(in ^ trace->not_ev_qualifier)) {
			sc->filtered = true;
			/*
			 * No need to do read tracepoint information since this will be
			 * filtered out.
			 */
			return 0;
		}
1428 1429
	}

1430
	sc->fmt  = syscall_fmt__find(sc->name);
A
Arnaldo Carvalho de Melo 已提交
1431

1432
	snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->name);
A
Arnaldo Carvalho de Melo 已提交
1433
	sc->tp_format = event_format__new("syscalls", tp_name);
1434 1435 1436 1437 1438

	if (sc->tp_format == NULL && sc->fmt && sc->fmt->alias) {
		snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->fmt->alias);
		sc->tp_format = event_format__new("syscalls", tp_name);
	}
A
Arnaldo Carvalho de Melo 已提交
1439

1440 1441 1442 1443
	if (sc->tp_format == NULL)
		return -1;

	return syscall__set_arg_fmts(sc);
A
Arnaldo Carvalho de Melo 已提交
1444 1445
}

1446
static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
1447 1448
				      unsigned long *args, struct trace *trace,
				      struct thread *thread)
A
Arnaldo Carvalho de Melo 已提交
1449 1450 1451 1452 1453
{
	size_t printed = 0;

	if (sc->tp_format != NULL) {
		struct format_field *field;
1454 1455
		u8 bit = 1;
		struct syscall_arg arg = {
1456 1457 1458 1459
			.idx	= 0,
			.mask	= 0,
			.trace  = trace,
			.thread = thread,
1460
		};
1461 1462

		for (field = sc->tp_format->format.fields->next; field;
1463 1464
		     field = field->next, ++arg.idx, bit <<= 1) {
			if (arg.mask & bit)
1465
				continue;
1466 1467 1468 1469 1470 1471 1472 1473 1474
			/*
 			 * Suppress this argument if its value is zero and
 			 * and we don't have a string associated in an
 			 * strarray for it.
 			 */
			if (args[arg.idx] == 0 &&
			    !(sc->arg_scnprintf &&
			      sc->arg_scnprintf[arg.idx] == SCA_STRARRAY &&
			      sc->arg_parm[arg.idx]))
1475 1476
				continue;

1477
			printed += scnprintf(bf + printed, size - printed,
1478
					     "%s%s: ", printed ? ", " : "", field->name);
1479 1480
			if (sc->arg_scnprintf && sc->arg_scnprintf[arg.idx]) {
				arg.val = args[arg.idx];
1481 1482
				if (sc->arg_parm)
					arg.parm = sc->arg_parm[arg.idx];
1483 1484
				printed += sc->arg_scnprintf[arg.idx](bf + printed,
								      size - printed, &arg);
1485
			} else {
1486
				printed += scnprintf(bf + printed, size - printed,
1487
						     "%ld", args[arg.idx]);
1488
			}
A
Arnaldo Carvalho de Melo 已提交
1489 1490
		}
	} else {
1491 1492
		int i = 0;

A
Arnaldo Carvalho de Melo 已提交
1493
		while (i < 6) {
1494 1495 1496
			printed += scnprintf(bf + printed, size - printed,
					     "%sarg%d: %ld",
					     printed ? ", " : "", i, args[i]);
A
Arnaldo Carvalho de Melo 已提交
1497 1498 1499 1500 1501 1502 1503
			++i;
		}
	}

	return printed;
}

1504 1505 1506 1507
typedef int (*tracepoint_handler)(struct trace *trace, struct perf_evsel *evsel,
				  struct perf_sample *sample);

static struct syscall *trace__syscall_info(struct trace *trace,
1508
					   struct perf_evsel *evsel, int id)
1509 1510 1511
{

	if (id < 0) {
1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527

		/*
		 * XXX: Noticed on x86_64, reproduced as far back as 3.0.36, haven't tried
		 * before that, leaving at a higher verbosity level till that is
		 * explained. Reproduced with plain ftrace with:
		 *
		 * echo 1 > /t/events/raw_syscalls/sys_exit/enable
		 * grep "NR -1 " /t/trace_pipe
		 *
		 * After generating some load on the machine.
 		 */
		if (verbose > 1) {
			static u64 n;
			fprintf(trace->output, "Invalid syscall %d id, skipping (%s, %" PRIu64 ") ...\n",
				id, perf_evsel__name(evsel), ++n);
		}
1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540
		return NULL;
	}

	if ((id > trace->syscalls.max || trace->syscalls.table[id].name == NULL) &&
	    trace__read_syscall_info(trace, id))
		goto out_cant_read;

	if ((id > trace->syscalls.max || trace->syscalls.table[id].name == NULL))
		goto out_cant_read;

	return &trace->syscalls.table[id];

out_cant_read:
1541 1542 1543 1544 1545 1546
	if (verbose) {
		fprintf(trace->output, "Problems reading syscall %d", id);
		if (id <= trace->syscalls.max && trace->syscalls.table[id].name != NULL)
			fprintf(trace->output, "(%s)", trace->syscalls.table[id].name);
		fputs(" information\n", trace->output);
	}
1547 1548 1549
	return NULL;
}

1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575
static void thread__update_stats(struct thread_trace *ttrace,
				 int id, struct perf_sample *sample)
{
	struct int_node *inode;
	struct stats *stats;
	u64 duration = 0;

	inode = intlist__findnew(ttrace->syscall_stats, id);
	if (inode == NULL)
		return;

	stats = inode->priv;
	if (stats == NULL) {
		stats = malloc(sizeof(struct stats));
		if (stats == NULL)
			return;
		init_stats(stats);
		inode->priv = stats;
	}

	if (ttrace->entry_time && sample->time > ttrace->entry_time)
		duration = sample->time - ttrace->entry_time;

	update_stats(stats, duration);
}

1576 1577 1578
static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
			    struct perf_sample *sample)
{
1579
	char *msg;
1580
	void *args;
1581
	size_t printed = 0;
1582
	struct thread *thread;
1583
	int id = perf_evsel__sc_tp_uint(evsel, id, sample);
1584
	struct syscall *sc = trace__syscall_info(trace, evsel, id);
1585 1586 1587 1588
	struct thread_trace *ttrace;

	if (sc == NULL)
		return -1;
1589

1590 1591 1592
	if (sc->filtered)
		return 0;

1593
	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
1594
	ttrace = thread__trace(thread, trace->output);
1595
	if (ttrace == NULL)
1596 1597
		return -1;

1598
	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610
	ttrace = thread->priv;

	if (ttrace->entry_str == NULL) {
		ttrace->entry_str = malloc(1024);
		if (!ttrace->entry_str)
			return -1;
	}

	ttrace->entry_time = sample->time;
	msg = ttrace->entry_str;
	printed += scnprintf(msg + printed, 1024 - printed, "%s(", sc->name);

1611 1612
	printed += syscall__scnprintf_args(sc, msg + printed, 1024 - printed,
					   args, trace, thread);
1613 1614

	if (!strcmp(sc->name, "exit_group") || !strcmp(sc->name, "exit")) {
D
David Ahern 已提交
1615
		if (!trace->duration_filter && !trace->summary_only) {
1616 1617
			trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output);
			fprintf(trace->output, "%-70s\n", ttrace->entry_str);
1618
		}
1619 1620
	} else
		ttrace->entry_pending = true;
1621 1622 1623 1624 1625 1626 1627 1628

	return 0;
}

static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
			   struct perf_sample *sample)
{
	int ret;
1629
	u64 duration = 0;
1630
	struct thread *thread;
1631
	int id = perf_evsel__sc_tp_uint(evsel, id, sample);
1632
	struct syscall *sc = trace__syscall_info(trace, evsel, id);
1633 1634 1635 1636
	struct thread_trace *ttrace;

	if (sc == NULL)
		return -1;
1637

1638 1639 1640
	if (sc->filtered)
		return 0;

1641
	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
1642
	ttrace = thread__trace(thread, trace->output);
1643
	if (ttrace == NULL)
1644 1645
		return -1;

1646 1647 1648
	if (trace->summary)
		thread__update_stats(ttrace, id, sample);

1649
	ret = perf_evsel__sc_tp_uint(evsel, ret, sample);
1650

1651 1652 1653 1654 1655 1656
	if (id == trace->audit.open_id && ret >= 0 && trace->last_vfs_getname) {
		trace__set_fd_pathname(thread, ret, trace->last_vfs_getname);
		trace->last_vfs_getname = NULL;
		++trace->stats.vfs_getname;
	}

1657 1658 1659 1660
	ttrace = thread->priv;

	ttrace->exit_time = sample->time;

1661
	if (ttrace->entry_time) {
1662
		duration = sample->time - ttrace->entry_time;
1663 1664 1665 1666
		if (trace__filter_duration(trace, duration))
			goto out;
	} else if (trace->duration_filter)
		goto out;
1667

D
David Ahern 已提交
1668 1669 1670
	if (trace->summary_only)
		goto out;

1671
	trace__fprintf_entry_head(trace, thread, duration, sample->time, trace->output);
1672 1673

	if (ttrace->entry_pending) {
1674
		fprintf(trace->output, "%-70s", ttrace->entry_str);
1675
	} else {
1676 1677 1678
		fprintf(trace->output, " ... [");
		color_fprintf(trace->output, PERF_COLOR_YELLOW, "continued");
		fprintf(trace->output, "]: %s()", sc->name);
1679 1680
	}

1681 1682 1683 1684
	if (sc->fmt == NULL) {
signed_print:
		fprintf(trace->output, ") = %d", ret);
	} else if (ret < 0 && sc->fmt->errmsg) {
1685 1686 1687 1688
		char bf[256];
		const char *emsg = strerror_r(-ret, bf, sizeof(bf)),
			   *e = audit_errno_to_name(-ret);

1689
		fprintf(trace->output, ") = -1 %s %s", e, emsg);
1690
	} else if (ret == 0 && sc->fmt->timeout)
1691
		fprintf(trace->output, ") = 0 Timeout");
1692 1693
	else if (sc->fmt->hexret)
		fprintf(trace->output, ") = %#x", ret);
1694
	else
1695
		goto signed_print;
1696

1697
	fputc('\n', trace->output);
1698
out:
1699 1700
	ttrace->entry_pending = false;

1701 1702 1703
	return 0;
}

1704 1705 1706 1707 1708 1709 1710
static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
			      struct perf_sample *sample)
{
	trace->last_vfs_getname = perf_evsel__rawptr(evsel, sample, "pathname");
	return 0;
}

1711 1712 1713 1714 1715
static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evsel,
				     struct perf_sample *sample)
{
        u64 runtime = perf_evsel__intval(evsel, sample, "runtime");
	double runtime_ms = (double)runtime / NSEC_PER_MSEC;
1716
	struct thread *thread = machine__findnew_thread(trace->host,
1717 1718
							sample->pid,
							sample->tid);
1719
	struct thread_trace *ttrace = thread__trace(thread, trace->output);
1720 1721 1722 1723 1724 1725 1726 1727 1728

	if (ttrace == NULL)
		goto out_dump;

	ttrace->runtime_ms += runtime_ms;
	trace->runtime_ms += runtime_ms;
	return 0;

out_dump:
1729
	fprintf(trace->output, "%s: comm=%s,pid=%u,runtime=%" PRIu64 ",vruntime=%" PRIu64 ")\n",
1730 1731 1732 1733 1734 1735 1736 1737
	       evsel->name,
	       perf_evsel__strval(evsel, sample, "comm"),
	       (pid_t)perf_evsel__intval(evsel, sample, "pid"),
	       runtime,
	       perf_evsel__intval(evsel, sample, "vruntime"));
	return 0;
}

1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749
static bool skip_sample(struct trace *trace, struct perf_sample *sample)
{
	if ((trace->pid_list && intlist__find(trace->pid_list, sample->pid)) ||
	    (trace->tid_list && intlist__find(trace->tid_list, sample->tid)))
		return false;

	if (trace->pid_list || trace->tid_list)
		return true;

	return false;
}

1750 1751 1752 1753 1754 1755 1756 1757 1758
static int trace__process_sample(struct perf_tool *tool,
				 union perf_event *event __maybe_unused,
				 struct perf_sample *sample,
				 struct perf_evsel *evsel,
				 struct machine *machine __maybe_unused)
{
	struct trace *trace = container_of(tool, struct trace, tool);
	int err = 0;

1759
	tracepoint_handler handler = evsel->handler;
1760

1761 1762 1763
	if (skip_sample(trace, sample))
		return 0;

1764
	if (!trace->full_time && trace->base_time == 0)
1765 1766 1767 1768 1769 1770 1771 1772
		trace->base_time = sample->time;

	if (handler)
		handler(trace, evsel, sample);

	return err;
}

1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793
static int parse_target_str(struct trace *trace)
{
	if (trace->opts.target.pid) {
		trace->pid_list = intlist__new(trace->opts.target.pid);
		if (trace->pid_list == NULL) {
			pr_err("Error parsing process id string\n");
			return -EINVAL;
		}
	}

	if (trace->opts.target.tid) {
		trace->tid_list = intlist__new(trace->opts.target.tid);
		if (trace->tid_list == NULL) {
			pr_err("Error parsing thread id string\n");
			return -EINVAL;
		}
	}

	return 0;
}

D
David Ahern 已提交
1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820
static int trace__record(int argc, const char **argv)
{
	unsigned int rec_argc, i, j;
	const char **rec_argv;
	const char * const record_args[] = {
		"record",
		"-R",
		"-m", "1024",
		"-c", "1",
		"-e", "raw_syscalls:sys_enter,raw_syscalls:sys_exit",
	};

	rec_argc = ARRAY_SIZE(record_args) + argc;
	rec_argv = calloc(rec_argc + 1, sizeof(char *));

	if (rec_argv == NULL)
		return -ENOMEM;

	for (i = 0; i < ARRAY_SIZE(record_args); i++)
		rec_argv[i] = record_args[i];

	for (j = 0; j < (unsigned int)argc; j++, i++)
		rec_argv[i] = argv[j];

	return cmd_record(i, rec_argv, NULL);
}

1821 1822
static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);

1823 1824
static void perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
{
1825
	struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname");
1826 1827 1828 1829 1830 1831 1832 1833
	if (evsel == NULL)
		return;

	if (perf_evsel__field(evsel, "pathname") == NULL) {
		perf_evsel__delete(evsel);
		return;
	}

1834
	evsel->handler = trace__vfs_getname;
1835 1836 1837
	perf_evlist__add(evlist, evsel);
}

1838
static int trace__run(struct trace *trace, int argc, const char **argv)
A
Arnaldo Carvalho de Melo 已提交
1839
{
1840
	struct perf_evlist *evlist = perf_evlist__new();
1841
	struct perf_evsel *evsel;
1842 1843
	int err = -1, i;
	unsigned long before;
1844
	const bool forks = argc > 0;
A
Arnaldo Carvalho de Melo 已提交
1845

1846 1847
	trace->live = true;

A
Arnaldo Carvalho de Melo 已提交
1848
	if (evlist == NULL) {
1849
		fprintf(trace->output, "Not enough memory to run!\n");
A
Arnaldo Carvalho de Melo 已提交
1850 1851 1852
		goto out;
	}

1853
	if (perf_evlist__add_syscall_newtp(evlist, trace__sys_enter, trace__sys_exit))
1854
		goto out_error_tp;
A
Arnaldo Carvalho de Melo 已提交
1855

1856 1857
	perf_evlist__add_vfs_getname(evlist);

1858
	if (trace->sched &&
1859 1860 1861
		perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
				trace__sched_stat_runtime))
		goto out_error_tp;
1862

A
Arnaldo Carvalho de Melo 已提交
1863 1864
	err = perf_evlist__create_maps(evlist, &trace->opts.target);
	if (err < 0) {
1865
		fprintf(trace->output, "Problems parsing the target to trace, check your options!\n");
A
Arnaldo Carvalho de Melo 已提交
1866 1867 1868
		goto out_delete_evlist;
	}

1869 1870
	err = trace__symbols_init(trace, evlist);
	if (err < 0) {
1871
		fprintf(trace->output, "Problems initializing symbol libraries!\n");
1872
		goto out_delete_maps;
1873 1874
	}

1875
	perf_evlist__config(evlist, &trace->opts);
A
Arnaldo Carvalho de Melo 已提交
1876

1877 1878 1879 1880
	signal(SIGCHLD, sig_handler);
	signal(SIGINT, sig_handler);

	if (forks) {
1881
		err = perf_evlist__prepare_workload(evlist, &trace->opts.target,
1882
						    argv, false, false);
1883
		if (err < 0) {
1884
			fprintf(trace->output, "Couldn't run the workload!\n");
1885
			goto out_delete_maps;
1886 1887 1888
		}
	}

A
Arnaldo Carvalho de Melo 已提交
1889
	err = perf_evlist__open(evlist);
1890 1891
	if (err < 0)
		goto out_error_open;
A
Arnaldo Carvalho de Melo 已提交
1892 1893 1894

	err = perf_evlist__mmap(evlist, UINT_MAX, false);
	if (err < 0) {
1895
		fprintf(trace->output, "Couldn't mmap the events: %s\n", strerror(errno));
1896
		goto out_close_evlist;
A
Arnaldo Carvalho de Melo 已提交
1897 1898 1899
	}

	perf_evlist__enable(evlist);
1900 1901 1902 1903

	if (forks)
		perf_evlist__start_workload(evlist);

1904
	trace->multiple_threads = evlist->threads->map[0] == -1 || evlist->threads->nr > 1;
A
Arnaldo Carvalho de Melo 已提交
1905
again:
1906
	before = trace->nr_events;
A
Arnaldo Carvalho de Melo 已提交
1907 1908 1909 1910 1911 1912

	for (i = 0; i < evlist->nr_mmaps; i++) {
		union perf_event *event;

		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
			const u32 type = event->header.type;
1913
			tracepoint_handler handler;
A
Arnaldo Carvalho de Melo 已提交
1914 1915
			struct perf_sample sample;

1916
			++trace->nr_events;
A
Arnaldo Carvalho de Melo 已提交
1917 1918 1919

			err = perf_evlist__parse_sample(evlist, event, &sample);
			if (err) {
1920
				fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err);
1921
				goto next_event;
A
Arnaldo Carvalho de Melo 已提交
1922 1923
			}

1924
			if (!trace->full_time && trace->base_time == 0)
1925 1926 1927
				trace->base_time = sample.time;

			if (type != PERF_RECORD_SAMPLE) {
1928
				trace__process_event(trace, trace->host, event, &sample);
1929 1930 1931
				continue;
			}

A
Arnaldo Carvalho de Melo 已提交
1932 1933
			evsel = perf_evlist__id2evsel(evlist, sample.id);
			if (evsel == NULL) {
1934
				fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample.id);
1935
				goto next_event;
A
Arnaldo Carvalho de Melo 已提交
1936 1937
			}

1938
			if (sample.raw_data == NULL) {
1939
				fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
1940 1941
				       perf_evsel__name(evsel), sample.tid,
				       sample.cpu, sample.raw_size);
1942
				goto next_event;
1943 1944
			}

1945
			handler = evsel->handler;
1946
			handler(trace, evsel, &sample);
1947 1948
next_event:
			perf_evlist__mmap_consume(evlist, i);
1949

1950 1951
			if (interrupted)
				goto out_disable;
A
Arnaldo Carvalho de Melo 已提交
1952 1953 1954
		}
	}

1955
	if (trace->nr_events == before) {
1956
		int timeout = done ? 100 : -1;
1957

1958 1959 1960 1961
		if (poll(evlist->pollfd, evlist->nr_fds, timeout) > 0)
			goto again;
	} else {
		goto again;
1962 1963
	}

1964 1965
out_disable:
	perf_evlist__disable(evlist);
A
Arnaldo Carvalho de Melo 已提交
1966

1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978
	if (!err) {
		if (trace->summary)
			trace__fprintf_thread_summary(trace, trace->output);

		if (trace->show_tool_stats) {
			fprintf(trace->output, "Stats:\n "
					       " vfs_getname : %" PRIu64 "\n"
					       " proc_getname: %" PRIu64 "\n",
				trace->stats.vfs_getname,
				trace->stats.proc_getname);
		}
	}
1979

1980 1981 1982 1983 1984
	perf_evlist__munmap(evlist);
out_close_evlist:
	perf_evlist__close(evlist);
out_delete_maps:
	perf_evlist__delete_maps(evlist);
A
Arnaldo Carvalho de Melo 已提交
1985 1986 1987
out_delete_evlist:
	perf_evlist__delete(evlist);
out:
1988
	trace->live = false;
A
Arnaldo Carvalho de Melo 已提交
1989
	return err;
1990 1991
{
	char errbuf[BUFSIZ];
1992 1993

out_error_tp:
1994
	perf_evlist__strerror_tp(evlist, errno, errbuf, sizeof(errbuf));
1995 1996 1997 1998 1999 2000
	goto out_error;

out_error_open:
	perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));

out_error:
2001
	fprintf(trace->output, "%s\n", errbuf);
2002
	goto out_delete_evlist;
A
Arnaldo Carvalho de Melo 已提交
2003
}
2004
}
A
Arnaldo Carvalho de Melo 已提交
2005

2006 2007 2008
static int trace__replay(struct trace *trace)
{
	const struct perf_evsel_str_handler handlers[] = {
2009
		{ "probe:vfs_getname",	     trace__vfs_getname, },
2010
	};
2011 2012 2013 2014
	struct perf_data_file file = {
		.path  = input_name,
		.mode  = PERF_DATA_MODE_READ,
	};
2015
	struct perf_session *session;
2016
	struct perf_evsel *evsel;
2017 2018 2019 2020
	int err = -1;

	trace->tool.sample	  = trace__process_sample;
	trace->tool.mmap	  = perf_event__process_mmap;
D
David Ahern 已提交
2021
	trace->tool.mmap2	  = perf_event__process_mmap2;
2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037
	trace->tool.comm	  = perf_event__process_comm;
	trace->tool.exit	  = perf_event__process_exit;
	trace->tool.fork	  = perf_event__process_fork;
	trace->tool.attr	  = perf_event__process_attr;
	trace->tool.tracing_data = perf_event__process_tracing_data;
	trace->tool.build_id	  = perf_event__process_build_id;

	trace->tool.ordered_samples = true;
	trace->tool.ordering_requires_timestamps = true;

	/* add tid to output */
	trace->multiple_threads = true;

	if (symbol__init() < 0)
		return -1;

2038
	session = perf_session__new(&file, false, &trace->tool);
2039 2040 2041
	if (session == NULL)
		return -ENOMEM;

2042 2043
	trace->host = &session->machines.host;

2044 2045 2046 2047
	err = perf_session__set_tracepoints_handlers(session, handlers);
	if (err)
		goto out;

2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064
	evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
						     "raw_syscalls:sys_enter");
	if (evsel == NULL) {
		pr_err("Data file does not have raw_syscalls:sys_enter event\n");
		goto out;
	}

	if (perf_evsel__init_syscall_tp(evsel, trace__sys_enter) < 0 ||
	    perf_evsel__init_sc_tp_ptr_field(evsel, args)) {
		pr_err("Error during initialize raw_syscalls:sys_enter event\n");
		goto out;
	}

	evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
						     "raw_syscalls:sys_exit");
	if (evsel == NULL) {
		pr_err("Data file does not have raw_syscalls:sys_exit event\n");
2065 2066 2067
		goto out;
	}

2068 2069 2070
	if (perf_evsel__init_syscall_tp(evsel, trace__sys_exit) < 0 ||
	    perf_evsel__init_sc_tp_uint_field(evsel, ret)) {
		pr_err("Error during initialize raw_syscalls:sys_exit event\n");
2071 2072 2073
		goto out;
	}

2074 2075 2076 2077
	err = parse_target_str(trace);
	if (err != 0)
		goto out;

2078 2079 2080 2081 2082 2083
	setup_pager();

	err = perf_session__process_events(session, &trace->tool);
	if (err)
		pr_err("Failed to process events, error %d", err);

2084 2085 2086
	else if (trace->summary)
		trace__fprintf_thread_summary(trace, trace->output);

2087 2088 2089 2090 2091 2092
out:
	perf_session__delete(session);

	return err;
}

2093 2094 2095 2096
static size_t trace__fprintf_threads_header(FILE *fp)
{
	size_t printed;

2097
	printed  = fprintf(fp, "\n Summary of events:\n\n");
2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114

	return printed;
}

static size_t thread__dump_stats(struct thread_trace *ttrace,
				 struct trace *trace, FILE *fp)
{
	struct stats *stats;
	size_t printed = 0;
	struct syscall *sc;
	struct int_node *inode = intlist__first(ttrace->syscall_stats);

	if (inode == NULL)
		return 0;

	printed += fprintf(fp, "\n");

2115 2116 2117 2118
	printed += fprintf(fp, "                                                    msec/call\n");
	printed += fprintf(fp, "   syscall            calls      min      avg      max stddev\n");
	printed += fprintf(fp, "   --------------- -------- -------- -------- -------- ------\n");

2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132
	/* each int_node is a syscall */
	while (inode) {
		stats = inode->priv;
		if (stats) {
			double min = (double)(stats->min) / NSEC_PER_MSEC;
			double max = (double)(stats->max) / NSEC_PER_MSEC;
			double avg = avg_stats(stats);
			double pct;
			u64 n = (u64) stats->n;

			pct = avg ? 100.0 * stddev_stats(stats)/avg : 0.0;
			avg /= NSEC_PER_MSEC;

			sc = &trace->syscalls.table[inode->i];
2133 2134
			printed += fprintf(fp, "   %-15s", sc->name);
			printed += fprintf(fp, " %8" PRIu64 " %8.3f %8.3f",
2135
					   n, min, avg);
2136
			printed += fprintf(fp, " %8.3f %6.2f\n", max, pct);
2137 2138 2139 2140 2141 2142
		}

		inode = intlist__next(inode);
	}

	printed += fprintf(fp, "\n\n");
2143 2144 2145 2146

	return printed;
}

2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176
/* struct used to pass data to per-thread function */
struct summary_data {
	FILE *fp;
	struct trace *trace;
	size_t printed;
};

static int trace__fprintf_one_thread(struct thread *thread, void *priv)
{
	struct summary_data *data = priv;
	FILE *fp = data->fp;
	size_t printed = data->printed;
	struct trace *trace = data->trace;
	struct thread_trace *ttrace = thread->priv;
	const char *color;
	double ratio;

	if (ttrace == NULL)
		return 0;

	ratio = (double)ttrace->nr_events / trace->nr_events * 100.0;

	color = PERF_COLOR_NORMAL;
	if (ratio > 50.0)
		color = PERF_COLOR_RED;
	else if (ratio > 25.0)
		color = PERF_COLOR_GREEN;
	else if (ratio > 5.0)
		color = PERF_COLOR_YELLOW;

2177 2178 2179 2180
	printed += color_fprintf(fp, color, " %s (%d), ", thread__comm_str(thread), thread->tid);
	printed += fprintf(fp, "%lu events, ", ttrace->nr_events);
	printed += color_fprintf(fp, color, "%.1f%%", ratio);
	printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
2181
	printed += thread__dump_stats(ttrace, trace, fp);
2182 2183 2184 2185 2186 2187

	data->printed += printed;

	return 0;
}

2188 2189
static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
{
2190 2191 2192 2193 2194
	struct summary_data data = {
		.fp = fp,
		.trace = trace
	};
	data.printed = trace__fprintf_threads_header(fp);
2195

2196 2197 2198
	machine__for_each_thread(trace->host, trace__fprintf_one_thread, &data);

	return data.printed;
2199 2200
}

2201 2202 2203 2204 2205 2206 2207 2208 2209
static int trace__set_duration(const struct option *opt, const char *str,
			       int unset __maybe_unused)
{
	struct trace *trace = opt->value;

	trace->duration_filter = atof(str);
	return 0;
}

2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226
static int trace__open_output(struct trace *trace, const char *filename)
{
	struct stat st;

	if (!stat(filename, &st) && st.st_size) {
		char oldname[PATH_MAX];

		scnprintf(oldname, sizeof(oldname), "%s.old", filename);
		unlink(oldname);
		rename(filename, oldname);
	}

	trace->output = fopen(filename, "w");

	return trace->output == NULL ? -errno : 0;
}

A
Arnaldo Carvalho de Melo 已提交
2227 2228 2229
int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
{
	const char * const trace_usage[] = {
2230 2231
		"perf trace [<options>] [<command>]",
		"perf trace [<options>] -- <command> [<options>]",
D
David Ahern 已提交
2232 2233
		"perf trace record [<options>] [<command>]",
		"perf trace record [<options>] -- <command> [<options>]",
A
Arnaldo Carvalho de Melo 已提交
2234 2235 2236
		NULL
	};
	struct trace trace = {
2237 2238 2239 2240
		.audit = {
			.machine = audit_detect_machine(),
			.open_id = audit_name_to_syscall("open", trace.audit.machine),
		},
A
Arnaldo Carvalho de Melo 已提交
2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253
		.syscalls = {
			. max = -1,
		},
		.opts = {
			.target = {
				.uid	   = UINT_MAX,
				.uses_mmap = true,
			},
			.user_freq     = UINT_MAX,
			.user_interval = ULLONG_MAX,
			.no_delay      = true,
			.mmap_pages    = 1024,
		},
2254
		.output = stdout,
2255
		.show_comm = true,
A
Arnaldo Carvalho de Melo 已提交
2256
	};
2257
	const char *output_name = NULL;
2258
	const char *ev_qualifier_str = NULL;
A
Arnaldo Carvalho de Melo 已提交
2259
	const struct option trace_options[] = {
2260 2261
	OPT_BOOLEAN(0, "comm", &trace.show_comm,
		    "show the thread COMM next to its id"),
2262
	OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"),
2263 2264
	OPT_STRING('e', "expr", &ev_qualifier_str, "expr",
		    "list of events to trace"),
2265
	OPT_STRING('o', "output", &output_name, "file", "output file name"),
2266
	OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
A
Arnaldo Carvalho de Melo 已提交
2267 2268
	OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
		    "trace events on existing process id"),
2269
	OPT_STRING('t', "tid", &trace.opts.target.tid, "tid",
A
Arnaldo Carvalho de Melo 已提交
2270
		    "trace events on existing thread id"),
2271
	OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide,
A
Arnaldo Carvalho de Melo 已提交
2272
		    "system-wide collection from all CPUs"),
2273
	OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu",
A
Arnaldo Carvalho de Melo 已提交
2274
		    "list of cpus to monitor"),
2275
	OPT_BOOLEAN(0, "no-inherit", &trace.opts.no_inherit,
A
Arnaldo Carvalho de Melo 已提交
2276
		    "child tasks do not inherit counters"),
2277 2278 2279
	OPT_CALLBACK('m', "mmap-pages", &trace.opts.mmap_pages, "pages",
		     "number of mmap data pages",
		     perf_evlist__parse_mmap_pages),
2280
	OPT_STRING('u', "uid", &trace.opts.target.uid_str, "user",
A
Arnaldo Carvalho de Melo 已提交
2281
		   "user to profile"),
2282 2283 2284
	OPT_CALLBACK(0, "duration", &trace, "float",
		     "show only events with duration > N.M ms",
		     trace__set_duration),
2285
	OPT_BOOLEAN(0, "sched", &trace.sched, "show blocking scheduler events"),
2286
	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
2287 2288
	OPT_BOOLEAN('T', "time", &trace.full_time,
		    "Show full timestamp, not time relative to first start"),
D
David Ahern 已提交
2289 2290 2291 2292
	OPT_BOOLEAN('s', "summary", &trace.summary_only,
		    "Show only syscall summary with statistics"),
	OPT_BOOLEAN('S', "with-summary", &trace.summary,
		    "Show all syscalls and summary with statistics"),
A
Arnaldo Carvalho de Melo 已提交
2293 2294 2295
	OPT_END()
	};
	int err;
2296
	char bf[BUFSIZ];
A
Arnaldo Carvalho de Melo 已提交
2297

D
David Ahern 已提交
2298 2299 2300
	if ((argc > 1) && (strcmp(argv[1], "record") == 0))
		return trace__record(argc-2, &argv[2]);

A
Arnaldo Carvalho de Melo 已提交
2301 2302
	argc = parse_options(argc, argv, trace_options, trace_usage, 0);

D
David Ahern 已提交
2303 2304 2305 2306
	/* summary_only implies summary option, but don't overwrite summary if set */
	if (trace.summary_only)
		trace.summary = trace.summary_only;

2307 2308 2309 2310 2311 2312 2313 2314
	if (output_name != NULL) {
		err = trace__open_output(&trace, output_name);
		if (err < 0) {
			perror("failed to create output file");
			goto out;
		}
	}

2315
	if (ev_qualifier_str != NULL) {
2316 2317 2318 2319 2320 2321
		const char *s = ev_qualifier_str;

		trace.not_ev_qualifier = *s == '!';
		if (trace.not_ev_qualifier)
			++s;
		trace.ev_qualifier = strlist__new(true, s);
2322
		if (trace.ev_qualifier == NULL) {
2323 2324 2325 2326
			fputs("Not enough memory to parse event qualifier",
			      trace.output);
			err = -ENOMEM;
			goto out_close;
2327 2328 2329
		}
	}

2330 2331 2332
	err = perf_target__validate(&trace.opts.target);
	if (err) {
		perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf));
2333 2334
		fprintf(trace.output, "%s", bf);
		goto out_close;
2335 2336
	}

A
Arnaldo Carvalho de Melo 已提交
2337 2338 2339
	err = perf_target__parse_uid(&trace.opts.target);
	if (err) {
		perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf));
2340 2341
		fprintf(trace.output, "%s", bf);
		goto out_close;
A
Arnaldo Carvalho de Melo 已提交
2342 2343
	}

2344
	if (!argc && perf_target__none(&trace.opts.target))
2345 2346
		trace.opts.target.system_wide = true;

2347 2348 2349 2350
	if (input_name)
		err = trace__replay(&trace);
	else
		err = trace__run(&trace, argc, argv);
2351

2352 2353 2354 2355
out_close:
	if (output_name != NULL)
		fclose(trace.output);
out:
2356
	return err;
A
Arnaldo Carvalho de Melo 已提交
2357
}