builtin-trace.c 62.1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220
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);
}

static struct perf_evsel *perf_evsel__syscall_newtp(const char *direction,
						    void *handler, int idx)
{
	struct perf_evsel *evsel = perf_evsel__newtp("raw_syscalls", direction, idx);

	if (evsel) {
		evsel->priv = malloc(sizeof(struct syscall_tp));

		if (evsel->priv == NULL)
			goto out_delete;

		if (perf_evsel__init_sc_tp_uint_field(evsel, id))
			goto out_delete;

		evsel->handler = handler;
	}

	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;
	int idx = evlist->nr_entries;
	struct perf_evsel *sys_enter, *sys_exit;

	sys_enter = perf_evsel__syscall_newtp("sys_enter", sys_enter_handler, idx++);
	if (sys_enter == NULL)
		goto out;

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

	sys_exit = perf_evsel__syscall_newtp("sys_exit", sys_exit_handler, idx++);
	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;
}


221 222
struct syscall_arg {
	unsigned long val;
223 224
	struct thread *thread;
	struct trace  *trace;
225
	void	      *parm;
226 227 228 229
	u8	      idx;
	u8	      mask;
};

230
struct strarray {
231
	int	    offset;
232 233 234 235 236 237 238 239 240
	int	    nr_entries;
	const char **entries;
};

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

241 242 243 244 245 246
#define DEFINE_STRARRAY_OFFSET(array, off) struct strarray strarray__##array = { \
	.offset	    = off, \
	.nr_entries = ARRAY_SIZE(array), \
	.entries = array, \
}

247 248 249
static size_t __syscall_arg__scnprintf_strarray(char *bf, size_t size,
						const char *intfmt,
					        struct syscall_arg *arg)
250 251
{
	struct strarray *sa = arg->parm;
252
	int idx = arg->val - sa->offset;
253 254

	if (idx < 0 || idx >= sa->nr_entries)
255
		return scnprintf(bf, size, intfmt, arg->val);
256 257 258 259

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

260 261 262 263 264 265
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);
}

266 267
#define SCA_STRARRAY syscall_arg__scnprintf_strarray

268 269 270 271 272 273 274 275
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

276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298
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

299
static size_t syscall_arg__scnprintf_hex(char *bf, size_t size,
300
					 struct syscall_arg *arg)
301
{
302
	return scnprintf(bf, size, "%#lx", arg->val);
303 304
}

305 306
#define SCA_HEX syscall_arg__scnprintf_hex

307
static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
308
					       struct syscall_arg *arg)
309
{
310
	int printed = 0, prot = arg->val;
311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337

	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

338
static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
339
						struct syscall_arg *arg)
340
{
341
	int printed = 0, flags = arg->val;
342 343 344 345 346 347 348 349 350

#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);
351
#ifdef MAP_32BIT
352
	P_MMAP_FLAG(32BIT);
353
#endif
354 355 356 357 358 359
	P_MMAP_FLAG(ANONYMOUS);
	P_MMAP_FLAG(DENYWRITE);
	P_MMAP_FLAG(EXECUTABLE);
	P_MMAP_FLAG(FILE);
	P_MMAP_FLAG(FIXED);
	P_MMAP_FLAG(GROWSDOWN);
360
#ifdef MAP_HUGETLB
361
	P_MMAP_FLAG(HUGETLB);
362
#endif
363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380
	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

381
static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
382
						      struct syscall_arg *arg)
383
{
384
	int behavior = arg->val;
385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401

	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);
402
#ifdef MADV_HUGEPAGE
403
	P_MADV_BHV(HUGEPAGE);
404 405
#endif
#ifdef MADV_NOHUGEPAGE
406
	P_MADV_BHV(NOHUGEPAGE);
407
#endif
408 409 410 411 412 413 414 415 416 417 418 419 420 421 422
#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

423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453
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

454
static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, struct syscall_arg *arg)
455 456 457 458 459 460 461 462 463
{
	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),
	};
464
	int op = arg->val;
465 466 467 468 469
	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);
470 471 472 473 474 475
	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;
476
	P_FUTEX_OP(WAKE_OP);							  break;
477 478 479 480 481
	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;
482 483 484 485 486 487 488 489 490 491 492 493 494
	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;
}

495 496
#define SCA_FUTEX_OP  syscall_arg__scnprintf_futex_op

497 498
static const char *epoll_ctl_ops[] = { "ADD", "DEL", "MOD", };
static DEFINE_STRARRAY_OFFSET(epoll_ctl_ops, 1);
499

500 501 502
static const char *itimers[] = { "REAL", "VIRTUAL", "PROF", };
static DEFINE_STRARRAY(itimers);

503 504 505 506 507 508 509 510 511
static const char *whences[] = { "SET", "CUR", "END",
#ifdef SEEK_DATA
"DATA",
#endif
#ifdef SEEK_HOLE
"HOLE",
#endif
};
static DEFINE_STRARRAY(whences);
512

513 514 515 516 517 518 519 520
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);

521 522 523 524 525 526 527
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);

528 529 530
static const char *sighow[] = { "BLOCK", "UNBLOCK", "SETMASK", };
static DEFINE_STRARRAY(sighow);

531 532 533 534 535 536
static const char *clockid[] = {
	"REALTIME", "MONOTONIC", "PROCESS_CPUTIME_ID", "THREAD_CPUTIME_ID",
	"MONOTONIC_RAW", "REALTIME_COARSE", "MONOTONIC_COARSE",
};
static DEFINE_STRARRAY(clockid);

537 538 539 540 541 542 543 544 545 546
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);

547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593
#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

594 595 596
#ifndef MSG_PROBE
#define MSG_PROBE	     0x10
#endif
597 598 599
#ifndef MSG_WAITFORONE
#define MSG_WAITFORONE	0x10000
#endif
600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650
#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

651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677
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

678
static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
679
					       struct syscall_arg *arg)
680
{
681
	int printed = 0, flags = arg->val;
682 683

	if (!(flags & O_CREAT))
684
		arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */
685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733

	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

734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759
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

760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782
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

783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827
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

828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849
#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);

850 851 852 853
#define STRARRAY(arg, name, array) \
	  .arg_scnprintf = { [arg] = SCA_STRARRAY, }, \
	  .arg_parm	 = { [arg] = &strarray__##array, }

A
Arnaldo Carvalho de Melo 已提交
854 855
static struct syscall_fmt {
	const char *name;
856
	const char *alias;
857
	size_t	   (*arg_scnprintf[6])(char *bf, size_t size, struct syscall_arg *arg);
858
	void	   *arg_parm[6];
A
Arnaldo Carvalho de Melo 已提交
859 860
	bool	   errmsg;
	bool	   timeout;
861
	bool	   hexret;
A
Arnaldo Carvalho de Melo 已提交
862
} syscall_fmts[] = {
863 864
	{ .name	    = "access",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_ACCMODE, /* mode */ }, },
865
	{ .name	    = "arch_prctl", .errmsg = true, .alias = "prctl", },
866 867
	{ .name	    = "brk",	    .hexret = true,
	  .arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, },
868
	{ .name     = "clock_gettime",  .errmsg = true, STRARRAY(0, clk_id, clockid), },
869 870
	{ .name	    = "close",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, }, 
871
	{ .name	    = "connect",    .errmsg = true, },
872 873 874 875 876 877
	{ .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 */ }, }, 
878
	{ .name	    = "epoll_ctl",  .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), },
879 880
	{ .name	    = "eventfd2",   .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, },
881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902
	{ .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 */ }, }, 
903
	{ .name	    = "flock",	    .errmsg = true,
904 905 906 907 908 909 910 911 912 913 914 915 916 917
	  .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 */ }, }, 
918 919
	{ .name	    = "futex",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, },
920 921 922 923 924 925
	{ .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 */ }, }, 
926 927
	{ .name	    = "getitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
	{ .name	    = "getrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
928
	{ .name	    = "ioctl",	    .errmsg = true,
929
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ 
930 931 932
			     [1] = SCA_STRHEXARRAY, /* cmd */
			     [2] = SCA_HEX, /* arg */ },
	  .arg_parm	 = { [1] = &strarray__tioctls, /* cmd */ }, },
933 934
	{ .name	    = "kill",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
935 936 937 938 939 940
	{ .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 */ }, },
941
	{ .name	    = "lstat",	    .errmsg = true, .alias = "newlstat", },
942 943 944
	{ .name     = "madvise",    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_HEX,	 /* start */
			     [2] = SCA_MADV_BHV, /* behavior */ }, },
945 946 947 948
	{ .name	    = "mkdirat",    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
	{ .name	    = "mknodat",    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
949 950 951 952
	{ .name	    = "mlock",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
	{ .name	    = "mlockall",   .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
953
	{ .name	    = "mmap",	    .hexret = true,
954
	  .arg_scnprintf = { [0] = SCA_HEX,	  /* addr */
955 956
			     [2] = SCA_MMAP_PROT, /* prot */
			     [3] = SCA_MMAP_FLAGS, /* flags */ }, },
957
	{ .name	    = "mprotect",   .errmsg = true,
958 959 960 961 962
	  .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 */ }, },
963 964
	{ .name	    = "munlock",    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
965 966
	{ .name	    = "munmap",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
967 968 969 970
	{ .name	    = "name_to_handle_at", .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
	{ .name	    = "newfstatat", .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
971 972
	{ .name	    = "open",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, },
973
	{ .name	    = "open_by_handle_at", .errmsg = true,
974 975
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
			     [2] = SCA_OPEN_FLAGS, /* flags */ }, },
976
	{ .name	    = "openat",	    .errmsg = true,
977 978
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
			     [2] = SCA_OPEN_FLAGS, /* flags */ }, },
979 980
	{ .name	    = "pipe2",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, },
981 982
	{ .name	    = "poll",	    .errmsg = true, .timeout = true, },
	{ .name	    = "ppoll",	    .errmsg = true, .timeout = true, },
983 984 985 986
	{ .name	    = "pread",	    .errmsg = true, .alias = "pread64",
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
	{ .name	    = "preadv",	    .errmsg = true, .alias = "pread",
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
987
	{ .name	    = "prlimit64",  .errmsg = true, STRARRAY(1, resource, rlimit_resources), },
988 989 990 991 992 993 994 995 996 997
	{ .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 */ }, }, 
998 999 1000 1001 1002 1003
	{ .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 */ }, },
1004 1005
	{ .name	    = "renameat",   .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
1006 1007
	{ .name	    = "rt_sigaction", .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, },
1008
	{ .name	    = "rt_sigprocmask",  .errmsg = true, STRARRAY(0, how, sighow), },
1009 1010 1011 1012
	{ .name	    = "rt_sigqueueinfo", .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
	{ .name	    = "rt_tgsigqueueinfo", .errmsg = true,
	  .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
1013
	{ .name	    = "select",	    .errmsg = true, .timeout = true, },
1014 1015 1016 1017 1018 1019
	{ .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 */ }, },
1020 1021
	{ .name	    = "setitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
	{ .name	    = "setrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
1022 1023
	{ .name	    = "shutdown",   .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
1024
	{ .name	    = "socket",	    .errmsg = true,
1025 1026
	  .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
			     [1] = SCA_SK_TYPE, /* type */ },
1027 1028 1029 1030
	  .arg_parm	 = { [0] = &strarray__socket_families, /* family */ }, },
	{ .name	    = "socketpair", .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
			     [1] = SCA_SK_TYPE, /* type */ },
1031
	  .arg_parm	 = { [0] = &strarray__socket_families, /* family */ }, },
1032
	{ .name	    = "stat",	    .errmsg = true, .alias = "newstat", },
1033 1034
	{ .name	    = "symlinkat",  .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
1035 1036 1037 1038
	{ .name	    = "tgkill",	    .errmsg = true,
	  .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
	{ .name	    = "tkill",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
1039
	{ .name	    = "uname",	    .errmsg = true, .alias = "newuname", },
1040 1041 1042 1043 1044 1045 1046 1047
	{ .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
1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064
};

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;
1065
	bool		    filtered;
A
Arnaldo Carvalho de Melo 已提交
1066
	struct syscall_fmt  *fmt;
1067
	size_t		    (**arg_scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
1068
	void		    **arg_parm;
A
Arnaldo Carvalho de Melo 已提交
1069 1070
};

1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081
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);
1082
	return printed + fprintf(fp, "): ");
1083 1084
}

1085 1086 1087 1088
struct thread_trace {
	u64		  entry_time;
	u64		  exit_time;
	bool		  entry_pending;
1089
	unsigned long	  nr_events;
1090
	char		  *entry_str;
1091
	double		  runtime_ms;
1092 1093 1094 1095
	struct {
		int	  max;
		char	  **table;
	} paths;
1096 1097

	struct intlist *syscall_stats;
1098 1099 1100 1101
};

static struct thread_trace *thread_trace__new(void)
{
1102 1103 1104 1105 1106
	struct thread_trace *ttrace =  zalloc(sizeof(struct thread_trace));

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

1107 1108
	ttrace->syscall_stats = intlist__new(NULL);

1109
	return ttrace;
1110 1111
}

1112
static struct thread_trace *thread__trace(struct thread *thread, FILE *fp)
1113
{
1114 1115
	struct thread_trace *ttrace;

1116 1117 1118 1119 1120
	if (thread == NULL)
		goto fail;

	if (thread->priv == NULL)
		thread->priv = thread_trace__new();
1121
		
1122 1123 1124
	if (thread->priv == NULL)
		goto fail;

1125 1126 1127 1128
	ttrace = thread->priv;
	++ttrace->nr_events;

	return ttrace;
1129
fail:
1130
	color_fprintf(fp, PERF_COLOR_RED,
1131 1132 1133 1134
		      "WARNING: not enough memory, dropping samples!\n");
	return NULL;
}

A
Arnaldo Carvalho de Melo 已提交
1135
struct trace {
1136
	struct perf_tool	tool;
1137 1138 1139 1140
	struct {
		int		machine;
		int		open_id;
	}			audit;
A
Arnaldo Carvalho de Melo 已提交
1141 1142 1143 1144 1145
	struct {
		int		max;
		struct syscall  *table;
	} syscalls;
	struct perf_record_opts opts;
1146
	struct machine		*host;
1147
	u64			base_time;
1148
	bool			full_time;
1149
	FILE			*output;
1150
	unsigned long		nr_events;
1151 1152
	struct strlist		*ev_qualifier;
	bool			not_ev_qualifier;
1153
	bool			live;
1154
	const char 		*last_vfs_getname;
1155 1156
	struct intlist		*tid_list;
	struct intlist		*pid_list;
1157
	bool			sched;
1158
	bool			multiple_threads;
1159
	bool			summary;
1160
	bool			show_comm;
1161
	bool			show_tool_stats;
1162
	double			duration_filter;
1163
	double			runtime_ms;
1164 1165 1166
	struct {
		u64		vfs_getname, proc_getname;
	} stats;
A
Arnaldo Carvalho de Melo 已提交
1167 1168
};

1169
static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194
{
	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;
}

1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220
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);
}

1221 1222
static const char *thread__fd_path(struct thread *thread, int fd,
				   struct trace *trace)
1223 1224 1225 1226 1227 1228 1229 1230 1231
{
	struct thread_trace *ttrace = thread->priv;

	if (ttrace == NULL)
		return NULL;

	if (fd < 0)
		return NULL;

1232 1233 1234 1235 1236 1237 1238
	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;
	}
1239 1240 1241 1242 1243 1244 1245 1246 1247

	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);
1248
	const char *path = thread__fd_path(arg->thread, fd, arg->trace);
1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270

	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;
}

1271 1272 1273 1274 1275
static bool trace__filter_duration(struct trace *trace, double t)
{
	return t < (trace->duration_filter * NSEC_PER_MSEC);
}

1276 1277 1278 1279
static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
{
	double ts = (double)(tstamp - trace->base_time) / NSEC_PER_MSEC;

1280
	return fprintf(fp, "%10.3f ", ts);
1281 1282
}

1283
static bool done = false;
1284
static bool interrupted = false;
1285

1286
static void sig_handler(int sig)
1287 1288
{
	done = true;
1289
	interrupted = sig == SIGINT;
1290 1291
}

1292
static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
1293
					u64 duration, u64 tstamp, FILE *fp)
1294 1295
{
	size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
1296
	printed += fprintf_duration(duration, fp);
1297

1298 1299
	if (trace->multiple_threads) {
		if (trace->show_comm)
1300
			printed += fprintf(fp, "%.14s/", thread__comm_str(thread));
1301
		printed += fprintf(fp, "%d ", thread->tid);
1302
	}
1303 1304 1305 1306

	return printed;
}

1307
static int trace__process_event(struct trace *trace, struct machine *machine,
1308
				union perf_event *event, struct perf_sample *sample)
1309 1310 1311 1312 1313
{
	int ret = 0;

	switch (event->header.type) {
	case PERF_RECORD_LOST:
1314
		color_fprintf(trace->output, PERF_COLOR_RED,
1315
			      "LOST %" PRIu64 " events!\n", event->lost.lost);
1316
		ret = machine__process_lost_event(machine, event, sample);
1317
	default:
1318
		ret = machine__process_event(machine, event, sample);
1319 1320 1321 1322 1323 1324
		break;
	}

	return ret;
}

1325
static int trace__tool_process(struct perf_tool *tool,
1326
			       union perf_event *event,
1327
			       struct perf_sample *sample,
1328 1329
			       struct machine *machine)
{
1330
	struct trace *trace = container_of(tool, struct trace, tool);
1331
	return trace__process_event(trace, machine, event, sample);
1332 1333 1334 1335 1336 1337 1338 1339 1340
}

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

	if (err)
		return err;

1341 1342 1343
	trace->host = machine__new_host();
	if (trace->host == NULL)
		return -ENOMEM;
1344 1345

	if (perf_target__has_task(&trace->opts.target)) {
1346
		err = perf_event__synthesize_thread_map(&trace->tool, evlist->threads,
1347
							trace__tool_process,
1348
							trace->host);
1349
	} else {
1350
		err = perf_event__synthesize_threads(&trace->tool, trace__tool_process,
1351
						     trace->host);
1352 1353 1354 1355 1356 1357 1358 1359
	}

	if (err)
		symbol__exit();

	return err;
}

1360 1361 1362 1363 1364 1365 1366 1367 1368
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;

1369 1370 1371
	if (sc->fmt)
		sc->arg_parm = sc->fmt->arg_parm;

1372
	for (field = sc->tp_format->format.fields->next; field; field = field->next) {
1373 1374 1375
		if (sc->fmt && sc->fmt->arg_scnprintf[idx])
			sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx];
		else if (field->flags & FIELD_IS_POINTER)
1376 1377 1378 1379 1380 1381 1382
			sc->arg_scnprintf[idx] = syscall_arg__scnprintf_hex;
		++idx;
	}

	return 0;
}

A
Arnaldo Carvalho de Melo 已提交
1383 1384 1385 1386
static int trace__read_syscall_info(struct trace *trace, int id)
{
	char tp_name[128];
	struct syscall *sc;
1387
	const char *name = audit_syscall_to_name(id, trace->audit.machine);
1388 1389 1390

	if (name == NULL)
		return -1;
A
Arnaldo Carvalho de Melo 已提交
1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409

	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;
1410
	sc->name = name;
1411

1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422
	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;
		}
1423 1424
	}

1425
	sc->fmt  = syscall_fmt__find(sc->name);
A
Arnaldo Carvalho de Melo 已提交
1426

1427
	snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->name);
A
Arnaldo Carvalho de Melo 已提交
1428
	sc->tp_format = event_format__new("syscalls", tp_name);
1429 1430 1431 1432 1433

	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
1434

1435 1436 1437 1438
	if (sc->tp_format == NULL)
		return -1;

	return syscall__set_arg_fmts(sc);
A
Arnaldo Carvalho de Melo 已提交
1439 1440
}

1441
static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
1442 1443
				      unsigned long *args, struct trace *trace,
				      struct thread *thread)
A
Arnaldo Carvalho de Melo 已提交
1444 1445 1446 1447 1448
{
	size_t printed = 0;

	if (sc->tp_format != NULL) {
		struct format_field *field;
1449 1450
		u8 bit = 1;
		struct syscall_arg arg = {
1451 1452 1453 1454
			.idx	= 0,
			.mask	= 0,
			.trace  = trace,
			.thread = thread,
1455
		};
1456 1457

		for (field = sc->tp_format->format.fields->next; field;
1458 1459
		     field = field->next, ++arg.idx, bit <<= 1) {
			if (arg.mask & bit)
1460
				continue;
1461 1462 1463 1464 1465 1466 1467 1468 1469
			/*
 			 * 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]))
1470 1471
				continue;

1472
			printed += scnprintf(bf + printed, size - printed,
1473
					     "%s%s: ", printed ? ", " : "", field->name);
1474 1475
			if (sc->arg_scnprintf && sc->arg_scnprintf[arg.idx]) {
				arg.val = args[arg.idx];
1476 1477
				if (sc->arg_parm)
					arg.parm = sc->arg_parm[arg.idx];
1478 1479
				printed += sc->arg_scnprintf[arg.idx](bf + printed,
								      size - printed, &arg);
1480
			} else {
1481
				printed += scnprintf(bf + printed, size - printed,
1482
						     "%ld", args[arg.idx]);
1483
			}
A
Arnaldo Carvalho de Melo 已提交
1484 1485
		}
	} else {
1486 1487
		int i = 0;

A
Arnaldo Carvalho de Melo 已提交
1488
		while (i < 6) {
1489 1490 1491
			printed += scnprintf(bf + printed, size - printed,
					     "%sarg%d: %ld",
					     printed ? ", " : "", i, args[i]);
A
Arnaldo Carvalho de Melo 已提交
1492 1493 1494 1495 1496 1497 1498
			++i;
		}
	}

	return printed;
}

1499 1500 1501 1502
typedef int (*tracepoint_handler)(struct trace *trace, struct perf_evsel *evsel,
				  struct perf_sample *sample);

static struct syscall *trace__syscall_info(struct trace *trace,
1503
					   struct perf_evsel *evsel, int id)
1504 1505 1506
{

	if (id < 0) {
1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522

		/*
		 * 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);
		}
1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535
		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:
1536 1537 1538 1539 1540 1541
	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);
	}
1542 1543 1544
	return NULL;
}

1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570
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);
}

1571 1572 1573
static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
			    struct perf_sample *sample)
{
1574
	char *msg;
1575
	void *args;
1576
	size_t printed = 0;
1577
	struct thread *thread;
1578
	int id = perf_evsel__sc_tp_uint(evsel, id, sample);
1579
	struct syscall *sc = trace__syscall_info(trace, evsel, id);
1580 1581 1582 1583
	struct thread_trace *ttrace;

	if (sc == NULL)
		return -1;
1584

1585 1586 1587
	if (sc->filtered)
		return 0;

1588
	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
1589
	ttrace = thread__trace(thread, trace->output);
1590
	if (ttrace == NULL)
1591 1592
		return -1;

1593
	args = perf_evsel__sc_tp_ptr(evsel, args, sample);
1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605
	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);

1606 1607
	printed += syscall__scnprintf_args(sc, msg + printed, 1024 - printed,
					   args, trace, thread);
1608 1609

	if (!strcmp(sc->name, "exit_group") || !strcmp(sc->name, "exit")) {
1610
		if (!trace->duration_filter) {
1611 1612
			trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output);
			fprintf(trace->output, "%-70s\n", ttrace->entry_str);
1613
		}
1614 1615
	} else
		ttrace->entry_pending = true;
1616 1617 1618 1619 1620 1621 1622 1623

	return 0;
}

static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
			   struct perf_sample *sample)
{
	int ret;
1624
	u64 duration = 0;
1625
	struct thread *thread;
1626
	int id = perf_evsel__sc_tp_uint(evsel, id, sample);
1627
	struct syscall *sc = trace__syscall_info(trace, evsel, id);
1628 1629 1630 1631
	struct thread_trace *ttrace;

	if (sc == NULL)
		return -1;
1632

1633 1634 1635
	if (sc->filtered)
		return 0;

1636
	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
1637
	ttrace = thread__trace(thread, trace->output);
1638
	if (ttrace == NULL)
1639 1640
		return -1;

1641 1642 1643
	if (trace->summary)
		thread__update_stats(ttrace, id, sample);

1644
	ret = perf_evsel__sc_tp_uint(evsel, ret, sample);
1645

1646 1647 1648 1649 1650 1651
	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;
	}

1652 1653 1654 1655
	ttrace = thread->priv;

	ttrace->exit_time = sample->time;

1656
	if (ttrace->entry_time) {
1657
		duration = sample->time - ttrace->entry_time;
1658 1659 1660 1661
		if (trace__filter_duration(trace, duration))
			goto out;
	} else if (trace->duration_filter)
		goto out;
1662

1663
	trace__fprintf_entry_head(trace, thread, duration, sample->time, trace->output);
1664 1665

	if (ttrace->entry_pending) {
1666
		fprintf(trace->output, "%-70s", ttrace->entry_str);
1667
	} else {
1668 1669 1670
		fprintf(trace->output, " ... [");
		color_fprintf(trace->output, PERF_COLOR_YELLOW, "continued");
		fprintf(trace->output, "]: %s()", sc->name);
1671 1672
	}

1673 1674 1675 1676
	if (sc->fmt == NULL) {
signed_print:
		fprintf(trace->output, ") = %d", ret);
	} else if (ret < 0 && sc->fmt->errmsg) {
1677 1678 1679 1680
		char bf[256];
		const char *emsg = strerror_r(-ret, bf, sizeof(bf)),
			   *e = audit_errno_to_name(-ret);

1681
		fprintf(trace->output, ") = -1 %s %s", e, emsg);
1682
	} else if (ret == 0 && sc->fmt->timeout)
1683
		fprintf(trace->output, ") = 0 Timeout");
1684 1685
	else if (sc->fmt->hexret)
		fprintf(trace->output, ") = %#x", ret);
1686
	else
1687
		goto signed_print;
1688

1689
	fputc('\n', trace->output);
1690
out:
1691 1692
	ttrace->entry_pending = false;

1693 1694 1695
	return 0;
}

1696 1697 1698 1699 1700 1701 1702
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;
}

1703 1704 1705 1706 1707
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;
1708
	struct thread *thread = machine__findnew_thread(trace->host,
1709 1710
							sample->pid,
							sample->tid);
1711
	struct thread_trace *ttrace = thread__trace(thread, trace->output);
1712 1713 1714 1715 1716 1717 1718 1719 1720

	if (ttrace == NULL)
		goto out_dump;

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

out_dump:
1721
	fprintf(trace->output, "%s: comm=%s,pid=%u,runtime=%" PRIu64 ",vruntime=%" PRIu64 ")\n",
1722 1723 1724 1725 1726 1727 1728 1729
	       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;
}

1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741
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;
}

1742 1743 1744 1745 1746 1747 1748 1749 1750
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;

1751
	tracepoint_handler handler = evsel->handler;
1752

1753 1754 1755
	if (skip_sample(trace, sample))
		return 0;

1756
	if (!trace->full_time && trace->base_time == 0)
1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774
		trace->base_time = sample->time;

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

	return err;
}

static bool
perf_session__has_tp(struct perf_session *session, const char *name)
{
	struct perf_evsel *evsel;

	evsel = perf_evlist__find_tracepoint_by_name(session->evlist, name);

	return evsel != NULL;
}

1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795
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
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 1821 1822
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);
}

1823 1824
static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);

1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836
static void perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
{
	struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname",
						     evlist->nr_entries);
	if (evsel == NULL)
		return;

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

1837
	evsel->handler = trace__vfs_getname;
1838 1839 1840
	perf_evlist__add(evlist, evsel);
}

1841
static int trace__run(struct trace *trace, int argc, const char **argv)
A
Arnaldo Carvalho de Melo 已提交
1842
{
1843
	struct perf_evlist *evlist = perf_evlist__new();
1844
	struct perf_evsel *evsel;
1845 1846
	int err = -1, i;
	unsigned long before;
1847
	const bool forks = argc > 0;
A
Arnaldo Carvalho de Melo 已提交
1848

1849 1850
	trace->live = true;

A
Arnaldo Carvalho de Melo 已提交
1851
	if (evlist == NULL) {
1852
		fprintf(trace->output, "Not enough memory to run!\n");
A
Arnaldo Carvalho de Melo 已提交
1853 1854 1855
		goto out;
	}

1856
	if (perf_evlist__add_syscall_newtp(evlist, trace__sys_enter, trace__sys_exit))
1857
		goto out_error_tp;
A
Arnaldo Carvalho de Melo 已提交
1858

1859 1860
	perf_evlist__add_vfs_getname(evlist);

1861
	if (trace->sched &&
1862 1863 1864
		perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
				trace__sched_stat_runtime))
		goto out_error_tp;
1865

A
Arnaldo Carvalho de Melo 已提交
1866 1867
	err = perf_evlist__create_maps(evlist, &trace->opts.target);
	if (err < 0) {
1868
		fprintf(trace->output, "Problems parsing the target to trace, check your options!\n");
A
Arnaldo Carvalho de Melo 已提交
1869 1870 1871
		goto out_delete_evlist;
	}

1872 1873
	err = trace__symbols_init(trace, evlist);
	if (err < 0) {
1874
		fprintf(trace->output, "Problems initializing symbol libraries!\n");
1875
		goto out_delete_maps;
1876 1877
	}

1878
	perf_evlist__config(evlist, &trace->opts);
A
Arnaldo Carvalho de Melo 已提交
1879

1880 1881 1882 1883
	signal(SIGCHLD, sig_handler);
	signal(SIGINT, sig_handler);

	if (forks) {
1884
		err = perf_evlist__prepare_workload(evlist, &trace->opts.target,
1885
						    argv, false, false);
1886
		if (err < 0) {
1887
			fprintf(trace->output, "Couldn't run the workload!\n");
1888
			goto out_delete_maps;
1889 1890 1891
		}
	}

A
Arnaldo Carvalho de Melo 已提交
1892
	err = perf_evlist__open(evlist);
1893 1894
	if (err < 0)
		goto out_error_open;
A
Arnaldo Carvalho de Melo 已提交
1895 1896 1897

	err = perf_evlist__mmap(evlist, UINT_MAX, false);
	if (err < 0) {
1898
		fprintf(trace->output, "Couldn't mmap the events: %s\n", strerror(errno));
1899
		goto out_close_evlist;
A
Arnaldo Carvalho de Melo 已提交
1900 1901 1902
	}

	perf_evlist__enable(evlist);
1903 1904 1905 1906

	if (forks)
		perf_evlist__start_workload(evlist);

1907
	trace->multiple_threads = evlist->threads->map[0] == -1 || evlist->threads->nr > 1;
A
Arnaldo Carvalho de Melo 已提交
1908
again:
1909
	before = trace->nr_events;
A
Arnaldo Carvalho de Melo 已提交
1910 1911 1912 1913 1914 1915

	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;
1916
			tracepoint_handler handler;
A
Arnaldo Carvalho de Melo 已提交
1917 1918
			struct perf_sample sample;

1919
			++trace->nr_events;
A
Arnaldo Carvalho de Melo 已提交
1920 1921 1922

			err = perf_evlist__parse_sample(evlist, event, &sample);
			if (err) {
1923
				fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err);
1924
				goto next_event;
A
Arnaldo Carvalho de Melo 已提交
1925 1926
			}

1927
			if (!trace->full_time && trace->base_time == 0)
1928 1929 1930
				trace->base_time = sample.time;

			if (type != PERF_RECORD_SAMPLE) {
1931
				trace__process_event(trace, trace->host, event, &sample);
1932 1933 1934
				continue;
			}

A
Arnaldo Carvalho de Melo 已提交
1935 1936
			evsel = perf_evlist__id2evsel(evlist, sample.id);
			if (evsel == NULL) {
1937
				fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample.id);
1938
				goto next_event;
A
Arnaldo Carvalho de Melo 已提交
1939 1940
			}

1941
			if (sample.raw_data == NULL) {
1942
				fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
1943 1944
				       perf_evsel__name(evsel), sample.tid,
				       sample.cpu, sample.raw_size);
1945
				goto next_event;
1946 1947
			}

1948
			handler = evsel->handler;
1949
			handler(trace, evsel, &sample);
1950 1951
next_event:
			perf_evlist__mmap_consume(evlist, i);
1952

1953 1954
			if (interrupted)
				goto out_disable;
A
Arnaldo Carvalho de Melo 已提交
1955 1956 1957
		}
	}

1958
	if (trace->nr_events == before) {
1959
		int timeout = done ? 100 : -1;
1960

1961 1962 1963 1964
		if (poll(evlist->pollfd, evlist->nr_fds, timeout) > 0)
			goto again;
	} else {
		goto again;
1965 1966
	}

1967 1968
out_disable:
	perf_evlist__disable(evlist);
A
Arnaldo Carvalho de Melo 已提交
1969

1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981
	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);
		}
	}
1982

1983 1984 1985 1986 1987
	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
1988 1989 1990
out_delete_evlist:
	perf_evlist__delete(evlist);
out:
1991
	trace->live = false;
A
Arnaldo Carvalho de Melo 已提交
1992
	return err;
1993 1994
{
	char errbuf[BUFSIZ];
1995 1996

out_error_tp:
1997
	perf_evlist__strerror_tp(evlist, errno, errbuf, sizeof(errbuf));
1998 1999 2000 2001 2002 2003
	goto out_error;

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

out_error:
2004
	fprintf(trace->output, "%s\n", errbuf);
2005
	goto out_delete_evlist;
A
Arnaldo Carvalho de Melo 已提交
2006
}
2007
}
A
Arnaldo Carvalho de Melo 已提交
2008

2009 2010 2011 2012 2013
static int trace__replay(struct trace *trace)
{
	const struct perf_evsel_str_handler handlers[] = {
		{ "raw_syscalls:sys_enter",  trace__sys_enter, },
		{ "raw_syscalls:sys_exit",   trace__sys_exit, },
2014
		{ "probe:vfs_getname",	     trace__vfs_getname, },
2015
	};
2016 2017 2018 2019
	struct perf_data_file file = {
		.path  = input_name,
		.mode  = PERF_DATA_MODE_READ,
	};
2020 2021 2022 2023 2024
	struct perf_session *session;
	int err = -1;

	trace->tool.sample	  = trace__process_sample;
	trace->tool.mmap	  = perf_event__process_mmap;
D
David Ahern 已提交
2025
	trace->tool.mmap2	  = perf_event__process_mmap2;
2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041
	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;

2042
	session = perf_session__new(&file, false, &trace->tool);
2043 2044 2045
	if (session == NULL)
		return -ENOMEM;

2046 2047
	trace->host = &session->machines.host;

2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061
	err = perf_session__set_tracepoints_handlers(session, handlers);
	if (err)
		goto out;

	if (!perf_session__has_tp(session, "raw_syscalls:sys_enter")) {
		pr_err("Data file does not have raw_syscalls:sys_enter events\n");
		goto out;
	}

	if (!perf_session__has_tp(session, "raw_syscalls:sys_exit")) {
		pr_err("Data file does not have raw_syscalls:sys_exit events\n");
		goto out;
	}

2062 2063 2064 2065
	err = parse_target_str(trace);
	if (err != 0)
		goto out;

2066 2067 2068 2069 2070 2071
	setup_pager();

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

2072 2073 2074
	else if (trace->summary)
		trace__fprintf_thread_summary(trace, trace->output);

2075 2076 2077 2078 2079 2080
out:
	perf_session__delete(session);

	return err;
}

2081 2082 2083 2084
static size_t trace__fprintf_threads_header(FILE *fp)
{
	size_t printed;

2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131
	printed  = fprintf(fp, "\n _____________________________________________________________________________\n");
	printed += fprintf(fp, " __)    Summary of events    (__\n\n");
	printed += fprintf(fp, "              [ task - pid ]     [ events ] [ ratio ]  [ runtime ]\n");
	printed += fprintf(fp, "                                  syscall  count    min     max    avg  stddev\n");
	printed += fprintf(fp, "                                                   msec    msec   msec     %%\n");
	printed += fprintf(fp, " _____________________________________________________________________________\n\n");

	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");

	/* 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];
			printed += fprintf(fp, "%24s  %14s : ", "", sc->name);
			printed += fprintf(fp, "%5" PRIu64 "  %8.3f  %8.3f",
					   n, min, max);
			printed += fprintf(fp, "  %8.3f  %6.2f\n", avg, pct);
		}

		inode = intlist__next(inode);
	}

	printed += fprintf(fp, "\n\n");
2132 2133 2134 2135

	return printed;
}

2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165
/* 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;

2166
	printed += color_fprintf(fp, color, "%20s", thread__comm_str(thread));
2167 2168 2169
	printed += fprintf(fp, " - %-5d :%11lu   [", thread->tid, ttrace->nr_events);
	printed += color_fprintf(fp, color, "%5.1f%%", ratio);
	printed += fprintf(fp, " ] %10.3f ms\n", ttrace->runtime_ms);
2170
	printed += thread__dump_stats(ttrace, trace, fp);
2171 2172 2173 2174 2175 2176

	data->printed += printed;

	return 0;
}

2177 2178
static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
{
2179 2180 2181 2182 2183
	struct summary_data data = {
		.fp = fp,
		.trace = trace
	};
	data.printed = trace__fprintf_threads_header(fp);
2184

2185 2186 2187
	machine__for_each_thread(trace->host, trace__fprintf_one_thread, &data);

	return data.printed;
2188 2189
}

2190 2191 2192 2193 2194 2195 2196 2197 2198
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;
}

2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215
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
2216 2217 2218
int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
{
	const char * const trace_usage[] = {
2219 2220
		"perf trace [<options>] [<command>]",
		"perf trace [<options>] -- <command> [<options>]",
D
David Ahern 已提交
2221 2222
		"perf trace record [<options>] [<command>]",
		"perf trace record [<options>] -- <command> [<options>]",
A
Arnaldo Carvalho de Melo 已提交
2223 2224 2225
		NULL
	};
	struct trace trace = {
2226 2227 2228 2229
		.audit = {
			.machine = audit_detect_machine(),
			.open_id = audit_name_to_syscall("open", trace.audit.machine),
		},
A
Arnaldo Carvalho de Melo 已提交
2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242
		.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,
		},
2243
		.output = stdout,
2244
		.show_comm = true,
A
Arnaldo Carvalho de Melo 已提交
2245
	};
2246
	const char *output_name = NULL;
2247
	const char *ev_qualifier_str = NULL;
A
Arnaldo Carvalho de Melo 已提交
2248
	const struct option trace_options[] = {
2249 2250
	OPT_BOOLEAN(0, "comm", &trace.show_comm,
		    "show the thread COMM next to its id"),
2251
	OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"),
2252 2253
	OPT_STRING('e', "expr", &ev_qualifier_str, "expr",
		    "list of events to trace"),
2254
	OPT_STRING('o', "output", &output_name, "file", "output file name"),
2255
	OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
A
Arnaldo Carvalho de Melo 已提交
2256 2257
	OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
		    "trace events on existing process id"),
2258
	OPT_STRING('t', "tid", &trace.opts.target.tid, "tid",
A
Arnaldo Carvalho de Melo 已提交
2259
		    "trace events on existing thread id"),
2260
	OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide,
A
Arnaldo Carvalho de Melo 已提交
2261
		    "system-wide collection from all CPUs"),
2262
	OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu",
A
Arnaldo Carvalho de Melo 已提交
2263
		    "list of cpus to monitor"),
2264
	OPT_BOOLEAN(0, "no-inherit", &trace.opts.no_inherit,
A
Arnaldo Carvalho de Melo 已提交
2265
		    "child tasks do not inherit counters"),
2266 2267 2268
	OPT_CALLBACK('m', "mmap-pages", &trace.opts.mmap_pages, "pages",
		     "number of mmap data pages",
		     perf_evlist__parse_mmap_pages),
2269
	OPT_STRING('u', "uid", &trace.opts.target.uid_str, "user",
A
Arnaldo Carvalho de Melo 已提交
2270
		   "user to profile"),
2271 2272 2273
	OPT_CALLBACK(0, "duration", &trace, "float",
		     "show only events with duration > N.M ms",
		     trace__set_duration),
2274
	OPT_BOOLEAN(0, "sched", &trace.sched, "show blocking scheduler events"),
2275
	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
2276 2277
	OPT_BOOLEAN('T', "time", &trace.full_time,
		    "Show full timestamp, not time relative to first start"),
2278 2279
	OPT_BOOLEAN(0, "summary", &trace.summary,
		    "Show syscall summary with statistics"),
A
Arnaldo Carvalho de Melo 已提交
2280 2281 2282
	OPT_END()
	};
	int err;
2283
	char bf[BUFSIZ];
A
Arnaldo Carvalho de Melo 已提交
2284

D
David Ahern 已提交
2285 2286 2287
	if ((argc > 1) && (strcmp(argv[1], "record") == 0))
		return trace__record(argc-2, &argv[2]);

A
Arnaldo Carvalho de Melo 已提交
2288 2289
	argc = parse_options(argc, argv, trace_options, trace_usage, 0);

2290 2291 2292 2293 2294 2295 2296 2297
	if (output_name != NULL) {
		err = trace__open_output(&trace, output_name);
		if (err < 0) {
			perror("failed to create output file");
			goto out;
		}
	}

2298
	if (ev_qualifier_str != NULL) {
2299 2300 2301 2302 2303 2304
		const char *s = ev_qualifier_str;

		trace.not_ev_qualifier = *s == '!';
		if (trace.not_ev_qualifier)
			++s;
		trace.ev_qualifier = strlist__new(true, s);
2305
		if (trace.ev_qualifier == NULL) {
2306 2307 2308 2309
			fputs("Not enough memory to parse event qualifier",
			      trace.output);
			err = -ENOMEM;
			goto out_close;
2310 2311 2312
		}
	}

2313 2314 2315
	err = perf_target__validate(&trace.opts.target);
	if (err) {
		perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf));
2316 2317
		fprintf(trace.output, "%s", bf);
		goto out_close;
2318 2319
	}

A
Arnaldo Carvalho de Melo 已提交
2320 2321 2322
	err = perf_target__parse_uid(&trace.opts.target);
	if (err) {
		perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf));
2323 2324
		fprintf(trace.output, "%s", bf);
		goto out_close;
A
Arnaldo Carvalho de Melo 已提交
2325 2326
	}

2327
	if (!argc && perf_target__none(&trace.opts.target))
2328 2329
		trace.opts.target.system_wide = true;

2330 2331 2332 2333
	if (input_name)
		err = trace__replay(&trace);
	else
		err = trace__run(&trace, argc, argv);
2334

2335 2336 2337 2338
out_close:
	if (output_name != NULL)
		fclose(trace.output);
out:
2339
	return err;
A
Arnaldo Carvalho de Melo 已提交
2340
}