builtin-trace.c 56.6 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
struct syscall_arg {
	unsigned long val;
40 41
	struct thread *thread;
	struct trace  *trace;
42
	void	      *parm;
43 44 45 46
	u8	      idx;
	u8	      mask;
};

47
struct strarray {
48
	int	    offset;
49 50 51 52 53 54 55 56 57
	int	    nr_entries;
	const char **entries;
};

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

58 59 60 61 62 63
#define DEFINE_STRARRAY_OFFSET(array, off) struct strarray strarray__##array = { \
	.offset	    = off, \
	.nr_entries = ARRAY_SIZE(array), \
	.entries = array, \
}

64 65 66
static size_t __syscall_arg__scnprintf_strarray(char *bf, size_t size,
						const char *intfmt,
					        struct syscall_arg *arg)
67 68
{
	struct strarray *sa = arg->parm;
69
	int idx = arg->val - sa->offset;
70 71

	if (idx < 0 || idx >= sa->nr_entries)
72
		return scnprintf(bf, size, intfmt, arg->val);
73 74 75 76

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

77 78 79 80 81 82
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);
}

83 84
#define SCA_STRARRAY syscall_arg__scnprintf_strarray

85 86 87 88 89 90 91 92
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

93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115
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

116
static size_t syscall_arg__scnprintf_hex(char *bf, size_t size,
117
					 struct syscall_arg *arg)
118
{
119
	return scnprintf(bf, size, "%#lx", arg->val);
120 121
}

122 123
#define SCA_HEX syscall_arg__scnprintf_hex

124
static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
125
					       struct syscall_arg *arg)
126
{
127
	int printed = 0, prot = arg->val;
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

	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

155
static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
156
						struct syscall_arg *arg)
157
{
158
	int printed = 0, flags = arg->val;
159 160 161 162 163 164 165 166 167

#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);
168
#ifdef MAP_32BIT
169
	P_MMAP_FLAG(32BIT);
170
#endif
171 172 173 174 175 176
	P_MMAP_FLAG(ANONYMOUS);
	P_MMAP_FLAG(DENYWRITE);
	P_MMAP_FLAG(EXECUTABLE);
	P_MMAP_FLAG(FILE);
	P_MMAP_FLAG(FIXED);
	P_MMAP_FLAG(GROWSDOWN);
177
#ifdef MAP_HUGETLB
178
	P_MMAP_FLAG(HUGETLB);
179
#endif
180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197
	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

198
static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
199
						      struct syscall_arg *arg)
200
{
201
	int behavior = arg->val;
202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218

	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);
219
#ifdef MADV_HUGEPAGE
220
	P_MADV_BHV(HUGEPAGE);
221 222
#endif
#ifdef MADV_NOHUGEPAGE
223
	P_MADV_BHV(NOHUGEPAGE);
224
#endif
225 226 227 228 229 230 231 232 233 234 235 236 237 238 239
#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

240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270
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

271
static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, struct syscall_arg *arg)
272 273 274 275 276 277 278 279 280
{
	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),
	};
281
	int op = arg->val;
282 283 284 285 286
	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);
287 288 289 290 291 292
	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;
293
	P_FUTEX_OP(WAKE_OP);							  break;
294 295 296 297 298
	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;
299 300 301 302 303 304 305 306 307 308 309 310 311
	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;
}

312 313
#define SCA_FUTEX_OP  syscall_arg__scnprintf_futex_op

314 315
static const char *epoll_ctl_ops[] = { "ADD", "DEL", "MOD", };
static DEFINE_STRARRAY_OFFSET(epoll_ctl_ops, 1);
316

317 318 319
static const char *itimers[] = { "REAL", "VIRTUAL", "PROF", };
static DEFINE_STRARRAY(itimers);

320 321 322 323 324 325 326 327 328
static const char *whences[] = { "SET", "CUR", "END",
#ifdef SEEK_DATA
"DATA",
#endif
#ifdef SEEK_HOLE
"HOLE",
#endif
};
static DEFINE_STRARRAY(whences);
329

330 331 332 333 334 335 336 337
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);

338 339 340 341 342 343 344
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);

345 346 347
static const char *sighow[] = { "BLOCK", "UNBLOCK", "SETMASK", };
static DEFINE_STRARRAY(sighow);

348 349 350 351 352 353
static const char *clockid[] = {
	"REALTIME", "MONOTONIC", "PROCESS_CPUTIME_ID", "THREAD_CPUTIME_ID",
	"MONOTONIC_RAW", "REALTIME_COARSE", "MONOTONIC_COARSE",
};
static DEFINE_STRARRAY(clockid);

354 355 356 357 358 359 360 361 362 363
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);

364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410
#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

411 412 413
#ifndef MSG_PROBE
#define MSG_PROBE	     0x10
#endif
414 415 416
#ifndef MSG_WAITFORONE
#define MSG_WAITFORONE	0x10000
#endif
417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467
#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

468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494
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

495
static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
496
					       struct syscall_arg *arg)
497
{
498
	int printed = 0, flags = arg->val;
499 500

	if (!(flags & O_CREAT))
501
		arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */
502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550

	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

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
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

577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599
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

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
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

645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666
#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);

667 668 669 670
#define STRARRAY(arg, name, array) \
	  .arg_scnprintf = { [arg] = SCA_STRARRAY, }, \
	  .arg_parm	 = { [arg] = &strarray__##array, }

A
Arnaldo Carvalho de Melo 已提交
671 672
static struct syscall_fmt {
	const char *name;
673
	const char *alias;
674
	size_t	   (*arg_scnprintf[6])(char *bf, size_t size, struct syscall_arg *arg);
675
	void	   *arg_parm[6];
A
Arnaldo Carvalho de Melo 已提交
676 677
	bool	   errmsg;
	bool	   timeout;
678
	bool	   hexret;
A
Arnaldo Carvalho de Melo 已提交
679
} syscall_fmts[] = {
680 681
	{ .name	    = "access",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_ACCMODE, /* mode */ }, },
682
	{ .name	    = "arch_prctl", .errmsg = true, .alias = "prctl", },
683 684
	{ .name	    = "brk",	    .hexret = true,
	  .arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, },
685
	{ .name     = "clock_gettime",  .errmsg = true, STRARRAY(0, clk_id, clockid), },
686 687
	{ .name	    = "close",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, }, 
688
	{ .name	    = "connect",    .errmsg = true, },
689 690 691 692 693 694
	{ .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 */ }, }, 
695
	{ .name	    = "epoll_ctl",  .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), },
696 697
	{ .name	    = "eventfd2",   .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, },
698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719
	{ .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 */ }, }, 
720
	{ .name	    = "flock",	    .errmsg = true,
721 722 723 724 725 726 727 728 729 730 731 732 733 734
	  .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 */ }, }, 
735 736
	{ .name	    = "futex",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, },
737 738 739 740 741 742
	{ .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 */ }, }, 
743 744
	{ .name	    = "getitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
	{ .name	    = "getrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
745
	{ .name	    = "ioctl",	    .errmsg = true,
746
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ 
747 748 749
			     [1] = SCA_STRHEXARRAY, /* cmd */
			     [2] = SCA_HEX, /* arg */ },
	  .arg_parm	 = { [1] = &strarray__tioctls, /* cmd */ }, },
750 751
	{ .name	    = "kill",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
752 753 754 755 756 757
	{ .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 */ }, },
758
	{ .name	    = "lstat",	    .errmsg = true, .alias = "newlstat", },
759 760 761
	{ .name     = "madvise",    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_HEX,	 /* start */
			     [2] = SCA_MADV_BHV, /* behavior */ }, },
762 763 764 765
	{ .name	    = "mkdirat",    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
	{ .name	    = "mknodat",    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, }, 
766 767 768 769
	{ .name	    = "mlock",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
	{ .name	    = "mlockall",   .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
770
	{ .name	    = "mmap",	    .hexret = true,
771
	  .arg_scnprintf = { [0] = SCA_HEX,	  /* addr */
772 773
			     [2] = SCA_MMAP_PROT, /* prot */
			     [3] = SCA_MMAP_FLAGS, /* flags */ }, },
774
	{ .name	    = "mprotect",   .errmsg = true,
775 776 777 778 779
	  .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 */ }, },
780 781
	{ .name	    = "munlock",    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
782 783
	{ .name	    = "munmap",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
784 785 786 787
	{ .name	    = "name_to_handle_at", .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
	{ .name	    = "newfstatat", .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
788 789
	{ .name	    = "open",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, },
790
	{ .name	    = "open_by_handle_at", .errmsg = true,
791 792
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
			     [2] = SCA_OPEN_FLAGS, /* flags */ }, },
793
	{ .name	    = "openat",	    .errmsg = true,
794 795
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
			     [2] = SCA_OPEN_FLAGS, /* flags */ }, },
796 797
	{ .name	    = "pipe2",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, },
798 799
	{ .name	    = "poll",	    .errmsg = true, .timeout = true, },
	{ .name	    = "ppoll",	    .errmsg = true, .timeout = true, },
800 801 802 803
	{ .name	    = "pread",	    .errmsg = true, .alias = "pread64",
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
	{ .name	    = "preadv",	    .errmsg = true, .alias = "pread",
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
804
	{ .name	    = "prlimit64",  .errmsg = true, STRARRAY(1, resource, rlimit_resources), },
805 806 807 808 809 810 811 812 813 814
	{ .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 */ }, }, 
815 816 817 818 819 820
	{ .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 */ }, },
821 822
	{ .name	    = "renameat",   .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
823 824
	{ .name	    = "rt_sigaction", .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, },
825
	{ .name	    = "rt_sigprocmask",  .errmsg = true, STRARRAY(0, how, sighow), },
826 827 828 829
	{ .name	    = "rt_sigqueueinfo", .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
	{ .name	    = "rt_tgsigqueueinfo", .errmsg = true,
	  .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
830
	{ .name	    = "select",	    .errmsg = true, .timeout = true, },
831 832 833 834 835 836
	{ .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 */ }, },
837 838
	{ .name	    = "setitimer",  .errmsg = true, STRARRAY(0, which, itimers), },
	{ .name	    = "setrlimit",  .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
839 840
	{ .name	    = "shutdown",   .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FD, /* fd */ }, }, 
841
	{ .name	    = "socket",	    .errmsg = true,
842 843
	  .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
			     [1] = SCA_SK_TYPE, /* type */ },
844 845 846 847
	  .arg_parm	 = { [0] = &strarray__socket_families, /* family */ }, },
	{ .name	    = "socketpair", .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
			     [1] = SCA_SK_TYPE, /* type */ },
848
	  .arg_parm	 = { [0] = &strarray__socket_families, /* family */ }, },
849
	{ .name	    = "stat",	    .errmsg = true, .alias = "newstat", },
850 851
	{ .name	    = "symlinkat",  .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, }, 
852 853 854 855
	{ .name	    = "tgkill",	    .errmsg = true,
	  .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
	{ .name	    = "tkill",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
856
	{ .name	    = "uname",	    .errmsg = true, .alias = "newuname", },
857 858 859 860 861 862 863 864
	{ .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
865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881
};

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;
882
	bool		    filtered;
A
Arnaldo Carvalho de Melo 已提交
883
	struct syscall_fmt  *fmt;
884
	size_t		    (**arg_scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
885
	void		    **arg_parm;
A
Arnaldo Carvalho de Melo 已提交
886 887
};

888 889 890 891 892 893 894 895 896 897 898
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);
899
	return printed + fprintf(fp, "): ");
900 901
}

902 903 904 905
struct thread_trace {
	u64		  entry_time;
	u64		  exit_time;
	bool		  entry_pending;
906
	unsigned long	  nr_events;
907
	char		  *entry_str;
908
	double		  runtime_ms;
909 910 911 912
	struct {
		int	  max;
		char	  **table;
	} paths;
913 914

	struct intlist *syscall_stats;
915 916 917 918
};

static struct thread_trace *thread_trace__new(void)
{
919 920 921 922 923
	struct thread_trace *ttrace =  zalloc(sizeof(struct thread_trace));

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

924 925
	ttrace->syscall_stats = intlist__new(NULL);

926
	return ttrace;
927 928
}

929
static struct thread_trace *thread__trace(struct thread *thread, FILE *fp)
930
{
931 932
	struct thread_trace *ttrace;

933 934 935 936 937
	if (thread == NULL)
		goto fail;

	if (thread->priv == NULL)
		thread->priv = thread_trace__new();
938
		
939 940 941
	if (thread->priv == NULL)
		goto fail;

942 943 944 945
	ttrace = thread->priv;
	++ttrace->nr_events;

	return ttrace;
946
fail:
947
	color_fprintf(fp, PERF_COLOR_RED,
948 949 950 951
		      "WARNING: not enough memory, dropping samples!\n");
	return NULL;
}

A
Arnaldo Carvalho de Melo 已提交
952
struct trace {
953
	struct perf_tool	tool;
A
Arnaldo Carvalho de Melo 已提交
954 955 956 957 958 959
	int			audit_machine;
	struct {
		int		max;
		struct syscall  *table;
	} syscalls;
	struct perf_record_opts opts;
960
	struct machine		*host;
961
	u64			base_time;
962
	bool			full_time;
963
	FILE			*output;
964
	unsigned long		nr_events;
965 966
	struct strlist		*ev_qualifier;
	bool			not_ev_qualifier;
967
	bool			live;
968 969
	struct intlist		*tid_list;
	struct intlist		*pid_list;
970
	bool			sched;
971
	bool			multiple_threads;
972
	bool			summary;
973
	bool			show_comm;
974
	double			duration_filter;
975
	double			runtime_ms;
A
Arnaldo Carvalho de Melo 已提交
976 977
};

978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069
static int thread__read_fd_path(struct thread *thread, int fd)
{
	struct thread_trace *ttrace = thread->priv;
	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';

	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;
}

static const char *thread__fd_path(struct thread *thread, int fd, bool live)
{
	struct thread_trace *ttrace = thread->priv;

	if (ttrace == NULL)
		return NULL;

	if (fd < 0)
		return NULL;

	if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL) &&
	    (!live || thread__read_fd_path(thread, fd)))
		return NULL;

	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);
	const char *path = thread__fd_path(arg->thread, fd, arg->trace->live);

	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;
}

1070 1071 1072 1073 1074
static bool trace__filter_duration(struct trace *trace, double t)
{
	return t < (trace->duration_filter * NSEC_PER_MSEC);
}

1075 1076 1077 1078
static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
{
	double ts = (double)(tstamp - trace->base_time) / NSEC_PER_MSEC;

1079
	return fprintf(fp, "%10.3f ", ts);
1080 1081
}

1082 1083 1084 1085 1086 1087 1088
static bool done = false;

static void sig_handler(int sig __maybe_unused)
{
	done = true;
}

1089
static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
1090
					u64 duration, u64 tstamp, FILE *fp)
1091 1092
{
	size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
1093
	printed += fprintf_duration(duration, fp);
1094

1095 1096 1097
	if (trace->multiple_threads) {
		if (trace->show_comm)
			printed += fprintf(fp, "%.14s/", thread->comm);
1098
		printed += fprintf(fp, "%d ", thread->tid);
1099
	}
1100 1101 1102 1103

	return printed;
}

1104 1105
static int trace__process_event(struct trace *trace, struct machine *machine,
				union perf_event *event)
1106 1107 1108 1109 1110
{
	int ret = 0;

	switch (event->header.type) {
	case PERF_RECORD_LOST:
1111
		color_fprintf(trace->output, PERF_COLOR_RED,
1112 1113 1114 1115 1116 1117 1118 1119 1120 1121
			      "LOST %" PRIu64 " events!\n", event->lost.lost);
		ret = machine__process_lost_event(machine, event);
	default:
		ret = machine__process_event(machine, event);
		break;
	}

	return ret;
}

1122
static int trace__tool_process(struct perf_tool *tool,
1123 1124 1125 1126
			       union perf_event *event,
			       struct perf_sample *sample __maybe_unused,
			       struct machine *machine)
{
1127 1128
	struct trace *trace = container_of(tool, struct trace, tool);
	return trace__process_event(trace, machine, event);
1129 1130 1131 1132 1133 1134 1135 1136 1137
}

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

	if (err)
		return err;

1138 1139 1140
	trace->host = machine__new_host();
	if (trace->host == NULL)
		return -ENOMEM;
1141 1142

	if (perf_target__has_task(&trace->opts.target)) {
1143
		err = perf_event__synthesize_thread_map(&trace->tool, evlist->threads,
1144
							trace__tool_process,
1145
							trace->host);
1146
	} else {
1147
		err = perf_event__synthesize_threads(&trace->tool, trace__tool_process,
1148
						     trace->host);
1149 1150 1151 1152 1153 1154 1155 1156
	}

	if (err)
		symbol__exit();

	return err;
}

1157 1158 1159 1160 1161 1162 1163 1164 1165
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;

1166 1167 1168
	if (sc->fmt)
		sc->arg_parm = sc->fmt->arg_parm;

1169
	for (field = sc->tp_format->format.fields->next; field; field = field->next) {
1170 1171 1172
		if (sc->fmt && sc->fmt->arg_scnprintf[idx])
			sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx];
		else if (field->flags & FIELD_IS_POINTER)
1173 1174 1175 1176 1177 1178 1179
			sc->arg_scnprintf[idx] = syscall_arg__scnprintf_hex;
		++idx;
	}

	return 0;
}

A
Arnaldo Carvalho de Melo 已提交
1180 1181 1182 1183
static int trace__read_syscall_info(struct trace *trace, int id)
{
	char tp_name[128];
	struct syscall *sc;
1184 1185 1186 1187
	const char *name = audit_syscall_to_name(id, trace->audit_machine);

	if (name == NULL)
		return -1;
A
Arnaldo Carvalho de Melo 已提交
1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206

	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;
1207
	sc->name = name;
1208

1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219
	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;
		}
1220 1221
	}

1222
	sc->fmt  = syscall_fmt__find(sc->name);
A
Arnaldo Carvalho de Melo 已提交
1223

1224
	snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->name);
A
Arnaldo Carvalho de Melo 已提交
1225
	sc->tp_format = event_format__new("syscalls", tp_name);
1226 1227 1228 1229 1230

	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
1231

1232 1233 1234 1235
	if (sc->tp_format == NULL)
		return -1;

	return syscall__set_arg_fmts(sc);
A
Arnaldo Carvalho de Melo 已提交
1236 1237
}

1238
static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
1239 1240
				      unsigned long *args, struct trace *trace,
				      struct thread *thread)
A
Arnaldo Carvalho de Melo 已提交
1241 1242 1243 1244 1245
{
	size_t printed = 0;

	if (sc->tp_format != NULL) {
		struct format_field *field;
1246 1247
		u8 bit = 1;
		struct syscall_arg arg = {
1248 1249 1250 1251
			.idx	= 0,
			.mask	= 0,
			.trace  = trace,
			.thread = thread,
1252
		};
1253 1254

		for (field = sc->tp_format->format.fields->next; field;
1255 1256
		     field = field->next, ++arg.idx, bit <<= 1) {
			if (arg.mask & bit)
1257
				continue;
1258 1259 1260 1261 1262 1263 1264 1265 1266
			/*
 			 * 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]))
1267 1268
				continue;

1269
			printed += scnprintf(bf + printed, size - printed,
1270
					     "%s%s: ", printed ? ", " : "", field->name);
1271 1272
			if (sc->arg_scnprintf && sc->arg_scnprintf[arg.idx]) {
				arg.val = args[arg.idx];
1273 1274
				if (sc->arg_parm)
					arg.parm = sc->arg_parm[arg.idx];
1275 1276
				printed += sc->arg_scnprintf[arg.idx](bf + printed,
								      size - printed, &arg);
1277
			} else {
1278
				printed += scnprintf(bf + printed, size - printed,
1279
						     "%ld", args[arg.idx]);
1280
			}
A
Arnaldo Carvalho de Melo 已提交
1281 1282
		}
	} else {
1283 1284
		int i = 0;

A
Arnaldo Carvalho de Melo 已提交
1285
		while (i < 6) {
1286 1287 1288
			printed += scnprintf(bf + printed, size - printed,
					     "%sarg%d: %ld",
					     printed ? ", " : "", i, args[i]);
A
Arnaldo Carvalho de Melo 已提交
1289 1290 1291 1292 1293 1294 1295
			++i;
		}
	}

	return printed;
}

1296 1297 1298 1299
typedef int (*tracepoint_handler)(struct trace *trace, struct perf_evsel *evsel,
				  struct perf_sample *sample);

static struct syscall *trace__syscall_info(struct trace *trace,
1300
					   struct perf_evsel *evsel, int id)
1301 1302 1303
{

	if (id < 0) {
1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319

		/*
		 * 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);
		}
1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332
		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:
1333 1334 1335 1336 1337 1338
	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);
	}
1339 1340 1341
	return NULL;
}

1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367
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);
}

1368 1369 1370
static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
			    struct perf_sample *sample)
{
1371
	char *msg;
1372
	void *args;
1373
	size_t printed = 0;
1374
	struct thread *thread;
1375 1376
	int id = perf_evsel__intval(evsel, sample, "id");
	struct syscall *sc = trace__syscall_info(trace, evsel, id);
1377 1378 1379 1380
	struct thread_trace *ttrace;

	if (sc == NULL)
		return -1;
1381

1382 1383 1384
	if (sc->filtered)
		return 0;

1385
	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
1386
	ttrace = thread__trace(thread, trace->output);
1387
	if (ttrace == NULL)
1388 1389 1390 1391
		return -1;

	args = perf_evsel__rawptr(evsel, sample, "args");
	if (args == NULL) {
1392
		fprintf(trace->output, "Problems reading syscall arguments\n");
1393 1394 1395
		return -1;
	}

1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407
	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);

1408 1409
	printed += syscall__scnprintf_args(sc, msg + printed, 1024 - printed,
					   args, trace, thread);
1410 1411

	if (!strcmp(sc->name, "exit_group") || !strcmp(sc->name, "exit")) {
1412
		if (!trace->duration_filter) {
1413 1414
			trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output);
			fprintf(trace->output, "%-70s\n", ttrace->entry_str);
1415
		}
1416 1417
	} else
		ttrace->entry_pending = true;
1418 1419 1420 1421 1422 1423 1424 1425

	return 0;
}

static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
			   struct perf_sample *sample)
{
	int ret;
1426
	u64 duration = 0;
1427
	struct thread *thread;
1428 1429
	int id = perf_evsel__intval(evsel, sample, "id");
	struct syscall *sc = trace__syscall_info(trace, evsel, id);
1430 1431 1432 1433
	struct thread_trace *ttrace;

	if (sc == NULL)
		return -1;
1434

1435 1436 1437
	if (sc->filtered)
		return 0;

1438
	thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
1439
	ttrace = thread__trace(thread, trace->output);
1440
	if (ttrace == NULL)
1441 1442
		return -1;

1443 1444 1445
	if (trace->summary)
		thread__update_stats(ttrace, id, sample);

1446 1447
	ret = perf_evsel__intval(evsel, sample, "ret");

1448 1449 1450 1451
	ttrace = thread->priv;

	ttrace->exit_time = sample->time;

1452
	if (ttrace->entry_time) {
1453
		duration = sample->time - ttrace->entry_time;
1454 1455 1456 1457
		if (trace__filter_duration(trace, duration))
			goto out;
	} else if (trace->duration_filter)
		goto out;
1458

1459
	trace__fprintf_entry_head(trace, thread, duration, sample->time, trace->output);
1460 1461

	if (ttrace->entry_pending) {
1462
		fprintf(trace->output, "%-70s", ttrace->entry_str);
1463
	} else {
1464 1465 1466
		fprintf(trace->output, " ... [");
		color_fprintf(trace->output, PERF_COLOR_YELLOW, "continued");
		fprintf(trace->output, "]: %s()", sc->name);
1467 1468
	}

1469 1470 1471 1472
	if (sc->fmt == NULL) {
signed_print:
		fprintf(trace->output, ") = %d", ret);
	} else if (ret < 0 && sc->fmt->errmsg) {
1473 1474 1475 1476
		char bf[256];
		const char *emsg = strerror_r(-ret, bf, sizeof(bf)),
			   *e = audit_errno_to_name(-ret);

1477
		fprintf(trace->output, ") = -1 %s %s", e, emsg);
1478
	} else if (ret == 0 && sc->fmt->timeout)
1479
		fprintf(trace->output, ") = 0 Timeout");
1480 1481
	else if (sc->fmt->hexret)
		fprintf(trace->output, ") = %#x", ret);
1482
	else
1483
		goto signed_print;
1484

1485
	fputc('\n', trace->output);
1486
out:
1487 1488
	ttrace->entry_pending = false;

1489 1490 1491
	return 0;
}

1492 1493 1494 1495 1496
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;
1497
	struct thread *thread = machine__findnew_thread(trace->host,
1498 1499
							sample->pid,
							sample->tid);
1500
	struct thread_trace *ttrace = thread__trace(thread, trace->output);
1501 1502 1503 1504 1505 1506 1507 1508 1509

	if (ttrace == NULL)
		goto out_dump;

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

out_dump:
1510
	fprintf(trace->output, "%s: comm=%s,pid=%u,runtime=%" PRIu64 ",vruntime=%" PRIu64 ")\n",
1511 1512 1513 1514 1515 1516 1517 1518
	       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;
}

1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530
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;
}

1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541
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;

	tracepoint_handler handler = evsel->handler.func;

1542 1543 1544
	if (skip_sample(trace, sample))
		return 0;

1545
	if (!trace->full_time && trace->base_time == 0)
1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563
		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;
}

1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584
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
1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611
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);
}

1612 1613
static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);

1614
static int trace__run(struct trace *trace, int argc, const char **argv)
A
Arnaldo Carvalho de Melo 已提交
1615
{
1616
	struct perf_evlist *evlist = perf_evlist__new();
1617
	struct perf_evsel *evsel;
1618 1619
	int err = -1, i;
	unsigned long before;
1620
	const bool forks = argc > 0;
A
Arnaldo Carvalho de Melo 已提交
1621

1622 1623
	trace->live = true;

A
Arnaldo Carvalho de Melo 已提交
1624
	if (evlist == NULL) {
1625
		fprintf(trace->output, "Not enough memory to run!\n");
A
Arnaldo Carvalho de Melo 已提交
1626 1627 1628
		goto out;
	}

1629
	if (perf_evlist__add_newtp(evlist, "raw_syscalls", "sys_enter", trace__sys_enter) ||
1630 1631
		perf_evlist__add_newtp(evlist, "raw_syscalls", "sys_exit", trace__sys_exit))
		goto out_error_tp;
A
Arnaldo Carvalho de Melo 已提交
1632

1633
	if (trace->sched &&
1634 1635 1636
		perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
				trace__sched_stat_runtime))
		goto out_error_tp;
1637

A
Arnaldo Carvalho de Melo 已提交
1638 1639
	err = perf_evlist__create_maps(evlist, &trace->opts.target);
	if (err < 0) {
1640
		fprintf(trace->output, "Problems parsing the target to trace, check your options!\n");
A
Arnaldo Carvalho de Melo 已提交
1641 1642 1643
		goto out_delete_evlist;
	}

1644 1645
	err = trace__symbols_init(trace, evlist);
	if (err < 0) {
1646
		fprintf(trace->output, "Problems initializing symbol libraries!\n");
1647
		goto out_delete_maps;
1648 1649
	}

1650
	perf_evlist__config(evlist, &trace->opts);
A
Arnaldo Carvalho de Melo 已提交
1651

1652 1653 1654 1655
	signal(SIGCHLD, sig_handler);
	signal(SIGINT, sig_handler);

	if (forks) {
1656
		err = perf_evlist__prepare_workload(evlist, &trace->opts.target,
1657
						    argv, false, false);
1658
		if (err < 0) {
1659
			fprintf(trace->output, "Couldn't run the workload!\n");
1660
			goto out_delete_maps;
1661 1662 1663
		}
	}

A
Arnaldo Carvalho de Melo 已提交
1664 1665
	err = perf_evlist__open(evlist);
	if (err < 0) {
1666
		fprintf(trace->output, "Couldn't create the events: %s\n", strerror(errno));
1667
		goto out_delete_maps;
A
Arnaldo Carvalho de Melo 已提交
1668 1669 1670 1671
	}

	err = perf_evlist__mmap(evlist, UINT_MAX, false);
	if (err < 0) {
1672
		fprintf(trace->output, "Couldn't mmap the events: %s\n", strerror(errno));
1673
		goto out_close_evlist;
A
Arnaldo Carvalho de Melo 已提交
1674 1675 1676
	}

	perf_evlist__enable(evlist);
1677 1678 1679 1680

	if (forks)
		perf_evlist__start_workload(evlist);

1681
	trace->multiple_threads = evlist->threads->map[0] == -1 || evlist->threads->nr > 1;
A
Arnaldo Carvalho de Melo 已提交
1682
again:
1683
	before = trace->nr_events;
A
Arnaldo Carvalho de Melo 已提交
1684 1685 1686 1687 1688 1689

	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;
1690
			tracepoint_handler handler;
A
Arnaldo Carvalho de Melo 已提交
1691 1692
			struct perf_sample sample;

1693
			++trace->nr_events;
A
Arnaldo Carvalho de Melo 已提交
1694 1695 1696

			err = perf_evlist__parse_sample(evlist, event, &sample);
			if (err) {
1697
				fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err);
A
Arnaldo Carvalho de Melo 已提交
1698 1699 1700
				continue;
			}

1701
			if (!trace->full_time && trace->base_time == 0)
1702 1703 1704
				trace->base_time = sample.time;

			if (type != PERF_RECORD_SAMPLE) {
1705
				trace__process_event(trace, trace->host, event);
1706 1707 1708
				continue;
			}

A
Arnaldo Carvalho de Melo 已提交
1709 1710
			evsel = perf_evlist__id2evsel(evlist, sample.id);
			if (evsel == NULL) {
1711
				fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample.id);
A
Arnaldo Carvalho de Melo 已提交
1712 1713 1714
				continue;
			}

1715
			if (sample.raw_data == NULL) {
1716
				fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
1717 1718 1719 1720 1721
				       perf_evsel__name(evsel), sample.tid,
				       sample.cpu, sample.raw_size);
				continue;
			}

1722 1723
			handler = evsel->handler.func;
			handler(trace, evsel, &sample);
1724 1725 1726

			if (done)
				goto out_unmap_evlist;
A
Arnaldo Carvalho de Melo 已提交
1727 1728 1729
		}
	}

1730
	if (trace->nr_events == before) {
1731
		if (done)
1732
			goto out_unmap_evlist;
1733

A
Arnaldo Carvalho de Melo 已提交
1734
		poll(evlist->pollfd, evlist->nr_fds, -1);
1735 1736 1737 1738
	}

	if (done)
		perf_evlist__disable(evlist);
A
Arnaldo Carvalho de Melo 已提交
1739 1740 1741

	goto again;

1742
out_unmap_evlist:
1743 1744 1745
	if (!err && trace->summary)
		trace__fprintf_thread_summary(trace, trace->output);

1746 1747 1748 1749 1750
	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
1751 1752 1753
out_delete_evlist:
	perf_evlist__delete(evlist);
out:
1754
	trace->live = false;
A
Arnaldo Carvalho de Melo 已提交
1755
	return err;
1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778
out_error_tp:
	switch(errno) {
	case ENOENT:
		fputs("Error:\tUnable to find debugfs\n"
		      "Hint:\tWas your kernel was compiled with debugfs support?\n"
		      "Hint:\tIs the debugfs filesystem mounted?\n"
		      "Hint:\tTry 'sudo mount -t debugfs nodev /sys/kernel/debug'\n",
		      trace->output);
		break;
	case EACCES:
		fprintf(trace->output,
			"Error:\tNo permissions to read %s/tracing/events/raw_syscalls\n"
			"Hint:\tTry 'sudo mount -o remount,mode=755 %s'\n",
			debugfs_mountpoint, debugfs_mountpoint);
		break;
	default: {
		char bf[256];
		fprintf(trace->output, "Can't trace: %s\n",
			strerror_r(errno, bf, sizeof(bf)));
	}
		break;
	}
	goto out_delete_evlist;
A
Arnaldo Carvalho de Melo 已提交
1779 1780
}

1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792
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, },
	};

	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
1793
	trace->tool.mmap2	  = perf_event__process_mmap2;
1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814
	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;

	session = perf_session__new(input_name, O_RDONLY, 0, false,
				    &trace->tool);
	if (session == NULL)
		return -ENOMEM;

1815 1816
	trace->host = &session->machines.host;

1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830
	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;
	}

1831 1832 1833 1834
	err = parse_target_str(trace);
	if (err != 0)
		goto out;

1835 1836 1837 1838 1839 1840
	setup_pager();

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

1841 1842 1843
	else if (trace->summary)
		trace__fprintf_thread_summary(trace, trace->output);

1844 1845 1846 1847 1848 1849
out:
	perf_session__delete(session);

	return err;
}

1850 1851 1852 1853
static size_t trace__fprintf_threads_header(FILE *fp)
{
	size_t printed;

1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900
	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");
1901 1902 1903 1904

	return printed;
}

1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938
/* 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;

	printed += color_fprintf(fp, color, "%20s", thread->comm);
	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);
1939
	printed += thread__dump_stats(ttrace, trace, fp);
1940 1941 1942 1943 1944 1945

	data->printed += printed;

	return 0;
}

1946 1947
static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
{
1948 1949 1950 1951 1952
	struct summary_data data = {
		.fp = fp,
		.trace = trace
	};
	data.printed = trace__fprintf_threads_header(fp);
1953

1954 1955 1956
	machine__for_each_thread(trace->host, trace__fprintf_one_thread, &data);

	return data.printed;
1957 1958
}

1959 1960 1961 1962 1963 1964 1965 1966 1967
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;
}

1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984
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
1985 1986 1987
int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
{
	const char * const trace_usage[] = {
1988 1989
		"perf trace [<options>] [<command>]",
		"perf trace [<options>] -- <command> [<options>]",
D
David Ahern 已提交
1990 1991
		"perf trace record [<options>] [<command>]",
		"perf trace record [<options>] -- <command> [<options>]",
A
Arnaldo Carvalho de Melo 已提交
1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008
		NULL
	};
	struct trace trace = {
		.audit_machine = audit_detect_machine(),
		.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,
		},
2009
		.output = stdout,
2010
		.show_comm = true,
A
Arnaldo Carvalho de Melo 已提交
2011
	};
2012
	const char *output_name = NULL;
2013
	const char *ev_qualifier_str = NULL;
A
Arnaldo Carvalho de Melo 已提交
2014
	const struct option trace_options[] = {
2015 2016
	OPT_BOOLEAN(0, "comm", &trace.show_comm,
		    "show the thread COMM next to its id"),
2017 2018
	OPT_STRING('e', "expr", &ev_qualifier_str, "expr",
		    "list of events to trace"),
2019
	OPT_STRING('o', "output", &output_name, "file", "output file name"),
2020
	OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
A
Arnaldo Carvalho de Melo 已提交
2021 2022
	OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
		    "trace events on existing process id"),
2023
	OPT_STRING('t', "tid", &trace.opts.target.tid, "tid",
A
Arnaldo Carvalho de Melo 已提交
2024
		    "trace events on existing thread id"),
2025
	OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide,
A
Arnaldo Carvalho de Melo 已提交
2026
		    "system-wide collection from all CPUs"),
2027
	OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu",
A
Arnaldo Carvalho de Melo 已提交
2028
		    "list of cpus to monitor"),
2029
	OPT_BOOLEAN(0, "no-inherit", &trace.opts.no_inherit,
A
Arnaldo Carvalho de Melo 已提交
2030
		    "child tasks do not inherit counters"),
2031 2032 2033
	OPT_CALLBACK('m', "mmap-pages", &trace.opts.mmap_pages, "pages",
		     "number of mmap data pages",
		     perf_evlist__parse_mmap_pages),
2034
	OPT_STRING('u', "uid", &trace.opts.target.uid_str, "user",
A
Arnaldo Carvalho de Melo 已提交
2035
		   "user to profile"),
2036 2037 2038
	OPT_CALLBACK(0, "duration", &trace, "float",
		     "show only events with duration > N.M ms",
		     trace__set_duration),
2039
	OPT_BOOLEAN(0, "sched", &trace.sched, "show blocking scheduler events"),
2040
	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
2041 2042
	OPT_BOOLEAN('T', "time", &trace.full_time,
		    "Show full timestamp, not time relative to first start"),
2043 2044
	OPT_BOOLEAN(0, "summary", &trace.summary,
		    "Show syscall summary with statistics"),
A
Arnaldo Carvalho de Melo 已提交
2045 2046 2047
	OPT_END()
	};
	int err;
2048
	char bf[BUFSIZ];
A
Arnaldo Carvalho de Melo 已提交
2049

D
David Ahern 已提交
2050 2051 2052
	if ((argc > 1) && (strcmp(argv[1], "record") == 0))
		return trace__record(argc-2, &argv[2]);

A
Arnaldo Carvalho de Melo 已提交
2053 2054
	argc = parse_options(argc, argv, trace_options, trace_usage, 0);

2055 2056 2057 2058 2059 2060 2061 2062
	if (output_name != NULL) {
		err = trace__open_output(&trace, output_name);
		if (err < 0) {
			perror("failed to create output file");
			goto out;
		}
	}

2063
	if (ev_qualifier_str != NULL) {
2064 2065 2066 2067 2068 2069
		const char *s = ev_qualifier_str;

		trace.not_ev_qualifier = *s == '!';
		if (trace.not_ev_qualifier)
			++s;
		trace.ev_qualifier = strlist__new(true, s);
2070
		if (trace.ev_qualifier == NULL) {
2071 2072 2073 2074
			fputs("Not enough memory to parse event qualifier",
			      trace.output);
			err = -ENOMEM;
			goto out_close;
2075 2076 2077
		}
	}

2078 2079 2080
	err = perf_target__validate(&trace.opts.target);
	if (err) {
		perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf));
2081 2082
		fprintf(trace.output, "%s", bf);
		goto out_close;
2083 2084
	}

A
Arnaldo Carvalho de Melo 已提交
2085 2086 2087
	err = perf_target__parse_uid(&trace.opts.target);
	if (err) {
		perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf));
2088 2089
		fprintf(trace.output, "%s", bf);
		goto out_close;
A
Arnaldo Carvalho de Melo 已提交
2090 2091
	}

2092
	if (!argc && perf_target__none(&trace.opts.target))
2093 2094
		trace.opts.target.system_wide = true;

2095 2096 2097 2098
	if (input_name)
		err = trace__replay(&trace);
	else
		err = trace__run(&trace, argc, argv);
2099

2100 2101 2102 2103
out_close:
	if (output_name != NULL)
		fclose(trace.output);
out:
2104
	return err;
A
Arnaldo Carvalho de Melo 已提交
2105
}