builtin-trace.c 38.2 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 13 14 15
#include "util/thread_map.h"

#include <libaudit.h>
#include <stdlib.h>
16
#include <sys/mman.h>
17
#include <linux/futex.h>
A
Arnaldo Carvalho de Melo 已提交
18

19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35
/* 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

36 37
struct syscall_arg {
	unsigned long val;
38
	void	      *parm;
39 40 41 42
	u8	      idx;
	u8	      mask;
};

43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66
struct strarray {
	int	    nr_entries;
	const char **entries;
};

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

static size_t syscall_arg__scnprintf_strarray(char *bf, size_t size,
					      struct syscall_arg *arg)
{
	int idx = arg->val;
	struct strarray *sa = arg->parm;

	if (idx < 0 || idx >= sa->nr_entries)
		return scnprintf(bf, size, "%d", idx);

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

#define SCA_STRARRAY syscall_arg__scnprintf_strarray

67
static size_t syscall_arg__scnprintf_hex(char *bf, size_t size,
68
					 struct syscall_arg *arg)
69
{
70
	return scnprintf(bf, size, "%#lx", arg->val);
71 72
}

73 74
#define SCA_HEX syscall_arg__scnprintf_hex

75
static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
76
					       struct syscall_arg *arg)
77
{
78
	int printed = 0, prot = arg->val;
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

	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

106
static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
107
						struct syscall_arg *arg)
108
{
109
	int printed = 0, flags = arg->val;
110 111 112 113 114 115 116 117 118

#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);
119
#ifdef MAP_32BIT
120
	P_MMAP_FLAG(32BIT);
121
#endif
122 123 124 125 126 127
	P_MMAP_FLAG(ANONYMOUS);
	P_MMAP_FLAG(DENYWRITE);
	P_MMAP_FLAG(EXECUTABLE);
	P_MMAP_FLAG(FILE);
	P_MMAP_FLAG(FIXED);
	P_MMAP_FLAG(GROWSDOWN);
128
#ifdef MAP_HUGETLB
129
	P_MMAP_FLAG(HUGETLB);
130
#endif
131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148
	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

149
static size_t syscall_arg__scnprintf_madvise_behavior(char *bf, size_t size,
150
						      struct syscall_arg *arg)
151
{
152
	int behavior = arg->val;
153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169

	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);
170
#ifdef MADV_HUGEPAGE
171
	P_MADV_BHV(HUGEPAGE);
172 173
#endif
#ifdef MADV_NOHUGEPAGE
174
	P_MADV_BHV(NOHUGEPAGE);
175
#endif
176 177 178 179 180 181 182 183 184 185 186 187 188 189 190
#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

191
static size_t syscall_arg__scnprintf_futex_op(char *bf, size_t size, struct syscall_arg *arg)
192 193 194 195 196 197 198 199 200
{
	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),
	};
201
	int op = arg->val;
202 203 204 205 206
	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);
207 208 209 210 211 212
	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;
213
	P_FUTEX_OP(WAKE_OP);							  break;
214 215 216 217 218
	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;
219 220 221 222 223 224 225 226 227 228 229 230 231
	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;
}

232 233
#define SCA_FUTEX_OP  syscall_arg__scnprintf_futex_op

234 235 236
static const char *itimers[] = { "REAL", "VIRTUAL", "PROF", };
static DEFINE_STRARRAY(itimers);

237 238 239 240 241 242 243 244 245
static const char *whences[] = { "SET", "CUR", "END",
#ifdef SEEK_DATA
"DATA",
#endif
#ifdef SEEK_HOLE
"HOLE",
#endif
};
static DEFINE_STRARRAY(whences);
246

247 248 249 250 251 252 253 254
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);

255 256 257
static const char *sighow[] = { "BLOCK", "UNBLOCK", "SETMASK", };
static DEFINE_STRARRAY(sighow);

258 259 260 261 262 263 264 265 266 267
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);

268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314
#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

315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341
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

342
static size_t syscall_arg__scnprintf_open_flags(char *bf, size_t size,
343
					       struct syscall_arg *arg)
344
{
345
	int printed = 0, flags = arg->val;
346 347

	if (!(flags & O_CREAT))
348
		arg->mask |= 1 << (arg->idx + 1); /* Mask the mode parm */
349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397

	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

398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442
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

A
Arnaldo Carvalho de Melo 已提交
443 444
static struct syscall_fmt {
	const char *name;
445
	const char *alias;
446
	size_t	   (*arg_scnprintf[6])(char *bf, size_t size, struct syscall_arg *arg);
447
	void	   *arg_parm[6];
A
Arnaldo Carvalho de Melo 已提交
448 449
	bool	   errmsg;
	bool	   timeout;
450
	bool	   hexret;
A
Arnaldo Carvalho de Melo 已提交
451
} syscall_fmts[] = {
452 453
	{ .name	    = "access",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_ACCMODE, /* mode */ }, },
454
	{ .name	    = "arch_prctl", .errmsg = true, .alias = "prctl", },
455 456
	{ .name	    = "brk",	    .hexret = true,
	  .arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, },
457
	{ .name	    = "mmap",	    .hexret = true, },
458
	{ .name	    = "connect",    .errmsg = true, },
459 460 461
	{ .name	    = "fcntl",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_STRARRAY, /* cmd */ },
	  .arg_parm	 = { [1] = &strarray__fcntl_cmds, /* cmd */ }, },
462 463
	{ .name	    = "fstat",	    .errmsg = true, .alias = "newfstat", },
	{ .name	    = "fstatat",    .errmsg = true, .alias = "newfstatat", },
464 465
	{ .name	    = "futex",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, },
466 467 468
	{ .name	    = "getitimer",  .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_STRARRAY, /* which */ },
	  .arg_parm	 = { [0] = &strarray__itimers, /* which */ }, },
469 470
	{ .name	    = "ioctl",	    .errmsg = true,
	  .arg_scnprintf = { [2] = SCA_HEX, /* arg */ }, },
471 472
	{ .name	    = "kill",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
473
	{ .name	    = "lseek",	    .errmsg = true,
474 475
	  .arg_scnprintf = { [2] = SCA_STRARRAY, /* whence */ },
	  .arg_parm	 = { [2] = &strarray__whences, /* whence */ }, },
476
	{ .name	    = "lstat",	    .errmsg = true, .alias = "newlstat", },
477 478 479
	{ .name     = "madvise",    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_HEX,	 /* start */
			     [2] = SCA_MADV_BHV, /* behavior */ }, },
480
	{ .name	    = "mmap",	    .hexret = true,
481
	  .arg_scnprintf = { [0] = SCA_HEX,	  /* addr */
482 483
			     [2] = SCA_MMAP_PROT, /* prot */
			     [3] = SCA_MMAP_FLAGS, /* flags */ }, },
484
	{ .name	    = "mprotect",   .errmsg = true,
485 486 487 488 489
	  .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 */ }, },
490 491
	{ .name	    = "munmap",	    .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
492 493
	{ .name	    = "open",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, },
494 495 496 497
	{ .name	    = "open_by_handle_at", .errmsg = true,
	  .arg_scnprintf = { [2] = SCA_OPEN_FLAGS, /* flags */ }, },
	{ .name	    = "openat",	    .errmsg = true,
	  .arg_scnprintf = { [2] = SCA_OPEN_FLAGS, /* flags */ }, },
498 499
	{ .name	    = "poll",	    .errmsg = true, .timeout = true, },
	{ .name	    = "ppoll",	    .errmsg = true, .timeout = true, },
500 501
	{ .name	    = "pread",	    .errmsg = true, .alias = "pread64", },
	{ .name	    = "pwrite",	    .errmsg = true, .alias = "pwrite64", },
502 503
	{ .name	    = "read",	    .errmsg = true, },
	{ .name	    = "recvfrom",   .errmsg = true, },
504 505
	{ .name	    = "rt_sigaction", .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, },
506 507 508
	{ .name	    = "rt_sigprocmask", .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_STRARRAY, /* how */ },
	  .arg_parm	 = { [0] = &strarray__sighow, /* how */ }, },
509 510 511 512
	{ .name	    = "rt_sigqueueinfo", .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
	{ .name	    = "rt_tgsigqueueinfo", .errmsg = true,
	  .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
513
	{ .name	    = "select",	    .errmsg = true, .timeout = true, },
514 515 516
	{ .name	    = "setitimer",  .errmsg = true,
	  .arg_scnprintf = { [0] = SCA_STRARRAY, /* which */ },
	  .arg_parm	 = { [0] = &strarray__itimers, /* which */ }, },
517
	{ .name	    = "socket",	    .errmsg = true,
518 519
	  .arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
			     [1] = SCA_SK_TYPE, /* type */ },
520
	  .arg_parm	 = { [0] = &strarray__socket_families, /* family */ }, },
521
	{ .name	    = "stat",	    .errmsg = true, .alias = "newstat", },
522 523 524 525
	{ .name	    = "tgkill",	    .errmsg = true,
	  .arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
	{ .name	    = "tkill",	    .errmsg = true,
	  .arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
526
	{ .name	    = "uname",	    .errmsg = true, .alias = "newuname", },
A
Arnaldo Carvalho de Melo 已提交
527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543
};

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;
544
	bool		    filtered;
A
Arnaldo Carvalho de Melo 已提交
545
	struct syscall_fmt  *fmt;
546
	size_t		    (**arg_scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
547
	void		    **arg_parm;
A
Arnaldo Carvalho de Melo 已提交
548 549
};

550 551 552 553 554 555 556 557 558 559 560
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);
561
	return printed + fprintf(fp, "): ");
562 563
}

564 565 566 567
struct thread_trace {
	u64		  entry_time;
	u64		  exit_time;
	bool		  entry_pending;
568
	unsigned long	  nr_events;
569
	char		  *entry_str;
570
	double		  runtime_ms;
571 572 573 574 575 576 577
};

static struct thread_trace *thread_trace__new(void)
{
	return zalloc(sizeof(struct thread_trace));
}

578
static struct thread_trace *thread__trace(struct thread *thread, FILE *fp)
579
{
580 581
	struct thread_trace *ttrace;

582 583 584 585 586
	if (thread == NULL)
		goto fail;

	if (thread->priv == NULL)
		thread->priv = thread_trace__new();
587
		
588 589 590
	if (thread->priv == NULL)
		goto fail;

591 592 593 594
	ttrace = thread->priv;
	++ttrace->nr_events;

	return ttrace;
595
fail:
596
	color_fprintf(fp, PERF_COLOR_RED,
597 598 599 600
		      "WARNING: not enough memory, dropping samples!\n");
	return NULL;
}

A
Arnaldo Carvalho de Melo 已提交
601
struct trace {
602
	struct perf_tool	tool;
A
Arnaldo Carvalho de Melo 已提交
603 604 605 606 607 608
	int			audit_machine;
	struct {
		int		max;
		struct syscall  *table;
	} syscalls;
	struct perf_record_opts opts;
609 610
	struct machine		host;
	u64			base_time;
611
	FILE			*output;
612
	unsigned long		nr_events;
613 614
	struct strlist		*ev_qualifier;
	bool			not_ev_qualifier;
615 616
	struct intlist		*tid_list;
	struct intlist		*pid_list;
617
	bool			sched;
618
	bool			multiple_threads;
619
	double			duration_filter;
620
	double			runtime_ms;
A
Arnaldo Carvalho de Melo 已提交
621 622
};

623 624 625 626 627
static bool trace__filter_duration(struct trace *trace, double t)
{
	return t < (trace->duration_filter * NSEC_PER_MSEC);
}

628 629 630 631
static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
{
	double ts = (double)(tstamp - trace->base_time) / NSEC_PER_MSEC;

632
	return fprintf(fp, "%10.3f ", ts);
633 634
}

635 636 637 638 639 640 641
static bool done = false;

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

642
static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
643
					u64 duration, u64 tstamp, FILE *fp)
644 645
{
	size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
646
	printed += fprintf_duration(duration, fp);
647 648

	if (trace->multiple_threads)
649
		printed += fprintf(fp, "%d ", thread->tid);
650 651 652 653

	return printed;
}

654 655
static int trace__process_event(struct trace *trace, struct machine *machine,
				union perf_event *event)
656 657 658 659 660
{
	int ret = 0;

	switch (event->header.type) {
	case PERF_RECORD_LOST:
661
		color_fprintf(trace->output, PERF_COLOR_RED,
662 663 664 665 666 667 668 669 670 671
			      "LOST %" PRIu64 " events!\n", event->lost.lost);
		ret = machine__process_lost_event(machine, event);
	default:
		ret = machine__process_event(machine, event);
		break;
	}

	return ret;
}

672
static int trace__tool_process(struct perf_tool *tool,
673 674 675 676
			       union perf_event *event,
			       struct perf_sample *sample __maybe_unused,
			       struct machine *machine)
{
677 678
	struct trace *trace = container_of(tool, struct trace, tool);
	return trace__process_event(trace, machine, event);
679 680 681 682 683 684 685 686 687 688 689 690 691
}

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

	if (err)
		return err;

	machine__init(&trace->host, "", HOST_KERNEL_ID);
	machine__create_kernel_maps(&trace->host);

	if (perf_target__has_task(&trace->opts.target)) {
692
		err = perf_event__synthesize_thread_map(&trace->tool, evlist->threads,
693 694 695
							trace__tool_process,
							&trace->host);
	} else {
696
		err = perf_event__synthesize_threads(&trace->tool, trace__tool_process,
697 698 699 700 701 702 703 704 705
						     &trace->host);
	}

	if (err)
		symbol__exit();

	return err;
}

706 707 708 709 710 711 712 713 714
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;

715 716 717
	if (sc->fmt)
		sc->arg_parm = sc->fmt->arg_parm;

718
	for (field = sc->tp_format->format.fields->next; field; field = field->next) {
719 720 721
		if (sc->fmt && sc->fmt->arg_scnprintf[idx])
			sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx];
		else if (field->flags & FIELD_IS_POINTER)
722 723 724 725 726 727 728
			sc->arg_scnprintf[idx] = syscall_arg__scnprintf_hex;
		++idx;
	}

	return 0;
}

A
Arnaldo Carvalho de Melo 已提交
729 730 731 732
static int trace__read_syscall_info(struct trace *trace, int id)
{
	char tp_name[128];
	struct syscall *sc;
733 734 735 736
	const char *name = audit_syscall_to_name(id, trace->audit_machine);

	if (name == NULL)
		return -1;
A
Arnaldo Carvalho de Melo 已提交
737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755

	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;
756
	sc->name = name;
757

758 759 760 761 762 763 764 765 766 767 768
	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;
		}
769 770
	}

771
	sc->fmt  = syscall_fmt__find(sc->name);
A
Arnaldo Carvalho de Melo 已提交
772

773
	snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->name);
A
Arnaldo Carvalho de Melo 已提交
774
	sc->tp_format = event_format__new("syscalls", tp_name);
775 776 777 778 779

	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
780

781 782 783 784
	if (sc->tp_format == NULL)
		return -1;

	return syscall__set_arg_fmts(sc);
A
Arnaldo Carvalho de Melo 已提交
785 786
}

787 788
static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
				      unsigned long *args)
A
Arnaldo Carvalho de Melo 已提交
789 790 791 792 793
{
	size_t printed = 0;

	if (sc->tp_format != NULL) {
		struct format_field *field;
794 795 796 797 798
		u8 bit = 1;
		struct syscall_arg arg = {
			.idx  = 0,
			.mask = 0,
		};
799 800

		for (field = sc->tp_format->format.fields->next; field;
801 802
		     field = field->next, ++arg.idx, bit <<= 1) {
			if (arg.mask & bit)
803
				continue;
A
Arnaldo Carvalho de Melo 已提交
804

805
			printed += scnprintf(bf + printed, size - printed,
806
					     "%s%s: ", printed ? ", " : "", field->name);
807 808
			if (sc->arg_scnprintf && sc->arg_scnprintf[arg.idx]) {
				arg.val = args[arg.idx];
809 810
				if (sc->arg_parm)
					arg.parm = sc->arg_parm[arg.idx];
811 812
				printed += sc->arg_scnprintf[arg.idx](bf + printed,
								      size - printed, &arg);
813
			} else {
814
				printed += scnprintf(bf + printed, size - printed,
815
						     "%ld", args[arg.idx]);
816
			}
A
Arnaldo Carvalho de Melo 已提交
817 818
		}
	} else {
819 820
		int i = 0;

A
Arnaldo Carvalho de Melo 已提交
821
		while (i < 6) {
822 823 824
			printed += scnprintf(bf + printed, size - printed,
					     "%sarg%d: %ld",
					     printed ? ", " : "", i, args[i]);
A
Arnaldo Carvalho de Melo 已提交
825 826 827 828 829 830 831
			++i;
		}
	}

	return printed;
}

832 833 834 835 836 837 838 839 840 841
typedef int (*tracepoint_handler)(struct trace *trace, struct perf_evsel *evsel,
				  struct perf_sample *sample);

static struct syscall *trace__syscall_info(struct trace *trace,
					   struct perf_evsel *evsel,
					   struct perf_sample *sample)
{
	int id = perf_evsel__intval(evsel, sample, "id");

	if (id < 0) {
842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857

		/*
		 * 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);
		}
858 859 860 861 862 863 864 865 866 867 868 869 870
		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:
871 872 873 874 875 876
	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);
	}
877 878 879 880 881 882
	return NULL;
}

static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
			    struct perf_sample *sample)
{
883
	char *msg;
884
	void *args;
885
	size_t printed = 0;
886
	struct thread *thread;
887
	struct syscall *sc = trace__syscall_info(trace, evsel, sample);
888 889 890 891
	struct thread_trace *ttrace;

	if (sc == NULL)
		return -1;
892

893 894 895
	if (sc->filtered)
		return 0;

896 897
	thread = machine__findnew_thread(&trace->host, sample->pid,
					 sample->tid);
898
	ttrace = thread__trace(thread, trace->output);
899
	if (ttrace == NULL)
900 901 902 903
		return -1;

	args = perf_evsel__rawptr(evsel, sample, "args");
	if (args == NULL) {
904
		fprintf(trace->output, "Problems reading syscall arguments\n");
905 906 907
		return -1;
	}

908 909 910 911 912 913 914 915 916 917 918 919 920 921 922
	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);

	printed += syscall__scnprintf_args(sc, msg + printed, 1024 - printed,  args);

	if (!strcmp(sc->name, "exit_group") || !strcmp(sc->name, "exit")) {
923
		if (!trace->duration_filter) {
924 925
			trace__fprintf_entry_head(trace, thread, 1, sample->time, trace->output);
			fprintf(trace->output, "%-70s\n", ttrace->entry_str);
926
		}
927 928
	} else
		ttrace->entry_pending = true;
929 930 931 932 933 934 935 936

	return 0;
}

static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
			   struct perf_sample *sample)
{
	int ret;
937
	u64 duration = 0;
938
	struct thread *thread;
939
	struct syscall *sc = trace__syscall_info(trace, evsel, sample);
940 941 942 943
	struct thread_trace *ttrace;

	if (sc == NULL)
		return -1;
944

945 946 947
	if (sc->filtered)
		return 0;

948 949
	thread = machine__findnew_thread(&trace->host, sample->pid,
					 sample->tid);
950
	ttrace = thread__trace(thread, trace->output);
951
	if (ttrace == NULL)
952 953 954 955
		return -1;

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

956 957 958 959
	ttrace = thread->priv;

	ttrace->exit_time = sample->time;

960
	if (ttrace->entry_time) {
961
		duration = sample->time - ttrace->entry_time;
962 963 964 965
		if (trace__filter_duration(trace, duration))
			goto out;
	} else if (trace->duration_filter)
		goto out;
966

967
	trace__fprintf_entry_head(trace, thread, duration, sample->time, trace->output);
968 969

	if (ttrace->entry_pending) {
970
		fprintf(trace->output, "%-70s", ttrace->entry_str);
971
	} else {
972 973 974
		fprintf(trace->output, " ... [");
		color_fprintf(trace->output, PERF_COLOR_YELLOW, "continued");
		fprintf(trace->output, "]: %s()", sc->name);
975 976
	}

977 978 979 980
	if (sc->fmt == NULL) {
signed_print:
		fprintf(trace->output, ") = %d", ret);
	} else if (ret < 0 && sc->fmt->errmsg) {
981 982 983 984
		char bf[256];
		const char *emsg = strerror_r(-ret, bf, sizeof(bf)),
			   *e = audit_errno_to_name(-ret);

985
		fprintf(trace->output, ") = -1 %s %s", e, emsg);
986
	} else if (ret == 0 && sc->fmt->timeout)
987
		fprintf(trace->output, ") = 0 Timeout");
988 989
	else if (sc->fmt->hexret)
		fprintf(trace->output, ") = %#x", ret);
990
	else
991
		goto signed_print;
992

993
	fputc('\n', trace->output);
994
out:
995 996
	ttrace->entry_pending = false;

997 998 999
	return 0;
}

1000 1001 1002 1003 1004
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;
1005 1006 1007
	struct thread *thread = machine__findnew_thread(&trace->host,
							sample->pid,
							sample->tid);
1008
	struct thread_trace *ttrace = thread__trace(thread, trace->output);
1009 1010 1011 1012 1013 1014 1015 1016 1017

	if (ttrace == NULL)
		goto out_dump;

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

out_dump:
1018
	fprintf(trace->output, "%s: comm=%s,pid=%u,runtime=%" PRIu64 ",vruntime=%" PRIu64 ")\n",
1019 1020 1021 1022 1023 1024 1025 1026
	       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;
}

1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038
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;
}

1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049
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;

1050 1051 1052
	if (skip_sample(trace, sample))
		return 0;

1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071
	if (trace->base_time == 0)
		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;
}

1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092
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;
}

1093
static int trace__run(struct trace *trace, int argc, const char **argv)
A
Arnaldo Carvalho de Melo 已提交
1094
{
1095
	struct perf_evlist *evlist = perf_evlist__new();
1096
	struct perf_evsel *evsel;
1097 1098
	int err = -1, i;
	unsigned long before;
1099
	const bool forks = argc > 0;
A
Arnaldo Carvalho de Melo 已提交
1100 1101

	if (evlist == NULL) {
1102
		fprintf(trace->output, "Not enough memory to run!\n");
A
Arnaldo Carvalho de Melo 已提交
1103 1104 1105
		goto out;
	}

1106 1107
	if (perf_evlist__add_newtp(evlist, "raw_syscalls", "sys_enter", trace__sys_enter) ||
	    perf_evlist__add_newtp(evlist, "raw_syscalls", "sys_exit", trace__sys_exit)) {
1108
		fprintf(trace->output, "Couldn't read the raw_syscalls tracepoints information!\n");
A
Arnaldo Carvalho de Melo 已提交
1109 1110 1111
		goto out_delete_evlist;
	}

1112 1113 1114
	if (trace->sched &&
	    perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
				   trace__sched_stat_runtime)) {
1115
		fprintf(trace->output, "Couldn't read the sched_stat_runtime tracepoint information!\n");
1116 1117 1118
		goto out_delete_evlist;
	}

A
Arnaldo Carvalho de Melo 已提交
1119 1120
	err = perf_evlist__create_maps(evlist, &trace->opts.target);
	if (err < 0) {
1121
		fprintf(trace->output, "Problems parsing the target to trace, check your options!\n");
A
Arnaldo Carvalho de Melo 已提交
1122 1123 1124
		goto out_delete_evlist;
	}

1125 1126
	err = trace__symbols_init(trace, evlist);
	if (err < 0) {
1127
		fprintf(trace->output, "Problems initializing symbol libraries!\n");
1128
		goto out_delete_maps;
1129 1130
	}

1131
	perf_evlist__config(evlist, &trace->opts);
A
Arnaldo Carvalho de Melo 已提交
1132

1133 1134 1135 1136
	signal(SIGCHLD, sig_handler);
	signal(SIGINT, sig_handler);

	if (forks) {
1137
		err = perf_evlist__prepare_workload(evlist, &trace->opts.target,
1138
						    argv, false, false);
1139
		if (err < 0) {
1140
			fprintf(trace->output, "Couldn't run the workload!\n");
1141
			goto out_delete_maps;
1142 1143 1144
		}
	}

A
Arnaldo Carvalho de Melo 已提交
1145 1146
	err = perf_evlist__open(evlist);
	if (err < 0) {
1147
		fprintf(trace->output, "Couldn't create the events: %s\n", strerror(errno));
1148
		goto out_delete_maps;
A
Arnaldo Carvalho de Melo 已提交
1149 1150 1151 1152
	}

	err = perf_evlist__mmap(evlist, UINT_MAX, false);
	if (err < 0) {
1153
		fprintf(trace->output, "Couldn't mmap the events: %s\n", strerror(errno));
1154
		goto out_close_evlist;
A
Arnaldo Carvalho de Melo 已提交
1155 1156 1157
	}

	perf_evlist__enable(evlist);
1158 1159 1160 1161

	if (forks)
		perf_evlist__start_workload(evlist);

1162
	trace->multiple_threads = evlist->threads->map[0] == -1 || evlist->threads->nr > 1;
A
Arnaldo Carvalho de Melo 已提交
1163
again:
1164
	before = trace->nr_events;
A
Arnaldo Carvalho de Melo 已提交
1165 1166 1167 1168 1169 1170

	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;
1171
			tracepoint_handler handler;
A
Arnaldo Carvalho de Melo 已提交
1172 1173
			struct perf_sample sample;

1174
			++trace->nr_events;
A
Arnaldo Carvalho de Melo 已提交
1175 1176 1177

			err = perf_evlist__parse_sample(evlist, event, &sample);
			if (err) {
1178
				fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err);
A
Arnaldo Carvalho de Melo 已提交
1179 1180 1181
				continue;
			}

1182 1183 1184 1185
			if (trace->base_time == 0)
				trace->base_time = sample.time;

			if (type != PERF_RECORD_SAMPLE) {
1186
				trace__process_event(trace, &trace->host, event);
1187 1188 1189
				continue;
			}

A
Arnaldo Carvalho de Melo 已提交
1190 1191
			evsel = perf_evlist__id2evsel(evlist, sample.id);
			if (evsel == NULL) {
1192
				fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample.id);
A
Arnaldo Carvalho de Melo 已提交
1193 1194 1195
				continue;
			}

1196
			if (sample.raw_data == NULL) {
1197
				fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
1198 1199 1200 1201 1202
				       perf_evsel__name(evsel), sample.tid,
				       sample.cpu, sample.raw_size);
				continue;
			}

1203 1204
			handler = evsel->handler.func;
			handler(trace, evsel, &sample);
1205 1206 1207

			if (done)
				goto out_unmap_evlist;
A
Arnaldo Carvalho de Melo 已提交
1208 1209 1210
		}
	}

1211
	if (trace->nr_events == before) {
1212
		if (done)
1213
			goto out_unmap_evlist;
1214

A
Arnaldo Carvalho de Melo 已提交
1215
		poll(evlist->pollfd, evlist->nr_fds, -1);
1216 1217 1218 1219
	}

	if (done)
		perf_evlist__disable(evlist);
A
Arnaldo Carvalho de Melo 已提交
1220 1221 1222

	goto again;

1223 1224 1225 1226 1227 1228
out_unmap_evlist:
	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
1229 1230 1231 1232 1233 1234
out_delete_evlist:
	perf_evlist__delete(evlist);
out:
	return err;
}

1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246
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
1247
	trace->tool.mmap2	  = perf_event__process_mmap2;
1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282
	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;

	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;
	}

1283 1284 1285 1286
	err = parse_target_str(trace);
	if (err != 0)
		goto out;

1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298
	setup_pager();

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

out:
	perf_session__delete(session);

	return err;
}

1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335
static size_t trace__fprintf_threads_header(FILE *fp)
{
	size_t printed;

	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," _____________________________________________________________________\n\n");

	return printed;
}

static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
{
	size_t printed = trace__fprintf_threads_header(fp);
	struct rb_node *nd;

	for (nd = rb_first(&trace->host.threads); nd; nd = rb_next(nd)) {
		struct thread *thread = rb_entry(nd, struct thread, rb_node);
		struct thread_trace *ttrace = thread->priv;
		const char *color;
		double ratio;

		if (ttrace == NULL)
			continue;

		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);
1336
		printed += fprintf(fp, " - %-5d :%11lu   [", thread->tid, ttrace->nr_events);
1337 1338 1339 1340 1341 1342 1343
		printed += color_fprintf(fp, color, "%5.1f%%", ratio);
		printed += fprintf(fp, " ] %10.3f ms\n", ttrace->runtime_ms);
	}

	return printed;
}

1344 1345 1346 1347 1348 1349 1350 1351 1352
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;
}

1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369
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
1370 1371 1372
int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
{
	const char * const trace_usage[] = {
1373 1374
		"perf trace [<options>] [<command>]",
		"perf trace [<options>] -- <command> [<options>]",
A
Arnaldo Carvalho de Melo 已提交
1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391
		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,
		},
1392
		.output = stdout,
A
Arnaldo Carvalho de Melo 已提交
1393
	};
1394
	const char *output_name = NULL;
1395
	const char *ev_qualifier_str = NULL;
A
Arnaldo Carvalho de Melo 已提交
1396
	const struct option trace_options[] = {
1397 1398
	OPT_STRING('e', "expr", &ev_qualifier_str, "expr",
		    "list of events to trace"),
1399
	OPT_STRING('o', "output", &output_name, "file", "output file name"),
1400
	OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
A
Arnaldo Carvalho de Melo 已提交
1401 1402
	OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
		    "trace events on existing process id"),
1403
	OPT_STRING('t', "tid", &trace.opts.target.tid, "tid",
A
Arnaldo Carvalho de Melo 已提交
1404
		    "trace events on existing thread id"),
1405
	OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide,
A
Arnaldo Carvalho de Melo 已提交
1406
		    "system-wide collection from all CPUs"),
1407
	OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu",
A
Arnaldo Carvalho de Melo 已提交
1408
		    "list of cpus to monitor"),
1409
	OPT_BOOLEAN(0, "no-inherit", &trace.opts.no_inherit,
A
Arnaldo Carvalho de Melo 已提交
1410
		    "child tasks do not inherit counters"),
1411
	OPT_UINTEGER('m', "mmap-pages", &trace.opts.mmap_pages,
A
Arnaldo Carvalho de Melo 已提交
1412
		     "number of mmap data pages"),
1413
	OPT_STRING('u', "uid", &trace.opts.target.uid_str, "user",
A
Arnaldo Carvalho de Melo 已提交
1414
		   "user to profile"),
1415 1416 1417
	OPT_CALLBACK(0, "duration", &trace, "float",
		     "show only events with duration > N.M ms",
		     trace__set_duration),
1418
	OPT_BOOLEAN(0, "sched", &trace.sched, "show blocking scheduler events"),
1419
	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
A
Arnaldo Carvalho de Melo 已提交
1420 1421 1422
	OPT_END()
	};
	int err;
1423
	char bf[BUFSIZ];
A
Arnaldo Carvalho de Melo 已提交
1424 1425 1426

	argc = parse_options(argc, argv, trace_options, trace_usage, 0);

1427 1428 1429 1430 1431 1432 1433 1434
	if (output_name != NULL) {
		err = trace__open_output(&trace, output_name);
		if (err < 0) {
			perror("failed to create output file");
			goto out;
		}
	}

1435
	if (ev_qualifier_str != NULL) {
1436 1437 1438 1439 1440 1441
		const char *s = ev_qualifier_str;

		trace.not_ev_qualifier = *s == '!';
		if (trace.not_ev_qualifier)
			++s;
		trace.ev_qualifier = strlist__new(true, s);
1442
		if (trace.ev_qualifier == NULL) {
1443 1444 1445 1446
			fputs("Not enough memory to parse event qualifier",
			      trace.output);
			err = -ENOMEM;
			goto out_close;
1447 1448 1449
		}
	}

1450 1451 1452
	err = perf_target__validate(&trace.opts.target);
	if (err) {
		perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf));
1453 1454
		fprintf(trace.output, "%s", bf);
		goto out_close;
1455 1456
	}

A
Arnaldo Carvalho de Melo 已提交
1457 1458 1459
	err = perf_target__parse_uid(&trace.opts.target);
	if (err) {
		perf_target__strerror(&trace.opts.target, err, bf, sizeof(bf));
1460 1461
		fprintf(trace.output, "%s", bf);
		goto out_close;
A
Arnaldo Carvalho de Melo 已提交
1462 1463
	}

1464
	if (!argc && perf_target__none(&trace.opts.target))
1465 1466
		trace.opts.target.system_wide = true;

1467 1468 1469 1470
	if (input_name)
		err = trace__replay(&trace);
	else
		err = trace__run(&trace, argc, argv);
1471 1472

	if (trace.sched && !err)
1473
		trace__fprintf_thread_summary(&trace, trace.output);
1474

1475 1476 1477 1478
out_close:
	if (output_name != NULL)
		fclose(trace.output);
out:
1479
	return err;
A
Arnaldo Carvalho de Melo 已提交
1480
}