builtin-record.c 10.1 KB
Newer Older
1 2


3
#include "perf.h"
4
#include "builtin.h"
5
#include "util/util.h"
6
#include "util/parse-options.h"
7
#include "util/parse-events.h"
8

9 10
#include <sched.h>

11 12
#define ALIGN(x, a)		__ALIGN_MASK(x, (typeof(x))(a)-1)
#define __ALIGN_MASK(x, mask)	(((x)+(mask))&~(mask))
13

14 15
static int			default_interval = 100000;
static int			event_count[MAX_COUNTERS];
16

17 18 19 20 21
static int			fd[MAX_NR_CPUS][MAX_COUNTERS];
static int			nr_cpus				=  0;
static unsigned int		page_size;
static unsigned int		mmap_pages			= 16;
static int			output;
22
static const char		*output_name			= "perf.data";
23
static int			group				= 0;
24 25
static unsigned int		realtime_prio			= 0;
static int			system_wide			= 0;
26
static pid_t			target_pid			= -1;
27 28
static int			inherit				= 1;
static int			nmi				= 1;
29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135

const unsigned int default_count[] = {
	1000000,
	1000000,
	  10000,
	  10000,
	1000000,
	  10000,
};

struct mmap_data {
	int counter;
	void *base;
	unsigned int mask;
	unsigned int prev;
};

static unsigned int mmap_read_head(struct mmap_data *md)
{
	struct perf_counter_mmap_page *pc = md->base;
	int head;

	head = pc->data_head;
	rmb();

	return head;
}

static long events;
static struct timeval last_read, this_read;

static void mmap_read(struct mmap_data *md)
{
	unsigned int head = mmap_read_head(md);
	unsigned int old = md->prev;
	unsigned char *data = md->base + page_size;
	unsigned long size;
	void *buf;
	int diff;

	gettimeofday(&this_read, NULL);

	/*
	 * If we're further behind than half the buffer, there's a chance
	 * the writer will bite our tail and screw up the events under us.
	 *
	 * If we somehow ended up ahead of the head, we got messed up.
	 *
	 * In either case, truncate and restart at head.
	 */
	diff = head - old;
	if (diff > md->mask / 2 || diff < 0) {
		struct timeval iv;
		unsigned long msecs;

		timersub(&this_read, &last_read, &iv);
		msecs = iv.tv_sec*1000 + iv.tv_usec/1000;

		fprintf(stderr, "WARNING: failed to keep up with mmap data."
				"  Last read %lu msecs ago.\n", msecs);

		/*
		 * head points to a known good entry, start there.
		 */
		old = head;
	}

	last_read = this_read;

	if (old != head)
		events++;

	size = head - old;

	if ((old & md->mask) + size != (head & md->mask)) {
		buf = &data[old & md->mask];
		size = md->mask + 1 - (old & md->mask);
		old += size;
		while (size) {
			int ret = write(output, buf, size);
			if (ret < 0) {
				perror("failed to write");
				exit(-1);
			}
			size -= ret;
			buf += ret;
		}
	}

	buf = &data[old & md->mask];
	size = head - old;
	old += size;
	while (size) {
		int ret = write(output, buf, size);
		if (ret < 0) {
			perror("failed to write");
			exit(-1);
		}
		size -= ret;
		buf += ret;
	}

	md->prev = old;
}

static volatile int done = 0;

136
static void sig_handler(int sig)
137
{
138
	done = 1;
139 140
}

141 142 143 144 145 146
static struct pollfd event_array[MAX_NR_CPUS * MAX_COUNTERS];
static struct mmap_data mmap_array[MAX_NR_CPUS][MAX_COUNTERS];

static int nr_poll;
static int nr_cpu;

147
struct mmap_event {
148 149 150 151 152 153 154
	struct perf_event_header	header;
	__u32				pid;
	__u32				tid;
	__u64				start;
	__u64				len;
	__u64				pgoff;
	char				filename[PATH_MAX];
155
};
156

157
struct comm_event {
158 159 160 161
	struct perf_event_header	header;
	__u32				pid;
	__u32				tid;
	char				comm[16];
162 163 164 165
};

static pid_t pid_synthesize_comm_event(pid_t pid)
{
166
	struct comm_event comm_ev;
167
	char filename[PATH_MAX];
168
	pid_t spid, ppid;
169
	char bf[BUFSIZ];
170 171
	int fd, nr, ret;
	char comm[18];
172
	size_t size;
173
	char state;
174 175 176 177 178 179 180 181 182 183 184 185 186 187 188

	snprintf(filename, sizeof(filename), "/proc/%d/stat", pid);

	fd = open(filename, O_RDONLY);
	if (fd < 0) {
		fprintf(stderr, "couldn't open %s\n", filename);
		exit(EXIT_FAILURE);
	}
	if (read(fd, bf, sizeof(bf)) < 0) {
		fprintf(stderr, "couldn't read %s\n", filename);
		exit(EXIT_FAILURE);
	}
	close(fd);

	memset(&comm_ev, 0, sizeof(comm_ev));
189
        nr = sscanf(bf, "%d %s %c %d %d ",
190 191 192 193 194 195 196 197 198 199 200 201 202 203
			&spid, comm, &state, &ppid, &comm_ev.pid);
	if (nr != 5) {
		fprintf(stderr, "couldn't get COMM and pgid, malformed %s\n",
			filename);
		exit(EXIT_FAILURE);
	}
	comm_ev.header.type = PERF_EVENT_COMM;
	comm_ev.tid = pid;
	size = strlen(comm);
	comm[--size] = '\0'; /* Remove the ')' at the end */
	--size; /* Remove the '(' at the begin */
	memcpy(comm_ev.comm, comm + 1, size);
	size = ALIGN(size, sizeof(uint64_t));
	comm_ev.header.size = sizeof(comm_ev) - (sizeof(comm_ev.comm) - size);
204 205

	ret = write(output, &comm_ev, comm_ev.header.size);
206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269
	if (ret < 0) {
		perror("failed to write");
		exit(-1);
	}
	return comm_ev.pid;
}

static void pid_synthesize_mmap_events(pid_t pid, pid_t pgid)
{
	char filename[PATH_MAX];
	FILE *fp;

	snprintf(filename, sizeof(filename), "/proc/%d/maps", pid);

	fp = fopen(filename, "r");
	if (fp == NULL) {
		fprintf(stderr, "couldn't open %s\n", filename);
		exit(EXIT_FAILURE);
	}
	while (1) {
		char bf[BUFSIZ];
		unsigned char vm_read, vm_write, vm_exec, vm_mayshare;
		struct mmap_event mmap_ev = {
			.header.type = PERF_EVENT_MMAP,
		};
		unsigned long ino;
		int major, minor;
		size_t size;
		if (fgets(bf, sizeof(bf), fp) == NULL)
			break;

		/* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
		sscanf(bf, "%llx-%llx %c%c%c%c %llx %x:%x %lu",
			&mmap_ev.start, &mmap_ev.len,
                        &vm_read, &vm_write, &vm_exec, &vm_mayshare,
                        &mmap_ev.pgoff, &major, &minor, &ino);
		if (vm_exec == 'x') {
			char *execname = strrchr(bf, ' ');

			if (execname == NULL || execname[1] != '/')
				continue;

			execname += 1;
			size = strlen(execname);
			execname[size - 1] = '\0'; /* Remove \n */
			memcpy(mmap_ev.filename, execname, size);
			size = ALIGN(size, sizeof(uint64_t));
			mmap_ev.len -= mmap_ev.start;
			mmap_ev.header.size = (sizeof(mmap_ev) -
					       (sizeof(mmap_ev.filename) - size));
			mmap_ev.pid = pgid;
			mmap_ev.tid = pid;

			if (write(output, &mmap_ev, mmap_ev.header.size) < 0) {
				perror("failed to write");
				exit(-1);
			}
		}
	}

	fclose(fp);
}

static void open_counters(int cpu, pid_t pid)
270 271
{
	struct perf_counter_hw_event hw_event;
272 273 274
	int counter, group_fd;
	int track = 1;

275 276 277 278
	if (pid > 0) {
		pid_t pgid = pid_synthesize_comm_event(pid);
		pid_synthesize_mmap_events(pid, pgid);
	}
279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331

	group_fd = -1;
	for (counter = 0; counter < nr_counters; counter++) {

		memset(&hw_event, 0, sizeof(hw_event));
		hw_event.config		= event_id[counter];
		hw_event.irq_period	= event_count[counter];
		hw_event.record_type	= PERF_RECORD_IP | PERF_RECORD_TID;
		hw_event.nmi		= nmi;
		hw_event.mmap		= track;
		hw_event.comm		= track;
		hw_event.inherit	= (cpu < 0) && inherit;

		track = 0; // only the first counter needs these

		fd[nr_cpu][counter] =
			sys_perf_counter_open(&hw_event, pid, cpu, group_fd, 0);

		if (fd[nr_cpu][counter] < 0) {
			int err = errno;
			printf("kerneltop error: syscall returned with %d (%s)\n",
					fd[nr_cpu][counter], strerror(err));
			if (err == EPERM)
				printf("Are you root?\n");
			exit(-1);
		}
		assert(fd[nr_cpu][counter] >= 0);
		fcntl(fd[nr_cpu][counter], F_SETFL, O_NONBLOCK);

		/*
		 * First counter acts as the group leader:
		 */
		if (group && group_fd == -1)
			group_fd = fd[nr_cpu][counter];

		event_array[nr_poll].fd = fd[nr_cpu][counter];
		event_array[nr_poll].events = POLLIN;
		nr_poll++;

		mmap_array[nr_cpu][counter].counter = counter;
		mmap_array[nr_cpu][counter].prev = 0;
		mmap_array[nr_cpu][counter].mask = mmap_pages*page_size - 1;
		mmap_array[nr_cpu][counter].base = mmap(NULL, (mmap_pages+1)*page_size,
				PROT_READ, MAP_SHARED, fd[nr_cpu][counter], 0);
		if (mmap_array[nr_cpu][counter].base == MAP_FAILED) {
			printf("kerneltop error: failed to mmap with %d (%s)\n",
					errno, strerror(errno));
			exit(-1);
		}
	}
	nr_cpu++;
}

332
static int __cmd_record(int argc, const char **argv)
333 334
{
	int i, counter;
335 336 337 338 339 340 341 342 343 344 345 346 347 348
	pid_t pid;
	int ret;

	page_size = sysconf(_SC_PAGE_SIZE);
	nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
	assert(nr_cpus <= MAX_NR_CPUS);
	assert(nr_cpus >= 0);

	output = open(output_name, O_CREAT|O_RDWR, S_IRWXU);
	if (output < 0) {
		perror("failed to create output file");
		exit(-1);
	}

349 350 351 352
	if (!system_wide) {
		open_counters(-1, target_pid != -1 ? target_pid : 0);
	} else for (i = 0; i < nr_cpus; i++)
		open_counters(i, target_pid);
353

354 355
	signal(SIGCHLD, sig_handler);
	signal(SIGINT, sig_handler);
356

357
	if (target_pid == -1 && argc) {
358 359 360
		pid = fork();
		if (pid < 0)
			perror("failed to fork");
361

362
		if (!pid) {
363
			if (execvp(argv[0], (char **)argv)) {
364 365 366
				perror(argv[0]);
				exit(-1);
			}
367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386
		}
	}

	if (realtime_prio) {
		struct sched_param param;

		param.sched_priority = realtime_prio;
		if (sched_setscheduler(0, SCHED_FIFO, &param)) {
			printf("Could not set realtime priority.\n");
			exit(-1);
		}
	}

	/*
	 * TODO: store the current /proc/$/maps information somewhere
	 */

	while (!done) {
		int hits = events;

387
		for (i = 0; i < nr_cpu; i++) {
388 389 390 391 392 393 394 395 396 397
			for (counter = 0; counter < nr_counters; counter++)
				mmap_read(&mmap_array[i][counter]);
		}

		if (hits == events)
			ret = poll(event_array, nr_poll, 100);
	}

	return 0;
}
398 399 400 401 402 403

static const char * const record_usage[] = {
	"perf record [<options>] <command>",
	NULL
};

404 405
static char events_help_msg[EVENTS_HELP_MAX];

406
static const struct option options[] = {
407
	OPT_CALLBACK('e', "event", NULL, "event",
408
		     events_help_msg, parse_events),
409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429
	OPT_INTEGER('c', "count", &default_interval,
		    "event period to sample"),
	OPT_INTEGER('m', "mmap-pages", &mmap_pages,
		    "number of mmap data pages"),
	OPT_STRING('o', "output", &output_name, "file",
		    "output file name"),
	OPT_BOOLEAN('i', "inherit", &inherit,
		    "child tasks inherit counters"),
	OPT_INTEGER('p', "pid", &target_pid,
		    "record events on existing pid"),
	OPT_INTEGER('r', "realtime", &realtime_prio,
		    "collect data with this RT SCHED_FIFO priority"),
	OPT_BOOLEAN('a', "all-cpus", &system_wide,
			    "system-wide collection from all CPUs"),
	OPT_END()
};

int cmd_record(int argc, const char **argv, const char *prefix)
{
	int counter;

430
	create_events_help(events_help_msg);
431 432

	argc = parse_options(argc, argv, options, record_usage, 0);
433
	if (!argc && target_pid == -1 && !system_wide)
434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449
		usage_with_options(record_usage, options);

	if (!nr_counters) {
		nr_counters = 1;
		event_id[0] = 0;
	}

	for (counter = 0; counter < nr_counters; counter++) {
		if (event_count[counter])
			continue;

		event_count[counter] = default_interval;
	}

	return __cmd_record(argc, argv);
}