summaryrefslogtreecommitdiffstats
path: root/tools/perf/builtin-ftrace.c
blob: 2bfc1b0db536325d5f6e92cffa73eeecd13d7c58 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
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
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
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
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
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
342
343
344
345
346
347
348
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
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
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
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
495
496
497
498
499
500
501
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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * builtin-ftrace.c
 *
 * Copyright (c) 2013  LG Electronics,  Namhyung Kim <namhyung@kernel.org>
 */

#include "builtin.h"

#include <errno.h>
#include <unistd.h>
#include <signal.h>
#include <stdlib.h>
#include <fcntl.h>
#include <poll.h>
#include <linux/capability.h>
#include <linux/string.h>

#include "debug.h"
#include <subcmd/pager.h>
#include <subcmd/parse-options.h>
#include <api/fs/tracing_path.h>
#include "evlist.h"
#include "target.h"
#include "cpumap.h"
#include "thread_map.h"
#include "util/cap.h"
#include "util/config.h"

#define DEFAULT_TRACER  "function_graph"

struct perf_ftrace {
	struct evlist		*evlist;
	struct target		target;
	const char		*tracer;
	struct list_head	filters;
	struct list_head	notrace;
	struct list_head	graph_funcs;
	struct list_head	nograph_funcs;
	int			graph_depth;
};

struct filter_entry {
	struct list_head	list;
	char			name[];
};

static volatile int workload_exec_errno;
static bool done;

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

/*
 * perf_evlist__prepare_workload will send a SIGUSR1 if the fork fails, since
 * we asked by setting its exec_error to the function below,
 * ftrace__workload_exec_failed_signal.
 *
 * XXX We need to handle this more appropriately, emitting an error, etc.
 */
static void ftrace__workload_exec_failed_signal(int signo __maybe_unused,
						siginfo_t *info __maybe_unused,
						void *ucontext __maybe_unused)
{
	workload_exec_errno = info->si_value.sival_int;
	done = true;
}

static int __write_tracing_file(const char *name, const char *val, bool append)
{
	char *file;
	int fd, ret = -1;
	ssize_t size = strlen(val);
	int flags = O_WRONLY;
	char errbuf[512];
	char *val_copy;

	file = get_tracing_file(name);
	if (!file) {
		pr_debug("cannot get tracing file: %s\n", name);
		return -1;
	}

	if (append)
		flags |= O_APPEND;
	else
		flags |= O_TRUNC;

	fd = open(file, flags);
	if (fd < 0) {
		pr_debug("cannot open tracing file: %s: %s\n",
			 name, str_error_r(errno, errbuf, sizeof(errbuf)));
		goto out;
	}

	/*
	 * Copy the original value and append a '\n'. Without this,
	 * the kernel can hide possible errors.
	 */
	val_copy = strdup(val);
	if (!val_copy)
		goto out_close;
	val_copy[size] = '\n';

	if (write(fd, val_copy, size + 1) == size + 1)
		ret = 0;
	else
		pr_debug("write '%s' to tracing/%s failed: %s\n",
			 val, name, str_error_r(errno, errbuf, sizeof(errbuf)));

	free(val_copy);
out_close:
	close(fd);
out:
	put_tracing_file(file);
	return ret;
}

static int write_tracing_file(const char *name, const char *val)
{
	return __write_tracing_file(name, val, false);
}

static int append_tracing_file(const char *name, const char *val)
{
	return __write_tracing_file(name, val, true);
}

static int reset_tracing_cpu(void);
static void reset_tracing_filters(void);

static int reset_tracing_files(struct perf_ftrace *ftrace __maybe_unused)
{
	if (write_tracing_file("tracing_on", "0") < 0)
		return -1;

	if (write_tracing_file("current_tracer", "nop") < 0)
		return -1;

	if (write_tracing_file("set_ftrace_pid", " ") < 0)
		return -1;

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

	if (write_tracing_file("max_graph_depth", "0") < 0)
		return -1;

	reset_tracing_filters();
	return 0;
}

static int set_tracing_pid(struct perf_ftrace *ftrace)
{
	int i;
	char buf[16];

	if (target__has_cpu(&ftrace->target))
		return 0;

	for (i = 0; i < perf_thread_map__nr(ftrace->evlist->core.threads); i++) {
		scnprintf(buf, sizeof(buf), "%d",
			  ftrace->evlist->core.threads->map[i]);
		if (append_tracing_file("set_ftrace_pid", buf) < 0)
			return -1;
	}
	return 0;
}

static int set_tracing_cpumask(struct perf_cpu_map *cpumap)
{
	char *cpumask;
	size_t mask_size;
	int ret;
	int last_cpu;

	last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1);
	mask_size = last_cpu / 4 + 2; /* one more byte for EOS */
	mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */

	cpumask = malloc(mask_size);
	if (cpumask == NULL) {
		pr_debug("failed to allocate cpu mask\n");
		return -1;
	}

	cpu_map__snprint_mask(cpumap, cpumask, mask_size);

	ret = write_tracing_file("tracing_cpumask", cpumask);

	free(cpumask);
	return ret;
}

static int set_tracing_cpu(struct perf_ftrace *ftrace)
{
	struct perf_cpu_map *cpumap = ftrace->evlist->core.cpus;

	if (!target__has_cpu(&ftrace->target))
		return 0;

	return set_tracing_cpumask(cpumap);
}

static int reset_tracing_cpu(void)
{
	struct perf_cpu_map *cpumap = perf_cpu_map__new(NULL);
	int ret;

	ret = set_tracing_cpumask(cpumap);
	perf_cpu_map__put(cpumap);
	return ret;
}

static int __set_tracing_filter(const char *filter_file, struct list_head *funcs)
{
	struct filter_entry *pos;

	list_for_each_entry(pos, funcs, list) {
		if (append_tracing_file(filter_file, pos->name) < 0)
			return -1;
	}

	return 0;
}

static int set_tracing_filters(struct perf_ftrace *ftrace)
{
	int ret;

	ret = __set_tracing_filter("set_ftrace_filter", &ftrace->filters);
	if (ret < 0)
		return ret;

	ret = __set_tracing_filter("set_ftrace_notrace", &ftrace->notrace);
	if (ret < 0)
		return ret;

	ret = __set_tracing_filter("set_graph_function", &ftrace->graph_funcs);
	if (ret < 0)
		return ret;

	/* old kernels do not have this filter */
	__set_tracing_filter("set_graph_notrace", &ftrace->nograph_funcs);

	return ret;
}

static void reset_tracing_filters(void)
{
	write_tracing_file("set_ftrace_filter", " ");
	write_tracing_file("set_ftrace_notrace", " ");
	write_tracing_file("set_graph_function", " ");
	write_tracing_file("set_graph_notrace", " ");
}

static int set_tracing_depth(struct perf_ftrace *ftrace)
{
	char buf[16];

	if (ftrace->graph_depth == 0)
		return 0;

	if (ftrace->graph_depth < 0) {
		pr_err("invalid graph depth: %d\n", ftrace->graph_depth);
		return -1;
	}

	snprintf(buf, sizeof(buf), "%d", ftrace->graph_depth);

	if (write_tracing_file("max_graph_depth", buf) < 0)
		return -1;

	return 0;
}

static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
{
	char *trace_file;
	int trace_fd;
	char buf[4096];
	struct pollfd pollfd = {
		.events = POLLIN,
	};

	if (!(perf_cap__capable(CAP_PERFMON) ||
	      perf_cap__capable(CAP_SYS_ADMIN))) {
		pr_err("ftrace only works for %s!\n",
#ifdef HAVE_LIBCAP_SUPPORT
		"users with the CAP_PERFMON or CAP_SYS_ADMIN capability"
#else
		"root"
#endif
		);
		return -1;
	}

	signal(SIGINT, sig_handler);
	signal(SIGUSR1, sig_handler);
	signal(SIGCHLD, sig_handler);
	signal(SIGPIPE, sig_handler);

	if (reset_tracing_files(ftrace) < 0) {
		pr_err("failed to reset ftrace\n");
		goto out;
	}

	/* reset ftrace buffer */
	if (write_tracing_file("trace", "0") < 0)
		goto out;

	if (argc && perf_evlist__prepare_workload(ftrace->evlist,
				&ftrace->target, argv, false,
				ftrace__workload_exec_failed_signal) < 0) {
		goto out;
	}

	if (set_tracing_pid(ftrace) < 0) {
		pr_err("failed to set ftrace pid\n");
		goto out_reset;
	}

	if (set_tracing_cpu(ftrace) < 0) {
		pr_err("failed to set tracing cpumask\n");
		goto out_reset;
	}

	if (set_tracing_filters(ftrace) < 0) {
		pr_err("failed to set tracing filters\n");
		goto out_reset;
	}

	if (set_tracing_depth(ftrace) < 0) {
		pr_err("failed to set graph depth\n");
		goto out_reset;
	}

	if (write_tracing_file("current_tracer", ftrace->tracer) < 0) {
		pr_err("failed to set current_tracer to %s\n", ftrace->tracer);
		goto out_reset;
	}

	setup_pager();

	trace_file = get_tracing_file("trace_pipe");
	if (!trace_file) {
		pr_err("failed to open trace_pipe\n");
		goto out_reset;
	}

	trace_fd = open(trace_file, O_RDONLY);

	put_tracing_file(trace_file);

	if (trace_fd < 0) {
		pr_err("failed to open trace_pipe\n");
		goto out_reset;
	}

	fcntl(trace_fd, F_SETFL, O_NONBLOCK);
	pollfd.fd = trace_fd;

	if (write_tracing_file("tracing_on", "1") < 0) {
		pr_err("can't enable tracing\n");
		goto out_close_fd;
	}

	perf_evlist__start_workload(ftrace->evlist);

	while (!done) {
		if (poll(&pollfd, 1, -1) < 0)
			break;

		if (pollfd.revents & POLLIN) {
			int n = read(trace_fd, buf, sizeof(buf));
			if (n < 0)
				break;
			if (fwrite(buf, n, 1, stdout) != 1)
				break;
		}
	}

	write_tracing_file("tracing_on", "0");

	if (workload_exec_errno) {
		const char *emsg = str_error_r(workload_exec_errno, buf, sizeof(buf));
		/* flush stdout first so below error msg appears at the end. */
		fflush(stdout);
		pr_err("workload failed: %s\n", emsg);
		goto out_close_fd;
	}

	/* read remaining buffer contents */
	while (true) {
		int n = read(trace_fd, buf, sizeof(buf));
		if (n <= 0)
			break;
		if (fwrite(buf, n, 1, stdout) != 1)
			break;
	}

out_close_fd:
	close(trace_fd);
out_reset:
	reset_tracing_files(ftrace);
out:
	return (done && !workload_exec_errno) ? 0 : -1;
}

static int perf_ftrace_config(const char *var, const char *value, void *cb)
{
	struct perf_ftrace *ftrace = cb;

	if (!strstarts(var, "ftrace."))
		return 0;

	if (strcmp(var, "ftrace.tracer"))
		return -1;

	if (!strcmp(value, "function_graph") ||
	    !strcmp(value, "function")) {
		ftrace->tracer = value;
		return 0;
	}

	pr_err("Please select \"function_graph\" (default) or \"function\"\n");
	return -1;
}

static int parse_filter_func(const struct option *opt, const char *str,
			     int unset __maybe_unused)
{
	struct list_head *head = opt->value;
	struct filter_entry *entry;

	entry = malloc(sizeof(*entry) + strlen(str) + 1);
	if (entry == NULL)
		return -ENOMEM;

	strcpy(entry->name, str);
	list_add_tail(&entry->list, head);

	return 0;
}

static void delete_filter_func(struct list_head *head)
{
	struct filter_entry *pos, *tmp;

	list_for_each_entry_safe(pos, tmp, head, list) {
		list_del_init(&pos->list);
		free(pos);
	}
}

int cmd_ftrace(int argc, const char **argv)
{
	int ret;
	struct perf_ftrace ftrace = {
		.tracer = DEFAULT_TRACER,
		.target = { .uid = UINT_MAX, },
	};
	const char * const ftrace_usage[] = {
		"perf ftrace [<options>] [<command>]",
		"perf ftrace [<options>] -- <command> [<options>]",
		NULL
	};
	const struct option ftrace_options[] = {
	OPT_STRING('t', "tracer", &ftrace.tracer, "tracer",
		   "tracer to use: function_graph(default) or function"),
	OPT_STRING('p', "pid", &ftrace.target.pid, "pid",
		   "trace on existing process id"),
	OPT_INCR('v', "verbose", &verbose,
		 "be more verbose"),
	OPT_BOOLEAN('a', "all-cpus", &ftrace.target.system_wide,
		    "system-wide collection from all CPUs"),
	OPT_STRING('C', "cpu", &ftrace.target.cpu_list, "cpu",
		    "list of cpus to monitor"),
	OPT_CALLBACK('T', "trace-funcs", &ftrace.filters, "func",
		     "trace given functions only", parse_filter_func),
	OPT_CALLBACK('N', "notrace-funcs", &ftrace.notrace, "func",
		     "do not trace given functions", parse_filter_func),
	OPT_CALLBACK('G', "graph-funcs", &ftrace.graph_funcs, "func",
		     "Set graph filter on given functions", parse_filter_func),
	OPT_CALLBACK('g', "nograph-funcs", &ftrace.nograph_funcs, "func",
		     "Set nograph filter on given functions", parse_filter_func),
	OPT_INTEGER('D', "graph-depth", &ftrace.graph_depth,
		    "Max depth for function graph tracer"),
	OPT_END()
	};

	INIT_LIST_HEAD(&ftrace.filters);
	INIT_LIST_HEAD(&ftrace.notrace);
	INIT_LIST_HEAD(&ftrace.graph_funcs);
	INIT_LIST_HEAD(&ftrace.nograph_funcs);

	ret = perf_config(perf_ftrace_config, &ftrace);
	if (ret < 0)
		return -1;

	argc = parse_options(argc, argv, ftrace_options, ftrace_usage,
			    PARSE_OPT_STOP_AT_NON_OPTION);
	if (!argc && target__none(&ftrace.target))
		ftrace.target.system_wide = true;

	ret = target__validate(&ftrace.target);
	if (ret) {
		char errbuf[512];

		target__strerror(&ftrace.target, ret, errbuf, 512);
		pr_err("%s\n", errbuf);
		goto out_delete_filters;
	}

	ftrace.evlist = evlist__new();
	if (ftrace.evlist == NULL) {
		ret = -ENOMEM;
		goto out_delete_filters;
	}

	ret = perf_evlist__create_maps(ftrace.evlist, &ftrace.target);
	if (ret < 0)
		goto out_delete_evlist;

	ret = __cmd_ftrace(&ftrace, argc, argv);

out_delete_evlist:
	evlist__delete(ftrace.evlist);

out_delete_filters:
	delete_filter_func(&ftrace.filters);
	delete_filter_func(&ftrace.notrace);
	delete_filter_func(&ftrace.graph_funcs);
	delete_filter_func(&ftrace.nograph_funcs);

	return ret;
}