aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/trace/trace_events.c
blob: 64ec4d278ffbcd56b94d0d161b855914756f3e0b (plain) (blame)
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
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
/*
 * event tracer
 *
 * Copyright (C) 2008 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
 *
 *  - Added format output of fields of the trace point.
 *    This was based off of work by Tom Zanussi <tzanussi@gmail.com>.
 *
 */

#include <linux/debugfs.h>
#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/ctype.h>

#include "trace_output.h"

#define TRACE_SYSTEM "TRACE_SYSTEM"

static DEFINE_MUTEX(event_mutex);

int trace_define_field(struct ftrace_event_call *call, char *type,
		       char *name, int offset, int size)
{
	struct ftrace_event_field *field;

	field = kzalloc(sizeof(*field), GFP_KERNEL);
	if (!field)
		goto err;

	field->name = kstrdup(name, GFP_KERNEL);
	if (!field->name)
		goto err;

	field->type = kstrdup(type, GFP_KERNEL);
	if (!field->type)
		goto err;

	field->offset = offset;
	field->size = size;
	list_add(&field->link, &call->fields);

	return 0;

err:
	if (field) {
		kfree(field->name);
		kfree(field->type);
	}
	kfree(field);

	return -ENOMEM;
}

static void ftrace_clear_events(void)
{
	struct ftrace_event_call *call = (void *)__start_ftrace_events;


	while ((unsigned long)call < (unsigned long)__stop_ftrace_events) {

		if (call->enabled) {
			call->enabled = 0;
			call->unregfunc();
		}
		call++;
	}
}

static void ftrace_event_enable_disable(struct ftrace_event_call *call,
					int enable)
{

	switch (enable) {
	case 0:
		if (call->enabled) {
			call->enabled = 0;
			call->unregfunc();
		}
		break;
	case 1:
		if (!call->enabled) {
			call->enabled = 1;
			call->regfunc();
		}
		break;
	}
}

static int ftrace_set_clr_event(char *buf, int set)
{
	struct ftrace_event_call *call = __start_ftrace_events;
	char *event = NULL, *sub = NULL, *match;
	int ret = -EINVAL;

	/*
	 * The buf format can be <subsystem>:<event-name>
	 *  *:<event-name> means any event by that name.
	 *  :<event-name> is the same.
	 *
	 *  <subsystem>:* means all events in that subsystem
	 *  <subsystem>: means the same.
	 *
	 *  <name> (no ':') means all events in a subsystem with
	 *  the name <name> or any event that matches <name>
	 */

	match = strsep(&buf, ":");
	if (buf) {
		sub = match;
		event = buf;
		match = NULL;

		if (!strlen(sub) || strcmp(sub, "*") == 0)
			sub = NULL;
		if (!strlen(event) || strcmp(event, "*") == 0)
			event = NULL;
	}

	mutex_lock(&event_mutex);
	for_each_event(call) {

		if (!call->name || !call->regfunc)
			continue;

		if (match &&
		    strcmp(match, call->name) != 0 &&
		    strcmp(match, call->system) != 0)
			continue;

		if (sub && strcmp(sub, call->system) != 0)
			continue;

		if (event && strcmp(event, call->name) != 0)
			continue;

		ftrace_event_enable_disable(call, set);

		ret = 0;
	}
	mutex_unlock(&event_mutex);

	return ret;
}

/* 128 should be much more than enough */
#define EVENT_BUF_SIZE		127

static ssize_t
ftrace_event_write(struct file *file, const char __user *ubuf,
		   size_t cnt, loff_t *ppos)
{
	size_t read = 0;
	int i, set = 1;
	ssize_t ret;
	char *buf;
	char ch;

	if (!cnt || cnt < 0)
		return 0;

	ret = tracing_update_buffers();
	if (ret < 0)
		return ret;

	ret = get_user(ch, ubuf++);
	if (ret)
		return ret;
	read++;
	cnt--;

	/* skip white space */
	while (cnt && isspace(ch)) {
		ret = get_user(ch, ubuf++);
		if (ret)
			return ret;
		read++;
		cnt--;
	}

	/* Only white space found? */
	if (isspace(ch)) {
		file->f_pos += read;
		ret = read;
		return ret;
	}

	buf = kmalloc(EVENT_BUF_SIZE+1, GFP_KERNEL);
	if (!buf)
		return -ENOMEM;

	if (cnt > EVENT_BUF_SIZE)
		cnt = EVENT_BUF_SIZE;

	i = 0;
	while (cnt && !isspace(ch)) {
		if (!i && ch == '!')
			set = 0;
		else
			buf[i++] = ch;

		ret = get_user(ch, ubuf++);
		if (ret)
			goto out_free;
		read++;
		cnt--;
	}
	buf[i] = 0;

	file->f_pos += read;

	ret = ftrace_set_clr_event(buf, set);
	if (ret)
		goto out_free;

	ret = read;

 out_free:
	kfree(buf);

	return ret;
}

static void *
t_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct ftrace_event_call *call = m->private;
	struct ftrace_event_call *next = call;

	(*pos)++;

	for (;;) {
		if ((unsigned long)call >= (unsigned long)__stop_ftrace_events)
			return NULL;

		/*
		 * The ftrace subsystem is for showing formats only.
		 * They can not be enabled or disabled via the event files.
		 */
		if (call->regfunc)
			break;

		call++;
		next = call;
	}

	m->private = ++next;

	return call;
}

static void *t_start(struct seq_file *m, loff_t *pos)
{
	return t_next(m, NULL, pos);
}

static void *
s_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct ftrace_event_call *call = m->private;
	struct ftrace_event_call *next;

	(*pos)++;

 retry:
	if ((unsigned long)call >= (unsigned long)__stop_ftrace_events)
		return NULL;

	if (!call->enabled) {
		call++;
		goto retry;
	}

	next = call;
	m->private = ++next;

	return call;
}

static void *s_start(struct seq_file *m, loff_t *pos)
{
	return s_next(m, NULL, pos);
}

static int t_show(struct seq_file *m, void *v)
{
	struct ftrace_event_call *call = v;

	if (strcmp(call->system, TRACE_SYSTEM) != 0)
		seq_printf(m, "%s:", call->system);
	seq_printf(m, "%s\n", call->name);

	return 0;
}

static void t_stop(struct seq_file *m, void *p)
{
}

static int
ftrace_event_seq_open(struct inode *inode, struct file *file)
{
	int ret;
	const struct seq_operations *seq_ops;

	if ((file->f_mode & FMODE_WRITE) &&
	    !(file->f_flags & O_APPEND))
		ftrace_clear_events();

	seq_ops = inode->i_private;
	ret = seq_open(file, seq_ops);
	if (!ret) {
		struct seq_file *m = file->private_data;

		m->private = __start_ftrace_events;
	}
	return ret;
}

static ssize_t
event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
		  loff_t *ppos)
{
	struct ftrace_event_call *call = filp->private_data;
	char *buf;

	if (call->enabled)
		buf = "1\n";
	else
		buf = "0\n";

	return simple_read_from_buffer(ubuf, cnt, ppos, buf, 2);
}

static ssize_t
event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
		   loff_t *ppos)
{
	struct ftrace_event_call *call = filp->private_data;
	char buf[64];
	unsigned long val;
	int ret;

	if (cnt >= sizeof(buf))
		return -EINVAL;

	if (copy_from_user(&buf, ubuf, cnt))
		return -EFAULT;

	buf[cnt] = 0;

	ret = strict_strtoul(buf, 10, &val);
	if (ret < 0)
		return ret;

	ret = tracing_update_buffers();
	if (ret < 0)
		return ret;

	switch (val) {
	case 0:
	case 1:
		mutex_lock(&event_mutex);
		ftrace_event_enable_disable(call, val);
		mutex_unlock(&event_mutex);
		break;

	default:
		return -EINVAL;
	}

	*ppos += cnt;

	return cnt;
}

#undef FIELD
#define FIELD(type, name)						\
	#type, "common_" #name, offsetof(typeof(field), name),		\
		sizeof(field.name)

static int trace_write_header(struct trace_seq *s)
{
	struct trace_entry field;

	/* struct trace_entry */
	return trace_seq_printf(s,
				"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
				"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
				"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
				"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
				"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
				"\n",
				FIELD(unsigned char, type),
				FIELD(unsigned char, flags),
				FIELD(unsigned char, preempt_count),
				FIELD(int, pid),
				FIELD(int, tgid));
}

static ssize_t
event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
		  loff_t *ppos)
{
	struct ftrace_event_call *call = filp->private_data;
	struct trace_seq *s;
	char *buf;
	int r;

	if (*ppos)
		return 0;

	s = kmalloc(sizeof(*s), GFP_KERNEL);
	if (!s)
		return -ENOMEM;

	trace_seq_init(s);

	/* If any of the first writes fail, so will the show_format. */

	trace_seq_printf(s, "name: %s\n", call->name);
	trace_seq_printf(s, "ID: %d\n", call->id);
	trace_seq_printf(s, "format:\n");
	trace_write_header(s);

	r = call->show_format(s);
	if (!r) {
		/*
		 * ug!  The format output is bigger than a PAGE!!
		 */
		buf = "FORMAT TOO BIG\n";
		r = simple_read_from_buffer(ubuf, cnt, ppos,
					      buf, strlen(buf));
		goto out;
	}

	r = simple_read_from_buffer(ubuf, cnt, ppos,
				    s->buffer, s->len);
 out:
	kfree(s);
	return r;
}

static ssize_t
event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
{
	struct ftrace_event_call *call = filp->private_data;
	struct trace_seq *s;
	int r;

	if (*ppos)
		return 0;

	s = kmalloc(sizeof(*s), GFP_KERNEL);
	if (!s)
		return -ENOMEM;

	trace_seq_init(s);
	trace_seq_printf(s, "%d\n", call->id);

	r = simple_read_from_buffer(ubuf, cnt, ppos,
				    s->buffer, s->len);
	kfree(s);
	return r;
}

static ssize_t
event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
		  loff_t *ppos)
{
	struct ftrace_event_call *call = filp->private_data;
	struct trace_seq *s;
	int r;

	if (*ppos)
		return 0;

	s = kmalloc(sizeof(*s), GFP_KERNEL);
	if (!s)
		return -ENOMEM;

	trace_seq_init(s);

	filter_print_preds(call->preds, s);
	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);

	kfree(s);

	return r;
}

static ssize_t
event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
		   loff_t *ppos)
{
	struct ftrace_event_call *call = filp->private_data;
	char buf[64], *pbuf = buf;
	struct filter_pred *pred;
	int err;

	if (cnt >= sizeof(buf))
		return -EINVAL;

	if (copy_from_user(&buf, ubuf, cnt))
		return -EFAULT;

	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
	if (!pred)
		return -ENOMEM;

	err = filter_parse(&pbuf, pred);
	if (err < 0) {
		filter_free_pred(pred);
		return err;
	}

	if (pred->clear) {
		filter_free_preds(call);
		filter_free_pred(pred);
		return cnt;
	}

	if (filter_add_pred(call, pred)) {
		filter_free_pred(pred);
		return -EINVAL;
	}

	*ppos += cnt;

	return cnt;
}

static ssize_t
subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
		      loff_t *ppos)
{
	struct event_subsystem *system = filp->private_data;
	struct trace_seq *s;
	int r;

	if (*ppos)
		return 0;

	s = kmalloc(sizeof(*s), GFP_KERNEL);
	if (!s)
		return -ENOMEM;

	trace_seq_init(s);

	filter_print_preds(system->preds, s);
	r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);

	kfree(s);

	return r;
}

static ssize_t
subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
		       loff_t *ppos)
{
	struct event_subsystem *system = filp->private_data;
	char buf[64], *pbuf = buf;
	struct filter_pred *pred;
	int err;

	if (cnt >= sizeof(buf))
		return -EINVAL;

	if (copy_from_user(&buf, ubuf, cnt))
		return -EFAULT;

	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
	if (!pred)
		return -ENOMEM;

	err = filter_parse(&pbuf, pred);
	if (err < 0) {
		filter_free_pred(pred);
		return err;
	}

	if (pred->clear) {
		filter_free_subsystem_preds(system);
		filter_free_pred(pred);
		return cnt;
	}

	if (filter_add_subsystem_pred(system, pred)) {
		filter_free_subsystem_preds(system);
		filter_free_pred(pred);
		return -EINVAL;
	}

	*ppos += cnt;

	return cnt;
}

static const struct seq_operations show_event_seq_ops = {
	.start = t_start,
	.next = t_next,
	.show = t_show,
	.stop = t_stop,
};

static const struct seq_operations show_set_event_seq_ops = {
	.start = s_start,
	.next = s_next,
	.show = t_show,
	.stop = t_stop,
};

static const struct file_operations ftrace_avail_fops = {
	.open = ftrace_event_seq_open,
	.read = seq_read,
	.llseek = seq_lseek,
	.release = seq_release,
};

static const struct file_operations ftrace_set_event_fops = {
	.open = ftrace_event_seq_open,
	.read = seq_read,
	.write = ftrace_event_write,
	.llseek = seq_lseek,
	.release = seq_release,
};

static const struct file_operations ftrace_enable_fops = {
	.open = tracing_open_generic,
	.read = event_enable_read,
	.write = event_enable_write,
};

static const struct file_operations ftrace_event_format_fops = {
	.open = tracing_open_generic,
	.read = event_format_read,
};

static const struct file_operations ftrace_event_id_fops = {
	.open = tracing_open_generic,
	.read = event_id_read,
};

static const struct file_operations ftrace_event_filter_fops = {
	.open = tracing_open_generic,
	.read = event_filter_read,
	.write = event_filter_write,
};

static const struct file_operations ftrace_subsystem_filter_fops = {
	.open = tracing_open_generic,
	.read = subsystem_filter_read,
	.write = subsystem_filter_write,
};

static struct dentry *event_trace_events_dir(void)
{
	static struct dentry *d_tracer;
	static struct dentry *d_events;

	if (d_events)
		return d_events;

	d_tracer = tracing_init_dentry();
	if (!d_tracer)
		return NULL;

	d_events = debugfs_create_dir("events", d_tracer);
	if (!d_events)
		pr_warning("Could not create debugfs "
			   "'events' directory\n");

	return d_events;
}

static LIST_HEAD(event_subsystems);

static struct dentry *
event_subsystem_dir(const char *name, struct dentry *d_events)
{
	struct event_subsystem *system;

	/* First see if we did not already create this dir */
	list_for_each_entry(system, &event_subsystems, list) {
		if (strcmp(system->name, name) == 0)
			return system->entry;
	}

	/* need to create new entry */
	system = kmalloc(sizeof(*system), GFP_KERNEL);
	if (!system) {
		pr_warning("No memory to create event subsystem %s\n",
			   name);
		return d_events;
	}

	system->entry = debugfs_create_dir(name, d_events);
	if (!system->entry) {
		pr_warning("Could not create event subsystem %s\n",
			   name);
		kfree(system);
		return d_events;
	}

	system->name = name;
	list_add(&system->list, &event_subsystems);

	system->preds = NULL;

	return system->entry;
}

static int
event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
{
	struct dentry *entry;
	int ret;

	/*
	 * If the trace point header did not define TRACE_SYSTEM
	 * then the system would be called "TRACE_SYSTEM".
	 */
	if (strcmp(call->system, "TRACE_SYSTEM") != 0)
		d_events = event_subsystem_dir(call->system, d_events);

	if (call->raw_init) {
		ret = call->raw_init();
		if (ret < 0) {
			pr_warning("Could not initialize trace point"
				   " events/%s\n", call->name);
			return ret;
		}
	}

	call->dir = debugfs_create_dir(call->name, d_events);
	if (!call->dir) {
		pr_warning("Could not create debugfs "
			   "'%s' directory\n", call->name);
		return -1;
	}

	if (call->regfunc) {
		entry = debugfs_create_file("enable", 0644, call->dir, call,
					    &ftrace_enable_fops);
		if (!entry)
			pr_warning("Could not create debugfs "
				   "'%s/enable' entry\n", call->name);
	}

	if (call->id) {
		entry = debugfs_create_file("id", 0444, call->dir, call,
				&ftrace_event_id_fops);
		if (!entry)
			pr_warning("Could not create debugfs '%s/id' entry\n",
					call->name);
	}

	if (call->define_fields) {
		ret = call->define_fields();
		if (ret < 0) {
			pr_warning("Could not initialize trace point"
				   " events/%s\n", call->name);
			return ret;
		}
		entry = debugfs_create_file("filter", 0644, call->dir, call,
					    &ftrace_event_filter_fops);
		if (!entry)
			pr_warning("Could not create debugfs "
				   "'%s/filter' entry\n", call->name);
	}

	/* A trace may not want to export its format */
	if (!call->show_format)
		return 0;

	entry = debugfs_create_file("format", 0444, call->dir, call,
				    &ftrace_event_format_fops);
	if (!entry)
		pr_warning("Could not create debugfs "
			   "'%s/format' entry\n", call->name);

	return 0;
}

static __init int event_trace_init(void)
{
	struct ftrace_event_call *call = __start_ftrace_events;
	struct dentry *d_tracer;
	struct dentry *entry;
	struct dentry *d_events;

	d_tracer = tracing_init_dentry();
	if (!d_tracer)
		return 0;

	entry = debugfs_create_file("available_events", 0444, d_tracer,
				    (void *)&show_event_seq_ops,
				    &ftrace_avail_fops);
	if (!entry)
		pr_warning("Could not create debugfs "
			   "'available_events' entry\n");

	entry = debugfs_create_file("set_event", 0644, d_tracer,
				    (void *)&show_set_event_seq_ops,
				    &ftrace_set_event_fops);
	if (!entry)
		pr_warning("Could not create debugfs "
			   "'set_event' entry\n");

	d_events = event_trace_events_dir();
	if (!d_events)
		return 0;

	for_each_event(call) {
		/* The linker may leave blanks */
		if (!call->name)
			continue;
		event_create_dir(call, d_events);
	}

	return 0;
}
fs_initcall(event_trace_init);