trace_syscalls.c 10.4 KB
Newer Older
1
#include <trace/syscall.h>
2
#include <linux/kernel.h>
3
#include <linux/ftrace.h>
4
#include <linux/perf_counter.h>
5
6
7
8
9
#include <asm/syscall.h>

#include "trace_output.h"
#include "trace.h"

10
static DEFINE_MUTEX(syscall_trace_lock);
11
12
13
14
static int sys_refcount_enter;
static int sys_refcount_exit;
static DECLARE_BITMAP(enabled_enter_syscalls, FTRACE_SYSCALL_MAX);
static DECLARE_BITMAP(enabled_exit_syscalls, FTRACE_SYSCALL_MAX);
15

16
/* Option to display the parameters types */
17
18
19
20
21
22
23
24
25
26
enum {
	TRACE_SYSCALLS_OPT_TYPES = 0x1,
};

static struct tracer_opt syscalls_opts[] = {
	{ TRACER_OPT(syscall_arg_type, TRACE_SYSCALLS_OPT_TYPES) },
	{ }
};

static struct tracer_flags syscalls_flags = {
27
	.val = 0, /* By default: no parameters types */
28
29
30
31
32
33
34
35
36
37
38
39
	.opts = syscalls_opts
};

enum print_line_t
print_syscall_enter(struct trace_iterator *iter, int flags)
{
	struct trace_seq *s = &iter->seq;
	struct trace_entry *ent = iter->ent;
	struct syscall_trace_enter *trace;
	struct syscall_metadata *entry;
	int i, ret, syscall;

40
	trace = (typeof(trace))ent;
41
42
	syscall = trace->nr;
	entry = syscall_nr_to_meta(syscall);
43

44
45
46
	if (!entry)
		goto end;

47
48
49
50
51
	if (entry->enter_id != ent->type) {
		WARN_ON_ONCE(1);
		goto end;
	}

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
	ret = trace_seq_printf(s, "%s(", entry->name);
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	for (i = 0; i < entry->nb_args; i++) {
		/* parameter types */
		if (syscalls_flags.val & TRACE_SYSCALLS_OPT_TYPES) {
			ret = trace_seq_printf(s, "%s ", entry->types[i]);
			if (!ret)
				return TRACE_TYPE_PARTIAL_LINE;
		}
		/* parameter values */
		ret = trace_seq_printf(s, "%s: %lx%s ", entry->args[i],
				       trace->args[i],
				       i == entry->nb_args - 1 ? ")" : ",");
		if (!ret)
			return TRACE_TYPE_PARTIAL_LINE;
	}

end:
	trace_seq_printf(s, "\n");
	return TRACE_TYPE_HANDLED;
}

enum print_line_t
print_syscall_exit(struct trace_iterator *iter, int flags)
{
	struct trace_seq *s = &iter->seq;
	struct trace_entry *ent = iter->ent;
	struct syscall_trace_exit *trace;
	int syscall;
	struct syscall_metadata *entry;
	int ret;

86
	trace = (typeof(trace))ent;
87
88
	syscall = trace->nr;
	entry = syscall_nr_to_meta(syscall);
89

90
91
92
93
94
	if (!entry) {
		trace_seq_printf(s, "\n");
		return TRACE_TYPE_HANDLED;
	}

95
96
97
98
99
	if (entry->exit_id != ent->type) {
		WARN_ON_ONCE(1);
		return TRACE_TYPE_UNHANDLED;
	}

100
101
102
103
104
105
106
107
	ret = trace_seq_printf(s, "%s -> 0x%lx\n", entry->name,
				trace->ret);
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	return TRACE_TYPE_HANDLED;
}

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
int ftrace_format_syscall(struct ftrace_event_call *call, struct trace_seq *s)
{
	int i;
	int nr;
	int ret = 0;
	struct syscall_metadata *entry;
	int offset = sizeof(struct trace_entry);

	nr = syscall_name_to_nr((char *)call->data);
	entry = syscall_nr_to_meta(nr);

	if (!entry)
		return ret;

	for (i = 0; i < entry->nb_args; i++) {
		ret = trace_seq_printf(s, "\tfield:%s %s;", entry->types[i],
				        entry->args[i]);
		if (!ret)
			return 0;
		ret = trace_seq_printf(s, "\toffset:%d;\tsize:%lu;\n", offset,
				       sizeof(unsigned long));
		if (!ret)
			return 0;
		offset += sizeof(unsigned long);
	}

	trace_seq_printf(s, "\nprint fmt: \"");
	for (i = 0; i < entry->nb_args; i++) {
		ret = trace_seq_printf(s, "%s: 0x%%0%lulx%s", entry->args[i],
				        sizeof(unsigned long),
					i == entry->nb_args - 1 ? "\", " : ", ");
		if (!ret)
			return 0;
	}

	for (i = 0; i < entry->nb_args; i++) {
		ret = trace_seq_printf(s, "((unsigned long)(REC->%s))%s",
				        entry->args[i],
					i == entry->nb_args - 1 ? "\n" : ", ");
		if (!ret)
			return 0;
	}

	return ret;
}

154
void ftrace_syscall_enter(struct pt_regs *regs, long id)
155
{
156
157
158
159
	struct syscall_trace_enter *entry;
	struct syscall_metadata *sys_data;
	struct ring_buffer_event *event;
	int size;
160
161
162
	int syscall_nr;

	syscall_nr = syscall_get_nr(current, regs);
163
164
	if (!test_bit(syscall_nr, enabled_enter_syscalls))
		return;
165

166
167
168
169
170
171
	sys_data = syscall_nr_to_meta(syscall_nr);
	if (!sys_data)
		return;

	size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;

172
	event = trace_current_buffer_lock_reserve(sys_data->enter_id, size,
173
174
175
176
177
178
179
180
181
182
							0, 0);
	if (!event)
		return;

	entry = ring_buffer_event_data(event);
	entry->nr = syscall_nr;
	syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);

	trace_current_buffer_unlock_commit(event, 0, 0);
	trace_wake_up();
183
184
}

185
void ftrace_syscall_exit(struct pt_regs *regs, long ret)
186
{
187
188
189
	struct syscall_trace_exit *entry;
	struct syscall_metadata *sys_data;
	struct ring_buffer_event *event;
190
191
192
	int syscall_nr;

	syscall_nr = syscall_get_nr(current, regs);
193
194
	if (!test_bit(syscall_nr, enabled_exit_syscalls))
		return;
195

196
197
198
199
	sys_data = syscall_nr_to_meta(syscall_nr);
	if (!sys_data)
		return;

200
	event = trace_current_buffer_lock_reserve(sys_data->exit_id,
201
202
203
204
205
206
207
208
209
210
				sizeof(*entry), 0, 0);
	if (!event)
		return;

	entry = ring_buffer_event_data(event);
	entry->nr = syscall_nr;
	entry->ret = syscall_get_return_value(current, regs);

	trace_current_buffer_unlock_commit(event, 0, 0);
	trace_wake_up();
211
212
}

213
int reg_event_syscall_enter(void *ptr)
214
{
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
	int ret = 0;
	int num;
	char *name;

	name = (char *)ptr;
	num = syscall_name_to_nr(name);
	if (num < 0 || num >= FTRACE_SYSCALL_MAX)
		return -ENOSYS;
	mutex_lock(&syscall_trace_lock);
	if (!sys_refcount_enter)
		ret = register_trace_syscall_enter(ftrace_syscall_enter);
	if (ret) {
		pr_info("event trace: Could not activate"
				"syscall entry trace point");
	} else {
		set_bit(num, enabled_enter_syscalls);
		sys_refcount_enter++;
	}
	mutex_unlock(&syscall_trace_lock);
	return ret;
235
236
}

237
void unreg_event_syscall_enter(void *ptr)
238
{
239
240
	int num;
	char *name;
241

242
243
244
245
246
247
248
249
250
251
252
	name = (char *)ptr;
	num = syscall_name_to_nr(name);
	if (num < 0 || num >= FTRACE_SYSCALL_MAX)
		return;
	mutex_lock(&syscall_trace_lock);
	sys_refcount_enter--;
	clear_bit(num, enabled_enter_syscalls);
	if (!sys_refcount_enter)
		unregister_trace_syscall_enter(ftrace_syscall_enter);
	mutex_unlock(&syscall_trace_lock);
}
253

254
int reg_event_syscall_exit(void *ptr)
255
{
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
	int ret = 0;
	int num;
	char *name;

	name = (char *)ptr;
	num = syscall_name_to_nr(name);
	if (num < 0 || num >= FTRACE_SYSCALL_MAX)
		return -ENOSYS;
	mutex_lock(&syscall_trace_lock);
	if (!sys_refcount_exit)
		ret = register_trace_syscall_exit(ftrace_syscall_exit);
	if (ret) {
		pr_info("event trace: Could not activate"
				"syscall exit trace point");
	} else {
		set_bit(num, enabled_exit_syscalls);
		sys_refcount_exit++;
273
	}
274
275
276
	mutex_unlock(&syscall_trace_lock);
	return ret;
}
277

278
279
280
281
void unreg_event_syscall_exit(void *ptr)
{
	int num;
	char *name;
282

283
284
285
286
287
288
289
290
291
292
	name = (char *)ptr;
	num = syscall_name_to_nr(name);
	if (num < 0 || num >= FTRACE_SYSCALL_MAX)
		return;
	mutex_lock(&syscall_trace_lock);
	sys_refcount_exit--;
	clear_bit(num, enabled_exit_syscalls);
	if (!sys_refcount_exit)
		unregister_trace_syscall_exit(ftrace_syscall_exit);
	mutex_unlock(&syscall_trace_lock);
293
}
294
295
296
297
298
299
300
301

struct trace_event event_syscall_enter = {
	.trace			= print_syscall_enter,
};

struct trace_event event_syscall_exit = {
	.trace			= print_syscall_exit,
};
302
303

#ifdef CONFIG_EVENT_PROFILE
304
305
306
307
308
309
310
311
312
313
314

struct syscall_enter_record {
	struct trace_entry	entry;
	unsigned long		args[0];
};

struct syscall_exit_record {
	struct trace_entry	entry;
	unsigned long		ret;
};

315
316
317
318
319
320
321
static DECLARE_BITMAP(enabled_prof_enter_syscalls, FTRACE_SYSCALL_MAX);
static DECLARE_BITMAP(enabled_prof_exit_syscalls, FTRACE_SYSCALL_MAX);
static int sys_prof_refcount_enter;
static int sys_prof_refcount_exit;

static void prof_syscall_enter(struct pt_regs *regs, long id)
{
322
	struct syscall_enter_record *rec;
323
324
	struct syscall_metadata *sys_data;
	int syscall_nr;
325
	int size;
326
327
328
329
330
331
332
333
334

	syscall_nr = syscall_get_nr(current, regs);
	if (!test_bit(syscall_nr, enabled_prof_enter_syscalls))
		return;

	sys_data = syscall_nr_to_meta(syscall_nr);
	if (!sys_data)
		return;

335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
	/* get the size after alignment with the u32 buffer size field */
	size = sizeof(unsigned long) * sys_data->nb_args + sizeof(*rec);
	size = ALIGN(size + sizeof(u32), sizeof(u64));
	size -= sizeof(u32);

	do {
		char raw_data[size];

		/* zero the dead bytes from align to not leak stack to user */
		*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;

		rec = (struct syscall_enter_record *) raw_data;
		tracing_generic_entry_update(&rec->entry, 0, 0);
		rec->entry.type = sys_data->enter_id;
		syscall_get_arguments(current, regs, 0, sys_data->nb_args,
				       (unsigned long *)&rec->args);
		perf_tpcounter_event(sys_data->enter_id, 0, 1, rec, size);
	} while(0);
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
}

int reg_prof_syscall_enter(char *name)
{
	int ret = 0;
	int num;

	num = syscall_name_to_nr(name);
	if (num < 0 || num >= FTRACE_SYSCALL_MAX)
		return -ENOSYS;

	mutex_lock(&syscall_trace_lock);
	if (!sys_prof_refcount_enter)
		ret = register_trace_syscall_enter(prof_syscall_enter);
	if (ret) {
		pr_info("event trace: Could not activate"
				"syscall entry trace point");
	} else {
		set_bit(num, enabled_prof_enter_syscalls);
		sys_prof_refcount_enter++;
	}
	mutex_unlock(&syscall_trace_lock);
	return ret;
}

void unreg_prof_syscall_enter(char *name)
{
	int num;

	num = syscall_name_to_nr(name);
	if (num < 0 || num >= FTRACE_SYSCALL_MAX)
		return;

	mutex_lock(&syscall_trace_lock);
	sys_prof_refcount_enter--;
	clear_bit(num, enabled_prof_enter_syscalls);
	if (!sys_prof_refcount_enter)
		unregister_trace_syscall_enter(prof_syscall_enter);
	mutex_unlock(&syscall_trace_lock);
}

static void prof_syscall_exit(struct pt_regs *regs, long ret)
{
	struct syscall_metadata *sys_data;
397
	struct syscall_exit_record rec;
398
399
400
401
402
403
404
405
406
407
	int syscall_nr;

	syscall_nr = syscall_get_nr(current, regs);
	if (!test_bit(syscall_nr, enabled_prof_exit_syscalls))
		return;

	sys_data = syscall_nr_to_meta(syscall_nr);
	if (!sys_data)
		return;

408
409
410
411
412
	tracing_generic_entry_update(&rec.entry, 0, 0);
	rec.entry.type = sys_data->exit_id;
	rec.ret = syscall_get_return_value(current, regs);

	perf_tpcounter_event(sys_data->exit_id, 0, 1, &rec, sizeof(rec));
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
}

int reg_prof_syscall_exit(char *name)
{
	int ret = 0;
	int num;

	num = syscall_name_to_nr(name);
	if (num < 0 || num >= FTRACE_SYSCALL_MAX)
		return -ENOSYS;

	mutex_lock(&syscall_trace_lock);
	if (!sys_prof_refcount_exit)
		ret = register_trace_syscall_exit(prof_syscall_exit);
	if (ret) {
		pr_info("event trace: Could not activate"
				"syscall entry trace point");
	} else {
		set_bit(num, enabled_prof_exit_syscalls);
		sys_prof_refcount_exit++;
	}
	mutex_unlock(&syscall_trace_lock);
	return ret;
}

void unreg_prof_syscall_exit(char *name)
{
	int num;

	num = syscall_name_to_nr(name);
	if (num < 0 || num >= FTRACE_SYSCALL_MAX)
		return;

	mutex_lock(&syscall_trace_lock);
	sys_prof_refcount_exit--;
	clear_bit(num, enabled_prof_exit_syscalls);
	if (!sys_prof_refcount_exit)
		unregister_trace_syscall_exit(prof_syscall_exit);
	mutex_unlock(&syscall_trace_lock);
}

#endif