trace_syscalls.c 11.7 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 17 18 19 20 21 22 23 24
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;

25
	trace = (typeof(trace))ent;
26 27
	syscall = trace->nr;
	entry = syscall_nr_to_meta(syscall);
28

29 30 31
	if (!entry)
		goto end;

32 33 34 35 36
	if (entry->enter_id != ent->type) {
		WARN_ON_ONCE(1);
		goto end;
	}

37 38 39 40 41 42
	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 */
43
		if (trace_flags & TRACE_ITER_VERBOSE) {
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
			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;

71
	trace = (typeof(trace))ent;
72 73
	syscall = trace->nr;
	entry = syscall_nr_to_meta(syscall);
74

75 76 77 78 79
	if (!entry) {
		trace_seq_printf(s, "\n");
		return TRACE_TYPE_HANDLED;
	}

80 81 82 83 84
	if (entry->exit_id != ent->type) {
		WARN_ON_ONCE(1);
		return TRACE_TYPE_UNHANDLED;
	}

85 86 87 88 89 90 91 92
	ret = trace_seq_printf(s, "%s -> 0x%lx\n", entry->name,
				trace->ret);
	if (!ret)
		return TRACE_TYPE_PARTIAL_LINE;

	return TRACE_TYPE_HANDLED;
}

93 94 95 96 97 98 99
extern char *__bad_type_size(void);

#define SYSCALL_FIELD(type, name)					\
	sizeof(type) != sizeof(trace.name) ?				\
		__bad_type_size() :					\
		#type, #name, offsetof(typeof(trace), name), sizeof(trace.name)

100
int syscall_enter_format(struct ftrace_event_call *call, struct trace_seq *s)
101 102 103
{
	int i;
	int nr;
104
	int ret;
105
	struct syscall_metadata *entry;
106 107
	struct syscall_trace_enter trace;
	int offset = offsetof(struct syscall_trace_enter, args);
108

109
	nr = syscall_name_to_nr(call->data);
110 111 112
	entry = syscall_nr_to_meta(nr);

	if (!entry)
113 114 115 116 117 118
		return 0;

	ret = trace_seq_printf(s, "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n",
			       SYSCALL_FIELD(int, nr));
	if (!ret)
		return 0;
119 120 121 122 123 124

	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;
125
		ret = trace_seq_printf(s, "\toffset:%d;\tsize:%zu;\n", offset,
126 127 128 129 130 131 132 133
				       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++) {
134
		ret = trace_seq_printf(s, "%s: 0x%%0%zulx%s", entry->args[i],
135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151
				        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;
}

152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167
int syscall_exit_format(struct ftrace_event_call *call, struct trace_seq *s)
{
	int ret;
	struct syscall_trace_exit trace;

	ret = trace_seq_printf(s,
			       "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
			       "\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n",
			       SYSCALL_FIELD(int, nr),
			       SYSCALL_FIELD(unsigned long, ret));
	if (!ret)
		return 0;

	return trace_seq_printf(s, "\nprint fmt: \"0x%%lx\", REC->ret\n");
}

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
int syscall_enter_define_fields(struct ftrace_event_call *call)
{
	struct syscall_trace_enter trace;
	struct syscall_metadata *meta;
	int ret;
	int nr;
	int i;
	int offset = offsetof(typeof(trace), args);

	nr = syscall_name_to_nr(call->data);
	meta = syscall_nr_to_meta(nr);

	if (!meta)
		return 0;

	ret = trace_define_common_fields(call);
	if (ret)
		return ret;

	for (i = 0; i < meta->nb_args; i++) {
		ret = trace_define_field(call, meta->types[i],
					 meta->args[i], offset,
					 sizeof(unsigned long), 0);
		offset += sizeof(unsigned long);
	}

	return ret;
}

int syscall_exit_define_fields(struct ftrace_event_call *call)
{
	struct syscall_trace_exit trace;
	int ret;

	ret = trace_define_common_fields(call);
	if (ret)
		return ret;

	ret = trace_define_field(call, SYSCALL_FIELD(unsigned long, ret), 0);

	return ret;
}

211
void ftrace_syscall_enter(struct pt_regs *regs, long id)
212
{
213 214 215 216
	struct syscall_trace_enter *entry;
	struct syscall_metadata *sys_data;
	struct ring_buffer_event *event;
	int size;
217 218 219
	int syscall_nr;

	syscall_nr = syscall_get_nr(current, regs);
220 221
	if (!test_bit(syscall_nr, enabled_enter_syscalls))
		return;
222

223 224 225 226 227 228
	sys_data = syscall_nr_to_meta(syscall_nr);
	if (!sys_data)
		return;

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

229
	event = trace_current_buffer_lock_reserve(sys_data->enter_id, size,
230 231 232 233 234 235 236 237
							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);

238 239
	if (!filter_current_check_discard(sys_data->enter_event, entry, event))
		trace_current_buffer_unlock_commit(event, 0, 0);
240 241
}

242
void ftrace_syscall_exit(struct pt_regs *regs, long ret)
243
{
244 245 246
	struct syscall_trace_exit *entry;
	struct syscall_metadata *sys_data;
	struct ring_buffer_event *event;
247 248 249
	int syscall_nr;

	syscall_nr = syscall_get_nr(current, regs);
250 251
	if (!test_bit(syscall_nr, enabled_exit_syscalls))
		return;
252

253 254 255 256
	sys_data = syscall_nr_to_meta(syscall_nr);
	if (!sys_data)
		return;

257
	event = trace_current_buffer_lock_reserve(sys_data->exit_id,
258 259 260 261 262 263 264 265
				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);

266 267
	if (!filter_current_check_discard(sys_data->exit_event, entry, event))
		trace_current_buffer_unlock_commit(event, 0, 0);
268 269
}

270
int reg_event_syscall_enter(void *ptr)
271
{
272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291
	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;
292 293
}

294
void unreg_event_syscall_enter(void *ptr)
295
{
296 297
	int num;
	char *name;
298

299 300 301 302 303 304 305 306 307 308 309
	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);
}
310

311
int reg_event_syscall_exit(void *ptr)
312
{
313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329
	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++;
330
	}
331 332 333
	mutex_unlock(&syscall_trace_lock);
	return ret;
}
334

335 336 337 338
void unreg_event_syscall_exit(void *ptr)
{
	int num;
	char *name;
339

340 341 342 343 344 345 346 347 348 349
	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);
350
}
351 352 353 354 355 356 357 358

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

struct trace_event event_syscall_exit = {
	.trace			= print_syscall_exit,
};
359 360

#ifdef CONFIG_EVENT_PROFILE
361

362 363 364 365 366 367 368
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)
{
369
	struct syscall_trace_enter *rec;
370 371
	struct syscall_metadata *sys_data;
	int syscall_nr;
372
	int size;
373 374 375 376 377 378 379 380 381

	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;

382 383 384 385 386 387 388 389 390 391 392
	/* 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;

393 394 395 396
		rec = (struct syscall_trace_enter *) raw_data;
		tracing_generic_entry_update(&rec->ent, 0, 0);
		rec->ent.type = sys_data->enter_id;
		rec->nr = syscall_nr;
397 398 399 400
		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);
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
}

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;
445
	struct syscall_trace_exit rec;
446 447 448 449 450 451 452 453 454 455
	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;

456 457 458
	tracing_generic_entry_update(&rec.ent, 0, 0);
	rec.ent.type = sys_data->exit_id;
	rec.nr = syscall_nr;
459 460 461
	rec.ret = syscall_get_return_value(current, regs);

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

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