trace.h 16.1 KB
Newer Older
1 2 3 4 5 6 7
#ifndef _LINUX_KERNEL_TRACE_H
#define _LINUX_KERNEL_TRACE_H

#include <linux/fs.h>
#include <asm/atomic.h>
#include <linux/sched.h>
#include <linux/clocksource.h>
8
#include <linux/ring_buffer.h>
P
Pekka Paalanen 已提交
9
#include <linux/mmiotrace.h>
10
#include <linux/ftrace.h>
11
#include <trace/boot.h>
12

13 14 15 16 17 18
enum trace_type {
	__TRACE_FIRST_TYPE = 0,

	TRACE_FN,
	TRACE_CTX,
	TRACE_WAKE,
19
	TRACE_CONT,
20
	TRACE_STACK,
21
	TRACE_PRINT,
22
	TRACE_SPECIAL,
P
Pekka Paalanen 已提交
23 24
	TRACE_MMIO_RW,
	TRACE_MMIO_MAP,
25
	TRACE_BRANCH,
26 27
	TRACE_BOOT_CALL,
	TRACE_BOOT_RET,
28
	TRACE_FN_RET,
29
	TRACE_USER_STACK,
30 31 32 33

	__TRACE_LAST_TYPE
};

34 35 36 37 38 39 40 41 42 43 44 45
/*
 * The trace entry - the most basic unit of tracing. This is what
 * is printed in the end as a single line in the trace output, such as:
 *
 *     bash-15816 [01]   235.197585: idle_cpu <- irq_enter
 */
struct trace_entry {
	unsigned char		type;
	unsigned char		cpu;
	unsigned char		flags;
	unsigned char		preempt_count;
	int			pid;
46
	int			tgid;
47 48
};

49 50 51 52
/*
 * Function trace entry - function address and parent function addres:
 */
struct ftrace_entry {
53
	struct trace_entry	ent;
54 55 56
	unsigned long		ip;
	unsigned long		parent_ip;
};
57 58 59 60 61 62 63 64

/* Function return entry */
struct ftrace_ret_entry {
	struct trace_entry	ent;
	unsigned long		ip;
	unsigned long		parent_ip;
	unsigned long long	calltime;
	unsigned long long	rettime;
65
	unsigned long		overrun;
66
};
67
extern struct tracer boot_tracer;
68 69 70 71 72

/*
 * Context switch trace entry - which task (and prio) we switched from/to:
 */
struct ctx_switch_entry {
73
	struct trace_entry	ent;
74 75 76 77 78
	unsigned int		prev_pid;
	unsigned char		prev_prio;
	unsigned char		prev_state;
	unsigned int		next_pid;
	unsigned char		next_prio;
P
Peter Zijlstra 已提交
79
	unsigned char		next_state;
80
	unsigned int		next_cpu;
81 82
};

I
Ingo Molnar 已提交
83 84 85 86
/*
 * Special (free-form) trace entry:
 */
struct special_entry {
87
	struct trace_entry	ent;
I
Ingo Molnar 已提交
88 89 90 91 92
	unsigned long		arg1;
	unsigned long		arg2;
	unsigned long		arg3;
};

I
Ingo Molnar 已提交
93 94 95 96
/*
 * Stack-trace entry:
 */

I
Ingo Molnar 已提交
97
#define FTRACE_STACK_ENTRIES	8
I
Ingo Molnar 已提交
98 99

struct stack_entry {
100
	struct trace_entry	ent;
I
Ingo Molnar 已提交
101 102 103
	unsigned long		caller[FTRACE_STACK_ENTRIES];
};

104 105 106 107 108
struct userstack_entry {
	struct trace_entry	ent;
	unsigned long		caller[FTRACE_STACK_ENTRIES];
};

109 110 111 112
/*
 * ftrace_printk entry:
 */
struct print_entry {
113
	struct trace_entry	ent;
114 115 116 117
	unsigned long		ip;
	char			buf[];
};

118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135
#define TRACE_OLD_SIZE		88

struct trace_field_cont {
	unsigned char		type;
	/* Temporary till we get rid of this completely */
	char			buf[TRACE_OLD_SIZE - 1];
};

struct trace_mmiotrace_rw {
	struct trace_entry	ent;
	struct mmiotrace_rw	rw;
};

struct trace_mmiotrace_map {
	struct trace_entry	ent;
	struct mmiotrace_map	map;
};

136
struct trace_boot_call {
137
	struct trace_entry	ent;
138 139 140 141 142 143
	struct boot_trace_call boot_call;
};

struct trace_boot_ret {
	struct trace_entry	ent;
	struct boot_trace_ret boot_ret;
144 145
};

146 147
#define TRACE_FUNC_SIZE 30
#define TRACE_FILE_SIZE 20
148
struct trace_branch {
149 150 151 152 153 154 155
	struct trace_entry	ent;
	unsigned	        line;
	char			func[TRACE_FUNC_SIZE+1];
	char			file[TRACE_FILE_SIZE+1];
	char			correct;
};

156 157 158
/*
 * trace_flag_type is an enumeration that holds different
 * states when a trace occurs. These are:
159 160 161 162 163 164
 *  IRQS_OFF		- interrupts were disabled
 *  IRQS_NOSUPPORT 	- arch does not support irqs_disabled_flags
 *  NEED_RESCED		- reschedule is requested
 *  HARDIRQ		- inside an interrupt handler
 *  SOFTIRQ		- inside a softirq handler
 *  CONT		- multiple entries hold the trace item
165 166 167
 */
enum trace_flag_type {
	TRACE_FLAG_IRQS_OFF		= 0x01,
168 169 170 171 172
	TRACE_FLAG_IRQS_NOSUPPORT	= 0x02,
	TRACE_FLAG_NEED_RESCHED		= 0x04,
	TRACE_FLAG_HARDIRQ		= 0x08,
	TRACE_FLAG_SOFTIRQ		= 0x10,
	TRACE_FLAG_CONT			= 0x20,
173 174
};

175
#define TRACE_BUF_SIZE		1024
176 177 178 179 180 181 182 183

/*
 * The CPU trace array - it consists of thousands of trace entries
 * plus some other descriptor data: (for example which task started
 * the trace, etc.)
 */
struct trace_array_cpu {
	atomic_t		disabled;
I
Ingo Molnar 已提交
184

I
Ingo Molnar 已提交
185 186
	/* these fields get copied into max-trace: */
	unsigned long		trace_idx;
187
	unsigned long		overrun;
188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208
	unsigned long		saved_latency;
	unsigned long		critical_start;
	unsigned long		critical_end;
	unsigned long		critical_sequence;
	unsigned long		nice;
	unsigned long		policy;
	unsigned long		rt_priority;
	cycle_t			preempt_timestamp;
	pid_t			pid;
	uid_t			uid;
	char			comm[TASK_COMM_LEN];
};

struct trace_iterator;

/*
 * The trace array - an array of per-CPU trace arrays. This is the
 * highest level data structure that individual tracers deal with.
 * They have on/off state as well:
 */
struct trace_array {
209
	struct ring_buffer	*buffer;
210 211 212
	unsigned long		entries;
	int			cpu;
	cycle_t			time_start;
213
	struct task_struct	*waiter;
214 215 216
	struct trace_array_cpu	*data[NR_CPUS];
};

S
Steven Rostedt 已提交
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
#define FTRACE_CMP_TYPE(var, type) \
	__builtin_types_compatible_p(typeof(var), type *)

#undef IF_ASSIGN
#define IF_ASSIGN(var, entry, etype, id)		\
	if (FTRACE_CMP_TYPE(var, etype)) {		\
		var = (typeof(var))(entry);		\
		WARN_ON(id && (entry)->type != id);	\
		break;					\
	}

/* Will cause compile errors if type is not found. */
extern void __ftrace_bad_type(void);

/*
 * The trace_assign_type is a verifier that the entry type is
 * the same as the type being assigned. To add new types simply
 * add a line with the following format:
 *
 * IF_ASSIGN(var, ent, type, id);
 *
 *  Where "type" is the trace type that includes the trace_entry
 *  as the "ent" item. And "id" is the trace identifier that is
 *  used in the trace_type enum.
 *
 *  If the type can have more than one id, then use zero.
 */
#define trace_assign_type(var, ent)					\
	do {								\
		IF_ASSIGN(var, ent, struct ftrace_entry, TRACE_FN);	\
		IF_ASSIGN(var, ent, struct ctx_switch_entry, 0);	\
		IF_ASSIGN(var, ent, struct trace_field_cont, TRACE_CONT); \
		IF_ASSIGN(var, ent, struct stack_entry, TRACE_STACK);	\
250
		IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\
S
Steven Rostedt 已提交
251 252 253 254 255 256
		IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT);	\
		IF_ASSIGN(var, ent, struct special_entry, 0);		\
		IF_ASSIGN(var, ent, struct trace_mmiotrace_rw,		\
			  TRACE_MMIO_RW);				\
		IF_ASSIGN(var, ent, struct trace_mmiotrace_map,		\
			  TRACE_MMIO_MAP);				\
257 258
		IF_ASSIGN(var, ent, struct trace_boot_call, TRACE_BOOT_CALL);\
		IF_ASSIGN(var, ent, struct trace_boot_ret, TRACE_BOOT_RET);\
259
		IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \
260
		IF_ASSIGN(var, ent, struct ftrace_ret_entry, TRACE_FN_RET);\
S
Steven Rostedt 已提交
261 262
		__ftrace_bad_type();					\
	} while (0)
263 264 265 266 267 268 269 270

/* Return values for print_line callback */
enum print_line_t {
	TRACE_TYPE_PARTIAL_LINE	= 0,	/* Retry after flushing the seq */
	TRACE_TYPE_HANDLED	= 1,
	TRACE_TYPE_UNHANDLED	= 2	/* Relay to other output functions */
};

271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293

/*
 * An option specific to a tracer. This is a boolean value.
 * The bit is the bit index that sets its value on the
 * flags value in struct tracer_flags.
 */
struct tracer_opt {
	const char 	*name; /* Will appear on the trace_options file */
	u32 		bit; /* Mask assigned in val field in tracer_flags */
};

/*
 * The set of specific options for a tracer. Your tracer
 * have to set the initial value of the flags val.
 */
struct tracer_flags {
	u32			val;
	struct tracer_opt 	*opts;
};

/* Makes more easy to define a tracer opt */
#define TRACER_OPT(s, b)	.name = #s, .bit = b

294 295 296 297 298
/*
 * A specific tracer, represented by methods that operate on a trace array:
 */
struct tracer {
	const char		*name;
299 300
	/* Your tracer should raise a warning if init fails */
	int			(*init)(struct trace_array *tr);
301
	void			(*reset)(struct trace_array *tr);
302 303
	void			(*start)(struct trace_array *tr);
	void			(*stop)(struct trace_array *tr);
304
	void			(*open)(struct trace_iterator *iter);
305
	void			(*pipe_open)(struct trace_iterator *iter);
306
	void			(*close)(struct trace_iterator *iter);
307 308 309
	ssize_t			(*read)(struct trace_iterator *iter,
					struct file *filp, char __user *ubuf,
					size_t cnt, loff_t *ppos);
S
Steven Rostedt 已提交
310 311 312 313
#ifdef CONFIG_FTRACE_STARTUP_TEST
	int			(*selftest)(struct tracer *trace,
					    struct trace_array *tr);
#endif
314
	enum print_line_t	(*print_line)(struct trace_iterator *iter);
315 316
	/* If you handled the flag setting, return 0 */
	int			(*set_flag)(u32 old_flags, u32 bit, int set);
317 318
	struct tracer		*next;
	int			print_max;
319
	struct tracer_flags 	*flags;
320 321
};

S
Steven Rostedt 已提交
322 323 324
struct trace_seq {
	unsigned char		buffer[PAGE_SIZE];
	unsigned int		len;
325
	unsigned int		readpos;
S
Steven Rostedt 已提交
326 327
};

328 329 330 331 332 333 334
/*
 * Trace iterator - used by printout routines who present trace
 * results to users and which routines might sleep, etc:
 */
struct trace_iterator {
	struct trace_array	*tr;
	struct tracer		*trace;
335
	void			*private;
336
	struct ring_buffer_iter	*buffer_iter[NR_CPUS];
I
Ingo Molnar 已提交
337

338 339
	/* The below is zeroed out in pipe_read */
	struct trace_seq	seq;
340
	struct trace_entry	*ent;
I
Ingo Molnar 已提交
341
	int			cpu;
342
	u64			ts;
I
Ingo Molnar 已提交
343

344 345
	unsigned long		iter_flags;
	loff_t			pos;
346
	long			idx;
347 348

	cpumask_t		started;
349 350
};

351
int tracing_is_enabled(void);
352
void trace_wake_up(void);
353
void tracing_reset(struct trace_array *tr, int cpu);
354 355
int tracing_open_generic(struct inode *inode, struct file *filp);
struct dentry *tracing_init_dentry(void);
I
Ingo Molnar 已提交
356 357
void init_tracer_sysprof_debugfs(struct dentry *d_tracer);

358 359 360
struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
						struct trace_array_cpu *data);
void tracing_generic_entry_update(struct trace_entry *entry,
361 362
				  unsigned long flags,
				  int pc);
363

364 365 366 367
void ftrace(struct trace_array *tr,
			    struct trace_array_cpu *data,
			    unsigned long ip,
			    unsigned long parent_ip,
368
			    unsigned long flags, int pc);
369 370 371 372
void tracing_sched_switch_trace(struct trace_array *tr,
				struct trace_array_cpu *data,
				struct task_struct *prev,
				struct task_struct *next,
373
				unsigned long flags, int pc);
374
void tracing_record_cmdline(struct task_struct *tsk);
375 376 377 378 379

void tracing_sched_wakeup_trace(struct trace_array *tr,
				struct trace_array_cpu *data,
				struct task_struct *wakee,
				struct task_struct *cur,
380
				unsigned long flags, int pc);
I
Ingo Molnar 已提交
381 382 383 384
void trace_special(struct trace_array *tr,
		   struct trace_array_cpu *data,
		   unsigned long arg1,
		   unsigned long arg2,
385
		   unsigned long arg3, int pc);
386 387 388 389
void trace_function(struct trace_array *tr,
		    struct trace_array_cpu *data,
		    unsigned long ip,
		    unsigned long parent_ip,
390
		    unsigned long flags, int pc);
391 392
void
trace_function_return(struct ftrace_retfunc *trace);
393

394 395
void tracing_start_cmdline_record(void);
void tracing_stop_cmdline_record(void);
S
Steven Rostedt 已提交
396 397 398
void tracing_sched_switch_assign_trace(struct trace_array *tr);
void tracing_stop_sched_switch_record(void);
void tracing_start_sched_switch_record(void);
399 400 401 402 403 404 405 406 407 408 409 410
int register_tracer(struct tracer *type);
void unregister_tracer(struct tracer *type);

extern unsigned long nsecs_to_usecs(unsigned long nsecs);

extern unsigned long tracing_max_latency;
extern unsigned long tracing_thresh;

void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
void update_max_tr_single(struct trace_array *tr,
			  struct task_struct *tsk, int cpu);

I
Ingo Molnar 已提交
411
extern cycle_t ftrace_now(int cpu);
412

413
#ifdef CONFIG_FUNCTION_TRACER
414 415 416 417 418 419 420
void tracing_start_function_trace(void);
void tracing_stop_function_trace(void);
#else
# define tracing_start_function_trace()		do { } while (0)
# define tracing_stop_function_trace()		do { } while (0)
#endif

421 422 423
#ifdef CONFIG_CONTEXT_SWITCH_TRACER
typedef void
(*tracer_switch_func_t)(void *private,
M
Mathieu Desnoyers 已提交
424
			void *__rq,
425 426 427 428 429 430 431 432 433 434 435 436 437
			struct task_struct *prev,
			struct task_struct *next);

struct tracer_switch_ops {
	tracer_switch_func_t		func;
	void				*private;
	struct tracer_switch_ops	*next;
};

#endif /* CONFIG_CONTEXT_SWITCH_TRACER */

#ifdef CONFIG_DYNAMIC_FTRACE
extern unsigned long ftrace_update_tot_cnt;
438 439
#define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func
extern int DYN_FTRACE_TEST_NAME(void);
440 441
#endif

S
Steven Rostedt 已提交
442 443 444 445 446 447 448 449 450 451 452
#ifdef CONFIG_FTRACE_STARTUP_TEST
extern int trace_selftest_startup_function(struct tracer *trace,
					   struct trace_array *tr);
extern int trace_selftest_startup_irqsoff(struct tracer *trace,
					  struct trace_array *tr);
extern int trace_selftest_startup_preemptoff(struct tracer *trace,
					     struct trace_array *tr);
extern int trace_selftest_startup_preemptirqsoff(struct tracer *trace,
						 struct trace_array *tr);
extern int trace_selftest_startup_wakeup(struct tracer *trace,
					 struct trace_array *tr);
S
Steven Noonan 已提交
453 454
extern int trace_selftest_startup_nop(struct tracer *trace,
					 struct trace_array *tr);
S
Steven Rostedt 已提交
455 456
extern int trace_selftest_startup_sched_switch(struct tracer *trace,
					       struct trace_array *tr);
457 458
extern int trace_selftest_startup_sysprof(struct tracer *trace,
					       struct trace_array *tr);
S
Steven Rostedt 已提交
459 460
extern int trace_selftest_startup_branch(struct tracer *trace,
					 struct trace_array *tr);
S
Steven Rostedt 已提交
461 462
#endif /* CONFIG_FTRACE_STARTUP_TEST */

I
Ingo Molnar 已提交
463
extern void *head_page(struct trace_array_cpu *data);
464
extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...);
465 466
extern void trace_seq_print_cont(struct trace_seq *s,
				 struct trace_iterator *iter);
467 468 469 470

extern int
seq_print_ip_sym(struct trace_seq *s, unsigned long ip,
		unsigned long sym_flags);
471 472
extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
				 size_t cnt);
473
extern long ns2usecs(cycle_t nsec);
P
Pekka Paalanen 已提交
474
extern int trace_vprintk(unsigned long ip, const char *fmt, va_list args);
I
Ingo Molnar 已提交
475

476 477
extern unsigned long trace_flags;

478 479 480 481 482 483 484 485 486 487 488
/* Standard output formatting function used for function return traces */
#ifdef CONFIG_FUNCTION_RET_TRACER
extern enum print_line_t print_return_function(struct trace_iterator *iter);
#else
static inline enum print_line_t
print_return_function(struct trace_iterator *iter)
{
	return TRACE_TYPE_UNHANDLED;
}
#endif

S
Steven Rostedt 已提交
489 490 491 492 493 494 495
/*
 * trace_iterator_flags is an enumeration that defines bit
 * positions into trace_flags that controls the output.
 *
 * NOTE: These bits must match the trace_options array in
 *       trace.c.
 */
496 497 498 499 500 501 502 503 504 505
enum trace_iterator_flags {
	TRACE_ITER_PRINT_PARENT		= 0x01,
	TRACE_ITER_SYM_OFFSET		= 0x02,
	TRACE_ITER_SYM_ADDR		= 0x04,
	TRACE_ITER_VERBOSE		= 0x08,
	TRACE_ITER_RAW			= 0x10,
	TRACE_ITER_HEX			= 0x20,
	TRACE_ITER_BIN			= 0x40,
	TRACE_ITER_BLOCK		= 0x80,
	TRACE_ITER_STACKTRACE		= 0x100,
I
Ingo Molnar 已提交
506
	TRACE_ITER_SCHED_TREE		= 0x200,
507
	TRACE_ITER_PRINTK		= 0x400,
508
	TRACE_ITER_PREEMPTONLY		= 0x800,
509
	TRACE_ITER_BRANCH		= 0x1000,
510
	TRACE_ITER_ANNOTATE		= 0x2000,
511
	TRACE_ITER_USERSTACKTRACE       = 0x4000
512 513
};

514 515 516 517 518 519 520
/*
 * TRACE_ITER_SYM_MASK masks the options in trace_flags that
 * control the output of kernel symbols.
 */
#define TRACE_ITER_SYM_MASK \
	(TRACE_ITER_PRINT_PARENT|TRACE_ITER_SYM_OFFSET|TRACE_ITER_SYM_ADDR)

521 522
extern struct tracer nop_trace;

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
/**
 * ftrace_preempt_disable - disable preemption scheduler safe
 *
 * When tracing can happen inside the scheduler, there exists
 * cases that the tracing might happen before the need_resched
 * flag is checked. If this happens and the tracer calls
 * preempt_enable (after a disable), a schedule might take place
 * causing an infinite recursion.
 *
 * To prevent this, we read the need_recshed flag before
 * disabling preemption. When we want to enable preemption we
 * check the flag, if it is set, then we call preempt_enable_no_resched.
 * Otherwise, we call preempt_enable.
 *
 * The rational for doing the above is that if need resched is set
 * and we have yet to reschedule, we are either in an atomic location
 * (where we do not need to check for scheduling) or we are inside
 * the scheduler and do not want to resched.
 */
static inline int ftrace_preempt_disable(void)
{
	int resched;

	resched = need_resched();
	preempt_disable_notrace();

	return resched;
}

/**
 * ftrace_preempt_enable - enable preemption scheduler safe
 * @resched: the return value from ftrace_preempt_disable
 *
 * This is a scheduler safe way to enable preemption and not miss
 * any preemption checks. The disabled saved the state of preemption.
 * If resched is set, then we were either inside an atomic or
 * are inside the scheduler (we would have already scheduled
 * otherwise). In this case, we do not want to call normal
 * preempt_enable, but preempt_enable_no_resched instead.
 */
static inline void ftrace_preempt_enable(int resched)
{
	if (resched)
		preempt_enable_no_resched_notrace();
	else
		preempt_enable_notrace();
}

571
#ifdef CONFIG_BRANCH_TRACER
572 573 574
extern int enable_branch_tracing(struct trace_array *tr);
extern void disable_branch_tracing(void);
static inline int trace_branch_enable(struct trace_array *tr)
575
{
576 577
	if (trace_flags & TRACE_ITER_BRANCH)
		return enable_branch_tracing(tr);
578 579
	return 0;
}
580
static inline void trace_branch_disable(void)
581 582
{
	/* due to races, always disable */
583
	disable_branch_tracing();
584 585
}
#else
586
static inline int trace_branch_enable(struct trace_array *tr)
587 588 589
{
	return 0;
}
590
static inline void trace_branch_disable(void)
591 592
{
}
593
#endif /* CONFIG_BRANCH_TRACER */
594

595
#endif /* _LINUX_KERNEL_TRACE_H */