trace.h 30.1 KB
Newer Older
1 2 3 4
#ifndef _LINUX_KERNEL_TRACE_H
#define _LINUX_KERNEL_TRACE_H

#include <linux/fs.h>
A
Arun Sharma 已提交
5
#include <linux/atomic.h>
6 7
#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/tracepoint.h>
11
#include <linux/ftrace.h>
12
#include <linux/hw_breakpoint.h>
13
#include <linux/trace_seq.h>
14
#include <linux/ftrace_event.h>
15

16 17 18 19 20
#ifdef CONFIG_FTRACE_SYSCALLS
#include <asm/unistd.h>		/* For NR_SYSCALLS	     */
#include <asm/syscall.h>	/* some archs define it here */
#endif

21 22 23 24 25 26 27
enum trace_type {
	__TRACE_FIRST_TYPE = 0,

	TRACE_FN,
	TRACE_CTX,
	TRACE_WAKE,
	TRACE_STACK,
28
	TRACE_PRINT,
29
	TRACE_BPRINT,
P
Pekka Paalanen 已提交
30 31
	TRACE_MMIO_RW,
	TRACE_MMIO_MAP,
32
	TRACE_BRANCH,
33 34
	TRACE_GRAPH_RET,
	TRACE_GRAPH_ENT,
35
	TRACE_USER_STACK,
36
	TRACE_BLK,
37
	TRACE_BPUTS,
38

39
	__TRACE_LAST_TYPE,
40 41
};

42

43 44
#undef __field
#define __field(type, item)		type	item;
I
Ingo Molnar 已提交
45

46 47
#undef __field_struct
#define __field_struct(type, item)	__field(type, item)
I
Ingo Molnar 已提交
48

49 50
#undef __field_desc
#define __field_desc(type, container, item)
51

52 53
#undef __array
#define __array(type, item, size)	type	item[size];
54

55 56
#undef __array_desc
#define __array_desc(type, container, item, size)
57

58 59
#undef __dynamic_array
#define __dynamic_array(type, item)	type	item[];
60

61 62
#undef F_STRUCT
#define F_STRUCT(args...)		args
63

64
#undef FTRACE_ENTRY
65 66 67 68
#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter)	\
	struct struct_name {						\
		struct trace_entry	ent;				\
		tstruct							\
69
	}
70

71 72
#undef TP_ARGS
#define TP_ARGS(args...)	args
73

74
#undef FTRACE_ENTRY_DUP
75
#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk, filter)
76

77
#undef FTRACE_ENTRY_REG
78 79 80 81
#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print,	\
			 filter, regfn) \
	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
		     filter)
82

83
#include "trace_entries.h"
84

85 86 87 88
/*
 * syscalls are special, and need special handling, this is why
 * they are not included in trace_entries.h
 */
89 90 91 92 93 94 95 96 97
struct syscall_trace_enter {
	struct trace_entry	ent;
	int			nr;
	unsigned long		args[];
};

struct syscall_trace_exit {
	struct trace_entry	ent;
	int			nr;
98
	long			ret;
99 100
};

101
struct kprobe_trace_entry_head {
102 103 104 105
	struct trace_entry	ent;
	unsigned long		ip;
};

106
struct kretprobe_trace_entry_head {
107 108 109 110 111
	struct trace_entry	ent;
	unsigned long		func;
	unsigned long		ret_ip;
};

112 113 114
/*
 * trace_flag_type is an enumeration that holds different
 * states when a trace occurs. These are:
115
 *  IRQS_OFF		- interrupts were disabled
I
Ingo Molnar 已提交
116
 *  IRQS_NOSUPPORT	- arch does not support irqs_disabled_flags
L
Li Zefan 已提交
117
 *  NEED_RESCHED	- reschedule is requested
118 119
 *  HARDIRQ		- inside an interrupt handler
 *  SOFTIRQ		- inside a softirq handler
120 121 122
 */
enum trace_flag_type {
	TRACE_FLAG_IRQS_OFF		= 0x01,
123 124 125 126
	TRACE_FLAG_IRQS_NOSUPPORT	= 0x02,
	TRACE_FLAG_NEED_RESCHED		= 0x04,
	TRACE_FLAG_HARDIRQ		= 0x08,
	TRACE_FLAG_SOFTIRQ		= 0x10,
127 128
};

129
#define TRACE_BUF_SIZE		1024
130

131 132 133 134 135 136 137 138
struct trace_array;

struct trace_cpu {
	struct trace_array	*tr;
	struct dentry		*dir;
	int			cpu;
};

139 140 141 142 143 144
/*
 * 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 {
145
	struct trace_cpu	trace_cpu;
146
	atomic_t		disabled;
147
	void			*buffer_page;	/* ring buffer spare */
I
Ingo Molnar 已提交
148

149
	unsigned long		entries;
150 151 152 153 154 155 156
	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;
157
	unsigned long		skipped_entries;
158 159
	cycle_t			preempt_timestamp;
	pid_t			pid;
160
	kuid_t			uid;
161 162 163
	char			comm[TASK_COMM_LEN];
};

164 165
struct tracer;

166 167 168 169 170 171 172 173
struct trace_buffer {
	struct trace_array		*tr;
	struct ring_buffer		*buffer;
	struct trace_array_cpu __percpu	*data;
	cycle_t				time_start;
	int				cpu;
};

174 175 176 177 178 179
/*
 * 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 {
180
	struct list_head	list;
181
	char			*name;
182 183 184 185 186 187 188 189 190 191 192 193 194 195
	struct trace_buffer	trace_buffer;
#ifdef CONFIG_TRACER_MAX_TRACE
	/*
	 * The max_buffer is used to snapshot the trace when a maximum
	 * latency is reached, or when the user initiates a snapshot.
	 * Some tracers will use this to store a maximum trace while
	 * it continues examining live traces.
	 *
	 * The buffers for the max_buffer are set up the same as the trace_buffer
	 * When a snapshot is taken, the buffer of the max_buffer is swapped
	 * with the buffer of the trace_buffer and the buffers are reset for
	 * the trace_buffer so the tracing can continue.
	 */
	struct trace_buffer	max_buffer;
196
	bool			allocated_snapshot;
197
#endif
198
	int			buffer_disabled;
199
	struct trace_cpu	trace_cpu;	/* place holder */
200 201 202 203 204 205
#ifdef CONFIG_FTRACE_SYSCALLS
	int			sys_refcount_enter;
	int			sys_refcount_exit;
	DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
	DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
#endif
206 207 208
	int			stop_count;
	int			clock_id;
	struct tracer		*current_trace;
209
	unsigned int		flags;
210
	raw_spinlock_t		start_lock;
211
	struct dentry		*dir;
212 213
	struct dentry		*options;
	struct dentry		*percpu_dir;
214 215 216
	struct dentry		*event_dir;
	struct list_head	systems;
	struct list_head	events;
217
	struct task_struct	*waiter;
218
	int			ref;
219 220
};

221 222 223 224 225 226
enum {
	TRACE_ARRAY_FL_GLOBAL	= (1 << 0)
};

extern struct list_head ftrace_trace_arrays;

227 228
extern struct mutex trace_types_lock;

229 230 231
extern int trace_array_get(struct trace_array *tr);
extern void trace_array_put(struct trace_array *tr);

232 233 234 235 236 237 238 239 240 241 242 243 244 245
/*
 * The global tracer (top) should be the first trace array added,
 * but we check the flag anyway.
 */
static inline struct trace_array *top_trace_array(void)
{
	struct trace_array *tr;

	tr = list_entry(ftrace_trace_arrays.prev,
			typeof(*tr), list);
	WARN_ON(!(tr->flags & TRACE_ARRAY_FL_GLOBAL));
	return tr;
}

S
Steven Rostedt 已提交
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
#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 stack_entry, TRACE_STACK);	\
278
		IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\
S
Steven Rostedt 已提交
279
		IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT);	\
280
		IF_ASSIGN(var, ent, struct bprint_entry, TRACE_BPRINT);	\
281
		IF_ASSIGN(var, ent, struct bputs_entry, TRACE_BPUTS);	\
S
Steven Rostedt 已提交
282 283 284 285
		IF_ASSIGN(var, ent, struct trace_mmiotrace_rw,		\
			  TRACE_MMIO_RW);				\
		IF_ASSIGN(var, ent, struct trace_mmiotrace_map,		\
			  TRACE_MMIO_MAP);				\
286
		IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \
287 288 289 290
		IF_ASSIGN(var, ent, struct ftrace_graph_ent_entry,	\
			  TRACE_GRAPH_ENT);		\
		IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry,	\
			  TRACE_GRAPH_RET);		\
S
Steven Rostedt 已提交
291 292
		__ftrace_bad_type();					\
	} while (0)
293

294 295 296 297 298 299
/*
 * 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 {
I
Ingo Molnar 已提交
300 301
	const char	*name; /* Will appear on the trace_options file */
	u32		bit; /* Mask assigned in val field in tracer_flags */
302 303 304 305 306 307 308 309
};

/*
 * 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;
I
Ingo Molnar 已提交
310
	struct tracer_opt	*opts;
311 312 313 314 315
};

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

316

317 318 319 320 321 322 323 324 325 326 327
/**
 * struct tracer - a specific tracer and its callbacks to interact with debugfs
 * @name: the name chosen to select it on the available_tracers file
 * @init: called when one switches to this tracer (echo name > current_tracer)
 * @reset: called when one switches to another tracer
 * @start: called when tracing is unpaused (echo 1 > tracing_enabled)
 * @stop: called when tracing is paused (echo 0 > tracing_enabled)
 * @open: called when the trace file is opened
 * @pipe_open: called when the trace_pipe file is opened
 * @wait_pipe: override how the user waits for traces on trace_pipe
 * @close: called when the trace file is released
S
Steven Rostedt 已提交
328
 * @pipe_close: called when the trace_pipe file is released
329 330 331 332 333 334 335
 * @read: override the default read callback on trace_pipe
 * @splice_read: override the default splice_read callback on trace_pipe
 * @selftest: selftest to run on boot (see trace_selftest.c)
 * @print_headers: override the first lines that describe your columns
 * @print_line: callback that prints a trace
 * @set_flag: signals one of your private flags changed (trace_options file)
 * @flags: your private flags
336 337 338
 */
struct tracer {
	const char		*name;
339
	int			(*init)(struct trace_array *tr);
340
	void			(*reset)(struct trace_array *tr);
341 342
	void			(*start)(struct trace_array *tr);
	void			(*stop)(struct trace_array *tr);
343
	void			(*open)(struct trace_iterator *iter);
344
	void			(*pipe_open)(struct trace_iterator *iter);
345
	void			(*wait_pipe)(struct trace_iterator *iter);
346
	void			(*close)(struct trace_iterator *iter);
S
Steven Rostedt 已提交
347
	void			(*pipe_close)(struct trace_iterator *iter);
348 349 350
	ssize_t			(*read)(struct trace_iterator *iter,
					struct file *filp, char __user *ubuf,
					size_t cnt, loff_t *ppos);
351 352 353 354 355 356
	ssize_t			(*splice_read)(struct trace_iterator *iter,
					       struct file *filp,
					       loff_t *ppos,
					       struct pipe_inode_info *pipe,
					       size_t len,
					       unsigned int flags);
S
Steven Rostedt 已提交
357 358 359 360
#ifdef CONFIG_FTRACE_STARTUP_TEST
	int			(*selftest)(struct tracer *trace,
					    struct trace_array *tr);
#endif
361
	void			(*print_header)(struct seq_file *m);
362
	enum print_line_t	(*print_line)(struct trace_iterator *iter);
363 364
	/* If you handled the flag setting, return 0 */
	int			(*set_flag)(u32 old_flags, u32 bit, int set);
365 366 367
	/* Return 0 if OK with change, else return non-zero */
	int			(*flag_changed)(struct tracer *tracer,
						u32 mask, int set);
368
	struct tracer		*next;
I
Ingo Molnar 已提交
369
	struct tracer_flags	*flags;
370
	bool			print_max;
371 372
	bool			enabled;
#ifdef CONFIG_TRACER_MAX_TRACE
373
	bool			use_max_tr;
374
#endif
375 376
};

377

378 379
/* Only current can touch trace_recursion */

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
/*
 * For function tracing recursion:
 *  The order of these bits are important.
 *
 *  When function tracing occurs, the following steps are made:
 *   If arch does not support a ftrace feature:
 *    call internal function (uses INTERNAL bits) which calls...
 *   If callback is registered to the "global" list, the list
 *    function is called and recursion checks the GLOBAL bits.
 *    then this function calls...
 *   The function callback, which can use the FTRACE bits to
 *    check for recursion.
 *
 * Now if the arch does not suppport a feature, and it calls
 * the global list function which calls the ftrace callback
 * all three of these steps will do a recursion protection.
 * There's no reason to do one if the previous caller already
 * did. The recursion that we are protecting against will
 * go through the same steps again.
 *
 * To prevent the multiple recursion checks, if a recursion
 * bit is set that is higher than the MAX bit of the current
 * check, then we know that the check was made by the previous
 * caller, and we can skip the current check.
 */
405
enum {
406 407 408 409 410 411 412
	TRACE_BUFFER_BIT,
	TRACE_BUFFER_NMI_BIT,
	TRACE_BUFFER_IRQ_BIT,
	TRACE_BUFFER_SIRQ_BIT,

	/* Start of function recursion bits */
	TRACE_FTRACE_BIT,
413 414 415
	TRACE_FTRACE_NMI_BIT,
	TRACE_FTRACE_IRQ_BIT,
	TRACE_FTRACE_SIRQ_BIT,
416

417
	/* GLOBAL_BITs must be greater than FTRACE_BITs */
418 419 420 421 422
	TRACE_GLOBAL_BIT,
	TRACE_GLOBAL_NMI_BIT,
	TRACE_GLOBAL_IRQ_BIT,
	TRACE_GLOBAL_SIRQ_BIT,

423 424 425 426 427 428
	/* INTERNAL_BITs must be greater than GLOBAL_BITs */
	TRACE_INTERNAL_BIT,
	TRACE_INTERNAL_NMI_BIT,
	TRACE_INTERNAL_IRQ_BIT,
	TRACE_INTERNAL_SIRQ_BIT,

429
	TRACE_CONTROL_BIT,
430

431 432 433 434 435 436 437
/*
 * Abuse of the trace_recursion.
 * As we need a way to maintain state if we are tracing the function
 * graph in irq because we want to trace a particular function that
 * was called in irq context but we have irq tracing off. Since this
 * can only be modified by current, we can reuse trace_recursion.
 */
438 439
	TRACE_IRQ_BIT,
};
440

441 442 443
#define trace_recursion_set(bit)	do { (current)->trace_recursion |= (1<<(bit)); } while (0)
#define trace_recursion_clear(bit)	do { (current)->trace_recursion &= ~(1<<(bit)); } while (0)
#define trace_recursion_test(bit)	((current)->trace_recursion & (1<<(bit)))
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
#define TRACE_CONTEXT_BITS	4

#define TRACE_FTRACE_START	TRACE_FTRACE_BIT
#define TRACE_FTRACE_MAX	((1 << (TRACE_FTRACE_START + TRACE_CONTEXT_BITS)) - 1)

#define TRACE_GLOBAL_START	TRACE_GLOBAL_BIT
#define TRACE_GLOBAL_MAX	((1 << (TRACE_GLOBAL_START + TRACE_CONTEXT_BITS)) - 1)

#define TRACE_LIST_START	TRACE_INTERNAL_BIT
#define TRACE_LIST_MAX		((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1)

#define TRACE_CONTEXT_MASK	TRACE_LIST_MAX

static __always_inline int trace_get_context_bit(void)
{
	int bit;

	if (in_interrupt()) {
		if (in_nmi())
			bit = 0;

		else if (in_irq())
			bit = 1;
		else
			bit = 2;
	} else
		bit = 3;

	return bit;
}

static __always_inline int trace_test_and_set_recursion(int start, int max)
{
	unsigned int val = current->trace_recursion;
	int bit;

	/* A previous recursion check was made */
	if ((val & TRACE_CONTEXT_MASK) > max)
		return 0;

	bit = trace_get_context_bit() + start;
	if (unlikely(val & (1 << bit)))
		return -1;

	val |= 1 << bit;
	current->trace_recursion = val;
	barrier();

	return bit;
}

static __always_inline void trace_clear_recursion(int bit)
{
	unsigned int val = current->trace_recursion;

	if (!bit)
		return;

	bit = 1 << bit;
	val &= ~bit;

	barrier();
	current->trace_recursion = val;
}

510 511 512 513 514 515 516 517
static inline struct ring_buffer_iter *
trace_buffer_iter(struct trace_iterator *iter, int cpu)
{
	if (iter->buffer_iter && iter->buffer_iter[cpu])
		return iter->buffer_iter[cpu];
	return NULL;
}

518
int tracer_init(struct tracer *t, struct trace_array *tr);
519
int tracing_is_enabled(void);
520 521
void tracing_reset(struct trace_buffer *buf, int cpu);
void tracing_reset_online_cpus(struct trace_buffer *buf);
522
void tracing_reset_current(int cpu);
523
void tracing_reset_all_online_cpus(void);
524
int tracing_open_generic(struct inode *inode, struct file *filp);
525
struct dentry *trace_create_file(const char *name,
A
Al Viro 已提交
526
				 umode_t mode,
527 528 529 530
				 struct dentry *parent,
				 void *data,
				 const struct file_operations *fops);

531
struct dentry *tracing_init_dentry_tr(struct trace_array *tr);
532
struct dentry *tracing_init_dentry(void);
I
Ingo Molnar 已提交
533

534 535
struct ring_buffer_event;

536 537 538 539 540 541
struct ring_buffer_event *
trace_buffer_lock_reserve(struct ring_buffer *buffer,
			  int type,
			  unsigned long len,
			  unsigned long flags,
			  int pc);
542

543 544
struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
						struct trace_array_cpu *data);
545 546 547 548

struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
					  int *ent_cpu, u64 *ent_ts);

549 550 551
void __buffer_unlock_commit(struct ring_buffer *buffer,
			    struct ring_buffer_event *event);

552 553 554 555 556 557 558 559
int trace_empty(struct trace_iterator *iter);

void *trace_find_next_entry_inc(struct trace_iterator *iter);

void trace_init_global_iter(struct trace_iterator *iter);

void tracing_iter_reset(struct trace_iterator *iter, int cpu);

560 561
void poll_wait_pipe(struct trace_iterator *iter);

562 563 564
void tracing_sched_switch_trace(struct trace_array *tr,
				struct task_struct *prev,
				struct task_struct *next,
565
				unsigned long flags, int pc);
566 567 568 569

void tracing_sched_wakeup_trace(struct trace_array *tr,
				struct task_struct *wakee,
				struct task_struct *cur,
570
				unsigned long flags, int pc);
571 572 573
void trace_function(struct trace_array *tr,
		    unsigned long ip,
		    unsigned long parent_ip,
574
		    unsigned long flags, int pc);
575 576 577 578
void trace_graph_function(struct trace_array *tr,
		    unsigned long ip,
		    unsigned long parent_ip,
		    unsigned long flags, int pc);
579
void trace_latency_header(struct seq_file *m);
580 581 582
void trace_default_header(struct seq_file *m);
void print_trace_header(struct seq_file *m, struct trace_iterator *iter);
int trace_empty(struct trace_iterator *iter);
583

584
void trace_graph_return(struct ftrace_graph_ret *trace);
585
int trace_graph_entry(struct ftrace_graph_ent *trace);
586
void set_graph_array(struct trace_array *tr);
587

588 589
void tracing_start_cmdline_record(void);
void tracing_stop_cmdline_record(void);
S
Steven Rostedt 已提交
590 591 592
void tracing_sched_switch_assign_trace(struct trace_array *tr);
void tracing_stop_sched_switch_record(void);
void tracing_start_sched_switch_record(void);
593
int register_tracer(struct tracer *type);
594
int is_tracing_stopped(void);
595 596 597 598 599

extern cpumask_var_t __read_mostly tracing_buffer_mask;

#define for_each_tracing_cpu(cpu)	\
	for_each_cpu(cpu, tracing_buffer_mask)
600 601 602

extern unsigned long nsecs_to_usecs(unsigned long nsecs);

603 604
extern unsigned long tracing_thresh;

605
#ifdef CONFIG_TRACER_MAX_TRACE
606 607 608 609 610
extern unsigned long tracing_max_latency;

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);
611
#endif /* CONFIG_TRACER_MAX_TRACE */
612

613
#ifdef CONFIG_STACKTRACE
614
void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
615 616
			int skip, int pc);

617 618 619
void ftrace_trace_stack_regs(struct ring_buffer *buffer, unsigned long flags,
			     int skip, int pc, struct pt_regs *regs);

620
void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags,
621 622 623 624 625
			    int pc);

void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
		   int pc);
#else
626
static inline void ftrace_trace_stack(struct ring_buffer *buffer,
627 628 629 630
				      unsigned long flags, int skip, int pc)
{
}

631 632 633 634 635 636
static inline void ftrace_trace_stack_regs(struct ring_buffer *buffer,
					   unsigned long flags, int skip,
					   int pc, struct pt_regs *regs)
{
}

637
static inline void ftrace_trace_userstack(struct ring_buffer *buffer,
638 639 640 641 642 643 644 645 646
					  unsigned long flags, int pc)
{
}

static inline void __trace_stack(struct trace_array *tr, unsigned long flags,
				 int skip, int pc)
{
}
#endif /* CONFIG_STACKTRACE */
647

I
Ingo Molnar 已提交
648
extern cycle_t ftrace_now(int cpu);
649

650
extern void trace_find_cmdline(int pid, char comm[]);
651

652 653
#ifdef CONFIG_DYNAMIC_FTRACE
extern unsigned long ftrace_update_tot_cnt;
654
#endif
655 656
#define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func
extern int DYN_FTRACE_TEST_NAME(void);
657 658
#define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2
extern int DYN_FTRACE_TEST_NAME2(void);
659

660
extern bool ring_buffer_expanded;
661
extern bool tracing_selftest_disabled;
662
DECLARE_PER_CPU(int, ftrace_cpu_disabled);
663

S
Steven Rostedt 已提交
664 665 666
#ifdef CONFIG_FTRACE_STARTUP_TEST
extern int trace_selftest_startup_function(struct tracer *trace,
					   struct trace_array *tr);
667 668
extern int trace_selftest_startup_function_graph(struct tracer *trace,
						 struct trace_array *tr);
S
Steven Rostedt 已提交
669 670 671 672 673 674 675 676
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
677 678
extern int trace_selftest_startup_nop(struct tracer *trace,
					 struct trace_array *tr);
S
Steven Rostedt 已提交
679 680
extern int trace_selftest_startup_sched_switch(struct tracer *trace,
					       struct trace_array *tr);
S
Steven Rostedt 已提交
681 682
extern int trace_selftest_startup_branch(struct tracer *trace,
					 struct trace_array *tr);
683 684 685 686 687 688 689 690 691
/*
 * Tracer data references selftest functions that only occur
 * on boot up. These can be __init functions. Thus, when selftests
 * are enabled, then the tracers need to reference __init functions.
 */
#define __tracer_data		__refdata
#else
/* Tracers are seldom changed. Optimize when selftests are disabled. */
#define __tracer_data		__read_mostly
S
Steven Rostedt 已提交
692 693
#endif /* CONFIG_FTRACE_STARTUP_TEST */

I
Ingo Molnar 已提交
694
extern void *head_page(struct trace_array_cpu *data);
695
extern unsigned long long ns2usecs(cycle_t nsec);
696
extern int
697
trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
698
extern int
699
trace_vprintk(unsigned long ip, const char *fmt, va_list args);
700 701 702 703 704
extern int
trace_array_vprintk(struct trace_array *tr,
		    unsigned long ip, const char *fmt, va_list args);
int trace_array_printk(struct trace_array *tr,
		       unsigned long ip, const char *fmt, ...);
705 706
int trace_array_printk_buf(struct ring_buffer *buffer,
			   unsigned long ip, const char *fmt, ...);
707 708
void trace_printk_seq(struct trace_seq *s);
enum print_line_t print_trace_line(struct trace_iterator *iter);
I
Ingo Molnar 已提交
709

710 711
extern unsigned long trace_flags;

712
/* Standard output formatting function used for function return traces */
713
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
714 715 716 717 718 719 720 721 722

/* Flag options */
#define TRACE_GRAPH_PRINT_OVERRUN       0x1
#define TRACE_GRAPH_PRINT_CPU           0x2
#define TRACE_GRAPH_PRINT_OVERHEAD      0x4
#define TRACE_GRAPH_PRINT_PROC          0x8
#define TRACE_GRAPH_PRINT_DURATION      0x10
#define TRACE_GRAPH_PRINT_ABS_TIME      0x20

723 724 725
extern enum print_line_t
print_graph_function_flags(struct trace_iterator *iter, u32 flags);
extern void print_graph_headers_flags(struct seq_file *s, u32 flags);
726 727
extern enum print_line_t
trace_print_graph_duration(unsigned long long duration, struct trace_seq *s);
728 729 730 731 732 733 734 735 736
extern void graph_trace_open(struct trace_iterator *iter);
extern void graph_trace_close(struct trace_iterator *iter);
extern int __trace_graph_entry(struct trace_array *tr,
			       struct ftrace_graph_ent *trace,
			       unsigned long flags, int pc);
extern void __trace_graph_return(struct trace_array *tr,
				 struct ftrace_graph_ret *trace,
				 unsigned long flags, int pc);

737 738 739 740

#ifdef CONFIG_DYNAMIC_FTRACE
/* TODO: make this variable */
#define FTRACE_GRAPH_MAX_FUNCS		32
741
extern int ftrace_graph_filter_enabled;
742 743 744 745 746 747 748
extern int ftrace_graph_count;
extern unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS];

static inline int ftrace_graph_addr(unsigned long addr)
{
	int i;

749
	if (!ftrace_graph_filter_enabled)
750 751 752
		return 1;

	for (i = 0; i < ftrace_graph_count; i++) {
753 754 755 756 757 758 759 760 761 762
		if (addr == ftrace_graph_funcs[i]) {
			/*
			 * If no irqs are to be traced, but a set_graph_function
			 * is set, and called by an interrupt handler, we still
			 * want to trace it.
			 */
			if (in_irq())
				trace_recursion_set(TRACE_IRQ_BIT);
			else
				trace_recursion_clear(TRACE_IRQ_BIT);
763
			return 1;
764
		}
765 766 767 768
	}

	return 0;
}
769
#else
770 771 772
static inline int ftrace_graph_addr(unsigned long addr)
{
	return 1;
773 774 775
}
#endif /* CONFIG_DYNAMIC_FTRACE */
#else /* CONFIG_FUNCTION_GRAPH_TRACER */
776
static inline enum print_line_t
777
print_graph_function_flags(struct trace_iterator *iter, u32 flags)
778 779 780
{
	return TRACE_TYPE_UNHANDLED;
}
781
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
782

783
extern struct list_head ftrace_pids;
784

785
#ifdef CONFIG_FUNCTION_TRACER
786
extern bool ftrace_filter_param __initdata;
787 788
static inline int ftrace_trace_task(struct task_struct *task)
{
789
	if (list_empty(&ftrace_pids))
790 791 792 793
		return 1;

	return test_tsk_trace_trace(task);
}
794
extern int ftrace_is_dead(void);
795 796 797 798 799
#else
static inline int ftrace_trace_task(struct task_struct *task)
{
	return 1;
}
800
static inline int ftrace_is_dead(void) { return 0; }
801
#endif
802

803 804
int ftrace_event_is_function(struct ftrace_event_call *call);

805 806 807 808
/*
 * struct trace_parser - servers for reading the user input separated by spaces
 * @cont: set if the input is not complete - no final space char was found
 * @buffer: holds the parsed user input
809
 * @idx: user input length
810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839
 * @size: buffer size
 */
struct trace_parser {
	bool		cont;
	char		*buffer;
	unsigned	idx;
	unsigned	size;
};

static inline bool trace_parser_loaded(struct trace_parser *parser)
{
	return (parser->idx != 0);
}

static inline bool trace_parser_cont(struct trace_parser *parser)
{
	return parser->cont;
}

static inline void trace_parser_clear(struct trace_parser *parser)
{
	parser->cont = false;
	parser->idx = 0;
}

extern int trace_parser_get_init(struct trace_parser *parser, int size);
extern void trace_parser_put(struct trace_parser *parser);
extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
	size_t cnt, loff_t *ppos);

S
Steven Rostedt 已提交
840 841 842 843 844 845 846
/*
 * 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.
 */
847 848 849 850 851 852 853 854 855 856
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,
L
Li Zefan 已提交
857 858 859 860 861 862 863 864 865 866 867
	TRACE_ITER_PRINTK		= 0x200,
	TRACE_ITER_PREEMPTONLY		= 0x400,
	TRACE_ITER_BRANCH		= 0x800,
	TRACE_ITER_ANNOTATE		= 0x1000,
	TRACE_ITER_USERSTACKTRACE       = 0x2000,
	TRACE_ITER_SYM_USEROBJ          = 0x4000,
	TRACE_ITER_PRINTK_MSGONLY	= 0x8000,
	TRACE_ITER_CONTEXT_INFO		= 0x10000, /* Print pid/cpu/time */
	TRACE_ITER_LATENCY_FMT		= 0x20000,
	TRACE_ITER_SLEEP_TIME		= 0x40000,
	TRACE_ITER_GRAPH_TIME		= 0x80000,
868
	TRACE_ITER_RECORD_CMD		= 0x100000,
869
	TRACE_ITER_OVERWRITE		= 0x200000,
870
	TRACE_ITER_STOP_ON_FREE		= 0x400000,
871
	TRACE_ITER_IRQ_INFO		= 0x800000,
872
	TRACE_ITER_MARKERS		= 0x1000000,
873
	TRACE_ITER_FUNCTION		= 0x2000000,
874 875
};

876 877 878 879 880 881 882
/*
 * 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)

883 884
extern struct tracer nop_trace;

885
#ifdef CONFIG_BRANCH_TRACER
886 887 888
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)
889
{
890 891
	if (trace_flags & TRACE_ITER_BRANCH)
		return enable_branch_tracing(tr);
892 893
	return 0;
}
894
static inline void trace_branch_disable(void)
895 896
{
	/* due to races, always disable */
897
	disable_branch_tracing();
898 899
}
#else
900
static inline int trace_branch_enable(struct trace_array *tr)
901 902 903
{
	return 0;
}
904
static inline void trace_branch_disable(void)
905 906
{
}
907
#endif /* CONFIG_BRANCH_TRACER */
908

909 910 911
/* set ring buffers to default size if not already done so */
int tracing_update_buffers(void);

912 913
struct ftrace_event_field {
	struct list_head	link;
914 915
	const char		*name;
	const char		*type;
916
	int			filter_type;
917 918
	int			offset;
	int			size;
919
	int			is_signed;
920 921
};

922
struct event_filter {
923 924
	int			n_preds;	/* Number assigned */
	int			a_preds;	/* allocated */
925
	struct filter_pred	*preds;
926
	struct filter_pred	*root;
927
	char			*filter_string;
928 929
};

930 931 932
struct event_subsystem {
	struct list_head	list;
	const char		*name;
933
	struct event_filter	*filter;
934
	int			ref_count;
935 936
};

937 938 939 940 941 942 943 944 945
struct ftrace_subsystem_dir {
	struct list_head		list;
	struct event_subsystem		*subsystem;
	struct trace_array		*tr;
	struct dentry			*entry;
	int				ref_count;
	int				nr_events;
};

946 947
#define FILTER_PRED_INVALID	((unsigned short)-1)
#define FILTER_PRED_IS_RIGHT	(1 << 15)
948
#define FILTER_PRED_FOLD	(1 << 15)
949

950 951 952 953 954 955 956 957
/*
 * The max preds is the size of unsigned short with
 * two flags at the MSBs. One bit is used for both the IS_RIGHT
 * and FOLD flags. The other is reserved.
 *
 * 2^14 preds is way more than enough.
 */
#define MAX_FILTER_PRED		16384
958

T
Tom Zanussi 已提交
959
struct filter_pred;
960
struct regex;
T
Tom Zanussi 已提交
961

962
typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event);
T
Tom Zanussi 已提交
963

964 965
typedef int (*regex_match_func)(char *str, struct regex *r, int len);

966
enum regex_type {
967
	MATCH_FULL = 0,
968 969 970 971 972
	MATCH_FRONT_ONLY,
	MATCH_MIDDLE_ONLY,
	MATCH_END_ONLY,
};

973 974 975 976 977 978 979
struct regex {
	char			pattern[MAX_FILTER_STR_VAL];
	int			len;
	int			field_len;
	regex_match_func	match;
};

T
Tom Zanussi 已提交
980
struct filter_pred {
981 982 983
	filter_pred_fn_t 	fn;
	u64 			val;
	struct regex		regex;
984
	unsigned short		*ops;
985
	struct ftrace_event_field *field;
986 987 988
	int 			offset;
	int 			not;
	int 			op;
989 990 991 992
	unsigned short		index;
	unsigned short		parent;
	unsigned short		left;
	unsigned short		right;
T
Tom Zanussi 已提交
993 994
};

995 996
extern enum regex_type
filter_parse_regex(char *buff, int len, char **search, int *not);
997
extern void print_event_filter(struct ftrace_event_call *call,
998
			       struct trace_seq *s);
999 1000
extern int apply_event_filter(struct ftrace_event_call *call,
			      char *filter_string);
1001
extern int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,
1002 1003
					char *filter_string);
extern void print_subsystem_event_filter(struct event_subsystem *system,
1004
					 struct trace_seq *s);
1005
extern int filter_assign_type(const char *type);
T
Tom Zanussi 已提交
1006

1007 1008
struct ftrace_event_field *
trace_find_event_field(struct ftrace_event_call *call, char *name);
1009

1010
static inline int
1011
filter_check_discard(struct ftrace_event_call *call, void *rec,
1012
		     struct ring_buffer *buffer,
1013 1014
		     struct ring_buffer_event *event)
{
1015
	if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) &&
L
Li Zefan 已提交
1016
	    !filter_match_preds(call->filter, rec)) {
1017 1018 1019 1020 1021
		ring_buffer_discard_commit(buffer, event);
		return 1;
	}

	return 0;
1022 1023
}

1024
extern void trace_event_enable_cmd_record(bool enable);
1025
extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
1026
extern int event_trace_del_tracer(struct trace_array *tr);
1027

1028
extern struct mutex event_mutex;
1029
extern struct list_head ftrace_events;
P
Peter Zijlstra 已提交
1030

1031 1032 1033
extern const char *__start___trace_bprintk_fmt[];
extern const char *__stop___trace_bprintk_fmt[];

1034
void trace_printk_init_buffers(void);
1035
void trace_printk_start_comm(void);
1036
int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set);
1037
int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled);
1038

1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049
/*
 * Normal trace_printk() and friends allocates special buffers
 * to do the manipulation, as well as saves the print formats
 * into sections to display. But the trace infrastructure wants
 * to use these without the added overhead at the price of being
 * a bit slower (used mainly for warnings, where we don't care
 * about performance). The internal_trace_puts() is for such
 * a purpose.
 */
#define internal_trace_puts(str) __trace_puts(_THIS_IP_, str, strlen(str))

1050
#undef FTRACE_ENTRY
1051
#define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter)	\
1052 1053
	extern struct ftrace_event_call					\
	__attribute__((__aligned__(4))) event_##call;
1054
#undef FTRACE_ENTRY_DUP
1055 1056 1057
#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter)	\
	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \
		     filter)
1058
#include "trace_entries.h"
1059

1060
#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_FUNCTION_TRACER)
1061 1062 1063 1064
int perf_ftrace_event_register(struct ftrace_event_call *call,
			       enum trace_reg type, void *data);
#else
#define perf_ftrace_event_register NULL
1065
#endif
1066

1067
#endif /* _LINUX_KERNEL_TRACE_H */