trace.h 52.2 KB
Newer Older
1

2 3 4 5
#ifndef _LINUX_KERNEL_TRACE_H
#define _LINUX_KERNEL_TRACE_H

#include <linux/fs.h>
A
Arun Sharma 已提交
6
#include <linux/atomic.h>
7 8
#include <linux/sched.h>
#include <linux/clocksource.h>
9
#include <linux/ring_buffer.h>
P
Pekka Paalanen 已提交
10
#include <linux/mmiotrace.h>
11
#include <linux/tracepoint.h>
12
#include <linux/ftrace.h>
13
#include <linux/hw_breakpoint.h>
14
#include <linux/trace_seq.h>
15
#include <linux/trace_events.h>
16
#include <linux/compiler.h>
17
#include <linux/trace_seq.h>
18

19 20 21 22 23
#ifdef CONFIG_FTRACE_SYSCALLS
#include <asm/unistd.h>		/* For NR_SYSCALLS	     */
#include <asm/syscall.h>	/* some archs define it here */
#endif

24 25 26 27 28 29 30
enum trace_type {
	__TRACE_FIRST_TYPE = 0,

	TRACE_FN,
	TRACE_CTX,
	TRACE_WAKE,
	TRACE_STACK,
31
	TRACE_PRINT,
32
	TRACE_BPRINT,
P
Pekka Paalanen 已提交
33 34
	TRACE_MMIO_RW,
	TRACE_MMIO_MAP,
35
	TRACE_BRANCH,
36 37
	TRACE_GRAPH_RET,
	TRACE_GRAPH_ENT,
38
	TRACE_USER_STACK,
39
	TRACE_BLK,
40
	TRACE_BPUTS,
41
	TRACE_HWLAT,
42

43
	__TRACE_LAST_TYPE,
44 45
};

46

47 48
#undef __field
#define __field(type, item)		type	item;
I
Ingo Molnar 已提交
49

50 51
#undef __field_struct
#define __field_struct(type, item)	__field(type, item)
I
Ingo Molnar 已提交
52

53 54
#undef __field_desc
#define __field_desc(type, container, item)
55

56 57
#undef __array
#define __array(type, item, size)	type	item[size];
58

59 60
#undef __array_desc
#define __array_desc(type, container, item, size)
61

62 63
#undef __dynamic_array
#define __dynamic_array(type, item)	type	item[];
64

65 66
#undef F_STRUCT
#define F_STRUCT(args...)		args
67

68
#undef FTRACE_ENTRY
69 70 71 72
#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter)	\
	struct struct_name {						\
		struct trace_entry	ent;				\
		tstruct							\
73
	}
74

75
#undef FTRACE_ENTRY_DUP
76
#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk, filter)
77

78
#undef FTRACE_ENTRY_REG
79 80 81 82
#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print,	\
			 filter, regfn) \
	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
		     filter)
83

84 85 86 87 88 89
#undef FTRACE_ENTRY_PACKED
#define FTRACE_ENTRY_PACKED(name, struct_name, id, tstruct, print,	\
			    filter)					\
	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
		     filter) __packed

90
#include "trace_entries.h"
91

92 93 94 95
/*
 * syscalls are special, and need special handling, this is why
 * they are not included in trace_entries.h
 */
96 97 98 99 100 101 102 103 104
struct syscall_trace_enter {
	struct trace_entry	ent;
	int			nr;
	unsigned long		args[];
};

struct syscall_trace_exit {
	struct trace_entry	ent;
	int			nr;
105
	long			ret;
106 107
};

108
struct kprobe_trace_entry_head {
109 110 111 112
	struct trace_entry	ent;
	unsigned long		ip;
};

113
struct kretprobe_trace_entry_head {
114 115 116 117 118
	struct trace_entry	ent;
	unsigned long		func;
	unsigned long		ret_ip;
};

119 120 121
/*
 * trace_flag_type is an enumeration that holds different
 * states when a trace occurs. These are:
122
 *  IRQS_OFF		- interrupts were disabled
I
Ingo Molnar 已提交
123
 *  IRQS_NOSUPPORT	- arch does not support irqs_disabled_flags
L
Li Zefan 已提交
124
 *  NEED_RESCHED	- reschedule is requested
125 126
 *  HARDIRQ		- inside an interrupt handler
 *  SOFTIRQ		- inside a softirq handler
127 128 129
 */
enum trace_flag_type {
	TRACE_FLAG_IRQS_OFF		= 0x01,
130 131 132 133
	TRACE_FLAG_IRQS_NOSUPPORT	= 0x02,
	TRACE_FLAG_NEED_RESCHED		= 0x04,
	TRACE_FLAG_HARDIRQ		= 0x08,
	TRACE_FLAG_SOFTIRQ		= 0x10,
134
	TRACE_FLAG_PREEMPT_RESCHED	= 0x20,
135
	TRACE_FLAG_NMI			= 0x40,
136 137
};

138
#define TRACE_BUF_SIZE		1024
139

140 141
struct trace_array;

142 143 144 145 146 147 148
/*
 * 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;
149
	void			*buffer_page;	/* ring buffer spare */
I
Ingo Molnar 已提交
150

151
	unsigned long		entries;
152 153 154 155 156 157 158
	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;
159
	unsigned long		skipped_entries;
160 161
	cycle_t			preempt_timestamp;
	pid_t			pid;
162
	kuid_t			uid;
163
	char			comm[TASK_COMM_LEN];
164 165

	bool			ignore_pid;
166 167 168
#ifdef CONFIG_FUNCTION_TRACER
	bool			ftrace_ignore_pid;
#endif
169 170
};

171
struct tracer;
172
struct trace_option_dentry;
173

174 175 176 177 178 179 180 181
struct trace_buffer {
	struct trace_array		*tr;
	struct ring_buffer		*buffer;
	struct trace_array_cpu __percpu	*data;
	cycle_t				time_start;
	int				cpu;
};

182 183
#define TRACE_FLAGS_MAX_SIZE		32

184 185 186 187 188
struct trace_options {
	struct tracer			*tracer;
	struct trace_option_dentry	*topts;
};

189
struct trace_pid_list {
190 191
	int				pid_max;
	unsigned long			*pids;
192 193
};

194 195 196 197 198 199
/*
 * 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 {
200
	struct list_head	list;
201
	char			*name;
202 203 204 205 206 207 208 209 210 211 212 213 214 215
	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;
216
	bool			allocated_snapshot;
217 218
#endif
#if defined(CONFIG_TRACER_MAX_TRACE) || defined(CONFIG_HWLAT_TRACER)
219
	unsigned long		max_latency;
220
#endif
221
	struct trace_pid_list	__rcu *filtered_pids;
222 223 224 225 226 227 228 229 230 231 232 233 234 235
	/*
	 * max_lock is used to protect the swapping of buffers
	 * when taking a max snapshot. The buffers themselves are
	 * protected by per_cpu spinlocks. But the action of the swap
	 * needs its own lock.
	 *
	 * This is defined as a arch_spinlock_t in order to help
	 * with performance when lockdep debugging is enabled.
	 *
	 * It is also used in other places outside the update_max_tr
	 * so it needs to be defined outside of the
	 * CONFIG_TRACER_MAX_TRACE.
	 */
	arch_spinlock_t		max_lock;
236
	int			buffer_disabled;
237 238 239
#ifdef CONFIG_FTRACE_SYSCALLS
	int			sys_refcount_enter;
	int			sys_refcount_exit;
240 241
	struct trace_event_file __rcu *enter_syscall_files[NR_syscalls];
	struct trace_event_file __rcu *exit_syscall_files[NR_syscalls];
242
#endif
243 244
	int			stop_count;
	int			clock_id;
245
	int			nr_topts;
246
	struct tracer		*current_trace;
247
	unsigned int		trace_flags;
248
	unsigned char		trace_flags_index[TRACE_FLAGS_MAX_SIZE];
249
	unsigned int		flags;
250
	raw_spinlock_t		start_lock;
251
	struct dentry		*dir;
252 253
	struct dentry		*options;
	struct dentry		*percpu_dir;
254
	struct dentry		*event_dir;
255
	struct trace_options	*topts;
256 257
	struct list_head	systems;
	struct list_head	events;
258
	cpumask_var_t		tracing_cpumask; /* only trace on set CPUs */
259
	int			ref;
260 261
#ifdef CONFIG_FUNCTION_TRACER
	struct ftrace_ops	*ops;
262
	struct trace_pid_list	__rcu *function_pids;
263 264 265
	/* function tracing enabled */
	int			function_enabled;
#endif
266 267
};

268 269 270 271 272 273
enum {
	TRACE_ARRAY_FL_GLOBAL	= (1 << 0)
};

extern struct list_head ftrace_trace_arrays;

274 275
extern struct mutex trace_types_lock;

276 277 278
extern int trace_array_get(struct trace_array *tr);
extern void trace_array_put(struct trace_array *tr);

279 280 281 282 283 284 285 286
/*
 * 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;

287
	if (list_empty(&ftrace_trace_arrays))
288 289
		return NULL;

290 291 292 293 294 295
	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
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
#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);	\
328
		IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\
S
Steven Rostedt 已提交
329
		IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT);	\
330
		IF_ASSIGN(var, ent, struct bprint_entry, TRACE_BPRINT);	\
331
		IF_ASSIGN(var, ent, struct bputs_entry, TRACE_BPUTS);	\
332
		IF_ASSIGN(var, ent, struct hwlat_entry, TRACE_HWLAT);	\
S
Steven Rostedt 已提交
333 334 335 336
		IF_ASSIGN(var, ent, struct trace_mmiotrace_rw,		\
			  TRACE_MMIO_RW);				\
		IF_ASSIGN(var, ent, struct trace_mmiotrace_map,		\
			  TRACE_MMIO_MAP);				\
337
		IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \
338 339 340 341
		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
342 343
		__ftrace_bad_type();					\
	} while (0)
344

345 346 347 348 349 350
/*
 * 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
351 352
	const char	*name; /* Will appear on the trace_options file */
	u32		bit; /* Mask assigned in val field in tracer_flags */
353 354 355 356 357 358 359 360
};

/*
 * 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
361
	struct tracer_opt	*opts;
362
	struct tracer		*trace;
363 364 365 366 367
};

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

368

369 370 371 372 373 374 375
struct trace_option_dentry {
	struct tracer_opt		*opt;
	struct tracer_flags		*flags;
	struct trace_array		*tr;
	struct dentry			*entry;
};

376
/**
377
 * struct tracer - a specific tracer and its callbacks to interact with tracefs
378 379 380
 * @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
381 382
 * @start: called when tracing is unpaused (echo 1 > tracing_on)
 * @stop: called when tracing is paused (echo 0 > tracing_on)
383
 * @update_thresh: called when tracing_thresh is updated
384 385 386
 * @open: called when the trace file is opened
 * @pipe_open: called when the trace_pipe file is opened
 * @close: called when the trace file is released
S
Steven Rostedt 已提交
387
 * @pipe_close: called when the trace_pipe file is released
388 389 390 391 392 393 394
 * @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
395 396 397
 */
struct tracer {
	const char		*name;
398
	int			(*init)(struct trace_array *tr);
399
	void			(*reset)(struct trace_array *tr);
400 401
	void			(*start)(struct trace_array *tr);
	void			(*stop)(struct trace_array *tr);
402
	int			(*update_thresh)(struct trace_array *tr);
403
	void			(*open)(struct trace_iterator *iter);
404
	void			(*pipe_open)(struct trace_iterator *iter);
405
	void			(*close)(struct trace_iterator *iter);
S
Steven Rostedt 已提交
406
	void			(*pipe_close)(struct trace_iterator *iter);
407 408 409
	ssize_t			(*read)(struct trace_iterator *iter,
					struct file *filp, char __user *ubuf,
					size_t cnt, loff_t *ppos);
410 411 412 413 414 415
	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
416 417 418 419
#ifdef CONFIG_FTRACE_STARTUP_TEST
	int			(*selftest)(struct tracer *trace,
					    struct trace_array *tr);
#endif
420
	void			(*print_header)(struct seq_file *m);
421
	enum print_line_t	(*print_line)(struct trace_iterator *iter);
422
	/* If you handled the flag setting, return 0 */
423 424
	int			(*set_flag)(struct trace_array *tr,
					    u32 old_flags, u32 bit, int set);
425
	/* Return 0 if OK with change, else return non-zero */
426
	int			(*flag_changed)(struct trace_array *tr,
427
						u32 mask, int set);
428
	struct tracer		*next;
I
Ingo Molnar 已提交
429
	struct tracer_flags	*flags;
430
	int			enabled;
431
	int			ref;
432
	bool			print_max;
433
	bool			allow_instances;
434
#ifdef CONFIG_TRACER_MAX_TRACE
435
	bool			use_max_tr;
436
#endif
437 438
};

439

440 441
/* Only current can touch trace_recursion */

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
/*
 * 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.
 */
467
enum {
468 469 470 471 472 473 474
	TRACE_BUFFER_BIT,
	TRACE_BUFFER_NMI_BIT,
	TRACE_BUFFER_IRQ_BIT,
	TRACE_BUFFER_SIRQ_BIT,

	/* Start of function recursion bits */
	TRACE_FTRACE_BIT,
475 476 477
	TRACE_FTRACE_NMI_BIT,
	TRACE_FTRACE_IRQ_BIT,
	TRACE_FTRACE_SIRQ_BIT,
478

479
	/* INTERNAL_BITs must be greater than FTRACE_BITs */
480 481 482 483 484
	TRACE_INTERNAL_BIT,
	TRACE_INTERNAL_NMI_BIT,
	TRACE_INTERNAL_IRQ_BIT,
	TRACE_INTERNAL_SIRQ_BIT,

485
	TRACE_BRANCH_BIT,
486 487 488 489 490 491 492
/*
 * 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.
 */
493 494
	TRACE_IRQ_BIT,
};
495

496 497 498
#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)))
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
#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_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;
}

562 563 564 565 566 567 568 569
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;
}

570
int tracer_init(struct tracer *t, struct trace_array *tr);
571
int tracing_is_enabled(void);
572 573
void tracing_reset(struct trace_buffer *buf, int cpu);
void tracing_reset_online_cpus(struct trace_buffer *buf);
574
void tracing_reset_current(int cpu);
575
void tracing_reset_all_online_cpus(void);
576
int tracing_open_generic(struct inode *inode, struct file *filp);
577
bool tracing_is_disabled(void);
578
int tracer_tracing_is_on(struct trace_array *tr);
579
struct dentry *trace_create_file(const char *name,
A
Al Viro 已提交
580
				 umode_t mode,
581 582 583 584
				 struct dentry *parent,
				 void *data,
				 const struct file_operations *fops);

585
struct dentry *tracing_init_dentry(void);
I
Ingo Molnar 已提交
586

587 588
struct ring_buffer_event;

589 590 591 592 593 594
struct ring_buffer_event *
trace_buffer_lock_reserve(struct ring_buffer *buffer,
			  int type,
			  unsigned long len,
			  unsigned long flags,
			  int pc);
595

596 597
struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
						struct trace_array_cpu *data);
598 599 600 601

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

602 603 604
void __buffer_unlock_commit(struct ring_buffer *buffer,
			    struct ring_buffer_event *event);

605 606 607 608 609 610 611 612
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);

613 614 615
void trace_function(struct trace_array *tr,
		    unsigned long ip,
		    unsigned long parent_ip,
616
		    unsigned long flags, int pc);
617 618 619 620
void trace_graph_function(struct trace_array *tr,
		    unsigned long ip,
		    unsigned long parent_ip,
		    unsigned long flags, int pc);
621
void trace_latency_header(struct seq_file *m);
622 623 624
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);
625

626
void trace_graph_return(struct ftrace_graph_ret *trace);
627
int trace_graph_entry(struct ftrace_graph_ent *trace);
628
void set_graph_array(struct trace_array *tr);
629

630 631
void tracing_start_cmdline_record(void);
void tracing_stop_cmdline_record(void);
632
int register_tracer(struct tracer *type);
633
int is_tracing_stopped(void);
634

635 636
loff_t tracing_lseek(struct file *file, loff_t offset, int whence);

637 638 639 640
extern cpumask_var_t __read_mostly tracing_buffer_mask;

#define for_each_tracing_cpu(cpu)	\
	for_each_cpu(cpu, tracing_buffer_mask)
641 642 643

extern unsigned long nsecs_to_usecs(unsigned long nsecs);

644 645
extern unsigned long tracing_thresh;

646
/* PID filtering */
647 648 649

extern int pid_max;

650 651 652 653 654 655 656
bool trace_find_filtered_pid(struct trace_pid_list *filtered_pids,
			     pid_t search_pid);
bool trace_ignore_this_task(struct trace_pid_list *filtered_pids,
			    struct task_struct *task);
void trace_filter_add_remove_task(struct trace_pid_list *pid_list,
				  struct task_struct *self,
				  struct task_struct *task);
657 658 659
void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos);
void *trace_pid_start(struct trace_pid_list *pid_list, loff_t *pos);
int trace_pid_show(struct seq_file *m, void *v);
660 661 662 663
void trace_free_pid_list(struct trace_pid_list *pid_list);
int trace_pid_write(struct trace_pid_list *filtered_pids,
		    struct trace_pid_list **new_pid_list,
		    const char __user *ubuf, size_t cnt);
664

665
#ifdef CONFIG_TRACER_MAX_TRACE
666 667 668
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);
669
#endif /* CONFIG_TRACER_MAX_TRACE */
670

671
#ifdef CONFIG_STACKTRACE
672
void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags,
673 674 675 676 677
			    int pc);

void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
		   int pc);
#else
678
static inline void ftrace_trace_userstack(struct ring_buffer *buffer,
679 680 681 682 683 684 685 686 687
					  unsigned long flags, int pc)
{
}

static inline void __trace_stack(struct trace_array *tr, unsigned long flags,
				 int skip, int pc)
{
}
#endif /* CONFIG_STACKTRACE */
688

I
Ingo Molnar 已提交
689
extern cycle_t ftrace_now(int cpu);
690

691
extern void trace_find_cmdline(int pid, char comm[]);
692
extern void trace_event_follow_fork(struct trace_array *tr, bool enable);
693

694 695
#ifdef CONFIG_DYNAMIC_FTRACE
extern unsigned long ftrace_update_tot_cnt;
696
#endif
697 698
#define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func
extern int DYN_FTRACE_TEST_NAME(void);
699 700
#define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2
extern int DYN_FTRACE_TEST_NAME2(void);
701

702
extern bool ring_buffer_expanded;
703 704
extern bool tracing_selftest_disabled;

S
Steven Rostedt 已提交
705 706 707
#ifdef CONFIG_FTRACE_STARTUP_TEST
extern int trace_selftest_startup_function(struct tracer *trace,
					   struct trace_array *tr);
708 709
extern int trace_selftest_startup_function_graph(struct tracer *trace,
						 struct trace_array *tr);
S
Steven Rostedt 已提交
710 711 712 713 714 715 716 717
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
718 719
extern int trace_selftest_startup_nop(struct tracer *trace,
					 struct trace_array *tr);
S
Steven Rostedt 已提交
720 721
extern int trace_selftest_startup_sched_switch(struct tracer *trace,
					       struct trace_array *tr);
S
Steven Rostedt 已提交
722 723
extern int trace_selftest_startup_branch(struct tracer *trace,
					 struct trace_array *tr);
724 725 726 727 728 729 730 731 732
/*
 * 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
733 734
#endif /* CONFIG_FTRACE_STARTUP_TEST */

I
Ingo Molnar 已提交
735
extern void *head_page(struct trace_array_cpu *data);
736
extern unsigned long long ns2usecs(cycle_t nsec);
737
extern int
738
trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
739
extern int
740
trace_vprintk(unsigned long ip, const char *fmt, va_list args);
741 742 743 744 745
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, ...);
746 747
int trace_array_printk_buf(struct ring_buffer *buffer,
			   unsigned long ip, const char *fmt, ...);
748 749
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
750

751 752
extern char trace_find_mark(unsigned long long duration);

753
/* Standard output formatting function used for function return traces */
754
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
755 756 757 758 759 760 761 762

/* 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
763
#define TRACE_GRAPH_PRINT_IRQS          0x40
764
#define TRACE_GRAPH_PRINT_TAIL          0x80
765 766
#define TRACE_GRAPH_SLEEP_TIME		0x100
#define TRACE_GRAPH_GRAPH_TIME		0x200
767 768
#define TRACE_GRAPH_PRINT_FILL_SHIFT	28
#define TRACE_GRAPH_PRINT_FILL_MASK	(0x3 << TRACE_GRAPH_PRINT_FILL_SHIFT)
769

770 771 772
extern void ftrace_graph_sleep_time_control(bool enable);
extern void ftrace_graph_graph_time_control(bool enable);

773 774 775
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);
776
extern void
777
trace_print_graph_duration(unsigned long long duration, struct trace_seq *s);
778 779 780 781 782 783 784 785 786
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);

787 788 789 790 791 792

#ifdef CONFIG_DYNAMIC_FTRACE
/* TODO: make this variable */
#define FTRACE_GRAPH_MAX_FUNCS		32
extern int ftrace_graph_count;
extern unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS];
793 794
extern int ftrace_graph_notrace_count;
extern unsigned long ftrace_graph_notrace_funcs[FTRACE_GRAPH_MAX_FUNCS];
795 796 797 798 799

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

800
	if (!ftrace_graph_count)
801 802 803
		return 1;

	for (i = 0; i < ftrace_graph_count; i++) {
804 805 806 807 808 809 810 811 812 813
		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);
814
			return 1;
815
		}
816 817 818 819
	}

	return 0;
}
820 821 822 823 824 825 826 827 828 829 830 831 832 833 834

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

	if (!ftrace_graph_notrace_count)
		return 0;

	for (i = 0; i < ftrace_graph_notrace_count; i++) {
		if (addr == ftrace_graph_notrace_funcs[i])
			return 1;
	}

	return 0;
}
835
#else
836 837 838
static inline int ftrace_graph_addr(unsigned long addr)
{
	return 1;
839
}
840 841 842 843 844

static inline int ftrace_graph_notrace_addr(unsigned long addr)
{
	return 0;
}
845 846
#endif /* CONFIG_DYNAMIC_FTRACE */
#else /* CONFIG_FUNCTION_GRAPH_TRACER */
847
static inline enum print_line_t
848
print_graph_function_flags(struct trace_iterator *iter, u32 flags)
849 850 851
{
	return TRACE_TYPE_UNHANDLED;
}
852
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
853

854
extern struct list_head ftrace_pids;
855

856
#ifdef CONFIG_FUNCTION_TRACER
857
extern bool ftrace_filter_param __initdata;
858
static inline int ftrace_trace_task(struct trace_array *tr)
859
{
860
	return !this_cpu_read(tr->trace_buffer.data->ftrace_ignore_pid);
861
}
862
extern int ftrace_is_dead(void);
863 864 865
int ftrace_create_function_files(struct trace_array *tr,
				 struct dentry *parent);
void ftrace_destroy_function_files(struct trace_array *tr);
866 867 868
void ftrace_init_global_array_ops(struct trace_array *tr);
void ftrace_init_array_ops(struct trace_array *tr, ftrace_func_t func);
void ftrace_reset_array_ops(struct trace_array *tr);
869
int using_ftrace_ops_list_func(void);
870
void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer);
871 872
void ftrace_init_tracefs_toplevel(struct trace_array *tr,
				  struct dentry *d_tracer);
873
#else
874
static inline int ftrace_trace_task(struct trace_array *tr)
875 876 877
{
	return 1;
}
878
static inline int ftrace_is_dead(void) { return 0; }
879 880 881 882 883 884 885
static inline int
ftrace_create_function_files(struct trace_array *tr,
			     struct dentry *parent)
{
	return 0;
}
static inline void ftrace_destroy_function_files(struct trace_array *tr) { }
886 887 888
static inline __init void
ftrace_init_global_array_ops(struct trace_array *tr) { }
static inline void ftrace_reset_array_ops(struct trace_array *tr) { }
889
static inline void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d) { }
890
static inline void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d) { }
891 892
/* ftace_func_t type is not defined, use macro instead of static inline */
#define ftrace_init_array_ops(tr, func) do { } while (0)
893 894 895 896 897 898 899 900 901 902 903 904 905 906
#endif /* CONFIG_FUNCTION_TRACER */

#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE)
void ftrace_create_filter_files(struct ftrace_ops *ops,
				struct dentry *parent);
void ftrace_destroy_filter_files(struct ftrace_ops *ops);
#else
/*
 * The ops parameter passed in is usually undefined.
 * This must be a macro.
 */
#define ftrace_create_filter_files(ops, parent) do { } while (0)
#define ftrace_destroy_filter_files(ops) do { } while (0)
#endif /* CONFIG_FUNCTION_TRACER && CONFIG_DYNAMIC_FTRACE */
907

908
bool ftrace_event_is_function(struct trace_event_call *call);
909

910 911 912 913
/*
 * 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
914
 * @idx: user input length
915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944
 * @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);

945 946 947 948 949 950 951 952 953 954
/*
 * Only create function graph options if function graph is configured.
 */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
# define FGRAPH_FLAGS						\
		C(DISPLAY_GRAPH,	"display-graph"),
#else
# define FGRAPH_FLAGS
#endif

955 956 957 958 959 960 961
#ifdef CONFIG_BRANCH_TRACER
# define BRANCH_FLAGS					\
		C(BRANCH,		"branch"),
#else
# define BRANCH_FLAGS
#endif

962 963 964 965 966 967 968 969 970
#ifdef CONFIG_FUNCTION_TRACER
# define FUNCTION_FLAGS						\
		C(FUNCTION,		"function-trace"),
# define FUNCTION_DEFAULT_FLAGS		TRACE_ITER_FUNCTION
#else
# define FUNCTION_FLAGS
# define FUNCTION_DEFAULT_FLAGS		0UL
#endif

971 972 973 974 975 976 977
#ifdef CONFIG_STACKTRACE
# define STACK_FLAGS				\
		C(STACKTRACE,		"stacktrace"),
#else
# define STACK_FLAGS
#endif

S
Steven Rostedt 已提交
978 979 980 981 982
/*
 * 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
983
 *       trace.c (this macro guarantees it).
S
Steven Rostedt 已提交
984
 */
985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005
#define TRACE_FLAGS						\
		C(PRINT_PARENT,		"print-parent"),	\
		C(SYM_OFFSET,		"sym-offset"),		\
		C(SYM_ADDR,		"sym-addr"),		\
		C(VERBOSE,		"verbose"),		\
		C(RAW,			"raw"),			\
		C(HEX,			"hex"),			\
		C(BIN,			"bin"),			\
		C(BLOCK,		"block"),		\
		C(PRINTK,		"trace_printk"),	\
		C(ANNOTATE,		"annotate"),		\
		C(USERSTACKTRACE,	"userstacktrace"),	\
		C(SYM_USEROBJ,		"sym-userobj"),		\
		C(PRINTK_MSGONLY,	"printk-msg-only"),	\
		C(CONTEXT_INFO,		"context-info"),   /* Print pid/cpu/time */ \
		C(LATENCY_FMT,		"latency-format"),	\
		C(RECORD_CMD,		"record-cmd"),		\
		C(OVERWRITE,		"overwrite"),		\
		C(STOP_ON_FREE,		"disable_on_free"),	\
		C(IRQ_INFO,		"irq-info"),		\
		C(MARKERS,		"markers"),		\
1006
		C(EVENT_FORK,		"event-fork"),		\
1007
		FUNCTION_FLAGS					\
1008
		FGRAPH_FLAGS					\
1009
		STACK_FLAGS					\
1010
		BRANCH_FLAGS
1011

1012 1013 1014 1015 1016 1017 1018
/*
 * By defining C, we can make TRACE_FLAGS a list of bit names
 * that will define the bits for the flag masks.
 */
#undef C
#define C(a, b) TRACE_ITER_##a##_BIT

1019 1020 1021 1022 1023
enum trace_iterator_bits {
	TRACE_FLAGS
	/* Make sure we don't go more than we have bits for */
	TRACE_ITER_LAST_BIT
};
1024 1025 1026 1027 1028 1029 1030 1031 1032

/*
 * By redefining C, we can make TRACE_FLAGS a list of masks that
 * use the bits as defined above.
 */
#undef C
#define C(a, b) TRACE_ITER_##a = (1 << TRACE_ITER_##a##_BIT)

enum trace_iterator_flags { TRACE_FLAGS };
1033

1034 1035 1036 1037 1038 1039 1040
/*
 * 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)

1041 1042
extern struct tracer nop_trace;

1043
#ifdef CONFIG_BRANCH_TRACER
1044 1045 1046
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)
1047
{
1048
	if (tr->trace_flags & TRACE_ITER_BRANCH)
1049
		return enable_branch_tracing(tr);
1050 1051
	return 0;
}
1052
static inline void trace_branch_disable(void)
1053 1054
{
	/* due to races, always disable */
1055
	disable_branch_tracing();
1056 1057
}
#else
1058
static inline int trace_branch_enable(struct trace_array *tr)
1059 1060 1061
{
	return 0;
}
1062
static inline void trace_branch_disable(void)
1063 1064
{
}
1065
#endif /* CONFIG_BRANCH_TRACER */
1066

1067 1068 1069
/* set ring buffers to default size if not already done so */
int tracing_update_buffers(void);

1070 1071
struct ftrace_event_field {
	struct list_head	link;
1072 1073
	const char		*name;
	const char		*type;
1074
	int			filter_type;
1075 1076
	int			offset;
	int			size;
1077
	int			is_signed;
1078 1079
};

1080
struct event_filter {
1081 1082
	int			n_preds;	/* Number assigned */
	int			a_preds;	/* allocated */
1083
	struct filter_pred	*preds;
1084
	struct filter_pred	*root;
1085
	char			*filter_string;
1086 1087
};

1088 1089 1090
struct event_subsystem {
	struct list_head	list;
	const char		*name;
1091
	struct event_filter	*filter;
1092
	int			ref_count;
1093 1094
};

1095
struct trace_subsystem_dir {
1096 1097 1098 1099 1100 1101 1102 1103
	struct list_head		list;
	struct event_subsystem		*subsystem;
	struct trace_array		*tr;
	struct dentry			*entry;
	int				ref_count;
	int				nr_events;
};

1104 1105 1106
extern int call_filter_check_discard(struct trace_event_call *call, void *rec,
				     struct ring_buffer *buffer,
				     struct ring_buffer_event *event);
1107 1108 1109 1110 1111 1112

void trace_buffer_unlock_commit_regs(struct trace_array *tr,
				     struct ring_buffer *buffer,
				     struct ring_buffer_event *event,
				     unsigned long flags, int pc,
				     struct pt_regs *regs);
1113 1114 1115 1116 1117 1118 1119 1120 1121

static inline void trace_buffer_unlock_commit(struct trace_array *tr,
					      struct ring_buffer *buffer,
					      struct ring_buffer_event *event,
					      unsigned long flags, int pc)
{
	trace_buffer_unlock_commit_regs(tr, buffer, event, flags, pc, NULL);
}

1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138
DECLARE_PER_CPU(struct ring_buffer_event *, trace_buffered_event);
DECLARE_PER_CPU(int, trace_buffered_event_cnt);
void trace_buffered_event_disable(void);
void trace_buffered_event_enable(void);

static inline void
__trace_event_discard_commit(struct ring_buffer *buffer,
			     struct ring_buffer_event *event)
{
	if (this_cpu_read(trace_buffered_event) == event) {
		/* Simply release the temp buffer */
		this_cpu_dec(trace_buffered_event_cnt);
		return;
	}
	ring_buffer_discard_commit(buffer, event);
}

1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163
/*
 * Helper function for event_trigger_unlock_commit{_regs}().
 * If there are event triggers attached to this event that requires
 * filtering against its fields, then they wil be called as the
 * entry already holds the field information of the current event.
 *
 * It also checks if the event should be discarded or not.
 * It is to be discarded if the event is soft disabled and the
 * event was only recorded to process triggers, or if the event
 * filter is active and this event did not match the filters.
 *
 * Returns true if the event is discarded, false otherwise.
 */
static inline bool
__event_trigger_test_discard(struct trace_event_file *file,
			     struct ring_buffer *buffer,
			     struct ring_buffer_event *event,
			     void *entry,
			     enum event_trigger_type *tt)
{
	unsigned long eflags = file->flags;

	if (eflags & EVENT_FILE_FL_TRIGGER_COND)
		*tt = event_triggers_call(file, entry);

1164 1165 1166
	if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) ||
	    (unlikely(file->flags & EVENT_FILE_FL_FILTERED) &&
	     !filter_match_preds(file->filter, entry))) {
1167
		__trace_event_discard_commit(buffer, event);
1168 1169
		return true;
	}
1170

1171
	return false;
1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234
}

/**
 * event_trigger_unlock_commit - handle triggers and finish event commit
 * @file: The file pointer assoctiated to the event
 * @buffer: The ring buffer that the event is being written to
 * @event: The event meta data in the ring buffer
 * @entry: The event itself
 * @irq_flags: The state of the interrupts at the start of the event
 * @pc: The state of the preempt count at the start of the event.
 *
 * This is a helper function to handle triggers that require data
 * from the event itself. It also tests the event against filters and
 * if the event is soft disabled and should be discarded.
 */
static inline void
event_trigger_unlock_commit(struct trace_event_file *file,
			    struct ring_buffer *buffer,
			    struct ring_buffer_event *event,
			    void *entry, unsigned long irq_flags, int pc)
{
	enum event_trigger_type tt = ETT_NONE;

	if (!__event_trigger_test_discard(file, buffer, event, entry, &tt))
		trace_buffer_unlock_commit(file->tr, buffer, event, irq_flags, pc);

	if (tt)
		event_triggers_post_call(file, tt, entry);
}

/**
 * event_trigger_unlock_commit_regs - handle triggers and finish event commit
 * @file: The file pointer assoctiated to the event
 * @buffer: The ring buffer that the event is being written to
 * @event: The event meta data in the ring buffer
 * @entry: The event itself
 * @irq_flags: The state of the interrupts at the start of the event
 * @pc: The state of the preempt count at the start of the event.
 *
 * This is a helper function to handle triggers that require data
 * from the event itself. It also tests the event against filters and
 * if the event is soft disabled and should be discarded.
 *
 * Same as event_trigger_unlock_commit() but calls
 * trace_buffer_unlock_commit_regs() instead of trace_buffer_unlock_commit().
 */
static inline void
event_trigger_unlock_commit_regs(struct trace_event_file *file,
				 struct ring_buffer *buffer,
				 struct ring_buffer_event *event,
				 void *entry, unsigned long irq_flags, int pc,
				 struct pt_regs *regs)
{
	enum event_trigger_type tt = ETT_NONE;

	if (!__event_trigger_test_discard(file, buffer, event, entry, &tt))
		trace_buffer_unlock_commit_regs(file->tr, buffer, event,
						irq_flags, pc, regs);

	if (tt)
		event_triggers_post_call(file, tt, entry);
}

1235 1236
#define FILTER_PRED_INVALID	((unsigned short)-1)
#define FILTER_PRED_IS_RIGHT	(1 << 15)
1237
#define FILTER_PRED_FOLD	(1 << 15)
1238

1239 1240 1241 1242 1243 1244 1245 1246
/*
 * 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
1247

T
Tom Zanussi 已提交
1248
struct filter_pred;
1249
struct regex;
T
Tom Zanussi 已提交
1250

1251
typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event);
T
Tom Zanussi 已提交
1252

1253 1254
typedef int (*regex_match_func)(char *str, struct regex *r, int len);

1255
enum regex_type {
1256
	MATCH_FULL = 0,
1257 1258 1259 1260 1261
	MATCH_FRONT_ONLY,
	MATCH_MIDDLE_ONLY,
	MATCH_END_ONLY,
};

1262 1263 1264 1265 1266 1267 1268
struct regex {
	char			pattern[MAX_FILTER_STR_VAL];
	int			len;
	int			field_len;
	regex_match_func	match;
};

T
Tom Zanussi 已提交
1269
struct filter_pred {
1270 1271 1272
	filter_pred_fn_t 	fn;
	u64 			val;
	struct regex		regex;
1273
	unsigned short		*ops;
1274
	struct ftrace_event_field *field;
1275 1276 1277
	int 			offset;
	int 			not;
	int 			op;
1278 1279 1280 1281
	unsigned short		index;
	unsigned short		parent;
	unsigned short		left;
	unsigned short		right;
T
Tom Zanussi 已提交
1282 1283
};

1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295
static inline bool is_string_field(struct ftrace_event_field *field)
{
	return field->filter_type == FILTER_DYN_STRING ||
	       field->filter_type == FILTER_STATIC_STRING ||
	       field->filter_type == FILTER_PTR_STRING;
}

static inline bool is_function_field(struct ftrace_event_field *field)
{
	return field->filter_type == FILTER_TRACE_FN;
}

1296 1297
extern enum regex_type
filter_parse_regex(char *buff, int len, char **search, int *not);
1298
extern void print_event_filter(struct trace_event_file *file,
1299
			       struct trace_seq *s);
1300
extern int apply_event_filter(struct trace_event_file *file,
1301
			      char *filter_string);
1302
extern int apply_subsystem_event_filter(struct trace_subsystem_dir *dir,
1303 1304
					char *filter_string);
extern void print_subsystem_event_filter(struct event_subsystem *system,
1305
					 struct trace_seq *s);
1306
extern int filter_assign_type(const char *type);
1307
extern int create_event_filter(struct trace_event_call *call,
1308 1309 1310
			       char *filter_str, bool set_str,
			       struct event_filter **filterp);
extern void free_event_filter(struct event_filter *filter);
T
Tom Zanussi 已提交
1311

1312
struct ftrace_event_field *
1313
trace_find_event_field(struct trace_event_call *call, char *name);
1314

1315
extern void trace_event_enable_cmd_record(bool enable);
1316
extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
1317
extern int event_trace_del_tracer(struct trace_array *tr);
1318

1319 1320 1321
extern struct trace_event_file *find_event_file(struct trace_array *tr,
						const char *system,
						const char *event);
1322

1323 1324 1325 1326 1327
static inline void *event_file_data(struct file *filp)
{
	return ACCESS_ONCE(file_inode(filp)->i_private);
}

1328
extern struct mutex event_mutex;
1329
extern struct list_head ftrace_events;
P
Peter Zijlstra 已提交
1330

1331
extern const struct file_operations event_trigger_fops;
1332 1333 1334 1335
extern const struct file_operations event_hist_fops;

#ifdef CONFIG_HIST_TRIGGERS
extern int register_trigger_hist_cmd(void);
1336
extern int register_trigger_hist_enable_disable_cmds(void);
1337 1338
#else
static inline int register_trigger_hist_cmd(void) { return 0; }
1339
static inline int register_trigger_hist_enable_disable_cmds(void) { return 0; }
1340
#endif
1341 1342 1343 1344 1345 1346 1347 1348 1349

extern int register_trigger_cmds(void);
extern void clear_event_triggers(struct trace_array *tr);

struct event_trigger_data {
	unsigned long			count;
	int				ref;
	struct event_trigger_ops	*ops;
	struct event_command		*cmd_ops;
1350
	struct event_filter __rcu	*filter;
1351 1352
	char				*filter_str;
	void				*private_data;
1353
	bool				paused;
1354
	bool				paused_tmp;
1355
	struct list_head		list;
1356 1357 1358
	char				*name;
	struct list_head		named_list;
	struct event_trigger_data	*named_data;
1359 1360
};

1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388
/* Avoid typos */
#define ENABLE_EVENT_STR	"enable_event"
#define DISABLE_EVENT_STR	"disable_event"
#define ENABLE_HIST_STR		"enable_hist"
#define DISABLE_HIST_STR	"disable_hist"

struct enable_trigger_data {
	struct trace_event_file		*file;
	bool				enable;
	bool				hist;
};

extern int event_enable_trigger_print(struct seq_file *m,
				      struct event_trigger_ops *ops,
				      struct event_trigger_data *data);
extern void event_enable_trigger_free(struct event_trigger_ops *ops,
				      struct event_trigger_data *data);
extern int event_enable_trigger_func(struct event_command *cmd_ops,
				     struct trace_event_file *file,
				     char *glob, char *cmd, char *param);
extern int event_enable_register_trigger(char *glob,
					 struct event_trigger_ops *ops,
					 struct event_trigger_data *data,
					 struct trace_event_file *file);
extern void event_enable_unregister_trigger(char *glob,
					    struct event_trigger_ops *ops,
					    struct event_trigger_data *test,
					    struct trace_event_file *file);
1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400
extern void trigger_data_free(struct event_trigger_data *data);
extern int event_trigger_init(struct event_trigger_ops *ops,
			      struct event_trigger_data *data);
extern int trace_event_trigger_enable_disable(struct trace_event_file *file,
					      int trigger_enable);
extern void update_cond_flag(struct trace_event_file *file);
extern void unregister_trigger(char *glob, struct event_trigger_ops *ops,
			       struct event_trigger_data *test,
			       struct trace_event_file *file);
extern int set_trigger_filter(char *filter_str,
			      struct event_trigger_data *trigger_data,
			      struct trace_event_file *file);
1401 1402 1403 1404 1405 1406 1407 1408 1409
extern struct event_trigger_data *find_named_trigger(const char *name);
extern bool is_named_trigger(struct event_trigger_data *test);
extern int save_named_trigger(const char *name,
			      struct event_trigger_data *data);
extern void del_named_trigger(struct event_trigger_data *data);
extern void pause_named_trigger(struct event_trigger_data *data);
extern void unpause_named_trigger(struct event_trigger_data *data);
extern void set_named_trigger_data(struct event_trigger_data *data,
				   struct event_trigger_data *named_data);
1410
extern int register_event_command(struct event_command *cmd);
1411 1412
extern int unregister_event_command(struct event_command *cmd);
extern int register_trigger_hist_enable_disable_cmds(void);
1413

1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425
/**
 * struct event_trigger_ops - callbacks for trace event triggers
 *
 * The methods in this structure provide per-event trigger hooks for
 * various trigger operations.
 *
 * All the methods below, except for @init() and @free(), must be
 * implemented.
 *
 * @func: The trigger 'probe' function called when the triggering
 *	event occurs.  The data passed into this callback is the data
 *	that was supplied to the event_command @reg() function that
1426 1427
 *	registered the trigger (see struct event_command) along with
 *	the trace record, rec.
1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451
 *
 * @init: An optional initialization function called for the trigger
 *	when the trigger is registered (via the event_command reg()
 *	function).  This can be used to perform per-trigger
 *	initialization such as incrementing a per-trigger reference
 *	count, for instance.  This is usually implemented by the
 *	generic utility function @event_trigger_init() (see
 *	trace_event_triggers.c).
 *
 * @free: An optional de-initialization function called for the
 *	trigger when the trigger is unregistered (via the
 *	event_command @reg() function).  This can be used to perform
 *	per-trigger de-initialization such as decrementing a
 *	per-trigger reference count and freeing corresponding trigger
 *	data, for instance.  This is usually implemented by the
 *	generic utility function @event_trigger_free() (see
 *	trace_event_triggers.c).
 *
 * @print: The callback function invoked to have the trigger print
 *	itself.  This is usually implemented by a wrapper function
 *	that calls the generic utility function @event_trigger_print()
 *	(see trace_event_triggers.c).
 */
struct event_trigger_ops {
1452 1453
	void			(*func)(struct event_trigger_data *data,
					void *rec);
1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494
	int			(*init)(struct event_trigger_ops *ops,
					struct event_trigger_data *data);
	void			(*free)(struct event_trigger_ops *ops,
					struct event_trigger_data *data);
	int			(*print)(struct seq_file *m,
					 struct event_trigger_ops *ops,
					 struct event_trigger_data *data);
};

/**
 * struct event_command - callbacks and data members for event commands
 *
 * Event commands are invoked by users by writing the command name
 * into the 'trigger' file associated with a trace event.  The
 * parameters associated with a specific invocation of an event
 * command are used to create an event trigger instance, which is
 * added to the list of trigger instances associated with that trace
 * event.  When the event is hit, the set of triggers associated with
 * that event is invoked.
 *
 * The data members in this structure provide per-event command data
 * for various event commands.
 *
 * All the data members below, except for @post_trigger, must be set
 * for each event command.
 *
 * @name: The unique name that identifies the event command.  This is
 *	the name used when setting triggers via trigger files.
 *
 * @trigger_type: A unique id that identifies the event command
 *	'type'.  This value has two purposes, the first to ensure that
 *	only one trigger of the same type can be set at a given time
 *	for a particular event e.g. it doesn't make sense to have both
 *	a traceon and traceoff trigger attached to a single event at
 *	the same time, so traceon and traceoff have the same type
 *	though they have different names.  The @trigger_type value is
 *	also used as a bit value for deferring the actual trigger
 *	action until after the current event is finished.  Some
 *	commands need to do this if they themselves log to the trace
 *	buffer (see the @post_trigger() member below).  @trigger_type
 *	values are defined by adding new values to the trigger_type
1495
 *	enum in include/linux/trace_events.h.
1496
 *
1497
 * @flags: See the enum event_command_flags below.
1498
 *
1499 1500
 * All the methods below, except for @set_filter() and @unreg_all(),
 * must be implemented.
1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524
 *
 * @func: The callback function responsible for parsing and
 *	registering the trigger written to the 'trigger' file by the
 *	user.  It allocates the trigger instance and registers it with
 *	the appropriate trace event.  It makes use of the other
 *	event_command callback functions to orchestrate this, and is
 *	usually implemented by the generic utility function
 *	@event_trigger_callback() (see trace_event_triggers.c).
 *
 * @reg: Adds the trigger to the list of triggers associated with the
 *	event, and enables the event trigger itself, after
 *	initializing it (via the event_trigger_ops @init() function).
 *	This is also where commands can use the @trigger_type value to
 *	make the decision as to whether or not multiple instances of
 *	the trigger should be allowed.  This is usually implemented by
 *	the generic utility function @register_trigger() (see
 *	trace_event_triggers.c).
 *
 * @unreg: Removes the trigger from the list of triggers associated
 *	with the event, and disables the event trigger itself, after
 *	initializing it (via the event_trigger_ops @free() function).
 *	This is usually implemented by the generic utility function
 *	@unregister_trigger() (see trace_event_triggers.c).
 *
1525 1526 1527 1528
 * @unreg_all: An optional function called to remove all the triggers
 *	from the list of triggers associated with the event.  Called
 *	when a trigger file is opened in truncate mode.
 *
1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541
 * @set_filter: An optional function called to parse and set a filter
 *	for the trigger.  If no @set_filter() method is set for the
 *	event command, filters set by the user for the command will be
 *	ignored.  This is usually implemented by the generic utility
 *	function @set_trigger_filter() (see trace_event_triggers.c).
 *
 * @get_trigger_ops: The callback function invoked to retrieve the
 *	event_trigger_ops implementation associated with the command.
 */
struct event_command {
	struct list_head	list;
	char			*name;
	enum event_trigger_type	trigger_type;
1542
	int			flags;
1543
	int			(*func)(struct event_command *cmd_ops,
1544
					struct trace_event_file *file,
1545 1546 1547 1548
					char *glob, char *cmd, char *params);
	int			(*reg)(char *glob,
				       struct event_trigger_ops *ops,
				       struct event_trigger_data *data,
1549
				       struct trace_event_file *file);
1550 1551 1552
	void			(*unreg)(char *glob,
					 struct event_trigger_ops *ops,
					 struct event_trigger_data *data,
1553
					 struct trace_event_file *file);
1554
	void			(*unreg_all)(struct trace_event_file *file);
1555 1556
	int			(*set_filter)(char *filter_str,
					      struct event_trigger_data *data,
1557
					      struct trace_event_file *file);
1558 1559 1560
	struct event_trigger_ops *(*get_trigger_ops)(char *cmd, char *param);
};

1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603
/**
 * enum event_command_flags - flags for struct event_command
 *
 * @POST_TRIGGER: A flag that says whether or not this command needs
 *	to have its action delayed until after the current event has
 *	been closed.  Some triggers need to avoid being invoked while
 *	an event is currently in the process of being logged, since
 *	the trigger may itself log data into the trace buffer.  Thus
 *	we make sure the current event is committed before invoking
 *	those triggers.  To do that, the trigger invocation is split
 *	in two - the first part checks the filter using the current
 *	trace record; if a command has the @post_trigger flag set, it
 *	sets a bit for itself in the return value, otherwise it
 *	directly invokes the trigger.  Once all commands have been
 *	either invoked or set their return flag, the current record is
 *	either committed or discarded.  At that point, if any commands
 *	have deferred their triggers, those commands are finally
 *	invoked following the close of the current event.  In other
 *	words, if the event_trigger_ops @func() probe implementation
 *	itself logs to the trace buffer, this flag should be set,
 *	otherwise it can be left unspecified.
 *
 * @NEEDS_REC: A flag that says whether or not this command needs
 *	access to the trace record in order to perform its function,
 *	regardless of whether or not it has a filter associated with
 *	it (filters make a trigger require access to the trace record
 *	but are not always present).
 */
enum event_command_flags {
	EVENT_CMD_FL_POST_TRIGGER	= 1,
	EVENT_CMD_FL_NEEDS_REC		= 2,
};

static inline bool event_command_post_trigger(struct event_command *cmd_ops)
{
	return cmd_ops->flags & EVENT_CMD_FL_POST_TRIGGER;
}

static inline bool event_command_needs_rec(struct event_command *cmd_ops)
{
	return cmd_ops->flags & EVENT_CMD_FL_NEEDS_REC;
}

1604
extern int trace_event_enable_disable(struct trace_event_file *file,
1605
				      int enable, int soft_disable);
1606
extern int tracing_alloc_snapshot(void);
1607

1608 1609 1610
extern const char *__start___trace_bprintk_fmt[];
extern const char *__stop___trace_bprintk_fmt[];

1611 1612 1613
extern const char *__start___tracepoint_str[];
extern const char *__stop___tracepoint_str[];

1614
void trace_printk_control(bool enabled);
1615
void trace_printk_init_buffers(void);
1616
void trace_printk_start_comm(void);
1617
int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set);
1618
int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled);
1619

1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630
/*
 * 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))

1631
#undef FTRACE_ENTRY
1632
#define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter)	\
1633
	extern struct trace_event_call					\
1634
	__aligned(4) event_##call;
1635
#undef FTRACE_ENTRY_DUP
1636 1637 1638
#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter)	\
	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \
		     filter)
1639 1640 1641 1642 1643
#undef FTRACE_ENTRY_PACKED
#define FTRACE_ENTRY_PACKED(call, struct_name, id, tstruct, print, filter) \
	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \
		     filter)

1644
#include "trace_entries.h"
1645

1646
#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_FUNCTION_TRACER)
1647
int perf_ftrace_event_register(struct trace_event_call *call,
1648 1649 1650
			       enum trace_reg type, void *data);
#else
#define perf_ftrace_event_register NULL
1651
#endif
1652

1653 1654
#ifdef CONFIG_FTRACE_SYSCALLS
void init_ftrace_syscalls(void);
T
Tom Zanussi 已提交
1655
const char *get_syscall_name(int syscall);
1656 1657
#else
static inline void init_ftrace_syscalls(void) { }
T
Tom Zanussi 已提交
1658 1659 1660 1661
static inline const char *get_syscall_name(int syscall)
{
	return NULL;
}
1662 1663 1664 1665
#endif

#ifdef CONFIG_EVENT_TRACING
void trace_event_init(void);
1666
void trace_event_enum_update(struct trace_enum_map **map, int len);
1667 1668
#else
static inline void __init trace_event_init(void) { }
1669
static inline void trace_event_enum_update(struct trace_enum_map **map, int len) { }
1670 1671
#endif

1672
extern struct trace_iterator *tracepoint_print_iter;
1673

1674
#endif /* _LINUX_KERNEL_TRACE_H */