aboutsummaryrefslogtreecommitdiffstats
path: root/include/linux/ftrace_event.h
blob: 8c9b7a1c4138b87a79833bc400370a13e94cf270 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
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
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
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
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
#ifndef _LINUX_FTRACE_EVENT_H
#define _LINUX_FTRACE_EVENT_H

#include <linux/ring_buffer.h>
#include <linux/trace_seq.h>
#include <linux/percpu.h>
#include <linux/hardirq.h>
#include <linux/perf_event.h>

struct trace_array;
struct trace_buffer;
struct tracer;
struct dentry;

struct trace_print_flags {
	unsigned long		mask;
	const char		*name;
};

struct trace_print_flags_u64 {
	unsigned long long	mask;
	const char		*name;
};

const char *ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
				   unsigned long flags,
				   const struct trace_print_flags *flag_array);

const char *ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
				     const struct trace_print_flags *symbol_array);

#if BITS_PER_LONG == 32
const char *ftrace_print_symbols_seq_u64(struct trace_seq *p,
					 unsigned long long val,
					 const struct trace_print_flags_u64
								 *symbol_array);
#endif

const char *ftrace_print_hex_seq(struct trace_seq *p,
				 const unsigned char *buf, int len);

struct trace_iterator;
struct trace_event;

int ftrace_raw_output_prep(struct trace_iterator *iter,
			   struct trace_event *event);

/*
 * The trace entry - the most basic unit of tracing. This is what
 * is printed in the end as a single line in the trace output, such as:
 *
 *     bash-15816 [01]   235.197585: idle_cpu <- irq_enter
 */
struct trace_entry {
	unsigned short		type;
	unsigned char		flags;
	unsigned char		preempt_count;
	int			pid;
};

#define FTRACE_MAX_EVENT						\
	((1 << (sizeof(((struct trace_entry *)0)->type) * 8)) - 1)

/*
 * Trace iterator - used by printout routines who present trace
 * results to users and which routines might sleep, etc:
 */
struct trace_iterator {
	struct trace_array	*tr;
	struct tracer		*trace;
	struct trace_buffer	*trace_buffer;
	void			*private;
	int			cpu_file;
	struct mutex		mutex;
	struct ring_buffer_iter	**buffer_iter;
	unsigned long		iter_flags;

	/* trace_seq for __print_flags() and __print_symbolic() etc. */
	struct trace_seq	tmp_seq;

	cpumask_var_t		started;

	/* it's true when current open file is snapshot */
	bool			snapshot;

	/* The below is zeroed out in pipe_read */
	struct trace_seq	seq;
	struct trace_entry	*ent;
	unsigned long		lost_events;
	int			leftover;
	int			ent_size;
	int			cpu;
	u64			ts;

	loff_t			pos;
	long			idx;

	/* All new field here will be zeroed out in pipe_read */
};

enum trace_iter_flags {
	TRACE_FILE_LAT_FMT	= 1,
	TRACE_FILE_ANNOTATE	= 2,
	TRACE_FILE_TIME_IN_NS	= 4,
};


typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter,
				      int flags, struct trace_event *event);

struct trace_event_functions {
	trace_print_func	trace;
	trace_print_func	raw;
	trace_print_func	hex;
	trace_print_func	binary;
};

struct trace_event {
	struct hlist_node		node;
	struct list_head		list;
	int				type;
	struct trace_event_functions	*funcs;
};

extern int register_ftrace_event(struct trace_event *event);
extern int unregister_ftrace_event(struct trace_event *event);

/* Return values for print_line callback */
enum print_line_t {
	TRACE_TYPE_PARTIAL_LINE	= 0,	/* Retry after flushing the seq */
	TRACE_TYPE_HANDLED	= 1,
	TRACE_TYPE_UNHANDLED	= 2,	/* Relay to other output functions */
	TRACE_TYPE_NO_CONSUME	= 3	/* Handled but ask to not consume */
};

void tracing_generic_entry_update(struct trace_entry *entry,
				  unsigned long flags,
				  int pc);
struct ftrace_event_file;

struct ring_buffer_event *
trace_event_buffer_lock_reserve(struct ring_buffer **current_buffer,
				struct ftrace_event_file *ftrace_file,
				int type, unsigned long len,
				unsigned long flags, int pc);
struct ring_buffer_event *
trace_current_buffer_lock_reserve(struct ring_buffer **current_buffer,
				  int type, unsigned long len,
				  unsigned long flags, int pc);
void trace_current_buffer_unlock_commit(struct ring_buffer *buffer,
					struct ring_buffer_event *event,
					unsigned long flags, int pc);
void trace_buffer_unlock_commit(struct ring_buffer *buffer,
				struct ring_buffer_event *event,
				unsigned long flags, int pc);
void trace_buffer_unlock_commit_regs(struct ring_buffer *buffer,
				     struct ring_buffer_event *event,
				     unsigned long flags, int pc,
				     struct pt_regs *regs);
void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
					 struct ring_buffer_event *event);

void tracing_record_cmdline(struct task_struct *tsk);

struct event_filter;

enum trace_reg {
	TRACE_REG_REGISTER,
	TRACE_REG_UNREGISTER,
#ifdef CONFIG_PERF_EVENTS
	TRACE_REG_PERF_REGISTER,
	TRACE_REG_PERF_UNREGISTER,
	TRACE_REG_PERF_OPEN,
	TRACE_REG_PERF_CLOSE,
	TRACE_REG_PERF_ADD,
	TRACE_REG_PERF_DEL,
#endif
};

struct ftrace_event_call;

struct ftrace_event_class {
	char			*system;
	void			*probe;
#ifdef CONFIG_PERF_EVENTS
	void			*perf_probe;
#endif
	int			(*reg)(struct ftrace_event_call *event,
				       enum trace_reg type, void *data);
	int			(*define_fields)(struct ftrace_event_call *);
	struct list_head	*(*get_fields)(struct ftrace_event_call *);
	struct list_head	fields;
	int			(*raw_init)(struct ftrace_event_call *);
};

extern int ftrace_event_reg(struct ftrace_event_call *event,
			    enum trace_reg type, void *data);

enum {
	TRACE_EVENT_FL_FILTERED_BIT,
	TRACE_EVENT_FL_CAP_ANY_BIT,
	TRACE_EVENT_FL_NO_SET_FILTER_BIT,
	TRACE_EVENT_FL_IGNORE_ENABLE_BIT,
	TRACE_EVENT_FL_WAS_ENABLED_BIT,
	TRACE_EVENT_FL_USE_CALL_FILTER_BIT,
};

/*
 * Event flags:
 *  FILTERED	  - The event has a filter attached
 *  CAP_ANY	  - Any user can enable for perf
 *  NO_SET_FILTER - Set when filter has error and is to be ignored
 *  IGNORE_ENABLE - For ftrace internal events, do not enable with debugfs file
 *  WAS_ENABLED   - Set and stays set when an event was ever enabled
 *                    (used for module unloading, if a module event is enabled,
 *                     it is best to clear the buffers that used it).
 *  USE_CALL_FILTER - For ftrace internal events, don't use file filter
 */
enum {
	TRACE_EVENT_FL_FILTERED		= (1 << TRACE_EVENT_FL_FILTERED_BIT),
	TRACE_EVENT_FL_CAP_ANY		= (1 << TRACE_EVENT_FL_CAP_ANY_BIT),
	TRACE_EVENT_FL_NO_SET_FILTER	= (1 << TRACE_EVENT_FL_NO_SET_FILTER_BIT),
	TRACE_EVENT_FL_IGNORE_ENABLE	= (1 << TRACE_EVENT_FL_IGNORE_ENABLE_BIT),
	TRACE_EVENT_FL_WAS_ENABLED	= (1 << TRACE_EVENT_FL_WAS_ENABLED_BIT),
	TRACE_EVENT_FL_USE_CALL_FILTER	= (1 << TRACE_EVENT_FL_USE_CALL_FILTER_BIT),
};

struct ftrace_event_call {
	struct list_head	list;
	struct ftrace_event_class *class;
	char			*name;
	struct trace_event	event;
	const char		*print_fmt;
	struct event_filter	*filter;
	struct list_head	*files;
	void			*mod;
	void			*data;
	/*
	 *   bit 0:		filter_active
	 *   bit 1:		allow trace by non root (cap any)
	 *   bit 2:		failed to apply filter
	 *   bit 3:		ftrace internal event (do not enable)
	 *   bit 4:		Event was enabled by module
	 *   bit 5:		use call filter rather than file filter
	 */
	int			flags; /* static flags of different events */

#ifdef CONFIG_PERF_EVENTS
	int				perf_refcount;
	struct hlist_head __percpu	*perf_events;

	int	(*perf_perm)(struct ftrace_event_call *,
			     struct perf_event *);
#endif
};

struct trace_array;
struct ftrace_subsystem_dir;

enum {
	FTRACE_EVENT_FL_ENABLED_BIT,
	FTRACE_EVENT_FL_RECORDED_CMD_BIT,
	FTRACE_EVENT_FL_FILTERED_BIT,
	FTRACE_EVENT_FL_NO_SET_FILTER_BIT,
	FTRACE_EVENT_FL_SOFT_MODE_BIT,
	FTRACE_EVENT_FL_SOFT_DISABLED_BIT,
};

/*
 * Ftrace event file flags:
 *  ENABLED	  - The event is enabled
 *  RECORDED_CMD  - The comms should be recorded at sched_switch
 *  FILTERED	  - The event has a filter attached
 *  NO_SET_FILTER - Set when filter has error and is to be ignored
 *  SOFT_MODE     - The event is enabled/disabled by SOFT_DISABLED
 *  SOFT_DISABLED - When set, do not trace the event (even though its
 *                   tracepoint may be enabled)
 */
enum {
	FTRACE_EVENT_FL_ENABLED		= (1 << FTRACE_EVENT_FL_ENABLED_BIT),
	FTRACE_EVENT_FL_RECORDED_CMD	= (1 << FTRACE_EVENT_FL_RECORDED_CMD_BIT),
	FTRACE_EVENT_FL_FILTERED	= (1 << FTRACE_EVENT_FL_FILTERED_BIT),
	FTRACE_EVENT_FL_NO_SET_FILTER	= (1 << FTRACE_EVENT_FL_NO_SET_FILTER_BIT),
	FTRACE_EVENT_FL_SOFT_MODE	= (1 << FTRACE_EVENT_FL_SOFT_MODE_BIT),
	FTRACE_EVENT_FL_SOFT_DISABLED	= (1 << FTRACE_EVENT_FL_SOFT_DISABLED_BIT),
};

struct ftrace_event_file {
	struct list_head		list;
	struct ftrace_event_call	*event_call;
	struct event_filter		*filter;
	struct dentry			*dir;
	struct trace_array		*tr;
	struct ftrace_subsystem_dir	*system;

	/*
	 * 32 bit flags:
	 *   bit 0:		enabled
	 *   bit 1:		enabled cmd record
	 *   bit 2:		enable/disable with the soft disable bit
	 *   bit 3:		soft disabled
	 *
	 * Note: The bits must be set atomically to prevent races
	 * from other writers. Reads of flags do not need to be in
	 * sync as they occur in critical sections. But the way flags
	 * is currently used, these changes do not affect the code
	 * except that when a change is made, it may have a slight
	 * delay in propagating the changes to other CPUs due to
	 * caching and such. Which is mostly OK ;-)
	 */
	unsigned long		flags;
	atomic_t		sm_ref;	/* soft-mode reference counter */
};

#define __TRACE_EVENT_FLAGS(name, value)				\
	static int __init trace_init_flags_##name(void)			\
	{								\
		event_##name.flags = value;				\
		return 0;						\
	}								\
	early_initcall(trace_init_flags_##name);

#define __TRACE_EVENT_PERF_PERM(name, expr...)				\
	static int perf_perm_##name(struct ftrace_event_call *tp_event, \
				    struct perf_event *p_event)		\
	{								\
		return ({ expr; });					\
	}								\
	static int __init trace_init_perf_perm_##name(void)		\
	{								\
		event_##name.perf_perm = &perf_perm_##name;		\
		return 0;						\
	}								\
	early_initcall(trace_init_perf_perm_##name);

#define PERF_MAX_TRACE_SIZE	2048

#define MAX_FILTER_STR_VAL	256	/* Should handle KSYM_SYMBOL_LEN */

extern void destroy_preds(struct ftrace_event_file *file);
extern void destroy_call_preds(struct ftrace_event_call *call);
extern int filter_match_preds(struct event_filter *filter, void *rec);

extern int filter_check_discard(struct ftrace_event_file *file, void *rec,
				struct ring_buffer *buffer,
				struct ring_buffer_event *event);
extern int call_filter_check_discard(struct ftrace_event_call *call, void *rec,
				     struct ring_buffer *buffer,
				     struct ring_buffer_event *event);

enum {
	FILTER_OTHER = 0,
	FILTER_STATIC_STRING,
	FILTER_DYN_STRING,
	FILTER_PTR_STRING,
	FILTER_TRACE_FN,
};

#define EVENT_STORAGE_SIZE 128
extern struct mutex event_storage_mutex;
extern char event_storage[EVENT_STORAGE_SIZE];

extern int trace_event_raw_init(struct ftrace_event_call *call);
extern int trace_define_field(struct ftrace_event_call *call, const char *type,
			      const char *name, int offset, int size,
			      int is_signed, int filter_type);
extern int trace_add_event_call(struct ftrace_event_call *call);
extern int trace_remove_event_call(struct ftrace_event_call *call);

#define is_signed_type(type)	(((type)(-1)) < (type)1)

int trace_set_clr_event(const char *system, const char *event, int set);

/*
 * The double __builtin_constant_p is because gcc will give us an error
 * if we try to allocate the static variable to fmt if it is not a
 * constant. Even with the outer if statement optimizing out.
 */
#define event_trace_printk(ip, fmt, args...)				\
do {									\
	__trace_printk_check_format(fmt, ##args);			\
	tracing_record_cmdline(current);				\
	if (__builtin_constant_p(fmt)) {				\
		static const char *trace_printk_fmt			\
		  __attribute__((section("__trace_printk_fmt"))) =	\
			__builtin_constant_p(fmt) ? fmt : NULL;		\
									\
		__trace_bprintk(ip, trace_printk_fmt, ##args);		\
	} else								\
		__trace_printk(ip, fmt, ##args);			\
} while (0)

/**
 * tracepoint_string - register constant persistent string to trace system
 * @str - a constant persistent string that will be referenced in tracepoints
 *
 * If constant strings are being used in tracepoints, it is faster and
 * more efficient to just save the pointer to the string and reference
 * that with a printf "%s" instead of saving the string in the ring buffer
 * and wasting space and time.
 *
 * The problem with the above approach is that userspace tools that read
 * the binary output of the trace buffers do not have access to the string.
 * Instead they just show the address of the string which is not very
 * useful to users.
 *
 * With tracepoint_string(), the string will be registered to the tracing
 * system and exported to userspace via the debugfs/tracing/printk_formats
 * file that maps the string address to the string text. This way userspace
 * tools that read the binary buffers have a way to map the pointers to
 * the ASCII strings they represent.
 *
 * The @str used must be a constant string and persistent as it would not
 * make sense to show a string that no longer exists. But it is still fine
 * to be used with modules, because when modules are unloaded, if they
 * had tracepoints, the ring buffers are cleared too. As long as the string
 * does not change during the life of the module, it is fine to use
 * tracepoint_string() within a module.
 */
#define tracepoint_string(str)						\
	({								\
		static const char *___tp_str __tracepoint_string = str; \
		___tp_str;						\
	})
#define __tracepoint_string	__attribute__((section("__tracepoint_str")))

#ifdef CONFIG_PERF_EVENTS
struct perf_event;

DECLARE_PER_CPU(struct pt_regs, perf_trace_regs);

extern int  perf_trace_init(struct perf_event *event);
extern void perf_trace_destroy(struct perf_event *event);
extern int  perf_trace_add(struct perf_event *event, int flags);
extern void perf_trace_del(struct perf_event *event, int flags);
extern int  ftrace_profile_set_filter(struct perf_event *event, int event_id,
				     char *filter_str);
extern void ftrace_profile_free_filter(struct perf_event *event);
extern void *perf_trace_buf_prepare(int size, unsigned short type,
				    struct pt_regs *regs, int *rctxp);

static inline void
perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr,
		       u64 count, struct pt_regs *regs, void *head,
		       struct task_struct *task)
{
	perf_tp_event(addr, count, raw_data, size, regs, head, rctx, task);
}
#endif

#endif /* _LINUX_FTRACE_EVENT_H */