2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-22 12:14:01 +08:00
linux-next/include/linux/ftrace_event.h
Steven Rostedt a63ce5b306 tracing: Buffer the output of seq_file in case of filled buffer
If the seq_read fills the buffer it will call s_start again on the next
itertation with the same position. This causes a problem with the
function_graph tracer because it consumes the iteration in order to
determine leaf functions.

What happens is that the iterator stores the entry, and the function
graph plugin will look at the next entry. If that next entry is a return
of the same function and task, then the function is a leaf and the
function_graph plugin calls ring_buffer_read which moves the ring buffer
iterator forward (the trace iterator still points to the function start
entry).

The copying of the trace_seq to the seq_file buffer will fail if the
seq_file buffer is full. The seq_read will not show this entry.
The next read by userspace will cause seq_read to again call s_start
which will reuse the trace iterator entry (the function start entry).
But the function return entry was already consumed. The function graph
plugin will think that this entry is a nested function and not a leaf.

To solve this, the trace code now checks the return status of the
seq_printf (trace_print_seq). If the writing to the seq_file buffer
fails, we set a flag in the iterator (leftover) and we do not reset
the trace_seq buffer. On the next call to s_start, we check the leftover
flag, and if it is set, we just reuse the trace_seq buffer and do not
call into the plugin print functions.

Before this patch:

 2)               |      fput() {
 2)               |        __fput() {
 2)   0.550 us    |          inotify_inode_queue_event();
 2)               |          __fsnotify_parent() {
 2)   0.540 us    |          inotify_dentry_parent_queue_event();

After the patch:

 2)               |      fput() {
 2)               |        __fput() {
 2)   0.550 us    |          inotify_inode_queue_event();
 2)   0.548 us    |          __fsnotify_parent();
 2)   0.540 us    |          inotify_dentry_parent_queue_event();

[
  Updated the patch to fix a missing return 0 from the trace_print_seq()
  stub when CONFIG_TRACING is disabled.

  Reported-by: Ingo Molnar <mingo@elte.hu>
]

Reported-by: Jiri Olsa <jolsa@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-12-09 13:55:26 -05:00

201 lines
5.7 KiB
C

#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>
struct trace_array;
struct tracer;
struct dentry;
DECLARE_PER_CPU(struct trace_seq, ftrace_event_seq);
struct trace_print_flags {
unsigned 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);
/*
* 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;
int lock_depth;
};
#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;
void *private;
int cpu_file;
struct mutex mutex;
struct ring_buffer_iter *buffer_iter[NR_CPUS];
unsigned long iter_flags;
/* The below is zeroed out in pipe_read */
struct trace_seq seq;
struct trace_entry *ent;
int leftover;
int cpu;
u64 ts;
loff_t pos;
long idx;
cpumask_var_t started;
};
typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter,
int flags);
struct trace_event {
struct hlist_node node;
struct list_head list;
int type;
trace_print_func trace;
trace_print_func raw;
trace_print_func hex;
trace_print_func binary;
};
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 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_nowake_buffer_unlock_commit(struct ring_buffer *buffer,
struct ring_buffer_event *event,
unsigned long flags, int pc);
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;
struct ftrace_event_call {
struct list_head list;
char *name;
char *system;
struct dentry *dir;
struct trace_event *event;
int enabled;
int (*regfunc)(struct ftrace_event_call *);
void (*unregfunc)(struct ftrace_event_call *);
int id;
int (*raw_init)(struct ftrace_event_call *);
int (*show_format)(struct ftrace_event_call *,
struct trace_seq *);
int (*define_fields)(struct ftrace_event_call *);
struct list_head fields;
int filter_active;
struct event_filter *filter;
void *mod;
void *data;
atomic_t profile_count;
int (*profile_enable)(struct ftrace_event_call *);
void (*profile_disable)(struct ftrace_event_call *);
};
#define FTRACE_MAX_PROFILE_SIZE 2048
extern char *perf_trace_buf;
extern char *perf_trace_buf_nmi;
#define MAX_FILTER_PRED 32
#define MAX_FILTER_STR_VAL 256 /* Should handle KSYM_SYMBOL_LEN */
extern void destroy_preds(struct ftrace_event_call *call);
extern int filter_match_preds(struct event_filter *filter, void *rec);
extern int filter_current_check_discard(struct ring_buffer *buffer,
struct ftrace_event_call *call,
void *rec,
struct ring_buffer_event *event);
enum {
FILTER_OTHER = 0,
FILTER_STATIC_STRING,
FILTER_DYN_STRING,
FILTER_PTR_STRING,
};
extern int trace_define_common_fields(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 void trace_remove_event_call(struct ftrace_event_call *call);
#define is_signed_type(type) (((type)(-1)) < 0)
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)
#ifdef CONFIG_EVENT_PROFILE
struct perf_event;
extern int ftrace_profile_enable(int event_id);
extern void ftrace_profile_disable(int event_id);
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);
#endif
#endif /* _LINUX_FTRACE_EVENT_H */