mirror of
https://github.com/torvalds/linux.git
synced 2024-11-14 16:12:02 +00:00
b156040869
When eventfs was introduced, special care had to be done to coordinate the
freeing of the file meta data with the files that are exposed to user
space. The file meta data would have a ref count that is set when the file
is created and would be decremented and freed after the last user that
opened the file closed it. When the file meta data was to be freed, it
would set a flag (EVENT_FILE_FL_FREED) to denote that the file is freed,
and any new references made (like new opens or reads) would fail as it is
marked freed. This allowed other meta data to be freed after this flag was
set (under the event_mutex).
All the files that were dynamically created in the events directory had a
pointer to the file meta data and would call event_release() when the last
reference to the user space file was closed. This would be the time that it
is safe to free the file meta data.
A shortcut was made for the "format" file. It's i_private would point to
the "call" entry directly and not point to the file's meta data. This is
because all format files are the same for the same "call", so it was
thought there was no reason to differentiate them. The other files
maintain state (like the "enable", "trigger", etc). But this meant if the
file were to disappear, the "format" file would be unaware of it.
This caused a race that could be trigger via the user_events test (that
would create dynamic events and free them), and running a loop that would
read the user_events format files:
In one console run:
# cd tools/testing/selftests/user_events
# while true; do ./ftrace_test; done
And in another console run:
# cd /sys/kernel/tracing/
# while true; do cat events/user_events/__test_event/format; done 2>/dev/null
With KASAN memory checking, it would trigger a use-after-free bug report
(which was a real bug). This was because the format file was not checking
the file's meta data flag "EVENT_FILE_FL_FREED", so it would access the
event that the file meta data pointed to after the event was freed.
After inspection, there are other locations that were found to not check
the EVENT_FILE_FL_FREED flag when accessing the trace_event_file. Add a
new helper function: event_file_file() that will make sure that the
event_mutex is held, and will return NULL if the trace_event_file has the
EVENT_FILE_FL_FREED flag set. Have the first reference of the struct file
pointer use event_file_file() and check for NULL. Later uses can still use
the event_file_data() helper function if the event_mutex is still held and
was not released since the event_file_file() call.
Link: https://lore.kernel.org/all/20240719204701.1605950-1-minipli@grsecurity.net/
Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Ajay Kaher <ajay.kaher@broadcom.com>
Cc: Ilkka Naulapää <digirigawa@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dan Carpenter <dan.carpenter@linaro.org>
Cc: Beau Belgrave <beaub@linux.microsoft.com>
Cc: Florian Fainelli <florian.fainelli@broadcom.com>
Cc: Alexey Makhalov <alexey.makhalov@broadcom.com>
Cc: Vasavi Sirnapalli <vasavi.sirnapalli@broadcom.com>
Link: https://lore.kernel.org/20240730110657.3b69d3c1@gandalf.local.home
Fixes: b63db58e2f
("eventfs/tracing: Add callback for release of an eventfs_inode")
Reported-by: Mathias Krause <minipli@grsecurity.net>
Tested-by: Mathias Krause <minipli@grsecurity.net>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
2170 lines
70 KiB
C
2170 lines
70 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
|
|
#ifndef _LINUX_KERNEL_TRACE_H
|
|
#define _LINUX_KERNEL_TRACE_H
|
|
|
|
#include <linux/fs.h>
|
|
#include <linux/atomic.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/clocksource.h>
|
|
#include <linux/ring_buffer.h>
|
|
#include <linux/mmiotrace.h>
|
|
#include <linux/tracepoint.h>
|
|
#include <linux/ftrace.h>
|
|
#include <linux/trace.h>
|
|
#include <linux/hw_breakpoint.h>
|
|
#include <linux/trace_seq.h>
|
|
#include <linux/trace_events.h>
|
|
#include <linux/compiler.h>
|
|
#include <linux/glob.h>
|
|
#include <linux/irq_work.h>
|
|
#include <linux/workqueue.h>
|
|
#include <linux/ctype.h>
|
|
#include <linux/once_lite.h>
|
|
|
|
#include "pid_list.h"
|
|
|
|
#ifdef CONFIG_FTRACE_SYSCALLS
|
|
#include <asm/unistd.h> /* For NR_syscalls */
|
|
#include <asm/syscall.h> /* some archs define it here */
|
|
#endif
|
|
|
|
#define TRACE_MODE_WRITE 0640
|
|
#define TRACE_MODE_READ 0440
|
|
|
|
enum trace_type {
|
|
__TRACE_FIRST_TYPE = 0,
|
|
|
|
TRACE_FN,
|
|
TRACE_CTX,
|
|
TRACE_WAKE,
|
|
TRACE_STACK,
|
|
TRACE_PRINT,
|
|
TRACE_BPRINT,
|
|
TRACE_MMIO_RW,
|
|
TRACE_MMIO_MAP,
|
|
TRACE_BRANCH,
|
|
TRACE_GRAPH_RET,
|
|
TRACE_GRAPH_ENT,
|
|
TRACE_USER_STACK,
|
|
TRACE_BLK,
|
|
TRACE_BPUTS,
|
|
TRACE_HWLAT,
|
|
TRACE_OSNOISE,
|
|
TRACE_TIMERLAT,
|
|
TRACE_RAW_DATA,
|
|
TRACE_FUNC_REPEATS,
|
|
|
|
__TRACE_LAST_TYPE,
|
|
};
|
|
|
|
|
|
#undef __field
|
|
#define __field(type, item) type item;
|
|
|
|
#undef __field_fn
|
|
#define __field_fn(type, item) type item;
|
|
|
|
#undef __field_struct
|
|
#define __field_struct(type, item) __field(type, item)
|
|
|
|
#undef __field_desc
|
|
#define __field_desc(type, container, item)
|
|
|
|
#undef __field_packed
|
|
#define __field_packed(type, container, item)
|
|
|
|
#undef __array
|
|
#define __array(type, item, size) type item[size];
|
|
|
|
/*
|
|
* For backward compatibility, older user space expects to see the
|
|
* kernel_stack event with a fixed size caller field. But today the fix
|
|
* size is ignored by the kernel, and the real structure is dynamic.
|
|
* Expose to user space: "unsigned long caller[8];" but the real structure
|
|
* will be "unsigned long caller[] __counted_by(size)"
|
|
*/
|
|
#undef __stack_array
|
|
#define __stack_array(type, item, size, field) type item[] __counted_by(field);
|
|
|
|
#undef __array_desc
|
|
#define __array_desc(type, container, item, size)
|
|
|
|
#undef __dynamic_array
|
|
#define __dynamic_array(type, item) type item[];
|
|
|
|
#undef __rel_dynamic_array
|
|
#define __rel_dynamic_array(type, item) type item[];
|
|
|
|
#undef F_STRUCT
|
|
#define F_STRUCT(args...) args
|
|
|
|
#undef FTRACE_ENTRY
|
|
#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \
|
|
struct struct_name { \
|
|
struct trace_entry ent; \
|
|
tstruct \
|
|
}
|
|
|
|
#undef FTRACE_ENTRY_DUP
|
|
#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk)
|
|
|
|
#undef FTRACE_ENTRY_REG
|
|
#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, regfn) \
|
|
FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print))
|
|
|
|
#undef FTRACE_ENTRY_PACKED
|
|
#define FTRACE_ENTRY_PACKED(name, struct_name, id, tstruct, print) \
|
|
FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print)) __packed
|
|
|
|
#include "trace_entries.h"
|
|
|
|
/* Use this for memory failure errors */
|
|
#define MEM_FAIL(condition, fmt, ...) \
|
|
DO_ONCE_LITE_IF(condition, pr_err, "ERROR: " fmt, ##__VA_ARGS__)
|
|
|
|
#define FAULT_STRING "(fault)"
|
|
|
|
#define HIST_STACKTRACE_DEPTH 16
|
|
#define HIST_STACKTRACE_SIZE (HIST_STACKTRACE_DEPTH * sizeof(unsigned long))
|
|
#define HIST_STACKTRACE_SKIP 5
|
|
|
|
/*
|
|
* syscalls are special, and need special handling, this is why
|
|
* they are not included in trace_entries.h
|
|
*/
|
|
struct syscall_trace_enter {
|
|
struct trace_entry ent;
|
|
int nr;
|
|
unsigned long args[];
|
|
};
|
|
|
|
struct syscall_trace_exit {
|
|
struct trace_entry ent;
|
|
int nr;
|
|
long ret;
|
|
};
|
|
|
|
struct kprobe_trace_entry_head {
|
|
struct trace_entry ent;
|
|
unsigned long ip;
|
|
};
|
|
|
|
struct eprobe_trace_entry_head {
|
|
struct trace_entry ent;
|
|
};
|
|
|
|
struct kretprobe_trace_entry_head {
|
|
struct trace_entry ent;
|
|
unsigned long func;
|
|
unsigned long ret_ip;
|
|
};
|
|
|
|
struct fentry_trace_entry_head {
|
|
struct trace_entry ent;
|
|
unsigned long ip;
|
|
};
|
|
|
|
struct fexit_trace_entry_head {
|
|
struct trace_entry ent;
|
|
unsigned long func;
|
|
unsigned long ret_ip;
|
|
};
|
|
|
|
#define TRACE_BUF_SIZE 1024
|
|
|
|
struct trace_array;
|
|
|
|
/*
|
|
* 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;
|
|
void *buffer_page; /* ring buffer spare */
|
|
|
|
unsigned long entries;
|
|
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;
|
|
unsigned long skipped_entries;
|
|
u64 preempt_timestamp;
|
|
pid_t pid;
|
|
kuid_t uid;
|
|
char comm[TASK_COMM_LEN];
|
|
|
|
#ifdef CONFIG_FUNCTION_TRACER
|
|
int ftrace_ignore_pid;
|
|
#endif
|
|
bool ignore_pid;
|
|
};
|
|
|
|
struct tracer;
|
|
struct trace_option_dentry;
|
|
|
|
struct array_buffer {
|
|
struct trace_array *tr;
|
|
struct trace_buffer *buffer;
|
|
struct trace_array_cpu __percpu *data;
|
|
u64 time_start;
|
|
int cpu;
|
|
};
|
|
|
|
#define TRACE_FLAGS_MAX_SIZE 32
|
|
|
|
struct trace_options {
|
|
struct tracer *tracer;
|
|
struct trace_option_dentry *topts;
|
|
};
|
|
|
|
struct trace_pid_list *trace_pid_list_alloc(void);
|
|
void trace_pid_list_free(struct trace_pid_list *pid_list);
|
|
bool trace_pid_list_is_set(struct trace_pid_list *pid_list, unsigned int pid);
|
|
int trace_pid_list_set(struct trace_pid_list *pid_list, unsigned int pid);
|
|
int trace_pid_list_clear(struct trace_pid_list *pid_list, unsigned int pid);
|
|
int trace_pid_list_first(struct trace_pid_list *pid_list, unsigned int *pid);
|
|
int trace_pid_list_next(struct trace_pid_list *pid_list, unsigned int pid,
|
|
unsigned int *next);
|
|
|
|
enum {
|
|
TRACE_PIDS = BIT(0),
|
|
TRACE_NO_PIDS = BIT(1),
|
|
};
|
|
|
|
static inline bool pid_type_enabled(int type, struct trace_pid_list *pid_list,
|
|
struct trace_pid_list *no_pid_list)
|
|
{
|
|
/* Return true if the pid list in type has pids */
|
|
return ((type & TRACE_PIDS) && pid_list) ||
|
|
((type & TRACE_NO_PIDS) && no_pid_list);
|
|
}
|
|
|
|
static inline bool still_need_pid_events(int type, struct trace_pid_list *pid_list,
|
|
struct trace_pid_list *no_pid_list)
|
|
{
|
|
/*
|
|
* Turning off what is in @type, return true if the "other"
|
|
* pid list, still has pids in it.
|
|
*/
|
|
return (!(type & TRACE_PIDS) && pid_list) ||
|
|
(!(type & TRACE_NO_PIDS) && no_pid_list);
|
|
}
|
|
|
|
typedef bool (*cond_update_fn_t)(struct trace_array *tr, void *cond_data);
|
|
|
|
/**
|
|
* struct cond_snapshot - conditional snapshot data and callback
|
|
*
|
|
* The cond_snapshot structure encapsulates a callback function and
|
|
* data associated with the snapshot for a given tracing instance.
|
|
*
|
|
* When a snapshot is taken conditionally, by invoking
|
|
* tracing_snapshot_cond(tr, cond_data), the cond_data passed in is
|
|
* passed in turn to the cond_snapshot.update() function. That data
|
|
* can be compared by the update() implementation with the cond_data
|
|
* contained within the struct cond_snapshot instance associated with
|
|
* the trace_array. Because the tr->max_lock is held throughout the
|
|
* update() call, the update() function can directly retrieve the
|
|
* cond_snapshot and cond_data associated with the per-instance
|
|
* snapshot associated with the trace_array.
|
|
*
|
|
* The cond_snapshot.update() implementation can save data to be
|
|
* associated with the snapshot if it decides to, and returns 'true'
|
|
* in that case, or it returns 'false' if the conditional snapshot
|
|
* shouldn't be taken.
|
|
*
|
|
* The cond_snapshot instance is created and associated with the
|
|
* user-defined cond_data by tracing_cond_snapshot_enable().
|
|
* Likewise, the cond_snapshot instance is destroyed and is no longer
|
|
* associated with the trace instance by
|
|
* tracing_cond_snapshot_disable().
|
|
*
|
|
* The method below is required.
|
|
*
|
|
* @update: When a conditional snapshot is invoked, the update()
|
|
* callback function is invoked with the tr->max_lock held. The
|
|
* update() implementation signals whether or not to actually
|
|
* take the snapshot, by returning 'true' if so, 'false' if no
|
|
* snapshot should be taken. Because the max_lock is held for
|
|
* the duration of update(), the implementation is safe to
|
|
* directly retrieved and save any implementation data it needs
|
|
* to in association with the snapshot.
|
|
*/
|
|
struct cond_snapshot {
|
|
void *cond_data;
|
|
cond_update_fn_t update;
|
|
};
|
|
|
|
/*
|
|
* struct trace_func_repeats - used to keep track of the consecutive
|
|
* (on the same CPU) calls of a single function.
|
|
*/
|
|
struct trace_func_repeats {
|
|
unsigned long ip;
|
|
unsigned long parent_ip;
|
|
unsigned long count;
|
|
u64 ts_last_call;
|
|
};
|
|
|
|
/*
|
|
* 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 {
|
|
struct list_head list;
|
|
char *name;
|
|
struct array_buffer array_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 array_buffer
|
|
* When a snapshot is taken, the buffer of the max_buffer is swapped
|
|
* with the buffer of the array_buffer and the buffers are reset for
|
|
* the array_buffer so the tracing can continue.
|
|
*/
|
|
struct array_buffer max_buffer;
|
|
bool allocated_snapshot;
|
|
spinlock_t snapshot_trigger_lock;
|
|
unsigned int snapshot;
|
|
unsigned int mapped;
|
|
unsigned long max_latency;
|
|
#ifdef CONFIG_FSNOTIFY
|
|
struct dentry *d_max_latency;
|
|
struct work_struct fsnotify_work;
|
|
struct irq_work fsnotify_irqwork;
|
|
#endif
|
|
#endif
|
|
struct trace_pid_list __rcu *filtered_pids;
|
|
struct trace_pid_list __rcu *filtered_no_pids;
|
|
/*
|
|
* 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;
|
|
int buffer_disabled;
|
|
#ifdef CONFIG_FTRACE_SYSCALLS
|
|
int sys_refcount_enter;
|
|
int sys_refcount_exit;
|
|
struct trace_event_file __rcu *enter_syscall_files[NR_syscalls];
|
|
struct trace_event_file __rcu *exit_syscall_files[NR_syscalls];
|
|
#endif
|
|
int stop_count;
|
|
int clock_id;
|
|
int nr_topts;
|
|
bool clear_trace;
|
|
int buffer_percent;
|
|
unsigned int n_err_log_entries;
|
|
struct tracer *current_trace;
|
|
unsigned int trace_flags;
|
|
unsigned char trace_flags_index[TRACE_FLAGS_MAX_SIZE];
|
|
unsigned int flags;
|
|
raw_spinlock_t start_lock;
|
|
const char *system_names;
|
|
struct list_head err_log;
|
|
struct dentry *dir;
|
|
struct dentry *options;
|
|
struct dentry *percpu_dir;
|
|
struct eventfs_inode *event_dir;
|
|
struct trace_options *topts;
|
|
struct list_head systems;
|
|
struct list_head events;
|
|
struct trace_event_file *trace_marker_file;
|
|
cpumask_var_t tracing_cpumask; /* only trace on set CPUs */
|
|
/* one per_cpu trace_pipe can be opened by only one user */
|
|
cpumask_var_t pipe_cpumask;
|
|
int ref;
|
|
int trace_ref;
|
|
#ifdef CONFIG_FUNCTION_TRACER
|
|
struct ftrace_ops *ops;
|
|
struct trace_pid_list __rcu *function_pids;
|
|
struct trace_pid_list __rcu *function_no_pids;
|
|
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
|
|
struct fgraph_ops *gops;
|
|
#endif
|
|
#ifdef CONFIG_DYNAMIC_FTRACE
|
|
/* All of these are protected by the ftrace_lock */
|
|
struct list_head func_probes;
|
|
struct list_head mod_trace;
|
|
struct list_head mod_notrace;
|
|
#endif
|
|
/* function tracing enabled */
|
|
int function_enabled;
|
|
#endif
|
|
int no_filter_buffering_ref;
|
|
struct list_head hist_vars;
|
|
#ifdef CONFIG_TRACER_SNAPSHOT
|
|
struct cond_snapshot *cond_snapshot;
|
|
#endif
|
|
struct trace_func_repeats __percpu *last_func_repeats;
|
|
/*
|
|
* On boot up, the ring buffer is set to the minimum size, so that
|
|
* we do not waste memory on systems that are not using tracing.
|
|
*/
|
|
bool ring_buffer_expanded;
|
|
};
|
|
|
|
enum {
|
|
TRACE_ARRAY_FL_GLOBAL = (1 << 0)
|
|
};
|
|
|
|
extern struct list_head ftrace_trace_arrays;
|
|
|
|
extern struct mutex trace_types_lock;
|
|
|
|
extern int trace_array_get(struct trace_array *tr);
|
|
extern int tracing_check_open_get_tr(struct trace_array *tr);
|
|
extern struct trace_array *trace_array_find(const char *instance);
|
|
extern struct trace_array *trace_array_find_get(const char *instance);
|
|
|
|
extern u64 tracing_event_time_stamp(struct trace_buffer *buffer, struct ring_buffer_event *rbe);
|
|
extern int tracing_set_filter_buffering(struct trace_array *tr, bool set);
|
|
extern int tracing_set_clock(struct trace_array *tr, const char *clockstr);
|
|
|
|
extern bool trace_clock_in_ns(struct trace_array *tr);
|
|
|
|
/*
|
|
* 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;
|
|
|
|
if (list_empty(&ftrace_trace_arrays))
|
|
return NULL;
|
|
|
|
tr = list_entry(ftrace_trace_arrays.prev,
|
|
typeof(*tr), list);
|
|
WARN_ON(!(tr->flags & TRACE_ARRAY_FL_GLOBAL));
|
|
return tr;
|
|
}
|
|
|
|
#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 != 0 && (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); \
|
|
IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\
|
|
IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT); \
|
|
IF_ASSIGN(var, ent, struct bprint_entry, TRACE_BPRINT); \
|
|
IF_ASSIGN(var, ent, struct bputs_entry, TRACE_BPUTS); \
|
|
IF_ASSIGN(var, ent, struct hwlat_entry, TRACE_HWLAT); \
|
|
IF_ASSIGN(var, ent, struct osnoise_entry, TRACE_OSNOISE);\
|
|
IF_ASSIGN(var, ent, struct timerlat_entry, TRACE_TIMERLAT);\
|
|
IF_ASSIGN(var, ent, struct raw_data_entry, TRACE_RAW_DATA);\
|
|
IF_ASSIGN(var, ent, struct trace_mmiotrace_rw, \
|
|
TRACE_MMIO_RW); \
|
|
IF_ASSIGN(var, ent, struct trace_mmiotrace_map, \
|
|
TRACE_MMIO_MAP); \
|
|
IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \
|
|
IF_ASSIGN(var, ent, struct ftrace_graph_ent_entry, \
|
|
TRACE_GRAPH_ENT); \
|
|
IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry, \
|
|
TRACE_GRAPH_RET); \
|
|
IF_ASSIGN(var, ent, struct func_repeats_entry, \
|
|
TRACE_FUNC_REPEATS); \
|
|
__ftrace_bad_type(); \
|
|
} while (0)
|
|
|
|
/*
|
|
* An option specific to a tracer. This is a boolean value.
|
|
* The bit is the bit index that sets its value on the
|
|
* flags value in struct tracer_flags.
|
|
*/
|
|
struct tracer_opt {
|
|
const char *name; /* Will appear on the trace_options file */
|
|
u32 bit; /* Mask assigned in val field in tracer_flags */
|
|
};
|
|
|
|
/*
|
|
* The set of specific options for a tracer. Your tracer
|
|
* have to set the initial value of the flags val.
|
|
*/
|
|
struct tracer_flags {
|
|
u32 val;
|
|
struct tracer_opt *opts;
|
|
struct tracer *trace;
|
|
};
|
|
|
|
/* Makes more easy to define a tracer opt */
|
|
#define TRACER_OPT(s, b) .name = #s, .bit = b
|
|
|
|
|
|
struct trace_option_dentry {
|
|
struct tracer_opt *opt;
|
|
struct tracer_flags *flags;
|
|
struct trace_array *tr;
|
|
struct dentry *entry;
|
|
};
|
|
|
|
/**
|
|
* struct tracer - a specific tracer and its callbacks to interact with tracefs
|
|
* @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_on)
|
|
* @stop: called when tracing is paused (echo 0 > tracing_on)
|
|
* @update_thresh: called when tracing_thresh is updated
|
|
* @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
|
|
* @pipe_close: called when the trace_pipe file is released
|
|
* @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
|
|
*/
|
|
struct tracer {
|
|
const char *name;
|
|
int (*init)(struct trace_array *tr);
|
|
void (*reset)(struct trace_array *tr);
|
|
void (*start)(struct trace_array *tr);
|
|
void (*stop)(struct trace_array *tr);
|
|
int (*update_thresh)(struct trace_array *tr);
|
|
void (*open)(struct trace_iterator *iter);
|
|
void (*pipe_open)(struct trace_iterator *iter);
|
|
void (*close)(struct trace_iterator *iter);
|
|
void (*pipe_close)(struct trace_iterator *iter);
|
|
ssize_t (*read)(struct trace_iterator *iter,
|
|
struct file *filp, char __user *ubuf,
|
|
size_t cnt, loff_t *ppos);
|
|
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);
|
|
#ifdef CONFIG_FTRACE_STARTUP_TEST
|
|
int (*selftest)(struct tracer *trace,
|
|
struct trace_array *tr);
|
|
#endif
|
|
void (*print_header)(struct seq_file *m);
|
|
enum print_line_t (*print_line)(struct trace_iterator *iter);
|
|
/* If you handled the flag setting, return 0 */
|
|
int (*set_flag)(struct trace_array *tr,
|
|
u32 old_flags, u32 bit, int set);
|
|
/* Return 0 if OK with change, else return non-zero */
|
|
int (*flag_changed)(struct trace_array *tr,
|
|
u32 mask, int set);
|
|
struct tracer *next;
|
|
struct tracer_flags *flags;
|
|
int enabled;
|
|
bool print_max;
|
|
bool allow_instances;
|
|
#ifdef CONFIG_TRACER_MAX_TRACE
|
|
bool use_max_tr;
|
|
#endif
|
|
/* True if tracer cannot be enabled in kernel param */
|
|
bool noboot;
|
|
};
|
|
|
|
static inline struct ring_buffer_iter *
|
|
trace_buffer_iter(struct trace_iterator *iter, int cpu)
|
|
{
|
|
return iter->buffer_iter ? iter->buffer_iter[cpu] : NULL;
|
|
}
|
|
|
|
int tracer_init(struct tracer *t, struct trace_array *tr);
|
|
int tracing_is_enabled(void);
|
|
void tracing_reset_online_cpus(struct array_buffer *buf);
|
|
void tracing_reset_all_online_cpus(void);
|
|
void tracing_reset_all_online_cpus_unlocked(void);
|
|
int tracing_open_generic(struct inode *inode, struct file *filp);
|
|
int tracing_open_generic_tr(struct inode *inode, struct file *filp);
|
|
int tracing_release_generic_tr(struct inode *inode, struct file *file);
|
|
int tracing_open_file_tr(struct inode *inode, struct file *filp);
|
|
int tracing_release_file_tr(struct inode *inode, struct file *filp);
|
|
int tracing_single_release_file_tr(struct inode *inode, struct file *filp);
|
|
bool tracing_is_disabled(void);
|
|
bool tracer_tracing_is_on(struct trace_array *tr);
|
|
void tracer_tracing_on(struct trace_array *tr);
|
|
void tracer_tracing_off(struct trace_array *tr);
|
|
struct dentry *trace_create_file(const char *name,
|
|
umode_t mode,
|
|
struct dentry *parent,
|
|
void *data,
|
|
const struct file_operations *fops);
|
|
|
|
int tracing_init_dentry(void);
|
|
|
|
struct ring_buffer_event;
|
|
|
|
struct ring_buffer_event *
|
|
trace_buffer_lock_reserve(struct trace_buffer *buffer,
|
|
int type,
|
|
unsigned long len,
|
|
unsigned int trace_ctx);
|
|
|
|
struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
|
|
struct trace_array_cpu *data);
|
|
|
|
struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
|
|
int *ent_cpu, u64 *ent_ts);
|
|
|
|
void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer,
|
|
struct ring_buffer_event *event);
|
|
|
|
bool trace_is_tracepoint_string(const char *str);
|
|
const char *trace_event_format(struct trace_iterator *iter, const char *fmt);
|
|
void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
|
|
va_list ap) __printf(2, 0);
|
|
char *trace_iter_expand_format(struct trace_iterator *iter);
|
|
|
|
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);
|
|
|
|
unsigned long trace_total_entries_cpu(struct trace_array *tr, int cpu);
|
|
unsigned long trace_total_entries(struct trace_array *tr);
|
|
|
|
void trace_function(struct trace_array *tr,
|
|
unsigned long ip,
|
|
unsigned long parent_ip,
|
|
unsigned int trace_ctx);
|
|
void trace_graph_function(struct trace_array *tr,
|
|
unsigned long ip,
|
|
unsigned long parent_ip,
|
|
unsigned int trace_ctx);
|
|
void trace_latency_header(struct seq_file *m);
|
|
void trace_default_header(struct seq_file *m);
|
|
void print_trace_header(struct seq_file *m, struct trace_iterator *iter);
|
|
|
|
void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops);
|
|
int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops);
|
|
|
|
void tracing_start_cmdline_record(void);
|
|
void tracing_stop_cmdline_record(void);
|
|
void tracing_start_tgid_record(void);
|
|
void tracing_stop_tgid_record(void);
|
|
|
|
int register_tracer(struct tracer *type);
|
|
int is_tracing_stopped(void);
|
|
|
|
loff_t tracing_lseek(struct file *file, loff_t offset, int whence);
|
|
|
|
extern cpumask_var_t __read_mostly tracing_buffer_mask;
|
|
|
|
#define for_each_tracing_cpu(cpu) \
|
|
for_each_cpu(cpu, tracing_buffer_mask)
|
|
|
|
extern unsigned long nsecs_to_usecs(unsigned long nsecs);
|
|
|
|
extern unsigned long tracing_thresh;
|
|
|
|
/* PID filtering */
|
|
|
|
extern int pid_max;
|
|
|
|
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 trace_pid_list *filtered_no_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);
|
|
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);
|
|
int trace_pid_write(struct trace_pid_list *filtered_pids,
|
|
struct trace_pid_list **new_pid_list,
|
|
const char __user *ubuf, size_t cnt);
|
|
|
|
#ifdef CONFIG_TRACER_MAX_TRACE
|
|
void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu,
|
|
void *cond_data);
|
|
void update_max_tr_single(struct trace_array *tr,
|
|
struct task_struct *tsk, int cpu);
|
|
|
|
#ifdef CONFIG_FSNOTIFY
|
|
#define LATENCY_FS_NOTIFY
|
|
#endif
|
|
#endif /* CONFIG_TRACER_MAX_TRACE */
|
|
|
|
#ifdef LATENCY_FS_NOTIFY
|
|
void latency_fsnotify(struct trace_array *tr);
|
|
#else
|
|
static inline void latency_fsnotify(struct trace_array *tr) { }
|
|
#endif
|
|
|
|
#ifdef CONFIG_STACKTRACE
|
|
void __trace_stack(struct trace_array *tr, unsigned int trace_ctx, int skip);
|
|
#else
|
|
static inline void __trace_stack(struct trace_array *tr, unsigned int trace_ctx,
|
|
int skip)
|
|
{
|
|
}
|
|
#endif /* CONFIG_STACKTRACE */
|
|
|
|
void trace_last_func_repeats(struct trace_array *tr,
|
|
struct trace_func_repeats *last_info,
|
|
unsigned int trace_ctx);
|
|
|
|
extern u64 ftrace_now(int cpu);
|
|
|
|
extern void trace_find_cmdline(int pid, char comm[]);
|
|
extern int trace_find_tgid(int pid);
|
|
extern void trace_event_follow_fork(struct trace_array *tr, bool enable);
|
|
|
|
#ifdef CONFIG_DYNAMIC_FTRACE
|
|
extern unsigned long ftrace_update_tot_cnt;
|
|
extern unsigned long ftrace_number_of_pages;
|
|
extern unsigned long ftrace_number_of_groups;
|
|
void ftrace_init_trace_array(struct trace_array *tr);
|
|
#else
|
|
static inline void ftrace_init_trace_array(struct trace_array *tr) { }
|
|
#endif
|
|
#define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func
|
|
extern int DYN_FTRACE_TEST_NAME(void);
|
|
#define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2
|
|
extern int DYN_FTRACE_TEST_NAME2(void);
|
|
|
|
extern void trace_set_ring_buffer_expanded(struct trace_array *tr);
|
|
extern bool tracing_selftest_disabled;
|
|
|
|
#ifdef CONFIG_FTRACE_STARTUP_TEST
|
|
extern void __init disable_tracing_selftest(const char *reason);
|
|
|
|
extern int trace_selftest_startup_function(struct tracer *trace,
|
|
struct trace_array *tr);
|
|
extern int trace_selftest_startup_function_graph(struct tracer *trace,
|
|
struct trace_array *tr);
|
|
extern int trace_selftest_startup_irqsoff(struct tracer *trace,
|
|
struct trace_array *tr);
|
|
extern int trace_selftest_startup_preemptoff(struct tracer *trace,
|
|
struct trace_array *tr);
|
|
extern int trace_selftest_startup_preemptirqsoff(struct tracer *trace,
|
|
struct trace_array *tr);
|
|
extern int trace_selftest_startup_wakeup(struct tracer *trace,
|
|
struct trace_array *tr);
|
|
extern int trace_selftest_startup_nop(struct tracer *trace,
|
|
struct trace_array *tr);
|
|
extern int trace_selftest_startup_branch(struct tracer *trace,
|
|
struct trace_array *tr);
|
|
/*
|
|
* 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
|
|
static inline void __init disable_tracing_selftest(const char *reason)
|
|
{
|
|
}
|
|
/* Tracers are seldom changed. Optimize when selftests are disabled. */
|
|
#define __tracer_data __read_mostly
|
|
#endif /* CONFIG_FTRACE_STARTUP_TEST */
|
|
|
|
extern void *head_page(struct trace_array_cpu *data);
|
|
extern unsigned long long ns2usecs(u64 nsec);
|
|
extern int
|
|
trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
|
|
extern int
|
|
trace_vprintk(unsigned long ip, const char *fmt, va_list args);
|
|
extern int
|
|
trace_array_vprintk(struct trace_array *tr,
|
|
unsigned long ip, const char *fmt, va_list args);
|
|
int trace_array_printk_buf(struct trace_buffer *buffer,
|
|
unsigned long ip, const char *fmt, ...);
|
|
void trace_printk_seq(struct trace_seq *s);
|
|
enum print_line_t print_trace_line(struct trace_iterator *iter);
|
|
|
|
extern char trace_find_mark(unsigned long long duration);
|
|
|
|
struct ftrace_hash;
|
|
|
|
struct ftrace_mod_load {
|
|
struct list_head list;
|
|
char *func;
|
|
char *module;
|
|
int enable;
|
|
};
|
|
|
|
enum {
|
|
FTRACE_HASH_FL_MOD = (1 << 0),
|
|
};
|
|
|
|
struct ftrace_hash {
|
|
unsigned long size_bits;
|
|
struct hlist_head *buckets;
|
|
unsigned long count;
|
|
unsigned long flags;
|
|
struct rcu_head rcu;
|
|
};
|
|
|
|
struct ftrace_func_entry *
|
|
ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip);
|
|
|
|
static __always_inline bool ftrace_hash_empty(struct ftrace_hash *hash)
|
|
{
|
|
return !hash || !(hash->count || (hash->flags & FTRACE_HASH_FL_MOD));
|
|
}
|
|
|
|
/* Standard output formatting function used for function return traces */
|
|
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
|
|
|
|
/* 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
|
|
#define TRACE_GRAPH_PRINT_REL_TIME 0x40
|
|
#define TRACE_GRAPH_PRINT_IRQS 0x80
|
|
#define TRACE_GRAPH_PRINT_TAIL 0x100
|
|
#define TRACE_GRAPH_SLEEP_TIME 0x200
|
|
#define TRACE_GRAPH_GRAPH_TIME 0x400
|
|
#define TRACE_GRAPH_PRINT_RETVAL 0x800
|
|
#define TRACE_GRAPH_PRINT_RETVAL_HEX 0x1000
|
|
#define TRACE_GRAPH_PRINT_FILL_SHIFT 28
|
|
#define TRACE_GRAPH_PRINT_FILL_MASK (0x3 << TRACE_GRAPH_PRINT_FILL_SHIFT)
|
|
|
|
extern void ftrace_graph_sleep_time_control(bool enable);
|
|
|
|
#ifdef CONFIG_FUNCTION_PROFILER
|
|
extern void ftrace_graph_graph_time_control(bool enable);
|
|
#else
|
|
static inline void ftrace_graph_graph_time_control(bool enable) { }
|
|
#endif
|
|
|
|
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);
|
|
extern void
|
|
trace_print_graph_duration(unsigned long long duration, struct trace_seq *s);
|
|
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 int trace_ctx);
|
|
extern void __trace_graph_return(struct trace_array *tr,
|
|
struct ftrace_graph_ret *trace,
|
|
unsigned int trace_ctx);
|
|
extern void init_array_fgraph_ops(struct trace_array *tr, struct ftrace_ops *ops);
|
|
extern int allocate_fgraph_ops(struct trace_array *tr, struct ftrace_ops *ops);
|
|
extern void free_fgraph_ops(struct trace_array *tr);
|
|
|
|
enum {
|
|
TRACE_GRAPH_FL = 1,
|
|
|
|
/*
|
|
* In the very unlikely case that an interrupt came in
|
|
* at a start of graph tracing, and we want to trace
|
|
* the function in that interrupt, the depth can be greater
|
|
* than zero, because of the preempted start of a previous
|
|
* trace. In an even more unlikely case, depth could be 2
|
|
* if a softirq interrupted the start of graph tracing,
|
|
* followed by an interrupt preempting a start of graph
|
|
* tracing in the softirq, and depth can even be 3
|
|
* if an NMI came in at the start of an interrupt function
|
|
* that preempted a softirq start of a function that
|
|
* preempted normal context!!!! Luckily, it can't be
|
|
* greater than 3, so the next two bits are a mask
|
|
* of what the depth is when we set TRACE_GRAPH_FL
|
|
*/
|
|
|
|
TRACE_GRAPH_DEPTH_START_BIT,
|
|
TRACE_GRAPH_DEPTH_END_BIT,
|
|
|
|
/*
|
|
* To implement set_graph_notrace, if this bit is set, we ignore
|
|
* function graph tracing of called functions, until the return
|
|
* function is called to clear it.
|
|
*/
|
|
TRACE_GRAPH_NOTRACE_BIT,
|
|
};
|
|
|
|
#define TRACE_GRAPH_NOTRACE (1 << TRACE_GRAPH_NOTRACE_BIT)
|
|
|
|
static inline unsigned long ftrace_graph_depth(unsigned long *task_var)
|
|
{
|
|
return (*task_var >> TRACE_GRAPH_DEPTH_START_BIT) & 3;
|
|
}
|
|
|
|
static inline void ftrace_graph_set_depth(unsigned long *task_var, int depth)
|
|
{
|
|
*task_var &= ~(3 << TRACE_GRAPH_DEPTH_START_BIT);
|
|
*task_var |= (depth & 3) << TRACE_GRAPH_DEPTH_START_BIT;
|
|
}
|
|
|
|
#ifdef CONFIG_DYNAMIC_FTRACE
|
|
extern struct ftrace_hash __rcu *ftrace_graph_hash;
|
|
extern struct ftrace_hash __rcu *ftrace_graph_notrace_hash;
|
|
|
|
static inline int
|
|
ftrace_graph_addr(unsigned long *task_var, struct ftrace_graph_ent *trace)
|
|
{
|
|
unsigned long addr = trace->func;
|
|
int ret = 0;
|
|
struct ftrace_hash *hash;
|
|
|
|
preempt_disable_notrace();
|
|
|
|
/*
|
|
* Have to open code "rcu_dereference_sched()" because the
|
|
* function graph tracer can be called when RCU is not
|
|
* "watching".
|
|
* Protected with schedule_on_each_cpu(ftrace_sync)
|
|
*/
|
|
hash = rcu_dereference_protected(ftrace_graph_hash, !preemptible());
|
|
|
|
if (ftrace_hash_empty(hash)) {
|
|
ret = 1;
|
|
goto out;
|
|
}
|
|
|
|
if (ftrace_lookup_ip(hash, addr)) {
|
|
/*
|
|
* This needs to be cleared on the return functions
|
|
* when the depth is zero.
|
|
*/
|
|
*task_var |= TRACE_GRAPH_FL;
|
|
ftrace_graph_set_depth(task_var, trace->depth);
|
|
|
|
/*
|
|
* 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_hardirq())
|
|
trace_recursion_set(TRACE_IRQ_BIT);
|
|
else
|
|
trace_recursion_clear(TRACE_IRQ_BIT);
|
|
ret = 1;
|
|
}
|
|
|
|
out:
|
|
preempt_enable_notrace();
|
|
return ret;
|
|
}
|
|
|
|
static inline void
|
|
ftrace_graph_addr_finish(struct fgraph_ops *gops, struct ftrace_graph_ret *trace)
|
|
{
|
|
unsigned long *task_var = fgraph_get_task_var(gops);
|
|
|
|
if ((*task_var & TRACE_GRAPH_FL) &&
|
|
trace->depth == ftrace_graph_depth(task_var))
|
|
*task_var &= ~TRACE_GRAPH_FL;
|
|
}
|
|
|
|
static inline int ftrace_graph_notrace_addr(unsigned long addr)
|
|
{
|
|
int ret = 0;
|
|
struct ftrace_hash *notrace_hash;
|
|
|
|
preempt_disable_notrace();
|
|
|
|
/*
|
|
* Have to open code "rcu_dereference_sched()" because the
|
|
* function graph tracer can be called when RCU is not
|
|
* "watching".
|
|
* Protected with schedule_on_each_cpu(ftrace_sync)
|
|
*/
|
|
notrace_hash = rcu_dereference_protected(ftrace_graph_notrace_hash,
|
|
!preemptible());
|
|
|
|
if (ftrace_lookup_ip(notrace_hash, addr))
|
|
ret = 1;
|
|
|
|
preempt_enable_notrace();
|
|
return ret;
|
|
}
|
|
#else
|
|
static inline int ftrace_graph_addr(unsigned long *task_var, struct ftrace_graph_ent *trace)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
static inline int ftrace_graph_notrace_addr(unsigned long addr)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void ftrace_graph_addr_finish(struct fgraph_ops *gops, struct ftrace_graph_ret *trace)
|
|
{ }
|
|
#endif /* CONFIG_DYNAMIC_FTRACE */
|
|
|
|
extern unsigned int fgraph_max_depth;
|
|
|
|
static inline bool
|
|
ftrace_graph_ignore_func(struct fgraph_ops *gops, struct ftrace_graph_ent *trace)
|
|
{
|
|
unsigned long *task_var = fgraph_get_task_var(gops);
|
|
|
|
/* trace it when it is-nested-in or is a function enabled. */
|
|
return !((*task_var & TRACE_GRAPH_FL) ||
|
|
ftrace_graph_addr(task_var, trace)) ||
|
|
(trace->depth < 0) ||
|
|
(fgraph_max_depth && trace->depth >= fgraph_max_depth);
|
|
}
|
|
|
|
void fgraph_init_ops(struct ftrace_ops *dst_ops,
|
|
struct ftrace_ops *src_ops);
|
|
|
|
#else /* CONFIG_FUNCTION_GRAPH_TRACER */
|
|
static inline enum print_line_t
|
|
print_graph_function_flags(struct trace_iterator *iter, u32 flags)
|
|
{
|
|
return TRACE_TYPE_UNHANDLED;
|
|
}
|
|
static inline void free_fgraph_ops(struct trace_array *tr) { }
|
|
/* ftrace_ops may not be defined */
|
|
#define init_array_fgraph_ops(tr, ops) do { } while (0)
|
|
#define allocate_fgraph_ops(tr, ops) ({ 0; })
|
|
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
|
|
|
|
extern struct list_head ftrace_pids;
|
|
|
|
#ifdef CONFIG_FUNCTION_TRACER
|
|
|
|
#define FTRACE_PID_IGNORE -1
|
|
#define FTRACE_PID_TRACE -2
|
|
|
|
struct ftrace_func_command {
|
|
struct list_head list;
|
|
char *name;
|
|
int (*func)(struct trace_array *tr,
|
|
struct ftrace_hash *hash,
|
|
char *func, char *cmd,
|
|
char *params, int enable);
|
|
};
|
|
extern bool ftrace_filter_param __initdata;
|
|
static inline int ftrace_trace_task(struct trace_array *tr)
|
|
{
|
|
return this_cpu_read(tr->array_buffer.data->ftrace_ignore_pid) !=
|
|
FTRACE_PID_IGNORE;
|
|
}
|
|
extern int ftrace_is_dead(void);
|
|
int ftrace_create_function_files(struct trace_array *tr,
|
|
struct dentry *parent);
|
|
void ftrace_destroy_function_files(struct trace_array *tr);
|
|
int ftrace_allocate_ftrace_ops(struct trace_array *tr);
|
|
void ftrace_free_ftrace_ops(struct trace_array *tr);
|
|
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);
|
|
void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d_tracer);
|
|
void ftrace_init_tracefs_toplevel(struct trace_array *tr,
|
|
struct dentry *d_tracer);
|
|
void ftrace_clear_pids(struct trace_array *tr);
|
|
int init_function_trace(void);
|
|
void ftrace_pid_follow_fork(struct trace_array *tr, bool enable);
|
|
#else
|
|
static inline int ftrace_trace_task(struct trace_array *tr)
|
|
{
|
|
return 1;
|
|
}
|
|
static inline int ftrace_is_dead(void) { return 0; }
|
|
static inline int
|
|
ftrace_create_function_files(struct trace_array *tr,
|
|
struct dentry *parent)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int ftrace_allocate_ftrace_ops(struct trace_array *tr)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void ftrace_free_ftrace_ops(struct trace_array *tr) { }
|
|
static inline void ftrace_destroy_function_files(struct trace_array *tr) { }
|
|
static inline __init void
|
|
ftrace_init_global_array_ops(struct trace_array *tr) { }
|
|
static inline void ftrace_reset_array_ops(struct trace_array *tr) { }
|
|
static inline void ftrace_init_tracefs(struct trace_array *tr, struct dentry *d) { }
|
|
static inline void ftrace_init_tracefs_toplevel(struct trace_array *tr, struct dentry *d) { }
|
|
static inline void ftrace_clear_pids(struct trace_array *tr) { }
|
|
static inline int init_function_trace(void) { return 0; }
|
|
static inline void ftrace_pid_follow_fork(struct trace_array *tr, bool enable) { }
|
|
/* ftace_func_t type is not defined, use macro instead of static inline */
|
|
#define ftrace_init_array_ops(tr, func) do { } while (0)
|
|
#endif /* CONFIG_FUNCTION_TRACER */
|
|
|
|
#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE)
|
|
|
|
struct ftrace_probe_ops {
|
|
void (*func)(unsigned long ip,
|
|
unsigned long parent_ip,
|
|
struct trace_array *tr,
|
|
struct ftrace_probe_ops *ops,
|
|
void *data);
|
|
int (*init)(struct ftrace_probe_ops *ops,
|
|
struct trace_array *tr,
|
|
unsigned long ip, void *init_data,
|
|
void **data);
|
|
void (*free)(struct ftrace_probe_ops *ops,
|
|
struct trace_array *tr,
|
|
unsigned long ip, void *data);
|
|
int (*print)(struct seq_file *m,
|
|
unsigned long ip,
|
|
struct ftrace_probe_ops *ops,
|
|
void *data);
|
|
};
|
|
|
|
struct ftrace_func_mapper;
|
|
typedef int (*ftrace_mapper_func)(void *data);
|
|
|
|
struct ftrace_func_mapper *allocate_ftrace_func_mapper(void);
|
|
void **ftrace_func_mapper_find_ip(struct ftrace_func_mapper *mapper,
|
|
unsigned long ip);
|
|
int ftrace_func_mapper_add_ip(struct ftrace_func_mapper *mapper,
|
|
unsigned long ip, void *data);
|
|
void *ftrace_func_mapper_remove_ip(struct ftrace_func_mapper *mapper,
|
|
unsigned long ip);
|
|
void free_ftrace_func_mapper(struct ftrace_func_mapper *mapper,
|
|
ftrace_mapper_func free_func);
|
|
|
|
extern int
|
|
register_ftrace_function_probe(char *glob, struct trace_array *tr,
|
|
struct ftrace_probe_ops *ops, void *data);
|
|
extern int
|
|
unregister_ftrace_function_probe_func(char *glob, struct trace_array *tr,
|
|
struct ftrace_probe_ops *ops);
|
|
extern void clear_ftrace_function_probes(struct trace_array *tr);
|
|
|
|
int register_ftrace_command(struct ftrace_func_command *cmd);
|
|
int unregister_ftrace_command(struct ftrace_func_command *cmd);
|
|
|
|
void ftrace_create_filter_files(struct ftrace_ops *ops,
|
|
struct dentry *parent);
|
|
void ftrace_destroy_filter_files(struct ftrace_ops *ops);
|
|
|
|
extern int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
|
|
int len, int reset);
|
|
extern int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
|
|
int len, int reset);
|
|
#else
|
|
struct ftrace_func_command;
|
|
|
|
static inline __init int register_ftrace_command(struct ftrace_func_command *cmd)
|
|
{
|
|
return -EINVAL;
|
|
}
|
|
static inline __init int unregister_ftrace_command(char *cmd_name)
|
|
{
|
|
return -EINVAL;
|
|
}
|
|
static inline void clear_ftrace_function_probes(struct trace_array *tr)
|
|
{
|
|
}
|
|
|
|
/*
|
|
* 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 */
|
|
|
|
bool ftrace_event_is_function(struct trace_event_call *call);
|
|
|
|
/*
|
|
* 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
|
|
* @idx: user input length
|
|
* @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);
|
|
|
|
/*
|
|
* 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
|
|
|
|
#ifdef CONFIG_BRANCH_TRACER
|
|
# define BRANCH_FLAGS \
|
|
C(BRANCH, "branch"),
|
|
#else
|
|
# define BRANCH_FLAGS
|
|
#endif
|
|
|
|
#ifdef CONFIG_FUNCTION_TRACER
|
|
# define FUNCTION_FLAGS \
|
|
C(FUNCTION, "function-trace"), \
|
|
C(FUNC_FORK, "function-fork"),
|
|
# define FUNCTION_DEFAULT_FLAGS TRACE_ITER_FUNCTION
|
|
#else
|
|
# define FUNCTION_FLAGS
|
|
# define FUNCTION_DEFAULT_FLAGS 0UL
|
|
# define TRACE_ITER_FUNC_FORK 0UL
|
|
#endif
|
|
|
|
#ifdef CONFIG_STACKTRACE
|
|
# define STACK_FLAGS \
|
|
C(STACKTRACE, "stacktrace"),
|
|
#else
|
|
# define STACK_FLAGS
|
|
#endif
|
|
|
|
/*
|
|
* 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 (this macro guarantees it).
|
|
*/
|
|
#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(FIELDS, "fields"), \
|
|
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(RECORD_TGID, "record-tgid"), \
|
|
C(OVERWRITE, "overwrite"), \
|
|
C(STOP_ON_FREE, "disable_on_free"), \
|
|
C(IRQ_INFO, "irq-info"), \
|
|
C(MARKERS, "markers"), \
|
|
C(EVENT_FORK, "event-fork"), \
|
|
C(PAUSE_ON_TRACE, "pause-on-trace"), \
|
|
C(HASH_PTR, "hash-ptr"), /* Print hashed pointer */ \
|
|
FUNCTION_FLAGS \
|
|
FGRAPH_FLAGS \
|
|
STACK_FLAGS \
|
|
BRANCH_FLAGS
|
|
|
|
/*
|
|
* 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
|
|
|
|
enum trace_iterator_bits {
|
|
TRACE_FLAGS
|
|
/* Make sure we don't go more than we have bits for */
|
|
TRACE_ITER_LAST_BIT
|
|
};
|
|
|
|
/*
|
|
* 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 };
|
|
|
|
/*
|
|
* 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)
|
|
|
|
extern struct tracer nop_trace;
|
|
|
|
#ifdef CONFIG_BRANCH_TRACER
|
|
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)
|
|
{
|
|
if (tr->trace_flags & TRACE_ITER_BRANCH)
|
|
return enable_branch_tracing(tr);
|
|
return 0;
|
|
}
|
|
static inline void trace_branch_disable(void)
|
|
{
|
|
/* due to races, always disable */
|
|
disable_branch_tracing();
|
|
}
|
|
#else
|
|
static inline int trace_branch_enable(struct trace_array *tr)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void trace_branch_disable(void)
|
|
{
|
|
}
|
|
#endif /* CONFIG_BRANCH_TRACER */
|
|
|
|
/* set ring buffers to default size if not already done so */
|
|
int tracing_update_buffers(struct trace_array *tr);
|
|
|
|
union trace_synth_field {
|
|
u8 as_u8;
|
|
u16 as_u16;
|
|
u32 as_u32;
|
|
u64 as_u64;
|
|
struct trace_dynamic_info as_dynamic;
|
|
};
|
|
|
|
struct ftrace_event_field {
|
|
struct list_head link;
|
|
const char *name;
|
|
const char *type;
|
|
int filter_type;
|
|
int offset;
|
|
int size;
|
|
int is_signed;
|
|
int len;
|
|
};
|
|
|
|
struct prog_entry;
|
|
|
|
struct event_filter {
|
|
struct prog_entry __rcu *prog;
|
|
char *filter_string;
|
|
};
|
|
|
|
struct event_subsystem {
|
|
struct list_head list;
|
|
const char *name;
|
|
struct event_filter *filter;
|
|
int ref_count;
|
|
};
|
|
|
|
struct trace_subsystem_dir {
|
|
struct list_head list;
|
|
struct event_subsystem *subsystem;
|
|
struct trace_array *tr;
|
|
struct eventfs_inode *ei;
|
|
int ref_count;
|
|
int nr_events;
|
|
};
|
|
|
|
extern int call_filter_check_discard(struct trace_event_call *call, void *rec,
|
|
struct trace_buffer *buffer,
|
|
struct ring_buffer_event *event);
|
|
|
|
void trace_buffer_unlock_commit_regs(struct trace_array *tr,
|
|
struct trace_buffer *buffer,
|
|
struct ring_buffer_event *event,
|
|
unsigned int trcace_ctx,
|
|
struct pt_regs *regs);
|
|
|
|
static inline void trace_buffer_unlock_commit(struct trace_array *tr,
|
|
struct trace_buffer *buffer,
|
|
struct ring_buffer_event *event,
|
|
unsigned int trace_ctx)
|
|
{
|
|
trace_buffer_unlock_commit_regs(tr, buffer, event, trace_ctx, NULL);
|
|
}
|
|
|
|
DECLARE_PER_CPU(bool, trace_taskinfo_save);
|
|
int trace_save_cmdline(struct task_struct *tsk);
|
|
int trace_create_savedcmd(void);
|
|
int trace_alloc_tgid_map(void);
|
|
void trace_free_saved_cmdlines_buffer(void);
|
|
|
|
extern const struct file_operations tracing_saved_cmdlines_fops;
|
|
extern const struct file_operations tracing_saved_tgids_fops;
|
|
extern const struct file_operations tracing_saved_cmdlines_size_fops;
|
|
|
|
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);
|
|
|
|
void early_enable_events(struct trace_array *tr, char *buf, bool disable_first);
|
|
|
|
static inline void
|
|
__trace_event_discard_commit(struct trace_buffer *buffer,
|
|
struct ring_buffer_event *event)
|
|
{
|
|
if (this_cpu_read(trace_buffered_event) == event) {
|
|
/* Simply release the temp buffer and enable preemption */
|
|
this_cpu_dec(trace_buffered_event_cnt);
|
|
preempt_enable_notrace();
|
|
return;
|
|
}
|
|
/* ring_buffer_discard_commit() enables preemption */
|
|
ring_buffer_discard_commit(buffer, event);
|
|
}
|
|
|
|
/*
|
|
* 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 will 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 trace_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, buffer, entry, event);
|
|
|
|
if (likely(!(file->flags & (EVENT_FILE_FL_SOFT_DISABLED |
|
|
EVENT_FILE_FL_FILTERED |
|
|
EVENT_FILE_FL_PID_FILTER))))
|
|
return false;
|
|
|
|
if (file->flags & EVENT_FILE_FL_SOFT_DISABLED)
|
|
goto discard;
|
|
|
|
if (file->flags & EVENT_FILE_FL_FILTERED &&
|
|
!filter_match_preds(file->filter, entry))
|
|
goto discard;
|
|
|
|
if ((file->flags & EVENT_FILE_FL_PID_FILTER) &&
|
|
trace_event_ignore_this_pid(file))
|
|
goto discard;
|
|
|
|
return false;
|
|
discard:
|
|
__trace_event_discard_commit(buffer, event);
|
|
return true;
|
|
}
|
|
|
|
/**
|
|
* event_trigger_unlock_commit - handle triggers and finish event commit
|
|
* @file: The file pointer associated with 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
|
|
* @trace_ctx: The tracing context flags.
|
|
*
|
|
* 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 trace_buffer *buffer,
|
|
struct ring_buffer_event *event,
|
|
void *entry, unsigned int trace_ctx)
|
|
{
|
|
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, trace_ctx);
|
|
|
|
if (tt)
|
|
event_triggers_post_call(file, tt);
|
|
}
|
|
|
|
#define FILTER_PRED_INVALID ((unsigned short)-1)
|
|
#define FILTER_PRED_IS_RIGHT (1 << 15)
|
|
#define FILTER_PRED_FOLD (1 << 15)
|
|
|
|
/*
|
|
* 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
|
|
|
|
struct filter_pred;
|
|
struct regex;
|
|
|
|
typedef int (*regex_match_func)(char *str, struct regex *r, int len);
|
|
|
|
enum regex_type {
|
|
MATCH_FULL = 0,
|
|
MATCH_FRONT_ONLY,
|
|
MATCH_MIDDLE_ONLY,
|
|
MATCH_END_ONLY,
|
|
MATCH_GLOB,
|
|
MATCH_INDEX,
|
|
};
|
|
|
|
struct regex {
|
|
char pattern[MAX_FILTER_STR_VAL];
|
|
int len;
|
|
int field_len;
|
|
regex_match_func match;
|
|
};
|
|
|
|
static inline bool is_string_field(struct ftrace_event_field *field)
|
|
{
|
|
return field->filter_type == FILTER_DYN_STRING ||
|
|
field->filter_type == FILTER_RDYN_STRING ||
|
|
field->filter_type == FILTER_STATIC_STRING ||
|
|
field->filter_type == FILTER_PTR_STRING ||
|
|
field->filter_type == FILTER_COMM;
|
|
}
|
|
|
|
static inline bool is_function_field(struct ftrace_event_field *field)
|
|
{
|
|
return field->filter_type == FILTER_TRACE_FN;
|
|
}
|
|
|
|
extern enum regex_type
|
|
filter_parse_regex(char *buff, int len, char **search, int *not);
|
|
extern void print_event_filter(struct trace_event_file *file,
|
|
struct trace_seq *s);
|
|
extern int apply_event_filter(struct trace_event_file *file,
|
|
char *filter_string);
|
|
extern int apply_subsystem_event_filter(struct trace_subsystem_dir *dir,
|
|
char *filter_string);
|
|
extern void print_subsystem_event_filter(struct event_subsystem *system,
|
|
struct trace_seq *s);
|
|
extern int filter_assign_type(const char *type);
|
|
extern int create_event_filter(struct trace_array *tr,
|
|
struct trace_event_call *call,
|
|
char *filter_str, bool set_str,
|
|
struct event_filter **filterp);
|
|
extern void free_event_filter(struct event_filter *filter);
|
|
|
|
struct ftrace_event_field *
|
|
trace_find_event_field(struct trace_event_call *call, char *name);
|
|
|
|
extern void trace_event_enable_cmd_record(bool enable);
|
|
extern void trace_event_enable_tgid_record(bool enable);
|
|
|
|
extern int event_trace_init(void);
|
|
extern int init_events(void);
|
|
extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
|
|
extern int event_trace_del_tracer(struct trace_array *tr);
|
|
extern void __trace_early_add_events(struct trace_array *tr);
|
|
|
|
extern struct trace_event_file *__find_event_file(struct trace_array *tr,
|
|
const char *system,
|
|
const char *event);
|
|
extern struct trace_event_file *find_event_file(struct trace_array *tr,
|
|
const char *system,
|
|
const char *event);
|
|
|
|
static inline void *event_file_data(struct file *filp)
|
|
{
|
|
return READ_ONCE(file_inode(filp)->i_private);
|
|
}
|
|
|
|
extern struct mutex event_mutex;
|
|
extern struct list_head ftrace_events;
|
|
|
|
/*
|
|
* When the trace_event_file is the filp->i_private pointer,
|
|
* it must be taken under the event_mutex lock, and then checked
|
|
* if the EVENT_FILE_FL_FREED flag is set. If it is, then the
|
|
* data pointed to by the trace_event_file can not be trusted.
|
|
*
|
|
* Use the event_file_file() to access the trace_event_file from
|
|
* the filp the first time under the event_mutex and check for
|
|
* NULL. If it is needed to be retrieved again and the event_mutex
|
|
* is still held, then the event_file_data() can be used and it
|
|
* is guaranteed to be valid.
|
|
*/
|
|
static inline struct trace_event_file *event_file_file(struct file *filp)
|
|
{
|
|
struct trace_event_file *file;
|
|
|
|
lockdep_assert_held(&event_mutex);
|
|
file = READ_ONCE(file_inode(filp)->i_private);
|
|
if (!file || file->flags & EVENT_FILE_FL_FREED)
|
|
return NULL;
|
|
return file;
|
|
}
|
|
|
|
extern const struct file_operations event_trigger_fops;
|
|
extern const struct file_operations event_hist_fops;
|
|
extern const struct file_operations event_hist_debug_fops;
|
|
extern const struct file_operations event_inject_fops;
|
|
|
|
#ifdef CONFIG_HIST_TRIGGERS
|
|
extern int register_trigger_hist_cmd(void);
|
|
extern int register_trigger_hist_enable_disable_cmds(void);
|
|
#else
|
|
static inline int register_trigger_hist_cmd(void) { return 0; }
|
|
static inline int register_trigger_hist_enable_disable_cmds(void) { return 0; }
|
|
#endif
|
|
|
|
extern int register_trigger_cmds(void);
|
|
extern void clear_event_triggers(struct trace_array *tr);
|
|
|
|
enum {
|
|
EVENT_TRIGGER_FL_PROBE = BIT(0),
|
|
};
|
|
|
|
struct event_trigger_data {
|
|
unsigned long count;
|
|
int ref;
|
|
int flags;
|
|
struct event_trigger_ops *ops;
|
|
struct event_command *cmd_ops;
|
|
struct event_filter __rcu *filter;
|
|
char *filter_str;
|
|
void *private_data;
|
|
bool paused;
|
|
bool paused_tmp;
|
|
struct list_head list;
|
|
char *name;
|
|
struct list_head named_list;
|
|
struct event_trigger_data *named_data;
|
|
};
|
|
|
|
/* 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_data *data);
|
|
extern void event_enable_trigger_free(struct event_trigger_data *data);
|
|
extern int event_enable_trigger_parse(struct event_command *cmd_ops,
|
|
struct trace_event_file *file,
|
|
char *glob, char *cmd,
|
|
char *param_and_filter);
|
|
extern int event_enable_register_trigger(char *glob,
|
|
struct event_trigger_data *data,
|
|
struct trace_event_file *file);
|
|
extern void event_enable_unregister_trigger(char *glob,
|
|
struct event_trigger_data *test,
|
|
struct trace_event_file *file);
|
|
extern void trigger_data_free(struct event_trigger_data *data);
|
|
extern int event_trigger_init(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 int set_trigger_filter(char *filter_str,
|
|
struct event_trigger_data *trigger_data,
|
|
struct trace_event_file *file);
|
|
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);
|
|
extern struct event_trigger_data *
|
|
get_named_trigger_data(struct event_trigger_data *data);
|
|
extern int register_event_command(struct event_command *cmd);
|
|
extern int unregister_event_command(struct event_command *cmd);
|
|
extern int register_trigger_hist_enable_disable_cmds(void);
|
|
extern bool event_trigger_check_remove(const char *glob);
|
|
extern bool event_trigger_empty_param(const char *param);
|
|
extern int event_trigger_separate_filter(char *param_and_filter, char **param,
|
|
char **filter, bool param_required);
|
|
extern struct event_trigger_data *
|
|
event_trigger_alloc(struct event_command *cmd_ops,
|
|
char *cmd,
|
|
char *param,
|
|
void *private_data);
|
|
extern int event_trigger_parse_num(char *trigger,
|
|
struct event_trigger_data *trigger_data);
|
|
extern int event_trigger_set_filter(struct event_command *cmd_ops,
|
|
struct trace_event_file *file,
|
|
char *param,
|
|
struct event_trigger_data *trigger_data);
|
|
extern void event_trigger_reset_filter(struct event_command *cmd_ops,
|
|
struct event_trigger_data *trigger_data);
|
|
extern int event_trigger_register(struct event_command *cmd_ops,
|
|
struct trace_event_file *file,
|
|
char *glob,
|
|
struct event_trigger_data *trigger_data);
|
|
extern void event_trigger_unregister(struct event_command *cmd_ops,
|
|
struct trace_event_file *file,
|
|
char *glob,
|
|
struct event_trigger_data *trigger_data);
|
|
|
|
extern void event_file_get(struct trace_event_file *file);
|
|
extern void event_file_put(struct trace_event_file *file);
|
|
|
|
/**
|
|
* struct event_trigger_ops - callbacks for trace event triggers
|
|
*
|
|
* The methods in this structure provide per-event trigger hooks for
|
|
* various trigger operations.
|
|
*
|
|
* The @init and @free methods are used during trigger setup and
|
|
* teardown, typically called from an event_command's @parse()
|
|
* function implementation.
|
|
*
|
|
* The @print method is used to print the trigger spec.
|
|
*
|
|
* The @trigger method is the function that actually implements the
|
|
* trigger and is called in the context of the triggering event
|
|
* whenever that event occurs.
|
|
*
|
|
* All the methods below, except for @init() and @free(), must be
|
|
* implemented.
|
|
*
|
|
* @trigger: 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
|
|
* registered the trigger (see struct event_command) along with
|
|
* the trace record, rec.
|
|
*
|
|
* @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 {
|
|
void (*trigger)(struct event_trigger_data *data,
|
|
struct trace_buffer *buffer,
|
|
void *rec,
|
|
struct ring_buffer_event *rbe);
|
|
int (*init)(struct event_trigger_data *data);
|
|
void (*free)(struct event_trigger_data *data);
|
|
int (*print)(struct seq_file *m,
|
|
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
|
|
* enum in include/linux/trace_events.h.
|
|
*
|
|
* @flags: See the enum event_command_flags below.
|
|
*
|
|
* All the methods below, except for @set_filter() and @unreg_all(),
|
|
* must be implemented.
|
|
*
|
|
* @parse: 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).
|
|
*
|
|
* @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.
|
|
*
|
|
* @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.
|
|
* This callback function allows a single event_command to
|
|
* support multiple trigger implementations via different sets of
|
|
* event_trigger_ops, depending on the value of the @param
|
|
* string.
|
|
*/
|
|
struct event_command {
|
|
struct list_head list;
|
|
char *name;
|
|
enum event_trigger_type trigger_type;
|
|
int flags;
|
|
int (*parse)(struct event_command *cmd_ops,
|
|
struct trace_event_file *file,
|
|
char *glob, char *cmd,
|
|
char *param_and_filter);
|
|
int (*reg)(char *glob,
|
|
struct event_trigger_data *data,
|
|
struct trace_event_file *file);
|
|
void (*unreg)(char *glob,
|
|
struct event_trigger_data *data,
|
|
struct trace_event_file *file);
|
|
void (*unreg_all)(struct trace_event_file *file);
|
|
int (*set_filter)(char *filter_str,
|
|
struct event_trigger_data *data,
|
|
struct trace_event_file *file);
|
|
struct event_trigger_ops *(*get_trigger_ops)(char *cmd, char *param);
|
|
};
|
|
|
|
/**
|
|
* 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;
|
|
}
|
|
|
|
extern int trace_event_enable_disable(struct trace_event_file *file,
|
|
int enable, int soft_disable);
|
|
extern int tracing_alloc_snapshot(void);
|
|
extern void tracing_snapshot_cond(struct trace_array *tr, void *cond_data);
|
|
extern int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, cond_update_fn_t update);
|
|
|
|
extern int tracing_snapshot_cond_disable(struct trace_array *tr);
|
|
extern void *tracing_cond_snapshot_data(struct trace_array *tr);
|
|
|
|
extern const char *__start___trace_bprintk_fmt[];
|
|
extern const char *__stop___trace_bprintk_fmt[];
|
|
|
|
extern const char *__start___tracepoint_str[];
|
|
extern const char *__stop___tracepoint_str[];
|
|
|
|
void trace_printk_control(bool enabled);
|
|
void trace_printk_start_comm(void);
|
|
int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set);
|
|
int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled);
|
|
|
|
/* Used from boot time tracer */
|
|
extern int trace_set_options(struct trace_array *tr, char *option);
|
|
extern int tracing_set_tracer(struct trace_array *tr, const char *buf);
|
|
extern ssize_t tracing_resize_ring_buffer(struct trace_array *tr,
|
|
unsigned long size, int cpu_id);
|
|
extern int tracing_set_cpumask(struct trace_array *tr,
|
|
cpumask_var_t tracing_cpumask_new);
|
|
|
|
|
|
#define MAX_EVENT_NAME_LEN 64
|
|
|
|
extern ssize_t trace_parse_run_command(struct file *file,
|
|
const char __user *buffer, size_t count, loff_t *ppos,
|
|
int (*createfn)(const char *));
|
|
|
|
extern unsigned int err_pos(char *cmd, const char *str);
|
|
extern void tracing_log_err(struct trace_array *tr,
|
|
const char *loc, const char *cmd,
|
|
const char **errs, u8 type, u16 pos);
|
|
|
|
/*
|
|
* 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))
|
|
|
|
#undef FTRACE_ENTRY
|
|
#define FTRACE_ENTRY(call, struct_name, id, tstruct, print) \
|
|
extern struct trace_event_call \
|
|
__aligned(4) event_##call;
|
|
#undef FTRACE_ENTRY_DUP
|
|
#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print) \
|
|
FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
|
|
#undef FTRACE_ENTRY_PACKED
|
|
#define FTRACE_ENTRY_PACKED(call, struct_name, id, tstruct, print) \
|
|
FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
|
|
|
|
#include "trace_entries.h"
|
|
|
|
#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_FUNCTION_TRACER)
|
|
int perf_ftrace_event_register(struct trace_event_call *call,
|
|
enum trace_reg type, void *data);
|
|
#else
|
|
#define perf_ftrace_event_register NULL
|
|
#endif
|
|
|
|
#ifdef CONFIG_FTRACE_SYSCALLS
|
|
void init_ftrace_syscalls(void);
|
|
const char *get_syscall_name(int syscall);
|
|
#else
|
|
static inline void init_ftrace_syscalls(void) { }
|
|
static inline const char *get_syscall_name(int syscall)
|
|
{
|
|
return NULL;
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_EVENT_TRACING
|
|
void trace_event_init(void);
|
|
void trace_event_eval_update(struct trace_eval_map **map, int len);
|
|
/* Used from boot time tracer */
|
|
extern int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set);
|
|
extern int trigger_process_regex(struct trace_event_file *file, char *buff);
|
|
#else
|
|
static inline void __init trace_event_init(void) { }
|
|
static inline void trace_event_eval_update(struct trace_eval_map **map, int len) { }
|
|
#endif
|
|
|
|
#ifdef CONFIG_TRACER_SNAPSHOT
|
|
void tracing_snapshot_instance(struct trace_array *tr);
|
|
int tracing_alloc_snapshot_instance(struct trace_array *tr);
|
|
int tracing_arm_snapshot(struct trace_array *tr);
|
|
void tracing_disarm_snapshot(struct trace_array *tr);
|
|
#else
|
|
static inline void tracing_snapshot_instance(struct trace_array *tr) { }
|
|
static inline int tracing_alloc_snapshot_instance(struct trace_array *tr)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int tracing_arm_snapshot(struct trace_array *tr) { return 0; }
|
|
static inline void tracing_disarm_snapshot(struct trace_array *tr) { }
|
|
#endif
|
|
|
|
#ifdef CONFIG_PREEMPT_TRACER
|
|
void tracer_preempt_on(unsigned long a0, unsigned long a1);
|
|
void tracer_preempt_off(unsigned long a0, unsigned long a1);
|
|
#else
|
|
static inline void tracer_preempt_on(unsigned long a0, unsigned long a1) { }
|
|
static inline void tracer_preempt_off(unsigned long a0, unsigned long a1) { }
|
|
#endif
|
|
#ifdef CONFIG_IRQSOFF_TRACER
|
|
void tracer_hardirqs_on(unsigned long a0, unsigned long a1);
|
|
void tracer_hardirqs_off(unsigned long a0, unsigned long a1);
|
|
#else
|
|
static inline void tracer_hardirqs_on(unsigned long a0, unsigned long a1) { }
|
|
static inline void tracer_hardirqs_off(unsigned long a0, unsigned long a1) { }
|
|
#endif
|
|
|
|
/*
|
|
* Reset the state of the trace_iterator so that it can read consumed data.
|
|
* Normally, the trace_iterator is used for reading the data when it is not
|
|
* consumed, and must retain state.
|
|
*/
|
|
static __always_inline void trace_iterator_reset(struct trace_iterator *iter)
|
|
{
|
|
memset_startat(iter, 0, seq);
|
|
iter->pos = -1;
|
|
}
|
|
|
|
/* Check the name is good for event/group/fields */
|
|
static inline bool __is_good_name(const char *name, bool hash_ok)
|
|
{
|
|
if (!isalpha(*name) && *name != '_' && (!hash_ok || *name != '-'))
|
|
return false;
|
|
while (*++name != '\0') {
|
|
if (!isalpha(*name) && !isdigit(*name) && *name != '_' &&
|
|
(!hash_ok || *name != '-'))
|
|
return false;
|
|
}
|
|
return true;
|
|
}
|
|
|
|
/* Check the name is good for event/group/fields */
|
|
static inline bool is_good_name(const char *name)
|
|
{
|
|
return __is_good_name(name, false);
|
|
}
|
|
|
|
/* Check the name is good for system */
|
|
static inline bool is_good_system_name(const char *name)
|
|
{
|
|
return __is_good_name(name, true);
|
|
}
|
|
|
|
/* Convert certain expected symbols into '_' when generating event names */
|
|
static inline void sanitize_event_name(char *name)
|
|
{
|
|
while (*name++ != '\0')
|
|
if (*name == ':' || *name == '.')
|
|
*name = '_';
|
|
}
|
|
|
|
/*
|
|
* This is a generic way to read and write a u64 value from a file in tracefs.
|
|
*
|
|
* The value is stored on the variable pointed by *val. The value needs
|
|
* to be at least *min and at most *max. The write is protected by an
|
|
* existing *lock.
|
|
*/
|
|
struct trace_min_max_param {
|
|
struct mutex *lock;
|
|
u64 *val;
|
|
u64 *min;
|
|
u64 *max;
|
|
};
|
|
|
|
#define U64_STR_SIZE 24 /* 20 digits max */
|
|
|
|
extern const struct file_operations trace_min_max_fops;
|
|
|
|
#ifdef CONFIG_RV
|
|
extern int rv_init_interface(void);
|
|
#else
|
|
static inline int rv_init_interface(void)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
#endif /* _LINUX_KERNEL_TRACE_H */
|