linux-stable/include/linux/tracepoint.h
Mathieu Desnoyers 6549864629 tracepoints: Fix section alignment using pointer array
Make the tracepoints more robust, making them solid enough to handle compiler
changes by not relying on anything based on compiler-specific behavior with
respect to structure alignment. Implement an approach proposed by David Miller:
use an array of const pointers to refer to the individual structures, and export
this pointer array through the linker script rather than the structures per se.
It will consume 32 extra bytes per tracepoint (24 for structure padding and 8
for the pointers), but are less likely to break due to compiler changes.

History:

commit 7e066fb8 tracepoints: add DECLARE_TRACE() and DEFINE_TRACE()
added the aligned(32) type and variable attribute to the tracepoint structures
to deal with gcc happily aligning statically defined structures on 32-byte
multiples.

One attempt was to use a 8-byte alignment for tracepoint structures by applying
both the variable and type attribute to tracepoint structures definitions and
declarations. It worked fine with gcc 4.5.1, but broke with gcc 4.4.4 and 4.4.5.

The reason is that the "aligned" attribute only specify the _minimum_ alignment
for a structure, leaving both the compiler and the linker free to align on
larger multiples. Because tracepoint.c expects the structures to be placed as an
array within each section, up-alignment cause NULL-pointer exceptions due to the
extra unexpected padding.

(this patch applies on top of -tip)

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: David S. Miller <davem@davemloft.net>
LKML-Reference: <20110126222622.GA10794@Krystal>
CC: Frederic Weisbecker <fweisbec@gmail.com>
CC: Ingo Molnar <mingo@elte.hu>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-02-03 09:28:46 -05:00

383 lines
12 KiB
C

#ifndef _LINUX_TRACEPOINT_H
#define _LINUX_TRACEPOINT_H
/*
* Kernel Tracepoint API.
*
* See Documentation/trace/tracepoints.txt.
*
* (C) Copyright 2008 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
*
* Heavily inspired from the Linux Kernel Markers.
*
* This file is released under the GPLv2.
* See the file COPYING for more details.
*/
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/rcupdate.h>
#include <linux/jump_label.h>
struct module;
struct tracepoint;
struct tracepoint_func {
void *func;
void *data;
};
struct tracepoint {
const char *name; /* Tracepoint name */
int state; /* State. */
void (*regfunc)(void);
void (*unregfunc)(void);
struct tracepoint_func __rcu *funcs;
};
/*
* Connect a probe to a tracepoint.
* Internal API, should not be used directly.
*/
extern int tracepoint_probe_register(const char *name, void *probe, void *data);
/*
* Disconnect a probe from a tracepoint.
* Internal API, should not be used directly.
*/
extern int
tracepoint_probe_unregister(const char *name, void *probe, void *data);
extern int tracepoint_probe_register_noupdate(const char *name, void *probe,
void *data);
extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe,
void *data);
extern void tracepoint_probe_update_all(void);
struct tracepoint_iter {
struct module *module;
struct tracepoint * const *tracepoint;
};
extern void tracepoint_iter_start(struct tracepoint_iter *iter);
extern void tracepoint_iter_next(struct tracepoint_iter *iter);
extern void tracepoint_iter_stop(struct tracepoint_iter *iter);
extern void tracepoint_iter_reset(struct tracepoint_iter *iter);
extern int tracepoint_get_iter_range(struct tracepoint * const **tracepoint,
struct tracepoint * const *begin, struct tracepoint * const *end);
/*
* tracepoint_synchronize_unregister must be called between the last tracepoint
* probe unregistration and the end of module exit to make sure there is no
* caller executing a probe when it is freed.
*/
static inline void tracepoint_synchronize_unregister(void)
{
synchronize_sched();
}
#define PARAMS(args...) args
#ifdef CONFIG_TRACEPOINTS
extern
void tracepoint_update_probe_range(struct tracepoint * const *begin,
struct tracepoint * const *end);
#else
static inline
void tracepoint_update_probe_range(struct tracepoint * const *begin,
struct tracepoint * const *end)
{ }
#endif /* CONFIG_TRACEPOINTS */
#endif /* _LINUX_TRACEPOINT_H */
/*
* Note: we keep the TRACE_EVENT and DECLARE_TRACE outside the include
* file ifdef protection.
* This is due to the way trace events work. If a file includes two
* trace event headers under one "CREATE_TRACE_POINTS" the first include
* will override the TRACE_EVENT and break the second include.
*/
#ifndef DECLARE_TRACE
#define TP_PROTO(args...) args
#define TP_ARGS(args...) args
#define TP_CONDITION(args...) args
#ifdef CONFIG_TRACEPOINTS
/*
* it_func[0] is never NULL because there is at least one element in the array
* when the array itself is non NULL.
*
* Note, the proto and args passed in includes "__data" as the first parameter.
* The reason for this is to handle the "void" prototype. If a tracepoint
* has a "void" prototype, then it is invalid to declare a function
* as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just
* "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto".
*/
#define __DO_TRACE(tp, proto, args, cond) \
do { \
struct tracepoint_func *it_func_ptr; \
void *it_func; \
void *__data; \
\
if (!(cond)) \
return; \
rcu_read_lock_sched_notrace(); \
it_func_ptr = rcu_dereference_sched((tp)->funcs); \
if (it_func_ptr) { \
do { \
it_func = (it_func_ptr)->func; \
__data = (it_func_ptr)->data; \
((void(*)(proto))(it_func))(args); \
} while ((++it_func_ptr)->func); \
} \
rcu_read_unlock_sched_notrace(); \
} while (0)
/*
* Make sure the alignment of the structure in the __tracepoints section will
* not add unwanted padding between the beginning of the section and the
* structure. Force alignment to the same alignment as the section start.
*/
#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \
extern struct tracepoint __tracepoint_##name; \
static inline void trace_##name(proto) \
{ \
JUMP_LABEL(&__tracepoint_##name.state, do_trace); \
return; \
do_trace: \
__DO_TRACE(&__tracepoint_##name, \
TP_PROTO(data_proto), \
TP_ARGS(data_args), \
TP_CONDITION(cond)); \
} \
static inline int \
register_trace_##name(void (*probe)(data_proto), void *data) \
{ \
return tracepoint_probe_register(#name, (void *)probe, \
data); \
} \
static inline int \
unregister_trace_##name(void (*probe)(data_proto), void *data) \
{ \
return tracepoint_probe_unregister(#name, (void *)probe, \
data); \
} \
static inline void \
check_trace_callback_type_##name(void (*cb)(data_proto)) \
{ \
}
/*
* We have no guarantee that gcc and the linker won't up-align the tracepoint
* structures, so we create an array of pointers that will be used for iteration
* on the tracepoints.
*/
#define DEFINE_TRACE_FN(name, reg, unreg) \
static const char __tpstrtab_##name[] \
__attribute__((section("__tracepoints_strings"))) = #name; \
struct tracepoint __tracepoint_##name \
__attribute__((section("__tracepoints"))) = \
{ __tpstrtab_##name, 0, reg, unreg, NULL }; \
static struct tracepoint * const __tracepoint_ptr_##name __used \
__attribute__((section("__tracepoints_ptrs"))) = \
&__tracepoint_##name;
#define DEFINE_TRACE(name) \
DEFINE_TRACE_FN(name, NULL, NULL);
#define EXPORT_TRACEPOINT_SYMBOL_GPL(name) \
EXPORT_SYMBOL_GPL(__tracepoint_##name)
#define EXPORT_TRACEPOINT_SYMBOL(name) \
EXPORT_SYMBOL(__tracepoint_##name)
#else /* !CONFIG_TRACEPOINTS */
#define __DECLARE_TRACE(name, proto, args, cond, data_proto, data_args) \
static inline void trace_##name(proto) \
{ } \
static inline int \
register_trace_##name(void (*probe)(data_proto), \
void *data) \
{ \
return -ENOSYS; \
} \
static inline int \
unregister_trace_##name(void (*probe)(data_proto), \
void *data) \
{ \
return -ENOSYS; \
} \
static inline void check_trace_callback_type_##name(void (*cb)(data_proto)) \
{ \
}
#define DEFINE_TRACE_FN(name, reg, unreg)
#define DEFINE_TRACE(name)
#define EXPORT_TRACEPOINT_SYMBOL_GPL(name)
#define EXPORT_TRACEPOINT_SYMBOL(name)
#endif /* CONFIG_TRACEPOINTS */
/*
* The need for the DECLARE_TRACE_NOARGS() is to handle the prototype
* (void). "void" is a special value in a function prototype and can
* not be combined with other arguments. Since the DECLARE_TRACE()
* macro adds a data element at the beginning of the prototype,
* we need a way to differentiate "(void *data, proto)" from
* "(void *data, void)". The second prototype is invalid.
*
* DECLARE_TRACE_NOARGS() passes "void" as the tracepoint prototype
* and "void *__data" as the callback prototype.
*
* DECLARE_TRACE() passes "proto" as the tracepoint protoype and
* "void *__data, proto" as the callback prototype.
*/
#define DECLARE_TRACE_NOARGS(name) \
__DECLARE_TRACE(name, void, , 1, void *__data, __data)
#define DECLARE_TRACE(name, proto, args) \
__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), 1, \
PARAMS(void *__data, proto), \
PARAMS(__data, args))
#define DECLARE_TRACE_CONDITION(name, proto, args, cond) \
__DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), PARAMS(cond), \
PARAMS(void *__data, proto), \
PARAMS(__data, args))
#define TRACE_EVENT_FLAGS(event, flag)
#endif /* DECLARE_TRACE */
#ifndef TRACE_EVENT
/*
* For use with the TRACE_EVENT macro:
*
* We define a tracepoint, its arguments, its printk format
* and its 'fast binay record' layout.
*
* Firstly, name your tracepoint via TRACE_EVENT(name : the
* 'subsystem_event' notation is fine.
*
* Think about this whole construct as the
* 'trace_sched_switch() function' from now on.
*
*
* TRACE_EVENT(sched_switch,
*
* *
* * A function has a regular function arguments
* * prototype, declare it via TP_PROTO():
* *
*
* TP_PROTO(struct rq *rq, struct task_struct *prev,
* struct task_struct *next),
*
* *
* * Define the call signature of the 'function'.
* * (Design sidenote: we use this instead of a
* * TP_PROTO1/TP_PROTO2/TP_PROTO3 ugliness.)
* *
*
* TP_ARGS(rq, prev, next),
*
* *
* * Fast binary tracing: define the trace record via
* * TP_STRUCT__entry(). You can think about it like a
* * regular C structure local variable definition.
* *
* * This is how the trace record is structured and will
* * be saved into the ring buffer. These are the fields
* * that will be exposed to user-space in
* * /sys/kernel/debug/tracing/events/<*>/format.
* *
* * The declared 'local variable' is called '__entry'
* *
* * __field(pid_t, prev_prid) is equivalent to a standard declariton:
* *
* * pid_t prev_pid;
* *
* * __array(char, prev_comm, TASK_COMM_LEN) is equivalent to:
* *
* * char prev_comm[TASK_COMM_LEN];
* *
*
* TP_STRUCT__entry(
* __array( char, prev_comm, TASK_COMM_LEN )
* __field( pid_t, prev_pid )
* __field( int, prev_prio )
* __array( char, next_comm, TASK_COMM_LEN )
* __field( pid_t, next_pid )
* __field( int, next_prio )
* ),
*
* *
* * Assign the entry into the trace record, by embedding
* * a full C statement block into TP_fast_assign(). You
* * can refer to the trace record as '__entry' -
* * otherwise you can put arbitrary C code in here.
* *
* * Note: this C code will execute every time a trace event
* * happens, on an active tracepoint.
* *
*
* TP_fast_assign(
* memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
* __entry->prev_pid = prev->pid;
* __entry->prev_prio = prev->prio;
* memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
* __entry->next_pid = next->pid;
* __entry->next_prio = next->prio;
* ),
*
* *
* * Formatted output of a trace record via TP_printk().
* * This is how the tracepoint will appear under ftrace
* * plugins that make use of this tracepoint.
* *
* * (raw-binary tracing wont actually perform this step.)
* *
*
* TP_printk("task %s:%d [%d] ==> %s:%d [%d]",
* __entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
* __entry->next_comm, __entry->next_pid, __entry->next_prio),
*
* );
*
* This macro construct is thus used for the regular printk format
* tracing setup, it is used to construct a function pointer based
* tracepoint callback (this is used by programmatic plugins and
* can also by used by generic instrumentation like SystemTap), and
* it is also used to expose a structured trace record in
* /sys/kernel/debug/tracing/events/.
*
* A set of (un)registration functions can be passed to the variant
* TRACE_EVENT_FN to perform any (un)registration work.
*/
#define DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, print)
#define DEFINE_EVENT(template, name, proto, args) \
DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
#define DEFINE_EVENT_CONDITION(template, name, proto, \
args, cond) \
DECLARE_TRACE_CONDITION(name, PARAMS(proto), \
PARAMS(args), PARAMS(cond))
#define TRACE_EVENT(name, proto, args, struct, assign, print) \
DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
#define TRACE_EVENT_FN(name, proto, args, struct, \
assign, print, reg, unreg) \
DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
#define TRACE_EVENT_CONDITION(name, proto, args, cond, \
struct, assign, print) \
DECLARE_TRACE_CONDITION(name, PARAMS(proto), \
PARAMS(args), PARAMS(cond))
#define TRACE_EVENT_FLAGS(event, flag)
#endif /* ifdef TRACE_EVENT (see note above) */