* [PATCH 01/13 v3] tracing: Create class struct for events
2010-05-14 19:22 [PATCH 00/13 v3] [GIT PULL] tracing: shrinking trace events and updates Steven Rostedt
@ 2010-05-14 19:22 ` Steven Rostedt
2010-05-14 19:22 ` [PATCH 02/13 v3] tracepoints: Add check trace callback type Steven Rostedt
` (11 subsequent siblings)
12 siblings, 0 replies; 19+ messages in thread
From: Steven Rostedt @ 2010-05-14 19:22 UTC (permalink / raw)
To: linux-kernel
Cc: Ingo Molnar, Andrew Morton, Frederic Weisbecker,
Mathieu Desnoyers, Masami Hiramatsu, Mathieu Desnoyers
[-- Attachment #1: 0001-tracing-Create-class-struct-for-events.patch --]
[-- Type: text/plain, Size: 13381 bytes --]
From: Steven Rostedt <srostedt@redhat.com>
This patch creates a ftrace_event_class struct that event structs point to.
This class struct will be made to hold information to modify the
events. Currently the class struct only holds the events system name.
This patch slightly increases the size, but this change lays the ground work
of other changes to make the footprint of tracepoints smaller.
With 82 standard tracepoints, and 618 system call tracepoints
(two tracepoints per syscall: enter and exit):
text data bss dec hex filename
4913961 1088356 861512 6863829 68bbd5 vmlinux.orig
4914025 1088868 861512 6864405 68be15 vmlinux.class
This patch also cleans up some stale comments in ftrace.h.
v2: Fixed missing semi-colon in macro.
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Masami Hiramatsu <mhiramat@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
include/linux/ftrace_event.h | 6 ++++-
include/linux/syscalls.h | 6 +++-
include/trace/ftrace.h | 44 +++++++++++++++--------------------
kernel/trace/trace_events.c | 20 ++++++++--------
kernel/trace/trace_events_filter.c | 6 ++--
kernel/trace/trace_export.c | 6 ++++-
kernel/trace/trace_kprobe.c | 12 +++++-----
kernel/trace/trace_syscalls.c | 4 +++
8 files changed, 56 insertions(+), 48 deletions(-)
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 39e71b0..496eea8 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -113,10 +113,14 @@ void tracing_record_cmdline(struct task_struct *tsk);
struct event_filter;
+struct ftrace_event_class {
+ char *system;
+};
+
struct ftrace_event_call {
struct list_head list;
+ struct ftrace_event_class *class;
char *name;
- char *system;
struct dentry *dir;
struct trace_event *event;
int enabled;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 057929b..ac5791d 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -134,6 +134,8 @@ struct perf_event_attr;
#define __SC_STR_TDECL5(t, a, ...) #t, __SC_STR_TDECL4(__VA_ARGS__)
#define __SC_STR_TDECL6(t, a, ...) #t, __SC_STR_TDECL5(__VA_ARGS__)
+extern struct ftrace_event_class event_class_syscalls;
+
#define SYSCALL_TRACE_ENTER_EVENT(sname) \
static const struct syscall_metadata __syscall_meta_##sname; \
static struct ftrace_event_call \
@@ -146,7 +148,7 @@ struct perf_event_attr;
__attribute__((section("_ftrace_events"))) \
event_enter_##sname = { \
.name = "sys_enter"#sname, \
- .system = "syscalls", \
+ .class = &event_class_syscalls, \
.event = &enter_syscall_print_##sname, \
.raw_init = init_syscall_trace, \
.define_fields = syscall_enter_define_fields, \
@@ -168,7 +170,7 @@ struct perf_event_attr;
__attribute__((section("_ftrace_events"))) \
event_exit_##sname = { \
.name = "sys_exit"#sname, \
- .system = "syscalls", \
+ .class = &event_class_syscalls, \
.event = &exit_syscall_print_##sname, \
.raw_init = init_syscall_trace, \
.define_fields = syscall_exit_define_fields, \
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 75dd778..7dcdfd8 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -62,7 +62,10 @@
struct trace_entry ent; \
tstruct \
char __data[0]; \
- };
+ }; \
+ \
+ static struct ftrace_event_class event_class_##name;
+
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, name, proto, args) \
static struct ftrace_event_call \
@@ -430,22 +433,6 @@ perf_trace_disable_##name(struct ftrace_event_call *unused) \
*
* Override the macros in <trace/trace_events.h> to include the following:
*
- * static void ftrace_event_<call>(proto)
- * {
- * event_trace_printk(_RET_IP_, "<call>: " <fmt>);
- * }
- *
- * static int ftrace_reg_event_<call>(struct ftrace_event_call *unused)
- * {
- * return register_trace_<call>(ftrace_event_<call>);
- * }
- *
- * static void ftrace_unreg_event_<call>(struct ftrace_event_call *unused)
- * {
- * unregister_trace_<call>(ftrace_event_<call>);
- * }
- *
- *
* For those macros defined with TRACE_EVENT:
*
* static struct ftrace_event_call event_<call>;
@@ -497,17 +484,21 @@ perf_trace_disable_##name(struct ftrace_event_call *unused) \
*
* static const char print_fmt_<call>[] = <TP_printk>;
*
+ * static struct ftrace_event_class __used event_class_<template> = {
+ * .system = "<system>",
+ * };
+ *
* static struct ftrace_event_call __used
* __attribute__((__aligned__(4)))
* __attribute__((section("_ftrace_events"))) event_<call> = {
* .name = "<call>",
- * .system = "<system>",
+ * .class = event_class_<template>,
* .raw_init = trace_event_raw_init,
- * .regfunc = ftrace_reg_event_<call>,
- * .unregfunc = ftrace_unreg_event_<call>,
+ * .regfunc = ftrace_raw_reg_event_<call>,
+ * .unregfunc = ftrace_raw_unreg_event_<call>,
* .print_fmt = print_fmt_<call>,
* .define_fields = ftrace_define_fields_<call>,
- * }
+ * };
*
*/
@@ -627,7 +618,10 @@ static struct trace_event ftrace_event_type_##call = { \
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
-static const char print_fmt_##call[] = print;
+static const char print_fmt_##call[] = print; \
+static struct ftrace_event_class __used event_class_##call = { \
+ .system = __stringify(TRACE_SYSTEM) \
+};
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, call, proto, args) \
@@ -636,7 +630,7 @@ static struct ftrace_event_call __used \
__attribute__((__aligned__(4))) \
__attribute__((section("_ftrace_events"))) event_##call = { \
.name = #call, \
- .system = __stringify(TRACE_SYSTEM), \
+ .class = &event_class_##template, \
.event = &ftrace_event_type_##call, \
.raw_init = trace_event_raw_init, \
.regfunc = ftrace_raw_reg_event_##call, \
@@ -644,7 +638,7 @@ __attribute__((section("_ftrace_events"))) event_##call = { \
.print_fmt = print_fmt_##template, \
.define_fields = ftrace_define_fields_##template, \
_TRACE_PERF_INIT(call) \
-}
+};
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, call, proto, args, print) \
@@ -655,7 +649,7 @@ static struct ftrace_event_call __used \
__attribute__((__aligned__(4))) \
__attribute__((section("_ftrace_events"))) event_##call = { \
.name = #call, \
- .system = __stringify(TRACE_SYSTEM), \
+ .class = &event_class_##template, \
.event = &ftrace_event_type_##call, \
.raw_init = trace_event_raw_init, \
.regfunc = ftrace_raw_reg_event_##call, \
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index c697c70..2f54b48 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -176,10 +176,10 @@ static int __ftrace_set_clr_event(const char *match, const char *sub,
if (match &&
strcmp(match, call->name) != 0 &&
- strcmp(match, call->system) != 0)
+ strcmp(match, call->class->system) != 0)
continue;
- if (sub && strcmp(sub, call->system) != 0)
+ if (sub && strcmp(sub, call->class->system) != 0)
continue;
if (event && strcmp(event, call->name) != 0)
@@ -355,8 +355,8 @@ static int t_show(struct seq_file *m, void *v)
{
struct ftrace_event_call *call = v;
- if (strcmp(call->system, TRACE_SYSTEM) != 0)
- seq_printf(m, "%s:", call->system);
+ if (strcmp(call->class->system, TRACE_SYSTEM) != 0)
+ seq_printf(m, "%s:", call->class->system);
seq_printf(m, "%s\n", call->name);
return 0;
@@ -453,7 +453,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
if (!call->name || !call->regfunc)
continue;
- if (system && strcmp(call->system, system) != 0)
+ if (system && strcmp(call->class->system, system) != 0)
continue;
/*
@@ -925,8 +925,8 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
* If the trace point header did not define TRACE_SYSTEM
* then the system would be called "TRACE_SYSTEM".
*/
- if (strcmp(call->system, TRACE_SYSTEM) != 0)
- d_events = event_subsystem_dir(call->system, d_events);
+ if (strcmp(call->class->system, TRACE_SYSTEM) != 0)
+ d_events = event_subsystem_dir(call->class->system, d_events);
call->dir = debugfs_create_dir(call->name, d_events);
if (!call->dir) {
@@ -1041,7 +1041,7 @@ static void __trace_remove_event_call(struct ftrace_event_call *call)
list_del(&call->list);
trace_destroy_fields(call);
destroy_preds(call);
- remove_subsystem_dir(call->system);
+ remove_subsystem_dir(call->class->system);
}
/* Remove an event_call */
@@ -1399,8 +1399,8 @@ static __init void event_trace_self_tests(void)
* syscalls as we test.
*/
#ifndef CONFIG_EVENT_TRACE_TEST_SYSCALLS
- if (call->system &&
- strcmp(call->system, "syscalls") == 0)
+ if (call->class->system &&
+ strcmp(call->class->system, "syscalls") == 0)
continue;
#endif
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 88c0b6d..ca32960 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -628,7 +628,7 @@ static int init_subsystem_preds(struct event_subsystem *system)
if (!call->define_fields)
continue;
- if (strcmp(call->system, system->name) != 0)
+ if (strcmp(call->class->system, system->name) != 0)
continue;
err = init_preds(call);
@@ -647,7 +647,7 @@ static void filter_free_subsystem_preds(struct event_subsystem *system)
if (!call->define_fields)
continue;
- if (strcmp(call->system, system->name) != 0)
+ if (strcmp(call->class->system, system->name) != 0)
continue;
filter_disable_preds(call);
@@ -1252,7 +1252,7 @@ static int replace_system_preds(struct event_subsystem *system,
if (!call->define_fields)
continue;
- if (strcmp(call->system, system->name) != 0)
+ if (strcmp(call->class->system, system->name) != 0)
continue;
/* try to see if the filter can be applied */
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index e091f64..7f16e21 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -18,6 +18,10 @@
#undef TRACE_SYSTEM
#define TRACE_SYSTEM ftrace
+struct ftrace_event_class event_class_ftrace = {
+ .system = __stringify(TRACE_SYSTEM),
+};
+
/* not needed for this file */
#undef __field_struct
#define __field_struct(type, item)
@@ -160,7 +164,7 @@ __attribute__((__aligned__(4))) \
__attribute__((section("_ftrace_events"))) event_##call = { \
.name = #call, \
.id = type, \
- .system = __stringify(TRACE_SYSTEM), \
+ .class = &event_class_ftrace, \
.raw_init = ftrace_raw_init_event, \
.print_fmt = print, \
.define_fields = ftrace_define_fields_##call, \
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 1251e36..eda220b 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -332,8 +332,8 @@ static struct trace_probe *alloc_trace_probe(const char *group,
goto error;
}
- tp->call.system = kstrdup(group, GFP_KERNEL);
- if (!tp->call.system)
+ tp->call.class->system = kstrdup(group, GFP_KERNEL);
+ if (!tp->call.class->system)
goto error;
INIT_LIST_HEAD(&tp->list);
@@ -361,7 +361,7 @@ static void free_trace_probe(struct trace_probe *tp)
for (i = 0; i < tp->nr_args; i++)
free_probe_arg(&tp->args[i]);
- kfree(tp->call.system);
+ kfree(tp->call.class->system);
kfree(tp->call.name);
kfree(tp->symbol);
kfree(tp);
@@ -374,7 +374,7 @@ static struct trace_probe *find_probe_event(const char *event,
list_for_each_entry(tp, &probe_list, list)
if (strcmp(tp->call.name, event) == 0 &&
- strcmp(tp->call.system, group) == 0)
+ strcmp(tp->call.class->system, group) == 0)
return tp;
return NULL;
}
@@ -399,7 +399,7 @@ static int register_trace_probe(struct trace_probe *tp)
mutex_lock(&probe_lock);
/* register as an event */
- old_tp = find_probe_event(tp->call.name, tp->call.system);
+ old_tp = find_probe_event(tp->call.name, tp->call.class->system);
if (old_tp) {
/* delete old event */
unregister_trace_probe(old_tp);
@@ -798,7 +798,7 @@ static int probes_seq_show(struct seq_file *m, void *v)
char buf[MAX_ARGSTR_LEN + 1];
seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p');
- seq_printf(m, ":%s/%s", tp->call.system, tp->call.name);
+ seq_printf(m, ":%s/%s", tp->call.class->system, tp->call.name);
if (!tp->symbol)
seq_printf(m, " 0x%p", tp->rp.kp.addr);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 4d6d711..d036a74 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -15,6 +15,10 @@ static int sys_refcount_exit;
static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
+struct ftrace_event_class event_class_syscalls = {
+ .system = "syscalls"
+};
+
extern unsigned long __start_syscalls_metadata[];
extern unsigned long __stop_syscalls_metadata[];
--
1.7.0
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH 02/13 v3] tracepoints: Add check trace callback type
2010-05-14 19:22 [PATCH 00/13 v3] [GIT PULL] tracing: shrinking trace events and updates Steven Rostedt
2010-05-14 19:22 ` [PATCH 01/13 v3] tracing: Create class struct for events Steven Rostedt
@ 2010-05-14 19:22 ` Steven Rostedt
2010-05-14 19:22 ` [PATCH 03/13 v3] tracing: Let tracepoints have data passed to tracepoint callbacks Steven Rostedt
` (10 subsequent siblings)
12 siblings, 0 replies; 19+ messages in thread
From: Steven Rostedt @ 2010-05-14 19:22 UTC (permalink / raw)
To: linux-kernel
Cc: Ingo Molnar, Andrew Morton, Frederic Weisbecker,
Mathieu Desnoyers, Masami Hiramatsu, Mathieu Desnoyers,
Thomas Gleixner, Peter Zijlstra, Arnaldo Carvalho de Melo,
Lai Jiangshan, Li Zefan, Christoph Hellwig
[-- Attachment #1: 0002-tracepoints-Add-check-trace-callback-type.patch --]
[-- Type: text/plain, Size: 2101 bytes --]
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
This check is meant to be used by tracepoint users which do a direct cast of
callbacks to (void *) for direct registration, thus bypassing the
register_trace_##name and unregister_trace_##name checks.
This permits to ensure that the callback type matches the function type at the
call site, but without generating any code.
Acked-by: Masami Hiramatsu <mhiramat@redhat.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
LKML-Reference: <20100430165959.GA25605@Krystal>
CC: Ingo Molnar <mingo@elte.hu>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Arnaldo Carvalho de Melo <acme@redhat.com>
CC: Lai Jiangshan <laijs@cn.fujitsu.com>
CC: Li Zefan <lizf@cn.fujitsu.com>
CC: Christoph Hellwig <hch@lst.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
include/linux/tracepoint.h | 7 ++++++-
1 files changed, 6 insertions(+), 1 deletions(-)
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 1d85f9a..8d5e4f6 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -137,9 +137,11 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
static inline int unregister_trace_##name(void (*probe)(proto)) \
{ \
return tracepoint_probe_unregister(#name, (void *)probe);\
+ } \
+ static inline void check_trace_callback_type_##name(void (*cb)(proto)) \
+ { \
}
-
#define DEFINE_TRACE_FN(name, reg, unreg) \
static const char __tpstrtab_##name[] \
__attribute__((section("__tracepoints_strings"))) = #name; \
@@ -168,6 +170,9 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
static inline int unregister_trace_##name(void (*probe)(proto)) \
{ \
return -ENOSYS; \
+ } \
+ static inline void check_trace_callback_type_##name(void (*cb)(proto)) \
+ { \
}
#define DEFINE_TRACE_FN(name, reg, unreg)
--
1.7.0
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH 03/13 v3] tracing: Let tracepoints have data passed to tracepoint callbacks
2010-05-14 19:22 [PATCH 00/13 v3] [GIT PULL] tracing: shrinking trace events and updates Steven Rostedt
2010-05-14 19:22 ` [PATCH 01/13 v3] tracing: Create class struct for events Steven Rostedt
2010-05-14 19:22 ` [PATCH 02/13 v3] tracepoints: Add check trace callback type Steven Rostedt
@ 2010-05-14 19:22 ` Steven Rostedt
2010-05-14 19:22 ` [PATCH 04/13 v3] tracing: Remove per event trace registering Steven Rostedt
` (9 subsequent siblings)
12 siblings, 0 replies; 19+ messages in thread
From: Steven Rostedt @ 2010-05-14 19:22 UTC (permalink / raw)
To: linux-kernel
Cc: Ingo Molnar, Andrew Morton, Frederic Weisbecker,
Mathieu Desnoyers, Masami Hiramatsu, Mathieu Desnoyers,
Neil Horman, David S. Miller
[-- Attachment #1: 0003-tracing-Let-tracepoints-have-data-passed-to-tracepoi.patch --]
[-- Type: text/plain, Size: 53936 bytes --]
From: Steven Rostedt <srostedt@redhat.com>
This patch adds data to be passed to tracepoint callbacks.
The created functions from DECLARE_TRACE() now need a mandatory data
parameter. For example:
DECLARE_TRACE(mytracepoint, int value, value)
Will create the register function:
int register_trace_mytracepoint((void(*)(void *data, int value))probe,
void *data);
As the first argument, all callbacks (probes) must take a (void *data)
parameter. So a callback for the above tracepoint will look like:
void myprobe(void *data, int value)
{
}
The callback may choose to ignore the data parameter.
This change allows callbacks to register a private data pointer along
with the function probe.
void mycallback(void *data, int value);
register_trace_mytracepoint(mycallback, mydata);
Then the mycallback() will receive the "mydata" as the first parameter
before the args.
A more detailed example:
DECLARE_TRACE(mytracepoint, TP_PROTO(int status), TP_ARGS(status));
/* In the C file */
DEFINE_TRACE(mytracepoint, TP_PROTO(int status), TP_ARGS(status));
[...]
trace_mytracepoint(status);
/* In a file registering this tracepoint */
int my_callback(void *data, int status)
{
struct my_struct my_data = data;
[...]
}
[...]
my_data = kmalloc(sizeof(*my_data), GFP_KERNEL);
init_my_data(my_data);
register_trace_mytracepoint(my_callback, my_data);
The same callback can also be registered to the same tracepoint as long
as the data registered is different. Note, the data must also be used
to unregister the callback:
unregister_trace_mytracepoint(my_callback, my_data);
Because of the data parameter, tracepoints declared this way can not have
no args. That is:
DECLARE_TRACE(mytracepoint, TP_PROTO(void), TP_ARGS());
will cause an error.
If no arguments are needed, a new macro can be used instead:
DECLARE_TRACE_NOARGS(mytracepoint);
Since there are no arguments, the proto and args fields are left out.
This is part of a series to make the tracepoint footprint smaller:
text data bss dec hex filename
4913961 1088356 861512 6863829 68bbd5 vmlinux.orig
4914025 1088868 861512 6864405 68be15 vmlinux.class
4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint
Again, this patch also increases the size of the kernel, but
lays the ground work for decreasing it.
v5: Fixed net/core/drop_monitor.c to handle these updates.
v4: Moved the DECLARE_TRACE() DECLARE_TRACE_NOARGS out of the
#ifdef CONFIG_TRACE_POINTS, since the two are the same in both
cases. The __DECLARE_TRACE() is what changes.
Thanks to Frederic Weisbecker for pointing this out.
v3: Made all register_* functions require data to be passed and
all callbacks to take a void * parameter as its first argument.
This makes the calling functions comply with C standards.
Also added more comments to the modifications of DECLARE_TRACE().
v2: Made the DECLARE_TRACE() have the ability to pass arguments
and added a new DECLARE_TRACE_NOARGS() for tracepoints that
do not need any arguments.
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Masami Hiramatsu <mhiramat@redhat.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
include/linux/tracepoint.h | 95 ++++++++++++++-----
include/trace/ftrace.h | 14 ++--
kernel/trace/blktrace.c | 125 +++++++++++++-----------
kernel/trace/ftrace.c | 7 +-
kernel/trace/kmemtrace.c | 42 +++++----
kernel/trace/trace_sched_switch.c | 20 ++--
kernel/trace/trace_sched_wakeup.c | 28 +++---
kernel/trace/trace_syscalls.c | 24 +++---
kernel/trace/trace_workqueue.c | 26 +++--
kernel/tracepoint.c | 91 ++++++++++--------
net/core/drop_monitor.c | 12 +-
samples/tracepoints/tp-samples-trace.h | 4 +-
samples/tracepoints/tracepoint-probe-sample.c | 13 ++-
samples/tracepoints/tracepoint-probe-sample2.c | 7 +-
14 files changed, 298 insertions(+), 210 deletions(-)
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 8d5e4f6..9a59d1f 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -20,12 +20,17 @@
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);
- void **funcs;
+ struct tracepoint_func *funcs;
} __attribute__((aligned(32))); /*
* Aligned on 32 bytes because it is
* globally visible and gcc happily
@@ -37,16 +42,19 @@ struct tracepoint {
* Connect a probe to a tracepoint.
* Internal API, should not be used directly.
*/
-extern int tracepoint_probe_register(const char *name, void *probe);
+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);
+extern int
+tracepoint_probe_unregister(const char *name, void *probe, void *data);
-extern int tracepoint_probe_register_noupdate(const char *name, void *probe);
-extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe);
+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 {
@@ -102,17 +110,27 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
/*
* 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) \
do { \
- void **it_func; \
+ struct tracepoint_func *it_func_ptr; \
+ void *it_func; \
+ void *__data; \
\
rcu_read_lock_sched_notrace(); \
- it_func = rcu_dereference_sched((tp)->funcs); \
- if (it_func) { \
+ it_func_ptr = rcu_dereference_sched((tp)->funcs); \
+ if (it_func_ptr) { \
do { \
- ((void(*)(proto))(*it_func))(args); \
- } while (*(++it_func)); \
+ 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)
@@ -122,23 +140,29 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
* 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) \
+#define __DECLARE_TRACE(name, proto, args, data_proto, data_args) \
extern struct tracepoint __tracepoint_##name; \
static inline void trace_##name(proto) \
{ \
if (unlikely(__tracepoint_##name.state)) \
__DO_TRACE(&__tracepoint_##name, \
- TP_PROTO(proto), TP_ARGS(args)); \
+ TP_PROTO(data_proto), \
+ TP_ARGS(data_args)); \
} \
- static inline int register_trace_##name(void (*probe)(proto)) \
+ static inline int \
+ register_trace_##name(void (*probe)(data_proto), void *data) \
{ \
- return tracepoint_probe_register(#name, (void *)probe); \
+ return tracepoint_probe_register(#name, (void *)probe, \
+ data); \
} \
- static inline int unregister_trace_##name(void (*probe)(proto)) \
+ static inline int \
+ unregister_trace_##name(void (*probe)(data_proto), void *data) \
{ \
- return tracepoint_probe_unregister(#name, (void *)probe);\
+ return tracepoint_probe_unregister(#name, (void *)probe, \
+ data); \
} \
- static inline void check_trace_callback_type_##name(void (*cb)(proto)) \
+ static inline void \
+ check_trace_callback_type_##name(void (*cb)(data_proto)) \
{ \
}
@@ -158,20 +182,22 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
EXPORT_SYMBOL(__tracepoint_##name)
#else /* !CONFIG_TRACEPOINTS */
-#define DECLARE_TRACE(name, proto, args) \
- static inline void _do_trace_##name(struct tracepoint *tp, proto) \
- { } \
+#define __DECLARE_TRACE(name, proto, args, data_proto, data_args) \
static inline void trace_##name(proto) \
{ } \
- static inline int register_trace_##name(void (*probe)(proto)) \
+ static inline int \
+ register_trace_##name(void (*probe)(data_proto), \
+ void *data) \
{ \
return -ENOSYS; \
} \
- static inline int unregister_trace_##name(void (*probe)(proto)) \
+ static inline int \
+ unregister_trace_##name(void (*probe)(data_proto), \
+ void *data) \
{ \
return -ENOSYS; \
} \
- static inline void check_trace_callback_type_##name(void (*cb)(proto)) \
+ static inline void check_trace_callback_type_##name(void (*cb)(data_proto)) \
{ \
}
@@ -181,6 +207,29 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
#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, , void *__data, __data)
+
+#define DECLARE_TRACE(name, proto, args) \
+ __DECLARE_TRACE(name, PARAMS(proto), PARAMS(args), \
+ PARAMS(void *__data, proto), \
+ PARAMS(__data, args))
+
#endif /* DECLARE_TRACE */
#ifndef TRACE_EVENT
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 7dcdfd8..ba28b64 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -406,18 +406,18 @@ static inline notrace int ftrace_get_offsets_##call( \
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, name, proto, args) \
\
-static void perf_trace_##name(proto); \
+static void perf_trace_##name(void *, proto); \
\
static notrace int \
perf_trace_enable_##name(struct ftrace_event_call *unused) \
{ \
- return register_trace_##name(perf_trace_##name); \
+ return register_trace_##name(perf_trace_##name, NULL); \
} \
\
static notrace void \
perf_trace_disable_##name(struct ftrace_event_call *unused) \
{ \
- unregister_trace_##name(perf_trace_##name); \
+ unregister_trace_##name(perf_trace_##name, NULL); \
}
#undef DEFINE_EVENT_PRINT
@@ -578,7 +578,7 @@ ftrace_raw_event_id_##call(struct ftrace_event_call *event_call, \
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, call, proto, args) \
\
-static notrace void ftrace_raw_event_##call(proto) \
+static notrace void ftrace_raw_event_##call(void *__ignore, proto) \
{ \
ftrace_raw_event_id_##template(&event_##call, args); \
} \
@@ -586,13 +586,13 @@ static notrace void ftrace_raw_event_##call(proto) \
static notrace int \
ftrace_raw_reg_event_##call(struct ftrace_event_call *unused) \
{ \
- return register_trace_##call(ftrace_raw_event_##call); \
+ return register_trace_##call(ftrace_raw_event_##call, NULL); \
} \
\
static notrace void \
ftrace_raw_unreg_event_##call(struct ftrace_event_call *unused) \
{ \
- unregister_trace_##call(ftrace_raw_event_##call); \
+ unregister_trace_##call(ftrace_raw_event_##call, NULL); \
} \
\
static struct trace_event ftrace_event_type_##call = { \
@@ -793,7 +793,7 @@ perf_trace_templ_##call(struct ftrace_event_call *event_call, \
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, call, proto, args) \
-static notrace void perf_trace_##call(proto) \
+static notrace void perf_trace_##call(void *__ignore, proto) \
{ \
struct ftrace_event_call *event_call = &event_##call; \
\
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index b3bc91a..19d93f8 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -675,28 +675,33 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
}
}
-static void blk_add_trace_rq_abort(struct request_queue *q, struct request *rq)
+static void blk_add_trace_rq_abort(void *ignore,
+ struct request_queue *q, struct request *rq)
{
blk_add_trace_rq(q, rq, BLK_TA_ABORT);
}
-static void blk_add_trace_rq_insert(struct request_queue *q, struct request *rq)
+static void blk_add_trace_rq_insert(void *ignore,
+ struct request_queue *q, struct request *rq)
{
blk_add_trace_rq(q, rq, BLK_TA_INSERT);
}
-static void blk_add_trace_rq_issue(struct request_queue *q, struct request *rq)
+static void blk_add_trace_rq_issue(void *ignore,
+ struct request_queue *q, struct request *rq)
{
blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
}
-static void blk_add_trace_rq_requeue(struct request_queue *q,
+static void blk_add_trace_rq_requeue(void *ignore,
+ struct request_queue *q,
struct request *rq)
{
blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
}
-static void blk_add_trace_rq_complete(struct request_queue *q,
+static void blk_add_trace_rq_complete(void *ignore,
+ struct request_queue *q,
struct request *rq)
{
blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
@@ -724,34 +729,40 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
!bio_flagged(bio, BIO_UPTODATE), 0, NULL);
}
-static void blk_add_trace_bio_bounce(struct request_queue *q, struct bio *bio)
+static void blk_add_trace_bio_bounce(void *ignore,
+ struct request_queue *q, struct bio *bio)
{
blk_add_trace_bio(q, bio, BLK_TA_BOUNCE);
}
-static void blk_add_trace_bio_complete(struct request_queue *q, struct bio *bio)
+static void blk_add_trace_bio_complete(void *ignore,
+ struct request_queue *q, struct bio *bio)
{
blk_add_trace_bio(q, bio, BLK_TA_COMPLETE);
}
-static void blk_add_trace_bio_backmerge(struct request_queue *q,
+static void blk_add_trace_bio_backmerge(void *ignore,
+ struct request_queue *q,
struct bio *bio)
{
blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE);
}
-static void blk_add_trace_bio_frontmerge(struct request_queue *q,
+static void blk_add_trace_bio_frontmerge(void *ignore,
+ struct request_queue *q,
struct bio *bio)
{
blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE);
}
-static void blk_add_trace_bio_queue(struct request_queue *q, struct bio *bio)
+static void blk_add_trace_bio_queue(void *ignore,
+ struct request_queue *q, struct bio *bio)
{
blk_add_trace_bio(q, bio, BLK_TA_QUEUE);
}
-static void blk_add_trace_getrq(struct request_queue *q,
+static void blk_add_trace_getrq(void *ignore,
+ struct request_queue *q,
struct bio *bio, int rw)
{
if (bio)
@@ -765,7 +776,8 @@ static void blk_add_trace_getrq(struct request_queue *q,
}
-static void blk_add_trace_sleeprq(struct request_queue *q,
+static void blk_add_trace_sleeprq(void *ignore,
+ struct request_queue *q,
struct bio *bio, int rw)
{
if (bio)
@@ -779,7 +791,7 @@ static void blk_add_trace_sleeprq(struct request_queue *q,
}
}
-static void blk_add_trace_plug(struct request_queue *q)
+static void blk_add_trace_plug(void *ignore, struct request_queue *q)
{
struct blk_trace *bt = q->blk_trace;
@@ -787,7 +799,7 @@ static void blk_add_trace_plug(struct request_queue *q)
__blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL);
}
-static void blk_add_trace_unplug_io(struct request_queue *q)
+static void blk_add_trace_unplug_io(void *ignore, struct request_queue *q)
{
struct blk_trace *bt = q->blk_trace;
@@ -800,7 +812,7 @@ static void blk_add_trace_unplug_io(struct request_queue *q)
}
}
-static void blk_add_trace_unplug_timer(struct request_queue *q)
+static void blk_add_trace_unplug_timer(void *ignore, struct request_queue *q)
{
struct blk_trace *bt = q->blk_trace;
@@ -813,7 +825,8 @@ static void blk_add_trace_unplug_timer(struct request_queue *q)
}
}
-static void blk_add_trace_split(struct request_queue *q, struct bio *bio,
+static void blk_add_trace_split(void *ignore,
+ struct request_queue *q, struct bio *bio,
unsigned int pdu)
{
struct blk_trace *bt = q->blk_trace;
@@ -839,8 +852,9 @@ static void blk_add_trace_split(struct request_queue *q, struct bio *bio,
* it spans a stripe (or similar). Add a trace for that action.
*
**/
-static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
- dev_t dev, sector_t from)
+static void blk_add_trace_remap(void *ignore,
+ struct request_queue *q, struct bio *bio,
+ dev_t dev, sector_t from)
{
struct blk_trace *bt = q->blk_trace;
struct blk_io_trace_remap r;
@@ -869,7 +883,8 @@ static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
* Add a trace for that action.
*
**/
-static void blk_add_trace_rq_remap(struct request_queue *q,
+static void blk_add_trace_rq_remap(void *ignore,
+ struct request_queue *q,
struct request *rq, dev_t dev,
sector_t from)
{
@@ -921,64 +936,64 @@ static void blk_register_tracepoints(void)
{
int ret;
- ret = register_trace_block_rq_abort(blk_add_trace_rq_abort);
+ ret = register_trace_block_rq_abort(blk_add_trace_rq_abort, NULL);
WARN_ON(ret);
- ret = register_trace_block_rq_insert(blk_add_trace_rq_insert);
+ ret = register_trace_block_rq_insert(blk_add_trace_rq_insert, NULL);
WARN_ON(ret);
- ret = register_trace_block_rq_issue(blk_add_trace_rq_issue);
+ ret = register_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
WARN_ON(ret);
- ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue);
+ ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL);
WARN_ON(ret);
- ret = register_trace_block_rq_complete(blk_add_trace_rq_complete);
+ ret = register_trace_block_rq_complete(blk_add_trace_rq_complete, NULL);
WARN_ON(ret);
- ret = register_trace_block_bio_bounce(blk_add_trace_bio_bounce);
+ ret = register_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL);
WARN_ON(ret);
- ret = register_trace_block_bio_complete(blk_add_trace_bio_complete);
+ ret = register_trace_block_bio_complete(blk_add_trace_bio_complete, NULL);
WARN_ON(ret);
- ret = register_trace_block_bio_backmerge(blk_add_trace_bio_backmerge);
+ ret = register_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL);
WARN_ON(ret);
- ret = register_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge);
+ ret = register_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL);
WARN_ON(ret);
- ret = register_trace_block_bio_queue(blk_add_trace_bio_queue);
+ ret = register_trace_block_bio_queue(blk_add_trace_bio_queue, NULL);
WARN_ON(ret);
- ret = register_trace_block_getrq(blk_add_trace_getrq);
+ ret = register_trace_block_getrq(blk_add_trace_getrq, NULL);
WARN_ON(ret);
- ret = register_trace_block_sleeprq(blk_add_trace_sleeprq);
+ ret = register_trace_block_sleeprq(blk_add_trace_sleeprq, NULL);
WARN_ON(ret);
- ret = register_trace_block_plug(blk_add_trace_plug);
+ ret = register_trace_block_plug(blk_add_trace_plug, NULL);
WARN_ON(ret);
- ret = register_trace_block_unplug_timer(blk_add_trace_unplug_timer);
+ ret = register_trace_block_unplug_timer(blk_add_trace_unplug_timer, NULL);
WARN_ON(ret);
- ret = register_trace_block_unplug_io(blk_add_trace_unplug_io);
+ ret = register_trace_block_unplug_io(blk_add_trace_unplug_io, NULL);
WARN_ON(ret);
- ret = register_trace_block_split(blk_add_trace_split);
+ ret = register_trace_block_split(blk_add_trace_split, NULL);
WARN_ON(ret);
- ret = register_trace_block_remap(blk_add_trace_remap);
+ ret = register_trace_block_remap(blk_add_trace_remap, NULL);
WARN_ON(ret);
- ret = register_trace_block_rq_remap(blk_add_trace_rq_remap);
+ ret = register_trace_block_rq_remap(blk_add_trace_rq_remap, NULL);
WARN_ON(ret);
}
static void blk_unregister_tracepoints(void)
{
- unregister_trace_block_rq_remap(blk_add_trace_rq_remap);
- unregister_trace_block_remap(blk_add_trace_remap);
- unregister_trace_block_split(blk_add_trace_split);
- unregister_trace_block_unplug_io(blk_add_trace_unplug_io);
- unregister_trace_block_unplug_timer(blk_add_trace_unplug_timer);
- unregister_trace_block_plug(blk_add_trace_plug);
- unregister_trace_block_sleeprq(blk_add_trace_sleeprq);
- unregister_trace_block_getrq(blk_add_trace_getrq);
- unregister_trace_block_bio_queue(blk_add_trace_bio_queue);
- unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge);
- unregister_trace_block_bio_backmerge(blk_add_trace_bio_backmerge);
- unregister_trace_block_bio_complete(blk_add_trace_bio_complete);
- unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce);
- unregister_trace_block_rq_complete(blk_add_trace_rq_complete);
- unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue);
- unregister_trace_block_rq_issue(blk_add_trace_rq_issue);
- unregister_trace_block_rq_insert(blk_add_trace_rq_insert);
- unregister_trace_block_rq_abort(blk_add_trace_rq_abort);
+ unregister_trace_block_rq_remap(blk_add_trace_rq_remap, NULL);
+ unregister_trace_block_remap(blk_add_trace_remap, NULL);
+ unregister_trace_block_split(blk_add_trace_split, NULL);
+ unregister_trace_block_unplug_io(blk_add_trace_unplug_io, NULL);
+ unregister_trace_block_unplug_timer(blk_add_trace_unplug_timer, NULL);
+ unregister_trace_block_plug(blk_add_trace_plug, NULL);
+ unregister_trace_block_sleeprq(blk_add_trace_sleeprq, NULL);
+ unregister_trace_block_getrq(blk_add_trace_getrq, NULL);
+ unregister_trace_block_bio_queue(blk_add_trace_bio_queue, NULL);
+ unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL);
+ unregister_trace_block_bio_backmerge(blk_add_trace_bio_backmerge, NULL);
+ unregister_trace_block_bio_complete(blk_add_trace_bio_complete, NULL);
+ unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL);
+ unregister_trace_block_rq_complete(blk_add_trace_rq_complete, NULL);
+ unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL);
+ unregister_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
+ unregister_trace_block_rq_insert(blk_add_trace_rq_insert, NULL);
+ unregister_trace_block_rq_abort(blk_add_trace_rq_abort, NULL);
tracepoint_synchronize_unregister();
}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 32837e1..6d2cb14 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3234,7 +3234,8 @@ free:
}
static void
-ftrace_graph_probe_sched_switch(struct task_struct *prev, struct task_struct *next)
+ftrace_graph_probe_sched_switch(void *ignore,
+ struct task_struct *prev, struct task_struct *next)
{
unsigned long long timestamp;
int index;
@@ -3288,7 +3289,7 @@ static int start_graph_tracing(void)
} while (ret == -EAGAIN);
if (!ret) {
- ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch);
+ ret = register_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
if (ret)
pr_info("ftrace_graph: Couldn't activate tracepoint"
" probe to kernel_sched_switch\n");
@@ -3364,7 +3365,7 @@ void unregister_ftrace_graph(void)
ftrace_graph_entry = ftrace_graph_entry_stub;
ftrace_shutdown(FTRACE_STOP_FUNC_RET);
unregister_pm_notifier(&ftrace_suspend_notifier);
- unregister_trace_sched_switch(ftrace_graph_probe_sched_switch);
+ unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);
out:
mutex_unlock(&ftrace_lock);
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
index a91da69..7253d0c 100644
--- a/kernel/trace/kmemtrace.c
+++ b/kernel/trace/kmemtrace.c
@@ -95,7 +95,8 @@ static inline void kmemtrace_free(enum kmemtrace_type_id type_id,
trace_wake_up();
}
-static void kmemtrace_kmalloc(unsigned long call_site,
+static void kmemtrace_kmalloc(void *ignore,
+ unsigned long call_site,
const void *ptr,
size_t bytes_req,
size_t bytes_alloc,
@@ -105,7 +106,8 @@ static void kmemtrace_kmalloc(unsigned long call_site,
bytes_req, bytes_alloc, gfp_flags, -1);
}
-static void kmemtrace_kmem_cache_alloc(unsigned long call_site,
+static void kmemtrace_kmem_cache_alloc(void *ignore,
+ unsigned long call_site,
const void *ptr,
size_t bytes_req,
size_t bytes_alloc,
@@ -115,7 +117,8 @@ static void kmemtrace_kmem_cache_alloc(unsigned long call_site,
bytes_req, bytes_alloc, gfp_flags, -1);
}
-static void kmemtrace_kmalloc_node(unsigned long call_site,
+static void kmemtrace_kmalloc_node(void *ignore,
+ unsigned long call_site,
const void *ptr,
size_t bytes_req,
size_t bytes_alloc,
@@ -126,7 +129,8 @@ static void kmemtrace_kmalloc_node(unsigned long call_site,
bytes_req, bytes_alloc, gfp_flags, node);
}
-static void kmemtrace_kmem_cache_alloc_node(unsigned long call_site,
+static void kmemtrace_kmem_cache_alloc_node(void *ignore,
+ unsigned long call_site,
const void *ptr,
size_t bytes_req,
size_t bytes_alloc,
@@ -137,12 +141,14 @@ static void kmemtrace_kmem_cache_alloc_node(unsigned long call_site,
bytes_req, bytes_alloc, gfp_flags, node);
}
-static void kmemtrace_kfree(unsigned long call_site, const void *ptr)
+static void
+kmemtrace_kfree(void *ignore, unsigned long call_site, const void *ptr)
{
kmemtrace_free(KMEMTRACE_TYPE_KMALLOC, call_site, ptr);
}
-static void kmemtrace_kmem_cache_free(unsigned long call_site, const void *ptr)
+static void kmemtrace_kmem_cache_free(void *ignore,
+ unsigned long call_site, const void *ptr)
{
kmemtrace_free(KMEMTRACE_TYPE_CACHE, call_site, ptr);
}
@@ -151,34 +157,34 @@ static int kmemtrace_start_probes(void)
{
int err;
- err = register_trace_kmalloc(kmemtrace_kmalloc);
+ err = register_trace_kmalloc(kmemtrace_kmalloc, NULL);
if (err)
return err;
- err = register_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc);
+ err = register_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc, NULL);
if (err)
return err;
- err = register_trace_kmalloc_node(kmemtrace_kmalloc_node);
+ err = register_trace_kmalloc_node(kmemtrace_kmalloc_node, NULL);
if (err)
return err;
- err = register_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node);
+ err = register_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node, NULL);
if (err)
return err;
- err = register_trace_kfree(kmemtrace_kfree);
+ err = register_trace_kfree(kmemtrace_kfree, NULL);
if (err)
return err;
- err = register_trace_kmem_cache_free(kmemtrace_kmem_cache_free);
+ err = register_trace_kmem_cache_free(kmemtrace_kmem_cache_free, NULL);
return err;
}
static void kmemtrace_stop_probes(void)
{
- unregister_trace_kmalloc(kmemtrace_kmalloc);
- unregister_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc);
- unregister_trace_kmalloc_node(kmemtrace_kmalloc_node);
- unregister_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node);
- unregister_trace_kfree(kmemtrace_kfree);
- unregister_trace_kmem_cache_free(kmemtrace_kmem_cache_free);
+ unregister_trace_kmalloc(kmemtrace_kmalloc, NULL);
+ unregister_trace_kmem_cache_alloc(kmemtrace_kmem_cache_alloc, NULL);
+ unregister_trace_kmalloc_node(kmemtrace_kmalloc_node, NULL);
+ unregister_trace_kmem_cache_alloc_node(kmemtrace_kmem_cache_alloc_node, NULL);
+ unregister_trace_kfree(kmemtrace_kfree, NULL);
+ unregister_trace_kmem_cache_free(kmemtrace_kmem_cache_free, NULL);
}
static int kmem_trace_init(struct trace_array *tr)
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index a55fccf..8f758d0 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -50,7 +50,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
}
static void
-probe_sched_switch(struct task_struct *prev, struct task_struct *next)
+probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *next)
{
struct trace_array_cpu *data;
unsigned long flags;
@@ -108,7 +108,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
}
static void
-probe_sched_wakeup(struct task_struct *wakee, int success)
+probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success)
{
struct trace_array_cpu *data;
unsigned long flags;
@@ -138,21 +138,21 @@ static int tracing_sched_register(void)
{
int ret;
- ret = register_trace_sched_wakeup(probe_sched_wakeup);
+ ret = register_trace_sched_wakeup(probe_sched_wakeup, NULL);
if (ret) {
pr_info("wakeup trace: Couldn't activate tracepoint"
" probe to kernel_sched_wakeup\n");
return ret;
}
- ret = register_trace_sched_wakeup_new(probe_sched_wakeup);
+ ret = register_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
if (ret) {
pr_info("wakeup trace: Couldn't activate tracepoint"
" probe to kernel_sched_wakeup_new\n");
goto fail_deprobe;
}
- ret = register_trace_sched_switch(probe_sched_switch);
+ ret = register_trace_sched_switch(probe_sched_switch, NULL);
if (ret) {
pr_info("sched trace: Couldn't activate tracepoint"
" probe to kernel_sched_switch\n");
@@ -161,17 +161,17 @@ static int tracing_sched_register(void)
return ret;
fail_deprobe_wake_new:
- unregister_trace_sched_wakeup_new(probe_sched_wakeup);
+ unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
fail_deprobe:
- unregister_trace_sched_wakeup(probe_sched_wakeup);
+ unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
return ret;
}
static void tracing_sched_unregister(void)
{
- unregister_trace_sched_switch(probe_sched_switch);
- unregister_trace_sched_wakeup_new(probe_sched_wakeup);
- unregister_trace_sched_wakeup(probe_sched_wakeup);
+ unregister_trace_sched_switch(probe_sched_switch, NULL);
+ unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
+ unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
}
static void tracing_start_sched_switch(void)
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 8052446..0e73bc2 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -98,7 +98,8 @@ static int report_latency(cycle_t delta)
return 1;
}
-static void probe_wakeup_migrate_task(struct task_struct *task, int cpu)
+static void
+probe_wakeup_migrate_task(void *ignore, struct task_struct *task, int cpu)
{
if (task != wakeup_task)
return;
@@ -107,7 +108,8 @@ static void probe_wakeup_migrate_task(struct task_struct *task, int cpu)
}
static void notrace
-probe_wakeup_sched_switch(struct task_struct *prev, struct task_struct *next)
+probe_wakeup_sched_switch(void *ignore,
+ struct task_struct *prev, struct task_struct *next)
{
struct trace_array_cpu *data;
cycle_t T0, T1, delta;
@@ -199,7 +201,7 @@ static void wakeup_reset(struct trace_array *tr)
}
static void
-probe_wakeup(struct task_struct *p, int success)
+probe_wakeup(void *ignore, struct task_struct *p, int success)
{
struct trace_array_cpu *data;
int cpu = smp_processor_id();
@@ -263,28 +265,28 @@ static void start_wakeup_tracer(struct trace_array *tr)
{
int ret;
- ret = register_trace_sched_wakeup(probe_wakeup);
+ ret = register_trace_sched_wakeup(probe_wakeup, NULL);
if (ret) {
pr_info("wakeup trace: Couldn't activate tracepoint"
" probe to kernel_sched_wakeup\n");
return;
}
- ret = register_trace_sched_wakeup_new(probe_wakeup);
+ ret = register_trace_sched_wakeup_new(probe_wakeup, NULL);
if (ret) {
pr_info("wakeup trace: Couldn't activate tracepoint"
" probe to kernel_sched_wakeup_new\n");
goto fail_deprobe;
}
- ret = register_trace_sched_switch(probe_wakeup_sched_switch);
+ ret = register_trace_sched_switch(probe_wakeup_sched_switch, NULL);
if (ret) {
pr_info("sched trace: Couldn't activate tracepoint"
" probe to kernel_sched_switch\n");
goto fail_deprobe_wake_new;
}
- ret = register_trace_sched_migrate_task(probe_wakeup_migrate_task);
+ ret = register_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL);
if (ret) {
pr_info("wakeup trace: Couldn't activate tracepoint"
" probe to kernel_sched_migrate_task\n");
@@ -311,19 +313,19 @@ static void start_wakeup_tracer(struct trace_array *tr)
return;
fail_deprobe_wake_new:
- unregister_trace_sched_wakeup_new(probe_wakeup);
+ unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
fail_deprobe:
- unregister_trace_sched_wakeup(probe_wakeup);
+ unregister_trace_sched_wakeup(probe_wakeup, NULL);
}
static void stop_wakeup_tracer(struct trace_array *tr)
{
tracer_enabled = 0;
unregister_ftrace_function(&trace_ops);
- unregister_trace_sched_switch(probe_wakeup_sched_switch);
- unregister_trace_sched_wakeup_new(probe_wakeup);
- unregister_trace_sched_wakeup(probe_wakeup);
- unregister_trace_sched_migrate_task(probe_wakeup_migrate_task);
+ unregister_trace_sched_switch(probe_wakeup_sched_switch, NULL);
+ unregister_trace_sched_wakeup_new(probe_wakeup, NULL);
+ unregister_trace_sched_wakeup(probe_wakeup, NULL);
+ unregister_trace_sched_migrate_task(probe_wakeup_migrate_task, NULL);
}
static int __wakeup_tracer_init(struct trace_array *tr)
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index d036a74..b8d30e7 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -247,7 +247,7 @@ int syscall_exit_define_fields(struct ftrace_event_call *call)
return ret;
}
-void ftrace_syscall_enter(struct pt_regs *regs, long id)
+void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
{
struct syscall_trace_enter *entry;
struct syscall_metadata *sys_data;
@@ -282,7 +282,7 @@ void ftrace_syscall_enter(struct pt_regs *regs, long id)
trace_current_buffer_unlock_commit(buffer, event, 0, 0);
}
-void ftrace_syscall_exit(struct pt_regs *regs, long ret)
+void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
{
struct syscall_trace_exit *entry;
struct syscall_metadata *sys_data;
@@ -324,7 +324,7 @@ int reg_event_syscall_enter(struct ftrace_event_call *call)
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
if (!sys_refcount_enter)
- ret = register_trace_sys_enter(ftrace_syscall_enter);
+ ret = register_trace_sys_enter(ftrace_syscall_enter, NULL);
if (!ret) {
set_bit(num, enabled_enter_syscalls);
sys_refcount_enter++;
@@ -344,7 +344,7 @@ void unreg_event_syscall_enter(struct ftrace_event_call *call)
sys_refcount_enter--;
clear_bit(num, enabled_enter_syscalls);
if (!sys_refcount_enter)
- unregister_trace_sys_enter(ftrace_syscall_enter);
+ unregister_trace_sys_enter(ftrace_syscall_enter, NULL);
mutex_unlock(&syscall_trace_lock);
}
@@ -358,7 +358,7 @@ int reg_event_syscall_exit(struct ftrace_event_call *call)
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
if (!sys_refcount_exit)
- ret = register_trace_sys_exit(ftrace_syscall_exit);
+ ret = register_trace_sys_exit(ftrace_syscall_exit, NULL);
if (!ret) {
set_bit(num, enabled_exit_syscalls);
sys_refcount_exit++;
@@ -378,7 +378,7 @@ void unreg_event_syscall_exit(struct ftrace_event_call *call)
sys_refcount_exit--;
clear_bit(num, enabled_exit_syscalls);
if (!sys_refcount_exit)
- unregister_trace_sys_exit(ftrace_syscall_exit);
+ unregister_trace_sys_exit(ftrace_syscall_exit, NULL);
mutex_unlock(&syscall_trace_lock);
}
@@ -438,7 +438,7 @@ static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls);
static int sys_perf_refcount_enter;
static int sys_perf_refcount_exit;
-static void perf_syscall_enter(struct pt_regs *regs, long id)
+static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
{
struct syscall_metadata *sys_data;
struct syscall_trace_enter *rec;
@@ -484,7 +484,7 @@ int perf_sysenter_enable(struct ftrace_event_call *call)
mutex_lock(&syscall_trace_lock);
if (!sys_perf_refcount_enter)
- ret = register_trace_sys_enter(perf_syscall_enter);
+ ret = register_trace_sys_enter(perf_syscall_enter, NULL);
if (ret) {
pr_info("event trace: Could not activate"
"syscall entry trace point");
@@ -506,11 +506,11 @@ void perf_sysenter_disable(struct ftrace_event_call *call)
sys_perf_refcount_enter--;
clear_bit(num, enabled_perf_enter_syscalls);
if (!sys_perf_refcount_enter)
- unregister_trace_sys_enter(perf_syscall_enter);
+ unregister_trace_sys_enter(perf_syscall_enter, NULL);
mutex_unlock(&syscall_trace_lock);
}
-static void perf_syscall_exit(struct pt_regs *regs, long ret)
+static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
{
struct syscall_metadata *sys_data;
struct syscall_trace_exit *rec;
@@ -559,7 +559,7 @@ int perf_sysexit_enable(struct ftrace_event_call *call)
mutex_lock(&syscall_trace_lock);
if (!sys_perf_refcount_exit)
- ret = register_trace_sys_exit(perf_syscall_exit);
+ ret = register_trace_sys_exit(perf_syscall_exit, NULL);
if (ret) {
pr_info("event trace: Could not activate"
"syscall exit trace point");
@@ -581,7 +581,7 @@ void perf_sysexit_disable(struct ftrace_event_call *call)
sys_perf_refcount_exit--;
clear_bit(num, enabled_perf_exit_syscalls);
if (!sys_perf_refcount_exit)
- unregister_trace_sys_exit(perf_syscall_exit);
+ unregister_trace_sys_exit(perf_syscall_exit, NULL);
mutex_unlock(&syscall_trace_lock);
}
diff --git a/kernel/trace/trace_workqueue.c b/kernel/trace/trace_workqueue.c
index cc2d2fa..a7cc379 100644
--- a/kernel/trace/trace_workqueue.c
+++ b/kernel/trace/trace_workqueue.c
@@ -49,7 +49,8 @@ static void cpu_workqueue_stat_free(struct kref *kref)
/* Insertion of a work */
static void
-probe_workqueue_insertion(struct task_struct *wq_thread,
+probe_workqueue_insertion(void *ignore,
+ struct task_struct *wq_thread,
struct work_struct *work)
{
int cpu = cpumask_first(&wq_thread->cpus_allowed);
@@ -70,7 +71,8 @@ found:
/* Execution of a work */
static void
-probe_workqueue_execution(struct task_struct *wq_thread,
+probe_workqueue_execution(void *ignore,
+ struct task_struct *wq_thread,
struct work_struct *work)
{
int cpu = cpumask_first(&wq_thread->cpus_allowed);
@@ -90,7 +92,8 @@ found:
}
/* Creation of a cpu workqueue thread */
-static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu)
+static void probe_workqueue_creation(void *ignore,
+ struct task_struct *wq_thread, int cpu)
{
struct cpu_workqueue_stats *cws;
unsigned long flags;
@@ -114,7 +117,8 @@ static void probe_workqueue_creation(struct task_struct *wq_thread, int cpu)
}
/* Destruction of a cpu workqueue thread */
-static void probe_workqueue_destruction(struct task_struct *wq_thread)
+static void
+probe_workqueue_destruction(void *ignore, struct task_struct *wq_thread)
{
/* Workqueue only execute on one cpu */
int cpu = cpumask_first(&wq_thread->cpus_allowed);
@@ -259,19 +263,19 @@ int __init trace_workqueue_early_init(void)
{
int ret, cpu;
- ret = register_trace_workqueue_insertion(probe_workqueue_insertion);
+ ret = register_trace_workqueue_insertion(probe_workqueue_insertion, NULL);
if (ret)
goto out;
- ret = register_trace_workqueue_execution(probe_workqueue_execution);
+ ret = register_trace_workqueue_execution(probe_workqueue_execution, NULL);
if (ret)
goto no_insertion;
- ret = register_trace_workqueue_creation(probe_workqueue_creation);
+ ret = register_trace_workqueue_creation(probe_workqueue_creation, NULL);
if (ret)
goto no_execution;
- ret = register_trace_workqueue_destruction(probe_workqueue_destruction);
+ ret = register_trace_workqueue_destruction(probe_workqueue_destruction, NULL);
if (ret)
goto no_creation;
@@ -283,11 +287,11 @@ int __init trace_workqueue_early_init(void)
return 0;
no_creation:
- unregister_trace_workqueue_creation(probe_workqueue_creation);
+ unregister_trace_workqueue_creation(probe_workqueue_creation, NULL);
no_execution:
- unregister_trace_workqueue_execution(probe_workqueue_execution);
+ unregister_trace_workqueue_execution(probe_workqueue_execution, NULL);
no_insertion:
- unregister_trace_workqueue_insertion(probe_workqueue_insertion);
+ unregister_trace_workqueue_insertion(probe_workqueue_insertion, NULL);
out:
pr_warning("trace_workqueue: unable to trace workqueues\n");
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index cc89be5..c77f3ec 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -54,7 +54,7 @@ static struct hlist_head tracepoint_table[TRACEPOINT_TABLE_SIZE];
*/
struct tracepoint_entry {
struct hlist_node hlist;
- void **funcs;
+ struct tracepoint_func *funcs;
int refcount; /* Number of times armed. 0 if disarmed. */
char name[0];
};
@@ -64,12 +64,12 @@ struct tp_probes {
struct rcu_head rcu;
struct list_head list;
} u;
- void *probes[0];
+ struct tracepoint_func probes[0];
};
static inline void *allocate_probes(int count)
{
- struct tp_probes *p = kmalloc(count * sizeof(void *)
+ struct tp_probes *p = kmalloc(count * sizeof(struct tracepoint_func)
+ sizeof(struct tp_probes), GFP_KERNEL);
return p == NULL ? NULL : p->probes;
}
@@ -79,7 +79,7 @@ static void rcu_free_old_probes(struct rcu_head *head)
kfree(container_of(head, struct tp_probes, u.rcu));
}
-static inline void release_probes(void *old)
+static inline void release_probes(struct tracepoint_func *old)
{
if (old) {
struct tp_probes *tp_probes = container_of(old,
@@ -95,15 +95,16 @@ static void debug_print_probes(struct tracepoint_entry *entry)
if (!tracepoint_debug || !entry->funcs)
return;
- for (i = 0; entry->funcs[i]; i++)
- printk(KERN_DEBUG "Probe %d : %p\n", i, entry->funcs[i]);
+ for (i = 0; entry->funcs[i].func; i++)
+ printk(KERN_DEBUG "Probe %d : %p\n", i, entry->funcs[i].func);
}
-static void *
-tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe)
+static struct tracepoint_func *
+tracepoint_entry_add_probe(struct tracepoint_entry *entry,
+ void *probe, void *data)
{
int nr_probes = 0;
- void **old, **new;
+ struct tracepoint_func *old, *new;
WARN_ON(!probe);
@@ -111,8 +112,9 @@ tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe)
old = entry->funcs;
if (old) {
/* (N -> N+1), (N != 0, 1) probes */
- for (nr_probes = 0; old[nr_probes]; nr_probes++)
- if (old[nr_probes] == probe)
+ for (nr_probes = 0; old[nr_probes].func; nr_probes++)
+ if (old[nr_probes].func == probe &&
+ old[nr_probes].data == data)
return ERR_PTR(-EEXIST);
}
/* + 2 : one for new probe, one for NULL func */
@@ -120,9 +122,10 @@ tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe)
if (new == NULL)
return ERR_PTR(-ENOMEM);
if (old)
- memcpy(new, old, nr_probes * sizeof(void *));
- new[nr_probes] = probe;
- new[nr_probes + 1] = NULL;
+ memcpy(new, old, nr_probes * sizeof(struct tracepoint_func));
+ new[nr_probes].func = probe;
+ new[nr_probes].data = data;
+ new[nr_probes + 1].func = NULL;
entry->refcount = nr_probes + 1;
entry->funcs = new;
debug_print_probes(entry);
@@ -130,10 +133,11 @@ tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe)
}
static void *
-tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe)
+tracepoint_entry_remove_probe(struct tracepoint_entry *entry,
+ void *probe, void *data)
{
int nr_probes = 0, nr_del = 0, i;
- void **old, **new;
+ struct tracepoint_func *old, *new;
old = entry->funcs;
@@ -142,8 +146,10 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe)
debug_print_probes(entry);
/* (N -> M), (N > 1, M >= 0) probes */
- for (nr_probes = 0; old[nr_probes]; nr_probes++) {
- if ((!probe || old[nr_probes] == probe))
+ for (nr_probes = 0; old[nr_probes].func; nr_probes++) {
+ if (!probe ||
+ (old[nr_probes].func == probe &&
+ old[nr_probes].data == data))
nr_del++;
}
@@ -160,10 +166,11 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe)
new = allocate_probes(nr_probes - nr_del + 1);
if (new == NULL)
return ERR_PTR(-ENOMEM);
- for (i = 0; old[i]; i++)
- if ((probe && old[i] != probe))
+ for (i = 0; old[i].func; i++)
+ if (probe &&
+ (old[i].func != probe || old[i].data != data))
new[j++] = old[i];
- new[nr_probes - nr_del] = NULL;
+ new[nr_probes - nr_del].func = NULL;
entry->refcount = nr_probes - nr_del;
entry->funcs = new;
}
@@ -315,18 +322,19 @@ static void tracepoint_update_probes(void)
module_update_tracepoints();
}
-static void *tracepoint_add_probe(const char *name, void *probe)
+static struct tracepoint_func *
+tracepoint_add_probe(const char *name, void *probe, void *data)
{
struct tracepoint_entry *entry;
- void *old;
+ struct tracepoint_func *old;
entry = get_tracepoint(name);
if (!entry) {
entry = add_tracepoint(name);
if (IS_ERR(entry))
- return entry;
+ return (struct tracepoint_func *)entry;
}
- old = tracepoint_entry_add_probe(entry, probe);
+ old = tracepoint_entry_add_probe(entry, probe, data);
if (IS_ERR(old) && !entry->refcount)
remove_tracepoint(entry);
return old;
@@ -340,12 +348,12 @@ static void *tracepoint_add_probe(const char *name, void *probe)
* Returns 0 if ok, error value on error.
* The probe address must at least be aligned on the architecture pointer size.
*/
-int tracepoint_probe_register(const char *name, void *probe)
+int tracepoint_probe_register(const char *name, void *probe, void *data)
{
- void *old;
+ struct tracepoint_func *old;
mutex_lock(&tracepoints_mutex);
- old = tracepoint_add_probe(name, probe);
+ old = tracepoint_add_probe(name, probe, data);
mutex_unlock(&tracepoints_mutex);
if (IS_ERR(old))
return PTR_ERR(old);
@@ -356,15 +364,16 @@ int tracepoint_probe_register(const char *name, void *probe)
}
EXPORT_SYMBOL_GPL(tracepoint_probe_register);
-static void *tracepoint_remove_probe(const char *name, void *probe)
+static struct tracepoint_func *
+tracepoint_remove_probe(const char *name, void *probe, void *data)
{
struct tracepoint_entry *entry;
- void *old;
+ struct tracepoint_func *old;
entry = get_tracepoint(name);
if (!entry)
return ERR_PTR(-ENOENT);
- old = tracepoint_entry_remove_probe(entry, probe);
+ old = tracepoint_entry_remove_probe(entry, probe, data);
if (IS_ERR(old))
return old;
if (!entry->refcount)
@@ -382,12 +391,12 @@ static void *tracepoint_remove_probe(const char *name, void *probe)
* itself uses stop_machine(), which insures that every preempt disabled section
* have finished.
*/
-int tracepoint_probe_unregister(const char *name, void *probe)
+int tracepoint_probe_unregister(const char *name, void *probe, void *data)
{
- void *old;
+ struct tracepoint_func *old;
mutex_lock(&tracepoints_mutex);
- old = tracepoint_remove_probe(name, probe);
+ old = tracepoint_remove_probe(name, probe, data);
mutex_unlock(&tracepoints_mutex);
if (IS_ERR(old))
return PTR_ERR(old);
@@ -418,12 +427,13 @@ static void tracepoint_add_old_probes(void *old)
*
* caller must call tracepoint_probe_update_all()
*/
-int tracepoint_probe_register_noupdate(const char *name, void *probe)
+int tracepoint_probe_register_noupdate(const char *name, void *probe,
+ void *data)
{
- void *old;
+ struct tracepoint_func *old;
mutex_lock(&tracepoints_mutex);
- old = tracepoint_add_probe(name, probe);
+ old = tracepoint_add_probe(name, probe, data);
if (IS_ERR(old)) {
mutex_unlock(&tracepoints_mutex);
return PTR_ERR(old);
@@ -441,12 +451,13 @@ EXPORT_SYMBOL_GPL(tracepoint_probe_register_noupdate);
*
* caller must call tracepoint_probe_update_all()
*/
-int tracepoint_probe_unregister_noupdate(const char *name, void *probe)
+int tracepoint_probe_unregister_noupdate(const char *name, void *probe,
+ void *data)
{
- void *old;
+ struct tracepoint_func *old;
mutex_lock(&tracepoints_mutex);
- old = tracepoint_remove_probe(name, probe);
+ old = tracepoint_remove_probe(name, probe, data);
if (IS_ERR(old)) {
mutex_unlock(&tracepoints_mutex);
return PTR_ERR(old);
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index cf208d8..ad41529 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -172,12 +172,12 @@ out:
return;
}
-static void trace_kfree_skb_hit(struct sk_buff *skb, void *location)
+static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location)
{
trace_drop_common(skb, location);
}
-static void trace_napi_poll_hit(struct napi_struct *napi)
+static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi)
{
struct dm_hw_stat_delta *new_stat;
@@ -225,12 +225,12 @@ static int set_all_monitor_traces(int state)
switch (state) {
case TRACE_ON:
- rc |= register_trace_kfree_skb(trace_kfree_skb_hit);
- rc |= register_trace_napi_poll(trace_napi_poll_hit);
+ rc |= register_trace_kfree_skb(trace_kfree_skb_hit, NULL);
+ rc |= register_trace_napi_poll(trace_napi_poll_hit, NULL);
break;
case TRACE_OFF:
- rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit);
- rc |= unregister_trace_napi_poll(trace_napi_poll_hit);
+ rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit, NULL);
+ rc |= unregister_trace_napi_poll(trace_napi_poll_hit, NULL);
tracepoint_synchronize_unregister();
diff --git a/samples/tracepoints/tp-samples-trace.h b/samples/tracepoints/tp-samples-trace.h
index dffdc49..4d46be9 100644
--- a/samples/tracepoints/tp-samples-trace.h
+++ b/samples/tracepoints/tp-samples-trace.h
@@ -7,7 +7,5 @@
DECLARE_TRACE(subsys_event,
TP_PROTO(struct inode *inode, struct file *file),
TP_ARGS(inode, file));
-DECLARE_TRACE(subsys_eventb,
- TP_PROTO(void),
- TP_ARGS());
+DECLARE_TRACE_NOARGS(subsys_eventb);
#endif
diff --git a/samples/tracepoints/tracepoint-probe-sample.c b/samples/tracepoints/tracepoint-probe-sample.c
index 9e60eb6..744c0b9 100644
--- a/samples/tracepoints/tracepoint-probe-sample.c
+++ b/samples/tracepoints/tracepoint-probe-sample.c
@@ -13,7 +13,8 @@
* Here the caller only guarantees locking for struct file and struct inode.
* Locking must therefore be done in the probe to use the dentry.
*/
-static void probe_subsys_event(struct inode *inode, struct file *file)
+static void probe_subsys_event(void *ignore,
+ struct inode *inode, struct file *file)
{
path_get(&file->f_path);
dget(file->f_path.dentry);
@@ -23,7 +24,7 @@ static void probe_subsys_event(struct inode *inode, struct file *file)
path_put(&file->f_path);
}
-static void probe_subsys_eventb(void)
+static void probe_subsys_eventb(void *ignore)
{
printk(KERN_INFO "Event B is encountered\n");
}
@@ -32,9 +33,9 @@ static int __init tp_sample_trace_init(void)
{
int ret;
- ret = register_trace_subsys_event(probe_subsys_event);
+ ret = register_trace_subsys_event(probe_subsys_event, NULL);
WARN_ON(ret);
- ret = register_trace_subsys_eventb(probe_subsys_eventb);
+ ret = register_trace_subsys_eventb(probe_subsys_eventb, NULL);
WARN_ON(ret);
return 0;
@@ -44,8 +45,8 @@ module_init(tp_sample_trace_init);
static void __exit tp_sample_trace_exit(void)
{
- unregister_trace_subsys_eventb(probe_subsys_eventb);
- unregister_trace_subsys_event(probe_subsys_event);
+ unregister_trace_subsys_eventb(probe_subsys_eventb, NULL);
+ unregister_trace_subsys_event(probe_subsys_event, NULL);
tracepoint_synchronize_unregister();
}
diff --git a/samples/tracepoints/tracepoint-probe-sample2.c b/samples/tracepoints/tracepoint-probe-sample2.c
index be2a960..9fcf990 100644
--- a/samples/tracepoints/tracepoint-probe-sample2.c
+++ b/samples/tracepoints/tracepoint-probe-sample2.c
@@ -12,7 +12,8 @@
* Here the caller only guarantees locking for struct file and struct inode.
* Locking must therefore be done in the probe to use the dentry.
*/
-static void probe_subsys_event(struct inode *inode, struct file *file)
+static void probe_subsys_event(void *ignore,
+ struct inode *inode, struct file *file)
{
printk(KERN_INFO "Event is encountered with inode number %lu\n",
inode->i_ino);
@@ -22,7 +23,7 @@ static int __init tp_sample_trace_init(void)
{
int ret;
- ret = register_trace_subsys_event(probe_subsys_event);
+ ret = register_trace_subsys_event(probe_subsys_event, NULL);
WARN_ON(ret);
return 0;
@@ -32,7 +33,7 @@ module_init(tp_sample_trace_init);
static void __exit tp_sample_trace_exit(void)
{
- unregister_trace_subsys_event(probe_subsys_event);
+ unregister_trace_subsys_event(probe_subsys_event, NULL);
tracepoint_synchronize_unregister();
}
--
1.7.0
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH 04/13 v3] tracing: Remove per event trace registering
2010-05-14 19:22 [PATCH 00/13 v3] [GIT PULL] tracing: shrinking trace events and updates Steven Rostedt
` (2 preceding siblings ...)
2010-05-14 19:22 ` [PATCH 03/13 v3] tracing: Let tracepoints have data passed to tracepoint callbacks Steven Rostedt
@ 2010-05-14 19:22 ` Steven Rostedt
2010-05-14 19:22 ` [PATCH 05/13 v3] tracing: Move fields from event to class structure Steven Rostedt
` (8 subsequent siblings)
12 siblings, 0 replies; 19+ messages in thread
From: Steven Rostedt @ 2010-05-14 19:22 UTC (permalink / raw)
To: linux-kernel
Cc: Ingo Molnar, Andrew Morton, Frederic Weisbecker,
Mathieu Desnoyers, Masami Hiramatsu, Mathieu Desnoyers
[-- Attachment #1: 0004-tracing-Remove-per-event-trace-registering.patch --]
[-- Type: text/plain, Size: 23060 bytes --]
From: Steven Rostedt <srostedt@redhat.com>
This patch removes the register functions of TRACE_EVENT() to enable
and disable tracepoints. The registering of a event is now down
directly in the trace_events.c file. The tracepoint_probe_register()
is now called directly.
The prototypes are no longer type checked, but this should not be
an issue since the tracepoints are created automatically by the
macros. If a prototype is incorrect in the TRACE_EVENT() macro, then
other macros will catch it.
The trace_event_class structure now holds the probes to be called
by the callbacks. This removes needing to have each event have
a separate pointer for the probe.
To handle kprobes and syscalls, since they register probes in a
different manner, a "reg" field is added to the ftrace_event_class
structure. If the "reg" field is assigned, then it will be called for
enabling and disabling of the probe for either ftrace or perf. To let
the reg function know what is happening, a new enum (trace_reg) is
created that has the type of control that is needed.
With this new rework, the 82 kernel events and 618 syscall events
has their footprint dramatically lowered:
text data bss dec hex filename
4913961 1088356 861512 6863829 68bbd5 vmlinux.orig
4914025 1088868 861512 6864405 68be15 vmlinux.class
4918492 1084612 861512 6864616 68bee8 vmlinux.tracepoint
4900252 1057412 861512 6819176 680d68 vmlinux.regs
The size went from 6863829 to 6819176, that's a total of 44K
in savings. With tracepoints being continuously added, this is
critical that the footprint becomes minimal.
v5: Added #ifdef CONFIG_PERF_EVENTS around a reference to perf
specific structure in trace_events.c.
v4: Fixed trace self tests to check probe because regfunc no longer
exists.
v3: Updated to handle void *data in beginning of probe parameters.
Also added the tracepoint: check_trace_callback_type_##call().
v2: Changed the callback probes to pass void * and typecast the
value within the function.
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Masami Hiramatsu <mhiramat@redhat.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
include/linux/ftrace_event.h | 19 +++++-
include/linux/syscalls.h | 29 +-------
include/trace/ftrace.h | 133 +++++++++++----------------------------
kernel/trace/trace_event_perf.c | 15 ++++-
kernel/trace/trace_events.c | 32 +++++++---
kernel/trace/trace_kprobe.c | 34 +++++++---
kernel/trace/trace_syscalls.c | 56 ++++++++++++++++-
7 files changed, 171 insertions(+), 147 deletions(-)
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 496eea8..e665ed3 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -113,8 +113,23 @@ void tracing_record_cmdline(struct task_struct *tsk);
struct event_filter;
+enum trace_reg {
+ TRACE_REG_REGISTER,
+ TRACE_REG_UNREGISTER,
+ TRACE_REG_PERF_REGISTER,
+ TRACE_REG_PERF_UNREGISTER,
+};
+
+struct ftrace_event_call;
+
struct ftrace_event_class {
char *system;
+ void *probe;
+#ifdef CONFIG_PERF_EVENTS
+ void *perf_probe;
+#endif
+ int (*reg)(struct ftrace_event_call *event,
+ enum trace_reg type);
};
struct ftrace_event_call {
@@ -124,8 +139,6 @@ struct ftrace_event_call {
struct dentry *dir;
struct trace_event *event;
int enabled;
- int (*regfunc)(struct ftrace_event_call *);
- void (*unregfunc)(struct ftrace_event_call *);
int id;
const char *print_fmt;
int (*raw_init)(struct ftrace_event_call *);
@@ -137,8 +150,6 @@ struct ftrace_event_call {
void *data;
int perf_refcount;
- int (*perf_event_enable)(struct ftrace_event_call *);
- void (*perf_event_disable)(struct ftrace_event_call *);
};
#define PERF_MAX_TRACE_SIZE 2048
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index ac5791d..e3348c4 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -103,22 +103,6 @@ struct perf_event_attr;
#define __SC_TEST5(t5, a5, ...) __SC_TEST(t5); __SC_TEST4(__VA_ARGS__)
#define __SC_TEST6(t6, a6, ...) __SC_TEST(t6); __SC_TEST5(__VA_ARGS__)
-#ifdef CONFIG_PERF_EVENTS
-
-#define TRACE_SYS_ENTER_PERF_INIT(sname) \
- .perf_event_enable = perf_sysenter_enable, \
- .perf_event_disable = perf_sysenter_disable,
-
-#define TRACE_SYS_EXIT_PERF_INIT(sname) \
- .perf_event_enable = perf_sysexit_enable, \
- .perf_event_disable = perf_sysexit_disable,
-#else
-#define TRACE_SYS_ENTER_PERF(sname)
-#define TRACE_SYS_ENTER_PERF_INIT(sname)
-#define TRACE_SYS_EXIT_PERF(sname)
-#define TRACE_SYS_EXIT_PERF_INIT(sname)
-#endif /* CONFIG_PERF_EVENTS */
-
#ifdef CONFIG_FTRACE_SYSCALLS
#define __SC_STR_ADECL1(t, a) #a
#define __SC_STR_ADECL2(t, a, ...) #a, __SC_STR_ADECL1(__VA_ARGS__)
@@ -134,7 +118,8 @@ struct perf_event_attr;
#define __SC_STR_TDECL5(t, a, ...) #t, __SC_STR_TDECL4(__VA_ARGS__)
#define __SC_STR_TDECL6(t, a, ...) #t, __SC_STR_TDECL5(__VA_ARGS__)
-extern struct ftrace_event_class event_class_syscalls;
+extern struct ftrace_event_class event_class_syscall_enter;
+extern struct ftrace_event_class event_class_syscall_exit;
#define SYSCALL_TRACE_ENTER_EVENT(sname) \
static const struct syscall_metadata __syscall_meta_##sname; \
@@ -148,14 +133,11 @@ extern struct ftrace_event_class event_class_syscalls;
__attribute__((section("_ftrace_events"))) \
event_enter_##sname = { \
.name = "sys_enter"#sname, \
- .class = &event_class_syscalls, \
+ .class = &event_class_syscall_enter, \
.event = &enter_syscall_print_##sname, \
.raw_init = init_syscall_trace, \
.define_fields = syscall_enter_define_fields, \
- .regfunc = reg_event_syscall_enter, \
- .unregfunc = unreg_event_syscall_enter, \
.data = (void *)&__syscall_meta_##sname,\
- TRACE_SYS_ENTER_PERF_INIT(sname) \
}
#define SYSCALL_TRACE_EXIT_EVENT(sname) \
@@ -170,14 +152,11 @@ extern struct ftrace_event_class event_class_syscalls;
__attribute__((section("_ftrace_events"))) \
event_exit_##sname = { \
.name = "sys_exit"#sname, \
- .class = &event_class_syscalls, \
+ .class = &event_class_syscall_exit, \
.event = &exit_syscall_print_##sname, \
.raw_init = init_syscall_trace, \
.define_fields = syscall_exit_define_fields, \
- .regfunc = reg_event_syscall_exit, \
- .unregfunc = unreg_event_syscall_exit, \
.data = (void *)&__syscall_meta_##sname,\
- TRACE_SYS_EXIT_PERF_INIT(sname) \
}
#define SYSCALL_METADATA(sname, nb) \
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index ba28b64..26d1324 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -381,53 +381,6 @@ static inline notrace int ftrace_get_offsets_##call( \
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
-#ifdef CONFIG_PERF_EVENTS
-
-/*
- * Generate the functions needed for tracepoint perf_event support.
- *
- * NOTE: The insertion profile callback (ftrace_profile_<call>) is defined later
- *
- * static int ftrace_profile_enable_<call>(void)
- * {
- * return register_trace_<call>(ftrace_profile_<call>);
- * }
- *
- * static void ftrace_profile_disable_<call>(void)
- * {
- * unregister_trace_<call>(ftrace_profile_<call>);
- * }
- *
- */
-
-#undef DECLARE_EVENT_CLASS
-#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)
-
-#undef DEFINE_EVENT
-#define DEFINE_EVENT(template, name, proto, args) \
- \
-static void perf_trace_##name(void *, proto); \
- \
-static notrace int \
-perf_trace_enable_##name(struct ftrace_event_call *unused) \
-{ \
- return register_trace_##name(perf_trace_##name, NULL); \
-} \
- \
-static notrace void \
-perf_trace_disable_##name(struct ftrace_event_call *unused) \
-{ \
- unregister_trace_##name(perf_trace_##name, NULL); \
-}
-
-#undef DEFINE_EVENT_PRINT
-#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
- DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
-
-#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
-
-#endif /* CONFIG_PERF_EVENTS */
-
/*
* Stage 4 of the trace events.
*
@@ -437,8 +390,9 @@ perf_trace_disable_##name(struct ftrace_event_call *unused) \
*
* static struct ftrace_event_call event_<call>;
*
- * static void ftrace_raw_event_<call>(proto)
+ * static void ftrace_raw_event_<call>(void *__data, proto)
* {
+ * struct ftrace_event_call *event_call = __data;
* struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
* struct ring_buffer_event *event;
* struct ftrace_raw_<call> *entry; <-- defined in stage 1
@@ -468,16 +422,6 @@ perf_trace_disable_##name(struct ftrace_event_call *unused) \
* event, irq_flags, pc);
* }
*
- * static int ftrace_raw_reg_event_<call>(struct ftrace_event_call *unused)
- * {
- * return register_trace_<call>(ftrace_raw_event_<call>);
- * }
- *
- * static void ftrace_unreg_event_<call>(struct ftrace_event_call *unused)
- * {
- * unregister_trace_<call>(ftrace_raw_event_<call>);
- * }
- *
* static struct trace_event ftrace_event_type_<call> = {
* .trace = ftrace_raw_output_<call>, <-- stage 2
* };
@@ -504,11 +448,15 @@ perf_trace_disable_##name(struct ftrace_event_call *unused) \
#ifdef CONFIG_PERF_EVENTS
+#define _TRACE_PERF_PROTO(call, proto) \
+ static notrace void \
+ perf_trace_##call(void *__data, proto);
+
#define _TRACE_PERF_INIT(call) \
- .perf_event_enable = perf_trace_enable_##call, \
- .perf_event_disable = perf_trace_disable_##call,
+ .perf_probe = perf_trace_##call,
#else
+#define _TRACE_PERF_PROTO(call, proto)
#define _TRACE_PERF_INIT(call)
#endif /* CONFIG_PERF_EVENTS */
@@ -542,9 +490,9 @@ perf_trace_disable_##name(struct ftrace_event_call *unused) \
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
\
static notrace void \
-ftrace_raw_event_id_##call(struct ftrace_event_call *event_call, \
- proto) \
+ftrace_raw_event_##call(void *__data, proto) \
{ \
+ struct ftrace_event_call *event_call = __data; \
struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
struct ring_buffer_event *event; \
struct ftrace_raw_##call *entry; \
@@ -574,30 +522,23 @@ ftrace_raw_event_id_##call(struct ftrace_event_call *event_call, \
trace_nowake_buffer_unlock_commit(buffer, \
event, irq_flags, pc); \
}
+/*
+ * The ftrace_test_probe is compiled out, it is only here as a build time check
+ * to make sure that if the tracepoint handling changes, the ftrace probe will
+ * fail to compile unless it too is updated.
+ */
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, call, proto, args) \
\
-static notrace void ftrace_raw_event_##call(void *__ignore, proto) \
-{ \
- ftrace_raw_event_id_##template(&event_##call, args); \
-} \
- \
-static notrace int \
-ftrace_raw_reg_event_##call(struct ftrace_event_call *unused) \
-{ \
- return register_trace_##call(ftrace_raw_event_##call, NULL); \
-} \
- \
-static notrace void \
-ftrace_raw_unreg_event_##call(struct ftrace_event_call *unused) \
-{ \
- unregister_trace_##call(ftrace_raw_event_##call, NULL); \
-} \
- \
static struct trace_event ftrace_event_type_##call = { \
.trace = ftrace_raw_output_##call, \
-};
+}; \
+ \
+static inline void ftrace_test_probe_##call(void) \
+{ \
+ check_trace_callback_type_##call(ftrace_raw_event_##template); \
+}
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
@@ -618,9 +559,12 @@ static struct trace_event ftrace_event_type_##call = { \
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
+_TRACE_PERF_PROTO(call, PARAMS(proto)); \
static const char print_fmt_##call[] = print; \
static struct ftrace_event_class __used event_class_##call = { \
- .system = __stringify(TRACE_SYSTEM) \
+ .system = __stringify(TRACE_SYSTEM), \
+ .probe = ftrace_raw_event_##call, \
+ _TRACE_PERF_INIT(call) \
};
#undef DEFINE_EVENT
@@ -633,11 +577,8 @@ __attribute__((section("_ftrace_events"))) event_##call = { \
.class = &event_class_##template, \
.event = &ftrace_event_type_##call, \
.raw_init = trace_event_raw_init, \
- .regfunc = ftrace_raw_reg_event_##call, \
- .unregfunc = ftrace_raw_unreg_event_##call, \
.print_fmt = print_fmt_##template, \
.define_fields = ftrace_define_fields_##template, \
- _TRACE_PERF_INIT(call) \
};
#undef DEFINE_EVENT_PRINT
@@ -652,11 +593,8 @@ __attribute__((section("_ftrace_events"))) event_##call = { \
.class = &event_class_##template, \
.event = &ftrace_event_type_##call, \
.raw_init = trace_event_raw_init, \
- .regfunc = ftrace_raw_reg_event_##call, \
- .unregfunc = ftrace_raw_unreg_event_##call, \
.print_fmt = print_fmt_##call, \
.define_fields = ftrace_define_fields_##template, \
- _TRACE_PERF_INIT(call) \
}
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
@@ -756,9 +694,9 @@ __attribute__((section("_ftrace_events"))) event_##call = { \
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
static notrace void \
-perf_trace_templ_##call(struct ftrace_event_call *event_call, \
- proto) \
+perf_trace_##call(void *__data, proto) \
{ \
+ struct ftrace_event_call *event_call = __data; \
struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
struct ftrace_raw_##call *entry; \
u64 __addr = 0, __count = 1; \
@@ -791,15 +729,20 @@ perf_trace_templ_##call(struct ftrace_event_call *event_call, \
__count, irq_flags, __regs); \
}
+/*
+ * This part is compiled out, it is only here as a build time check
+ * to make sure that if the tracepoint handling changes, the
+ * perf probe will fail to compile unless it too is updated.
+ */
#undef DEFINE_EVENT
-#define DEFINE_EVENT(template, call, proto, args) \
-static notrace void perf_trace_##call(void *__ignore, proto) \
-{ \
- struct ftrace_event_call *event_call = &event_##call; \
- \
- perf_trace_templ_##template(event_call, args); \
+#define DEFINE_EVENT(template, call, proto, args) \
+static inline void perf_test_probe_##call(void) \
+{ \
+ check_trace_callback_type_##call(perf_trace_##template); \
+ \
}
+
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 0565bb4..196fe9d 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -49,7 +49,12 @@ static int perf_trace_event_enable(struct ftrace_event_call *event)
rcu_assign_pointer(perf_trace_buf_nmi, buf);
}
- ret = event->perf_event_enable(event);
+ if (event->class->reg)
+ ret = event->class->reg(event, TRACE_REG_PERF_REGISTER);
+ else
+ ret = tracepoint_probe_register(event->name,
+ event->class->perf_probe,
+ event);
if (!ret) {
total_ref_count++;
return 0;
@@ -75,7 +80,8 @@ int perf_trace_enable(int event_id)
mutex_lock(&event_mutex);
list_for_each_entry(event, &ftrace_events, list) {
- if (event->id == event_id && event->perf_event_enable &&
+ if (event->id == event_id &&
+ event->class && event->class->perf_probe &&
try_module_get(event->mod)) {
ret = perf_trace_event_enable(event);
break;
@@ -93,7 +99,10 @@ static void perf_trace_event_disable(struct ftrace_event_call *event)
if (--event->perf_refcount > 0)
return;
- event->perf_event_disable(event);
+ if (event->class->reg)
+ event->class->reg(event, TRACE_REG_PERF_UNREGISTER);
+ else
+ tracepoint_probe_unregister(event->name, event->class->perf_probe, event);
if (!--total_ref_count) {
buf = perf_trace_buf;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 2f54b48..19d1eb0 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -127,13 +127,23 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call,
if (call->enabled) {
call->enabled = 0;
tracing_stop_cmdline_record();
- call->unregfunc(call);
+ if (call->class->reg)
+ call->class->reg(call, TRACE_REG_UNREGISTER);
+ else
+ tracepoint_probe_unregister(call->name,
+ call->class->probe,
+ call);
}
break;
case 1:
if (!call->enabled) {
tracing_start_cmdline_record();
- ret = call->regfunc(call);
+ if (call->class->reg)
+ ret = call->class->reg(call, TRACE_REG_REGISTER);
+ else
+ ret = tracepoint_probe_register(call->name,
+ call->class->probe,
+ call);
if (ret) {
tracing_stop_cmdline_record();
pr_info("event trace: Could not enable event "
@@ -171,7 +181,8 @@ static int __ftrace_set_clr_event(const char *match, const char *sub,
mutex_lock(&event_mutex);
list_for_each_entry(call, &ftrace_events, list) {
- if (!call->name || !call->regfunc)
+ if (!call->name || !call->class ||
+ (!call->class->probe && !call->class->reg))
continue;
if (match &&
@@ -297,7 +308,7 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
* The ftrace subsystem is for showing formats only.
* They can not be enabled or disabled via the event files.
*/
- if (call->regfunc)
+ if (call->class && (call->class->probe || call->class->reg))
return call;
}
@@ -450,7 +461,8 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
mutex_lock(&event_mutex);
list_for_each_entry(call, &ftrace_events, list) {
- if (!call->name || !call->regfunc)
+ if (!call->name || !call->class ||
+ (!call->class->probe && !call->class->reg))
continue;
if (system && strcmp(call->class->system, system) != 0)
@@ -935,13 +947,15 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
return -1;
}
- if (call->regfunc)
+ if (call->class->probe || call->class->reg)
trace_create_file("enable", 0644, call->dir, call,
enable);
- if (call->id && call->perf_event_enable)
+#ifdef CONFIG_PERF_EVENTS
+ if (call->id && (call->class->perf_probe || call->class->reg))
trace_create_file("id", 0444, call->dir, call,
id);
+#endif
if (call->define_fields) {
ret = trace_define_common_fields(call);
@@ -1388,8 +1402,8 @@ static __init void event_trace_self_tests(void)
list_for_each_entry(call, &ftrace_events, list) {
- /* Only test those that have a regfunc */
- if (!call->regfunc)
+ /* Only test those that have a probe */
+ if (!call->class || !call->class->probe)
continue;
/*
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index eda220b..f8af21a 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -202,6 +202,7 @@ struct trace_probe {
unsigned long nhit;
unsigned int flags; /* For TP_FLAG_* */
const char *symbol; /* symbol name */
+ struct ftrace_event_class class;
struct ftrace_event_call call;
struct trace_event event;
unsigned int nr_args;
@@ -323,6 +324,7 @@ static struct trace_probe *alloc_trace_probe(const char *group,
goto error;
}
+ tp->call.class = &tp->class;
tp->call.name = kstrdup(event, GFP_KERNEL);
if (!tp->call.name)
goto error;
@@ -332,8 +334,8 @@ static struct trace_probe *alloc_trace_probe(const char *group,
goto error;
}
- tp->call.class->system = kstrdup(group, GFP_KERNEL);
- if (!tp->call.class->system)
+ tp->class.system = kstrdup(group, GFP_KERNEL);
+ if (!tp->class.system)
goto error;
INIT_LIST_HEAD(&tp->list);
@@ -1302,6 +1304,26 @@ static void probe_perf_disable(struct ftrace_event_call *call)
}
#endif /* CONFIG_PERF_EVENTS */
+static __kprobes
+int kprobe_register(struct ftrace_event_call *event, enum trace_reg type)
+{
+ switch (type) {
+ case TRACE_REG_REGISTER:
+ return probe_event_enable(event);
+ case TRACE_REG_UNREGISTER:
+ probe_event_disable(event);
+ return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+ case TRACE_REG_PERF_REGISTER:
+ return probe_perf_enable(event);
+ case TRACE_REG_PERF_UNREGISTER:
+ probe_perf_disable(event);
+ return 0;
+#endif
+ }
+ return 0;
+}
static __kprobes
int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs)
@@ -1355,13 +1377,7 @@ static int register_probe_event(struct trace_probe *tp)
return -ENODEV;
}
call->enabled = 0;
- call->regfunc = probe_event_enable;
- call->unregfunc = probe_event_disable;
-
-#ifdef CONFIG_PERF_EVENTS
- call->perf_event_enable = probe_perf_enable;
- call->perf_event_disable = probe_perf_disable;
-#endif
+ call->class->reg = kprobe_register;
call->data = tp;
ret = trace_add_event_call(call);
if (ret) {
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index b8d30e7..a21d366 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -15,8 +15,19 @@ static int sys_refcount_exit;
static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
-struct ftrace_event_class event_class_syscalls = {
- .system = "syscalls"
+static int syscall_enter_register(struct ftrace_event_call *event,
+ enum trace_reg type);
+static int syscall_exit_register(struct ftrace_event_call *event,
+ enum trace_reg type);
+
+struct ftrace_event_class event_class_syscall_enter = {
+ .system = "syscalls",
+ .reg = syscall_enter_register
+};
+
+struct ftrace_event_class event_class_syscall_exit = {
+ .system = "syscalls",
+ .reg = syscall_exit_register
};
extern unsigned long __start_syscalls_metadata[];
@@ -587,3 +598,44 @@ void perf_sysexit_disable(struct ftrace_event_call *call)
#endif /* CONFIG_PERF_EVENTS */
+static int syscall_enter_register(struct ftrace_event_call *event,
+ enum trace_reg type)
+{
+ switch (type) {
+ case TRACE_REG_REGISTER:
+ return reg_event_syscall_enter(event);
+ case TRACE_REG_UNREGISTER:
+ unreg_event_syscall_enter(event);
+ return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+ case TRACE_REG_PERF_REGISTER:
+ return perf_sysenter_enable(event);
+ case TRACE_REG_PERF_UNREGISTER:
+ perf_sysenter_disable(event);
+ return 0;
+#endif
+ }
+ return 0;
+}
+
+static int syscall_exit_register(struct ftrace_event_call *event,
+ enum trace_reg type)
+{
+ switch (type) {
+ case TRACE_REG_REGISTER:
+ return reg_event_syscall_exit(event);
+ case TRACE_REG_UNREGISTER:
+ unreg_event_syscall_exit(event);
+ return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+ case TRACE_REG_PERF_REGISTER:
+ return perf_sysexit_enable(event);
+ case TRACE_REG_PERF_UNREGISTER:
+ perf_sysexit_disable(event);
+ return 0;
+#endif
+ }
+ return 0;
+}
--
1.7.0
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH 05/13 v3] tracing: Move fields from event to class structure
2010-05-14 19:22 [PATCH 00/13 v3] [GIT PULL] tracing: shrinking trace events and updates Steven Rostedt
` (3 preceding siblings ...)
2010-05-14 19:22 ` [PATCH 04/13 v3] tracing: Remove per event trace registering Steven Rostedt
@ 2010-05-14 19:22 ` Steven Rostedt
2010-05-18 4:51 ` Li Zefan
2010-05-14 19:22 ` [PATCH 06/13 v3] tracing: Move raw_init from events to class Steven Rostedt
` (7 subsequent siblings)
12 siblings, 1 reply; 19+ messages in thread
From: Steven Rostedt @ 2010-05-14 19:22 UTC (permalink / raw)
To: linux-kernel
Cc: Ingo Molnar, Andrew Morton, Frederic Weisbecker,
Mathieu Desnoyers, Masami Hiramatsu, Mathieu Desnoyers,
Tom Zanussi, Peter Zijlstra
[-- Attachment #1: 0005-tracing-Move-fields-from-event-to-class-structure.patch --]
[-- Type: text/plain, Size: 19558 bytes --]
From: Steven Rostedt <srostedt@redhat.com>
Move the defined fields from the event to the class structure.
Since the fields of the event are defined by the class they belong
to, it makes sense to have the class hold the information instead
of the individual events. The events of the same class would just
hold duplicate information.
After this change the size of the kernel dropped another 3K:
text data bss dec hex filename
4913961 1088356 861512 6863829 68bbd5 vmlinux.orig
4900252 1057412 861512 6819176 680d68 vmlinux.regs
4900375 1053380 861512 6815267 67fe23 vmlinux.fields
Although the text increased, this was mainly due to the C files
having to adapt to the change. This is a constant increase, where
new tracepoints will not increase the Text. But the big drop is
in the data size (as well as needed allocations to hold the fields).
This will give even more savings as more tracepoints are created.
Note, if just TRACE_EVENT()s are used and not DECLARE_EVENT_CLASS()
with several DEFINE_EVENT()s, then the savings will be lost. But
we are pushing developers to consolidate events with DEFINE_EVENT()
so this should not be an issue.
The kprobes define a unique class to every new event, but are dynamic
so it should not be a issue.
The syscalls however have a single class but the fields for the individual
events are different. The syscalls use a metadata to define the
fields. I moved the fields list from the event to the metadata and
added a "get_fields()" function to the class. This function is used
to find the fields. For normal events and kprobes, get_fields() just
returns a pointer to the fields list_head in the class. For syscall
events, it returns the fields list_head in the metadata for the event.
v2: Fixed the syscall fields. The syscall metadata needs a list
of fields for both enter and exit.
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
include/linux/ftrace_event.h | 5 ++-
include/linux/syscalls.h | 14 ++++++----
include/trace/ftrace.h | 11 ++++---
include/trace/syscall.h | 4 +-
kernel/trace/trace.h | 3 ++
kernel/trace/trace_events.c | 48 +++++++++++++++++++++++++++---------
kernel/trace/trace_events_filter.c | 10 ++++---
kernel/trace/trace_export.c | 14 +++++-----
kernel/trace/trace_kprobe.c | 8 +++---
kernel/trace/trace_syscalls.c | 31 ++++++++++++++++++++---
10 files changed, 102 insertions(+), 46 deletions(-)
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index e665ed3..479c3c1 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -130,6 +130,9 @@ struct ftrace_event_class {
#endif
int (*reg)(struct ftrace_event_call *event,
enum trace_reg type);
+ int (*define_fields)(struct ftrace_event_call *);
+ struct list_head *(*get_fields)(struct ftrace_event_call *);
+ struct list_head fields;
};
struct ftrace_event_call {
@@ -142,8 +145,6 @@ struct ftrace_event_call {
int id;
const char *print_fmt;
int (*raw_init)(struct ftrace_event_call *);
- int (*define_fields)(struct ftrace_event_call *);
- struct list_head fields;
int filter_active;
struct event_filter *filter;
void *mod;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index e3348c4..fd0f1f2 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -122,7 +122,7 @@ extern struct ftrace_event_class event_class_syscall_enter;
extern struct ftrace_event_class event_class_syscall_exit;
#define SYSCALL_TRACE_ENTER_EVENT(sname) \
- static const struct syscall_metadata __syscall_meta_##sname; \
+ static struct syscall_metadata __syscall_meta_##sname; \
static struct ftrace_event_call \
__attribute__((__aligned__(4))) event_enter_##sname; \
static struct trace_event enter_syscall_print_##sname = { \
@@ -136,12 +136,11 @@ extern struct ftrace_event_class event_class_syscall_exit;
.class = &event_class_syscall_enter, \
.event = &enter_syscall_print_##sname, \
.raw_init = init_syscall_trace, \
- .define_fields = syscall_enter_define_fields, \
.data = (void *)&__syscall_meta_##sname,\
}
#define SYSCALL_TRACE_EXIT_EVENT(sname) \
- static const struct syscall_metadata __syscall_meta_##sname; \
+ static struct syscall_metadata __syscall_meta_##sname; \
static struct ftrace_event_call \
__attribute__((__aligned__(4))) event_exit_##sname; \
static struct trace_event exit_syscall_print_##sname = { \
@@ -155,14 +154,13 @@ extern struct ftrace_event_class event_class_syscall_exit;
.class = &event_class_syscall_exit, \
.event = &exit_syscall_print_##sname, \
.raw_init = init_syscall_trace, \
- .define_fields = syscall_exit_define_fields, \
.data = (void *)&__syscall_meta_##sname,\
}
#define SYSCALL_METADATA(sname, nb) \
SYSCALL_TRACE_ENTER_EVENT(sname); \
SYSCALL_TRACE_EXIT_EVENT(sname); \
- static const struct syscall_metadata __used \
+ static struct syscall_metadata __used \
__attribute__((__aligned__(4))) \
__attribute__((section("__syscalls_metadata"))) \
__syscall_meta_##sname = { \
@@ -172,12 +170,14 @@ extern struct ftrace_event_class event_class_syscall_exit;
.args = args_##sname, \
.enter_event = &event_enter_##sname, \
.exit_event = &event_exit_##sname, \
+ .enter_fields = LIST_HEAD_INIT(__syscall_meta_##sname.enter_fields), \
+ .exit_fields = LIST_HEAD_INIT(__syscall_meta_##sname.exit_fields), \
};
#define SYSCALL_DEFINE0(sname) \
SYSCALL_TRACE_ENTER_EVENT(_##sname); \
SYSCALL_TRACE_EXIT_EVENT(_##sname); \
- static const struct syscall_metadata __used \
+ static struct syscall_metadata __used \
__attribute__((__aligned__(4))) \
__attribute__((section("__syscalls_metadata"))) \
__syscall_meta__##sname = { \
@@ -185,6 +185,8 @@ extern struct ftrace_event_class event_class_syscall_exit;
.nb_args = 0, \
.enter_event = &event_enter__##sname, \
.exit_event = &event_exit__##sname, \
+ .enter_fields = LIST_HEAD_INIT(__syscall_meta__##sname.enter_fields), \
+ .exit_fields = LIST_HEAD_INIT(__syscall_meta__##sname.exit_fields), \
}; \
asmlinkage long sys_##sname(void)
#else
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 26d1324..c7e3bcd 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -430,6 +430,9 @@ static inline notrace int ftrace_get_offsets_##call( \
*
* static struct ftrace_event_class __used event_class_<template> = {
* .system = "<system>",
+ * .define_fields = ftrace_define_fields_<call>,
+ * .fields = LIST_HEAD_INIT(event_class_##call.fields), \
+ * .probe = ftrace_raw_event_##call, \
* };
*
* static struct ftrace_event_call __used
@@ -438,10 +441,8 @@ static inline notrace int ftrace_get_offsets_##call( \
* .name = "<call>",
* .class = event_class_<template>,
* .raw_init = trace_event_raw_init,
- * .regfunc = ftrace_raw_reg_event_<call>,
- * .unregfunc = ftrace_raw_unreg_event_<call>,
+ * .event = &ftrace_event_type_<call>,
* .print_fmt = print_fmt_<call>,
- * .define_fields = ftrace_define_fields_<call>,
* };
*
*/
@@ -563,6 +564,8 @@ _TRACE_PERF_PROTO(call, PARAMS(proto)); \
static const char print_fmt_##call[] = print; \
static struct ftrace_event_class __used event_class_##call = { \
.system = __stringify(TRACE_SYSTEM), \
+ .define_fields = ftrace_define_fields_##call, \
+ .fields = LIST_HEAD_INIT(event_class_##call.fields),\
.probe = ftrace_raw_event_##call, \
_TRACE_PERF_INIT(call) \
};
@@ -578,7 +581,6 @@ __attribute__((section("_ftrace_events"))) event_##call = { \
.event = &ftrace_event_type_##call, \
.raw_init = trace_event_raw_init, \
.print_fmt = print_fmt_##template, \
- .define_fields = ftrace_define_fields_##template, \
};
#undef DEFINE_EVENT_PRINT
@@ -594,7 +596,6 @@ __attribute__((section("_ftrace_events"))) event_##call = { \
.event = &ftrace_event_type_##call, \
.raw_init = trace_event_raw_init, \
.print_fmt = print_fmt_##call, \
- .define_fields = ftrace_define_fields_##template, \
}
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index e5e5f48..3964774 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -25,6 +25,8 @@ struct syscall_metadata {
int nb_args;
const char **types;
const char **args;
+ struct list_head enter_fields;
+ struct list_head exit_fields;
struct ftrace_event_call *enter_event;
struct ftrace_event_call *exit_event;
@@ -34,8 +36,6 @@ struct syscall_metadata {
extern unsigned long arch_syscall_addr(int nr);
extern int init_syscall_trace(struct ftrace_event_call *call);
-extern int syscall_enter_define_fields(struct ftrace_event_call *call);
-extern int syscall_exit_define_fields(struct ftrace_event_call *call);
extern int reg_event_syscall_enter(struct ftrace_event_call *call);
extern void unreg_event_syscall_enter(struct ftrace_event_call *call);
extern int reg_event_syscall_exit(struct ftrace_event_call *call);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 911e986..c88c563 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -794,6 +794,9 @@ extern void print_subsystem_event_filter(struct event_subsystem *system,
struct trace_seq *s);
extern int filter_assign_type(const char *type);
+struct list_head *
+trace_get_fields(struct ftrace_event_call *event_call);
+
static inline int
filter_check_discard(struct ftrace_event_call *call, void *rec,
struct ring_buffer *buffer,
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 19d1eb0..acc0f55 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -29,11 +29,23 @@ DEFINE_MUTEX(event_mutex);
LIST_HEAD(ftrace_events);
+struct list_head *
+trace_get_fields(struct ftrace_event_call *event_call)
+{
+ if (!event_call->class->get_fields)
+ return &event_call->class->fields;
+ return event_call->class->get_fields(event_call);
+}
+
int trace_define_field(struct ftrace_event_call *call, const char *type,
const char *name, int offset, int size, int is_signed,
int filter_type)
{
struct ftrace_event_field *field;
+ struct list_head *head;
+
+ if (WARN_ON(!call->class))
+ return 0;
field = kzalloc(sizeof(*field), GFP_KERNEL);
if (!field)
@@ -56,7 +68,8 @@ int trace_define_field(struct ftrace_event_call *call, const char *type,
field->size = size;
field->is_signed = is_signed;
- list_add(&field->link, &call->fields);
+ head = trace_get_fields(call);
+ list_add(&field->link, head);
return 0;
@@ -94,8 +107,10 @@ static int trace_define_common_fields(struct ftrace_event_call *call)
void trace_destroy_fields(struct ftrace_event_call *call)
{
struct ftrace_event_field *field, *next;
+ struct list_head *head;
- list_for_each_entry_safe(field, next, &call->fields, link) {
+ head = trace_get_fields(call);
+ list_for_each_entry_safe(field, next, head, link) {
list_del(&field->link);
kfree(field->type);
kfree(field->name);
@@ -111,7 +126,6 @@ int trace_event_raw_init(struct ftrace_event_call *call)
if (!id)
return -ENODEV;
call->id = id;
- INIT_LIST_HEAD(&call->fields);
return 0;
}
@@ -537,6 +551,7 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
{
struct ftrace_event_call *call = filp->private_data;
struct ftrace_event_field *field;
+ struct list_head *head;
struct trace_seq *s;
int common_field_count = 5;
char *buf;
@@ -555,7 +570,8 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
trace_seq_printf(s, "ID: %d\n", call->id);
trace_seq_printf(s, "format:\n");
- list_for_each_entry_reverse(field, &call->fields, link) {
+ head = trace_get_fields(call);
+ list_for_each_entry_reverse(field, head, link) {
/*
* Smartly shows the array type(except dynamic array).
* Normal:
@@ -931,6 +947,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
const struct file_operations *filter,
const struct file_operations *format)
{
+ struct list_head *head;
int ret;
/*
@@ -957,14 +974,21 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
id);
#endif
- if (call->define_fields) {
- ret = trace_define_common_fields(call);
- if (!ret)
- ret = call->define_fields(call);
- if (ret < 0) {
- pr_warning("Could not initialize trace point"
- " events/%s\n", call->name);
- return ret;
+ if (call->class->define_fields) {
+ /*
+ * Other events may have the same class. Only update
+ * the fields if they are not already defined.
+ */
+ head = trace_get_fields(call);
+ if (list_empty(head)) {
+ ret = trace_define_common_fields(call);
+ if (!ret)
+ ret = call->class->define_fields(call);
+ if (ret < 0) {
+ pr_warning("Could not initialize trace point"
+ " events/%s\n", call->name);
+ return ret;
+ }
}
trace_create_file("filter", 0644, call->dir, call,
filter);
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index ca32960..961f99b 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -500,8 +500,10 @@ static struct ftrace_event_field *
find_event_field(struct ftrace_event_call *call, char *name)
{
struct ftrace_event_field *field;
+ struct list_head *head;
- list_for_each_entry(field, &call->fields, link) {
+ head = trace_get_fields(call);
+ list_for_each_entry(field, head, link) {
if (!strcmp(field->name, name))
return field;
}
@@ -625,7 +627,7 @@ static int init_subsystem_preds(struct event_subsystem *system)
int err;
list_for_each_entry(call, &ftrace_events, list) {
- if (!call->define_fields)
+ if (!call->class || !call->class->define_fields)
continue;
if (strcmp(call->class->system, system->name) != 0)
@@ -644,7 +646,7 @@ static void filter_free_subsystem_preds(struct event_subsystem *system)
struct ftrace_event_call *call;
list_for_each_entry(call, &ftrace_events, list) {
- if (!call->define_fields)
+ if (!call->class || !call->class->define_fields)
continue;
if (strcmp(call->class->system, system->name) != 0)
@@ -1249,7 +1251,7 @@ static int replace_system_preds(struct event_subsystem *system,
list_for_each_entry(call, &ftrace_events, list) {
struct event_filter *filter = call->filter;
- if (!call->define_fields)
+ if (!call->class || !call->class->define_fields)
continue;
if (strcmp(call->class->system, system->name) != 0)
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 7f16e21..e700a0c 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -18,10 +18,6 @@
#undef TRACE_SYSTEM
#define TRACE_SYSTEM ftrace
-struct ftrace_event_class event_class_ftrace = {
- .system = __stringify(TRACE_SYSTEM),
-};
-
/* not needed for this file */
#undef __field_struct
#define __field_struct(type, item)
@@ -131,7 +127,7 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \
static int ftrace_raw_init_event(struct ftrace_event_call *call)
{
- INIT_LIST_HEAD(&call->fields);
+ INIT_LIST_HEAD(&call->class->fields);
return 0;
}
@@ -159,15 +155,19 @@ static int ftrace_raw_init_event(struct ftrace_event_call *call)
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(call, struct_name, type, tstruct, print) \
\
+struct ftrace_event_class event_class_ftrace_##call = { \
+ .system = __stringify(TRACE_SYSTEM), \
+ .define_fields = ftrace_define_fields_##call, \
+}; \
+ \
struct ftrace_event_call __used \
__attribute__((__aligned__(4))) \
__attribute__((section("_ftrace_events"))) event_##call = { \
.name = #call, \
.id = type, \
- .class = &event_class_ftrace, \
+ .class = &event_class_ftrace_##call, \
.raw_init = ftrace_raw_init_event, \
.print_fmt = print, \
- .define_fields = ftrace_define_fields_##call, \
}; \
#include "trace_entries.h"
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index f8af21a..b14bf74 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1112,8 +1112,6 @@ static void probe_event_disable(struct ftrace_event_call *call)
static int probe_event_raw_init(struct ftrace_event_call *event_call)
{
- INIT_LIST_HEAD(&event_call->fields);
-
return 0;
}
@@ -1362,11 +1360,13 @@ static int register_probe_event(struct trace_probe *tp)
if (probe_is_return(tp)) {
tp->event.trace = print_kretprobe_event;
call->raw_init = probe_event_raw_init;
- call->define_fields = kretprobe_event_define_fields;
+ INIT_LIST_HEAD(&call->class->fields);
+ call->class->define_fields = kretprobe_event_define_fields;
} else {
tp->event.trace = print_kprobe_event;
call->raw_init = probe_event_raw_init;
- call->define_fields = kprobe_event_define_fields;
+ INIT_LIST_HEAD(&call->class->fields);
+ call->class->define_fields = kprobe_event_define_fields;
}
if (set_print_fmt(tp) < 0)
return -ENOMEM;
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index a21d366..cceccf0 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -20,14 +20,37 @@ static int syscall_enter_register(struct ftrace_event_call *event,
static int syscall_exit_register(struct ftrace_event_call *event,
enum trace_reg type);
+static int syscall_enter_define_fields(struct ftrace_event_call *call);
+static int syscall_exit_define_fields(struct ftrace_event_call *call);
+
+static struct list_head *
+syscall_get_enter_fields(struct ftrace_event_call *call)
+{
+ struct syscall_metadata *entry = call->data;
+
+ return &entry->enter_fields;
+}
+
+static struct list_head *
+syscall_get_exit_fields(struct ftrace_event_call *call)
+{
+ struct syscall_metadata *entry = call->data;
+
+ return &entry->exit_fields;
+}
+
struct ftrace_event_class event_class_syscall_enter = {
.system = "syscalls",
- .reg = syscall_enter_register
+ .reg = syscall_enter_register,
+ .define_fields = syscall_enter_define_fields,
+ .get_fields = syscall_get_enter_fields,
};
struct ftrace_event_class event_class_syscall_exit = {
.system = "syscalls",
- .reg = syscall_exit_register
+ .reg = syscall_exit_register,
+ .define_fields = syscall_exit_define_fields,
+ .get_fields = syscall_get_exit_fields,
};
extern unsigned long __start_syscalls_metadata[];
@@ -220,7 +243,7 @@ static void free_syscall_print_fmt(struct ftrace_event_call *call)
kfree(call->print_fmt);
}
-int syscall_enter_define_fields(struct ftrace_event_call *call)
+static int syscall_enter_define_fields(struct ftrace_event_call *call)
{
struct syscall_trace_enter trace;
struct syscall_metadata *meta = call->data;
@@ -243,7 +266,7 @@ int syscall_enter_define_fields(struct ftrace_event_call *call)
return ret;
}
-int syscall_exit_define_fields(struct ftrace_event_call *call)
+static int syscall_exit_define_fields(struct ftrace_event_call *call)
{
struct syscall_trace_exit trace;
int ret;
--
1.7.0
^ permalink raw reply related [flat|nested] 19+ messages in thread* Re: [PATCH 05/13 v3] tracing: Move fields from event to class structure
2010-05-14 19:22 ` [PATCH 05/13 v3] tracing: Move fields from event to class structure Steven Rostedt
@ 2010-05-18 4:51 ` Li Zefan
0 siblings, 0 replies; 19+ messages in thread
From: Li Zefan @ 2010-05-18 4:51 UTC (permalink / raw)
To: Steven Rostedt
Cc: linux-kernel, Ingo Molnar, Andrew Morton, Frederic Weisbecker,
Mathieu Desnoyers, Masami Hiramatsu, Mathieu Desnoyers,
Tom Zanussi, Peter Zijlstra
Steven Rostedt wrote:
> From: Steven Rostedt <srostedt@redhat.com>
>
> Move the defined fields from the event to the class structure.
> Since the fields of the event are defined by the class they belong
> to, it makes sense to have the class hold the information instead
> of the individual events. The events of the same class would just
> hold duplicate information.
>
> After this change the size of the kernel dropped another 3K:
>
> text data bss dec hex filename
> 4913961 1088356 861512 6863829 68bbd5 vmlinux.orig
> 4900252 1057412 861512 6819176 680d68 vmlinux.regs
> 4900375 1053380 861512 6815267 67fe23 vmlinux.fields
>
It also saves memory allocated by trace_define_field(). :)
> Although the text increased, this was mainly due to the C files
> having to adapt to the change. This is a constant increase, where
> new tracepoints will not increase the Text. But the big drop is
> in the data size (as well as needed allocations to hold the fields).
> This will give even more savings as more tracepoints are created.
>
> Note, if just TRACE_EVENT()s are used and not DECLARE_EVENT_CLASS()
> with several DEFINE_EVENT()s, then the savings will be lost. But
> we are pushing developers to consolidate events with DEFINE_EVENT()
> so this should not be an issue.
>
> The kprobes define a unique class to every new event, but are dynamic
> so it should not be a issue.
>
> The syscalls however have a single class but the fields for the individual
> events are different. The syscalls use a metadata to define the
> fields. I moved the fields list from the event to the metadata and
> added a "get_fields()" function to the class. This function is used
> to find the fields. For normal events and kprobes, get_fields() just
> returns a pointer to the fields list_head in the class. For syscall
> events, it returns the fields list_head in the metadata for the event.
>
All syscall exit events have the same fields. I'll make a patch for this.
^ permalink raw reply [flat|nested] 19+ messages in thread
* [PATCH 06/13 v3] tracing: Move raw_init from events to class
2010-05-14 19:22 [PATCH 00/13 v3] [GIT PULL] tracing: shrinking trace events and updates Steven Rostedt
` (4 preceding siblings ...)
2010-05-14 19:22 ` [PATCH 05/13 v3] tracing: Move fields from event to class structure Steven Rostedt
@ 2010-05-14 19:22 ` Steven Rostedt
2010-05-14 19:22 ` [PATCH 07/13 v3] tracing: Allow events to share their print functions Steven Rostedt
` (6 subsequent siblings)
12 siblings, 0 replies; 19+ messages in thread
From: Steven Rostedt @ 2010-05-14 19:22 UTC (permalink / raw)
To: linux-kernel
Cc: Ingo Molnar, Andrew Morton, Frederic Weisbecker,
Mathieu Desnoyers, Masami Hiramatsu, Mathieu Desnoyers
[-- Attachment #1: 0006-tracing-Move-raw_init-from-events-to-class.patch --]
[-- Type: text/plain, Size: 8610 bytes --]
From: Steven Rostedt <srostedt@redhat.com>
The raw_init function pointer in the event is used to initialize
various kinds of events. The type of initialization needed is usually
classed to the kind of event it is.
Two events with the same class will always have the same initialization
function, so it makes sense to move this to the class structure.
Perhaps even making a special system structure would work since
the initialization is the same for all events within a system.
But since there's no system structure (yet), this will just move it
to the class.
text data bss dec hex filename
4913961 1088356 861512 6863829 68bbd5 vmlinux.orig
4900375 1053380 861512 6815267 67fe23 vmlinux.fields
4900382 1048964 861512 6810858 67ecea vmlinux.init
The text grew very slightly, but this is a constant growth that happened
with the changing of the C files that call the init code.
The bigger savings is the data which will be saved the more events share
a class.
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Masami Hiramatsu <mhiramat@redhat.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
include/linux/ftrace_event.h | 2 +-
include/linux/syscalls.h | 2 --
include/trace/ftrace.h | 9 ++++-----
kernel/trace/trace_events.c | 12 ++++++------
kernel/trace/trace_export.c | 2 +-
kernel/trace/trace_kprobe.c | 6 +++---
kernel/trace/trace_syscalls.c | 2 ++
7 files changed, 17 insertions(+), 18 deletions(-)
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 479c3c1..393a839 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -133,6 +133,7 @@ struct ftrace_event_class {
int (*define_fields)(struct ftrace_event_call *);
struct list_head *(*get_fields)(struct ftrace_event_call *);
struct list_head fields;
+ int (*raw_init)(struct ftrace_event_call *);
};
struct ftrace_event_call {
@@ -144,7 +145,6 @@ struct ftrace_event_call {
int enabled;
int id;
const char *print_fmt;
- int (*raw_init)(struct ftrace_event_call *);
int filter_active;
struct event_filter *filter;
void *mod;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index fd0f1f2..211c704 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -135,7 +135,6 @@ extern struct ftrace_event_class event_class_syscall_exit;
.name = "sys_enter"#sname, \
.class = &event_class_syscall_enter, \
.event = &enter_syscall_print_##sname, \
- .raw_init = init_syscall_trace, \
.data = (void *)&__syscall_meta_##sname,\
}
@@ -153,7 +152,6 @@ extern struct ftrace_event_class event_class_syscall_exit;
.name = "sys_exit"#sname, \
.class = &event_class_syscall_exit, \
.event = &exit_syscall_print_##sname, \
- .raw_init = init_syscall_trace, \
.data = (void *)&__syscall_meta_##sname,\
}
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index c7e3bcd..e7eb334 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -431,8 +431,9 @@ static inline notrace int ftrace_get_offsets_##call( \
* static struct ftrace_event_class __used event_class_<template> = {
* .system = "<system>",
* .define_fields = ftrace_define_fields_<call>,
- * .fields = LIST_HEAD_INIT(event_class_##call.fields), \
- * .probe = ftrace_raw_event_##call, \
+ * .fields = LIST_HEAD_INIT(event_class_##call.fields),
+ * .raw_init = trace_event_raw_init,
+ * .probe = ftrace_raw_event_##call,
* };
*
* static struct ftrace_event_call __used
@@ -440,7 +441,6 @@ static inline notrace int ftrace_get_offsets_##call( \
* __attribute__((section("_ftrace_events"))) event_<call> = {
* .name = "<call>",
* .class = event_class_<template>,
- * .raw_init = trace_event_raw_init,
* .event = &ftrace_event_type_<call>,
* .print_fmt = print_fmt_<call>,
* };
@@ -566,6 +566,7 @@ static struct ftrace_event_class __used event_class_##call = { \
.system = __stringify(TRACE_SYSTEM), \
.define_fields = ftrace_define_fields_##call, \
.fields = LIST_HEAD_INIT(event_class_##call.fields),\
+ .raw_init = trace_event_raw_init, \
.probe = ftrace_raw_event_##call, \
_TRACE_PERF_INIT(call) \
};
@@ -579,7 +580,6 @@ __attribute__((section("_ftrace_events"))) event_##call = { \
.name = #call, \
.class = &event_class_##template, \
.event = &ftrace_event_type_##call, \
- .raw_init = trace_event_raw_init, \
.print_fmt = print_fmt_##template, \
};
@@ -594,7 +594,6 @@ __attribute__((section("_ftrace_events"))) event_##call = { \
.name = #call, \
.class = &event_class_##template, \
.event = &ftrace_event_type_##call, \
- .raw_init = trace_event_raw_init, \
.print_fmt = print_fmt_##call, \
}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index acc0f55..8e94255 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1008,8 +1008,8 @@ static int __trace_add_event_call(struct ftrace_event_call *call)
if (!call->name)
return -EINVAL;
- if (call->raw_init) {
- ret = call->raw_init(call);
+ if (call->class->raw_init) {
+ ret = call->class->raw_init(call);
if (ret < 0) {
if (ret != -ENOSYS)
pr_warning("Could not initialize trace "
@@ -1170,8 +1170,8 @@ static void trace_module_add_events(struct module *mod)
/* The linker may leave blanks */
if (!call->name)
continue;
- if (call->raw_init) {
- ret = call->raw_init(call);
+ if (call->class->raw_init) {
+ ret = call->class->raw_init(call);
if (ret < 0) {
if (ret != -ENOSYS)
pr_warning("Could not initialize trace "
@@ -1324,8 +1324,8 @@ static __init int event_trace_init(void)
/* The linker may leave blanks */
if (!call->name)
continue;
- if (call->raw_init) {
- ret = call->raw_init(call);
+ if (call->class->raw_init) {
+ ret = call->class->raw_init(call);
if (ret < 0) {
if (ret != -ENOSYS)
pr_warning("Could not initialize trace "
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index e700a0c..e878d06 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -158,6 +158,7 @@ static int ftrace_raw_init_event(struct ftrace_event_call *call)
struct ftrace_event_class event_class_ftrace_##call = { \
.system = __stringify(TRACE_SYSTEM), \
.define_fields = ftrace_define_fields_##call, \
+ .raw_init = ftrace_raw_init_event, \
}; \
\
struct ftrace_event_call __used \
@@ -166,7 +167,6 @@ __attribute__((section("_ftrace_events"))) event_##call = { \
.name = #call, \
.id = type, \
.class = &event_class_ftrace_##call, \
- .raw_init = ftrace_raw_init_event, \
.print_fmt = print, \
}; \
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index b14bf74..428f4a5 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1359,13 +1359,13 @@ static int register_probe_event(struct trace_probe *tp)
/* Initialize ftrace_event_call */
if (probe_is_return(tp)) {
tp->event.trace = print_kretprobe_event;
- call->raw_init = probe_event_raw_init;
INIT_LIST_HEAD(&call->class->fields);
+ call->class->raw_init = probe_event_raw_init;
call->class->define_fields = kretprobe_event_define_fields;
} else {
- tp->event.trace = print_kprobe_event;
- call->raw_init = probe_event_raw_init;
INIT_LIST_HEAD(&call->class->fields);
+ tp->event.trace = print_kprobe_event;
+ call->class->raw_init = probe_event_raw_init;
call->class->define_fields = kprobe_event_define_fields;
}
if (set_print_fmt(tp) < 0)
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index cceccf0..1c1b9bf 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -44,6 +44,7 @@ struct ftrace_event_class event_class_syscall_enter = {
.reg = syscall_enter_register,
.define_fields = syscall_enter_define_fields,
.get_fields = syscall_get_enter_fields,
+ .raw_init = init_syscall_trace,
};
struct ftrace_event_class event_class_syscall_exit = {
@@ -51,6 +52,7 @@ struct ftrace_event_class event_class_syscall_exit = {
.reg = syscall_exit_register,
.define_fields = syscall_exit_define_fields,
.get_fields = syscall_get_exit_fields,
+ .raw_init = init_syscall_trace,
};
extern unsigned long __start_syscalls_metadata[];
--
1.7.0
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH 07/13 v3] tracing: Allow events to share their print functions
2010-05-14 19:22 [PATCH 00/13 v3] [GIT PULL] tracing: shrinking trace events and updates Steven Rostedt
` (5 preceding siblings ...)
2010-05-14 19:22 ` [PATCH 06/13 v3] tracing: Move raw_init from events to class Steven Rostedt
@ 2010-05-14 19:22 ` Steven Rostedt
2010-05-14 19:22 ` [PATCH 08/13 v3] tracing: Move print functions into event class Steven Rostedt
` (5 subsequent siblings)
12 siblings, 0 replies; 19+ messages in thread
From: Steven Rostedt @ 2010-05-14 19:22 UTC (permalink / raw)
To: linux-kernel
Cc: Ingo Molnar, Andrew Morton, Frederic Weisbecker,
Mathieu Desnoyers, Masami Hiramatsu, Mathieu Desnoyers
[-- Attachment #1: 0007-tracing-Allow-events-to-share-their-print-functions.patch --]
[-- Type: text/plain, Size: 29282 bytes --]
From: Steven Rostedt <srostedt@redhat.com>
Multiple events may use the same method to print their data.
Instead of having all events have a pointer to their print funtions,
the trace_event structure now points to a trace_event_functions structure
that will hold the way to print ouf the event.
The event itself is now passed to the print function to let the print
function know what kind of event it should print.
This opens the door to consolidating the way several events print
their output.
text data bss dec hex filename
4913961 1088356 861512 6863829 68bbd5 vmlinux.orig
4900382 1048964 861512 6810858 67ecea vmlinux.init
4900446 1049028 861512 6810986 67ed6a vmlinux.preprint
This change slightly increases the size but is needed for the next change.
v3: Fix the branch tracer events to handle this change.
v2: Fix the new function graph tracer event calls to handle this change.
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Masami Hiramatsu <mhiramat@redhat.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
include/linux/ftrace_event.h | 17 +++-
include/linux/syscalls.h | 10 ++-
include/trace/ftrace.h | 13 ++-
include/trace/syscall.h | 6 +-
kernel/trace/blktrace.c | 13 ++-
kernel/trace/kmemtrace.c | 28 +++++--
kernel/trace/trace.c | 9 +-
kernel/trace/trace_branch.c | 8 ++-
kernel/trace/trace_functions_graph.c | 13 ++-
kernel/trace/trace_kprobe.c | 22 ++++--
kernel/trace/trace_output.c | 137 +++++++++++++++++++++++-----------
kernel/trace/trace_output.h | 2 +-
kernel/trace/trace_syscalls.c | 6 +-
13 files changed, 192 insertions(+), 92 deletions(-)
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 393a839..4f77932 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -70,18 +70,25 @@ struct trace_iterator {
};
+struct trace_event;
+
typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter,
- int flags);
-struct trace_event {
- struct hlist_node node;
- struct list_head list;
- int type;
+ int flags, struct trace_event *event);
+
+struct trace_event_functions {
trace_print_func trace;
trace_print_func raw;
trace_print_func hex;
trace_print_func binary;
};
+struct trace_event {
+ struct hlist_node node;
+ struct list_head list;
+ int type;
+ struct trace_event_functions *funcs;
+};
+
extern int register_ftrace_event(struct trace_event *event);
extern int unregister_ftrace_event(struct trace_event *event);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 211c704..f725677 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -125,9 +125,12 @@ extern struct ftrace_event_class event_class_syscall_exit;
static struct syscall_metadata __syscall_meta_##sname; \
static struct ftrace_event_call \
__attribute__((__aligned__(4))) event_enter_##sname; \
- static struct trace_event enter_syscall_print_##sname = { \
+ static struct trace_event_functions enter_syscall_print_funcs_##sname = { \
.trace = print_syscall_enter, \
}; \
+ static struct trace_event enter_syscall_print_##sname = { \
+ .funcs = &enter_syscall_print_funcs_##sname, \
+ }; \
static struct ftrace_event_call __used \
__attribute__((__aligned__(4))) \
__attribute__((section("_ftrace_events"))) \
@@ -142,9 +145,12 @@ extern struct ftrace_event_class event_class_syscall_exit;
static struct syscall_metadata __syscall_meta_##sname; \
static struct ftrace_event_call \
__attribute__((__aligned__(4))) event_exit_##sname; \
- static struct trace_event exit_syscall_print_##sname = { \
+ static struct trace_event_functions exit_syscall_print_funcs_##sname = { \
.trace = print_syscall_exit, \
}; \
+ static struct trace_event exit_syscall_print_##sname = { \
+ .funcs = &exit_syscall_print_funcs_##sname, \
+ }; \
static struct ftrace_event_call __used \
__attribute__((__aligned__(4))) \
__attribute__((section("_ftrace_events"))) \
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index e7eb334..51ed7f3 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -239,7 +239,8 @@ ftrace_raw_output_id_##call(int event_id, const char *name, \
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, name, proto, args) \
static notrace enum print_line_t \
-ftrace_raw_output_##name(struct trace_iterator *iter, int flags) \
+ftrace_raw_output_##name(struct trace_iterator *iter, int flags, \
+ struct trace_event *event) \
{ \
return ftrace_raw_output_id_##template(event_##name.id, \
#name, iter, flags); \
@@ -248,7 +249,8 @@ ftrace_raw_output_##name(struct trace_iterator *iter, int flags) \
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, call, proto, args, print) \
static notrace enum print_line_t \
-ftrace_raw_output_##call(struct trace_iterator *iter, int flags) \
+ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \
+ struct trace_event *event) \
{ \
struct trace_seq *s = &iter->seq; \
struct ftrace_raw_##template *field; \
@@ -531,11 +533,12 @@ ftrace_raw_event_##call(void *__data, proto) \
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, call, proto, args) \
- \
-static struct trace_event ftrace_event_type_##call = { \
+static struct trace_event_functions ftrace_event_type_funcs_##call = { \
.trace = ftrace_raw_output_##call, \
}; \
- \
+static struct trace_event ftrace_event_type_##call = { \
+ .funcs = &ftrace_event_type_funcs_##call, \
+}; \
static inline void ftrace_test_probe_##call(void) \
{ \
check_trace_callback_type_##call(ftrace_raw_event_##template); \
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index 3964774..257e089 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -42,8 +42,10 @@ extern int reg_event_syscall_exit(struct ftrace_event_call *call);
extern void unreg_event_syscall_exit(struct ftrace_event_call *call);
extern int
ftrace_format_syscall(struct ftrace_event_call *call, struct trace_seq *s);
-enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags);
-enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags);
+enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags,
+ struct trace_event *event);
+enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags,
+ struct trace_event *event);
#endif
#ifdef CONFIG_PERF_EVENTS
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 19d93f8..36ea2b6 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -1336,7 +1336,7 @@ out:
}
static enum print_line_t blk_trace_event_print(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
return print_one_line(iter, false);
}
@@ -1358,7 +1358,8 @@ static int blk_trace_synthesize_old_trace(struct trace_iterator *iter)
}
static enum print_line_t
-blk_trace_event_print_binary(struct trace_iterator *iter, int flags)
+blk_trace_event_print_binary(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
return blk_trace_synthesize_old_trace(iter) ?
TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
@@ -1396,12 +1397,16 @@ static struct tracer blk_tracer __read_mostly = {
.set_flag = blk_tracer_set_flag,
};
-static struct trace_event trace_blk_event = {
- .type = TRACE_BLK,
+static struct trace_event_functions trace_blk_event_funcs = {
.trace = blk_trace_event_print,
.binary = blk_trace_event_print_binary,
};
+static struct trace_event trace_blk_event = {
+ .type = TRACE_BLK,
+ .funcs = &trace_blk_event_funcs,
+};
+
static int __init init_blk_tracer(void)
{
if (!register_ftrace_event(&trace_blk_event)) {
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
index 7253d0c..bbfc1bb 100644
--- a/kernel/trace/kmemtrace.c
+++ b/kernel/trace/kmemtrace.c
@@ -243,7 +243,8 @@ struct kmemtrace_user_event_alloc {
};
static enum print_line_t
-kmemtrace_print_alloc(struct trace_iterator *iter, int flags)
+kmemtrace_print_alloc(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct trace_seq *s = &iter->seq;
struct kmemtrace_alloc_entry *entry;
@@ -263,7 +264,8 @@ kmemtrace_print_alloc(struct trace_iterator *iter, int flags)
}
static enum print_line_t
-kmemtrace_print_free(struct trace_iterator *iter, int flags)
+kmemtrace_print_free(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct trace_seq *s = &iter->seq;
struct kmemtrace_free_entry *entry;
@@ -281,7 +283,8 @@ kmemtrace_print_free(struct trace_iterator *iter, int flags)
}
static enum print_line_t
-kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags)
+kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct trace_seq *s = &iter->seq;
struct kmemtrace_alloc_entry *entry;
@@ -315,7 +318,8 @@ kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags)
}
static enum print_line_t
-kmemtrace_print_free_user(struct trace_iterator *iter, int flags)
+kmemtrace_print_free_user(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct trace_seq *s = &iter->seq;
struct kmemtrace_free_entry *entry;
@@ -469,18 +473,26 @@ static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
}
}
-static struct trace_event kmem_trace_alloc = {
- .type = TRACE_KMEM_ALLOC,
+static struct trace_event_functions kmem_trace_alloc_funcs = {
.trace = kmemtrace_print_alloc,
.binary = kmemtrace_print_alloc_user,
};
-static struct trace_event kmem_trace_free = {
- .type = TRACE_KMEM_FREE,
+static struct trace_event kmem_trace_alloc = {
+ .type = TRACE_KMEM_ALLOC,
+ .funcs = &kmem_trace_alloc_funcs,
+};
+
+static struct trace_event_functions kmem_trace_free_funcs = {
.trace = kmemtrace_print_free,
.binary = kmemtrace_print_free_user,
};
+static struct trace_event kmem_trace_free = {
+ .type = TRACE_KMEM_FREE,
+ .funcs = &kmem_trace_free_funcs,
+};
+
static struct tracer kmem_tracer __read_mostly = {
.name = "kmemtrace",
.init = kmem_trace_init,
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 756d728..ba0ec81 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1936,7 +1936,7 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
}
if (event)
- return event->trace(iter, sym_flags);
+ return event->funcs->trace(iter, sym_flags, event);
if (!trace_seq_printf(s, "Unknown type %d\n", entry->type))
goto partial;
@@ -1962,7 +1962,7 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
event = ftrace_find_event(entry->type);
if (event)
- return event->raw(iter, 0);
+ return event->funcs->raw(iter, 0, event);
if (!trace_seq_printf(s, "%d ?\n", entry->type))
goto partial;
@@ -1989,7 +1989,7 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
event = ftrace_find_event(entry->type);
if (event) {
- enum print_line_t ret = event->hex(iter, 0);
+ enum print_line_t ret = event->funcs->hex(iter, 0, event);
if (ret != TRACE_TYPE_HANDLED)
return ret;
}
@@ -2014,7 +2014,8 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
}
event = ftrace_find_event(entry->type);
- return event ? event->binary(iter, 0) : TRACE_TYPE_HANDLED;
+ return event ? event->funcs->binary(iter, 0, event) :
+ TRACE_TYPE_HANDLED;
}
int trace_empty(struct trace_iterator *iter)
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index b9bc4d4..8d3538b 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -143,7 +143,7 @@ static void branch_trace_reset(struct trace_array *tr)
}
static enum print_line_t trace_branch_print(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
struct trace_branch *field;
@@ -167,9 +167,13 @@ static void branch_print_header(struct seq_file *s)
" |\n");
}
+static struct trace_event_functions trace_branch_funcs = {
+ .trace = trace_branch_print,
+};
+
static struct trace_event trace_branch_event = {
.type = TRACE_BRANCH,
- .trace = trace_branch_print,
+ .funcs = &trace_branch_funcs,
};
static struct tracer branch_trace __read_mostly =
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index dd11c83..79f4bac 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -1025,7 +1025,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
if (!event)
return TRACE_TYPE_UNHANDLED;
- ret = event->trace(iter, sym_flags);
+ ret = event->funcs->trace(iter, sym_flags, event);
if (ret != TRACE_TYPE_HANDLED)
return ret;
}
@@ -1112,7 +1112,8 @@ print_graph_function(struct trace_iterator *iter)
}
static enum print_line_t
-print_graph_function_event(struct trace_iterator *iter, int flags)
+print_graph_function_event(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
return print_graph_function(iter);
}
@@ -1225,14 +1226,18 @@ void graph_trace_close(struct trace_iterator *iter)
}
}
+static struct trace_event_functions graph_functions = {
+ .trace = print_graph_function_event,
+};
+
static struct trace_event graph_trace_entry_event = {
.type = TRACE_GRAPH_ENT,
- .trace = print_graph_function_event,
+ .funcs = &graph_functions,
};
static struct trace_event graph_trace_ret_event = {
.type = TRACE_GRAPH_RET,
- .trace = print_graph_function_event,
+ .funcs = &graph_functions
};
static struct tracer graph_trace __read_mostly = {
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 428f4a5..b989ae2 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1011,16 +1011,15 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri,
/* Event entry printers */
enum print_line_t
-print_kprobe_event(struct trace_iterator *iter, int flags)
+print_kprobe_event(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct kprobe_trace_entry *field;
struct trace_seq *s = &iter->seq;
- struct trace_event *event;
struct trace_probe *tp;
int i;
field = (struct kprobe_trace_entry *)iter->ent;
- event = ftrace_find_event(field->ent.type);
tp = container_of(event, struct trace_probe, event);
if (!trace_seq_printf(s, "%s: (", tp->call.name))
@@ -1046,16 +1045,15 @@ partial:
}
enum print_line_t
-print_kretprobe_event(struct trace_iterator *iter, int flags)
+print_kretprobe_event(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct kretprobe_trace_entry *field;
struct trace_seq *s = &iter->seq;
- struct trace_event *event;
struct trace_probe *tp;
int i;
field = (struct kretprobe_trace_entry *)iter->ent;
- event = ftrace_find_event(field->ent.type);
tp = container_of(event, struct trace_probe, event);
if (!trace_seq_printf(s, "%s: (", tp->call.name))
@@ -1351,6 +1349,14 @@ int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs)
return 0; /* We don't tweek kernel, so just return 0 */
}
+static struct trace_event_functions kretprobe_funcs = {
+ .trace = print_kretprobe_event
+};
+
+static struct trace_event_functions kprobe_funcs = {
+ .trace = print_kprobe_event
+};
+
static int register_probe_event(struct trace_probe *tp)
{
struct ftrace_event_call *call = &tp->call;
@@ -1358,13 +1364,13 @@ static int register_probe_event(struct trace_probe *tp)
/* Initialize ftrace_event_call */
if (probe_is_return(tp)) {
- tp->event.trace = print_kretprobe_event;
+ tp->event.funcs = &kretprobe_funcs;
INIT_LIST_HEAD(&call->class->fields);
call->class->raw_init = probe_event_raw_init;
call->class->define_fields = kretprobe_event_define_fields;
} else {
INIT_LIST_HEAD(&call->class->fields);
- tp->event.trace = print_kprobe_event;
+ tp->event.funcs = &kprobe_funcs;
call->class->raw_init = probe_event_raw_init;
call->class->define_fields = kprobe_event_define_fields;
}
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 2404c12..fc9d4db 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -726,6 +726,9 @@ int register_ftrace_event(struct trace_event *event)
if (WARN_ON(!event))
goto out;
+ if (WARN_ON(!event->funcs))
+ goto out;
+
INIT_LIST_HEAD(&event->list);
if (!event->type) {
@@ -758,14 +761,14 @@ int register_ftrace_event(struct trace_event *event)
goto out;
}
- if (event->trace == NULL)
- event->trace = trace_nop_print;
- if (event->raw == NULL)
- event->raw = trace_nop_print;
- if (event->hex == NULL)
- event->hex = trace_nop_print;
- if (event->binary == NULL)
- event->binary = trace_nop_print;
+ if (event->funcs->trace == NULL)
+ event->funcs->trace = trace_nop_print;
+ if (event->funcs->raw == NULL)
+ event->funcs->raw = trace_nop_print;
+ if (event->funcs->hex == NULL)
+ event->funcs->hex = trace_nop_print;
+ if (event->funcs->binary == NULL)
+ event->funcs->binary = trace_nop_print;
key = event->type & (EVENT_HASHSIZE - 1);
@@ -807,13 +810,15 @@ EXPORT_SYMBOL_GPL(unregister_ftrace_event);
* Standard events
*/
-enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags)
+enum print_line_t trace_nop_print(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
return TRACE_TYPE_HANDLED;
}
/* TRACE_FN */
-static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct ftrace_entry *field;
struct trace_seq *s = &iter->seq;
@@ -840,7 +845,8 @@ static enum print_line_t trace_fn_trace(struct trace_iterator *iter, int flags)
return TRACE_TYPE_PARTIAL_LINE;
}
-static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct ftrace_entry *field;
@@ -854,7 +860,8 @@ static enum print_line_t trace_fn_raw(struct trace_iterator *iter, int flags)
return TRACE_TYPE_HANDLED;
}
-static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct ftrace_entry *field;
struct trace_seq *s = &iter->seq;
@@ -867,7 +874,8 @@ static enum print_line_t trace_fn_hex(struct trace_iterator *iter, int flags)
return TRACE_TYPE_HANDLED;
}
-static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct ftrace_entry *field;
struct trace_seq *s = &iter->seq;
@@ -880,14 +888,18 @@ static enum print_line_t trace_fn_bin(struct trace_iterator *iter, int flags)
return TRACE_TYPE_HANDLED;
}
-static struct trace_event trace_fn_event = {
- .type = TRACE_FN,
+static struct trace_event_functions trace_fn_funcs = {
.trace = trace_fn_trace,
.raw = trace_fn_raw,
.hex = trace_fn_hex,
.binary = trace_fn_bin,
};
+static struct trace_event trace_fn_event = {
+ .type = TRACE_FN,
+ .funcs = &trace_fn_funcs,
+};
+
/* TRACE_CTX an TRACE_WAKE */
static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
char *delim)
@@ -916,13 +928,14 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter,
return TRACE_TYPE_HANDLED;
}
-static enum print_line_t trace_ctx_print(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_ctx_print(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
return trace_ctxwake_print(iter, "==>");
}
static enum print_line_t trace_wake_print(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
return trace_ctxwake_print(iter, " +");
}
@@ -950,12 +963,14 @@ static int trace_ctxwake_raw(struct trace_iterator *iter, char S)
return TRACE_TYPE_HANDLED;
}
-static enum print_line_t trace_ctx_raw(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_ctx_raw(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
return trace_ctxwake_raw(iter, 0);
}
-static enum print_line_t trace_wake_raw(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_wake_raw(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
return trace_ctxwake_raw(iter, '+');
}
@@ -984,18 +999,20 @@ static int trace_ctxwake_hex(struct trace_iterator *iter, char S)
return TRACE_TYPE_HANDLED;
}
-static enum print_line_t trace_ctx_hex(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_ctx_hex(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
return trace_ctxwake_hex(iter, 0);
}
-static enum print_line_t trace_wake_hex(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_wake_hex(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
return trace_ctxwake_hex(iter, '+');
}
static enum print_line_t trace_ctxwake_bin(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
struct ctx_switch_entry *field;
struct trace_seq *s = &iter->seq;
@@ -1012,25 +1029,33 @@ static enum print_line_t trace_ctxwake_bin(struct trace_iterator *iter,
return TRACE_TYPE_HANDLED;
}
-static struct trace_event trace_ctx_event = {
- .type = TRACE_CTX,
+static struct trace_event_functions trace_ctx_funcs = {
.trace = trace_ctx_print,
.raw = trace_ctx_raw,
.hex = trace_ctx_hex,
.binary = trace_ctxwake_bin,
};
-static struct trace_event trace_wake_event = {
- .type = TRACE_WAKE,
+static struct trace_event trace_ctx_event = {
+ .type = TRACE_CTX,
+ .funcs = &trace_ctx_funcs,
+};
+
+static struct trace_event_functions trace_wake_funcs = {
.trace = trace_wake_print,
.raw = trace_wake_raw,
.hex = trace_wake_hex,
.binary = trace_ctxwake_bin,
};
+static struct trace_event trace_wake_event = {
+ .type = TRACE_WAKE,
+ .funcs = &trace_wake_funcs,
+};
+
/* TRACE_SPECIAL */
static enum print_line_t trace_special_print(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
struct special_entry *field;
@@ -1046,7 +1071,7 @@ static enum print_line_t trace_special_print(struct trace_iterator *iter,
}
static enum print_line_t trace_special_hex(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
struct special_entry *field;
struct trace_seq *s = &iter->seq;
@@ -1061,7 +1086,7 @@ static enum print_line_t trace_special_hex(struct trace_iterator *iter,
}
static enum print_line_t trace_special_bin(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
struct special_entry *field;
struct trace_seq *s = &iter->seq;
@@ -1075,18 +1100,22 @@ static enum print_line_t trace_special_bin(struct trace_iterator *iter,
return TRACE_TYPE_HANDLED;
}
-static struct trace_event trace_special_event = {
- .type = TRACE_SPECIAL,
+static struct trace_event_functions trace_special_funcs = {
.trace = trace_special_print,
.raw = trace_special_print,
.hex = trace_special_hex,
.binary = trace_special_bin,
};
+static struct trace_event trace_special_event = {
+ .type = TRACE_SPECIAL,
+ .funcs = &trace_special_funcs,
+};
+
/* TRACE_STACK */
static enum print_line_t trace_stack_print(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
struct stack_entry *field;
struct trace_seq *s = &iter->seq;
@@ -1114,17 +1143,21 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter,
return TRACE_TYPE_PARTIAL_LINE;
}
-static struct trace_event trace_stack_event = {
- .type = TRACE_STACK,
+static struct trace_event_functions trace_stack_funcs = {
.trace = trace_stack_print,
.raw = trace_special_print,
.hex = trace_special_hex,
.binary = trace_special_bin,
};
+static struct trace_event trace_stack_event = {
+ .type = TRACE_STACK,
+ .funcs = &trace_stack_funcs,
+};
+
/* TRACE_USER_STACK */
static enum print_line_t trace_user_stack_print(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
struct userstack_entry *field;
struct trace_seq *s = &iter->seq;
@@ -1143,17 +1176,22 @@ static enum print_line_t trace_user_stack_print(struct trace_iterator *iter,
return TRACE_TYPE_PARTIAL_LINE;
}
-static struct trace_event trace_user_stack_event = {
- .type = TRACE_USER_STACK,
+static struct trace_event_functions trace_user_stack_funcs = {
.trace = trace_user_stack_print,
.raw = trace_special_print,
.hex = trace_special_hex,
.binary = trace_special_bin,
};
+static struct trace_event trace_user_stack_event = {
+ .type = TRACE_USER_STACK,
+ .funcs = &trace_user_stack_funcs,
+};
+
/* TRACE_BPRINT */
static enum print_line_t
-trace_bprint_print(struct trace_iterator *iter, int flags)
+trace_bprint_print(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct trace_entry *entry = iter->ent;
struct trace_seq *s = &iter->seq;
@@ -1178,7 +1216,8 @@ trace_bprint_print(struct trace_iterator *iter, int flags)
static enum print_line_t
-trace_bprint_raw(struct trace_iterator *iter, int flags)
+trace_bprint_raw(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct bprint_entry *field;
struct trace_seq *s = &iter->seq;
@@ -1197,16 +1236,19 @@ trace_bprint_raw(struct trace_iterator *iter, int flags)
return TRACE_TYPE_PARTIAL_LINE;
}
+static struct trace_event_functions trace_bprint_funcs = {
+ .trace = trace_bprint_print,
+ .raw = trace_bprint_raw,
+};
static struct trace_event trace_bprint_event = {
.type = TRACE_BPRINT,
- .trace = trace_bprint_print,
- .raw = trace_bprint_raw,
+ .funcs = &trace_bprint_funcs,
};
/* TRACE_PRINT */
static enum print_line_t trace_print_print(struct trace_iterator *iter,
- int flags)
+ int flags, struct trace_event *event)
{
struct print_entry *field;
struct trace_seq *s = &iter->seq;
@@ -1225,7 +1267,8 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter,
return TRACE_TYPE_PARTIAL_LINE;
}
-static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags)
+static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct print_entry *field;
@@ -1240,12 +1283,16 @@ static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags)
return TRACE_TYPE_PARTIAL_LINE;
}
-static struct trace_event trace_print_event = {
- .type = TRACE_PRINT,
+static struct trace_event_functions trace_print_funcs = {
.trace = trace_print_print,
.raw = trace_print_raw,
};
+static struct trace_event trace_print_event = {
+ .type = TRACE_PRINT,
+ .funcs = &trace_print_funcs,
+};
+
static struct trace_event *events[] __initdata = {
&trace_fn_event,
diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
index 9d91c72..c038eba 100644
--- a/kernel/trace/trace_output.h
+++ b/kernel/trace/trace_output.h
@@ -25,7 +25,7 @@ extern void trace_event_read_unlock(void);
extern struct trace_event *ftrace_find_event(int type);
extern enum print_line_t trace_nop_print(struct trace_iterator *iter,
- int flags);
+ int flags, struct trace_event *event);
extern int
trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 1c1b9bf..3751c81 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -93,7 +93,8 @@ static struct syscall_metadata *syscall_nr_to_meta(int nr)
}
enum print_line_t
-print_syscall_enter(struct trace_iterator *iter, int flags)
+print_syscall_enter(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct trace_seq *s = &iter->seq;
struct trace_entry *ent = iter->ent;
@@ -145,7 +146,8 @@ end:
}
enum print_line_t
-print_syscall_exit(struct trace_iterator *iter, int flags)
+print_syscall_exit(struct trace_iterator *iter, int flags,
+ struct trace_event *event)
{
struct trace_seq *s = &iter->seq;
struct trace_entry *ent = iter->ent;
--
1.7.0
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH 08/13 v3] tracing: Move print functions into event class
2010-05-14 19:22 [PATCH 00/13 v3] [GIT PULL] tracing: shrinking trace events and updates Steven Rostedt
` (6 preceding siblings ...)
2010-05-14 19:22 ` [PATCH 07/13 v3] tracing: Allow events to share their print functions Steven Rostedt
@ 2010-05-14 19:22 ` Steven Rostedt
2010-05-14 19:22 ` [PATCH 09/13 v3] tracing: Remove duplicate id information in event structure Steven Rostedt
` (4 subsequent siblings)
12 siblings, 0 replies; 19+ messages in thread
From: Steven Rostedt @ 2010-05-14 19:22 UTC (permalink / raw)
To: linux-kernel
Cc: Ingo Molnar, Andrew Morton, Frederic Weisbecker,
Mathieu Desnoyers, Masami Hiramatsu, Mathieu Desnoyers
[-- Attachment #1: 0008-tracing-Move-print-functions-into-event-class.patch --]
[-- Type: text/plain, Size: 12039 bytes --]
From: Steven Rostedt <srostedt@redhat.com>
Currently, every event has its own trace_event structure. This is
fine since the structure is needed anyway. But the print function
structure (trace_event_functions) is now separate. Since the output
of the trace event is done by the class (with the exception of events
defined by DEFINE_EVENT_PRINT), it makes sense to have the class
define the print functions that all events in the class can use.
This makes a bigger deal with the syscall events since all syscall events
use the same class. The savings here is another 30K.
text data bss dec hex filename
4913961 1088356 861512 6863829 68bbd5 vmlinux.orig
4900382 1048964 861512 6810858 67ecea vmlinux.init
4900446 1049028 861512 6810986 67ed6a vmlinux.preprint
4895024 1023812 861512 6780348 6775bc vmlinux.print
To accomplish this, and to let the class know what event is being
printed, the event structure is embedded in the ftrace_event_call
structure. This should not be an issues since the event structure
was created for each event anyway.
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Masami Hiramatsu <mhiramat@redhat.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
include/linux/ftrace_event.h | 2 +-
include/linux/syscalls.h | 18 +++------------
include/trace/ftrace.h | 45 +++++++++++++++++-----------------------
kernel/trace/trace_events.c | 6 ++--
kernel/trace/trace_kprobe.c | 14 +++++-------
kernel/trace/trace_syscalls.c | 8 +++++++
6 files changed, 41 insertions(+), 52 deletions(-)
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 4f77932..b1a007d 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -148,7 +148,7 @@ struct ftrace_event_call {
struct ftrace_event_class *class;
char *name;
struct dentry *dir;
- struct trace_event *event;
+ struct trace_event event;
int enabled;
int id;
const char *print_fmt;
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index f725677..a1a86a5 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -120,24 +120,20 @@ struct perf_event_attr;
extern struct ftrace_event_class event_class_syscall_enter;
extern struct ftrace_event_class event_class_syscall_exit;
+extern struct trace_event_functions enter_syscall_print_funcs;
+extern struct trace_event_functions exit_syscall_print_funcs;
#define SYSCALL_TRACE_ENTER_EVENT(sname) \
static struct syscall_metadata __syscall_meta_##sname; \
static struct ftrace_event_call \
__attribute__((__aligned__(4))) event_enter_##sname; \
- static struct trace_event_functions enter_syscall_print_funcs_##sname = { \
- .trace = print_syscall_enter, \
- }; \
- static struct trace_event enter_syscall_print_##sname = { \
- .funcs = &enter_syscall_print_funcs_##sname, \
- }; \
static struct ftrace_event_call __used \
__attribute__((__aligned__(4))) \
__attribute__((section("_ftrace_events"))) \
event_enter_##sname = { \
.name = "sys_enter"#sname, \
.class = &event_class_syscall_enter, \
- .event = &enter_syscall_print_##sname, \
+ .event.funcs = &enter_syscall_print_funcs, \
.data = (void *)&__syscall_meta_##sname,\
}
@@ -145,19 +141,13 @@ extern struct ftrace_event_class event_class_syscall_exit;
static struct syscall_metadata __syscall_meta_##sname; \
static struct ftrace_event_call \
__attribute__((__aligned__(4))) event_exit_##sname; \
- static struct trace_event_functions exit_syscall_print_funcs_##sname = { \
- .trace = print_syscall_exit, \
- }; \
- static struct trace_event exit_syscall_print_##sname = { \
- .funcs = &exit_syscall_print_funcs_##sname, \
- }; \
static struct ftrace_event_call __used \
__attribute__((__aligned__(4))) \
__attribute__((section("_ftrace_events"))) \
event_exit_##sname = { \
.name = "sys_exit"#sname, \
.class = &event_class_syscall_exit, \
- .event = &exit_syscall_print_##sname, \
+ .event.funcs = &exit_syscall_print_funcs, \
.data = (void *)&__syscall_meta_##sname,\
}
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 51ed7f3..824141d 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -206,18 +206,22 @@
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
static notrace enum print_line_t \
-ftrace_raw_output_id_##call(int event_id, const char *name, \
- struct trace_iterator *iter, int flags) \
+ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \
+ struct trace_event *trace_event) \
{ \
+ struct ftrace_event_call *event; \
struct trace_seq *s = &iter->seq; \
struct ftrace_raw_##call *field; \
struct trace_entry *entry; \
struct trace_seq *p; \
int ret; \
\
+ event = container_of(trace_event, struct ftrace_event_call, \
+ event); \
+ \
entry = iter->ent; \
\
- if (entry->type != event_id) { \
+ if (entry->type != event->id) { \
WARN_ON_ONCE(1); \
return TRACE_TYPE_UNHANDLED; \
} \
@@ -226,7 +230,7 @@ ftrace_raw_output_id_##call(int event_id, const char *name, \
\
p = &get_cpu_var(ftrace_event_seq); \
trace_seq_init(p); \
- ret = trace_seq_printf(s, "%s: ", name); \
+ ret = trace_seq_printf(s, "%s: ", event->name); \
if (ret) \
ret = trace_seq_printf(s, print); \
put_cpu(); \
@@ -234,17 +238,10 @@ ftrace_raw_output_id_##call(int event_id, const char *name, \
return TRACE_TYPE_PARTIAL_LINE; \
\
return TRACE_TYPE_HANDLED; \
-}
-
-#undef DEFINE_EVENT
-#define DEFINE_EVENT(template, name, proto, args) \
-static notrace enum print_line_t \
-ftrace_raw_output_##name(struct trace_iterator *iter, int flags, \
- struct trace_event *event) \
-{ \
- return ftrace_raw_output_id_##template(event_##name.id, \
- #name, iter, flags); \
-}
+} \
+static struct trace_event_functions ftrace_event_type_funcs_##call = { \
+ .trace = ftrace_raw_output_##call, \
+};
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, call, proto, args, print) \
@@ -277,7 +274,10 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \
return TRACE_TYPE_PARTIAL_LINE; \
\
return TRACE_TYPE_HANDLED; \
-}
+} \
+static struct trace_event_functions ftrace_event_type_funcs_##call = { \
+ .trace = ftrace_raw_output_##call, \
+};
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
@@ -533,20 +533,13 @@ ftrace_raw_event_##call(void *__data, proto) \
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, call, proto, args) \
-static struct trace_event_functions ftrace_event_type_funcs_##call = { \
- .trace = ftrace_raw_output_##call, \
-}; \
-static struct trace_event ftrace_event_type_##call = { \
- .funcs = &ftrace_event_type_funcs_##call, \
-}; \
static inline void ftrace_test_probe_##call(void) \
{ \
check_trace_callback_type_##call(ftrace_raw_event_##template); \
}
#undef DEFINE_EVENT_PRINT
-#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
- DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
@@ -582,7 +575,7 @@ __attribute__((__aligned__(4))) \
__attribute__((section("_ftrace_events"))) event_##call = { \
.name = #call, \
.class = &event_class_##template, \
- .event = &ftrace_event_type_##call, \
+ .event.funcs = &ftrace_event_type_funcs_##template, \
.print_fmt = print_fmt_##template, \
};
@@ -596,7 +589,7 @@ __attribute__((__aligned__(4))) \
__attribute__((section("_ftrace_events"))) event_##call = { \
.name = #call, \
.class = &event_class_##template, \
- .event = &ftrace_event_type_##call, \
+ .event.funcs = &ftrace_event_type_funcs_##call, \
.print_fmt = print_fmt_##call, \
}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 8e94255..aafe5bf 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -122,7 +122,7 @@ int trace_event_raw_init(struct ftrace_event_call *call)
{
int id;
- id = register_ftrace_event(call->event);
+ id = register_ftrace_event(&call->event);
if (!id)
return -ENODEV;
call->id = id;
@@ -1073,8 +1073,8 @@ static void remove_subsystem_dir(const char *name)
static void __trace_remove_event_call(struct ftrace_event_call *call)
{
ftrace_event_enable_disable(call, 0);
- if (call->event)
- __unregister_ftrace_event(call->event);
+ if (call->event.funcs)
+ __unregister_ftrace_event(&call->event);
debugfs_remove_recursive(call->dir);
list_del(&call->list);
trace_destroy_fields(call);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index b989ae2..d8061c3 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -204,7 +204,6 @@ struct trace_probe {
const char *symbol; /* symbol name */
struct ftrace_event_class class;
struct ftrace_event_call call;
- struct trace_event event;
unsigned int nr_args;
struct probe_arg args[];
};
@@ -1020,7 +1019,7 @@ print_kprobe_event(struct trace_iterator *iter, int flags,
int i;
field = (struct kprobe_trace_entry *)iter->ent;
- tp = container_of(event, struct trace_probe, event);
+ tp = container_of(event, struct trace_probe, call.event);
if (!trace_seq_printf(s, "%s: (", tp->call.name))
goto partial;
@@ -1054,7 +1053,7 @@ print_kretprobe_event(struct trace_iterator *iter, int flags,
int i;
field = (struct kretprobe_trace_entry *)iter->ent;
- tp = container_of(event, struct trace_probe, event);
+ tp = container_of(event, struct trace_probe, call.event);
if (!trace_seq_printf(s, "%s: (", tp->call.name))
goto partial;
@@ -1364,20 +1363,19 @@ static int register_probe_event(struct trace_probe *tp)
/* Initialize ftrace_event_call */
if (probe_is_return(tp)) {
- tp->event.funcs = &kretprobe_funcs;
INIT_LIST_HEAD(&call->class->fields);
+ call->event.funcs = &kretprobe_funcs;
call->class->raw_init = probe_event_raw_init;
call->class->define_fields = kretprobe_event_define_fields;
} else {
INIT_LIST_HEAD(&call->class->fields);
- tp->event.funcs = &kprobe_funcs;
+ call->event.funcs = &kprobe_funcs;
call->class->raw_init = probe_event_raw_init;
call->class->define_fields = kprobe_event_define_fields;
}
if (set_print_fmt(tp) < 0)
return -ENOMEM;
- call->event = &tp->event;
- call->id = register_ftrace_event(&tp->event);
+ call->id = register_ftrace_event(&call->event);
if (!call->id) {
kfree(call->print_fmt);
return -ENODEV;
@@ -1389,7 +1387,7 @@ static int register_probe_event(struct trace_probe *tp)
if (ret) {
pr_info("Failed to register kprobe event: %s\n", call->name);
kfree(call->print_fmt);
- unregister_ftrace_event(&tp->event);
+ unregister_ftrace_event(&call->event);
}
return ret;
}
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 3751c81..7c7cfe9 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -39,6 +39,14 @@ syscall_get_exit_fields(struct ftrace_event_call *call)
return &entry->exit_fields;
}
+struct trace_event_functions enter_syscall_print_funcs = {
+ .trace = print_syscall_enter,
+};
+
+struct trace_event_functions exit_syscall_print_funcs = {
+ .trace = print_syscall_exit,
+};
+
struct ftrace_event_class event_class_syscall_enter = {
.system = "syscalls",
.reg = syscall_enter_register,
--
1.7.0
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH 09/13 v3] tracing: Remove duplicate id information in event structure
2010-05-14 19:22 [PATCH 00/13 v3] [GIT PULL] tracing: shrinking trace events and updates Steven Rostedt
` (7 preceding siblings ...)
2010-05-14 19:22 ` [PATCH 08/13 v3] tracing: Move print functions into event class Steven Rostedt
@ 2010-05-14 19:22 ` Steven Rostedt
2010-05-14 19:22 ` [PATCH 10/13 v3] tracing: Combine event filter_active and enable into single flags field Steven Rostedt
` (3 subsequent siblings)
12 siblings, 0 replies; 19+ messages in thread
From: Steven Rostedt @ 2010-05-14 19:22 UTC (permalink / raw)
To: linux-kernel
Cc: Ingo Molnar, Andrew Morton, Frederic Weisbecker,
Mathieu Desnoyers, Masami Hiramatsu, Mathieu Desnoyers
[-- Attachment #1: 0009-tracing-Remove-duplicate-id-information-in-event-str.patch --]
[-- Type: text/plain, Size: 11130 bytes --]
From: Steven Rostedt <srostedt@redhat.com>
Now that the trace_event structure is embedded in the ftrace_event_call
structure, there is no need for the ftrace_event_call id field.
The id field is the same as the trace_event type field.
Removing the id and re-arranging the structure brings down the tracepoint
footprint by another 5K.
text data bss dec hex filename
4913961 1088356 861512 6863829 68bbd5 vmlinux.orig
4895024 1023812 861512 6780348 6775bc vmlinux.print
4894944 1018052 861512 6774508 675eec vmlinux.id
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Masami Hiramatsu <mhiramat@redhat.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
include/linux/ftrace_event.h | 5 ++---
include/trace/ftrace.h | 12 ++++++------
kernel/trace/trace_event_perf.c | 4 ++--
kernel/trace/trace_events.c | 7 +++----
kernel/trace/trace_events_filter.c | 2 +-
kernel/trace/trace_export.c | 4 ++--
kernel/trace/trace_kprobe.c | 18 ++++++++++--------
kernel/trace/trace_syscalls.c | 14 ++++++++------
8 files changed, 34 insertions(+), 32 deletions(-)
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index b1a007d..0be0285 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -149,14 +149,13 @@ struct ftrace_event_call {
char *name;
struct dentry *dir;
struct trace_event event;
- int enabled;
- int id;
const char *print_fmt;
- int filter_active;
struct event_filter *filter;
void *mod;
void *data;
+ int enabled;
+ int filter_active;
int perf_refcount;
};
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 824141d..4866c10 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -150,7 +150,7 @@
*
* entry = iter->ent;
*
- * if (entry->type != event_<call>.id) {
+ * if (entry->type != event_<call>->event.type) {
* WARN_ON_ONCE(1);
* return TRACE_TYPE_UNHANDLED;
* }
@@ -221,7 +221,7 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \
\
entry = iter->ent; \
\
- if (entry->type != event->id) { \
+ if (entry->type != event->event.type) { \
WARN_ON_ONCE(1); \
return TRACE_TYPE_UNHANDLED; \
} \
@@ -257,7 +257,7 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags, \
\
entry = iter->ent; \
\
- if (entry->type != event_##call.id) { \
+ if (entry->type != event_##call.event.type) { \
WARN_ON_ONCE(1); \
return TRACE_TYPE_UNHANDLED; \
} \
@@ -409,7 +409,7 @@ static inline notrace int ftrace_get_offsets_##call( \
* __data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
*
* event = trace_current_buffer_lock_reserve(&buffer,
- * event_<call>.id,
+ * event_<call>->event.type,
* sizeof(*entry) + __data_size,
* irq_flags, pc);
* if (!event)
@@ -510,7 +510,7 @@ ftrace_raw_event_##call(void *__data, proto) \
__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
\
event = trace_current_buffer_lock_reserve(&buffer, \
- event_call->id, \
+ event_call->event.type, \
sizeof(*entry) + __data_size, \
irq_flags, pc); \
if (!event) \
@@ -711,7 +711,7 @@ perf_trace_##call(void *__data, proto) \
"profile buffer not large enough")) \
return; \
entry = (struct ftrace_raw_##call *)perf_trace_buf_prepare( \
- __entry_size, event_call->id, &rctx, &irq_flags); \
+ __entry_size, event_call->event.type, &rctx, &irq_flags); \
if (!entry) \
return; \
tstruct \
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 196fe9d..0a47e8d 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -80,7 +80,7 @@ int perf_trace_enable(int event_id)
mutex_lock(&event_mutex);
list_for_each_entry(event, &ftrace_events, list) {
- if (event->id == event_id &&
+ if (event->event.type == event_id &&
event->class && event->class->perf_probe &&
try_module_get(event->mod)) {
ret = perf_trace_event_enable(event);
@@ -128,7 +128,7 @@ void perf_trace_disable(int event_id)
mutex_lock(&event_mutex);
list_for_each_entry(event, &ftrace_events, list) {
- if (event->id == event_id) {
+ if (event->event.type == event_id) {
perf_trace_event_disable(event);
module_put(event->mod);
break;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index aafe5bf..8daaca5 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -125,7 +125,6 @@ int trace_event_raw_init(struct ftrace_event_call *call)
id = register_ftrace_event(&call->event);
if (!id)
return -ENODEV;
- call->id = id;
return 0;
}
@@ -567,7 +566,7 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
trace_seq_init(s);
trace_seq_printf(s, "name: %s\n", call->name);
- trace_seq_printf(s, "ID: %d\n", call->id);
+ trace_seq_printf(s, "ID: %d\n", call->event.type);
trace_seq_printf(s, "format:\n");
head = trace_get_fields(call);
@@ -641,7 +640,7 @@ event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
return -ENOMEM;
trace_seq_init(s);
- trace_seq_printf(s, "%d\n", call->id);
+ trace_seq_printf(s, "%d\n", call->event.type);
r = simple_read_from_buffer(ubuf, cnt, ppos,
s->buffer, s->len);
@@ -969,7 +968,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
enable);
#ifdef CONFIG_PERF_EVENTS
- if (call->id && (call->class->perf_probe || call->class->reg))
+ if (call->event.type && (call->class->perf_probe || call->class->reg))
trace_create_file("id", 0444, call->dir, call,
id);
#endif
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 961f99b..2702d6b 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1395,7 +1395,7 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id,
mutex_lock(&event_mutex);
list_for_each_entry(call, &ftrace_events, list) {
- if (call->id == event_id)
+ if (call->event.type == event_id)
break;
}
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index e878d06..8536e2a 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -153,7 +153,7 @@ static int ftrace_raw_init_event(struct ftrace_event_call *call)
#define F_printk(fmt, args...) #fmt ", " __stringify(args)
#undef FTRACE_ENTRY
-#define FTRACE_ENTRY(call, struct_name, type, tstruct, print) \
+#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print) \
\
struct ftrace_event_class event_class_ftrace_##call = { \
.system = __stringify(TRACE_SYSTEM), \
@@ -165,7 +165,7 @@ struct ftrace_event_call __used \
__attribute__((__aligned__(4))) \
__attribute__((section("_ftrace_events"))) event_##call = { \
.name = #call, \
- .id = type, \
+ .event.type = etype, \
.class = &event_class_ftrace_##call, \
.print_fmt = print, \
}; \
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index d8061c3..934078b 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -960,8 +960,8 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
- event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
- irq_flags, pc);
+ event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
+ size, irq_flags, pc);
if (!event)
return;
@@ -992,8 +992,8 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri,
size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
- event = trace_current_buffer_lock_reserve(&buffer, call->id, size,
- irq_flags, pc);
+ event = trace_current_buffer_lock_reserve(&buffer, call->event.type,
+ size, irq_flags, pc);
if (!event)
return;
@@ -1228,7 +1228,8 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp,
"profile buffer not large enough"))
return;
- entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags);
+ entry = perf_trace_buf_prepare(size, call->event.type,
+ &rctx, &irq_flags);
if (!entry)
return;
@@ -1258,7 +1259,8 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
"profile buffer not large enough"))
return;
- entry = perf_trace_buf_prepare(size, call->id, &rctx, &irq_flags);
+ entry = perf_trace_buf_prepare(size, call->event.type,
+ &rctx, &irq_flags);
if (!entry)
return;
@@ -1375,8 +1377,8 @@ static int register_probe_event(struct trace_probe *tp)
}
if (set_print_fmt(tp) < 0)
return -ENOMEM;
- call->id = register_ftrace_event(&call->event);
- if (!call->id) {
+ ret = register_ftrace_event(&call->event);
+ if (!ret) {
kfree(call->print_fmt);
return -ENODEV;
}
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 7c7cfe9..9d35830 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -117,7 +117,7 @@ print_syscall_enter(struct trace_iterator *iter, int flags,
if (!entry)
goto end;
- if (entry->enter_event->id != ent->type) {
+ if (entry->enter_event->event.type != ent->type) {
WARN_ON_ONCE(1);
goto end;
}
@@ -173,7 +173,7 @@ print_syscall_exit(struct trace_iterator *iter, int flags,
return TRACE_TYPE_HANDLED;
}
- if (entry->exit_event->id != ent->type) {
+ if (entry->exit_event->event.type != ent->type) {
WARN_ON_ONCE(1);
return TRACE_TYPE_UNHANDLED;
}
@@ -315,7 +315,7 @@ void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
event = trace_current_buffer_lock_reserve(&buffer,
- sys_data->enter_event->id, size, 0, 0);
+ sys_data->enter_event->event.type, size, 0, 0);
if (!event)
return;
@@ -347,7 +347,7 @@ void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
return;
event = trace_current_buffer_lock_reserve(&buffer,
- sys_data->exit_event->id, sizeof(*entry), 0, 0);
+ sys_data->exit_event->event.type, sizeof(*entry), 0, 0);
if (!event)
return;
@@ -511,7 +511,8 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
return;
rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
- sys_data->enter_event->id, &rctx, &flags);
+ sys_data->enter_event->event.type,
+ &rctx, &flags);
if (!rec)
return;
@@ -586,7 +587,8 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
return;
rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
- sys_data->exit_event->id, &rctx, &flags);
+ sys_data->exit_event->event.type,
+ &rctx, &flags);
if (!rec)
return;
--
1.7.0
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH 10/13 v3] tracing: Combine event filter_active and enable into single flags field
2010-05-14 19:22 [PATCH 00/13 v3] [GIT PULL] tracing: shrinking trace events and updates Steven Rostedt
` (8 preceding siblings ...)
2010-05-14 19:22 ` [PATCH 09/13 v3] tracing: Remove duplicate id information in event structure Steven Rostedt
@ 2010-05-14 19:22 ` Steven Rostedt
2010-05-14 19:22 ` [PATCH 11/13 v3] tracing: Fix function declarations if !CONFIG_STACKTRACE Steven Rostedt
` (2 subsequent siblings)
12 siblings, 0 replies; 19+ messages in thread
From: Steven Rostedt @ 2010-05-14 19:22 UTC (permalink / raw)
To: linux-kernel
Cc: Ingo Molnar, Andrew Morton, Frederic Weisbecker,
Mathieu Desnoyers, Masami Hiramatsu, Mathieu Desnoyers,
Tom Zanussi
[-- Attachment #1: 0010-tracing-Combine-event-filter_active-and-enable-into-.patch --]
[-- Type: text/plain, Size: 7251 bytes --]
From: Steven Rostedt <srostedt@redhat.com>
The filter_active and enable both use an int (4 bytes each) to
set a single flag. We can save 4 bytes per event by combining the
two into a single integer.
text data bss dec hex filename
4913961 1088356 861512 6863829 68bbd5 vmlinux.orig
4894944 1018052 861512 6774508 675eec vmlinux.id
4894871 1012292 861512 6768675 674823 vmlinux.flags
This gives us another 5K in savings.
The modification of both the enable and filter fields are done
under the event_mutex, so it is still safe to combine the two.
Note: Although Mathieu gave his Acked-by, he would like it documented
that the reads of flags are not protected by the mutex. The way the
code works, these reads will not break anything, but will have a
residual effect. Since this behavior is the same even before this
patch, describing this situation is left to another patch, as this
patch does not change the behavior, but just brought it to Mathieu's
attention.
v2: Updated the event trace self test to for this change.
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Masami Hiramatsu <mhiramat@redhat.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
include/linux/ftrace_event.h | 21 +++++++++++++++++++--
kernel/trace/trace.h | 2 +-
kernel/trace/trace_events.c | 16 ++++++++--------
kernel/trace/trace_events_filter.c | 10 +++++-----
kernel/trace/trace_kprobe.c | 2 +-
5 files changed, 34 insertions(+), 17 deletions(-)
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 0be0285..5ac97a4 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -143,6 +143,16 @@ struct ftrace_event_class {
int (*raw_init)(struct ftrace_event_call *);
};
+enum {
+ TRACE_EVENT_FL_ENABLED_BIT,
+ TRACE_EVENT_FL_FILTERED_BIT,
+};
+
+enum {
+ TRACE_EVENT_FL_ENABLED = (1 << TRACE_EVENT_FL_ENABLED_BIT),
+ TRACE_EVENT_FL_FILTERED = (1 << TRACE_EVENT_FL_FILTERED_BIT),
+};
+
struct ftrace_event_call {
struct list_head list;
struct ftrace_event_class *class;
@@ -154,8 +164,15 @@ struct ftrace_event_call {
void *mod;
void *data;
- int enabled;
- int filter_active;
+ /*
+ * 32 bit flags:
+ * bit 1: enabled
+ * bit 2: filter_active
+ *
+ * Must hold event_mutex to change.
+ */
+ unsigned int flags;
+
int perf_refcount;
};
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index c88c563..6356259 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -802,7 +802,7 @@ filter_check_discard(struct ftrace_event_call *call, void *rec,
struct ring_buffer *buffer,
struct ring_buffer_event *event)
{
- if (unlikely(call->filter_active) &&
+ if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) &&
!filter_match_preds(call->filter, rec)) {
ring_buffer_discard_commit(buffer, event);
return 1;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 8daaca5..53cffc0 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -137,8 +137,8 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call,
switch (enable) {
case 0:
- if (call->enabled) {
- call->enabled = 0;
+ if (call->flags & TRACE_EVENT_FL_ENABLED) {
+ call->flags &= ~TRACE_EVENT_FL_ENABLED;
tracing_stop_cmdline_record();
if (call->class->reg)
call->class->reg(call, TRACE_REG_UNREGISTER);
@@ -149,7 +149,7 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call,
}
break;
case 1:
- if (!call->enabled) {
+ if (!(call->flags & TRACE_EVENT_FL_ENABLED)) {
tracing_start_cmdline_record();
if (call->class->reg)
ret = call->class->reg(call, TRACE_REG_REGISTER);
@@ -163,7 +163,7 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call,
"%s\n", call->name);
break;
}
- call->enabled = 1;
+ call->flags |= TRACE_EVENT_FL_ENABLED;
}
break;
}
@@ -352,7 +352,7 @@ s_next(struct seq_file *m, void *v, loff_t *pos)
(*pos)++;
list_for_each_entry_continue(call, &ftrace_events, list) {
- if (call->enabled)
+ if (call->flags & TRACE_EVENT_FL_ENABLED)
return call;
}
@@ -411,7 +411,7 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
struct ftrace_event_call *call = filp->private_data;
char *buf;
- if (call->enabled)
+ if (call->flags & TRACE_EVENT_FL_ENABLED)
buf = "1\n";
else
buf = "0\n";
@@ -486,7 +486,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
* or if all events or cleared, or if we have
* a mixture.
*/
- set |= (1 << !!call->enabled);
+ set |= (1 << !!(call->flags & TRACE_EVENT_FL_ENABLED));
/*
* If we have a mixture, no need to look further.
@@ -1447,7 +1447,7 @@ static __init void event_trace_self_tests(void)
* If an event is already enabled, someone is using
* it and the self test should not be on.
*/
- if (call->enabled) {
+ if (call->flags & TRACE_EVENT_FL_ENABLED) {
pr_warning("Enabled event during self test!\n");
WARN_ON_ONCE(1);
continue;
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 2702d6b..239ea5d 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -547,7 +547,7 @@ static void filter_disable_preds(struct ftrace_event_call *call)
struct event_filter *filter = call->filter;
int i;
- call->filter_active = 0;
+ call->flags &= ~TRACE_EVENT_FL_FILTERED;
filter->n_preds = 0;
for (i = 0; i < MAX_FILTER_PRED; i++)
@@ -574,7 +574,7 @@ void destroy_preds(struct ftrace_event_call *call)
{
__free_preds(call->filter);
call->filter = NULL;
- call->filter_active = 0;
+ call->flags &= ~TRACE_EVENT_FL_FILTERED;
}
static struct event_filter *__alloc_preds(void)
@@ -613,7 +613,7 @@ static int init_preds(struct ftrace_event_call *call)
if (call->filter)
return 0;
- call->filter_active = 0;
+ call->flags &= ~TRACE_EVENT_FL_FILTERED;
call->filter = __alloc_preds();
if (IS_ERR(call->filter))
return PTR_ERR(call->filter);
@@ -1268,7 +1268,7 @@ static int replace_system_preds(struct event_subsystem *system,
if (err)
filter_disable_preds(call);
else {
- call->filter_active = 1;
+ call->flags |= TRACE_EVENT_FL_FILTERED;
replace_filter_string(filter, filter_string);
}
fail = false;
@@ -1317,7 +1317,7 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
if (err)
append_filter_err(ps, call->filter);
else
- call->filter_active = 1;
+ call->flags |= TRACE_EVENT_FL_FILTERED;
out:
filter_opstack_clear(ps);
postfix_clear(ps);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 934078b..0e3ded6 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1382,7 +1382,7 @@ static int register_probe_event(struct trace_probe *tp)
kfree(call->print_fmt);
return -ENODEV;
}
- call->enabled = 0;
+ call->flags = 0;
call->class->reg = kprobe_register;
call->data = tp;
ret = trace_add_event_call(call);
--
1.7.0
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH 11/13 v3] tracing: Fix function declarations if !CONFIG_STACKTRACE
2010-05-14 19:22 [PATCH 00/13 v3] [GIT PULL] tracing: shrinking trace events and updates Steven Rostedt
` (9 preceding siblings ...)
2010-05-14 19:22 ` [PATCH 10/13 v3] tracing: Combine event filter_active and enable into single flags field Steven Rostedt
@ 2010-05-14 19:22 ` Steven Rostedt
2010-05-14 19:22 ` [PATCH 12/13 v3] ring-buffer: Add cached pages when freeing reader page Steven Rostedt
2010-05-14 19:22 ` [PATCH 13/13 v3] tracing: Comment the use of event_mutex with trace event flags Steven Rostedt
12 siblings, 0 replies; 19+ messages in thread
From: Steven Rostedt @ 2010-05-14 19:22 UTC (permalink / raw)
To: linux-kernel
Cc: Ingo Molnar, Andrew Morton, Frederic Weisbecker,
Mathieu Desnoyers, Masami Hiramatsu, Li Zefan
[-- Attachment #1: 0011-tracing-Fix-function-declarations-if-CONFIG_STACKTRA.patch --]
[-- Type: text/plain, Size: 1192 bytes --]
From: Li Zefan <lizf@cn.fujitsu.com>
ftrace_trace_stack() and frace_trace_userstacke() take a
struct ring_buffer argument, not struct trace_array. Commit
e77405ad("tracing: pass around ring buffer instead of tracer")
made this change.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <4BE77C14.5010806@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
kernel/trace/trace.h | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6356259..40cd171 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -419,12 +419,12 @@ void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags,
void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
int pc);
#else
-static inline void ftrace_trace_stack(struct trace_array *tr,
+static inline void ftrace_trace_stack(struct ring_buffer *buffer,
unsigned long flags, int skip, int pc)
{
}
-static inline void ftrace_trace_userstack(struct trace_array *tr,
+static inline void ftrace_trace_userstack(struct ring_buffer *buffer,
unsigned long flags, int pc)
{
}
--
1.7.0
^ permalink raw reply related [flat|nested] 19+ messages in thread* [PATCH 12/13 v3] ring-buffer: Add cached pages when freeing reader page
2010-05-14 19:22 [PATCH 00/13 v3] [GIT PULL] tracing: shrinking trace events and updates Steven Rostedt
` (10 preceding siblings ...)
2010-05-14 19:22 ` [PATCH 11/13 v3] tracing: Fix function declarations if !CONFIG_STACKTRACE Steven Rostedt
@ 2010-05-14 19:22 ` Steven Rostedt
2010-05-14 22:26 ` Mathieu Desnoyers
2010-05-14 19:22 ` [PATCH 13/13 v3] tracing: Comment the use of event_mutex with trace event flags Steven Rostedt
12 siblings, 1 reply; 19+ messages in thread
From: Steven Rostedt @ 2010-05-14 19:22 UTC (permalink / raw)
To: linux-kernel
Cc: Ingo Molnar, Andrew Morton, Frederic Weisbecker,
Mathieu Desnoyers, Masami Hiramatsu
[-- Attachment #1: 0012-ring-buffer-Add-cached-pages-when-freeing-reader-pag.patch --]
[-- Type: text/plain, Size: 4172 bytes --]
From: Steven Rostedt <srostedt@redhat.com>
When the pages are removed from the ring buffer for things like
splice they are freed with ring_buffer_free_read_page().
They are also allocated with ring_buffer_alloc_read_page().
Currently the ring buffer does not take advantage of this situation.
Every time the page is freed, the ring buffer simply frees it.
When a new page is needed, it allocates it. This means that reading
several pages with splice will cause a page to be freed and allocated
several times. This is simply a waste.
This patch adds a cache of the pages freed (16 max). This allows
the pages to be reused quickly without need to go back to the memory
pool.
v2: Added in locking that should have been there in the first release.
Reported-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
kernel/trace/ring_buffer.c | 52 ++++++++++++++++++++++++++++++++++++++------
1 files changed, 45 insertions(+), 7 deletions(-)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 7f6059c..7aded7d 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -157,6 +157,8 @@ static unsigned long ring_buffer_flags __read_mostly = RB_BUFFERS_ON;
#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data)
+#define RB_MAX_FREE_PAGES 16
+
/**
* tracing_on - enable all tracing buffers
*
@@ -325,7 +327,10 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
#define RB_MISSED_STORED (1 << 30)
struct buffer_data_page {
- u64 time_stamp; /* page time stamp */
+ union {
+ struct buffer_data_page *next; /* for free pages */
+ u64 time_stamp; /* page time stamp */
+ };
local_t commit; /* write committed index */
unsigned char data[]; /* data of buffer page */
};
@@ -472,6 +477,10 @@ struct ring_buffer {
atomic_t record_disabled;
cpumask_var_t cpumask;
+ struct buffer_data_page *free_pages;
+ int nr_free_pages;
+ spinlock_t free_pages_lock;
+
struct lock_class_key *reader_lock_key;
struct mutex mutex;
@@ -1118,6 +1127,7 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
buffer->flags = flags;
buffer->clock = trace_clock_local;
buffer->reader_lock_key = key;
+ spin_lock_init(&buffer->free_pages_lock);
/* need at least two pages */
if (buffer->pages < 2)
@@ -1184,6 +1194,7 @@ EXPORT_SYMBOL_GPL(__ring_buffer_alloc);
void
ring_buffer_free(struct ring_buffer *buffer)
{
+ struct buffer_data_page *bpage;
int cpu;
get_online_cpus();
@@ -1200,6 +1211,11 @@ ring_buffer_free(struct ring_buffer *buffer)
kfree(buffer->buffers);
free_cpumask_var(buffer->cpumask);
+ while (buffer->free_pages) {
+ bpage = buffer->free_pages;
+ buffer->free_pages = bpage->next;
+ free_page((unsigned long)bpage);
+ };
kfree(buffer);
}
EXPORT_SYMBOL_GPL(ring_buffer_free);
@@ -3714,14 +3730,24 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
*/
void *ring_buffer_alloc_read_page(struct ring_buffer *buffer)
{
- struct buffer_data_page *bpage;
+ struct buffer_data_page *bpage = NULL;
unsigned long addr;
- addr = __get_free_page(GFP_KERNEL);
- if (!addr)
- return NULL;
+ spin_lock(&buffer->free_pages_lock);
+ if (buffer->free_pages) {
+ bpage = buffer->free_pages;
+ buffer->free_pages = bpage->next;
+ buffer->nr_free_pages--;
+ }
+ spin_unlock(&buffer->free_pages_lock);
- bpage = (void *)addr;
+ if (!bpage) {
+ addr = __get_free_page(GFP_KERNEL);
+ if (!addr)
+ return NULL;
+
+ bpage = (void *)addr;
+ }
rb_init_page(bpage);
@@ -3738,7 +3764,19 @@ EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page);
*/
void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data)
{
- free_page((unsigned long)data);
+ struct buffer_data_page *bpage = data;
+
+ spin_lock(&buffer->free_pages_lock);
+ if (buffer->nr_free_pages >= RB_MAX_FREE_PAGES) {
+ spin_unlock(&buffer->free_pages_lock);
+ free_page((unsigned long)data);
+ return;
+ }
+
+ bpage->next = buffer->free_pages;
+ buffer->free_pages = bpage;
+ buffer->nr_free_pages++;
+ spin_unlock(&buffer->free_pages_lock);
}
EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
--
1.7.0
^ permalink raw reply related [flat|nested] 19+ messages in thread* Re: [PATCH 12/13 v3] ring-buffer: Add cached pages when freeing reader page
2010-05-14 19:22 ` [PATCH 12/13 v3] ring-buffer: Add cached pages when freeing reader page Steven Rostedt
@ 2010-05-14 22:26 ` Mathieu Desnoyers
2010-05-15 1:06 ` Steven Rostedt
0 siblings, 1 reply; 19+ messages in thread
From: Mathieu Desnoyers @ 2010-05-14 22:26 UTC (permalink / raw)
To: Steven Rostedt
Cc: linux-kernel, Ingo Molnar, Andrew Morton, Frederic Weisbecker,
Masami Hiramatsu
* Steven Rostedt (rostedt@goodmis.org) wrote:
> From: Steven Rostedt <srostedt@redhat.com>
>
> When the pages are removed from the ring buffer for things like
> splice they are freed with ring_buffer_free_read_page().
> They are also allocated with ring_buffer_alloc_read_page().
>
> Currently the ring buffer does not take advantage of this situation.
> Every time the page is freed, the ring buffer simply frees it.
> When a new page is needed, it allocates it. This means that reading
> several pages with splice will cause a page to be freed and allocated
> several times. This is simply a waste.
>
> This patch adds a cache of the pages freed (16 max). This allows
> the pages to be reused quickly without need to go back to the memory
> pool.
Trying to understand the effect of splice() putting the page in the page
cache and how it affects this patch.
Basically, how do you know you can call free_page() from splice() in the
first place ? Answering this question will probably help us see if this
page reuse is OK.
Thanks,
Mathieu
>
> v2: Added in locking that should have been there in the first release.
>
> Reported-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
> ---
> kernel/trace/ring_buffer.c | 52 ++++++++++++++++++++++++++++++++++++++------
> 1 files changed, 45 insertions(+), 7 deletions(-)
>
> diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
> index 7f6059c..7aded7d 100644
> --- a/kernel/trace/ring_buffer.c
> +++ b/kernel/trace/ring_buffer.c
> @@ -157,6 +157,8 @@ static unsigned long ring_buffer_flags __read_mostly = RB_BUFFERS_ON;
>
> #define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data)
>
> +#define RB_MAX_FREE_PAGES 16
> +
> /**
> * tracing_on - enable all tracing buffers
> *
> @@ -325,7 +327,10 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
> #define RB_MISSED_STORED (1 << 30)
>
> struct buffer_data_page {
> - u64 time_stamp; /* page time stamp */
> + union {
> + struct buffer_data_page *next; /* for free pages */
> + u64 time_stamp; /* page time stamp */
> + };
> local_t commit; /* write committed index */
> unsigned char data[]; /* data of buffer page */
> };
> @@ -472,6 +477,10 @@ struct ring_buffer {
> atomic_t record_disabled;
> cpumask_var_t cpumask;
>
> + struct buffer_data_page *free_pages;
> + int nr_free_pages;
> + spinlock_t free_pages_lock;
> +
> struct lock_class_key *reader_lock_key;
>
> struct mutex mutex;
> @@ -1118,6 +1127,7 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
> buffer->flags = flags;
> buffer->clock = trace_clock_local;
> buffer->reader_lock_key = key;
> + spin_lock_init(&buffer->free_pages_lock);
>
> /* need at least two pages */
> if (buffer->pages < 2)
> @@ -1184,6 +1194,7 @@ EXPORT_SYMBOL_GPL(__ring_buffer_alloc);
> void
> ring_buffer_free(struct ring_buffer *buffer)
> {
> + struct buffer_data_page *bpage;
> int cpu;
>
> get_online_cpus();
> @@ -1200,6 +1211,11 @@ ring_buffer_free(struct ring_buffer *buffer)
> kfree(buffer->buffers);
> free_cpumask_var(buffer->cpumask);
>
> + while (buffer->free_pages) {
> + bpage = buffer->free_pages;
> + buffer->free_pages = bpage->next;
> + free_page((unsigned long)bpage);
> + };
> kfree(buffer);
> }
> EXPORT_SYMBOL_GPL(ring_buffer_free);
> @@ -3714,14 +3730,24 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
> */
> void *ring_buffer_alloc_read_page(struct ring_buffer *buffer)
> {
> - struct buffer_data_page *bpage;
> + struct buffer_data_page *bpage = NULL;
> unsigned long addr;
>
> - addr = __get_free_page(GFP_KERNEL);
> - if (!addr)
> - return NULL;
> + spin_lock(&buffer->free_pages_lock);
> + if (buffer->free_pages) {
> + bpage = buffer->free_pages;
> + buffer->free_pages = bpage->next;
> + buffer->nr_free_pages--;
> + }
> + spin_unlock(&buffer->free_pages_lock);
>
> - bpage = (void *)addr;
> + if (!bpage) {
> + addr = __get_free_page(GFP_KERNEL);
> + if (!addr)
> + return NULL;
> +
> + bpage = (void *)addr;
> + }
>
> rb_init_page(bpage);
>
> @@ -3738,7 +3764,19 @@ EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page);
> */
> void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data)
> {
> - free_page((unsigned long)data);
> + struct buffer_data_page *bpage = data;
> +
> + spin_lock(&buffer->free_pages_lock);
> + if (buffer->nr_free_pages >= RB_MAX_FREE_PAGES) {
> + spin_unlock(&buffer->free_pages_lock);
> + free_page((unsigned long)data);
> + return;
> + }
> +
> + bpage->next = buffer->free_pages;
> + buffer->free_pages = bpage;
> + buffer->nr_free_pages++;
> + spin_unlock(&buffer->free_pages_lock);
> }
> EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
>
> --
> 1.7.0
>
>
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
^ permalink raw reply [flat|nested] 19+ messages in thread* Re: [PATCH 12/13 v3] ring-buffer: Add cached pages when freeing reader page
2010-05-14 22:26 ` Mathieu Desnoyers
@ 2010-05-15 1:06 ` Steven Rostedt
0 siblings, 0 replies; 19+ messages in thread
From: Steven Rostedt @ 2010-05-15 1:06 UTC (permalink / raw)
To: Mathieu Desnoyers
Cc: linux-kernel, Ingo Molnar, Andrew Morton, Frederic Weisbecker,
Masami Hiramatsu, Peter Zijlstra
[ Added Peter Zijlsta since he had an interest in this topic ]
On Fri, 2010-05-14 at 18:26 -0400, Mathieu Desnoyers wrote:
> * Steven Rostedt (rostedt@goodmis.org) wrote:
> Trying to understand the effect of splice() putting the page in the page
> cache and how it affects this patch.
>
> Basically, how do you know you can call free_page() from splice() in the
> first place ? Answering this question will probably help us see if this
> page reuse is OK.
Actually, looking at the code, I'm not sure this is safe. I was thinking
that free_page() would always free the page. But I forgot that pages
have a ref count. And a get_page() will prevent a page from freeing.
So I need to revert this patch, or rather, make a core-5 that removes
this patch and fixes the spelling in the comment.
I can later add something that checks the page ref count, but that can
wait till .36.
-- Steve
^ permalink raw reply [flat|nested] 19+ messages in thread
* [PATCH 13/13 v3] tracing: Comment the use of event_mutex with trace event flags
2010-05-14 19:22 [PATCH 00/13 v3] [GIT PULL] tracing: shrinking trace events and updates Steven Rostedt
` (11 preceding siblings ...)
2010-05-14 19:22 ` [PATCH 12/13 v3] ring-buffer: Add cached pages when freeing reader page Steven Rostedt
@ 2010-05-14 19:22 ` Steven Rostedt
2010-05-14 22:21 ` Mathieu Desnoyers
12 siblings, 1 reply; 19+ messages in thread
From: Steven Rostedt @ 2010-05-14 19:22 UTC (permalink / raw)
To: linux-kernel
Cc: Ingo Molnar, Andrew Morton, Frederic Weisbecker,
Mathieu Desnoyers, Masami Hiramatsu, Tom Zanussi
[-- Attachment #1: 0013-tracing-Comment-the-use-of-event_mutex-with-trace-ev.patch --]
[-- Type: text/plain, Size: 2224 bytes --]
From: Steven Rostedt <srostedt@redhat.com>
The flags variable is protected by the event_mutex when modifying,
but the event_mutex is not held when reading the variable.
This is due to the fact that the reads occur in critical sections where
taking a mutex (or even a spinlock) is not wanted.
But the two flags that exist (enable and filter_active) have the code
written as such to handle the reads to not need a lock.
The enable flag is used just to know if the event is enabled or not
and its use is always under the event_mutex. Whether or not the event
is actually enabled is really determined by the tracepoint being
registered. The flag is just a way to let the code know if the tracepoint
is registered.
The filter_active is different. It is read without the lock. If it
is set, then the event probes jump to the filter code. There can be a
slight mismatch between filters available and filter_active. If the flag is
set but no filters are available, the code safely jumps to a filter nop.
If the flag is not set and the filters are available, then the filters
are skipped. This is acceptable since filters are usually set before
tracing or they are set by humans, which would not notice the slight
delay that this causes.
Reported-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
include/linux/ftrace_event.h | 9 ++++++++-
1 files changed, 8 insertions(+), 1 deletions(-)
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 5ac97a4..3578e90 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -169,7 +169,14 @@ struct ftrace_event_call {
* bit 1: enabled
* bit 2: filter_active
*
- * Must hold event_mutex to change.
+ * Changes to flags must hold the event_mutex.
+ *
+ * Note: Reads of flags do not hold the event_mutex since
+ * they occur in critical sections. But the way flags
+ * is currently used, these changes do no affect the code
+ * except that when a change is made, it may have a slight
+ * delay in propagating the changes to other CPUs due to
+ * cacheing and such.
*/
unsigned int flags;
--
1.7.0
^ permalink raw reply related [flat|nested] 19+ messages in thread* Re: [PATCH 13/13 v3] tracing: Comment the use of event_mutex with trace event flags
2010-05-14 19:22 ` [PATCH 13/13 v3] tracing: Comment the use of event_mutex with trace event flags Steven Rostedt
@ 2010-05-14 22:21 ` Mathieu Desnoyers
2010-05-15 0:44 ` Steven Rostedt
0 siblings, 1 reply; 19+ messages in thread
From: Mathieu Desnoyers @ 2010-05-14 22:21 UTC (permalink / raw)
To: Steven Rostedt
Cc: linux-kernel, Ingo Molnar, Andrew Morton, Frederic Weisbecker,
Masami Hiramatsu, Tom Zanussi
* Steven Rostedt (rostedt@goodmis.org) wrote:
> From: Steven Rostedt <srostedt@redhat.com>
>
> The flags variable is protected by the event_mutex when modifying,
> but the event_mutex is not held when reading the variable.
>
> This is due to the fact that the reads occur in critical sections where
> taking a mutex (or even a spinlock) is not wanted.
>
> But the two flags that exist (enable and filter_active) have the code
> written as such to handle the reads to not need a lock.
>
> The enable flag is used just to know if the event is enabled or not
> and its use is always under the event_mutex. Whether or not the event
> is actually enabled is really determined by the tracepoint being
> registered. The flag is just a way to let the code know if the tracepoint
> is registered.
>
> The filter_active is different. It is read without the lock. If it
> is set, then the event probes jump to the filter code. There can be a
> slight mismatch between filters available and filter_active. If the flag is
> set but no filters are available, the code safely jumps to a filter nop.
> If the flag is not set and the filters are available, then the filters
> are skipped. This is acceptable since filters are usually set before
> tracing or they are set by humans, which would not notice the slight
> delay that this causes.
>
> Reported-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
> Cc: Tom Zanussi <tzanussi@gmail.com>
> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
> ---
> include/linux/ftrace_event.h | 9 ++++++++-
> 1 files changed, 8 insertions(+), 1 deletions(-)
>
> diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
> index 5ac97a4..3578e90 100644
> --- a/include/linux/ftrace_event.h
> +++ b/include/linux/ftrace_event.h
> @@ -169,7 +169,14 @@ struct ftrace_event_call {
> * bit 1: enabled
> * bit 2: filter_active
> *
> - * Must hold event_mutex to change.
> + * Changes to flags must hold the event_mutex.
> + *
> + * Note: Reads of flags do not hold the event_mutex since
> + * they occur in critical sections. But the way flags
> + * is currently used, these changes do no affect the code
> + * except that when a change is made, it may have a slight
> + * delay in propagating the changes to other CPUs due to
> + * cacheing and such.
cacheing -> caching ?
Besides this minor nit:
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
> */
> unsigned int flags;
>
> --
> 1.7.0
>
>
--
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
^ permalink raw reply [flat|nested] 19+ messages in thread* Re: [PATCH 13/13 v3] tracing: Comment the use of event_mutex with trace event flags
2010-05-14 22:21 ` Mathieu Desnoyers
@ 2010-05-15 0:44 ` Steven Rostedt
0 siblings, 0 replies; 19+ messages in thread
From: Steven Rostedt @ 2010-05-15 0:44 UTC (permalink / raw)
To: Mathieu Desnoyers
Cc: linux-kernel, Ingo Molnar, Andrew Morton, Frederic Weisbecker,
Masami Hiramatsu, Tom Zanussi
On Fri, 2010-05-14 at 18:21 -0400, Mathieu Desnoyers wrote:
> * Steven Rostedt (rostedt@goodmis.org) wrote:
> > + * Note: Reads of flags do not hold the event_mutex since
> > + * they occur in critical sections. But the way flags
> > + * is currently used, these changes do no affect the code
> > + * except that when a change is made, it may have a slight
> > + * delay in propagating the changes to other CPUs due to
> > + * cacheing and such.
>
> cacheing -> caching ?
hehe, I need spellcheck. I first wrote "caching", and thought to myself,
that looked wrong. Then I added the 'e'. Oh well.
>
> Besides this minor nit:
>
> Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Thanks!
-- Steve
>
> > */
> > unsigned int flags;
> >
> > --
> > 1.7.0
> >
> >
>
^ permalink raw reply [flat|nested] 19+ messages in thread