[PATCH 0/9] [GI PULL][2.6.36] tracing: various updates

[PATCH 0/9] [GI PULL][2.6.36] tracing: various updates

[Steven Rostedt]

Ingo,

I pushed some of these to you before, but you wanted to wait
till after the merge window to pull them.

The last patch is the full fix for the perf kprobe regression. But
since it was too big of a change for the -rc release we did
a quick fix. This reverts that change back to the true fix for
2.6.36.

Please pull the latest tip/perf/core tree, which can be found at:

  git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
tip/perf/core


Chase Douglas (1):
      tracing/function-graph: Use correct string size for snprintf

Li Zefan (7):
      tracing: Use a global field list for all syscall exit events
      tracing: Don't allocate common fields for every trace events
      tracing: Convert some timer events to DEFINE_EVENT
      tracing: Convert more sched events to DEFINE_EVENT
      tracing: Remove test of NULL define_fields callback
      tracing: Remove redundant raw_init callbacks
      tracing: Remove open-coded __trace_add_event_call()

Steven Rostedt (1):
      tracing: Use class->reg() for all registering of events

----
 include/linux/ftrace_event.h         |    3 +
 include/linux/syscalls.h             |    2 -
 include/trace/events/sched.h         |   32 +----
 include/trace/events/timer.h         |   80 ++++------
 include/trace/ftrace.h               |    2 +
 include/trace/syscall.h              |    1 -
 kernel/trace/trace.h                 |    2 +
 kernel/trace/trace_event_perf.c      |   19 +--
 kernel/trace/trace_events.c          |  264 +++++++++++++++++-----------------
 kernel/trace/trace_events_filter.c   |   27 ++--
 kernel/trace/trace_export.c          |    8 +-
 kernel/trace/trace_functions_graph.c |    3 +-
 kernel/trace/trace_kprobe.c          |   10 +--
 kernel/trace/trace_syscalls.c        |    7 +-
 14 files changed, 203 insertions(+), 257 deletions(-)

[PATCH 1/9] tracing: Use a global field list for all syscall exit events

[Steven Rostedt]

[-- Attachment #1: 0001-tracing-Use-a-global-field-list-for-all-syscall-exit.patch --]
[-- Type: text/plain, Size: 2827 bytes --]

From: Li Zefan <lizf@cn.fujitsu.com>

All syscall exit events have the same fields.

The kernel size drops 2.5K:

   text    data     bss     dec     hex filename
7018612 2034376 7251132 16304120         f8c7f8 vmlinux.o.orig
7018612 2031888 7251132 16301632         f8be40 vmlinux.o

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <4BFA3746.8070100@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/syscalls.h      |    2 --
 include/trace/syscall.h       |    1 -
 kernel/trace/trace_syscalls.c |    7 ++++---
 3 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 7f614ce..7994bd4 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -165,7 +165,6 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.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)					\
@@ -180,7 +179,6 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.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/syscall.h b/include/trace/syscall.h
index 257e089..31966a4 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -26,7 +26,6 @@ struct syscall_metadata {
 	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;
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 34e3580..bac752f 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -23,6 +23,9 @@ static int syscall_exit_register(struct ftrace_event_call *event,
 static int syscall_enter_define_fields(struct ftrace_event_call *call);
 static int syscall_exit_define_fields(struct ftrace_event_call *call);
 
+/* All syscall exit events have the same fields */
+static LIST_HEAD(syscall_exit_fields);
+
 static struct list_head *
 syscall_get_enter_fields(struct ftrace_event_call *call)
 {
@@ -34,9 +37,7 @@ syscall_get_enter_fields(struct ftrace_event_call *call)
 static struct list_head *
 syscall_get_exit_fields(struct ftrace_event_call *call)
 {
-	struct syscall_metadata *entry = call->data;
-
-	return &entry->exit_fields;
+	return &syscall_exit_fields;
 }
 
 struct trace_event_functions enter_syscall_print_funcs = {
-- 
1.7.1

[PATCH 2/9] tracing: Dont allocate common fields for every trace events

[Steven Rostedt]

[-- Attachment #1: 0002-tracing-Don-t-allocate-common-fields-for-every-trace.patch --]
[-- Type: text/plain, Size: 7700 bytes --]

From: Li Zefan <lizf@cn.fujitsu.com>

Every event has the same common fields, so it's a big waste of
memory to have a copy of those fields for every event.

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <4BFA3759.30105@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.h               |    2 +
 kernel/trace/trace_events.c        |  113 ++++++++++++++++++++----------------
 kernel/trace/trace_events_filter.c |   18 +++++-
 3 files changed, 81 insertions(+), 52 deletions(-)

diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 01ce088..cc90ccd 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -698,6 +698,8 @@ struct filter_pred {
 	int 			pop_n;
 };
 
+extern struct list_head ftrace_common_fields;
+
 extern enum regex_type
 filter_parse_regex(char *buff, int len, char **search, int *not);
 extern void print_event_filter(struct ftrace_event_call *call,
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index a594f9a..d3b4bdf 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -28,6 +28,7 @@
 DEFINE_MUTEX(event_mutex);
 
 LIST_HEAD(ftrace_events);
+LIST_HEAD(ftrace_common_fields);
 
 struct list_head *
 trace_get_fields(struct ftrace_event_call *event_call)
@@ -37,15 +38,11 @@ trace_get_fields(struct ftrace_event_call *event_call)
 	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)
+static int __trace_define_field(struct list_head *head, 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)
@@ -68,7 +65,6 @@ int trace_define_field(struct ftrace_event_call *call, const char *type,
 	field->size = size;
 	field->is_signed = is_signed;
 
-	head = trace_get_fields(call);
 	list_add(&field->link, head);
 
 	return 0;
@@ -80,17 +76,32 @@ err:
 
 	return -ENOMEM;
 }
+
+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 list_head *head;
+
+	if (WARN_ON(!call->class))
+		return 0;
+
+	head = trace_get_fields(call);
+	return __trace_define_field(head, type, name, offset, size,
+				    is_signed, filter_type);
+}
 EXPORT_SYMBOL_GPL(trace_define_field);
 
 #define __common_field(type, item)					\
-	ret = trace_define_field(call, #type, "common_" #item,		\
-				 offsetof(typeof(ent), item),		\
-				 sizeof(ent.item),			\
-				 is_signed_type(type), FILTER_OTHER);	\
+	ret = __trace_define_field(&ftrace_common_fields, #type,	\
+				   "common_" #item,			\
+				   offsetof(typeof(ent), item),		\
+				   sizeof(ent.item),			\
+				   is_signed_type(type), FILTER_OTHER);	\
 	if (ret)							\
 		return ret;
 
-static int trace_define_common_fields(struct ftrace_event_call *call)
+static int trace_define_common_fields(void)
 {
 	int ret;
 	struct trace_entry ent;
@@ -544,32 +555,10 @@ out:
 	return ret;
 }
 
-static ssize_t
-event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
-		  loff_t *ppos)
+static void print_event_fields(struct trace_seq *s, struct list_head *head)
 {
-	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;
-	int r = 0;
-
-	if (*ppos)
-		return 0;
-
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
-	if (!s)
-		return -ENOMEM;
-
-	trace_seq_init(s);
 
-	trace_seq_printf(s, "name: %s\n", call->name);
-	trace_seq_printf(s, "ID: %d\n", call->event.type);
-	trace_seq_printf(s, "format:\n");
-
-	head = trace_get_fields(call);
 	list_for_each_entry_reverse(field, head, link) {
 		/*
 		 * Smartly shows the array type(except dynamic array).
@@ -584,29 +573,54 @@ event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
 			array_descriptor = NULL;
 
 		if (!array_descriptor) {
-			r = trace_seq_printf(s, "\tfield:%s %s;\toffset:%u;"
+			trace_seq_printf(s, "\tfield:%s %s;\toffset:%u;"
 					"\tsize:%u;\tsigned:%d;\n",
 					field->type, field->name, field->offset,
 					field->size, !!field->is_signed);
 		} else {
-			r = trace_seq_printf(s, "\tfield:%.*s %s%s;\toffset:%u;"
+			trace_seq_printf(s, "\tfield:%.*s %s%s;\toffset:%u;"
 					"\tsize:%u;\tsigned:%d;\n",
 					(int)(array_descriptor - field->type),
 					field->type, field->name,
 					array_descriptor, field->offset,
 					field->size, !!field->is_signed);
 		}
+	}
+}
 
-		if (--common_field_count == 0)
-			r = trace_seq_printf(s, "\n");
+static ssize_t
+event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
+		  loff_t *ppos)
+{
+	struct ftrace_event_call *call = filp->private_data;
+	struct list_head *head;
+	struct trace_seq *s;
+	char *buf;
+	int r;
 
-		if (!r)
-			break;
-	}
+	if (*ppos)
+		return 0;
 
-	if (r)
-		r = trace_seq_printf(s, "\nprint fmt: %s\n",
-				call->print_fmt);
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	trace_seq_init(s);
+
+	trace_seq_printf(s, "name: %s\n", call->name);
+	trace_seq_printf(s, "ID: %d\n", call->event.type);
+	trace_seq_printf(s, "format:\n");
+
+	/* print common fields */
+	print_event_fields(s, &ftrace_common_fields);
+
+	trace_seq_putc(s, '\n');
+
+	/* print event specific fields */
+	head = trace_get_fields(call);
+	print_event_fields(s, head);
+
+	r = trace_seq_printf(s, "\nprint fmt: %s\n", call->print_fmt);
 
 	if (!r) {
 		/*
@@ -980,9 +994,7 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 		 */
 		head = trace_get_fields(call);
 		if (list_empty(head)) {
-			ret = trace_define_common_fields(call);
-			if (!ret)
-				ret = call->class->define_fields(call);
+			ret = call->class->define_fields(call);
 			if (ret < 0) {
 				pr_warning("Could not initialize trace point"
 					   " events/%s\n", call->name);
@@ -1319,6 +1331,9 @@ static __init int event_trace_init(void)
 	trace_create_file("enable", 0644, d_events,
 			  NULL, &ftrace_system_enable_fops);
 
+	if (trace_define_common_fields())
+		pr_warning("tracing: Failed to allocate common fields");
+
 	for_each_event(call, __start_ftrace_events, __stop_ftrace_events) {
 		/* The linker may leave blanks */
 		if (!call->name)
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 57bb1bb..330fefd 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -497,12 +497,10 @@ void print_subsystem_event_filter(struct event_subsystem *system,
 }
 
 static struct ftrace_event_field *
-find_event_field(struct ftrace_event_call *call, char *name)
+__find_event_field(struct list_head *head, char *name)
 {
 	struct ftrace_event_field *field;
-	struct list_head *head;
 
-	head = trace_get_fields(call);
 	list_for_each_entry(field, head, link) {
 		if (!strcmp(field->name, name))
 			return field;
@@ -511,6 +509,20 @@ find_event_field(struct ftrace_event_call *call, char *name)
 	return NULL;
 }
 
+static struct ftrace_event_field *
+find_event_field(struct ftrace_event_call *call, char *name)
+{
+	struct ftrace_event_field *field;
+	struct list_head *head;
+
+	field = __find_event_field(&ftrace_common_fields, name);
+	if (field)
+		return field;
+
+	head = trace_get_fields(call);
+	return __find_event_field(head, name);
+}
+
 static void filter_free_pred(struct filter_pred *pred)
 {
 	if (!pred)
-- 
1.7.1

[PATCH 3/9] tracing: Convert some timer events to DEFINE_EVENT

[Steven Rostedt]

[-- Attachment #1: 0003-tracing-Convert-some-timer-events-to-DEFINE_EVENT.patch --]
[-- Type: text/plain, Size: 3914 bytes --]

From: Li Zefan <lizf@cn.fujitsu.com>

Use DECLARE_EVENT_CLASS, and save ~2.3K:

   text    data     bss     dec     hex filename
7018823 2031888 7251132 16301843         f8bf13 vmlinux.o.orig
7016727 2031696 7251132 16299555         f8b623 vmlinux.o

5 events are converted:

  timer_class:   timer_init, timer_expire_exit, timer_cancel
  hrtimer_class: hrtimer_init, hrtimer_cancel

No change in functionality.

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <4BFA3773.3060200@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/trace/events/timer.h |   80 +++++++++++++++++-------------------------
 1 files changed, 32 insertions(+), 48 deletions(-)

diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index 9496b96..c624126 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -8,11 +8,7 @@
 #include <linux/hrtimer.h>
 #include <linux/timer.h>
 
-/**
- * timer_init - called when the timer is initialized
- * @timer:	pointer to struct timer_list
- */
-TRACE_EVENT(timer_init,
+DECLARE_EVENT_CLASS(timer_class,
 
 	TP_PROTO(struct timer_list *timer),
 
@@ -30,6 +26,17 @@ TRACE_EVENT(timer_init,
 );
 
 /**
+ * timer_init - called when the timer is initialized
+ * @timer:	pointer to struct timer_list
+ */
+DEFINE_EVENT(timer_class, timer_init,
+
+	TP_PROTO(struct timer_list *timer),
+
+	TP_ARGS(timer)
+);
+
+/**
  * timer_start - called when the timer is started
  * @timer:	pointer to struct timer_list
  * @expires:	the timers expiry time
@@ -94,42 +101,22 @@ TRACE_EVENT(timer_expire_entry,
  * NOTE: Do NOT derefernce timer in TP_fast_assign. The pointer might
  * be invalid. We solely track the pointer.
  */
-TRACE_EVENT(timer_expire_exit,
+DEFINE_EVENT(timer_class, timer_expire_exit,
 
 	TP_PROTO(struct timer_list *timer),
 
-	TP_ARGS(timer),
-
-	TP_STRUCT__entry(
-		__field(void *,	timer	)
-	),
-
-	TP_fast_assign(
-		__entry->timer	= timer;
-	),
-
-	TP_printk("timer=%p", __entry->timer)
+	TP_ARGS(timer)
 );
 
 /**
  * timer_cancel - called when the timer is canceled
  * @timer:	pointer to struct timer_list
  */
-TRACE_EVENT(timer_cancel,
+DEFINE_EVENT(timer_class, timer_cancel,
 
 	TP_PROTO(struct timer_list *timer),
 
-	TP_ARGS(timer),
-
-	TP_STRUCT__entry(
-		__field( void *,	timer	)
-	),
-
-	TP_fast_assign(
-		__entry->timer	= timer;
-	),
-
-	TP_printk("timer=%p", __entry->timer)
+	TP_ARGS(timer)
 );
 
 /**
@@ -224,14 +211,7 @@ TRACE_EVENT(hrtimer_expire_entry,
 		  (unsigned long long)ktime_to_ns((ktime_t) { .tv64 = __entry->now }))
  );
 
-/**
- * hrtimer_expire_exit - called immediately after the hrtimer callback returns
- * @timer:	pointer to struct hrtimer
- *
- * When used in combination with the hrtimer_expire_entry tracepoint we can
- * determine the runtime of the callback function.
- */
-TRACE_EVENT(hrtimer_expire_exit,
+DECLARE_EVENT_CLASS(hrtimer_class,
 
 	TP_PROTO(struct hrtimer *hrtimer),
 
@@ -249,24 +229,28 @@ TRACE_EVENT(hrtimer_expire_exit,
 );
 
 /**
- * hrtimer_cancel - called when the hrtimer is canceled
- * @hrtimer:	pointer to struct hrtimer
+ * hrtimer_expire_exit - called immediately after the hrtimer callback returns
+ * @timer:	pointer to struct hrtimer
+ *
+ * When used in combination with the hrtimer_expire_entry tracepoint we can
+ * determine the runtime of the callback function.
  */
-TRACE_EVENT(hrtimer_cancel,
+DEFINE_EVENT(hrtimer_class, hrtimer_expire_exit,
 
 	TP_PROTO(struct hrtimer *hrtimer),
 
-	TP_ARGS(hrtimer),
+	TP_ARGS(hrtimer)
+);
 
-	TP_STRUCT__entry(
-		__field( void *,	hrtimer	)
-	),
+/**
+ * hrtimer_cancel - called when the hrtimer is canceled
+ * @hrtimer:	pointer to struct hrtimer
+ */
+DEFINE_EVENT(hrtimer_class, hrtimer_cancel,
 
-	TP_fast_assign(
-		__entry->hrtimer	= hrtimer;
-	),
+	TP_PROTO(struct hrtimer *hrtimer),
 
-	TP_printk("hrtimer=%p", __entry->hrtimer)
+	TP_ARGS(hrtimer)
 );
 
 /**
-- 
1.7.1

[PATCH 4/9] tracing: Convert more sched events to DEFINE_EVENT

[Steven Rostedt]

[-- Attachment #1: 0004-tracing-Convert-more-sched-events-to-DEFINE_EVENT.patch --]
[-- Type: text/plain, Size: 1727 bytes --]

From: Li Zefan <lizf@cn.fujitsu.com>

Convert sched_wait_task to DEFINE_EVENT, and save ~1K:

   text    data     bss     dec     hex filename
 104595    9424    4992  119011   1d0e3 kernel/sched.o.orig
 103619    9344    4992  117955   1ccc3 kernel/sched.o

No change in functionality.

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <4BFA3787.2040800@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/trace/events/sched.h |   32 +++++++-------------------------
 1 files changed, 7 insertions(+), 25 deletions(-)

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index b9e1dd6..9208c92 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -50,31 +50,6 @@ TRACE_EVENT(sched_kthread_stop_ret,
 );
 
 /*
- * Tracepoint for waiting on task to unschedule:
- */
-TRACE_EVENT(sched_wait_task,
-
-	TP_PROTO(struct task_struct *p),
-
-	TP_ARGS(p),
-
-	TP_STRUCT__entry(
-		__array(	char,	comm,	TASK_COMM_LEN	)
-		__field(	pid_t,	pid			)
-		__field(	int,	prio			)
-	),
-
-	TP_fast_assign(
-		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
-		__entry->pid	= p->pid;
-		__entry->prio	= p->prio;
-	),
-
-	TP_printk("comm=%s pid=%d prio=%d",
-		  __entry->comm, __entry->pid, __entry->prio)
-);
-
-/*
  * Tracepoint for waking up a task:
  */
 DECLARE_EVENT_CLASS(sched_wakeup_template,
@@ -240,6 +215,13 @@ DEFINE_EVENT(sched_process_template, sched_process_exit,
 	     TP_ARGS(p));
 
 /*
+ * Tracepoint for waiting on task to unschedule:
+ */
+DEFINE_EVENT(sched_process_template, sched_wait_task,
+	TP_PROTO(struct task_struct *p),
+	TP_ARGS(p));
+
+/*
  * Tracepoint for a waiting task:
  */
 TRACE_EVENT(sched_process_wait,
-- 
1.7.1

[PATCH 5/9] tracing: Remove test of NULL define_fields callback

[Steven Rostedt]

[-- Attachment #1: 0005-tracing-Remove-test-of-NULL-define_fields-callback.patch --]
[-- Type: text/plain, Size: 2833 bytes --]

From: Li Zefan <lizf@cn.fujitsu.com>

Every event (or event class) has it's define_fields callback,
so the test is redundant.

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <4BFA37BC.8080707@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c        |   28 +++++++++++++---------------
 kernel/trace/trace_events_filter.c |    9 ---------
 2 files changed, 13 insertions(+), 24 deletions(-)

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index d3b4bdf..5bad9cb 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -987,23 +987,21 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 		 		  id);
 #endif
 
-	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 = call->class->define_fields(call);
-			if (ret < 0) {
-				pr_warning("Could not initialize trace point"
-					   " events/%s\n", call->name);
-				return ret;
-			}
+	/*
+	 * 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 = 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);
 	}
+	trace_create_file("filter", 0644, call->dir, call,
+			  filter);
 
 	trace_create_file("format", 0444, call->dir, call,
 			  format);
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 330fefd..36d4010 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -639,9 +639,6 @@ static int init_subsystem_preds(struct event_subsystem *system)
 	int err;
 
 	list_for_each_entry(call, &ftrace_events, list) {
-		if (!call->class || !call->class->define_fields)
-			continue;
-
 		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
@@ -658,9 +655,6 @@ 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->class || !call->class->define_fields)
-			continue;
-
 		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
@@ -1263,9 +1257,6 @@ 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->class || !call->class->define_fields)
-			continue;
-
 		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
-- 
1.7.1

[PATCH 6/9] tracing: Remove redundant raw_init callbacks

[Steven Rostedt]

[-- Attachment #1: 0006-tracing-Remove-redundant-raw_init-callbacks.patch --]
[-- Type: text/plain, Size: 2320 bytes --]

From: Li Zefan <lizf@cn.fujitsu.com>

raw_init callback is optional.

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <4BFA37D4.7070500@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace_export.c |    8 +-------
 kernel/trace/trace_kprobe.c |   10 +---------
 2 files changed, 2 insertions(+), 16 deletions(-)

diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 8536e2a..4ba44de 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -125,12 +125,6 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call)	\
 
 #include "trace_entries.h"
 
-static int ftrace_raw_init_event(struct ftrace_event_call *call)
-{
-	INIT_LIST_HEAD(&call->class->fields);
-	return 0;
-}
-
 #undef __entry
 #define __entry REC
 
@@ -158,7 +152,7 @@ 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,		\
+	.fields			= LIST_HEAD_INIT(event_class_ftrace_##call.fields),\
 };									\
 									\
 struct ftrace_event_call __used						\
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index f52b5f5..3b831d8 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1214,11 +1214,6 @@ static void probe_event_disable(struct ftrace_event_call *call)
 	}
 }
 
-static int probe_event_raw_init(struct ftrace_event_call *event_call)
-{
-	return 0;
-}
-
 #undef DEFINE_FIELD
 #define DEFINE_FIELD(type, item, name, is_signed)			\
 	do {								\
@@ -1486,15 +1481,12 @@ static int register_probe_event(struct trace_probe *tp)
 	int ret;
 
 	/* Initialize ftrace_event_call */
+	INIT_LIST_HEAD(&call->class->fields);
 	if (probe_is_return(tp)) {
-		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);
 		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)
-- 
1.7.1

[PATCH 7/9] tracing: Remove open-coded __trace_add_event_call()

[Steven Rostedt]

[-- Attachment #1: 0007-tracing-Remove-open-coded-__trace_add_event_call.patch --]
[-- Type: text/plain, Size: 4487 bytes --]

From: Li Zefan <lizf@cn.fujitsu.com>

Let trace_module_add_events() and event_trace_init() call
__trace_add_event_call().

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <4BFA37E9.1020106@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c |   70 +++++++++++-------------------------------
 1 files changed, 19 insertions(+), 51 deletions(-)

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 5bad9cb..69bee4c 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1009,11 +1009,17 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 	return 0;
 }
 
-static int __trace_add_event_call(struct ftrace_event_call *call)
+static int
+__trace_add_event_call(struct ftrace_event_call *call, struct module *mod,
+		       const struct file_operations *id,
+		       const struct file_operations *enable,
+		       const struct file_operations *filter,
+		       const struct file_operations *format)
 {
 	struct dentry *d_events;
 	int ret;
 
+	/* The linker may leave blanks */
 	if (!call->name)
 		return -EINVAL;
 
@@ -1021,8 +1027,8 @@ static int __trace_add_event_call(struct ftrace_event_call *call)
 		ret = call->class->raw_init(call);
 		if (ret < 0) {
 			if (ret != -ENOSYS)
-				pr_warning("Could not initialize trace "
-				"events/%s\n", call->name);
+				pr_warning("Could not initialize trace events/%s\n",
+					   call->name);
 			return ret;
 		}
 	}
@@ -1031,11 +1037,10 @@ static int __trace_add_event_call(struct ftrace_event_call *call)
 	if (!d_events)
 		return -ENOENT;
 
-	ret = event_create_dir(call, d_events, &ftrace_event_id_fops,
-				&ftrace_enable_fops, &ftrace_event_filter_fops,
-				&ftrace_event_format_fops);
+	ret = event_create_dir(call, d_events, id, enable, filter, format);
 	if (!ret)
 		list_add(&call->list, &ftrace_events);
+	call->mod = mod;
 
 	return ret;
 }
@@ -1045,7 +1050,10 @@ int trace_add_event_call(struct ftrace_event_call *call)
 {
 	int ret;
 	mutex_lock(&event_mutex);
-	ret = __trace_add_event_call(call);
+	ret = __trace_add_event_call(call, NULL, &ftrace_event_id_fops,
+				     &ftrace_enable_fops,
+				     &ftrace_event_filter_fops,
+				     &ftrace_event_format_fops);
 	mutex_unlock(&event_mutex);
 	return ret;
 }
@@ -1162,8 +1170,6 @@ static void trace_module_add_events(struct module *mod)
 {
 	struct ftrace_module_file_ops *file_ops = NULL;
 	struct ftrace_event_call *call, *start, *end;
-	struct dentry *d_events;
-	int ret;
 
 	start = mod->trace_events;
 	end = mod->trace_events + mod->num_trace_events;
@@ -1171,38 +1177,14 @@ static void trace_module_add_events(struct module *mod)
 	if (start == end)
 		return;
 
-	d_events = event_trace_events_dir();
-	if (!d_events)
+	file_ops = trace_create_file_ops(mod);
+	if (!file_ops)
 		return;
 
 	for_each_event(call, start, end) {
-		/* The linker may leave blanks */
-		if (!call->name)
-			continue;
-		if (call->class->raw_init) {
-			ret = call->class->raw_init(call);
-			if (ret < 0) {
-				if (ret != -ENOSYS)
-					pr_warning("Could not initialize trace "
-					"point events/%s\n", call->name);
-				continue;
-			}
-		}
-		/*
-		 * This module has events, create file ops for this module
-		 * if not already done.
-		 */
-		if (!file_ops) {
-			file_ops = trace_create_file_ops(mod);
-			if (!file_ops)
-				return;
-		}
-		call->mod = mod;
-		ret = event_create_dir(call, d_events,
+		__trace_add_event_call(call, mod,
 				       &file_ops->id, &file_ops->enable,
 				       &file_ops->filter, &file_ops->format);
-		if (!ret)
-			list_add(&call->list, &ftrace_events);
 	}
 }
 
@@ -1333,24 +1315,10 @@ static __init int event_trace_init(void)
 		pr_warning("tracing: Failed to allocate common fields");
 
 	for_each_event(call, __start_ftrace_events, __stop_ftrace_events) {
-		/* The linker may leave blanks */
-		if (!call->name)
-			continue;
-		if (call->class->raw_init) {
-			ret = call->class->raw_init(call);
-			if (ret < 0) {
-				if (ret != -ENOSYS)
-					pr_warning("Could not initialize trace "
-					"point events/%s\n", call->name);
-				continue;
-			}
-		}
-		ret = event_create_dir(call, d_events, &ftrace_event_id_fops,
+		__trace_add_event_call(call, NULL, &ftrace_event_id_fops,
 				       &ftrace_enable_fops,
 				       &ftrace_event_filter_fops,
 				       &ftrace_event_format_fops);
-		if (!ret)
-			list_add(&call->list, &ftrace_events);
 	}
 
 	while (true) {
-- 
1.7.1

[PATCH 8/9] tracing/function-graph: Use correct string size for snprintf

[Steven Rostedt]

[-- Attachment #1: 0008-tracing-function-graph-Use-correct-string-size-for-s.patch --]
[-- Type: text/plain, Size: 1498 bytes --]

From: Chase Douglas <chase.douglas@canonical.com>

The nsecs_str string is a local variable defined as:

char nsecs_str[5];

It is possible for the snprintf call to use a size value larger than the
size of the string. This should not cause a buffer overrun as it is
written now due to the value for the string format "%03lu" can not be
larger than 1000. However, this change makes it correct. By making the
size correct we guard against potential future changes that could actually
cause a buffer overrun.

Signed-off-by: Chase Douglas <chase.douglas@canonical.com>
LKML-Reference: <1276619355-18116-1-git-send-email-chase.douglas@canonical.com>

[ added 'UL' to number 8 to fix gcc warning comparing it to sizeof() ]

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace_functions_graph.c |    3 ++-
 1 files changed, 2 insertions(+), 1 deletions(-)

diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 79f4bac..6bff236 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -641,7 +641,8 @@ trace_print_graph_duration(unsigned long long duration, struct trace_seq *s)
 
 	/* Print nsecs (we don't want to exceed 7 numbers) */
 	if (len < 7) {
-		snprintf(nsecs_str, 8 - len, "%03lu", nsecs_rem);
+		snprintf(nsecs_str, min(sizeof(nsecs_str), 8UL - len), "%03lu",
+			 nsecs_rem);
 		ret = trace_seq_printf(s, ".%s", nsecs_str);
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
-- 
1.7.1

[PATCH 9/9] tracing: Use class->reg() for all registering of events

[Steven Rostedt]

[-- Attachment #1: 0009-tracing-Use-class-reg-for-all-registering-of-events.patch --]
[-- Type: text/plain, Size: 7179 bytes --]

From: Steven Rostedt <srostedt@redhat.com>

Because kprobes and syscalls need special processing to register
events, the class->reg() method was created to handle the differences.

But instead of creating a default ->reg for perf and ftrace events,
the code was scattered with:

	if (class->reg)
		class->reg();
	else
		default_reg();

This is messy and can also lead to bugs.

This patch cleans up this code and creates a default reg() entry for
the events allowing for the code to directly call the class->reg()
without the condition.

Reported-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace_event.h    |    3 ++
 include/trace/ftrace.h          |    2 +
 kernel/trace/trace_event_perf.c |   19 ++-----------
 kernel/trace/trace_events.c     |   55 +++++++++++++++++++++++++-------------
 4 files changed, 44 insertions(+), 35 deletions(-)

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 0af31cd..01df7ca 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -146,6 +146,9 @@ struct ftrace_event_class {
 	int			(*raw_init)(struct ftrace_event_call *);
 };
 
+extern int ftrace_event_reg(struct ftrace_event_call *event,
+			    enum trace_reg type);
+
 enum {
 	TRACE_EVENT_FL_ENABLED_BIT,
 	TRACE_EVENT_FL_FILTERED_BIT,
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index fc013a8..55c1fd1 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -439,6 +439,7 @@ static inline notrace int ftrace_get_offsets_##call(			\
  *	.fields			= LIST_HEAD_INIT(event_class_##call.fields),
  *	.raw_init		= trace_event_raw_init,
  *	.probe			= ftrace_raw_event_##call,
+ *	.reg			= ftrace_event_reg,
  * };
  *
  * static struct ftrace_event_call __used
@@ -567,6 +568,7 @@ static struct ftrace_event_class __used event_class_##call = {		\
 	.fields			= LIST_HEAD_INIT(event_class_##call.fields),\
 	.raw_init		= trace_event_raw_init,			\
 	.probe			= ftrace_raw_event_##call,		\
+	.reg			= ftrace_event_reg,			\
 	_TRACE_PERF_INIT(call)						\
 };
 
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 6053982..2375165 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -54,13 +54,7 @@ static int perf_trace_event_init(struct ftrace_event_call *tp_event,
 		}
 	}
 
-	if (tp_event->class->reg)
-		ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER);
-	else
-		ret = tracepoint_probe_register(tp_event->name,
-						tp_event->class->perf_probe,
-						tp_event);
-
+	ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER);
 	if (ret)
 		goto fail;
 
@@ -94,9 +88,7 @@ int perf_trace_init(struct perf_event *p_event)
 	mutex_lock(&event_mutex);
 	list_for_each_entry(tp_event, &ftrace_events, list) {
 		if (tp_event->event.type == event_id &&
-		    tp_event->class &&
-		    (tp_event->class->perf_probe ||
-		     tp_event->class->reg) &&
+		    tp_event->class && tp_event->class->reg &&
 		    try_module_get(tp_event->mod)) {
 			ret = perf_trace_event_init(tp_event, p_event);
 			break;
@@ -136,12 +128,7 @@ void perf_trace_destroy(struct perf_event *p_event)
 	if (--tp_event->perf_refcount > 0)
 		goto out;
 
-	if (tp_event->class->reg)
-		tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER);
-	else
-		tracepoint_probe_unregister(tp_event->name,
-					    tp_event->class->perf_probe,
-					    tp_event);
+	tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER);
 
 	/*
 	 * Ensure our callback won't be called anymore. See
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 69bee4c..e8e6043 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -141,6 +141,35 @@ int trace_event_raw_init(struct ftrace_event_call *call)
 }
 EXPORT_SYMBOL_GPL(trace_event_raw_init);
 
+int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type)
+{
+	switch (type) {
+	case TRACE_REG_REGISTER:
+		return tracepoint_probe_register(call->name,
+						 call->class->probe,
+						 call);
+	case TRACE_REG_UNREGISTER:
+		tracepoint_probe_unregister(call->name,
+					    call->class->probe,
+					    call);
+		return 0;
+
+#ifdef CONFIG_PERF_EVENTS
+	case TRACE_REG_PERF_REGISTER:
+		return tracepoint_probe_register(call->name,
+						 call->class->perf_probe,
+						 call);
+	case TRACE_REG_PERF_UNREGISTER:
+		tracepoint_probe_unregister(call->name,
+					    call->class->perf_probe,
+					    call);
+		return 0;
+#endif
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ftrace_event_reg);
+
 static int ftrace_event_enable_disable(struct ftrace_event_call *call,
 					int enable)
 {
@@ -151,23 +180,13 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call,
 		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);
-			else
-				tracepoint_probe_unregister(call->name,
-							    call->class->probe,
-							    call);
+			call->class->reg(call, TRACE_REG_UNREGISTER);
 		}
 		break;
 	case 1:
 		if (!(call->flags & TRACE_EVENT_FL_ENABLED)) {
 			tracing_start_cmdline_record();
-			if (call->class->reg)
-				ret = call->class->reg(call, TRACE_REG_REGISTER);
-			else
-				ret = tracepoint_probe_register(call->name,
-								call->class->probe,
-								call);
+			ret = call->class->reg(call, TRACE_REG_REGISTER);
 			if (ret) {
 				tracing_stop_cmdline_record();
 				pr_info("event trace: Could not enable event "
@@ -205,8 +224,7 @@ 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->class ||
-		    (!call->class->probe && !call->class->reg))
+		if (!call->name || !call->class || !call->class->reg)
 			continue;
 
 		if (match &&
@@ -332,7 +350,7 @@ 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->class && (call->class->probe || call->class->reg))
+		if (call->class && call->class->reg)
 			return call;
 	}
 
@@ -485,8 +503,7 @@ 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->class ||
-		    (!call->class->probe && !call->class->reg))
+		if (!call->name || !call->class || !call->class->reg)
 			continue;
 
 		if (system && strcmp(call->class->system, system) != 0)
@@ -977,12 +994,12 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events,
 		return -1;
 	}
 
-	if (call->class->probe || call->class->reg)
+	if (call->class->reg)
 		trace_create_file("enable", 0644, call->dir, call,
 				  enable);
 
 #ifdef CONFIG_PERF_EVENTS
-	if (call->event.type && (call->class->perf_probe || call->class->reg))
+	if (call->event.type && call->class->reg)
 		trace_create_file("id", 0444, call->dir, call,
 		 		  id);
 #endif
-- 
1.7.1

Re: [PATCH 0/9] [GI PULL][2.6.36] tracing: various updates

[Ingo Molnar]

* Steven Rostedt <rostedt@goodmis.org> wrote:

> Ingo,
> 
> I pushed some of these to you before, but you wanted to wait
> till after the merge window to pull them.
> 
> The last patch is the full fix for the perf kprobe regression. But
> since it was too big of a change for the -rc release we did
> a quick fix. This reverts that change back to the true fix for
> 2.6.36.
> 
> Please pull the latest tip/perf/core tree, which can be found at:
> 
>   git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
> tip/perf/core
> 
> 
> Chase Douglas (1):
>       tracing/function-graph: Use correct string size for snprintf
> 
> Li Zefan (7):
>       tracing: Use a global field list for all syscall exit events
>       tracing: Don't allocate common fields for every trace events
>       tracing: Convert some timer events to DEFINE_EVENT
>       tracing: Convert more sched events to DEFINE_EVENT
>       tracing: Remove test of NULL define_fields callback
>       tracing: Remove redundant raw_init callbacks
>       tracing: Remove open-coded __trace_add_event_call()
> 
> Steven Rostedt (1):
>       tracing: Use class->reg() for all registering of events
> 
> ----
>  include/linux/ftrace_event.h         |    3 +
>  include/linux/syscalls.h             |    2 -
>  include/trace/events/sched.h         |   32 +----
>  include/trace/events/timer.h         |   80 ++++------
>  include/trace/ftrace.h               |    2 +
>  include/trace/syscall.h              |    1 -
>  kernel/trace/trace.h                 |    2 +
>  kernel/trace/trace_event_perf.c      |   19 +--
>  kernel/trace/trace_events.c          |  264 +++++++++++++++++-----------------
>  kernel/trace/trace_events_filter.c   |   27 ++--
>  kernel/trace/trace_export.c          |    8 +-
>  kernel/trace/trace_functions_graph.c |    3 +-
>  kernel/trace/trace_kprobe.c          |   10 +--
>  kernel/trace/trace_syscalls.c        |    7 +-
>  14 files changed, 203 insertions(+), 257 deletions(-)

Pulled, thanks a lot Steve!

	Ingo