tracing: Create class struct for events

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

@@ -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;

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,	\

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)			\
@@ -636,15 +630,15 @@ 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,		\
 	.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
 #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,		\

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
 

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 */

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,		\

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);

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[];