tracing: Move fields from event to class structure

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>

6 files changed, 83 insertions, 31 deletions

diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 911e9864e94..c88c563a59a 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 19d1eb0a718..acc0f55742c 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 ca329603d0b..961f99b74bd 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 7f16e216381..e700a0c1803 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 f8af21a53f0..b14bf745356 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 a21d366cae4..cceccf0d2e9 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;