tracing: Separate out trace events from global variables

The trace events for ftrace are all defined via global variables.
The arrays of events and event systems are linked to a global list.
This prevents multiple users of the event system (what to enable and
what not to).

By adding descriptors to represent the event/file relation, as well
as to which trace_array descriptor they are associated with, allows
for more than one set of events to be defined. Once the trace events
files have a link between the trace event and the trace_array they
are associated with, we can create multiple trace_arrays that can
record separate events in separate buffers.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

include/linux/ftrace_event.h

@@ -182,18 +182,20 @@ extern int ftrace_event_reg(struct ftrace_event_call *event,
 			    enum trace_reg type, void *data);
 
 enum {
-	TRACE_EVENT_FL_ENABLED_BIT,
 	TRACE_EVENT_FL_FILTERED_BIT,
-	TRACE_EVENT_FL_RECORDED_CMD_BIT,
 	TRACE_EVENT_FL_CAP_ANY_BIT,
 	TRACE_EVENT_FL_NO_SET_FILTER_BIT,
 	TRACE_EVENT_FL_IGNORE_ENABLE_BIT,
 };
 
+/*
+ * Event flags:
+ *  FILTERED	  - The event has a filter attached
+ *  CAP_ANY	  - Any user can enable for perf
+ *  NO_SET_FILTER - Set when filter has error and is to be ignored
+ */
 enum {
-	TRACE_EVENT_FL_ENABLED		= (1 << TRACE_EVENT_FL_ENABLED_BIT),
 	TRACE_EVENT_FL_FILTERED		= (1 << TRACE_EVENT_FL_FILTERED_BIT),
-	TRACE_EVENT_FL_RECORDED_CMD	= (1 << TRACE_EVENT_FL_RECORDED_CMD_BIT),
 	TRACE_EVENT_FL_CAP_ANY		= (1 << TRACE_EVENT_FL_CAP_ANY_BIT),
 	TRACE_EVENT_FL_NO_SET_FILTER	= (1 << TRACE_EVENT_FL_NO_SET_FILTER_BIT),
 	TRACE_EVENT_FL_IGNORE_ENABLE	= (1 << TRACE_EVENT_FL_IGNORE_ENABLE_BIT),
@@ -203,12 +205,44 @@ struct ftrace_event_call {
 	struct list_head	list;
 	struct ftrace_event_class *class;
 	char			*name;
-	struct dentry		*dir;
 	struct trace_event	event;
 	const char		*print_fmt;
 	struct event_filter	*filter;
+	struct list_head	*files;
 	void			*mod;
 	void			*data;
+	int			flags; /* static flags of different events */
+
+#ifdef CONFIG_PERF_EVENTS
+	int				perf_refcount;
+	struct hlist_head __percpu	*perf_events;
+#endif
+};
+
+struct trace_array;
+struct ftrace_subsystem_dir;
+
+enum {
+	FTRACE_EVENT_FL_ENABLED_BIT,
+	FTRACE_EVENT_FL_RECORDED_CMD_BIT,
+};
+
+/*
+ * Ftrace event file flags:
+ *  ENABELD	  - The event is enabled
+ *  RECORDED_CMD  - The comms should be recorded at sched_switch
+ */
+enum {
+	FTRACE_EVENT_FL_ENABLED		= (1 << FTRACE_EVENT_FL_ENABLED_BIT),
+	FTRACE_EVENT_FL_RECORDED_CMD	= (1 << FTRACE_EVENT_FL_RECORDED_CMD_BIT),
+};
+
+struct ftrace_event_file {
+	struct list_head		list;
+	struct ftrace_event_call	*event_call;
+	struct dentry			*dir;
+	struct trace_array		*tr;
+	struct ftrace_subsystem_dir	*system;
 
 	/*
 	 * 32 bit flags:
@@ -223,17 +257,12 @@ struct ftrace_event_call {
 	 *
 	 * 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
+	 * is currently used, these changes do not 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
 	 * caching and such.
 	 */
 	unsigned int		flags;
-
-#ifdef CONFIG_PERF_EVENTS
-	int				perf_refcount;
-	struct hlist_head __percpu	*perf_events;
-#endif
 };
 
 #define __TRACE_EVENT_FLAGS(name, value)				\

include/trace/ftrace.h

@@ -518,7 +518,8 @@ static inline notrace int ftrace_get_offsets_##call(			\
 static notrace void							\
 ftrace_raw_event_##call(void *__data, proto)				\
 {									\
-	struct ftrace_event_call *event_call = __data;			\
+	struct ftrace_event_file *ftrace_file = __data;			\
+	struct ftrace_event_call *event_call = ftrace_file->event_call;	\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
 	struct ring_buffer_event *event;				\
 	struct ftrace_raw_##call *entry;				\

kernel/trace/trace.c

@@ -189,6 +189,8 @@ unsigned long long ns2usecs(cycle_t nsec)
  */
 static struct trace_array	global_trace;
 
+LIST_HEAD(ftrace_trace_arrays);
+
 static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);
 
 int filter_current_check_discard(struct ring_buffer *buffer,
@@ -5359,6 +5361,12 @@ __init static int tracer_alloc_buffers(void)
 
 	register_die_notifier(&trace_die_notifier);
 
+	global_trace.flags = TRACE_ARRAY_FL_GLOBAL;
+
+	INIT_LIST_HEAD(&global_trace.systems);
+	INIT_LIST_HEAD(&global_trace.events);
+	list_add(&global_trace.list, &ftrace_trace_arrays);
+
 	while (trace_boot_options) {
 		char *option;
 

kernel/trace/trace.h

@@ -158,13 +158,39 @@ struct trace_array_cpu {
  */
 struct trace_array {
 	struct ring_buffer	*buffer;
+	struct list_head	list;
 	int			cpu;
 	int			buffer_disabled;
+	unsigned int		flags;
 	cycle_t			time_start;
+	struct dentry		*dir;
+	struct dentry		*event_dir;
+	struct list_head	systems;
+	struct list_head	events;
 	struct task_struct	*waiter;
 	struct trace_array_cpu	*data[NR_CPUS];
 };
 
+enum {
+	TRACE_ARRAY_FL_GLOBAL	= (1 << 0)
+};
+
+extern struct list_head ftrace_trace_arrays;
+
+/*
+ * The global tracer (top) should be the first trace array added,
+ * but we check the flag anyway.
+ */
+static inline struct trace_array *top_trace_array(void)
+{
+	struct trace_array *tr;
+
+	tr = list_entry(ftrace_trace_arrays.prev,
+			typeof(*tr), list);
+	WARN_ON(!(tr->flags & TRACE_ARRAY_FL_GLOBAL));
+	return tr;
+}
+
 #define FTRACE_CMP_TYPE(var, type) \
 	__builtin_types_compatible_p(typeof(var), type *)
 
@@ -851,12 +877,19 @@ struct event_filter {
 struct event_subsystem {
 	struct list_head	list;
 	const char		*name;
-	struct dentry		*entry;
 	struct event_filter	*filter;
-	int			nr_events;
 	int			ref_count;
 };
 
+struct ftrace_subsystem_dir {
+	struct list_head		list;
+	struct event_subsystem		*subsystem;
+	struct trace_array		*tr;
+	struct dentry			*entry;
+	int				ref_count;
+	int				nr_events;
+};
+
 #define FILTER_PRED_INVALID	((unsigned short)-1)
 #define FILTER_PRED_IS_RIGHT	(1 << 15)
 #define FILTER_PRED_FOLD	(1 << 15)
@@ -914,7 +947,7 @@ extern void print_event_filter(struct ftrace_event_call *call,
 			       struct trace_seq *s);
 extern int apply_event_filter(struct ftrace_event_call *call,
 			      char *filter_string);
-extern int apply_subsystem_event_filter(struct event_subsystem *system,
+extern int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,
 					char *filter_string);
 extern void print_subsystem_event_filter(struct event_subsystem *system,
 					 struct trace_seq *s);

kernel/trace/trace_events_filter.c

@@ -1907,16 +1907,17 @@ out_unlock:
 	return err;
 }
 
-int apply_subsystem_event_filter(struct event_subsystem *system,
+int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,
 				 char *filter_string)
 {
+	struct event_subsystem *system = dir->subsystem;
 	struct event_filter *filter;
 	int err = 0;
 
 	mutex_lock(&event_mutex);
 
 	/* Make sure the system still has events */
-	if (!system->nr_events) {
+	if (!dir->nr_events) {
 		err = -ENODEV;
 		goto out_unlock;
 	}