tracing: Allow creating instances with specified system events

A trace instance may only need to enable specific events. As the eventfs
directory of an instance currently creates all events which adds overhead,
allow internal instances to be created with just the events in systems
that they care about. This currently only deals with systems and not
individual events, but this should bring down the overhead of creating
instances for specific use cases quite bit.

The trace_array_get_by_name() now has another parameter "systems". This
parameter is a const string pointer of a comma/space separated list of
event systems that should be created by the trace_array. (Note if the
trace_array already exists, this parameter is ignored).

The list of systems is saved and if a module is loaded, its events will
not be added unless the system for those events also match the systems
string.

Link: https://lore.kernel.org/linux-trace-kernel/20231213093701.03fddec0@gandalf.local.home

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Sean Paul <seanpaul@chromium.org>
Cc: Arun Easi   <aeasi@marvell.com>
Cc: Daniel Wagner <dwagner@suse.de>
Tested-by: Dmytro Maluka <dmaluka@chromium.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

1 files changed, 45 insertions, 3 deletions

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f29e815ca5b2..b70d03818038 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2896,6 +2896,27 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
 	up_write(&trace_event_sem);
 }
 
+static bool event_in_systems(struct trace_event_call *call,
+			     const char *systems)
+{
+	const char *system;
+	const char *p;
+
+	if (!systems)
+		return true;
+
+	system = call->class->system;
+	p = strstr(systems, system);
+	if (!p)
+		return false;
+
+	if (p != systems && !isspace(*(p - 1)) && *(p - 1) != ',')
+		return false;
+
+	p += strlen(system);
+	return !*p || isspace(*p) || *p == ',';
+}
+
 static struct trace_event_file *
 trace_create_new_event(struct trace_event_call *call,
 		       struct trace_array *tr)
@@ -2905,9 +2926,12 @@ trace_create_new_event(struct trace_event_call *call,
 	struct trace_event_file *file;
 	unsigned int first;
 
+	if (!event_in_systems(call, tr->system_names))
+		return NULL;
+
 	file = kmem_cache_alloc(file_cachep, GFP_TRACE);
 	if (!file)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	pid_list = rcu_dereference_protected(tr->filtered_pids,
 					     lockdep_is_held(&event_mutex));
@@ -2972,8 +2996,17 @@ __trace_add_new_event(struct trace_event_call *call, struct trace_array *tr)
 	struct trace_event_file *file;
 
 	file = trace_create_new_event(call, tr);
+	/*
+	 * trace_create_new_event() returns ERR_PTR(-ENOMEM) if failed
+	 * allocation, or NULL if the event is not part of the tr->system_names.
+	 * When the event is not part of the tr->system_names, return zero, not
+	 * an error.
+	 */
 	if (!file)
-		return -ENOMEM;
+		return 0;
+
+	if (IS_ERR(file))
+		return PTR_ERR(file);
 
 	if (eventdir_initialized)
 		return event_create_dir(tr->event_dir, file);
@@ -3012,8 +3045,17 @@ __trace_early_add_new_event(struct trace_event_call *call,
 	int ret;
 
 	file = trace_create_new_event(call, tr);
+	/*
+	 * trace_create_new_event() returns ERR_PTR(-ENOMEM) if failed
+	 * allocation, or NULL if the event is not part of the tr->system_names.
+	 * When the event is not part of the tr->system_names, return zero, not
+	 * an error.
+	 */
 	if (!file)
-		return -ENOMEM;
+		return 0;
+
+	if (IS_ERR(file))
+		return PTR_ERR(file);
 
 	ret = event_define_fields(call);
 	if (ret)