tracing: New flag to allow non privileged users to use a trace event

This adds a new trace event internal flag that allows them to be
used in perf by non privileged users in case of task bound tracing.

This is desired for syscalls tracepoint because they don't leak
global system informations, like some other tracepoints.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Jason Baron <jbaron@redhat.com>

3 files changed, 32 insertions, 10 deletions

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 8beabb9..312dce7 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -154,12 +154,14 @@ enum {
 	TRACE_EVENT_FL_ENABLED_BIT,
 	TRACE_EVENT_FL_FILTERED_BIT,
 	TRACE_EVENT_FL_RECORDED_CMD_BIT,
+	TRACE_EVENT_FL_CAP_ANY_BIT,
 };
 
 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),
 };
 
 struct ftrace_event_call {
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 517d827..ee1e903 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -4747,15 +4747,6 @@ static int perf_tp_event_init(struct perf_event *event)
 	if (event->attr.type != PERF_TYPE_TRACEPOINT)
 		return -ENOENT;
 
-	/*
-	 * Raw tracepoint data is a severe data leak, only allow root to
-	 * have these.
-	 */
-	if ((event->attr.sample_type & PERF_SAMPLE_RAW) &&
-			perf_paranoid_tracepoint_raw() &&
-			!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
 	err = perf_trace_init(event);
 	if (err)
 		return err;
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 39c059c..19a359d 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -21,17 +21,46 @@ typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
 /* Count the events in use (per event id, not per instance) */
 static int	total_ref_count;
 
+static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
+				 struct perf_event *p_event)
+{
+	/* No tracing, just counting, so no obvious leak */
+	if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
+		return 0;
+
+	/* Some events are ok to be traced by non-root users... */
+	if (p_event->attach_state == PERF_ATTACH_TASK) {
+		if (tp_event->flags & TRACE_EVENT_FL_CAP_ANY)
+			return 0;
+	}
+
+	/*
+	 * ...otherwise raw tracepoint data can be a severe data leak,
+	 * only allow root to have these.
+	 */
+	if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	return 0;
+}
+
 static int perf_trace_event_init(struct ftrace_event_call *tp_event,
 				 struct perf_event *p_event)
 {
 	struct hlist_head __percpu *list;
-	int ret = -ENOMEM;
+	int ret;
 	int cpu;
 
+	ret = perf_trace_event_perm(tp_event, p_event);
+	if (ret)
+		return ret;
+
 	p_event->tp_event = tp_event;
 	if (tp_event->perf_refcount++ > 0)
 		return 0;
 
+	ret = -ENOMEM;
+
 	list = alloc_percpu(struct hlist_head);
 	if (!list)
 		goto fail;