tracing: add trace_event_read_lock()

I found that there is nothing to protect event_hash in
ftrace_find_event(). Rcu protects the event hashlist
but not the event itself while we use it after its extraction
through ftrace_find_event().

This lack of a proper locking in this spot opens a race
window between any event dereferencing and module removal.

Eg:

--Task A--

print_trace_line(trace) {
  event = find_ftrace_event(trace)

--Task B--

trace_module_remove_events(mod) {
  list_trace_events_module(ev, mod) {
    unregister_ftrace_event(ev->event) {
      hlist_del(ev->event->node)
        list_del(....)
    }
  }
}
|--> module removed, the event has been dropped

--Task A--

  event->print(trace); // Dereferencing freed memory

If the event retrieved belongs to a module and this module
is concurrently removed, we may end up dereferencing a data
from a freed module.

RCU could solve this, but it would add latency to the kernel and
forbid tracers output callbacks to call any sleepable code.
So this fix converts 'trace_event_mutex' to a read/write semaphore,
and adds trace_event_read_lock() to protect ftrace_find_event().

[ Impact: fix possible freed memory dereference in ftrace ]

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <4A114806.7090302@cn.fujitsu.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>

1 files changed, 18 insertions, 7 deletions

diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 489c0e8ada09..7136420603aa 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -14,7 +14,7 @@
 /* must be a power of 2 */
 #define EVENT_HASHSIZE	128
 
-static DEFINE_MUTEX(trace_event_mutex);
+static DECLARE_RWSEM(trace_event_mutex);
 static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
 
 static int next_event_type = __TRACE_LAST_TYPE + 1;
@@ -466,6 +466,7 @@ static int task_state_char(unsigned long state)
  * @type: the type of event to look for
  *
  * Returns an event of type @type otherwise NULL
+ * Called with trace_event_read_lock() held.
  */
 struct trace_event *ftrace_find_event(int type)
 {
@@ -475,7 +476,7 @@ struct trace_event *ftrace_find_event(int type)
 
 	key = type & (EVENT_HASHSIZE - 1);
 
-	hlist_for_each_entry_rcu(event, n, &event_hash[key], node) {
+	hlist_for_each_entry(event, n, &event_hash[key], node) {
 		if (event->type == type)
 			return event;
 	}
@@ -513,6 +514,16 @@ static int trace_search_list(struct list_head **list)
 	return last + 1;
 }
 
+void trace_event_read_lock(void)
+{
+	down_read(&trace_event_mutex);
+}
+
+void trace_event_read_unlock(void)
+{
+	up_read(&trace_event_mutex);
+}
+
 /**
  * register_ftrace_event - register output for an event type
  * @event: the event type to register
@@ -533,7 +544,7 @@ int register_ftrace_event(struct trace_event *event)
 	unsigned key;
 	int ret = 0;
 
-	mutex_lock(&trace_event_mutex);
+	down_write(&trace_event_mutex);
 
 	if (WARN_ON(!event))
 		goto out;
@@ -581,11 +592,11 @@ int register_ftrace_event(struct trace_event *event)
 
 	key = event->type & (EVENT_HASHSIZE - 1);
 
-	hlist_add_head_rcu(&event->node, &event_hash[key]);
+	hlist_add_head(&event->node, &event_hash[key]);
 
 	ret = event->type;
  out:
-	mutex_unlock(&trace_event_mutex);
+	up_write(&trace_event_mutex);
 
 	return ret;
 }
@@ -597,10 +608,10 @@ EXPORT_SYMBOL_GPL(register_ftrace_event);
  */
 int unregister_ftrace_event(struct trace_event *event)
 {
-	mutex_lock(&trace_event_mutex);
+	down_write(&trace_event_mutex);
 	hlist_del(&event->node);
 	list_del(&event->list);
-	mutex_unlock(&trace_event_mutex);
+	up_write(&trace_event_mutex);
 
 	return 0;
 }