tracing: Drain deferred trigger frees if kthread creation fails

Boot-time trigger registration can fail before the trigger-data cleanup
kthread exists. Deferring those frees until late init is fine, but the
post-boot fallback must still drain the deferred list if kthread
creation never succeeds.

Otherwise, boot-deferred nodes can accumulate on
trigger_data_free_list, later frees fall back to synchronously freeing
only the current object, and the older queued entries are leaked
forever.

To trigger this, add the following to the kernel command line:

  trace_event=sched_switch trace_trigger=sched_switch.traceon,sched_switch.traceon

The second traceon trigger will fail and be freed. This triggers a NULL
pointer dereference and crashes the kernel.

Keep the deferred boot-time behavior, but when kthread creation fails,
drain the whole queued list synchronously. Do the same in the late-init
drain path so queued entries are not stranded there either.

Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20260324221326.1395799-3-atwellwea@gmail.com
Fixes: 61d445af0a ("tracing: Add bulk garbage collection of freeing event_trigger_data")
Signed-off-by: Wesley Atwell <atwellwea@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

kernel/trace/trace_events_trigger.c

@@ -22,6 +22,39 @@ static struct task_struct *trigger_kthread;
 static struct llist_head trigger_data_free_list;
 static DEFINE_MUTEX(trigger_data_kthread_mutex);
 
+static int trigger_kthread_fn(void *ignore);
+
+static void trigger_create_kthread_locked(void)
+{
+	lockdep_assert_held(&trigger_data_kthread_mutex);
+
+	if (!trigger_kthread) {
+		struct task_struct *kthread;
+
+		kthread = kthread_create(trigger_kthread_fn, NULL,
+					 "trigger_data_free");
+		if (!IS_ERR(kthread))
+			WRITE_ONCE(trigger_kthread, kthread);
+	}
+}
+
+static void trigger_data_free_queued_locked(void)
+{
+	struct event_trigger_data *data, *tmp;
+	struct llist_node *llnodes;
+
+	lockdep_assert_held(&trigger_data_kthread_mutex);
+
+	llnodes = llist_del_all(&trigger_data_free_list);
+	if (!llnodes)
+		return;
+
+	tracepoint_synchronize_unregister();
+
+	llist_for_each_entry_safe(data, tmp, llnodes, llist)
+		kfree(data);
+}
+
 /* Bulk garbage collection of event_trigger_data elements */
 static int trigger_kthread_fn(void *ignore)
 {
@@ -56,30 +89,50 @@ void trigger_data_free(struct event_trigger_data *data)
 	if (data->cmd_ops->set_filter)
 		data->cmd_ops->set_filter(NULL, data, NULL);
 
-	if (unlikely(!trigger_kthread)) {
+	/*
-		guard(mutex)(&trigger_data_kthread_mutex);
+	 * Boot-time trigger registration can fail before kthread creation
-		/* Check again after taking mutex */
+	 * works. Keep the deferred-free semantics during boot and let late
-		if (!trigger_kthread) {
+	 * init start the kthread to drain the list.
-			struct task_struct *kthread;
+	 */
-
+	if (system_state == SYSTEM_BOOTING && !trigger_kthread) {
-			kthread = kthread_create(trigger_kthread_fn, NULL,
+		llist_add(&data->llist, &trigger_data_free_list);
-						 "trigger_data_free");
+		return;
-			if (!IS_ERR(kthread))
-				WRITE_ONCE(trigger_kthread, kthread);
-		}
 	}
 
-	if (!trigger_kthread) {
+	if (unlikely(!trigger_kthread)) {
-		/* Do it the slow way */
+		guard(mutex)(&trigger_data_kthread_mutex);
-		tracepoint_synchronize_unregister();
+
-		kfree(data);
+		trigger_create_kthread_locked();
-		return;
+		/* Check again after taking mutex */
+		if (!trigger_kthread) {
+			llist_add(&data->llist, &trigger_data_free_list);
+			/* Drain the queued frees synchronously if creation failed. */
+			trigger_data_free_queued_locked();
+			return;
+		}
 	}
 
 	llist_add(&data->llist, &trigger_data_free_list);
 	wake_up_process(trigger_kthread);
 }
 
+static int __init trigger_data_free_init(void)
+{
+	guard(mutex)(&trigger_data_kthread_mutex);
+
+	if (llist_empty(&trigger_data_free_list))
+		return 0;
+
+	trigger_create_kthread_locked();
+	if (trigger_kthread)
+		wake_up_process(trigger_kthread);
+	else
+		trigger_data_free_queued_locked();
+
+	return 0;
+}
+late_initcall(trigger_data_free_init);
+
 static inline void data_ops_trigger(struct event_trigger_data *data,
 				    struct trace_buffer *buffer,  void *rec,
 				    struct ring_buffer_event *event)