Tracing fixes for 6.16:

- Fix timerlat with use of FORTIFY_SOURCE
 
   FORTIFY_SOURCE was added to the stack tracer where it compares the
   entry->caller array to having entry->size elements.
 
   timerlat has the following:
 
      memcpy(&entry->caller, fstack->calls, size);
      entry->size = size;
 
   Which triggers FORTIFY_SOURCE as the caller is populated before the
   entry->size is initialized.
 
   Swap the order to satisfy FORTIFY_SOURCE logic.
 
 - Add down_write(trace_event_sem) when adding trace events in modules
 
   Trace events being added to the ftrace_events array are protected by
   the trace_event_sem semaphore. But when loading modules that have
   trace events, the addition of the events are not protected by the
   semaphore and loading two modules that have events at the same time
   can corrupt the list.
 
   Also add a lockdep_assert_held(trace_event_sem) to
   _trace_add_event_dirs() to confirm its held when iterating the list.
 -----BEGIN PGP SIGNATURE-----
 
 iIoEABYKADIWIQRRSw7ePDh/lE+zeZMp5XQQmuv6qgUCaH06gBQccm9zdGVkdEBn
 b29kbWlzLm9yZwAKCRAp5XQQmuv6qoJsAP0a+/E0f+5g7O/OtYPVEDSCREv1vj9c
 3dr0iWopqaOC7gEAw8Vc5iWIHKcB/JuJ+GqALoutL+lihruG26MWkFFsOgU=
 =zH5J
 -----END PGP SIGNATURE-----

Merge tag 'trace-v6.16-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing fixes from Steven Rostedt:

 - Fix timerlat with use of FORTIFY_SOURCE

   FORTIFY_SOURCE was added to the stack tracer where it compares the
   entry->caller array to having entry->size elements.

   timerlat has the following:

      memcpy(&entry->caller, fstack->calls, size);
      entry->size = size;

   Which triggers FORTIFY_SOURCE as the caller is populated before the
   entry->size is initialized.

   Swap the order to satisfy FORTIFY_SOURCE logic.

 - Add down_write(trace_event_sem) when adding trace events in modules

   Trace events being added to the ftrace_events array are protected by
   the trace_event_sem semaphore. But when loading modules that have
   trace events, the addition of the events are not protected by the
   semaphore and loading two modules that have events at the same time
   can corrupt the list.

   Also add a lockdep_assert_held(trace_event_sem) to
   _trace_add_event_dirs() to confirm it is held when iterating the
   list.

* tag 'trace-v6.16-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  tracing: Add down_write(trace_event_sem) when adding trace event
  tracing/osnoise: Fix crash in timerlat_dump_stack()

kernel/trace/trace_events.c

@@ -3136,7 +3136,10 @@ __register_event(struct trace_event_call *call, struct module *mod)
 	if (ret < 0)
 		return ret;
 
+	down_write(&trace_event_sem);
 	list_add(&call->list, &ftrace_events);
+	up_write(&trace_event_sem);
+
 	if (call->flags & TRACE_EVENT_FL_DYNAMIC)
 		atomic_set(&call->refcnt, 0);
 	else
@@ -3750,6 +3753,8 @@ __trace_add_event_dirs(struct trace_array *tr)
 	struct trace_event_call *call;
 	int ret;
 
+	lockdep_assert_held(&trace_event_sem);
+
 	list_for_each_entry(call, &ftrace_events, list) {
 		ret = __trace_add_new_event(call, tr);
 		if (ret < 0)

kernel/trace/trace_osnoise.c

@@ -637,8 +637,8 @@ __timerlat_dump_stack(struct trace_buffer *buffer, struct trace_stack *fstack, u
 
 	entry = ring_buffer_event_data(event);
 
-	memcpy(&entry->caller, fstack->calls, size);
 	entry->size = fstack->nr_entries;
+	memcpy(&entry->caller, fstack->calls, size);
 
 	trace_buffer_unlock_commit_nostack(buffer, event);
 }