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

···
 	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
···
 {
 	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);

kernel/trace/trace_osnoise.c

···
 
 	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);
 }