On Mon, Sep 08, 2025 at 01:14:14PM -0400, Steven Rostedt wrote:
> +static void perf_event_callchain_deferred(struct callback_head *work)
> +{
> + struct perf_event *event = container_of(work, struct perf_event,
> pending_unwind_work);
> + struct perf_callchain_deferred_event deferred_event;
> + u64 callchain_context = PERF_CONTEXT_USER;
> + struct unwind_stacktrace trace;
> + struct perf_output_handle handle;
> + struct perf_sample_data data;
> + u64 nr;
> +
> + if (!event->pending_unwind_callback)
> + return;
> +
> + if (unwind_user_faultable(&trace) < 0)
> + goto out;
This is broken. Because:
> +
> + /*
> + * All accesses to the event must belong to the same implicit RCU
> + * read-side critical section as the ->pending_unwind_callback reset.
> + * See comment in perf_pending_unwind_sync().
> + */
> + guard(rcu)();
Here you start a guard, that lasts until close of function..
> +
> + if (current->flags & (PF_KTHREAD | PF_USER_WORKER))
> + goto out;
> +
> + nr = trace.nr + 1 ; /* '+1' == callchain_context */
> +
> + deferred_event.header.type = PERF_RECORD_CALLCHAIN_DEFERRED;
> + deferred_event.header.misc = PERF_RECORD_MISC_USER;
> + deferred_event.header.size = sizeof(deferred_event) + (nr *
> sizeof(u64));
> +
> + deferred_event.nr = nr;
> + deferred_event.cookie = unwind_user_get_cookie();
> +
> + perf_event_header__init_id(&deferred_event.header, &data, event);
> +
> + if (perf_output_begin(&handle, &data, event,
> deferred_event.header.size))
> + goto out;
> +
> + perf_output_put(&handle, deferred_event);
> + perf_output_put(&handle, callchain_context);
> + /* trace.entries[] are not guaranteed to be 64bit */
> + for (int i = 0; i < trace.nr; i++) {
> + u64 entry = trace.entries[i];
> + perf_output_put(&handle, entry);
> + }
> + perf_event__output_id_sample(event, &handle, &data);
> +
> + perf_output_end(&handle);
> +
> +out:
Which very much includes here, so your goto jumps into a scope, which is
not permitted.
GCC can fail to warn on this, but clang will consistently fail to
compile this. Surely the robot would've told you by now -- even if
you're not using clang yourself.
> + event->pending_unwind_callback = 0;
> + local_dec(&event->ctx->nr_no_switch_fast);
> + rcuwait_wake_up(&event->pending_unwind_wait);
> +}
