[OpenMP][FIX] Ensure custom state machine works

The custom state machine had a check for surplus threads that filtered
the main thread if the kernel was executed by a single warp only. We
now first check for the main thread, then for surplus threads, avoiding
to filter the former out.

Fixes #54214.

Reviewed By: jhuber6

Differential Revision: https://reviews.llvm.org/D121011