We clear the worker state in the worker thread after processing
all messages (and getting the terminate signal). This could cause
a race condition when interacting with the worker from the main thread.

This was previously working and broke with https://crrev.com/c/3318669

- Add is_joined_ variable which is mutex guarded
- Simplify Worker::State
- Mutex guard task_runner_ access

Bug: v8:12487
Change-Id: Ib53e5a1a636cb29db50efdb63526b0023a5ea768
Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/3345005Reviewed-by: Leszek Swirski <leszeks@chromium.org>
Commit-Queue: Camillo Bruni <cbruni@chromium.org>
Cr-Commit-Position: refs/heads/main@{#78415}