> The reason you think it may deadlock is that deadlock is because you miss
> what happened before the "time zero" on CPU 1. Let's see the whole
> picture:
I guess I had a brain burp there. Good point that it will work correctly
in the case provided.
> That's what I understood by reading your previous posts. It seems we don't
> need to enforce any ordering in IA32 as the hardware is doing that for us.
> Right? Of course the current code can't hurt, it's only slower (like what
> we have with spin_unlock right now).
Agreed.
--
Erich Stefan Boleyn \_ <erich@uruk.org>
Mad but Happy Scientist \__ http://www.uruk.org/
Motto: "I'll live forever or die trying" ---------------------------
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/