Re: [PATCH] Document that wake_up(), complete() and co. imply afull memory barrier

[Ingo Molnar]

* David Howells <dhowells@xxxxxxxxxx> wrote:

> Ingo Molnar <mingo@xxxxxxx> wrote:
> 
> > No. They dont generally imply a full memory barrier versus any
> > arbitrary prior (or following) memory access.
> >
> > try_to_wake_up() has an smp_wmb() so it is a write memory barrier
> > (but not necessarily a read memory barrier). Otherwise there are
> > spinlocks there but spinlocks are not explicit 'full memory
> > barriers'.
> 
> Blech.  That's a good point LOCK...UNLOCK does not imply a full 
> barrier.
> 
> So we can't assume that complete(), wake_up() and co. imply any 
> barriers.
> 
> All we can assume is that try_to_wake_up() implies a write 
> barrier, but we can't assume that that will be called via 
> __wake_up_common().

Yeah, it's all too special-case. We might rely on it in special, 
well-argued cases but we should not document it as a general barrier 
property.

	Ingo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/