Re: [PATCH] memcg: remove unneeded preempt_disable

[Peter Zijlstra]

On Thu, 2011-08-25 at 13:46 -0500, Christoph Lameter wrote:
> 
> RISC cpus have instruction to construct complex atomic actions by the cpu
> as I have shown before for ARM. 

Right, but it only makes sense if the whole thing remains cheaper than
the trivial implementation already available.

For instance, the ARM LL/SC constraints pretty much mandate we do
preempt_disable()/preempt_enable() around them, at which point the point
of doing LL/SC is gone (except maybe for the irqsafe_this_cpu_* stuff).
--
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/