Re: [Ksummit-discuss] [CORE TOPIC] lightweight per-cpu locks / restartable sequences

[Andy Lutomirski <luto@amacapital.net>]

On Mon, Jul 13, 2015 at 7:01 AM, Christoph Lameter <cl@linux.com> wrote:
> On Mon, 13 Jul 2015, Peter Zijlstra wrote:
>
>> Now the 'problem' is finding these special regions fast, the easy
>> solution is the same as the one proposed for userspace, one big section.
>> That way the interrupt only has to check if the IP is inside this
>> section which is minimal effort.
>>
>> The down side is that all percpu ops would then end up being full
>> function calls. Which on some archs is indeed faster than disabling
>> interrupts, but not by much I'm afraid.
>
> Well one could move the entire functions that are using these ops into the
> special sections. That is certainly an area requiring much more thought.

Hmm.

>
>> > optimize the x86 variants if interrupts also can detect critical sections
>> > and restart at defined points.
>>
>> I really don't see how we can beat %GS prefixes with any such scheme.
>
> We may be able to avoid RMV sequences which allows the processor to better
> schedule operations.

True, but cmpxchg is, surprisingly, pretty fast.

Crazy thought: At the risk of proposing something ridiculous, what if
we had per-cpu memory mappings?  We could do this at the cost of up to
2kB of memcpy whenever we switch mms.  Expensive but maybe not a
showstopper.

--Andy