On Wed, 22 Nov 2023, Mihai Carabas wrote:

> La 22.11.2023 22:51, Christoph Lameter a scris:
>> 
>> On Mon, 20 Nov 2023, Mihai Carabas wrote:
>> 
>>> cpu_relax on ARM64 does a simple "yield". Thus we replace it with
>>> smp_cond_load_relaxed which basically does a "wfe".
>> 
>> Well it clears events first (which requires the first WFE) and then does a 
>> WFE waiting for any events if no events were pending.
>> 
>> WFE does not cause a VMEXIT? Or does the inner loop of 
>> smp_cond_load_relaxed now do 2x VMEXITS?
>> 
>> KVM ARM64 code seems to indicate that WFE causes a VMEXIT. See 
>> kvm_handle_wfx().
>
> In KVM ARM64 the WFE traping is dynamic: it is enabled only if there are more 
> tasks waiting on the same core (e.g. on an oversubscribed system).
>
> In arch/arm64/kvm/arm.c:
>
>  457 >-------if (single_task_running())
>  458 >------->-------vcpu_clear_wfx_traps(vcpu);
>  459 >-------else
>  460 >------->-------vcpu_set_wfx_traps(vcpu);

Ahh. Cool did not know about that. But still: Lots of VMEXITs once the 
load has to be shared.

> This of course can be improved by having a knob where you can completly 
> disable wfx traping by your needs, but I left this as another subject to 
> tackle.

kvm_arch_vcpu_load() looks strange. On the one hand we pass a cpu 
number into it and then we use functions that only work if we are running 
on that cpu?

It would be better to use smp_processor_id() in the function 
and not pass the cpu number to it.