Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1700038 > unrolled thread

Re: [RFC] KVM: optimize the kvm_vcpu_on_spin

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

  Re: [RFC] KVM: optimize the kvm_vcpu_on_spin Paolo Bonzini <pbonzini@redhat.com> - 2017-07-31 15:30 +0200
    Re: [RFC] KVM: optimize the kvm_vcpu_on_spin "Longpeng (Mike)" <longpeng2@huawei.com> - 2017-08-01 05:30 +0200
      Re: [RFC] KVM: optimize the kvm_vcpu_on_spin Paolo Bonzini <pbonzini@redhat.com> - 2017-08-01 10:40 +0200

#1700038 — Re: [RFC] KVM: optimize the kvm_vcpu_on_spin

On 31/07/2017 14:27, David Hildenbrand wrote:
>> I'm not sure whether the operation of get the vcpu's priority-level is
>> expensive on all architectures, so I record it in kvm_sched_out() for
>> minimal the extra cycles cost in kvm_vcpu_on_spin().
>>
> as you only care for x86 right now either way, you can directly optimize
> here for the good (here: x86) case (keeping changes and therefore
> possible bugs minimal).

I agree with Cornelia that this is inconsistent, so you shouldn't update
me->in_kernmode in kvm_vcpu_on_spin.  However, get_cpl requires
vcpu_load on Intel x86, so Mike's patch is necessary (vmx_get_cpl ->
vmx_read_guest_seg_ar -> vmcs_read32).

Alternatively, we can add a new callback kvm_x86_ops->sched_out to x86
KVM, and call vmx_get_cpl from the Intel implementation (vmx_sched_out).
 This will cache the result until the next sched_in, so that
kvm_vcpu_on_spin can use it.

Paolo

[toc] | [next] | [standalone]

#1700601

On 2017/7/31 21:20, Paolo Bonzini wrote:

> On 31/07/2017 14:27, David Hildenbrand wrote:
>>> I'm not sure whether the operation of get the vcpu's priority-level is
>>> expensive on all architectures, so I record it in kvm_sched_out() for
>>> minimal the extra cycles cost in kvm_vcpu_on_spin().
>>>
>> as you only care for x86 right now either way, you can directly optimize
>> here for the good (here: x86) case (keeping changes and therefore
>> possible bugs minimal).
> 
> I agree with Cornelia that this is inconsistent, so you shouldn't update
> me->in_kernmode in kvm_vcpu_on_spin.  However, get_cpl requires
> vcpu_load on Intel x86, so Mike's patch is necessary (vmx_get_cpl ->
> vmx_read_guest_seg_ar -> vmcs_read32).
> 

Hi Paolo,

It seems that other architectures(e.g. arm/s390) needn't to cache the result,
but x86 need, so I need to move 'in_kernmode' into kvm_vcpu_arch and only add
this field to x86, right?

> Alternatively, we can add a new callback kvm_x86_ops->sched_out to x86
> KVM, and call vmx_get_cpl from the Intel implementation (vmx_sched_out).


In this approach, vmx_sched_out would only call vmx_get_cpl, isn't too
redundant, because we can just call kvm_x86_ops->get_cpl instead at the right place?

>  This will cache the result until the next sched_in, so that


'until the next sched_in' --> Do we need to clear the result in sched in ?

> kvm_vcpu_on_spin can use it.
> 
> Paolo
> 
> .
> 


-- 
Regards,
Longpeng(Mike)

[toc] | [prev] | [next] | [standalone]

#1700755

On 01/08/2017 05:26, Longpeng (Mike) wrote:
> 
> 
> On 2017/7/31 21:20, Paolo Bonzini wrote:
> 
>> On 31/07/2017 14:27, David Hildenbrand wrote:
>>>> I'm not sure whether the operation of get the vcpu's priority-level is
>>>> expensive on all architectures, so I record it in kvm_sched_out() for
>>>> minimal the extra cycles cost in kvm_vcpu_on_spin().
>>>>
>>> as you only care for x86 right now either way, you can directly optimize
>>> here for the good (here: x86) case (keeping changes and therefore
>>> possible bugs minimal).
>>
>> I agree with Cornelia that this is inconsistent, so you shouldn't update
>> me->in_kernmode in kvm_vcpu_on_spin.  However, get_cpl requires
>> vcpu_load on Intel x86, so Mike's patch is necessary (vmx_get_cpl ->
>> vmx_read_guest_seg_ar -> vmcs_read32).
>>
> 
> Hi Paolo,
> 
> It seems that other architectures(e.g. arm/s390) needn't to cache the result,
> but x86 need, so I need to move 'in_kernmode' into kvm_vcpu_arch and only add
> this field to x86, right?

That's another way to do it, and I like it.

>>  This will cache the result until the next sched_in, so that
> 
> 'until the next sched_in' --> Do we need to clear the result in sched in ?

No, thanks.

Paolo

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web