Re: [RFC Patch 3/3] KVM/x86: Add tlb_remote_flush callback support for vmcs

[Tianyu Lan]

On 6/14/2018 6:33 PM, Vitaly Kuznetsov wrote:
> Tianyu Lan <Tianyu.Lan@xxxxxxxxxxxxx> writes:
> 
>> On 6/12/2018 11:12 PM, Vitaly Kuznetsov wrote:
>>> Tianyu Lan <Tianyu.Lan@xxxxxxxxxxxxx> writes:
>>>
>>>>
>>>> +static int vmx_remote_flush_tlb(struct kvm *kvm)
>>>> +{
>>>> +	struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, 0);
>>>> +
>>>> +	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
>>>> +		return -1;
>>>
>>> Why vcpu0? Can arch.mmu.root_hpa-s differ across vCPUs? What happens if
>>> they do?
>>
>> Yes, it may take place that arch.mmu.root_hpa is differ across vCPUs.
>> We may check all vcpu root_hpa and use the hypercall when there is only
>> one validated ept table. If not, go back to current way.
>>
> 
> I'd suggest an optimization: keep track of wether root_hpas are equal
> across all vcpus (check this on change).
> 

Good suggestion. I will try it. Thanks.