Re: [PATCH] KMV: VMX: consult IA32_VMX_EPT_VPID_CAP to determine EPT paging-structure memory type

[Gui Jianfeng <guijianfeng@cn.fujitsu.com>]

Avi Kivity wrote:
> On 03/22/2010 11:13 AM, Sheng Yang wrote:
>>
>>> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
>>> index 06108f3..f971b9b 100644
>>> --- a/arch/x86/kvm/vmx.c
>>> +++ b/arch/x86/kvm/vmx.c
>>> @@ -1804,9 +1804,15 @@ static u64 construct_eptp(unsigned long root_hpa)
>>>   {
>>>       u64 eptp;
>>>
>>> -    /* TODO write the value reading from MSR */
>>> -    eptp = VMX_EPT_DEFAULT_MT |
>>> -        VMX_EPT_DEFAULT_GAW<<  VMX_EPT_GAW_EPTP_SHIFT;
>>> +    if (cpu_has_vmx_eptp_writeback())
>>> +        eptp = VMX_EPT_MT_WRBACK |
>>> +            VMX_EPT_DEFAULT_GAW<<  VMX_EPT_GAW_EPTP_SHIFT;
>>>      
>> I prefer to ensure WB is supported and used as default. Otherwise it
>> would be
>> a big trouble for memory subsystem(to use UC for all memory). Both WB
>> and UC
>> EPT memory types are ensured to be support in hardware.
>>
>> And you can remove VMX_EPT_DEFAULT_MT as well.
>>    
> 
> I agree, hopefully we never ever see a cpu that doesn't support EPT WB.

OK, seems we don't need to have this concern. :)

>