Re: Booting/installing WindowsNT

[Andre Przywara <andre.przywara@amd.com>]

Avi Kivity wrote:
> On 05/05/2010 11:32 AM, Andre Przywara wrote:
>> Avi Kivity wrote:
>>> On 05/04/2010 06:27 PM, Andre Przywara wrote:
>>>>
>>>>> 3.  In all other cases so far it BSoDs with STOP 0x3E error
>>>>>   right before displaying that kernel message.
>>>> MSDN talks about a mulitprocessor configuration error:
>>>> http://msdn.microsoft.com/en-us/library/ms819006.aspx
>>>> I suspected the offline CPUs in the mptable that confuse NT. But 
>>>> -smp 1,maxcpus=1 does not make a difference. I will try to dig 
>>>> deeper in this area.
>> OK, I tackled this down. It is the max CPUID level that differs.
>> In the AMD CPUID guide leafs 0000_0002 till 0000_0004 are reserved, 
>> the CPU that Michael and I used (K8RevF) actually have a max leaf of 1 
>> here.
>> Default qemu64 has a max leaf of 4.
>> So by saying -cpu qemu64,level=1 (or 2 or 3) it works for me.
>> Modern OS only read leaf 4 on Intel systems, it seems that NT4 is 
>> missing this.
>> I will now think about a proper fix for this.
> 
> I don't understand.  Shouldn't the values for cpuid leaf 4 be the same 
> for qemu64 whether the cpu is Intel or AMD?  The real cpuid shouldn't 
> matter.
Yes, but if the max leaf value is smaller than 4, then the guest will 
not read it. It seems that NT does not like the entries returned by KVM 
for leaf 4. I am about to find out what exactly is causing that.
I have the theory that the stop is intentional as NT4 workstation does 
not _want_ to support certain SMP configurations (more than 2 
processors?) I have seen similar issue with WinXPPro and -smp 4 (which 
went away with -smp 4,cores=4).

Regards,
Andre.

-- 
Andre Przywara
AMD-Operating System Research Center (OSRC), Dresden, Germany
Tel: +49 351 448-3567-12