RE: [Xen-ia64-devel][PATCH][VTD] small patches for VTD

["Xu, Anthony" <anthony.xu@xxxxxxxxx>]

Hi shimura

I only tested in old version 18134.
I can reproduce it.
And I find another way to handle it,
Will send out patch soon.

Thanks,
anthony


Kouya Shimura wrote:
> Hi Anthony,
>
> Xu, Anthony writes:
>>>> -    if (phy_pte.ma != VA_MATTR_NATPAGE)
>>>> +    /* if a device is assigned to a domain through VTD, the MMIO
>>>> for this +     * device needs to retain to UC attribute +     */
>>>> +    if (phy_pte.ma == VA_MATTR_WC)
>>>>          phy_pte.ma = VA_MATTR_WB;
>>>>
>>>
>>> Doesn't this break the intention of the c/s 15134:466f71b1e831?a
>>> To be honest, I'm not sure. Kyouya or Akio, do you have any
>>> comments?
>>>
>> This section is not included, need kyouya or akio confirmation.
>
> I applied only this hunk and tried invoking HVMs (windows2003 and
> RHEL5.1).
> In both of them, the system silently rebooted.
> The following Machine Check occurred.
>
>   BUS Check Info [0]
>     Transaction size: 0, Internal Bus Error:, Type: 1 (Partial read),
>   Severity: 0, Hierarchy: 0, Status information: 0
> (Unknown/unclassified) CPUID Regs: 0x49656e69756e6547 0x6c65746e 0
> 0x20000504
>
> I have no idea what's going on, though my machine might be
> ill-conditioned.
>
> Have you tested it?

_______________________________________________
Xen-ia64-devel mailing list
Xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-ia64-devel