Re: [Qemu-devel] [PATCH][uq/master] kvm: x86: Save/restore FPU OP, IP and DP

[Jan Kiszka <jan.kiszka@web.de>]

[-- Attachment #1: Type: text/plain, Size: 1617 bytes --]

On 2011-06-14 10:23, Avi Kivity wrote:
> On 06/14/2011 09:10 AM, Jan Kiszka wrote:
>> On 2011-06-13 10:45, Avi Kivity wrote:
>> >  On 06/11/2011 12:23 PM, Jan Kiszka wrote:
>> >>  From: Jan Kiszka<jan.kiszka@siemens.com>
>> >>
>> >>  These FPU states are properly maintained by KVM but not yet by
>> TCG. So
>> >>  far we unconditionally set them to 0 in the guest which may cause
>> >>  state corruptions - not only during migration.
>> >>
>> >>
>> >>  -#define CPU_SAVE_VERSION 12
>> >>  +#define CPU_SAVE_VERSION 13
>> >>
>> >
>> >  Incrementing the version number seems excessive - I can't imagine a
>> >  real-life guest will break due to fp pointer corruption
>> >
>> >  However, I don't think we have a mechanism for optional state.  We
>> >  discussed this during the 18th VMState Subsection Symposium and IIRC
>> >  agreed to re-raise the issue when we encountered it, which appears
>> to be
>> >  now.
>> >
>>
>> Whatever we invent, it has to be backported as well to allow that
>> infamous traveling back in time, migrating VMs from newer to older
>> versions.
>>
>> Would that backporting be simpler if we used an unconditional subsection
>> for the additional states?
> 
> Most likely.  It depends on what mechanism we use.
> 
> Let's spend some time to think about what it would be like.  This patch
> is not urgent, is it? (i.e. it was discovered by code inspection, not
> live migration that caught the cpu between an instruction that caused a
> math exception and the exception handler).

Right, not urgent, should just make it into 0.15 in the end.

Jan


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 259 bytes --]