Re: [PATCH 0/6] MTRR/PAT support for EPT (v3)

[Sheng Yang <sheng@linux.intel.com>]

On Friday 10 October 2008 14:49:13 Avi Kivity wrote:
> Sheng Yang wrote:
> > Yeah, I think the condition I mentioned is a example of yours. But in
> > fact it's difficult to get a optimize value... I think it's possible that
> > qemu may access all memory it owned, if so, no guest mtrr would affect.
> > But how can we tell qemu would access which region of memory? We know it
> > for vram, but any other cases? Seems it's indeed a big potential
> > problem... If we want to do this, maybe we can hack something into host
> > cache consistent check, though it's pretty dirty and got limit usage...
>
> qemu will access all of memory, for example during live migration.
>
> So we need to distinguish between RAM and mmio somehow.

Yes... But it's easy to do with assigned devices' mmio, but what if guest 
specific some non-mmio memory's memory type? E.g. we have met one issue in 
Xen, that a assigned-device's XP driver specific one memory region as buffer, 
and modify the memory type then do DMA.

Only map MMIO space can be first step, but I guess we can modify assigned 
memory region memory type follow guest's? 

--
regards
Yang, Sheng