gt; > de...@nongnu.org' ; 'bd.a...@gmail.com'
> >
> > Subject: Re: [Qemu-devel] [RFC PATCH 11/13] intel_iommu: provide its own
> > replay()
> > callback
> >
> > On Thu, Dec 29, 2016 at 10:23:21AM +, Liu, Yi L wrote:
> >
> > [...]
&g
> -Original Message-
> From: Peter Xu [mailto:pet...@redhat.com]
> Sent: Friday, December 30, 2016 11:44 AM
> To: Liu, Yi L
> Cc: Tian, Kevin ; Lan, Tianyu ;
> 'qemu-
> de...@nongnu.org' ; 'bd.a...@gmail.com'
>
> Subject: Re: [Qemu-devel]
On Thu, Dec 29, 2016 at 10:23:21AM +, Liu, Yi L wrote:
[...]
> > >
> > > Hereby, I have a minor concern on this part.
> > > The replay would be performed in vfio_listener_region_add() when device is
> > > assigned. Since guest is just started, so there will be no valid context
> > > entry fo
> -Original Message-
> From: Peter Xu [mailto:pet...@redhat.com]
> Sent: Thursday, December 29, 2016 5:56 PM
> To: Liu, Yi L
> Cc: Tian, Kevin ; Lan, Tianyu ;
> 'qemu-
> de...@nongnu.org' ; 'bd.a...@gmail.com'
>
> Subject: Re: [Qemu-devel]
On Thu, Dec 29, 2016 at 07:38:20AM +, Liu, Yi L wrote:
[...]
> > +static void vtd_iommu_replay(MemoryRegion *mr, IOMMUNotifier *n)
> > +{
> > +VTDAddressSpace *vtd_as = container_of(mr, VTDAddressSpace, iommu);
> > +IntelIOMMUState *s = vtd_as->iommu_state;
> > +uint8_t bus_n = pc
> The default replay() don't work for VT-d since vt-d will have a huge
> default memory region which covers address range 0-(2^64-1). This will
> normally bring a dead loop when guest starts.
>
> The solution is simple - we don't walk over all the regions. Instead, we
> jump over the regions when
On Thu, Dec 08, 2016 at 11:01:53AM +0800, Lan Tianyu wrote:
> On 2016年12月06日 18:36, Peter Xu wrote:
> > +/**
> > + * vtd_page_walk - walk specific IOVA range, and call the hook
> > + *
> > + * @ce: context entry to walk upon
> > + * @start: IOVA address to start the walk
> > + * @end: size of the I
On 2016年12月06日 18:36, Peter Xu wrote:
> +/**
> + * vtd_page_walk - walk specific IOVA range, and call the hook
> + *
> + * @ce: context entry to walk upon
> + * @start: IOVA address to start the walk
> + * @end: size of the IOVA range to walk over
*·@end:·IOVA·range·end·address·(start·<=·addr·<·e
The default replay() don't work for VT-d since vt-d will have a huge
default memory region which covers address range 0-(2^64-1). This will
normally bring a dead loop when guest starts.
The solution is simple - we don't walk over all the regions. Instead, we
jump over the regions when we found tha
