Re: [PATCH v1 2/2] KVM: arm64: allow the VM to select DEVICE_* and NORMAL_NC for IO memory

[Lorenzo Pieralisi]

On Thu, Oct 12, 2023 at 10:20:45AM -0300, Jason Gunthorpe wrote:
> On Thu, Oct 12, 2023 at 01:35:41PM +0100, Will Deacon wrote:
> 
> > > Failures containability is a property of the platform
> > > and is independent from the memory type used for MMIO
> > > device memory mappings (ie DEVICE_nGnRE memory type is
> > > even more problematic than NormalNC in terms of containability
> > > since eg aborts triggered on loads cannot be made synchronous,
> > > which make them harder to contain); this means that,
> > > regardless of the combined stage1+stage2 mappings a
> > > platform is safe if and only if device transactions cannot trigger
> > > uncontained failures; reworded, the default KVM device
> > > stage 2 memory attributes play no role in making device
> > > assignment safer for a given platform and therefore can
> > > be relaxed.
> > > 
> > > For all these reasons, relax the KVM stage 2 device
> > > memory attributes from DEVICE_nGnRE to NormalNC.
> > 
> > The reasoning above suggests to me that this should probably just be
> > Normal cacheable, as that is what actually allows the guest to control
> > the attributes. So what is the rationale behind stopping at Normal-NC?
> 
> I agree it would be very nice if the all the memory in the guest could
> just be cachable and the guest could select everything.
> 
> However, I think Lorenzo over stated the argument.
>
> The off-list discussion was focused on NormalNC for MMIO only. Nobody
> raised the idea that cachable was safe from uncontained errors for
> MMIO.

True, it should be made clearer ie "independent from the
non-cacheable/uncacheable memory type...", please update the
log accordingly, forgive me the confusion I raised.

Lorenzo
 
> I'm looking through the conversations and I wouldn't jump to
> concluding that "cachable MMIO" is safe from uncontained failures.
> 
> Catalin has already raised a number of conerns in the other patch
> about making actual "designed to be cachable memory" into KVM
> cachable.
> 
> Regards,
> Jason