Re: [PATCH 00/19] Refresh queued CET virtualization series

[Paolo Bonzini <pbonzini@redhat.com>]

On 6/16/22 16:18, Peter Zijlstra wrote:
> On Thu, Jun 16, 2022 at 12:21:20PM +0200, Paolo Bonzini wrote:
>> On 6/16/22 12:12, Peter Zijlstra wrote:
>>> Do I understand this right in that a host without X86_KERNEL_IBT cannot
>>> run a guest with X86_KERNEL_IBT on? That seems unfortunate, since that
>>> was exactly what I did while developing the X86_KERNEL_IBT patches.
>>>
>>> I'm thinking that if the hardware supports it, KVM should expose it,
>>> irrespective of the host kernel using it.
>>
>> For IBT in particular, I think all processor state is only loaded and stored
>> at vmentry/vmexit (does not need XSAVES), so it should be feasible.
> 
> That would be the S_CET stuff, yeah, that's VMCS managed. The U_CET
> stuff is all XSAVE though.

What matters is whether XFEATURE_MASK_USER_SUPPORTED includes 
XFEATURE_CET_USER.  If you build with !X86_KERNEL_IBT, KVM can still 
rely on the FPU state for U_CET state, and S_CET is saved/restored via 
the VMCS independent of X86_KERNEL_IBT.

Paolo

> But funny thing, CPUID doesn't enumerate {U,S}_CET separately. It *does*
> enumerate IBT and SS separately, but for each IBT/SS you have to
> implement both U and S.
> 
> That was a problem with the first series, which only implemented support
> for U_CET while advertising IBT and SS (very much including S_CET), and
> still is a problem with this series because S_SS is missing while
> advertised.