Re: [PATCH v2 RESEND] x86/asm: Force native_apic_mem_read to use mov

[Sean Christopherson]

On Wed, Sep 14, 2022, Dave Hansen wrote:
> On 9/14/22 04:13, Peter Gonda wrote:
> > On Thu, Sep 8, 2022 at 6:05 PM Adam Dunlap <acdunlap@xxxxxxxxxx> wrote:
> >> Previously, when compiled with clang, native_apic_mem_read gets inlined
> >> into __xapic_wait_icr_idle and optimized to a testl instruction. When
> >> run in a VM with SEV-ES enabled, it attempts to emulate this
> >> instruction, but the emulator does not support it. Instead, use inline
> >> assembly to force native_apic_mem_read to use the mov instruction which
> >> is supported by the emulator.
> > This seems to be an issue with the SEV-ES in guest #VC handler's
> > "emulator" right?
> 
> No.
> 
> It's not just an SEV-ES thing.  It's a problem for TDX and _probably_ a
> problem for normal virtualization where it's a host-side issue.  Kirill
> wrote a lot of great background information in here:
> 
> > https://lore.kernel.org/all/164946765464.4207.3715751176055921036.tip-bot2@tip-bot2/
> 
> So, the question is not "should we extend the MMIO instruction decoders
> to handle one more instruction?".  It is "should we extend the MMIO
> decoders to handle *ALL* memory read instructions?"
> 
> That's an even more emphatic "NO".

+1, keep the guest-side decoding as simple as possible.

> readl() seems to be the right thing to do.  Also, Dear TDX, SEV and virt
> folks: please look for more of these.  They're going to bite you sooner
> or later.  You should have caught this one before now.