Re: [PATCH] KVM: x86/mmu: Avoid retpoline on ->page_fault() with TDP

[Vitaly Kuznetsov]

Sean Christopherson <sean.j.christopherson@xxxxxxxxx> writes:

> On Fri, Feb 07, 2020 at 10:29:16AM +0100, Vitaly Kuznetsov wrote:
>> Sean Christopherson <sean.j.christopherson@xxxxxxxxx> writes:
>> 
>> > Wrap calls to ->page_fault() with a small shim to directly invoke the
>> > TDP fault handler when the kernel is using retpolines and TDP is being
>> > used.  Denote the TDP fault handler by nullifying mmu->page_fault, and
>> > annotate the TDP path as likely to coerce the compiler into preferring
>> > the TDP path.
>> >
>> > Rename tdp_page_fault() to kvm_tdp_page_fault() as it's exposed outside
>> > of mmu.c to allow inlining the shim.
>> >
>> > Signed-off-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
>> > ---
>> 
>> Out of pure curiosity, if we do something like
>> 
>> if (vcpu->arch.mmu->page_fault == tdp_page_fault)
>>     tdp_page_fault(...)
>> else if (vcpu->arch.mmu->page_fault == nonpaging_page_fault)
>>    nonpaging_page_fault(...)
>> ...
>> 
>> we also defeat the retpoline, right?
>
> Yep.
>
>> Should we use this technique ... everywhere? :-)
>
> It becomes a matter of weighing the maintenance cost and robustness against
> the performance benefits.  For the TDP case, amost no one (that cares about
> performance) uses shadow paging, the change is very explicit, tiny and
> isolated, and TDP page fault are a hot path, e.g. when booting the VM.
> I.e. low maintenance overhead, still robust, and IMO worth the shenanigans.
>
> The changes to VMX's VM-Exit handlers follow similar thinking: snipe off
> the exit handlers that are performance critical, but use a low maintenance
> implementation for the majority of handlers.
>
> There have been multiple attempts to add infrastructure to solve the
> maintenance and robustness problems[*], but AFAIK none of them have made
> their way upstream.
>
> [*] https://lwn.net/Articles/774743/
>

Oh I see, missed some of these discussion.

And I actualy forgot to say:

Reviewed-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>

as the patch itself looks good to me, I was just wondering about the
approach in general.

-- 
Vitaly