Date:   Wed, 15 Feb 2023 14:16:07 -0800
In-Reply-To: <20d189fc-8d20-8083-b448-460cc0420151@linux.microsoft.com>
Mime-Version: 1.0
References: <43980946-7bbf-dcef-7e40-af904c456250@linux.microsoft.com>
 <Y+p1j7tYT+16MX6B@google.com> <35ff8f48-2677-78ea-b5f3-329c75ce65c9@redhat.com>
 <Y+qLe42h9ZPRINrG@google.com> <CABgObfaZQOvt6v0yGz3MR7FBU7DcrTTGmS6M8RWCX0uy6WML1Q@mail.gmail.com>
 <20d189fc-8d20-8083-b448-460cc0420151@linux.microsoft.com>
Message-ID: <Y+1ZpxAkome9s1Ve@google.com>
Subject: Re: "KVM: x86/mmu: Overhaul TDP MMU zapping and flushing" breaks SVM
 on Hyper-V
From:   Sean Christopherson <seanjc@google.com>
To:     Jeremi Piotrowski <jpiotrowski@linux.microsoft.com>
Cc:     Paolo Bonzini <pbonzini@redhat.com>, kvm@vger.kernel.org,
        linux-kernel@vger.kernel.org, Tianyu Lan <ltykernel@gmail.com>,
        "Michael Kelley (LINUX)" <mikelley@microsoft.com>
Content-Type: text/plain; charset="us-ascii"
Precedence: bulk

On Tue, Feb 14, 2023, Jeremi Piotrowski wrote:
> On 13/02/2023 20:56, Paolo Bonzini wrote:
> > On Mon, Feb 13, 2023 at 8:12 PM Sean Christopherson <seanjc@google.com> wrote:
> >>> Depending on the performance results of adding the hypercall to
> >>> svm_flush_tlb_current, the fix could indeed be to just disable usage of
> >>> HV_X64_NESTED_ENLIGHTENED_TLB.
> >>
> >> Minus making nested SVM (L3) mutually exclusive, I believe this will do the trick:
> >>
> >> +       /* blah blah blah */
> >> +       hv_flush_tlb_current(vcpu);
> >> +
> > 
> > Yes, it's either this or disabling the feature.
> > 
> > Paolo
> 
> Combining the two sub-threads: both of the suggestions:
> 
> a) adding a hyperv_flush_guest_mapping(__pa(root->spt) after kvm_tdp_mmu_get_vcpu_root_hpa's call to tdp_mmu_alloc_sp()
> b) adding a hyperv_flush_guest_mapping(vcpu->arch.mmu->root.hpa) to svm_flush_tlb_current()
> 
> appear to work in my test case (L2 vm startup until panic due to missing rootfs).
> 
> But in both these cases (and also when I completely disable HV_X64_NESTED_ENLIGHTENED_TLB)
> the runtime of an iteration of the test is noticeably longer compared to tdp_mmu=0.

Hmm, what is test doing?

> So in terms of performance the ranking is (fastest to slowest):
> 1. tdp_mmu=0 + enlightened TLB
> 2. tdp_mmu=0 + no enlightened TLB
> 3. tdp_mmu=1 (enlightened TLB makes minimal difference)