Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
Message-ID: <6690c53c-fc99-44ea-9090-6e7438c1bc98@default>
Date:   Thu, 25 Jan 2018 01:55:06 -0800 (PST)
From:   Liran Alon <liran.alon@oracle.com>
To:     <vkuznets@redhat.com>
Cc:     <x86@kernel.org>, <rkrcmar@redhat.com>, <pbonzini@redhat.com>,
        <linux-kernel@vger.kernel.org>, <kvm@vger.kernel.org>
Subject: Re: [PATCH] x86/kvm: disable fast MMIO when running nested
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: quoted-printable
Content-Disposition: inline
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk


----- vkuznets@redhat.com wrote:

> I was investigating an issue with seabios >=3D 1.10 which stopped
> working
> for nested KVM on Hyper-V. The problem appears to be in
> handle_ept_violation() function: when we do fast mmio we need to skip
> the instruction so we do kvm_skip_emulated_instruction(). This,
> however,
> depends on VM_EXIT_INSTRUCTION_LEN field being set correctly in VMCS.
> However, this is not the case.
>=20
> Intel's manual doesn't mandate VM_EXIT_INSTRUCTION_LEN to be set when
> EPT MISCONFIG occurs. While on real hardware it was observed to be
> set,
> some hypervisors follow the spec and don't set it; we end up
> advancing
> IP with some random value.
>=20
> I checked with Microsoft and they confirmed they don't fill
> VM_EXIT_INSTRUCTION_LEN on EPT MISCONFIG.
>=20
> Fix the issue by disabling fast mmio when running nested.
>=20
> Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
> ---
>  arch/x86/kvm/vmx.c | 9 ++++++++-
>  1 file changed, 8 insertions(+), 1 deletion(-)
>=20
> diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
> index c829d89e2e63..54afb446f38e 100644
> --- a/arch/x86/kvm/vmx.c
> +++ b/arch/x86/kvm/vmx.c
> @@ -6558,9 +6558,16 @@ static int handle_ept_misconfig(struct kvm_vcpu
> *vcpu)
>  =09/*
>  =09 * A nested guest cannot optimize MMIO vmexits, because we have an
>  =09 * nGPA here instead of the required GPA.
> +=09 * Skipping instruction below depends on undefined behavior:
> Intel's
> +=09 * manual doesn't mandate VM_EXIT_INSTRUCTION_LEN to be set in VMCS
> +=09 * when EPT MISCONFIG occurs and while on real hardware it was
> observed
> +=09 * to be set, other hypervisors (namely Hyper-V) don't set it, we
> end
> +=09 * up advancing IP with some random value. Disable fast mmio when
> +=09 * running nested and keep it for real hardware in hope that
> +=09 * VM_EXIT_INSTRUCTION_LEN will always be set correctly.

If Intel manual doesn't mandate VM_EXIT_INSTRUCTION_LEN to be set in VMCS o=
n EPT_MISCONFIG,
I don't think we should do this on real-hardware as-well.

-Liran

>  =09 */
>  =09gpa =3D vmcs_read64(GUEST_PHYSICAL_ADDRESS);
> -=09if (!is_guest_mode(vcpu) &&
> +=09if (!static_cpu_has(X86_FEATURE_HYPERVISOR) && !is_guest_mode(vcpu)
> &&
>  =09    !kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
>  =09=09trace_kvm_fast_mmio(gpa);
>  =09=09return kvm_skip_emulated_instruction(vcpu);
> --=20
> 2.14.3