[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <87bkscxn3r.fsf@redhat.com>
Date: Mon, 22 Aug 2022 18:24:40 +0200
From: Vitaly Kuznetsov <vkuznets@...hat.com>
To: Sean Christopherson <seanjc@...gle.com>
Cc: kvm@...r.kernel.org, Paolo Bonzini <pbonzini@...hat.com>,
Anirudh Rayabharam <anrayabh@...ux.microsoft.com>,
Wanpeng Li <wanpengli@...cent.com>,
Jim Mattson <jmattson@...gle.com>,
Maxim Levitsky <mlevitsk@...hat.com>,
Nathan Chancellor <nathan@...nel.org>,
Michael Kelley <mikelley@...rosoft.com>,
linux-hyperv@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v5 03/26] x86/hyperv: Update 'struct
hv_enlightened_vmcs' definition
Sean Christopherson <seanjc@...gle.com> writes:
> On Mon, Aug 22, 2022, Vitaly Kuznetsov wrote:
>> So I reached out to Microsoft and their answer was that for all these new
>> eVMCS fields (including *PerfGlobalCtrl) observing architectural VMX
>> MSRs should be enough. *PerfGlobalCtrl case is special because of Win11
>> bug (if we expose the feature in VMX feature MSRs but don't set
>> CPUID.0x4000000A.EBX BIT(0) it just doesn't boot).
>
> Does this mean that KVM-on-HyperV needs to avoid using the PERF_GLOBAL_CTRL fields
> when the bit is not set?
It doesn't have to, based on the reply I got from Microsoft, if
PERF_GLOBAL_CTRL is exposed in architectural VMX feature MSRs than eVMCS
fields are guaranteed to be present. The PV bit is 'extra'.
--
Vitaly
Powered by blists - more mailing lists