Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Subject: Re: [PATCH 0/2] RFC: Precise TSC migration
To:     Andy Lutomirski <luto@kernel.org>,
        Maxim Levitsky <mlevitsk@redhat.com>
Cc:     kvm list <kvm@vger.kernel.org>, Oliver Upton <oupton@google.com>,
        Ingo Molnar <mingo@redhat.com>,
        Sean Christopherson <sean.j.christopherson@intel.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        open list <linux-kernel@vger.kernel.org>,
        Marcelo Tosatti <mtosatti@redhat.com>,
        Jonathan Corbet <corbet@lwn.net>,
        Wanpeng Li <wanpengli@tencent.com>,
        Borislav Petkov <bp@alien8.de>,
        Jim Mattson <jmattson@google.com>,
        "H. Peter Anvin" <hpa@zytor.com>,
        "open list:DOCUMENTATION" <linux-doc@vger.kernel.org>,
        Joerg Roedel <joro@8bytes.org>,
        "maintainer:X86 ARCHITECTURE (32-BIT AND 64-BIT)" <x86@kernel.org>,
        Vitaly Kuznetsov <vkuznets@redhat.com>
References: <20201130133559.233242-1-mlevitsk@redhat.com>
 <CALCETrVr2bM4yJTVpQULN+EYVQJuWGCvjX0SMFsCRy6BwqZc0w@mail.gmail.com>
From:   Paolo Bonzini <pbonzini@redhat.com>
Message-ID: <26444d65-083b-5df4-52c9-c1cfad556b10@redhat.com>
Date:   Mon, 30 Nov 2020 17:59:08 +0100
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:78.0) Gecko/20100101
 Thunderbird/78.4.0
MIME-Version: 1.0
In-Reply-To: <CALCETrVr2bM4yJTVpQULN+EYVQJuWGCvjX0SMFsCRy6BwqZc0w@mail.gmail.com>
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Language: en-US
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 30/11/20 17:54, Andy Lutomirski wrote:
>> I*do think*  however that we should redefine KVM_CLOCK_TSC_STABLE
>> in the documentation to state that it only guarantees invariance if the guest
>> doesn't mess with its own TSC.
>>
>> Also I think we should consider enabling the X86_FEATURE_TSC_RELIABLE
>> in the guest kernel, when kvm is detected to avoid the guest even from trying
>> to sync TSC on newly hotplugged vCPUs.
>>
>> (The guest doesn't end up touching TSC_ADJUST usually, but it still might
>> in some cases due to scheduling of guest vCPUs)
>>
>> (X86_FEATURE_TSC_RELIABLE short circuits tsc synchronization on CPU hotplug,
>> and TSC clocksource watchdog, and the later we might want to keep).
> If you're going to change the guest behavior to be more trusting of
> the host, I think
> the host should probably signal this to the guest using a new bit.
> 

Yes, a new CPUID bit takes longer to propagate to existing setups, but 
it is more future proof.

Paolo