[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <c3c84251-44b0-cff1-9607-b3686f1196b0@redhat.com>
Date: Mon, 8 Nov 2021 12:18:11 +0100
From: Paolo Bonzini <pbonzini@...hat.com>
To: zhenwei pi <pizhenwei@...edance.com>,
Maxim Levitsky <mlevitsk@...hat.com>,
Kele Huang <huangkele@...edance.com>
Cc: chaiwen.cc@...edance.com, xieyongji@...edance.com,
dengliang.1214@...edance.com, wanpengli@...cent.com,
seanjc@...gle.com, Vitaly Kuznetsov <vkuznets@...hat.com>,
Jim Mattson <jmattson@...gle.com>,
Joerg Roedel <joro@...tes.org>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
Dave Hansen <dave.hansen@...ux.intel.com>, x86@...nel.org,
"H. Peter Anvin" <hpa@...or.com>, kvm@...r.kernel.org,
linux-kernel@...r.kernel.org
Subject: Re: [RFC] KVM: x86: SVM: don't expose PV_SEND_IPI feature with AVIC
On 11/8/21 12:14, zhenwei pi wrote:
> I don't yet know if there is a solution to this which doesn't
> involve some management software decision (e.g libvirt or higher).
If we use a new hint, there's no problems with migration from/to older
QEMU and libvirt's host-model/host-passthrough would pick up the bit
automatically.
(I'm not sure if libvirt knows that hints can change across migration,
though).
Paolo
Powered by blists - more mailing lists