[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <3d9db6dd-3598-7cbe-fb70-46a36110da3b@amd.com>
Date: Tue, 12 Sep 2017 08:07:22 -0700
From: Suravee Suthikulpanit <Suravee.Suthikulpanit@....com>
To: Paolo Bonzini <pbonzini@...hat.com>,
Radim Krčmář <rkrcmar@...hat.com>
Cc: linux-kernel@...r.kernel.org, kvm@...r.kernel.org, joro@...tes.org
Subject: Re: [PATCH 3/3] KVM: SVM: Add irqchip_split() checks before enabling
AVIC
On 9/12/17 07:22, Paolo Bonzini wrote:
> On 12/09/2017 15:17, Radim Krčmář wrote:
>>>> Yeah, hacking TMR to get the VM exit could result in future bugs.
>>>> We have to push split irqchip as the deafult in userspaces with this
>>>> change.
>>> Actually, I'm not quite sure about the advantages/disadvantages with split
>>> irqchip, and how it would affect other cases, and why it was not used as
>>> default currently.
>> The main advantage of split irqchip is that we're moving code out of the
>> kernel, and QEMU's irqchip currently has more features too.
>>
>> I think it is not the default as the support for split irqchip is recent
>> (v4.3) and has lower performance, so it is only used in cases that need
>> the extra features.
>
> One other difference is that in-kernel PIT is not supported with
> split-irqchip, and the QEMU PIT lacks support for reinjecting lost
> ticks. But this should only be needed for very old guests at this point.
>
> Paolo
>
Thanks. I'll look into patch for changing the default in QEMU and follow up with
that separately then.
Suravee
Powered by blists - more mailing lists