linux-kernel - Re: 回复: Re: [PATCH] kvm: fix gpu passthrough into vm on arm64

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [day] [month] [year] [list]

Message-ID: <87ils25ghk.wl-maz@kernel.org>
Date:   Fri, 25 Mar 2022 13:06:15 +0000
From:   Marc Zyngier <maz@...nel.org>
To:     谢明 <xieming@...inos.cn>
Cc:     <christoffer.dall@....com>, <kvmarm@...ts.cs.columbia.edu>,
        <linux-arm-kernel@...ts.infradead.org>,
        <linux-kernel@...r.kernel.org>
Subject: Re: 回复: Re: [PATCH] kvm: fix gpu passthrough
 into vm on arm64

On Fri, 25 Mar 2022 01:06:17 +0000,
谢明 <xieming@...inos.cn> wrote:
> 
>    thanks for your reply !
>        you are right, 'If the device supports NORMAL_NC, this should
> be known by the host kernel and exposed to KVM'， accordding the kvm
> combining rules on arm64， stage1 is setting to NORMAL_NC， so can
> we add a conditional judement when ioremapping on stage2, if the
> device suppurt NORMAL_NC we setting the memory attribute to
> PAGE_S2_NC ?

The question remains: how do you convey that capability to the host?
There is nothing currently telling KVM what memory type to use.

	M.

-- 
Without deviation from the norm, progress is not possible.