[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ea0e3852-87ba-984b-4010-5eeac3d6c507@suse.com>
Date: Mon, 13 Mar 2023 09:56:55 +0100
From: Jan Beulich <jbeulich@...e.com>
To: Huang Rui <ray.huang@....com>
Cc: Alex Deucher <alexander.deucher@....com>,
Christian König <christian.koenig@....com>,
Stewart Hildebrand <Stewart.Hildebrand@....com>,
Xenia Ragiadakou <burzalodowa@...il.com>,
Honglei Huang <honglei1.huang@....com>,
Julia Zhang <julia.zhang@....com>,
Chen Jiqian <Jiqian.Chen@....com>,
Juergen Gross <jgross@...e.com>,
Stefano Stabellini <sstabellini@...nel.org>,
Oleksandr Tyshchenko <oleksandr_tyshchenko@...m.com>,
Boris Ostrovsky <boris.ostrovsky@...cle.com>,
Roger Pau Monné <roger.pau@...rix.com>,
xen-devel@...ts.xenproject.org, linux-kernel@...r.kernel.org,
dri-devel@...ts.freedesktop.org, amd-gfx@...ts.freedesktop.org
Subject: Re: [RFC PATCH 1/5] x86/xen: disable swiotlb for xen pvh
On 12.03.2023 13:01, Huang Rui wrote:
> Xen PVH is the paravirtualized mode and takes advantage of hardware
> virtualization support when possible. It will using the hardware IOMMU
> support instead of xen-swiotlb, so disable swiotlb if current domain is
> Xen PVH.
But the kernel has no way (yet) to drive the IOMMU, so how can it get
away without resorting to swiotlb in certain cases (like I/O to an
address-restricted device)?
Jan
Powered by blists - more mailing lists