[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20210504083005.GA12290@willie-the-truck>
Date: Tue, 4 May 2021 09:30:05 +0100
From: Will Deacon <will@...nel.org>
To: Vikram Sethi <vsethi@...dia.com>
Cc: Alex Williamson <alex.williamson@...hat.com>,
Mark Kettenis <mark.kettenis@...all.nl>,
Marc Zyngier <maz@...nel.org>,
Shanker Donthineni <sdonthineni@...dia.com>,
"catalin.marinas@....com" <catalin.marinas@....com>,
"christoffer.dall@....com" <christoffer.dall@....com>,
"linux-arm-kernel@...ts.infradead.org"
<linux-arm-kernel@...ts.infradead.org>,
"kvmarm@...ts.cs.columbia.edu" <kvmarm@...ts.cs.columbia.edu>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"kvm@...r.kernel.org" <kvm@...r.kernel.org>,
Jason Sequeira <jsequeira@...dia.com>
Subject: Re: [RFC 1/2] vfio/pci: keep the prefetchable attribute of a BAR
region in VMA
On Mon, May 03, 2021 at 10:03:59PM +0000, Vikram Sethi wrote:
> Will/Catalin, perhaps you could explain your thought process on why you chose
> Normal NC for ioremap_wc on the armv8 linux port instead of Device GRE or other
> Device Gxx.
I think a combination of: compatibility with 32-bit Arm, the need to
support unaligned accesses and the potential for higher performance.
Furthermore, ioremap() already gives you a Device memory type, and we're
tight on MAIR space.
Will
Powered by blists - more mailing lists