[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <9f06872d-f0ec-43c3-9b53-d144337100b3@www.fastmail.com>
Date: Fri, 26 Mar 2021 17:10:29 +0100
From: "Sven Peter" <sven@...npeter.dev>
To: "Mark Kettenis" <mark.kettenis@...all.nl>,
"Arnd Bergmann" <arnd@...nel.org>
Cc: "Rob Herring" <robh@...nel.org>, iommu@...ts.linux-foundation.org,
joro@...tes.org, "Will Deacon" <will@...nel.org>,
"Robin Murphy" <robin.murphy@....com>,
"Hector Martin" <marcan@...can.st>,
"Marc Zyngier" <maz@...nel.org>, mohamed.mediouni@...amail.com,
stan@...ellium.com, linux-arm-kernel@...ts.infradead.org,
linux-kernel@...r.kernel.org, devicetree@...r.kernel.org
Subject: Re: [PATCH 0/3] Apple M1 DART IOMMU driver
On Fri, Mar 26, 2021, at 16:59, Mark Kettenis wrote:
> Some of the DARTs provide a bypass facility. That code make using the
> standard "dma-ranges" property tricky. That property would need to
> contain the bypass address range. But that would mean that if the
> DART driver needs to look at that property to figure out the address
> range that supports translation it will need to be able to distinguish
> between the translatable address range and the bypass address range.
Do we understand if and why we even need to bypass certain streams?
And do you have an example for a node in the ADT that contains this bypass range?
I've only seen nodes with "bypass" and "bypass-adress" but that could just be
some software abstraction Apple uses which doesn't map well to Linux or other OSes
and might not even be required here.
Sven
Powered by blists - more mailing lists