From: Julien Grall <julien.grall@linaro.org>
To: Stefano Stabellini <sstabellini@kernel.org>,
"Edgar E. Iglesias" <edgar.iglesias@gmail.com>
Cc: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com>,
"Wei Chen" <Wei.Chen@arm.com>,
"Steve Capper" <Steve.Capper@arm.com>,
"Andrew Cooper" <andrew.cooper3@citrix.com>,
"Jiandi An" <anjiandi@codeaurora.org>,
"Punit Agrawal" <punit.agrawal@arm.com>,
alistair.francis@xilinx.com,
"Campbell Sean" <scampbel@codeaurora.org>,
xen-devel <xen-devel@lists.xenproject.org>,
"manish.jaggi@caviumnetworks.com"
<manish.jaggi@caviumnetworks.com>,
"Shanker Donthineni" <shankerd@codeaurora.org>,
"Roger Pau Monné" <roger.pau@citrix.com>
Subject: Re: [early RFC] ARM PCI Passthrough design document
Date: Mon, 13 Feb 2017 15:39:57 +0000 [thread overview]
Message-ID: <ec30a7a6-a7ce-ec4a-fbee-16f28862f05e@linaro.org> (raw)
In-Reply-To: <alpine.DEB.2.10.1702091658420.20549@sstabellini-ThinkPad-X260>
Hi Stefano,
On 10/02/17 01:01, Stefano Stabellini wrote:
> On Fri, 3 Feb 2017, Edgar E. Iglesias wrote:
>> A possible hack could be to allocate a chunk of DDR dedicated for PCI DMA.
>> PCI DMA devs could be locked in to only be able to access this mem + MSI doorbell.
>> Guests can still screw each other up but at least it becomes harder to read/write directly from each others OS memory.
>> It may not be worth the effort though....
>
> Actually, we do have the swiotlb in Dom0, which can be used to bounce
> DMA requests over a buffer that has been previously setup to be DMA safe
> using an hypercall. That is how the swiotlb is used on x86. On ARM it is
> used to issue cache flushes via hypercall, but it could be adapted to do
> both. It would degrade performance, due to the additional memcpy, but it
> would work, I believe.
A while ago, Globallogic suggested to use direct memory mapping for the
guest to allow guest using DMA on platform not supporting SMMU.
I believe we can use the same trick on platform where SMMUs can not
distinguish PCI devices.
Cheers,
--
Julien Grall
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
next prev parent reply other threads:[~2017-02-13 15:40 UTC|newest]
Thread overview: 82+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-12-29 14:04 [early RFC] ARM PCI Passthrough design document Julien Grall
2016-12-29 14:16 ` Jaggi, Manish
2016-12-29 17:03 ` Julien Grall
2016-12-29 18:41 ` Jaggi, Manish
2016-12-29 19:38 ` Julien Grall
2017-01-04 0:24 ` Stefano Stabellini
2017-01-24 14:28 ` Julien Grall
2017-01-24 20:07 ` Stefano Stabellini
2017-01-25 11:21 ` Roger Pau Monné
2017-01-25 18:53 ` Julien Grall
2017-01-31 16:53 ` Edgar E. Iglesias
2017-01-31 17:09 ` Julien Grall
2017-01-31 19:06 ` Edgar E. Iglesias
2017-01-31 22:08 ` Stefano Stabellini
2017-02-01 19:04 ` Julien Grall
2017-02-01 19:31 ` Stefano Stabellini
2017-02-01 20:24 ` Julien Grall
2017-02-02 15:33 ` Edgar E. Iglesias
2017-02-02 23:12 ` Stefano Stabellini
2017-02-02 23:44 ` Edgar E. Iglesias
2017-02-10 1:01 ` Stefano Stabellini
2017-02-13 15:39 ` Julien Grall [this message]
2017-02-13 19:59 ` Stefano Stabellini
2017-02-14 17:21 ` Julien Grall
2017-02-14 18:20 ` Stefano Stabellini
2017-02-14 20:18 ` Julien Grall
2017-02-13 15:35 ` Julien Grall
2017-02-22 4:03 ` Edgar E. Iglesias
2017-02-23 16:47 ` Julien Grall
2017-03-02 21:13 ` Edgar E. Iglesias
2017-02-02 15:40 ` Roger Pau Monné
2017-02-13 16:22 ` Julien Grall
2017-01-31 21:58 ` Stefano Stabellini
2017-02-01 20:12 ` Julien Grall
2017-02-01 10:55 ` Roger Pau Monné
2017-02-01 18:50 ` Stefano Stabellini
2017-02-10 9:48 ` Roger Pau Monné
2017-02-10 10:11 ` Paul Durrant
2017-02-10 12:57 ` Roger Pau Monne
2017-02-10 13:02 ` Paul Durrant
2017-02-10 21:04 ` Stefano Stabellini
2017-02-02 12:38 ` Julien Grall
2017-02-02 23:06 ` Stefano Stabellini
2017-03-08 19:06 ` Julien Grall
2017-03-08 19:12 ` Konrad Rzeszutek Wilk
2017-03-08 19:55 ` Stefano Stabellini
2017-03-08 21:51 ` Julien Grall
2017-03-09 2:59 ` Roger Pau Monné
2017-03-09 11:17 ` Konrad Rzeszutek Wilk
2017-03-09 13:26 ` Julien Grall
2017-03-10 0:29 ` Konrad Rzeszutek Wilk
2017-03-10 3:23 ` Roger Pau Monné
2017-03-10 15:28 ` Konrad Rzeszutek Wilk
2017-03-15 12:07 ` Roger Pau Monné
2017-03-15 12:42 ` Konrad Rzeszutek Wilk
2017-03-15 12:56 ` Roger Pau Monné
2017-03-15 15:11 ` Venu Busireddy
2017-03-15 16:38 ` Roger Pau Monn?
2017-03-15 16:54 ` Venu Busireddy
2017-03-15 17:00 ` Roger Pau Monn?
2017-05-03 12:38 ` Julien Grall
2017-05-03 12:53 ` Julien Grall
2017-01-25 4:23 ` Manish Jaggi
2017-01-06 15:12 ` Roger Pau Monné
2017-01-06 21:16 ` Stefano Stabellini
2017-01-24 17:17 ` Julien Grall
2017-01-25 11:42 ` Roger Pau Monné
2017-01-31 15:59 ` Julien Grall
2017-01-31 22:03 ` Stefano Stabellini
2017-02-01 10:28 ` Roger Pau Monné
2017-02-01 18:45 ` Stefano Stabellini
2017-01-06 16:27 ` Edgar E. Iglesias
2017-01-06 21:12 ` Stefano Stabellini
2017-01-09 17:50 ` Edgar E. Iglesias
2017-01-19 5:09 ` Manish Jaggi
2017-01-24 17:43 ` Julien Grall
2017-01-25 4:37 ` Manish Jaggi
2017-01-25 15:25 ` Julien Grall
2017-01-30 7:41 ` Manish Jaggi
2017-01-31 13:33 ` Julien Grall
2017-05-19 6:38 ` Goel, Sameer
2017-05-19 16:48 ` Julien Grall
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=ec30a7a6-a7ce-ec4a-fbee-16f28862f05e@linaro.org \
--to=julien.grall@linaro.org \
--cc=Steve.Capper@arm.com \
--cc=Wei.Chen@arm.com \
--cc=alistair.francis@xilinx.com \
--cc=andrew.cooper3@citrix.com \
--cc=anjiandi@codeaurora.org \
--cc=edgar.iglesias@gmail.com \
--cc=edgar.iglesias@xilinx.com \
--cc=manish.jaggi@caviumnetworks.com \
--cc=punit.agrawal@arm.com \
--cc=roger.pau@citrix.com \
--cc=scampbel@codeaurora.org \
--cc=shankerd@codeaurora.org \
--cc=sstabellini@kernel.org \
--cc=xen-devel@lists.xenproject.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).