From: Will Deacon <will.deacon@arm.com>
To: "Michael S. Tsirkin" <mst@redhat.com>
Cc: mark.rutland@arm.com, devicetree@vger.kernel.org,
pawel.moll@arm.com, virtualization@lists.linux-foundation.org,
robh+dt@kernel.org, Robin Murphy <robin.murphy@arm.com>,
linux-arm-kernel@lists.infradead.org
Subject: Re: [PATCH] virtio: Try to untangle DMA coherency
Date: Mon, 13 Feb 2017 11:57:59 +0000 [thread overview]
Message-ID: <20170213115758.GK1512@arm.com> (raw)
In-Reply-To: <20170210191409-mutt-send-email-mst@kernel.org>
On Fri, Feb 10, 2017 at 07:16:10PM +0200, Michael S. Tsirkin wrote:
> On Thu, Feb 09, 2017 at 06:31:18PM +0000, Will Deacon wrote:
> > On ARM (and other archs such as
> > Power), having a mismatch between a cacheable and a non-cacheable mapping
> > can result in a loss of coherency between the two (for example, if the
> > non-cacheable gues accesses bypass the cache, but the cacheable host
> > accesses allocate in the cache).
>
> I guess it's an optimization to avoid cache snoops for non-cacheable accesses?
The architecture doesn't rationalise the decision, but a micro-architecture
could indeed implement the optimisation you suggest (and we do observe the
loss of coherency in practice).
Will
WARNING: multiple messages have this Message-ID (diff)
From: will.deacon@arm.com (Will Deacon)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH] virtio: Try to untangle DMA coherency
Date: Mon, 13 Feb 2017 11:57:59 +0000 [thread overview]
Message-ID: <20170213115758.GK1512@arm.com> (raw)
In-Reply-To: <20170210191409-mutt-send-email-mst@kernel.org>
On Fri, Feb 10, 2017 at 07:16:10PM +0200, Michael S. Tsirkin wrote:
> On Thu, Feb 09, 2017 at 06:31:18PM +0000, Will Deacon wrote:
> > On ARM (and other archs such as
> > Power), having a mismatch between a cacheable and a non-cacheable mapping
> > can result in a loss of coherency between the two (for example, if the
> > non-cacheable gues accesses bypass the cache, but the cacheable host
> > accesses allocate in the cache).
>
> I guess it's an optimization to avoid cache snoops for non-cacheable accesses?
The architecture doesn't rationalise the decision, but a micro-architecture
could indeed implement the optimisation you suggest (and we do observe the
loss of coherency in practice).
Will
next prev parent reply other threads:[~2017-02-13 11:57 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-02-01 12:25 [PATCH] virtio: Try to untangle DMA coherency Robin Murphy
2017-02-01 12:25 ` Robin Murphy
2017-02-01 14:57 ` Will Deacon
2017-02-01 14:57 ` Will Deacon
2017-02-01 17:58 ` Rob Herring
2017-02-01 17:58 ` Rob Herring
2017-02-01 17:58 ` Rob Herring
2017-02-01 18:09 ` Michael S. Tsirkin
2017-02-01 18:09 ` Michael S. Tsirkin
2017-02-01 18:27 ` Will Deacon
2017-02-01 18:27 ` Will Deacon
2017-02-01 18:27 ` Will Deacon
2017-02-01 19:19 ` Michael S. Tsirkin
2017-02-01 19:19 ` Michael S. Tsirkin
2017-02-02 11:26 ` Will Deacon
2017-02-02 11:26 ` Will Deacon
2017-02-02 13:34 ` Robin Murphy
2017-02-02 13:34 ` Robin Murphy
2017-02-02 16:16 ` Michael S. Tsirkin
2017-02-02 16:16 ` Michael S. Tsirkin
2017-02-02 16:39 ` Marc Zyngier
2017-02-02 16:39 ` Marc Zyngier
2017-02-02 16:44 ` Michael S. Tsirkin
2017-02-02 16:44 ` Michael S. Tsirkin
2017-02-02 16:44 ` Michael S. Tsirkin
2017-02-02 16:39 ` Marc Zyngier
2017-02-02 16:16 ` Michael S. Tsirkin
2017-02-02 16:30 ` Michael S. Tsirkin
2017-02-02 16:30 ` Michael S. Tsirkin
2017-02-02 16:40 ` Will Deacon
2017-02-02 16:40 ` Will Deacon
2017-02-02 16:45 ` Michael S. Tsirkin
2017-02-02 16:45 ` Michael S. Tsirkin
2017-02-02 16:45 ` Michael S. Tsirkin
2017-02-09 18:17 ` Michael S. Tsirkin
2017-02-09 18:17 ` Michael S. Tsirkin
2017-02-09 18:31 ` Will Deacon
2017-02-09 18:31 ` Will Deacon
2017-02-09 18:49 ` Michael S. Tsirkin
2017-02-09 18:49 ` Michael S. Tsirkin
2017-02-09 18:54 ` Ard Biesheuvel
2017-02-09 18:54 ` Ard Biesheuvel
2017-02-09 18:54 ` Ard Biesheuvel
2017-02-09 18:56 ` Will Deacon
2017-02-09 18:56 ` Will Deacon
2017-02-10 17:16 ` Michael S. Tsirkin
2017-02-10 17:16 ` Michael S. Tsirkin
2017-02-13 11:57 ` Will Deacon [this message]
2017-02-13 11:57 ` Will Deacon
2017-02-02 16:30 ` Michael S. Tsirkin
2017-02-02 11:26 ` Will Deacon
2017-02-08 12:58 ` Alexander Graf
2017-02-08 12:58 ` Alexander Graf
2017-02-09 20:57 ` Michael S. Tsirkin
2017-02-09 20:57 ` Michael S. Tsirkin
2017-02-09 22:20 ` Alexander Graf
2017-02-09 22:20 ` Alexander Graf
2017-02-01 19:19 ` Michael S. Tsirkin
2017-02-01 18:09 ` Michael S. Tsirkin
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=20170213115758.GK1512@arm.com \
--to=will.deacon@arm.com \
--cc=devicetree@vger.kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=mark.rutland@arm.com \
--cc=mst@redhat.com \
--cc=pawel.moll@arm.com \
--cc=robh+dt@kernel.org \
--cc=robin.murphy@arm.com \
--cc=virtualization@lists.linux-foundation.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.