From: Dmitry Osipenko <digetx@gmail.com>
To: Christoph Hellwig <hch@infradead.org>
Cc: Thierry Reding <thierry.reding@gmail.com>,
dri-devel@lists.freedesktop.org, linux-tegra@vger.kernel.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH v1 1/3] gpu: host1x: Remove implicit IOMMU backing on client's registration
Date: Mon, 24 Jun 2019 15:55:04 +0300 [thread overview]
Message-ID: <e7ecff74-ef8e-fd7e-1be2-0f3c60abc6f8@gmail.com> (raw)
In-Reply-To: <20190624070413.GA23846@infradead.org>
24.06.2019 10:04, Christoph Hellwig пишет:
> Don't we have a device tree problem here if there is a domain covering
> them? I though we should only pick up an IOMMU for a given device
> if DT explicitly asked for that?
>
There is no specific domain that "covering them". The IOMMU domain is allocated
dynamically during of the Tegra DRM's driver initialization (see tegra_drm_load) and
then all of DRM devices are attached to that domain once all of the DRM sub-drivers
are probed successfully. On Tegra SoCs it's up to software (driver) to decide how to
separate hardware devices from each other, in a case of DRM we're putting all the
relevant graphics devices into a single domain. Is it even possible to express IOMMU
domain (not group!) assignments in a device-tree?
next prev parent reply other threads:[~2019-06-24 12:55 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-06-23 17:37 Dmitry Osipenko
2019-06-23 17:37 ` [PATCH v1 2/3] drm/tegra: Fix 2d and 3d clients detaching from IOMMU domain Dmitry Osipenko
2019-10-24 11:58 ` Thierry Reding
2019-10-24 13:28 ` Dmitry Osipenko
2019-10-24 13:50 ` Thierry Reding
2019-10-24 15:47 ` Dmitry Osipenko
2019-10-24 15:56 ` Thierry Reding
2019-10-24 15:57 ` Dmitry Osipenko
2019-10-24 16:09 ` Dmitry Osipenko
2019-10-24 16:21 ` Dmitry Osipenko
2019-10-24 16:31 ` Dmitry Osipenko
2019-10-24 17:28 ` Thierry Reding
2019-10-24 18:46 ` Dmitry Osipenko
2019-10-25 11:48 ` Thierry Reding
2019-10-25 12:35 ` Dmitry Osipenko
2019-06-23 17:37 ` [PATCH v1 3/3] drm/tegra: vic: Use common helpers to attach/detach " Dmitry Osipenko
2019-06-24 7:04 ` [PATCH v1 1/3] gpu: host1x: Remove implicit IOMMU backing on client's registration Christoph Hellwig
2019-06-24 12:55 ` Dmitry Osipenko [this message]
2019-10-24 11:50 ` Thierry Reding
2019-10-24 13:35 ` Dmitry Osipenko
2019-10-24 13:47 ` Thierry Reding
2019-10-24 17:15 ` Dmitry Osipenko
2019-10-24 17:09 ` Dmitry Osipenko
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=e7ecff74-ef8e-fd7e-1be2-0f3c60abc6f8@gmail.com \
--to=digetx@gmail.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=hch@infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-tegra@vger.kernel.org \
--cc=thierry.reding@gmail.com \
/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
Powered by JetHome