From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
To: "Koenig, Christian" <Christian.Koenig@amd.com>
Cc: "Christoph Hellwig" <hch@infradead.org>,
"Alex Deucher" <alexdeucher@gmail.com>,
"Michel Dänzer" <michel@daenzer.net>,
"Maxime Ripard" <maxime.ripard@bootlin.com>,
"Will Deacon" <will.deacon@arm.com>,
"Linux Kernel Mailing List" <linux-kernel@vger.kernel.org>,
"amd-gfx list" <amd-gfx@lists.freedesktop.org>,
"David Airlie" <airlied@linux.ie>,
"Huang, Ray" <Ray.Huang@amd.com>,
dri-devel <dri-devel@lists.freedesktop.org>,
"Michael Ellerman" <mpe@ellerman.id.au>,
"Zhang, Jerry" <Jerry.Zhang@amd.com>,
"Deucher, Alexander" <Alexander.Deucher@amd.com>,
"Sean Paul" <sean@poorly.run>,
linux-arm-kernel <linux-arm-kernel@lists.infradead.org>
Subject: Re: [RFC PATCH] drm: disable WC optimization for cache coherent devices on non-x86
Date: Thu, 24 Jan 2019 10:59:13 +0100 [thread overview]
Message-ID: <CAKv+Gu9umPEmB+wh54NOTYcQ14oxf7rwVAXgCqo7V2A+VwkqPA@mail.gmail.com> (raw)
In-Reply-To: <953e5e5f-5d47-d6df-40df-c8c94db5447f@amd.com>
On Thu, 24 Jan 2019 at 10:45, Koenig, Christian
<Christian.Koenig@amd.com> wrote:
>
> Am 24.01.19 um 10:28 schrieb Ard Biesheuvel:
> > On Thu, 24 Jan 2019 at 10:25, Koenig, Christian
> > <Christian.Koenig@amd.com> wrote:
> >> Am 24.01.19 um 10:13 schrieb Christoph Hellwig:
> >>> On Wed, Jan 23, 2019 at 05:52:50PM +0100, Ard Biesheuvel wrote:
> >>>> But my concern is that it seems likely that non-cache coherent
> >>>> implementations are relying on this hack as well. There must be a
> >>>> reason that this hack is only disabled for PowerPC platforms if they
> >>>> are cache coherent, for instance, and I suspect that that reason is
> >>>> that the hack is the only thing ensuring that the CPU mapping
> >>>> attributes match the device ones used for these buffers (the vmap()ed
> >>>> ones), whereas the rings and other consistent data structures are
> >>>> using the DMA API as intended, and thus getting uncached attributes in
> >>>> the correct way.
> >>> Dave, who added that commit is on Cc together with just about everyone
> >>> involved in the review chain. Based on the previous explanation
> >>> that idea what we might want an uncached mapping for some non-coherent
> >>> architectures for this to work at all makes sense, but then again
> >>> the way to create those mappings is entirely architecture specific,
> >>> and also need a cache flushing before creating the mapping to work
> >>> properly. So my working theory is that this code never properly
> >>> worked on architectures without DMA coherent for PCIe at all, but
> >>> I'd love to be corrected by concrete examples including an explanation
> >>> of how it actually ends up working.
> >> Cache coherency is mandatory for modern GPU operation.
> >>
> >> Otherwise you can't implement a bunch of the requirements of the
> >> userspace APIs.
> >>
> >> In other words the applications doesn't inform the driver that the GPU
> >> or the CPU is accessing data, it just does it and assumes that it works.
> >>
> > Wonderful!
> >
> > In that case, do you have any objections to the patch proposed by
> > Christoph above?
>
> Yeah, the patch of Christoph actually goes way to far cause we have
> reports that this works on a bunch of other architectures.
>
> E.g. X86 64bit, PowerPC (under some conditions) and some MIPS.
>
This is *exactly* my point the whole time.
The current code has
static inline bool drm_arch_can_wc_memory(void)
{
#if defined(CONFIG_PPC) && !defined(CONFIG_NOT_COHERENT_CACHE)
return false;
which means the optimization is disabled *unless the system is
non-cache coherent*
So if you have reports that the optimization works on some PowerPC, it
must be non-cache coherent PowerPC, because that is the only place
where it is enabled in the first place.
> The only problematic here actually seems to be ARM, so you should
> probably just add an "#ifdef .._ARM return false;".
>
ARM/arm64 does not have a Kconfig symbol like
CONFIG_NOT_COHERENT_CACHE, so we can only disable it everywhere. If
there are non-coherent ARM systems that are currently working in the
same way as those non-coherent PowerPC systems, we will break them by
doing this.
next prev parent reply other threads:[~2019-01-24 9:59 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-01-21 10:06 [RFC PATCH] drm: disable WC optimization for cache coherent devices on non-x86 Ard Biesheuvel
2019-01-21 10:11 ` Koenig, Christian
2019-01-21 15:07 ` Christoph Hellwig
2019-01-21 15:33 ` Ard Biesheuvel
2019-01-21 15:59 ` Christoph Hellwig
2019-01-21 16:14 ` Ard Biesheuvel
2019-01-21 16:22 ` Christoph Hellwig
2019-01-21 16:30 ` Ard Biesheuvel
2019-01-21 16:35 ` Christoph Hellwig
2019-01-21 16:50 ` Ard Biesheuvel
2019-01-21 17:55 ` Michel Dänzer
2019-01-21 17:59 ` Ard Biesheuvel
2019-01-21 18:04 ` Michel Dänzer
2019-01-21 18:20 ` Ard Biesheuvel
2019-01-21 18:23 ` Michel Dänzer
2019-01-21 18:28 ` Ard Biesheuvel
2019-01-21 19:04 ` Michel Dänzer
2019-01-21 19:18 ` Ard Biesheuvel
2019-01-22 8:38 ` Ard Biesheuvel
2019-01-22 20:56 ` Alex Deucher
2019-01-22 21:07 ` Ard Biesheuvel
2019-01-23 7:15 ` Christoph Hellwig
2019-01-23 9:08 ` Ard Biesheuvel
2019-01-23 16:44 ` Christoph Hellwig
2019-01-23 16:52 ` Ard Biesheuvel
2019-01-24 9:13 ` Christoph Hellwig
2019-01-24 9:25 ` Koenig, Christian
2019-01-24 9:28 ` Ard Biesheuvel
2019-01-24 9:45 ` Koenig, Christian
2019-01-24 9:59 ` Ard Biesheuvel [this message]
2019-01-24 11:23 ` Koenig, Christian
2019-01-24 11:26 ` Ard Biesheuvel
2019-01-24 11:37 ` Koenig, Christian
2019-01-24 11:45 ` Ard Biesheuvel
2019-01-24 13:54 ` Alex Deucher
2019-01-24 13:57 ` Ard Biesheuvel
2019-01-24 14:00 ` Alex Deucher
2019-01-24 16:04 ` Michel Dänzer
2019-01-24 9:31 ` Michel Dänzer
2019-01-24 9:37 ` Ard Biesheuvel
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=CAKv+Gu9umPEmB+wh54NOTYcQ14oxf7rwVAXgCqo7V2A+VwkqPA@mail.gmail.com \
--to=ard.biesheuvel@linaro.org \
--cc=Alexander.Deucher@amd.com \
--cc=Christian.Koenig@amd.com \
--cc=Jerry.Zhang@amd.com \
--cc=Ray.Huang@amd.com \
--cc=airlied@linux.ie \
--cc=alexdeucher@gmail.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=dri-devel@lists.freedesktop.org \
--cc=hch@infradead.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=maxime.ripard@bootlin.com \
--cc=michel@daenzer.net \
--cc=mpe@ellerman.id.au \
--cc=sean@poorly.run \
--cc=will.deacon@arm.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;
as well as URLs for NNTP newsgroup(s).