From: Will Deacon <will@kernel.org>
To: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org>
Cc: "Isaac J. Manjarres" <isaacm@codeaurora.org>,
freedreno <freedreno@lists.freedesktop.org>,
David Airlie <airlied@linux.ie>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
"list@263.net:IOMMU DRIVERS , Joerg Roedel <joro@8bytes.org>,
" <iommu@lists.linux-foundation.org>,
dri-devel <dri-devel@lists.freedesktop.org>,
Akhil P Oommen <akhilpo@codeaurora.org>,
Sean Paul <sean@poorly.run>,
Kristian H Kristensen <hoegsberg@google.com>,
Daniel Vetter <daniel@ffwll.ch>,
linux-arm-msm <linux-arm-msm@vger.kernel.org>,
Robin Murphy <robin.murphy@arm.com>,
linux-arm-kernel@lists.infradead.org
Subject: Re: [PATCH 2/3] iommu/io-pgtable-arm: Add IOMMU_LLC page protection flag
Date: Thu, 25 Mar 2021 17:33:11 +0000 [thread overview]
Message-ID: <20210325173311.GA15504@willie-the-truck> (raw)
In-Reply-To: <9362873a3bcf37cdd073a6128f29c683@codeaurora.org>
On Tue, Mar 09, 2021 at 12:10:44PM +0530, Sai Prakash Ranjan wrote:
> On 2021-02-05 17:38, Sai Prakash Ranjan wrote:
> > On 2021-02-04 03:16, Will Deacon wrote:
> > > On Tue, Feb 02, 2021 at 11:56:27AM +0530, Sai Prakash Ranjan wrote:
> > > > On 2021-02-01 23:50, Jordan Crouse wrote:
> > > > > On Mon, Feb 01, 2021 at 08:20:44AM -0800, Rob Clark wrote:
> > > > > > On Mon, Feb 1, 2021 at 3:16 AM Will Deacon <will@kernel.org> wrote:
> > > > > > > On Fri, Jan 29, 2021 at 03:12:59PM +0530, Sai Prakash Ranjan wrote:
> > > > > > > > On 2021-01-29 14:35, Will Deacon wrote:
> > > > > > > > > On Mon, Jan 11, 2021 at 07:45:04PM +0530, Sai Prakash Ranjan wrote:
> > > > > > > > > > +#define IOMMU_LLC (1 << 6)
> > > > > > > > >
> > > > > > > > > On reflection, I'm a bit worried about exposing this because I think it
> > > > > > > > > will
> > > > > > > > > introduce a mismatched virtual alias with the CPU (we don't even have a
> > > > > > > > > MAIR
> > > > > > > > > set up for this memory type). Now, we also have that issue for the PTW,
> > > > > > > > > but
> > > > > > > > > since we always use cache maintenance (i.e. the streaming API) for
> > > > > > > > > publishing the page-tables to a non-coheren walker, it works out.
> > > > > > > > > However,
> > > > > > > > > if somebody expects IOMMU_LLC to be coherent with a DMA API coherent
> > > > > > > > > allocation, then they're potentially in for a nasty surprise due to the
> > > > > > > > > mismatched outer-cacheability attributes.
> > > > > > > > >
> > > > > > > >
> > > > > > > > Can't we add the syscached memory type similar to what is done on android?
> > > > > > >
> > > > > > > Maybe. How does the GPU driver map these things on the CPU side?
> > > > > >
> > > > > > Currently we use writecombine mappings for everything, although there
> > > > > > are some cases that we'd like to use cached (but have not merged
> > > > > > patches that would give userspace a way to flush/invalidate)
> > > > > >
> > > > >
> > > > > LLC/system cache doesn't have a relationship with the CPU cache. Its
> > > > > just a
> > > > > little accelerator that sits on the connection from the GPU to DDR and
> > > > > caches
> > > > > accesses. The hint that Sai is suggesting is used to mark the buffers as
> > > > > 'no-write-allocate' to prevent GPU write operations from being cached in
> > > > > the LLC
> > > > > which a) isn't interesting and b) takes up cache space for read
> > > > > operations.
> > > > >
> > > > > Its easiest to think of the LLC as a bonus accelerator that has no cost
> > > > > for
> > > > > us to use outside of the unfortunate per buffer hint.
> > > > >
> > > > > We do have to worry about the CPU cache w.r.t I/O coherency (which is a
> > > > > different hint) and in that case we have all of concerns that Will
> > > > > identified.
> > > > >
> > > >
> > > > For mismatched outer cacheability attributes which Will
> > > > mentioned, I was
> > > > referring to [1] in android kernel.
> > >
> > > I've lost track of the conversation here :/
> > >
> > > When the GPU has a buffer mapped with IOMMU_LLC, is the buffer also
> > > mapped
> > > into the CPU and with what attributes? Rob said "writecombine for
> > > everything" -- does that mean ioremap_wc() / MEMREMAP_WC?
> > >
> >
> > Rob answered this.
> >
> > > Finally, we need to be careful when we use the word "hint" as
> > > "allocation
> > > hint" has a specific meaning in the architecture, and if we only
> > > mismatch on
> > > those then we're actually ok. But I think IOMMU_LLC is more than
> > > just a
> > > hint, since it actually drives eviction policy (i.e. it enables
> > > writeback).
> > >
> > > Sorry for the pedantry, but I just want to make sure we're all talking
> > > about the same things!
> > >
> >
> > Sorry for the confusion which probably was caused by my mentioning of
> > android, NWA(no write allocate) is an allocation hint which we can
> > ignore
> > for now as it is not introduced yet in upstream.
> >
>
> Any chance of taking this forward? We do not want to miss out on small fps
> gain when the product gets released.
Do we have a solution to the mismatched virtual alias?
Will
next prev parent reply other threads:[~2021-03-25 17:34 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-11 14:15 [PATCH 0/3] iommu/drm/msm: Allow non-coherent masters to use system cache Sai Prakash Ranjan
2021-01-11 14:15 ` [PATCH 1/3] iommu/io-pgtable: Rename last-level cache quirk to IO_PGTABLE_QUIRK_PTW_LLC Sai Prakash Ranjan
2021-01-11 14:15 ` [PATCH 2/3] iommu/io-pgtable-arm: Add IOMMU_LLC page protection flag Sai Prakash Ranjan
[not found] ` <20210129090516.GB3998@willie-the-truck>
[not found] ` <5d23fce629323bcda71594010824aad0@codeaurora.org>
2021-02-01 11:15 ` Will Deacon
2021-02-01 16:20 ` Rob Clark
2021-02-01 18:20 ` Jordan Crouse
2021-02-02 6:26 ` Sai Prakash Ranjan
2021-02-03 21:46 ` Will Deacon
2021-02-03 22:14 ` Rob Clark
2021-03-16 17:04 ` Rob Clark
2021-03-16 17:16 ` Rob Clark
2021-02-05 12:08 ` Sai Prakash Ranjan
2021-03-09 6:40 ` Sai Prakash Ranjan
2021-03-25 17:33 ` Will Deacon [this message]
2021-06-30 10:07 ` Sai Prakash Ranjan
2021-02-02 6:28 ` Sai Prakash Ranjan
2021-01-11 14:15 ` [PATCH 3/3] drm/msm: Use IOMMU_LLC page protection flag to map gpu buffers Sai Prakash Ranjan
2021-01-20 5:18 ` [PATCH 0/3] iommu/drm/msm: Allow non-coherent masters to use system cache Sai Prakash Ranjan
2021-07-28 14:00 ` Georgi Djakov
2021-07-29 4:38 ` Sai Prakash Ranjan
2021-08-02 10:55 ` Will Deacon
2021-08-02 15:08 ` [Freedreno] " Rob Clark
2021-08-02 15:14 ` Will Deacon
2021-08-03 1:36 ` Rob Clark
2021-08-09 14:56 ` Will Deacon
2021-08-09 16:57 ` Rob Clark
2021-08-09 17:05 ` Will Deacon
2021-08-09 17:18 ` Rob Clark
2021-08-09 17:40 ` Will Deacon
2021-08-09 17:47 ` Sai Prakash Ranjan
2021-08-09 18:07 ` Rob Clark
2021-08-09 18:10 ` Sai Prakash Ranjan
2021-08-09 18:30 ` Rob Clark
2021-08-09 18:32 ` Sai Prakash Ranjan
2021-08-10 9:16 ` Will Deacon
2021-08-10 9:54 ` Sai Prakash Ranjan
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=20210325173311.GA15504@willie-the-truck \
--to=will@kernel.org \
--cc=airlied@linux.ie \
--cc=akhilpo@codeaurora.org \
--cc=daniel@ffwll.ch \
--cc=dri-devel@lists.freedesktop.org \
--cc=freedreno@lists.freedesktop.org \
--cc=hoegsberg@google.com \
--cc=iommu@lists.linux-foundation.org \
--cc=isaacm@codeaurora.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-arm-msm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=robin.murphy@arm.com \
--cc=saiprakash.ranjan@codeaurora.org \
--cc=sean@poorly.run \
/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).