Re: [PATCH 1/2] drm: add cache support for arm64

From: Rob Clark <robdclark@chromium.org>
To: Christoph Hellwig <hch@lst.de>
Cc: Rob Clark <robdclark@gmail.com>,
	dri-devel <dri-devel@lists.freedesktop.org>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>,
	Maarten Lankhorst <maarten.lankhorst@linux.intel.com>,
	Maxime Ripard <maxime.ripard@bootlin.com>,
	Sean Paul <sean@poorly.run>, David Airlie <airlied@linux.ie>,
	Daniel Vetter <daniel@ffwll.ch>,
	Allison Randal <allison@lohutok.net>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	linux-arm-kernel@lists.infradead.org,
	LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 1/2] drm: add cache support for arm64
Date: Tue, 6 Aug 2019 09:23:51 -0700	[thread overview]
Message-ID: <CAJs_Fx6uztwDy2PqRy3Tc9p12k8r_ovS2tAcsMV6HqnAp=Ggug@mail.gmail.com> (raw)
In-Reply-To: <20190806155044.GC25050@lst.de>

On Tue, Aug 6, 2019 at 8:50 AM Christoph Hellwig <hch@lst.de> wrote:
>
> On Tue, Aug 06, 2019 at 07:11:41AM -0700, Rob Clark wrote:
> > Agreed that drm_cflush_* isn't a great API.  In this particular case
> > (IIUC), I need wb+inv so that there aren't dirty cache lines that drop
> > out to memory later, and so that I don't get a cache hit on
> > uncached/wc mmap'ing.
>
> So what is the use case here?  Allocate pages using the page allocator
> (or CMA for that matter), and then mmaping them to userspace and never
> touching them again from the kernel?

Currently, it is pages coming from tmpfs.  Ideally we want pages that
are swappable when unpinned.

CPU mappings are *mostly* just mapping to userspace.  There are a few
exceptions that are vmap'd (fbcon, and ringbuffer).

(Eventually I'd like to support pages passed in from userspace.. but
that is down the road.)

> > Tying it in w/ iommu seems a bit weird to me.. but maybe that is just
> > me, I'm certainly willing to consider proposals or to try things and
> > see how they work out.
>
> This was just my through as the fit seems easy.  But maybe you'll
> need to explain your use case(s) a bit more so that we can figure out
> what a good high level API is.

Tying it to iommu_map/unmap would be awkward, as we could need to
setup cpu mmap before it ends up mapped to iommu.  And the plan to
support per-process pagetables involved creating an iommu_domain per
userspace gl context.. some buffers would end up mapped into multiple
contexts/iommu_domains.

If the cache operation was detached from iommu_map/unmap, then it
would seem weird to be part of the iommu API.

I guess I'm not entirely sure what you had in mind, but this is why
iommu seemed to me like a bad fit.

> > Exposing the arch_sync_* API and using that directly (bypassing
> > drm_cflush_*) actually seems pretty reasonable and pragmatic.  I did
> > have one doubt, as phys_to_virt() is only valid for kernel direct
> > mapped memory (AFAIU), what happens for pages that are not in kernel
> > linear map?  Maybe it is ok to ignore those pages, since they won't
> > have an aliased mapping?
>
> They could have an aliased mapping in vmalloc/vmap space for example,
> if you created one.  We have the flush_kernel_vmap_range /
> invalidate_kernel_vmap_range APIs for those, that are implement
> on architectures with VIVT caches.

If I only have to worry about aliased mappings that I create myself,
that doesn't seem too bad..  I could track that myself easily enough.

BR,
-R