dri-devel Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
To: Steven Price <steven.price@arm.com>
Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com>,
	Maxime Ripard <maxime.ripard@bootlin.com>,
	Sean Paul <sean@poorly.run>,
	"dri-devel@lists.freedesktop.org"
	<dri-devel@lists.freedesktop.org>,
	David Airlie <airlied@linux.ie>,
	Boris Brezillon <boris.brezillon@collabora.com>,
	Robin Murphy <Robin.Murphy@arm.com>
Subject: Re: [PATCH v2 6/7] drm/panfrost: Add support for GPU heap allocations
Date: Fri, 26 Jul 2019 06:57:08 -0700	[thread overview]
Message-ID: <20190726135708.GA8834@kevin> (raw)
In-Reply-To: <1c54bd6c-a594-614d-7de0-badb00269ea1@arm.com>


[-- Attachment #1.1: Type: text/plain, Size: 1680 bytes --]

> It looks like the driver might be allocated a depth or stencil buffer
> without knowing whether it will be used. The buffer is then "grown" if
> it is needed by the GPU. The problem is it is possible for the
> application to access it later.

Hmm. I "think" you should be able to use a dummy (unbacked) Z/S buffer
when it won't be used, and as soon as the *driver* decides it will be
used (e.g. by setting the MALI_MFBD_DEPTH_WRITE bit), *that* is when you
allocate a real memory-backed BO. Neither case needs to be growable;
growable just pushes the logic into kernelspace (instead of handling it
in userspace).

The only wrinkle is if you need to give out addresses a priori, but that
could be solved by a mechanism to mmap a BO to a particular CPU address,
I think. (I recall MEM_ALIAS in kbase might be relevant?)

> * Use HMM: CPU VA==GPU VA. This nicely solves the problem, but falls over
> badly when the GPU VA size is smaller than the user space VA size - which is
> sadly true on many 64 bit integrations.
> 
> * Provide an allocation flag which causes the kernel driver to not pick a
> GPU address until the buffer is mapped on the CPU. The mmap callback would
> then need to look for a region that is free on both the CPU and GPU.
> 
> The second is obviously most similar to the kbase approach. kbase simplifies
> things because the kernel driver has the ultimate say over whether the
> buffer is SAME_VA or not. So on 64 bit user space we upgrade everything to
> be SAME_VA - which means the GPU VA space just follows the CPU VA (similar
> to HMM).

I'll let Rob chime in on this one. Thank you for the detailed write-up!

-Alyssa

[-- Attachment #1.2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

[-- Attachment #2: Type: text/plain, Size: 159 bytes --]

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

  reply	other threads:[~2019-07-26 13:57 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-25  1:09 [PATCH v2 0/7] drm/panfrost: Add heap and no execute buffer allocation Rob Herring
2019-07-25  1:09 ` [PATCH v2 1/7] drm/gem: Allow sparsely populated page arrays in drm_gem_put_pages Rob Herring
2019-07-25 15:36   ` Steven Price
2019-07-25  1:09 ` [PATCH v2 2/7] drm/shmem: Put pages independent of a SG table being set Rob Herring
2019-07-25 15:38   ` Steven Price
2019-07-25  1:09 ` [PATCH v2 3/7] drm/panfrost: Restructure the GEM object creation Rob Herring
2019-07-25 15:40   ` Steven Price
2019-07-25  1:10 ` [PATCH v2 4/7] drm/panfrost: Split panfrost_mmu_map SG list mapping to its own function Rob Herring
2019-07-25  1:10 ` [PATCH v2 5/7] drm/panfrost: Add a no execute flag for BO allocations Rob Herring
2019-07-25 15:45   ` Steven Price
2019-07-25  1:10 ` [PATCH v2 6/7] drm/panfrost: Add support for GPU heap allocations Rob Herring
2019-07-25 13:08   ` Robin Murphy
2019-07-25 21:11     ` Rob Herring
2019-07-26  9:15       ` Steven Price
2019-07-26  9:32         ` Robin Murphy
2019-07-26 16:11         ` Rob Herring
2019-07-25 14:59   ` Steven Price
2019-07-25 15:35     ` Steven Price
2019-07-25 16:13       ` Alyssa Rosenzweig
2019-07-25 16:28         ` Steven Price
2019-07-25 17:40           ` Alyssa Rosenzweig
2019-07-26 10:43             ` Steven Price
2019-07-26 13:57               ` Alyssa Rosenzweig [this message]
2019-07-30 18:49               ` Rob Herring
     [not found]                 ` <20190730185455.GA3205@kevin>
2019-07-30 19:08                   ` Rob Herring
2019-07-31  9:22                     ` Steven Price
2019-07-25 21:28       ` Rob Herring
2019-07-26  9:20         ` Steven Price
2019-07-30 20:03       ` Rob Herring
2019-07-31  9:30         ` Steven Price
2019-07-25  1:10 ` [PATCH v2 7/7] drm/panfrost: Bump driver version to 1.1 Rob Herring
2019-07-25 13:04 ` [PATCH v2 0/7] drm/panfrost: Add heap and no execute buffer allocation Alyssa Rosenzweig

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=20190726135708.GA8834@kevin \
    --to=alyssa.rosenzweig@collabora.com \
    --cc=Robin.Murphy@arm.com \
    --cc=airlied@linux.ie \
    --cc=boris.brezillon@collabora.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=maxime.ripard@bootlin.com \
    --cc=sean@poorly.run \
    --cc=steven.price@arm.com \
    --cc=tomeu.vizoso@collabora.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