From: Chris Wilson <chris@chris-wilson.co.uk>
To: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Intel-gfx@lists.freedesktop.org
Subject: Re: [RFC 3/5] drm/i915: Add support for CPU mapping to DRM_IOCTL_I915_GEM_MMAP_GTT
Date: Wed, 27 Jan 2016 16:36:00 +0000 [thread overview]
Message-ID: <20160127163600.GE8281@nuc-i3427.alporthouse.com> (raw)
In-Reply-To: <56A8E13B.5090105@linux.intel.com>
On Wed, Jan 27, 2016 at 03:24:43PM +0000, Tvrtko Ursulin wrote:
>
> On 26/01/16 16:59, Chris Wilson wrote:
> >Another thing I realised was that this severely limits the mmap space on
> >32-bit systems, as the vma manager is unsigned long. The CPU mmaping was
> >a way around some of the restrictions. That would seem fairly easy to
> >lift (and I hope without consequence).
>
> I did not manage to figure out what here limits the space on 32-bit systems?
A hang-over of mine. We once used to exhaust the 32bit mmap space quite
easily. I was thinking drm_vma_manager had the same limit due to its use
of unsigned long, but it is counting in pages not bytes, so we have
44bits available of space, which will hopefully be enuogh for the last
remaining 32bit system to grow old gracefully.
-Chris
--
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2016-01-27 16:36 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-01-26 14:53 [RFC 0/5] Adding CPU mmap support to DRM_IOCTL_I915_GEM_MMAP_GTT Tvrtko Ursulin
2016-01-26 14:53 ` [RFC 1/5] drm: Allow drivers setting vm_ops per vma offset node Tvrtko Ursulin
2016-01-26 14:53 ` [RFC 2/5] drm/i915: Extract code mapping errno to vm fault code Tvrtko Ursulin
2016-01-26 15:18 ` Chris Wilson
2016-01-26 16:24 ` Tvrtko Ursulin
2016-01-26 16:42 ` Chris Wilson
2016-01-26 14:53 ` [RFC 3/5] drm/i915: Add support for CPU mapping to DRM_IOCTL_I915_GEM_MMAP_GTT Tvrtko Ursulin
2016-01-26 15:10 ` Chris Wilson
2016-01-26 16:23 ` Tvrtko Ursulin
2016-01-26 16:59 ` Chris Wilson
2016-01-27 15:24 ` Tvrtko Ursulin
2016-01-27 16:36 ` Chris Wilson [this message]
2016-01-27 16:40 ` Chris Wilson
2016-01-27 15:21 ` [PATCH v2 " Tvrtko Ursulin
2016-01-27 15:51 ` Daniel Vetter
2016-01-27 16:01 ` Tvrtko Ursulin
2016-01-27 16:10 ` Daniel Vetter
2016-01-27 16:32 ` Chris Wilson
2016-01-26 14:53 ` [RFC 4/5] drm/i915: Add support for write-combined " Tvrtko Ursulin
2016-01-26 15:11 ` Chris Wilson
2016-01-27 15:22 ` [PATCH v2 " Tvrtko Ursulin
2016-01-26 14:53 ` [RFC 5/5] drm/i915: Announce the new DRM_IOCTL_I915_GEM_MMAP_GTT capabilities Tvrtko Ursulin
2016-01-28 9:18 ` ✓ Fi.CI.BAT: success for Adding CPU mmap support to DRM_IOCTL_I915_GEM_MMAP_GTT (rev3) Patchwork
2016-01-28 16:10 ` Patchwork
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=20160127163600.GE8281@nuc-i3427.alporthouse.com \
--to=chris@chris-wilson.co.uk \
--cc=Intel-gfx@lists.freedesktop.org \
--cc=tvrtko.ursulin@linux.intel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.