From: Daniel Vetter <daniel@ffwll.ch>
To: Ben Widawsky <ben@bwidawsk.net>
Cc: Intel GFX <intel-gfx@lists.freedesktop.org>
Subject: Re: [PATCH 07/11] drm/i915: Fix up map and fenceable for VMA
Date: Tue, 9 Jul 2013 09:16:54 +0200 [thread overview]
Message-ID: <20130709071654.GR18285@phenom.ffwll.local> (raw)
In-Reply-To: <1373350122-5118-8-git-send-email-ben@bwidawsk.net>
On Mon, Jul 08, 2013 at 11:08:38PM -0700, Ben Widawsky wrote:
> formerly: "drm/i915: Create VMAs (part 3.5) - map and fenceable
> tracking"
>
> The map_and_fenceable tracking is per object. GTT mapping, and fences
> only apply to global GTT. As such, object operations which are not
> performed on the global GTT should not effect mappable or fenceable
> characteristics.
>
> Functionally, this commit could very well be squashed in to the previous
> patch which updated object operations to take a VM argument. This
> commit is split out because it's a bit tricky (or at least it was for
> me).
> Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
> ---
> drivers/gpu/drm/i915/i915_gem.c | 9 ++++++---
> 1 file changed, 6 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
> index 21015cd..501c590 100644
> --- a/drivers/gpu/drm/i915/i915_gem.c
> +++ b/drivers/gpu/drm/i915/i915_gem.c
> @@ -2635,7 +2635,7 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj,
>
> trace_i915_gem_object_unbind(obj, vm);
>
> - if (obj->has_global_gtt_mapping)
> + if (obj->has_global_gtt_mapping && i915_is_ggtt(vm))
> i915_gem_gtt_unbind_object(obj);
Wont this part be done as part of the global gtt clear_range callback?
> if (obj->has_aliasing_ppgtt_mapping) {
> i915_ppgtt_unbind_object(dev_priv->mm.aliasing_ppgtt, obj);
And I have a hunch that we should shovel the aliasing ppgtt clearing into
the ggtt write_ptes/clear_range callbacks, too. Once all this has settled
at least.
> @@ -2646,7 +2646,8 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj,
>
> list_del(&obj->mm_list);
> /* Avoid an unnecessary call to unbind on rebind. */
> - obj->map_and_fenceable = true;
> + if (i915_is_ggtt(vm))
> + obj->map_and_fenceable = true;
>
> vma = i915_gem_obj_to_vma(obj, vm);
> list_del(&vma->vma_link);
> @@ -3213,7 +3214,9 @@ search_free:
> i915_is_ggtt(vm) &&
> vma->node.start + obj->base.size <= dev_priv->gtt.mappable_end;
>
> - obj->map_and_fenceable = mappable && fenceable;
> + /* Map and fenceable only changes if the VM is the global GGTT */
> + if (i915_is_ggtt(vm))
> + obj->map_and_fenceable = mappable && fenceable;
>
> trace_i915_gem_object_bind(obj, vm, map_and_fenceable);
> i915_gem_verify_gtt(dev);
> --
> 1.8.3.2
>
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
--
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
next prev parent reply other threads:[~2013-07-09 7:16 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-07-09 6:08 [PATCH 00/11] ppgtt: just the VMA Ben Widawsky
2013-07-09 6:08 ` [PATCH 01/11] drm/i915: Move gtt and ppgtt under address space umbrella Ben Widawsky
2013-07-09 6:37 ` Daniel Vetter
2013-07-10 16:36 ` Ben Widawsky
2013-07-10 17:03 ` Daniel Vetter
2013-07-11 11:14 ` Imre Deak
2013-07-11 23:57 ` Ben Widawsky
2013-07-12 15:59 ` Ben Widawsky
2013-07-09 6:08 ` [PATCH 02/11] drm/i915: Put the mm in the parent address space Ben Widawsky
2013-07-09 6:08 ` [PATCH 03/11] drm/i915: Create a global list of vms Ben Widawsky
2013-07-09 6:37 ` Daniel Vetter
2013-07-09 6:08 ` [PATCH 04/11] drm/i915: Move active/inactive lists to new mm Ben Widawsky
2013-07-09 6:08 ` [PATCH 05/11] drm/i915: Create VMAs Ben Widawsky
2013-07-11 11:20 ` Imre Deak
2013-07-12 2:23 ` Ben Widawsky
2013-07-09 6:08 ` [PATCH 06/11] drm/i915: plumb VM into object operations Ben Widawsky
2013-07-09 7:15 ` Daniel Vetter
2013-07-10 16:37 ` Ben Widawsky
2013-07-10 17:05 ` Daniel Vetter
2013-07-10 22:23 ` Ben Widawsky
2013-07-11 6:01 ` Daniel Vetter
2013-07-12 2:23 ` Ben Widawsky
2013-07-12 6:26 ` Daniel Vetter
2013-07-12 15:46 ` Ben Widawsky
2013-07-12 16:46 ` Daniel Vetter
2013-07-16 3:57 ` Ben Widawsky
2013-07-16 5:06 ` Daniel Vetter
2013-07-09 6:08 ` [PATCH 07/11] drm/i915: Fix up map and fenceable for VMA Ben Widawsky
2013-07-09 7:16 ` Daniel Vetter [this message]
2013-07-10 16:39 ` Ben Widawsky
2013-07-10 17:08 ` Daniel Vetter
2013-07-09 6:08 ` [PATCH 08/11] drm/i915: mm_list is per VMA Ben Widawsky
2013-07-09 7:18 ` Daniel Vetter
2013-07-10 16:39 ` Ben Widawsky
2013-07-09 6:08 ` [PATCH 09/11] drm/i915: Update error capture for VMs Ben Widawsky
2013-07-09 6:08 ` [PATCH 10/11] drm/i915: create an object_is_active() Ben Widawsky
2013-07-09 6:08 ` [PATCH 11/11] drm/i915: Move active to vma Ben Widawsky
2013-07-09 7:45 ` Daniel Vetter
2013-07-10 16:39 ` Ben Widawsky
2013-07-10 17:13 ` Daniel Vetter
2013-07-09 7:50 ` [PATCH 00/11] ppgtt: just the VMA Daniel Vetter
2013-07-13 4:45 ` [PATCH 12/15] [RFC] create vm->bind,unbind Ben Widawsky
2013-07-13 4:45 ` [PATCH 1/3] drm/i915: Add bind/unbind object functions to VM Ben Widawsky
2013-07-13 9:33 ` Daniel Vetter
2013-07-16 3:35 ` Ben Widawsky
2013-07-16 4:00 ` Ben Widawsky
2013-07-16 5:10 ` Daniel Vetter
2013-07-16 5:13 ` Daniel Vetter
2013-07-13 4:45 ` [PATCH 2/3] drm/i915: Use the new vm [un]bind functions Ben Widawsky
2013-07-13 4:45 ` [PATCH 3/3] drm/i915: eliminate vm->insert_entries() Ben Widawsky
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=20130709071654.GR18285@phenom.ffwll.local \
--to=daniel@ffwll.ch \
--cc=ben@bwidawsk.net \
--cc=intel-gfx@lists.freedesktop.org \
/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