From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
To: Chris Wilson <chris@chris-wilson.co.uk>, intel-gfx@lists.freedesktop.org
Cc: mika.kuoppala@intel.com
Subject: Re: [PATCH 16/17] drm/i915: Enable userspace to opt-out of implicit fencing
Date: Tue, 30 Aug 2016 11:45:10 +0300 [thread overview]
Message-ID: <1472546710.3692.14.camel@linux.intel.com> (raw)
In-Reply-To: <20160828204624.21193-17-chris@chris-wilson.co.uk>
On su, 2016-08-28 at 21:46 +0100, Chris Wilson wrote:
> Userspace is faced with a dilemma. The kernel requires implicit fencing
> to manage resource usage (we always must wait for the GPU to finish
> before releasing its PTE) and for third parties. However, userspace may
> wish to avoid this serialisation if it is either using explicit fencing
> between parties and wants more fine-grained access to buffers (e.g. it
> may partition the buffer between uses and track fences on ranges rather
> than the implicit fences tracking the whole object). To whit, userspace
s/whit/with/?
> @@ -1199,21 +1199,23 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
> struct drm_i915_gem_object *obj = vma->obj;
> struct reservation_object *resv;
>
> - if (obj->flags & other_rings) {
> - ret = eb_await_bo(req, obj,
> - obj->base.pending_write_domain);
> - if (ret)
> - return ret;
> - }
> + if ((vma->exec_entry->flags & EXEC_OBJECT_ASYNC) == 0) {
if (!(a & FOO)) would again be more readable.
With the typo fixed;
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Regards, Joonas
--
Joonas Lahtinen
Open Source Technology Center
Intel Corporation
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2016-08-30 8:45 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-08-28 20:46 Explicit fencing + nonblocking execbuf Chris Wilson
2016-08-28 20:46 ` [PATCH 01/17] drm/i915: Add a sw fence for collecting up dma fences Chris Wilson
2016-08-29 13:43 ` Joonas Lahtinen
2016-08-29 15:45 ` Chris Wilson
2016-08-30 7:42 ` Joonas Lahtinen
2016-08-28 20:46 ` [PATCH 02/17] drm/i915: Only queue requests during execlists submission Chris Wilson
2016-08-28 20:46 ` [PATCH 03/17] drm/i915: Record the position of the workarounds in the tail of the request Chris Wilson
2016-08-28 20:46 ` [PATCH 04/17] drm/i915: Compute the ELSP register location once Chris Wilson
2016-08-28 20:46 ` [PATCH 05/17] drm/i915: Reorder submitting the requests to ELSP Chris Wilson
2016-08-28 20:46 ` [PATCH 06/17] drm/i915: Simplify ELSP queue request tracking Chris Wilson
2016-08-29 12:31 ` Mika Kuoppala
2016-08-28 20:46 ` [PATCH 07/17] drm/i915: Separate out reset flags from the reset counter Chris Wilson
2016-08-30 14:23 ` [PATCH v2] " Chris Wilson
2016-08-30 14:40 ` Mika Kuoppala
2016-08-28 20:46 ` [PATCH 08/17] drm/i915: Drop local struct_mutex around intel_init_emon[ilk] Chris Wilson
2016-08-29 13:53 ` Mika Kuoppala
2016-08-29 13:57 ` Joonas Lahtinen
2016-08-28 20:46 ` [PATCH 09/17] drm/i915: Expand bool interruptible to pass flags to i915_wait_request() Chris Wilson
2016-08-29 14:00 ` Joonas Lahtinen
2016-08-28 20:46 ` [PATCH 10/17] drm/i915: Perform a direct reset of the GPU from the waiter Chris Wilson
2016-08-28 20:46 ` [PATCH 11/17] drm/i915: Update reset path to fix incomplete requests Chris Wilson
2016-08-28 20:46 ` [PATCH 12/17] drm/i915: Drive request submission through fence callbacks Chris Wilson
2016-08-30 8:07 ` Joonas Lahtinen
2016-08-28 20:46 ` [PATCH 13/17] drm/i915: Move execbuf object synchronisation to i915_gem_execbuffer Chris Wilson
2016-08-30 8:10 ` Joonas Lahtinen
2016-08-30 9:22 ` Chris Wilson
2016-08-28 20:46 ` [PATCH 14/17] drm/i915: Nonblocking request submission Chris Wilson
2016-08-30 8:35 ` Joonas Lahtinen
2016-08-30 8:43 ` Chris Wilson
2016-08-30 8:49 ` Joonas Lahtinen
2016-08-30 11:18 ` [PATCH v2] " Chris Wilson
2016-08-31 8:36 ` Joonas Lahtinen
2016-08-28 20:46 ` [PATCH 15/17] drm/i915: Serialise execbuf operation after a dma-buf reservation object Chris Wilson
2016-08-30 8:37 ` Joonas Lahtinen
2016-08-28 20:46 ` [PATCH 16/17] drm/i915: Enable userspace to opt-out of implicit fencing Chris Wilson
2016-08-30 8:45 ` Joonas Lahtinen [this message]
2016-08-30 9:00 ` Chris Wilson
2016-08-28 20:46 ` [PATCH 17/17] drm/i915: Support explicit fencing for execbuf Chris Wilson
2016-08-29 8:55 ` Chris Wilson
2016-08-30 9:42 ` Joonas Lahtinen
2016-08-28 21:18 ` ✓ Fi.CI.BAT: success for series starting with [01/17] drm/i915: Add a sw fence for collecting up dma fences Patchwork
2016-08-30 11:50 ` ✓ Fi.CI.BAT: success for series starting with [01/17] drm/i915: Add a sw fence for collecting up dma fences (rev2) Patchwork
2016-08-30 14:50 ` ✓ Fi.CI.BAT: success for series starting with [01/17] drm/i915: Add a sw fence for collecting up dma fences (rev3) 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=1472546710.3692.14.camel@linux.intel.com \
--to=joonas.lahtinen@linux.intel.com \
--cc=chris@chris-wilson.co.uk \
--cc=intel-gfx@lists.freedesktop.org \
--cc=mika.kuoppala@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox