From: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
To: Chris Wilson <chris@chris-wilson.co.uk>, intel-gfx@lists.freedesktop.org
Cc: mika.kuoppala@intel.com
Subject: Re: [PATCH v2 17/22] drm/i915/guc: Prepare for nonblocking execbuf submission
Date: Mon, 12 Sep 2016 15:14:52 +0100 [thread overview]
Message-ID: <57D6B85C.80007@linux.intel.com> (raw)
In-Reply-To: <20160907144516.29495-17-chris@chris-wilson.co.uk>
On 07/09/16 15:45, Chris Wilson wrote:
> Currently the presumption is that the request construction and its
> submission to the GuC are all under the same holding of struct_mutex. We
> wish to relax this to separate the request construction and the later
> submission to the GuC. This requires us to reserve some space in the
> GuC command queue for the future submission. For flexibility to handle
> out-of-order request submission we do not preallocate the next slot in
> the GuC command queue during request construction, just ensuring that
> there is enough space later.
>
> Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
> ---
> drivers/gpu/drm/i915/i915_guc_submission.c | 35 ++++++++++++++++++++----------
> drivers/gpu/drm/i915/intel_guc.h | 3 +++
> 2 files changed, 26 insertions(+), 12 deletions(-)
R-b is missing for this one and it is in the tree now.
Regards,
Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2016-09-12 14:14 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-09-05 13:04 Non-blocking, explict fences Chris Wilson
2016-09-05 13:04 ` [PATCH 01/21] drm/i915: Add a sw fence for collecting up dma fences Chris Wilson
2016-09-05 13:04 ` [PATCH 02/21] drm/i915: Only queue requests during execlists submission Chris Wilson
2016-09-05 13:04 ` [PATCH 03/21] drm/i915: Record the position of the workarounds in the tail of the request Chris Wilson
2016-09-05 13:04 ` [PATCH 04/21] drm/i915: Compute the ELSP register location once Chris Wilson
2016-09-05 13:04 ` [PATCH 05/21] drm/i915: Reorder submitting the requests to ELSP Chris Wilson
2016-09-05 13:04 ` [PATCH 06/21] drm/i915: Simplify ELSP queue request tracking Chris Wilson
2016-09-05 13:04 ` [PATCH 07/21] drm/i915: Separate out reset flags from the reset counter Chris Wilson
2016-09-05 13:04 ` [PATCH 08/21] drm/i915: Drop local struct_mutex around intel_init_emon[ilk] Chris Wilson
2016-09-05 13:04 ` [PATCH 09/21] drm/i915: Expand bool interruptible to pass flags to i915_wait_request() Chris Wilson
2016-09-05 13:04 ` [PATCH 10/21] drm/i915: Mark up all locked waiters Chris Wilson
2016-09-06 9:24 ` Mika Kuoppala
2016-09-05 13:04 ` [PATCH 11/21] drm/i915: Perform a direct reset of the GPU from the waiter Chris Wilson
2016-09-05 13:04 ` [PATCH 12/21] drm/i915: Replace wait-on-mutex with wait-on-bit in reset worker Chris Wilson
2016-09-06 9:28 ` Mika Kuoppala
2016-09-05 13:04 ` [PATCH 13/21] drm/i915: Update reset path to fix incomplete requests Chris Wilson
2016-09-05 13:04 ` [PATCH 14/21] drm/i915: Drive request submission through fence callbacks Chris Wilson
2016-09-05 13:04 ` [PATCH 15/21] drm/i915: Reorder i915_add_request to separate the phases better Chris Wilson
2016-09-06 9:36 ` Mika Kuoppala
2016-09-05 13:04 ` [PATCH 16/21] drm/i915: Prepare object synchronisation for asynchronicity Chris Wilson
2016-09-05 13:04 ` [PATCH 17/21] drm/i915/guc: Prepare for nonblocking execbuf submission Chris Wilson
2016-09-05 13:04 ` [PATCH 18/21] drm/i915: Nonblocking request submission Chris Wilson
2016-09-05 13:04 ` [PATCH 19/21] drm/i915: Serialise execbuf operation after a dma-buf reservation object Chris Wilson
2016-09-05 13:04 ` [PATCH 20/21] drm/i915: Enable userspace to opt-out of implicit fencing Chris Wilson
2016-09-05 13:04 ` [PATCH 21/21] drm/i915: Support explicit fencing for execbuf Chris Wilson
2016-09-05 13:59 ` ✗ Fi.CI.BAT: failure for series starting with [01/21] drm/i915: Add a sw fence for collecting up dma fences Patchwork
2016-09-05 14:07 ` Chris Wilson
2016-09-07 14:44 ` [PATCH v2 01/22] " Chris Wilson
2016-09-07 14:44 ` [PATCH v2 02/22] drm/i915: Only queue requests during execlists submission Chris Wilson
2016-09-07 14:44 ` [PATCH v2 03/22] drm/i915: Record the position of the workarounds in the tail of the request Chris Wilson
2016-09-07 14:44 ` [PATCH v2 04/22] drm/i915: Compute the ELSP register location once Chris Wilson
2016-09-07 14:44 ` [PATCH v2 05/22] drm/i915: Reorder submitting the requests to ELSP Chris Wilson
2016-09-07 14:45 ` [PATCH v2 06/22] drm/i915: Simplify ELSP queue request tracking Chris Wilson
2016-09-07 14:45 ` [PATCH v2 07/22] drm/i915: Separate out reset flags from the reset counter Chris Wilson
2016-09-07 14:45 ` [PATCH v2 08/22] drm/i915: Drop local struct_mutex around intel_init_emon[ilk] Chris Wilson
2016-09-07 14:45 ` [PATCH v2 09/22] drm/i915: Expand bool interruptible to pass flags to i915_wait_request() Chris Wilson
2016-09-07 14:45 ` [PATCH v2 10/22] drm/i915: Mark up all locked waiters Chris Wilson
2016-09-07 14:45 ` [PATCH v2 11/22] drm/i915: Perform a direct reset of the GPU from the waiter Chris Wilson
2016-09-08 9:35 ` Mika Kuoppala
2016-09-07 14:45 ` [PATCH v2 12/22] drm/i915: Replace wait-on-mutex with wait-on-bit in reset worker Chris Wilson
2016-09-08 10:52 ` Mika Kuoppala
2016-09-08 13:24 ` Chris Wilson
2016-09-07 14:45 ` [PATCH v2 13/22] drm/i915: Update reset path to fix incomplete requests Chris Wilson
2016-09-08 12:03 ` Mika Kuoppala
2016-10-03 12:44 ` Tvrtko Ursulin
2016-10-03 12:56 ` Chris Wilson
2016-09-07 14:45 ` [PATCH v2 14/22] drm/i915: Drive request submission through fence callbacks Chris Wilson
2016-09-07 14:45 ` [PATCH v2 15/22] drm/i915: Reorder i915_add_request to separate the phases better Chris Wilson
2016-09-07 14:45 ` [PATCH v2 16/22] drm/i915: Prepare object synchronisation for asynchronicity Chris Wilson
2016-09-07 14:45 ` [PATCH v2 17/22] drm/i915/guc: Prepare for nonblocking execbuf submission Chris Wilson
2016-09-12 14:14 ` Tvrtko Ursulin [this message]
2016-09-07 14:45 ` [PATCH v2 18/22] drm/i915: Ignore valid but unknown semaphores Chris Wilson
2016-09-08 6:31 ` Joonas Lahtinen
2016-09-07 14:45 ` [PATCH v2 19/22] drm/i915: Nonblocking request submission Chris Wilson
2016-09-07 14:45 ` [PATCH v2 20/22] drm/i915: Serialise execbuf operation after a dma-buf reservation object Chris Wilson
2016-09-07 14:45 ` [PATCH v2 21/22] drm/i915: Enable userspace to opt-out of implicit fencing Chris Wilson
2016-09-07 14:45 ` [PATCH v2 22/22] drm/i915: Support explicit fencing for execbuf Chris Wilson
2016-09-07 15:49 ` ✗ Fi.CI.BAT: warning for series starting with [01/21] drm/i915: Add a sw fence for collecting up dma fences (rev22) 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=57D6B85C.80007@linux.intel.com \
--to=tvrtko.ursulin@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 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.