Intel-GFX Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
To: Chris Wilson <chris@chris-wilson.co.uk>, intel-gfx@lists.freedesktop.org
Subject: Re: [PATCH 02/12] drm/i915/execlists: Suppress mere WAIT preemption
Date: Mon, 4 Feb 2019 12:29:15 +0000	[thread overview]
Message-ID: <bf0eb80c-d22e-ba0f-1280-5e7c7088a9ce@linux.intel.com> (raw)
In-Reply-To: <154928275341.14784.10617292594574710646@skylake-alporthouse-com>


On 04/02/2019 12:19, Chris Wilson wrote:
> Quoting Tvrtko Ursulin (2019-02-04 12:08:50)
>>
>> On 04/02/2019 10:18, Chris Wilson wrote:
>>>>> +static int effective_prio(const struct i915_request *rq)
>>>>> +{
>>>>> +     /* Restrict mere WAIT boosts from triggering preemption */
>>>>> +     return rq_prio(rq) | __NO_PREEMPTION;
>>>>> +}
>>>>
>>>> I suggest adding i915_request_effective_prio to i915_request.h - it is
>>>> verbose but avoids two implementation.
>>>
>>> Too verbose... And it may differ depending on backend details...
>>>
>>> We don't even need to or in no-preemption until later...
>>
>> Hmm.. I would hope it wouldn't depend on the backend. We should at least
>> I think try to make things decoupled at this level.
> 
> I'm speculating about what the long term interface will be. If they can
> only handle static priorities on a context level and take all
> dependencies as semaphores, guc submission is a mere conduit and very
> hands off.

Point taken, the force of GuC influencing the i915 design will be too 
strong.

Regards,

Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

  reply	other threads:[~2019-02-04 12:29 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-02-04  8:41 [PATCH 01/12] drm/i915: Allow normal clients to always preempt idle priority clients Chris Wilson
2019-02-04  8:41 ` [PATCH 02/12] drm/i915/execlists: Suppress mere WAIT preemption Chris Wilson
2019-02-04 10:06   ` Tvrtko Ursulin
2019-02-04 10:18     ` Chris Wilson
2019-02-04 12:08       ` Tvrtko Ursulin
2019-02-04 12:19         ` Chris Wilson
2019-02-04 12:29           ` Tvrtko Ursulin [this message]
2019-02-04 10:49   ` [PATCH] " Chris Wilson
2019-02-04  8:41 ` [PATCH 03/12] drm/i915/execlists: Suppress redundant preemption Chris Wilson
2019-02-04 12:05   ` Tvrtko Ursulin
2019-02-04 12:25     ` Chris Wilson
2019-02-04  8:41 ` [PATCH 04/12] drm/i915/selftests: Exercise some AB...BA preemption chains Chris Wilson
2019-02-04  8:41 ` [PATCH 05/12] drm/i915: Trim NEWCLIENT boosting Chris Wilson
2019-02-04 12:11   ` Tvrtko Ursulin
2019-02-04 12:26     ` Chris Wilson
2019-02-04 12:42       ` Tvrtko Ursulin
2019-02-04 12:27     ` Chris Wilson
2019-02-04  8:41 ` [PATCH 06/12] drm/i915: Show support for accurate sw PMU busyness tracking Chris Wilson
2019-02-04 12:14   ` Tvrtko Ursulin
2019-02-04 12:28     ` Chris Wilson
2019-02-04 12:29       ` Chris Wilson
2019-02-04 12:37       ` Tvrtko Ursulin
2019-02-04 12:43         ` Chris Wilson
2019-02-04  8:41 ` [PATCH 07/12] drm/i915: Revoke mmaps and prevent access to fence registers across reset Chris Wilson
2019-02-04 13:33   ` Mika Kuoppala
2019-02-04 13:47     ` Chris Wilson
2019-02-04  8:41 ` [PATCH 08/12] drm/i915: Force the GPU reset upon wedging Chris Wilson
2019-02-04  8:41 ` [PATCH 09/12] drm/i915: Uninterruptibly drain the timelines on unwedging Chris Wilson
2019-02-04  8:41 ` [PATCH 10/12] drm/i915: Wait for old resets before applying debugfs/i915_wedged Chris Wilson
2019-02-04  8:41 ` [PATCH 11/12] drm/i915: Serialise resets with wedging Chris Wilson
2019-02-04  8:41 ` [PATCH 12/12] drm/i915: Don't claim an unstarted request was guilty Chris Wilson
2019-02-04  9:20 ` [PATCH 01/12] drm/i915: Allow normal clients to always preempt idle priority clients Tvrtko Ursulin
2019-02-04 10:19 ` ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/12] " Patchwork
2019-02-04 10:23 ` ✗ Fi.CI.SPARSE: " Patchwork
2019-02-04 10:48 ` ✓ Fi.CI.BAT: success " Patchwork
2019-02-04 11:27 ` ✗ Fi.CI.BAT: failure for series starting with [01/12] drm/i915: Allow normal clients to always preempt idle priority clients (rev2) 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=bf0eb80c-d22e-ba0f-1280-5e7c7088a9ce@linux.intel.com \
    --to=tvrtko.ursulin@linux.intel.com \
    --cc=chris@chris-wilson.co.uk \
    --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