From: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
To: Chris Wilson <chris@chris-wilson.co.uk>, intel-gfx@lists.freedesktop.org
Subject: Re: [PATCH 03/12] drm/i915: Remove engine->execlist_lock
Date: Thu, 3 Nov 2016 13:31:28 +0000 [thread overview]
Message-ID: <d420b3cd-7550-ae49-9117-16455e1d6c2d@linux.intel.com> (raw)
In-Reply-To: <20161103122822.GJ7060@nuc-i3427.alporthouse.com>
On 03/11/2016 12:28, Chris Wilson wrote:
> On Thu, Nov 03, 2016 at 10:47:54AM +0000, Tvrtko Ursulin wrote:
>>
>> On 02/11/2016 17:50, Chris Wilson wrote:
>>> @@ -600,9 +598,8 @@ static void intel_lrc_irq_handler(unsigned long data)
>>> static void execlists_submit_request(struct drm_i915_gem_request *request)
>>> {
>>> struct intel_engine_cs *engine = request->engine;
>>> - unsigned long flags;
>>>
>>> - spin_lock_irqsave(&engine->execlist_lock, flags);
>>
>> Again I am confused why this wasn't just _bh.
>
> We may be in hardirq context here (normally, from just i915, we are
> not). At the very least irqs are disabled here making spin_unlock_bh()
> veboten.
Blast, I thought softirq are a subset of hardirq. :) On looking at the
code I see it is not implemented at all like that. Apart from sometimes. :)
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:[~2016-11-03 13:31 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-11-02 17:50 Trivial priority scheduler Chris Wilson
2016-11-02 17:50 ` [PATCH 01/12] drm/i915: Split request submit/execute phase into two Chris Wilson
2016-11-03 10:35 ` Tvrtko Ursulin
2016-11-02 17:50 ` [PATCH 02/12] drm/i915: Defer transfer onto execution timeline to actual hw submission Chris Wilson
2016-11-03 10:34 ` Tvrtko Ursulin
2016-11-03 10:51 ` Chris Wilson
2016-11-03 11:27 ` Chris Wilson
2016-11-02 17:50 ` [PATCH 03/12] drm/i915: Remove engine->execlist_lock Chris Wilson
2016-11-03 10:47 ` Tvrtko Ursulin
2016-11-03 12:28 ` Chris Wilson
2016-11-03 13:31 ` Tvrtko Ursulin [this message]
2016-11-02 17:50 ` [PATCH 04/12] drm/i915/scheduler: Signal the arrival of a new request Chris Wilson
2016-11-03 10:49 ` Tvrtko Ursulin
2016-11-02 17:50 ` [PATCH 05/12] drm/i915/scheduler: Record all dependencies upon request construction Chris Wilson
2016-11-03 11:03 ` Tvrtko Ursulin
2016-11-03 11:55 ` Chris Wilson
2016-11-04 14:44 ` Tvrtko Ursulin
2016-11-04 15:11 ` Chris Wilson
2016-11-07 9:12 ` Tvrtko Ursulin
2016-11-07 9:30 ` Chris Wilson
2016-11-07 13:30 ` Tvrtko Ursulin
2016-11-07 13:39 ` Chris Wilson
2016-11-07 13:42 ` Tvrtko Ursulin
2016-11-02 17:50 ` [PATCH 06/12] drm/i915/scheduler: Execute requests in order of priorities Chris Wilson
2016-11-03 16:21 ` Tvrtko Ursulin
2016-11-03 17:44 ` Chris Wilson
2016-11-03 19:47 ` Chris Wilson
2016-11-04 9:20 ` Chris Wilson
2016-11-02 17:50 ` [PATCH 07/12] drm/i915/scheduler: Boost priorities for flips Chris Wilson
2016-11-03 16:29 ` Tvrtko Ursulin
2016-11-03 16:54 ` Chris Wilson
2016-11-02 17:50 ` [PATCH 08/12] drm/i915/guc: Cache the client mapping Chris Wilson
2016-11-03 16:37 ` Tvrtko Ursulin
2016-11-03 20:01 ` Chris Wilson
2016-11-02 17:50 ` [PATCH 09/12] HACK drm/i915/scheduler: emulate a scheduler for guc Chris Wilson
2016-11-03 13:17 ` Tvrtko Ursulin
2016-11-02 17:50 ` [PATCH 10/12] drm/i915/scheduler: Support user-defined priorities Chris Wilson
2016-11-02 17:50 ` [PATCH 11/12] drm/i915: Enable userspace to opt-out of implicit fencing Chris Wilson
2016-11-02 17:50 ` [PATCH 12/12] drm/i915: Support explicit fencing for execbuf Chris Wilson
2016-11-02 18:45 ` ✓ Fi.CI.BAT: success for series starting with [01/12] drm/i915: Split request submit/execute phase into two 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=d420b3cd-7550-ae49-9117-16455e1d6c2d@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