From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
To: Chris Wilson <chris@chris-wilson.co.uk>, igt-dev@lists.freedesktop.org
Subject: Re: [igt-dev] [PATCH i-g-t 10/10] tests/i915/exec_fence: add timeline fence tests
Date: Fri, 2 Aug 2019 12:47:29 +0300 [thread overview]
Message-ID: <9a18b2c4-db2b-203e-e3e9-fee1ae0ca748@intel.com> (raw)
In-Reply-To: <156473711931.6598.14824855310596046770@skylake-alporthouse-com>
On 02/08/2019 12:11, Chris Wilson wrote:
> Quoting Lionel Landwerlin (2019-08-02 10:03:59)
>> On 31/07/2019 23:33, Chris Wilson wrote:
>>> Quoting Lionel Landwerlin (2019-07-25 11:30:34)
>>> You could move this to a second context and avoid the differentiation
>>> between engines:
>>>
>>> fence.flags = I915_EXEC_FENCE_WAIT;
>>> execbuf.rsvd1 = gem_context_create(fd);
>>>
>>> n = 0;
>>> for_each_engine(fd, engine) {
>>> obj.handle = gem_create(fd, 4096);
>>> gem_write(fd, obj.handle, 0, &bbe, sizeof(bbe));
>>>
>>> /* Unsynchronised will execute ahead of the blockage */
>>> execbuf.flags = engine;
>>> execbuf.cliprects_ptr = 0;
>>> gem_execbuf(fd, &execbuf);
>>> gem_sync(fd, obj.handle);
>>
>> Not quite sure this ends up blocking on engine=1.
> It's a different context, it's allowed to execute ahead of the spinner
> when the spinner exceeds its timeslice -- so long as preemption is
> enabled on the spinner. If not, that's kernel bug.
> -Chris
>
Hmm... modifying the existing test_syncobj_wait() to do the same leads
to a deadlock.
That's on a stable 5.0 kernel, so that appears unrelated to my timeline
semaphore changes.
-Lionel
_______________________________________________
igt-dev mailing list
igt-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/igt-dev
next prev parent reply other threads:[~2019-08-02 9:47 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-25 10:30 [igt-dev] [PATCH i-g-t 00/10] Vulkan performance queries support & others Lionel Landwerlin
2019-07-25 10:30 ` [igt-dev] [PATCH i-g-t 01/10] include: temporary import of headers Lionel Landwerlin
2019-07-25 10:30 ` [igt-dev] [PATCH i-g-t 02/10] tests/i915-query: add new tests for perf configurations queries Lionel Landwerlin
2019-07-25 10:30 ` [igt-dev] [PATCH i-g-t 03/10] tests/perf: add tests for holding preemption Lionel Landwerlin
2019-07-25 10:30 ` [igt-dev] [PATCH i-g-t 04/10] tests/perf: add tests to new OA reconfiguration execbuf extension Lionel Landwerlin
2019-07-25 10:30 ` [igt-dev] [PATCH i-g-t 05/10] lib/syncobj: drop local declarations Lionel Landwerlin
2019-07-25 10:30 ` [igt-dev] [PATCH i-g-t 06/10] igt: add timeline test cases Lionel Landwerlin
2019-07-26 2:56 ` zhoucm1
2019-07-26 9:07 ` Lionel Landwerlin
2019-07-25 10:30 ` [igt-dev] [PATCH i-g-t 07/10] tests/syncobj_timeline: add more timeline tests Lionel Landwerlin
2019-07-25 10:30 ` [igt-dev] [PATCH i-g-t 08/10] tests/i915/exec_fence: switch to internal headers Lionel Landwerlin
2019-07-25 10:30 ` [igt-dev] [PATCH i-g-t 09/10] tests/i915/exec_fence: reuse syncobj helpers Lionel Landwerlin
2019-07-25 10:30 ` [igt-dev] [PATCH i-g-t 10/10] tests/i915/exec_fence: add timeline fence tests Lionel Landwerlin
2019-07-31 20:33 ` Chris Wilson
2019-08-02 9:03 ` Lionel Landwerlin
2019-08-02 9:11 ` Chris Wilson
2019-08-02 9:47 ` Lionel Landwerlin [this message]
2019-07-31 20:35 ` Chris Wilson
2019-07-25 11:18 ` [igt-dev] ✗ GitLab.Pipeline: warning for Vulkan performance queries support & others Patchwork
2019-07-25 11:19 ` [igt-dev] ✓ Fi.CI.BAT: success " Patchwork
2019-07-25 16:37 ` [igt-dev] ✗ Fi.CI.IGT: failure " 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=9a18b2c4-db2b-203e-e3e9-fee1ae0ca748@intel.com \
--to=lionel.g.landwerlin@intel.com \
--cc=chris@chris-wilson.co.uk \
--cc=igt-dev@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