From: Chris Wilson <chris@chris-wilson.co.uk>
To: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>,
intel-gfx@lists.freedesktop.org
Subject: Re: [PATCH 3/3] drm/i915: Pipeline PDP updates for Braswell
Date: Fri, 07 Dec 2018 10:39:53 +0000 [thread overview]
Message-ID: <154417918867.31489.9840744199174610911@skylake-alporthouse-com> (raw)
In-Reply-To: <60283cd2-533b-a606-3879-be7e971ab343@linux.intel.com>
Quoting Tvrtko Ursulin (2018-12-07 10:30:53)
> Is BSW fixed now? Or just a tiny bit better?
For some value of a lot better. gem_concurrent_blit is still getting the
odd false-positive missed-breadcrumb report, the occasional incoherency
(I think is insufficient mb around fence register changes) and a rare
invalid TLB GPU hang (EMIT_INVALIDATE harder?).
On the positive side, the machine hasn't died for a few days (the
LRI forcewake errors kill the machine), and at its worst
gem_concurrent_blit could GPU hang within a few seconds. However, not
once have I been able to reproduce the GPU hangs with gem_ctx_create and
friends as seen by CI, so more than likely we are looking at more than
one problem. Fingers crossed this is sufficient to shut CI up (with the
exception of those rare gem_mmap_gtt incoherency failures).
-Chris
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2018-12-07 10:39 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-12-07 9:02 [PATCH 1/3] drm/i915: Push EMIT_INVALIDATE at request start to backends Chris Wilson
2018-12-07 9:02 ` [PATCH 2/3] drm/i915/ringbuffer: EMIT_INVALIDATE after switch context Chris Wilson
2018-12-07 10:25 ` Tvrtko Ursulin
2018-12-07 9:02 ` [PATCH 3/3] drm/i915: Pipeline PDP updates for Braswell Chris Wilson
2018-12-07 10:30 ` Tvrtko Ursulin
2018-12-07 10:39 ` Chris Wilson [this message]
2018-12-07 10:22 ` [PATCH 1/3] drm/i915: Push EMIT_INVALIDATE at request start to backends Tvrtko Ursulin
2018-12-07 11:28 ` ✓ Fi.CI.BAT: success for series starting with [1/3] " Patchwork
2018-12-07 13:34 ` Chris Wilson
2018-12-07 17:25 ` ✓ Fi.CI.IGT: " Patchwork
-- strict thread matches above, loose matches on Subject: below --
2018-11-28 12:26 [PATCH 1/3] drm/i915/ringbuffer: Clear semaphore sync registers on ring init Chris Wilson
2018-11-28 12:26 ` [PATCH 3/3] drm/i915: Pipeline PDP updates for Braswell Chris Wilson
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=154417918867.31489.9840744199174610911@skylake-alporthouse-com \
--to=chris@chris-wilson.co.uk \
--cc=intel-gfx@lists.freedesktop.org \
--cc=tvrtko.ursulin@linux.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.