From: Ted Phelps <phelps@gnusto.com>
To: intel-gfx@lists.freedesktop.org
Subject: Re: [PATCH 10/15] drm/i915: Invalidate fenced read domains upon flush
Date: Thu, 24 Mar 2011 23:52:43 +1000 [thread overview]
Message-ID: <2363.1300974763@orpheus.gnusto.com> (raw)
In-Reply-To: Your message of Thu, 24 Mar 2011 23:47:58 +1000. <2231.1300974478@orpheus.gnusto.com>
Ted Phelps writes:
> Chris Wilson writes:
> > Whenever we finish reading an object through a fence, for safety we
> > clear any GPU read domain and so invalidate any TLBs associated with
> > the fenced region upon its next use.
>
> This change is causing a regression on my Sandybridge CPU (i7 2600K).
> The colours all look right, but the pixels aren't in the right order.
> I'll try to get a screen shot for you.
Grr... Sorry, I've replied to the wrong patch. That one is fine. This
is the problematic one:
commit fc8cf546f12a353bfd344bf922649c0d064fc3f0
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri Mar 18 19:39:59 2011 +0000
drm/i915: Cleanup handling of last_fenced_seqno
Cc: Andy Whitcroft <apw@canonical.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
>From drm-intel-staging.
-Ted
next prev parent reply other threads:[~2011-03-24 13:57 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-03-20 8:58 drm-intel-fixes queue Chris Wilson
2011-03-20 8:58 ` [PATCH 01/15] drm/i915: Remove surplus POSTING_READs before wait_for_vblank Chris Wilson
2011-03-20 8:58 ` [PATCH 02/15] drm/i915: skip redundant operations whilst enabling pipes and planes Chris Wilson
2011-03-20 8:58 ` [PATCH 03/15] drm/i915: Prevent racy removal of request from client list Chris Wilson
2011-03-20 8:58 ` [PATCH 04/15] drm: Fix use-after-free in drm_gem_vm_close() Chris Wilson
2011-03-20 8:58 ` [PATCH 05/15] drm/i915: Re-enable self-refresh Chris Wilson
2011-03-20 8:58 ` [PATCH 06/15] drm/i915: Fix tiling corruption from pipelined fencing Chris Wilson
2011-03-20 8:58 ` [PATCH 07/15] drm/i915/dp: Correct the order of deletion for ghost eDP devices Chris Wilson
2011-03-20 8:58 ` [PATCH 08/15] drm/i915: report correct render clock frequencies on SNB Chris Wilson
2011-03-20 8:58 ` [PATCH 09/15] drm/i915: Track fence setup separately from fenced object lifetime Chris Wilson
2011-03-20 8:58 ` [PATCH 10/15] drm/i915: Invalidate fenced read domains upon flush Chris Wilson
2011-03-24 13:47 ` Ted Phelps
2011-03-24 13:52 ` Ted Phelps [this message]
2011-03-24 14:21 ` Chris Wilson
2011-03-20 8:58 ` [PATCH 11/15] drm/i915: Cleanup handling of last_fenced_seqno Chris Wilson
2011-03-20 8:58 ` [PATCH 12/15] drm/i915: Prevent fence-reuse stalls Chris Wilson
2011-03-20 8:58 ` [PATCH 13/15] drm/i915: Fix computation of pitch for dumb bo creator Chris Wilson
2011-03-20 8:58 ` [PATCH 14/15] drm/i915: Disable pagefaults along execbuffer relocation fast path Chris Wilson
2011-03-20 8:58 ` [PATCH 15/15] drm/i915: Restore missing command flush before interrupt on BLT ring Chris Wilson
2011-03-20 14:22 ` drm-intel-fixes queue Jan Niehusmann
2011-03-20 14:58 ` Chris Wilson
2011-04-07 9:42 ` Zdenek Kabelac
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=2363.1300974763@orpheus.gnusto.com \
--to=phelps@gnusto.com \
--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