From: Daniel Vetter <daniel@ffwll.ch>
To: Dave Gordon <david.s.gordon@intel.com>
Cc: intel-gfx@lists.freedesktop.org
Subject: Re: [PATCH] drm/i915: Bug fixes to ring 'head' updating
Date: Tue, 18 Nov 2014 09:02:43 +0100 [thread overview]
Message-ID: <20141118080243.GU25711@phenom.ffwll.local> (raw)
In-Reply-To: <1415021344-24875-1-git-send-email-david.s.gordon@intel.com>
On Mon, Nov 03, 2014 at 01:29:04PM +0000, Dave Gordon wrote:
> Fixes to both the LRC and the legacy ringbuffer code to correctly
> calculate and update the available space in a ring.
>
> The logical ring code was updating the software ring 'head' value
> by reading the hardware 'HEAD' register. In LRC mode, this is not
> valid as the hardware is not necessarily executing the same context
> that is being processed by the software. Thus reading the h/w HEAD
> could put an unrelated (undefined, effectively random) value into
> the s/w 'head' -- A Bad Thing for the free space calculations.
>
> In addition, the old code could update a ringbuffer's 'head' value
> from the 'last_retired_head' even when the latter hadn't been recently
> updated and therefore had a value of -1; this would also confuse the
> freespace calculations. Now, we consume 'last_retired_head' in just
> one place, ensuring that this confusion does not arise.
>
> Change-Id: Id7ce9096ed100a2882c68a54206f30b6c87e92fa
> Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
Is there an igt testcase which readily reproduces this? Or can we have
one?
-Daniel
--
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
next prev parent reply other threads:[~2014-11-18 8:02 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-11-03 13:29 [PATCH] drm/i915: Bug fixes to ring 'head' updating Dave Gordon
2014-11-03 20:59 ` Chris Wilson
2014-11-04 14:17 ` Dave Gordon
2014-11-17 16:31 ` Daniel Vetter
2014-11-18 4:43 ` akash goel
2014-11-18 8:02 ` Daniel Vetter [this message]
2014-11-24 9:35 ` Daniel Vetter
2014-11-18 15:00 ` Deepak S
2014-11-18 19:53 ` Dave Gordon
2014-11-18 20:07 ` [PATCH v2 0/3] " Dave Gordon
2014-11-18 20:07 ` [PATCH v2 1/3] drm/i915: Check for matching ringbuffer in logical_ring_wait_request() Dave Gordon
2014-11-25 4:14 ` Deepak S
2014-11-18 20:07 ` [PATCH v2 2/3] drm/i915: Don't read 'HEAD' MMIO register in LRC mode Dave Gordon
2014-11-25 7:57 ` Deepak S
2014-11-18 20:07 ` [PATCH v2 3/3] drm/i915: Consolidate ring freespace calculations Dave Gordon
2014-11-24 10:04 ` Daniel Vetter
2014-11-24 14:32 ` Dave Gordon
2014-11-25 11:41 ` Daniel Vetter
2014-11-25 11:47 ` Chris Wilson
2014-11-25 7:59 ` Deepak S
2014-11-27 11:22 ` [PATCH v3 0/2] Updates to " Dave Gordon
2014-11-27 11:22 ` [PATCH v3 1/2] drm/i915: Make ring freespace calculation more robust Dave Gordon
2014-11-27 11:22 ` [PATCH v3 2/2] drm/i915: Consolidate ring freespace calculations Dave Gordon
2014-11-27 19:20 ` [PATCH v3 2/2] drm/i915: Consolidate ring freespace shuang.he
2014-11-28 17:51 ` [PATCH v3 2/2] drm/i915: Consolidate ring freespace calculations Daniel Vetter
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=20141118080243.GU25711@phenom.ffwll.local \
--to=daniel@ffwll.ch \
--cc=david.s.gordon@intel.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 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.