All of lore.kernel.org
 help / color / mirror / Atom feed
From: Keith Packard <keithp@keithp.com>
To: Daniel Vetter <daniel@ffwll.ch>, Eric Anholt <eric@anholt.net>
Cc: intel-gfx@lists.freedesktop.org, "Dodonov,
	Eugeni" <eugeni.dodonov@intel.com>
Subject: Re: gen7 missed IRQ workaround series.
Date: Tue, 03 Jan 2012 15:38:25 -0800	[thread overview]
Message-ID: <86lipomk5q.fsf@sumi.keithp.com> (raw)
In-Reply-To: <CAKMK7uHt6y+v7ptwekL-CM4SvQiUUvnwVwR_=kc5rGAtoDo-aA@mail.gmail.com>


[-- Attachment #1.1: Type: text/plain, Size: 979 bytes --]

On Wed, 4 Jan 2012 00:04:18 +0100, Daniel Vetter <daniel@ffwll.ch> wrote:

> I kinda prefer Chris' approach of sticking with irqs, but backing it up
> with a timer in the msec range. Can't find that patch though atm (iirc
> it's in bugzilla somewhere).

I think we've resolved that the interrupt arrives, but that it is not
serialized wrt the memory write. So, what I'd love to see is whether
waiting for the irq and then busy looping for 'a while' works. This
would allow for long-running operations to idle the CPU and then hit the
interrupt and spin until the memory write is recognized.

Any solution which can leave operations unacknowledged for 'ms'
timeframes seems like a potential for serious performance
problems. Eric's simple spinning approach seems fine for the BLT ring
which we don't use that often; something more complicated and yet not
entirely timer-based might be more efficient for longer-running operations.

-- 
keith.packard@intel.com

[-- Attachment #1.2: Type: application/pgp-signature, Size: 827 bytes --]

[-- Attachment #2: Type: text/plain, Size: 159 bytes --]

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/intel-gfx

  reply	other threads:[~2012-01-03 23:36 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-12-22 22:54 gen7 missed IRQ workaround series Eric Anholt
2011-12-22 22:54 ` [PATCH 1/3] drm/i915: Do the fallback non-IRQ wait in ring throttle, too Eric Anholt
2011-12-22 22:55 ` [PATCH 2/3] drm/i915: Work around gen7 BLT ring synchronization issues Eric Anholt
2011-12-22 22:55 ` [PATCH 3/3] drm/i915: Make the fallback IRQ wait not sleep Eric Anholt
2012-01-02 18:25 ` gen7 missed IRQ workaround series Eugeni Dodonov
2012-01-02 20:17 ` Kenneth Graunke
2012-01-03 23:04 ` Daniel Vetter
2012-01-03 23:38   ` Keith Packard [this message]
2012-01-04 17:02     ` Daniel Vetter
2012-01-04 17:05       ` Keith Packard
2012-01-04 17:24         ` 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=86lipomk5q.fsf@sumi.keithp.com \
    --to=keithp@keithp.com \
    --cc=daniel@ffwll.ch \
    --cc=eric@anholt.net \
    --cc=eugeni.dodonov@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.