Date: Tue, 14 Jun 2011 21:43:59 -0700
From: Ben Widawsky <ben@bwidawsk.net>
To: Daniel J Blueman <daniel.blueman@gmail.com>
Cc: Eric Anholt <eric@anholt.net>, intel-gfx@lists.freedesktop.org,
        linux-kernel@vger.kernel.org, Dave Airlie <airlied@redhat.com>
Subject: Re: [Intel-gfx] [PATCH 3.0-rc3] i915: Fix gen6 (SNB) GPU stalling
Message-ID: <20110615044359.GA27884@snipes.kumite>
Mail-Followup-To: Daniel J Blueman <daniel.blueman@gmail.com>,
	Eric Anholt <eric@anholt.net>, intel-gfx@lists.freedesktop.org,
	linux-kernel@vger.kernel.org, Dave Airlie <airlied@redhat.com>
References: <1308070307-2630-1-git-send-email-daniel.blueman@gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <1308070307-2630-1-git-send-email-daniel.blueman@gmail.com>
User-Agent: Mutt/1.5.21 (2010-09-15)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 3033
Lines: 72

On Wed, Jun 15, 2011 at 12:51:47AM +0800, Daniel J Blueman wrote:
> On 14 June 2011 13:23, Eric Anholt <eric@anholt.net> wrote:
> > On Tue, 14 Jun 2011 12:18:36 +0800, Daniel J Blueman <daniel.blueman@gmail.com> wrote:
> >> Hi Eric,
> >>
> >> The frequent ~1.5s pauses I hit with SNB hardware in the gnome3 UI (eg
> >> whenever you hit the top-left of the screen to show all windows) are
> >> nicely addressed by your recent wake patch [1] (ported to -rc3). Thus
> >> I see no 'missed IRQ' kernel messages.
> >>
> >> As this addresses a significant usability regression, are you happy to
> >> add it to the 3.0-rc queue? I think it has very good value in -stable
> >> also (assuming correctness). What do you think?
> >
> > This one had significant performance impacts, and later hacks in this
> > series worked around the problem to approximately the same level of
> > success with less impact, and we don't actually have a justification of
> > why any of them work.  We were still hoping to come up with some clue,
> > and haven't yet.
> 
> True; that is quite heavy handed delay looping.
> 
> It's a pity the usual Intel font didn't make it to the programmer's
> reference manuals. Anyway, unmasking the blitter user interrupt in the hardware
> status mask register addresses the root cause. Out of reset it's FFFFFFFFh,
> so we don't need to read it here.
> 
> It would be good to get this into -rc4. -stable probably needs some additional
> tweaks.
> 
> Signed-off-by: Daniel J Blueman <daniel.blueman@gmail.com>
> ---
>  drivers/gpu/drm/i915/i915_irq.c |    6 ++++++
>  1 files changed, 6 insertions(+), 0 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
> index b9fafe3..9a98c1b 100644
> --- a/drivers/gpu/drm/i915/i915_irq.c
> +++ b/drivers/gpu/drm/i915/i915_irq.c
> @@ -1827,6 +1827,12 @@ int ironlake_irq_postinstall(struct drm_device *dev)
>  		ironlake_enable_display_irq(dev_priv, DE_PCU_EVENT);
>  	}
>  
> +	if (IS_GEN6(dev))
> +		/* allow blitter user interrupt to generate a MSI write from
> +		   the ISR */
> +		I915_WRITE(GEN6_BLITTER_HWSTAM,
> +			0xffffffff & ~GEN6_BLITTER_USER_INTERRUPT);
> +
>  	return 0;
>  }
>  

I wish the docs said that that this hwstam unmasked MI_USER_INTERRUPTS
parsed by the Blitter Command Parser, instead of the Render Command
parser.

I was just about to write an email about how this is just making the
same interrupt happen twice, when I realized that the docs make no
sense, and this must be a copy-paste doc bug.

This patch sounds good to me. Two small comments:
1. The HWSTAM is touched in preinstall already, why not move this there?
2. I'd prefer you read the register even though as you say it isn't
necessary. It just makes the code self-documented by doing it that way.

Ben
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/