Re: [PATCH] drm/i915: paper over missed irq issues with force wake vodoo

[Daniel Vetter <daniel@ffwll.ch>]

On Wed, Jan 04, 2012 at 07:40:45PM +0100, Daniel Vetter wrote:
> Two things seem to do the trick on my ivb machine here:
> - prevent the gt from powering down while waiting for seqno
>   notification interrupts by grabbing the force_wake in get_irq (and
>   dropping it in put_irq again).
> - ordering writes from the ring's CS by reading a CS register, ACTHD
>   seems to work.
> 
> Only the blt&bsd ring on ivb seem to be massively affected by this,
> but for paranoia do this dance also on the render ring and on snb
> (i.e. all gpus with forcewake).
> 
> Tested with Eric's glCopyPixels loop which without this patch scores a
> missed irq every few seconds.
> 
> This patch needs my forcewake rework to use a spinlock instead of
> dev->struct_mutex.
> 
> v2: Improve the comment per Eugeni Dodonov's suggestion.
> 
> Cc: stable@kernel.org
> Cc: Eric Anholt <eric@anholt.net>
> Cc: Kenneth Graunke <kenneth@whitecape.org>
> Cc: Eugeni Dodonov <eugeni.dodonov@intel.com>
> Tested-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
> Reviewed-by: Eugeni Dodonov <eugeni.dodonov@intel.com>
> Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

>From the internal doc "SNB GT PM Programming Guide", Section 4.3.1:

"GT does not generate interrupts while in RC6 (by design)"

It talks about the PM interrupt but I think this might also apply to
interrupts in general. So I think we should apply the voodoo patch also to
snb.

My current working theory is hw engineers changed the way hwstam writes
are generated wrt to the read/write/irq pipeline on ivb and we've only
been lucky that it syncs out everything on snb before the gpu goes into
deep sleep states.
-Daniel
-- 
Daniel Vetter
Mail: daniel@ffwll.ch
Mobile: +41 (0)79 365 57 48