[Intel-gfx] [PATCH v3] drm/i915/fbc: FBC causes display flicker when VT-d is enabled on Skylake

Zanoni, Paulo R paulo.r.zanoni at intel.com
Wed Jun 22 22:18:45 UTC 2016


Em Qua, 2016-06-22 às 21:34 +0100, Chris Wilson escreveu:
> On Tue, Jun 21, 2016 at 03:31:25PM +0200, Daniel Vetter wrote:
> > 
> > On Tue, Jun 21, 2016 at 08:25:27AM +0100, Chris Wilson wrote:
> > > 
> > > Erratum SKL075: Display Flicker May Occur When Both VT-d And FBC
> > > Are Enabled
> > > 
> > > "Display flickering may occur when both FBC (Frame Buffer
> > > Compression)
> > > and VT - d (Intel® Virtualization Technology for Directed I/O)
> > > are enabled
> > > and in use by the display controller."
> > > 
> > > Ville found the w/a name in the database:
> > > WaFbcTurnOffFbcWhenHyperVisorIsUsed:skl
> > > 
> > > v2: Log when the quirk is applied.
> > > v3: Ensure i915.enable_fbc is false when !HAS_FBC()
> > > 
> > > Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
> > > Cc: Paulo Zanoni <paulo.r.zanoni at intel.com>
> > > Cc: Ville Syrjälä <ville.syrjala at linux.intel.com>
> > Do we know whether this helps on other machines too? I can imagine
> > that
> > the additional lookup latency just plain wreaks havoc everywhere
> > ...
> Yeah, they do tend to play into fifo trouble. Could find anything
> though. But I think we have enough evidence to suggest acking this
> w/a
> and moving forward if we find any others...

From the HSD, it looks like this problem would lead to an underrun, so
the "disable FBC if we ever get an underrun" would at least help
diminish the damage in case the WA is actually valid for the previous
gens.

> -Chris
> 


More information about the Intel-gfx mailing list