Re: [PATCH 0/9] drm/i915: Cursor vblank evasion

["Ville Syrjälä" <ville.syrjala@linux.intel.com>]

On Wed, Jan 17, 2024 at 11:30:10AM +0000, Shankar, Uma wrote:
> 
> 
> > -----Original Message-----
> > From: Intel-gfx <intel-gfx-bounces@lists.freedesktop.org> On Behalf Of Ville
> > Syrjala
> > Sent: Wednesday, December 13, 2023 3:55 PM
> > To: intel-gfx@lists.freedesktop.org
> > Subject: [PATCH 0/9] drm/i915: Cursor vblank evasion
> > 
> > From: Ville Syrjälä <ville.syrjala@linux.intel.com>
> > 
> > MTL seems very good at racing the cursor mailbox updates against the vblank,
> > causing things to not latch for long enough to cause GTT faults. Attempt to hook
> > up vblank evasions into the legacy cursor path to avoid this.
> > 
> > Also revert a dangerous wm/ddb change related to cursors.
> 
> I have already RB'ed the changes in the series but somehow patchwork had issues and
> not reflecting the same.
> 
> FWIW, this series is
> Reviewed-by: Uma Shankar <uma.shankar@intel.com>
> 
> Please merge once the CI results show green, seems one test
> igt@kms_cursor_legacy@torture-move@pipe-a throwing some warnings.

Seems we're still seeing some timeouts from the vblank evasion,
indicating the schedule_timeout(1ms) took approximately some
integer multiple of the frame time :(

To confirm what's happening I might need to pull the full
vblank evasion debugs to into the cursor path as well...

-- 
Ville Syrjälä
Intel