[Intel-gfx] [PATCH v4 1/1] drm/i915/gt: Initialize reserved and unspecified MOCS indices

[Chris Wilson]

Quoting Lucas De Marchi (2020-10-12 17:55:03)
> On Fri, Jul 31, 2020 at 12:23:57AM -0700, Siddiqui, Ayaz A wrote:
> >
> >
> >> -----Original Message-----
> >> From: Siddiqui, Ayaz A <ayaz.siddiqui at intel.com>
> >> Sent: Wednesday, July 29, 2020 3:56 PM
> >> To: intel-gfx at lists.freedesktop.org
> >> Cc: Siddiqui, Ayaz A <ayaz.siddiqui at intel.com>; Chris Wilson <chris at chris-
> >> wilson.co.uk>; De Marchi, Lucas <lucas.demarchi at intel.com>; Lis, Tomasz
> >> <tomasz.lis at intel.com>; Roper, Matthew D <matthew.d.roper at intel.com>;
> >> Joonas Lahtinen <joonas.lahtinen at linux.intel.com>; Francisco Jerez
> >> <currojerez at riseup.net>; Mathew, Alwin <alwin.mathew at intel.com>; Mcguire,
> >> Russell W <russell.w.mcguire at intel.com>; Spruit, Neil R
> >> <neil.r.spruit at intel.com>; Zhou, Cheng <cheng.zhou at intel.com>; Benemelis,
> >> Mike G <mike.g.benemelis at intel.com>
> >> Subject: [PATCH v4 1/1] drm/i915/gt: Initialize reserved and unspecified MOCS
> >> indices
> >>
> >> In order to avoid functional breakage of mis-programmed applications that have
> >> grown to depend on unused MOCS entries, we are programming those entries to
> >> be equal to fully cached ("L3 + LLC") entry.
> >>
> >> These reserved and unspecified entries should not be used as they may be
> >> changed to less performant variants with better coherency in the future if more
> >> entries are needed.
> >>
> >> V2: As suggested by Lucas De Marchi to utilise __init_mocs_table for
> >> programming default value, setting I915_MOCS_PTE index of tgl_mocs_table
> >> with desired value.
> >>
> >> Cc: Chris Wilson <chris at chris-wilson.co.uk>
> >> Cc: Lucas De Marchi <lucas.demarchi at intel.com>
> >> Cc: Tomasz Lis <tomasz.lis at intel.com>
> >> Cc: Matt Roper <matthew.d.roper at intel.com>
> >> Cc: Joonas Lahtinen <joonas.lahtinen at linux.intel.com>
> >> Cc: Francisco Jerez <currojerez at riseup.net>
> >> Cc: Mathew Alwin <alwin.mathew at intel.com>
> >> Cc: Mcguire Russell W <russell.w.mcguire at intel.com>
> >> Cc: Spruit Neil R <neil.r.spruit at intel.com>
> >> Cc: Zhou Cheng <cheng.zhou at intel.com>
> >> Cc: Benemelis Mike G <mike.g.benemelis at intel.com>
> >>
> >> Signed-off-by: Ayaz A Siddiqui <ayaz.siddiqui at intel.com>
> >> Reviewed-by: Lucas De Marchi <lucas.demarchi at intel.com>
> >> ---
> >>  drivers/gpu/drm/i915/gt/intel_mocs.c | 15 +++++++++++----
> >>  1 file changed, 11 insertions(+), 4 deletions(-)
> >>
> >
> >I'm getting a false failure with this patch , which I tested locally and its passing
> >with this patch. I think that this failure is blocking merge of this patch.
> >Can Someone please let me know how to proceed in this case for merging?
> 
> If it's a false failure, you can go ahead and merge it. Better to reply
> to the CI email how is it unrelated.

I would say the kms_frontbuffer_tracking is genuine fail as that is very
cache sensitive. And I've just pushed this to upstream, oops, so now the
problem is a little more urgent.
-Chris