On Thu, Mar 27, 2025 at 12:42:50PM +0200, Jani Nikula wrote: > On Thu, 27 Mar 2025, Andi Shyti <andi.sh...@linux.intel.com> wrote: > > From: Andi Shyti <andi.sh...@intel.com> > > > > Some GPUs, like DG2, can host more than one CCS engine. Some > > workarounds or enablements need to happen only once for all the > > engines in the GT—for example, on the engine with the lowest > > instance. > > > > The FIRST_CCS() helper first checks if the engine is a Compute > > engine, and then whether it's the one with the lowest instance. > > > > Signed-off-by: Andi Shyti <andi.sh...@intel.com> > > --- > > drivers/gpu/drm/i915/i915_drv.h | 3 +++ > > 1 file changed, 3 insertions(+) > > > > diff --git a/drivers/gpu/drm/i915/i915_drv.h > > b/drivers/gpu/drm/i915/i915_drv.h > > index 54538b6f85df..5cb501393c4b 100644 > > --- a/drivers/gpu/drm/i915/i915_drv.h > > +++ b/drivers/gpu/drm/i915/i915_drv.h > > @@ -619,6 +619,9 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, > > #define CCS_MASK(gt) \ > > ENGINE_INSTANCES_MASK(gt, CCS0, I915_MAX_CCS) > > > > +#define FIRST_CCS(e__) \ > > + (CCS_MASK(e__->gt) && (__ffs(CCS_MASK(e__->gt)) == e__->instance)) > > + > > Could I persuade you to find a more specific header file for this, along > with the CCS_MASK etc.?
yes, sure, I think this should go inside the gt/ (I don't also like the name FIRST_CCS but could not come out with anything better). All the engine related defines should go inside the gt/, I will take care of it, but that's argument for another patch. Thanks, Jani, Andi
