drm/i915/icl: Default to Thread Group preemption for compute workloads
authorMichał Winiarski <michal.winiarski@intel.com>
Tue, 5 Mar 2019 12:48:26 +0000 (13:48 +0100)
committerChris Wilson <chris@chris-wilson.co.uk>
Tue, 5 Mar 2019 18:55:06 +0000 (18:55 +0000)
commitd846325ad0e5cd06f441299cdbec6ab8ba3a3c45
tree10ed62a47fe74d6a36e8a092aa323b1fcc1025b7
parentcf4331dd3975f89fe4d20c6113620c9139b1c147
drm/i915/icl: Default to Thread Group preemption for compute workloads

We assumed that the default preemption granularity is fine for ICL.
Unfortunately, it turns out that some drivers don't support mid-thread
preemption for compute workloads.
If a workload that doesn't support mid-thread preemption gets mid-thread
preempted, we're going to observe a GPU hang.
While I'm here, let's also update the "workaround" naming.

Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Anuj Phogat <anuj.phogat@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Rafael Antognolli <rafael.antognolli@intel.com>
Tested-by: Anuj Phogat <anuj.phogat@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: Rafael Antognolli <rafael.antognolli@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190305124827.23446-1-michal.winiarski@intel.com
drivers/gpu/drm/i915/intel_workarounds.c