All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH 1/2] drm/i915/icl: Default to Thread Group preemption for compute workloads
@ 2019-03-05 12:48 Michał Winiarski
  2019-03-05 12:48 ` [PATCH 2/2] drm/i915/icl: Apply WaEnablePreemptionGranularityControlByUMD Michał Winiarski
                   ` (4 more replies)
  0 siblings, 5 replies; 12+ messages in thread
From: Michał Winiarski @ 2019-03-05 12:48 UTC (permalink / raw)
  To: intel-gfx; +Cc: Anuj Phogat

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>
---
 drivers/gpu/drm/i915/intel_workarounds.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
index 89b4007d5200..2fba33509f4e 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -555,6 +555,11 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine)
 			   GEN10_CACHE_MODE_SS,
 			   0, /* write-only, so skip validation */
 			   _MASKED_BIT_ENABLE(FLOAT_BLEND_OPTIMIZATION_ENABLE));
+
+	/* WaDisableGPGPUMidThreadPreemption:icl */
+	WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1,
+			    GEN9_PREEMPT_GPGPU_LEVEL_MASK,
+			    GEN9_PREEMPT_GPGPU_THREAD_GROUP_LEVEL);
 }
 
 void intel_engine_init_ctx_wa(struct intel_engine_cs *engine)
@@ -1162,8 +1167,8 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 				    GEN7_DISABLE_SAMPLER_PREFETCH);
 	}
 
-	if (IS_GEN(i915, 9) || IS_CANNONLAKE(i915)) {
-		/* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl,cfl,cnl */
+	if (IS_GEN_RANGE(i915, 9, 11)) {
+		/* FtrPerCtxtPreemptionGranularityControl:skl,bxt,kbl,cfl,cnl,icl */
 		wa_masked_en(wal,
 			     GEN7_FF_SLICE_CS_CHICKEN1,
 			     GEN9_FFSC_PERCTX_PREEMPT_CTRL);
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

^ permalink raw reply related	[flat|nested] 12+ messages in thread
* [PATCH 1/2] drm/i915/icl: Default to Thread Group preemption for compute workloads
@ 2019-02-27 15:51 Michał Winiarski
  2019-02-27 17:09 ` ✓ Fi.CI.BAT: success for series starting with [1/2] " Patchwork
  0 siblings, 1 reply; 12+ messages in thread
From: Michał Winiarski @ 2019-02-27 15:51 UTC (permalink / raw)
  To: intel-gfx; +Cc: Anuj Phogat

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>
---
 drivers/gpu/drm/i915/intel_workarounds.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
index 743cf5b00155..a19e1c0052a7 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -555,6 +555,11 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine)
 			   GEN10_CACHE_MODE_SS,
 			   0, /* write-only, so skip validation */
 			   _MASKED_BIT_ENABLE(FLOAT_BLEND_OPTIMIZATION_ENABLE));
+
+	/* WaDisableGPGPUMidThreadPreemption:icl */
+	WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1,
+			    GEN9_PREEMPT_GPGPU_LEVEL_MASK,
+			    GEN9_PREEMPT_GPGPU_THREAD_GROUP_LEVEL);
 }
 
 void intel_engine_init_ctx_wa(struct intel_engine_cs *engine)
@@ -1170,8 +1175,8 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 				    GEN7_DISABLE_SAMPLER_PREFETCH);
 	}
 
-	if (IS_GEN(i915, 9) || IS_CANNONLAKE(i915)) {
-		/* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl,cfl,cnl */
+	if (IS_GEN_RANGE(i915, 9, 11)) {
+		/* FtrPerCtxtPreemptionGranularityControl:skl,bxt,kbl,cfl,cnl,icl */
 		wa_masked_en(wal,
 			     GEN7_FF_SLICE_CS_CHICKEN1,
 			     GEN9_FFSC_PERCTX_PREEMPT_CTRL);
-- 
2.20.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

^ permalink raw reply related	[flat|nested] 12+ messages in thread
end of thread, other threads:[~2020-03-03 18:31 UTC | newest]

Thread overview: 12+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-03-05 12:48 [PATCH 1/2] drm/i915/icl: Default to Thread Group preemption for compute workloads Michał Winiarski
2019-03-05 12:48 ` [PATCH 2/2] drm/i915/icl: Apply WaEnablePreemptionGranularityControlByUMD Michał Winiarski
2019-03-05 17:31   ` Rafael Antognolli
2019-03-05 18:41   ` Chris Wilson
2019-03-05 13:45 ` ✓ Fi.CI.BAT: success for series starting with [1/2] drm/i915/icl: Default to Thread Group preemption for compute workloads Patchwork
2019-03-05 14:48 ` ✓ Fi.CI.IGT: " Patchwork
2019-03-05 17:30 ` [PATCH 1/2] " Rafael Antognolli
2019-03-05 19:10   ` Chris Wilson
2019-03-06 11:20     ` Joonas Lahtinen
2020-03-03 18:31       ` [Intel-gfx] " Jason Ekstrand
2019-03-05 17:37 ` Anuj Phogat
  -- strict thread matches above, loose matches on Subject: below --
2019-02-27 15:51 Michał Winiarski
2019-02-27 17:09 ` ✓ Fi.CI.BAT: success for series starting with [1/2] " Patchwork

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.