Merge drm/drm-next into drm-intel-next

Catch up on 6.1-rc cycle in order to solve the intel_backlight
conflict on linux-next.

Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

1 files changed, 180 insertions, 91 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index ee8a38d02e14..6ae8b07cfaa1 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -488,6 +488,17 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id,
 	engine->logical_mask = BIT(logical_instance);
 	__sprint_engine_name(engine);
 
+	if ((engine->class == COMPUTE_CLASS && !RCS_MASK(engine->gt) &&
+	     __ffs(CCS_MASK(engine->gt)) == engine->instance) ||
+	     engine->class == RENDER_CLASS)
+		engine->flags |= I915_ENGINE_FIRST_RENDER_COMPUTE;
+
+	/* features common between engines sharing EUs */
+	if (engine->class == RENDER_CLASS || engine->class == COMPUTE_CLASS) {
+		engine->flags |= I915_ENGINE_HAS_RCS_REG_STATE;
+		engine->flags |= I915_ENGINE_HAS_EU_PRIORITY;
+	}
+
 	engine->props.heartbeat_interval_ms =
 		CONFIG_DRM_I915_HEARTBEAT_INTERVAL;
 	engine->props.max_busywait_duration_ns =
@@ -499,20 +510,34 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id,
 	engine->props.timeslice_duration_ms =
 		CONFIG_DRM_I915_TIMESLICE_DURATION;
 
-	/* Override to uninterruptible for OpenCL workloads. */
-	if (GRAPHICS_VER(i915) == 12 && engine->class == RENDER_CLASS)
-		engine->props.preempt_timeout_ms = 0;
-
-	if ((engine->class == COMPUTE_CLASS && !RCS_MASK(engine->gt) &&
-	     __ffs(CCS_MASK(engine->gt)) == engine->instance) ||
-	     engine->class == RENDER_CLASS)
-		engine->flags |= I915_ENGINE_FIRST_RENDER_COMPUTE;
-
-	/* features common between engines sharing EUs */
-	if (engine->class == RENDER_CLASS || engine->class == COMPUTE_CLASS) {
-		engine->flags |= I915_ENGINE_HAS_RCS_REG_STATE;
-		engine->flags |= I915_ENGINE_HAS_EU_PRIORITY;
-	}
+	/*
+	 * Mid-thread pre-emption is not available in Gen12. Unfortunately,
+	 * some compute workloads run quite long threads. That means they get
+	 * reset due to not pre-empting in a timely manner. So, bump the
+	 * pre-emption timeout value to be much higher for compute engines.
+	 */
+	if (GRAPHICS_VER(i915) == 12 && (engine->flags & I915_ENGINE_HAS_RCS_REG_STATE))
+		engine->props.preempt_timeout_ms = CONFIG_DRM_I915_PREEMPT_TIMEOUT_COMPUTE;
+
+	/* Cap properties according to any system limits */
+#define CLAMP_PROP(field) \
+	do { \
+		u64 clamp = intel_clamp_##field(engine, engine->props.field); \
+		if (clamp != engine->props.field) { \
+			drm_notice(&engine->i915->drm, \
+				   "Warning, clamping %s to %lld to prevent overflow\n", \
+				   #field, clamp); \
+			engine->props.field = clamp; \
+		} \
+	} while (0)
+
+	CLAMP_PROP(heartbeat_interval_ms);
+	CLAMP_PROP(max_busywait_duration_ns);
+	CLAMP_PROP(preempt_timeout_ms);
+	CLAMP_PROP(stop_timeout_ms);
+	CLAMP_PROP(timeslice_duration_ms);
+
+#undef CLAMP_PROP
 
 	engine->defaults = engine->props; /* never to change again */
 
@@ -536,6 +561,55 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id,
 	return 0;
 }
 
+u64 intel_clamp_heartbeat_interval_ms(struct intel_engine_cs *engine, u64 value)
+{
+	value = min_t(u64, value, jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT));
+
+	return value;
+}
+
+u64 intel_clamp_max_busywait_duration_ns(struct intel_engine_cs *engine, u64 value)
+{
+	value = min(value, jiffies_to_nsecs(2));
+
+	return value;
+}
+
+u64 intel_clamp_preempt_timeout_ms(struct intel_engine_cs *engine, u64 value)
+{
+	/*
+	 * NB: The GuC API only supports 32bit values. However, the limit is further
+	 * reduced due to internal calculations which would otherwise overflow.
+	 */
+	if (intel_guc_submission_is_wanted(&engine->gt->uc.guc))
+		value = min_t(u64, value, guc_policy_max_preempt_timeout_ms());
+
+	value = min_t(u64, value, jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT));
+
+	return value;
+}
+
+u64 intel_clamp_stop_timeout_ms(struct intel_engine_cs *engine, u64 value)
+{
+	value = min_t(u64, value, jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT));
+
+	return value;
+}
+
+u64 intel_clamp_timeslice_duration_ms(struct intel_engine_cs *engine, u64 value)
+{
+	/*
+	 * NB: The GuC API only supports 32bit values. However, the limit is further
+	 * reduced due to internal calculations which would otherwise overflow.
+	 */
+	if (intel_guc_submission_is_wanted(&engine->gt->uc.guc))
+		value = min_t(u64, value, guc_policy_max_exec_quantum_ms());
+
+	value = min_t(u64, value, jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT));
+
+	return value;
+}
+
 static void __setup_engine_capabilities(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *i915 = engine->i915;
@@ -656,16 +730,83 @@ bool gen11_vdbox_has_sfc(struct intel_gt *gt,
 	 */
 	if ((gt->info.sfc_mask & BIT(physical_vdbox / 2)) == 0)
 		return false;
-	else if (GRAPHICS_VER(i915) == 12)
+	else if (MEDIA_VER(i915) >= 12)
 		return (physical_vdbox % 2 == 0) ||
 			!(BIT(physical_vdbox - 1) & vdbox_mask);
-	else if (GRAPHICS_VER(i915) == 11)
+	else if (MEDIA_VER(i915) == 11)
 		return logical_vdbox % 2 == 0;
 
-	MISSING_CASE(GRAPHICS_VER(i915));
 	return false;
 }
 
+static void engine_mask_apply_media_fuses(struct intel_gt *gt)
+{
+	struct drm_i915_private *i915 = gt->i915;
+	unsigned int logical_vdbox = 0;
+	unsigned int i;
+	u32 media_fuse, fuse1;
+	u16 vdbox_mask;
+	u16 vebox_mask;
+
+	if (MEDIA_VER(gt->i915) < 11)
+		return;
+
+	/*
+	 * On newer platforms the fusing register is called 'enable' and has
+	 * enable semantics, while on older platforms it is called 'disable'
+	 * and bits have disable semantices.
+	 */
+	media_fuse = intel_uncore_read(gt->uncore, GEN11_GT_VEBOX_VDBOX_DISABLE);
+	if (MEDIA_VER_FULL(i915) < IP_VER(12, 50))
+		media_fuse = ~media_fuse;
+
+	vdbox_mask = media_fuse & GEN11_GT_VDBOX_DISABLE_MASK;
+	vebox_mask = (media_fuse & GEN11_GT_VEBOX_DISABLE_MASK) >>
+		      GEN11_GT_VEBOX_DISABLE_SHIFT;
+
+	if (MEDIA_VER_FULL(i915) >= IP_VER(12, 50)) {
+		fuse1 = intel_uncore_read(gt->uncore, HSW_PAVP_FUSE1);
+		gt->info.sfc_mask = REG_FIELD_GET(XEHP_SFC_ENABLE_MASK, fuse1);
+	} else {
+		gt->info.sfc_mask = ~0;
+	}
+
+	for (i = 0; i < I915_MAX_VCS; i++) {
+		if (!HAS_ENGINE(gt, _VCS(i))) {
+			vdbox_mask &= ~BIT(i);
+			continue;
+		}
+
+		if (!(BIT(i) & vdbox_mask)) {
+			gt->info.engine_mask &= ~BIT(_VCS(i));
+			drm_dbg(&i915->drm, "vcs%u fused off\n", i);
+			continue;
+		}
+
+		if (gen11_vdbox_has_sfc(gt, i, logical_vdbox, vdbox_mask))
+			gt->info.vdbox_sfc_access |= BIT(i);
+		logical_vdbox++;
+	}
+	drm_dbg(&i915->drm, "vdbox enable: %04x, instances: %04lx\n",
+		vdbox_mask, VDBOX_MASK(gt));
+	GEM_BUG_ON(vdbox_mask != VDBOX_MASK(gt));
+
+	for (i = 0; i < I915_MAX_VECS; i++) {
+		if (!HAS_ENGINE(gt, _VECS(i))) {
+			vebox_mask &= ~BIT(i);
+			continue;
+		}
+
+		if (!(BIT(i) & vebox_mask)) {
+			gt->info.engine_mask &= ~BIT(_VECS(i));
+			drm_dbg(&i915->drm, "vecs%u fused off\n", i);
+		}
+	}
+	drm_dbg(&i915->drm, "vebox enable: %04x, instances: %04lx\n",
+		vebox_mask, VEBOX_MASK(gt));
+	GEM_BUG_ON(vebox_mask != VEBOX_MASK(gt));
+}
+
 static void engine_mask_apply_compute_fuses(struct intel_gt *gt)
 {
 	struct drm_i915_private *i915 = gt->i915;
@@ -674,7 +815,10 @@ static void engine_mask_apply_compute_fuses(struct intel_gt *gt)
 	unsigned long ccs_mask;
 	unsigned int i;
 
-	if (GRAPHICS_VER_FULL(i915) < IP_VER(12, 50))
+	if (GRAPHICS_VER(i915) < 11)
+		return;
+
+	if (hweight32(CCS_MASK(gt)) <= 1)
 		return;
 
 	ccs_mask = intel_slicemask_from_xehp_dssmask(info->sseu.compute_subslice_mask,
@@ -696,6 +840,10 @@ static void engine_mask_apply_copy_fuses(struct intel_gt *gt)
 	unsigned long meml3_mask;
 	unsigned long quad;
 
+	if (!(GRAPHICS_VER_FULL(i915) >= IP_VER(12, 60) &&
+	      GRAPHICS_VER_FULL(i915) < IP_VER(12, 70)))
+		return;
+
 	meml3_mask = intel_uncore_read(gt->uncore, GEN10_MIRROR_FUSE3);
 	meml3_mask = REG_FIELD_GET(GEN12_MEML3_EN_MASK, meml3_mask);
 
@@ -729,75 +877,11 @@ static void engine_mask_apply_copy_fuses(struct intel_gt *gt)
  */
 static intel_engine_mask_t init_engine_mask(struct intel_gt *gt)
 {
-	struct drm_i915_private *i915 = gt->i915;
 	struct intel_gt_info *info = &gt->info;
-	struct intel_uncore *uncore = gt->uncore;
-	unsigned int logical_vdbox = 0;
-	unsigned int i;
-	u32 media_fuse, fuse1;
-	u16 vdbox_mask;
-	u16 vebox_mask;
-
-	info->engine_mask = RUNTIME_INFO(i915)->platform_engine_mask;
-
-	if (GRAPHICS_VER(i915) < 11)
-		return info->engine_mask;
-
-	/*
-	 * On newer platforms the fusing register is called 'enable' and has
-	 * enable semantics, while on older platforms it is called 'disable'
-	 * and bits have disable semantices.
-	 */
-	media_fuse = intel_uncore_read(uncore, GEN11_GT_VEBOX_VDBOX_DISABLE);
-	if (GRAPHICS_VER_FULL(i915) < IP_VER(12, 50))
-		media_fuse = ~media_fuse;
 
-	vdbox_mask = media_fuse & GEN11_GT_VDBOX_DISABLE_MASK;
-	vebox_mask = (media_fuse & GEN11_GT_VEBOX_DISABLE_MASK) >>
-		      GEN11_GT_VEBOX_DISABLE_SHIFT;
-
-	if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
-		fuse1 = intel_uncore_read(uncore, HSW_PAVP_FUSE1);
-		gt->info.sfc_mask = REG_FIELD_GET(XEHP_SFC_ENABLE_MASK, fuse1);
-	} else {
-		gt->info.sfc_mask = ~0;
-	}
-
-	for (i = 0; i < I915_MAX_VCS; i++) {
-		if (!HAS_ENGINE(gt, _VCS(i))) {
-			vdbox_mask &= ~BIT(i);
-			continue;
-		}
-
-		if (!(BIT(i) & vdbox_mask)) {
-			info->engine_mask &= ~BIT(_VCS(i));
-			drm_dbg(&i915->drm, "vcs%u fused off\n", i);
-			continue;
-		}
-
-		if (gen11_vdbox_has_sfc(gt, i, logical_vdbox, vdbox_mask))
-			gt->info.vdbox_sfc_access |= BIT(i);
-		logical_vdbox++;
-	}
-	drm_dbg(&i915->drm, "vdbox enable: %04x, instances: %04lx\n",
-		vdbox_mask, VDBOX_MASK(gt));
-	GEM_BUG_ON(vdbox_mask != VDBOX_MASK(gt));
-
-	for (i = 0; i < I915_MAX_VECS; i++) {
-		if (!HAS_ENGINE(gt, _VECS(i))) {
-			vebox_mask &= ~BIT(i);
-			continue;
-		}
-
-		if (!(BIT(i) & vebox_mask)) {
-			info->engine_mask &= ~BIT(_VECS(i));
-			drm_dbg(&i915->drm, "vecs%u fused off\n", i);
-		}
-	}
-	drm_dbg(&i915->drm, "vebox enable: %04x, instances: %04lx\n",
-		vebox_mask, VEBOX_MASK(gt));
-	GEM_BUG_ON(vebox_mask != VEBOX_MASK(gt));
+	GEM_BUG_ON(!info->engine_mask);
 
+	engine_mask_apply_media_fuses(gt);
 	engine_mask_apply_compute_fuses(gt);
 	engine_mask_apply_copy_fuses(gt);
 
@@ -1266,8 +1350,13 @@ int intel_engines_init(struct intel_gt *gt)
 			return err;
 
 		err = setup(engine);
-		if (err)
+		if (err) {
+			intel_engine_cleanup_common(engine);
 			return err;
+		}
+
+		/* The backend should now be responsible for cleanup */
+		GEM_BUG_ON(engine->release == NULL);
 
 		err = engine_init_common(engine);
 		if (err)
@@ -1546,11 +1635,11 @@ void intel_engine_get_instdone(const struct intel_engine_cs *engine,
 		for_each_ss_steering(iter, engine->gt, slice, subslice) {
 			instdone->sampler[slice][subslice] =
 				intel_gt_mcr_read(engine->gt,
-						  GEN7_SAMPLER_INSTDONE,
+						  GEN8_SAMPLER_INSTDONE,
 						  slice, subslice);
 			instdone->row[slice][subslice] =
 				intel_gt_mcr_read(engine->gt,
-						  GEN7_ROW_INSTDONE,
+						  GEN8_ROW_INSTDONE,
 						  slice, subslice);
 		}
 
@@ -1690,9 +1779,9 @@ bool intel_engine_irq_enable(struct intel_engine_cs *engine)
 		return false;
 
 	/* Caller disables interrupts */
-	spin_lock(&engine->gt->irq_lock);
+	spin_lock(engine->gt->irq_lock);
 	engine->irq_enable(engine);
-	spin_unlock(&engine->gt->irq_lock);
+	spin_unlock(engine->gt->irq_lock);
 
 	return true;
 }
@@ -1703,9 +1792,9 @@ void intel_engine_irq_disable(struct intel_engine_cs *engine)
 		return;
 
 	/* Caller disables interrupts */
-	spin_lock(&engine->gt->irq_lock);
+	spin_lock(engine->gt->irq_lock);
 	engine->irq_disable(engine);
-	spin_unlock(&engine->gt->irq_lock);
+	spin_unlock(engine->gt->irq_lock);
 }
 
 void intel_engines_reset_default_submission(struct intel_gt *gt)