[PATCH v3 4/4] drm/i915/gt: Enable only one CCS for compute workload

[Andi Shyti <andi.shyti@xxxxxxxxxxxxxxx>]

Enable only one CCS engine by default with all the compute sices
allocated to it.

While generating the list of UABI engines to be exposed to the
user, exclude any additional CCS engines beyond the first
instance.

This change can be tested with igt i915_query.

Fixes: d2eae8e98d59 ("drm/i915/dg2: Drop force_probe requirement")
Requires: 4e4f77d74878 ("drm/i915/gt: Refactor uabi engine class/instance list creation")
Signed-off-by: Andi Shyti <andi.shyti@xxxxxxxxxxxxxxx>
Cc: Chris Wilson <chris.p.wilson@xxxxxxxxxxxxxxx>
Cc: Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx>
Cc: Matt Roper <matthew.d.roper@xxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx> # v6.2+
---
 drivers/gpu/drm/i915/gt/intel_engine_user.c | 11 +++++++++++
 drivers/gpu/drm/i915/gt/intel_gt.c          | 11 +++++++++++
 drivers/gpu/drm/i915/gt/intel_gt_regs.h     |  2 ++
 3 files changed, 24 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c
index ec5bcd1c1ec4..6d6ef11f55e5 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_user.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c
@@ -208,6 +208,7 @@ void intel_engines_driver_register(struct drm_i915_private *i915)
 	struct list_head *it, *next;
 	struct rb_node **p, *prev;
 	LIST_HEAD(engines);
+	u16 uabi_ccs = 0;
 
 	sort_engines(i915, &engines);
 
@@ -256,6 +257,16 @@ void intel_engines_driver_register(struct drm_i915_private *i915)
 		      BIT(_CCS(engine->uabi_instance))))
 			continue;
 
+		/*
+		 * The load is balanced among all the available compute
+		 * slices. Expose only the first instance of the compute
+		 * engine.
+		 */
+		if (IS_DG2(i915) &&
+		    uabi_class == I915_ENGINE_CLASS_COMPUTE &&
+		    uabi_ccs++)
+			continue;
+
 		GEM_BUG_ON(uabi_class >=
 			   ARRAY_SIZE(i915->engine_uabi_class_count));
 		i915->engine_uabi_class_count[uabi_class]++;
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index a425db5ed3a2..e19df4ef47f6 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -168,6 +168,14 @@ static void init_unused_rings(struct intel_gt *gt)
 	}
 }
 
+static void intel_gt_apply_ccs_mode(struct intel_gt *gt)
+{
+	if (!IS_DG2(gt->i915))
+		return;
+
+	intel_uncore_write(gt->uncore, XEHP_CCS_MODE, 0);
+}
+
 int intel_gt_init_hw(struct intel_gt *gt)
 {
 	struct drm_i915_private *i915 = gt->i915;
@@ -195,6 +203,9 @@ int intel_gt_init_hw(struct intel_gt *gt)
 
 	intel_gt_init_swizzling(gt);
 
+	/* Configure CCS mode */
+	intel_gt_apply_ccs_mode(gt);
+
 	/*
 	 * At least 830 can leave some of the unused rings
 	 * "active" (ie. head != tail) after resume which
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index cf709f6c05ae..c148113770ea 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -1605,6 +1605,8 @@
 #define   GEN12_VOLTAGE_MASK			REG_GENMASK(10, 0)
 #define   GEN12_CAGF_MASK			REG_GENMASK(19, 11)
 
+#define XEHP_CCS_MODE                          _MMIO(0x14804)
+
 #define GEN11_GT_INTR_DW(x)			_MMIO(0x190018 + ((x) * 4))
 #define   GEN11_CSME				(31)
 #define   GEN12_HECI_2				(30)
-- 
2.43.0