drm/i915/gt: Disable HW load balancing for CCS

The hardware should not dynamically balance the load between CCS
engines. Wa_14019159160 recommends disabling it across all
platforms.

Fixes: d2eae8e9 ("drm/i915/dg2: Drop force_probe requirement")
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Cc: Chris Wilson <chris.p.wilson@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: <stable@vger.kernel.org> # v6.2+
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Acked-by: Michal Mrozek <michal.mrozek@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240328073409.674098-2-andi.shyti@linux.intel.com

drivers/gpu/drm/i915/gt/intel_gt_regs.h

@@ -1478,6 +1478,7 @@
 #define   ECOBITS_PPGTT_CACHE4B			(0 << 8)
 
 #define GEN12_RCU_MODE				_MMIO(0x14800)
+#define   XEHP_RCU_MODE_FIXED_SLICE_CCS_MODE	REG_BIT(1)
 #define   GEN12_RCU_MODE_CCS_ENABLE		REG_BIT(0)
 
 #define CHV_FUSE_GT				_MMIO(VLV_GUNIT_BASE + 0x2168)

drivers/gpu/drm/i915/gt/intel_workarounds.c

@@ -51,7 +51,8 @@
  *   registers belonging to BCS, VCS or VECS should be implemented in
  *   xcs_engine_wa_init(). Workarounds for registers not belonging to a specific
  *   engine's MMIO range but that are part of of the common RCS/CCS reset domain
- *   should be implemented in general_render_compute_wa_init().
+ *   should be implemented in general_render_compute_wa_init(). The settings
+ *   about the CCS load balancing should be added in ccs_engine_wa_mode().
  *
  * - GT workarounds: the list of these WAs is applied whenever these registers
  *   revert to their default values: on GPU reset, suspend/resume [1]_, etc.
@@ -2853,6 +2854,22 @@ add_render_compute_tuning_settings(struct intel_gt *gt,
 		wa_write_clr(wal, GEN8_GARBCNTL, GEN12_BUS_HASH_CTL_BIT_EXC);
 }
 
+static void ccs_engine_wa_mode(struct intel_engine_cs *engine, struct i915_wa_list *wal)
+{
+	struct intel_gt *gt = engine->gt;
+
+	if (!IS_DG2(gt->i915))
+		return;
+
+	/*
+	 * Wa_14019159160: This workaround, along with others, leads to
+	 * significant challenges in utilizing load balancing among the
+	 * CCS slices. Consequently, an architectural decision has been
+	 * made to completely disable automatic CCS load balancing.
+	 */
+	wa_masked_en(wal, GEN12_RCU_MODE, XEHP_RCU_MODE_FIXED_SLICE_CCS_MODE);
+}
+
 /*
  * The workarounds in this function apply to shared registers in
  * the general render reset domain that aren't tied to a
@@ -3003,8 +3020,10 @@ engine_init_workarounds(struct intel_engine_cs *engine, struct i915_wa_list *wal
 	 * to a single RCS/CCS engine's workaround list since
 	 * they're reset as part of the general render domain reset.
 	 */
-	if (engine->flags & I915_ENGINE_FIRST_RENDER_COMPUTE)
+	if (engine->flags & I915_ENGINE_FIRST_RENDER_COMPUTE) {
 		general_render_compute_wa_init(engine, wal);
+		ccs_engine_wa_mode(engine, wal);
+	}
 
 	if (engine->class == COMPUTE_CLASS)
 		ccs_engine_wa_init(engine, wal);