drm/i915/gt: Automate CCS Mode setting during engine resets

We missed setting the CCS mode during resume and engine resets.
Create a workaround to be added in the engine's workaround list.
This workaround sets the XEHP_CCS_MODE value at every reset.

The issue can be reproduced by running:

  $ clpeak --kernel-latency

Without resetting the CCS mode, we encounter a fence timeout:

  Fence expiration time out i915-0000:03:00.0:clpeak[2387]:2!

Fixes: 2bebae01 ("drm/i915/gt: Enable only one CCS for compute workload")
Reported-by: Gnattu OC <gnattuoc@me.com>
Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/10895Signed-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+
Tested-by: Gnattu OC <gnattuoc@me.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Tested-by: Krzysztof Gibala <krzysztof.gibala@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240426000723.229296-1-andi.shyti@linux.intel.com

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

@@ -8,14 +8,14 @@
 #include "intel_gt_ccs_mode.h"
 #include "intel_gt_regs.h"
 
-void intel_gt_apply_ccs_mode(struct intel_gt *gt)
+unsigned int intel_gt_apply_ccs_mode(struct intel_gt *gt)
 {
 	int cslice;
 	u32 mode = 0;
 	int first_ccs = __ffs(CCS_MASK(gt));
 
 	if (!IS_DG2(gt->i915))
-		return;
+		return 0;
 
 	/* Build the value for the fixed CCS load balancing */
 	for (cslice = 0; cslice < I915_MAX_CCS; cslice++) {
@@ -35,5 +35,5 @@ void intel_gt_apply_ccs_mode(struct intel_gt *gt)
 						     XEHP_CCS_MODE_CSLICE_MASK);
 	}
 
-	intel_uncore_write(gt->uncore, XEHP_CCS_MODE, mode);
+	return mode;
 }

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

@@ -8,6 +8,6 @@
 
 struct intel_gt;
 
-void intel_gt_apply_ccs_mode(struct intel_gt *gt);
+unsigned int intel_gt_apply_ccs_mode(struct intel_gt *gt);
 
 #endif /* __INTEL_GT_CCS_MODE_H__ */

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

@@ -2858,6 +2858,7 @@ add_render_compute_tuning_settings(struct intel_gt *gt,
 static void ccs_engine_wa_mode(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 {
 	struct intel_gt *gt = engine->gt;
+	u32 mode;
 
 	if (!IS_DG2(gt->i915))
 		return;
@@ -2874,7 +2875,8 @@ static void ccs_engine_wa_mode(struct intel_engine_cs *engine, struct i915_wa_li
 	 * After having disabled automatic load balancing we need to
 	 * assign all slices to a single CCS. We will call it CCS mode 1
 	 */
-	intel_gt_apply_ccs_mode(gt);
+	mode = intel_gt_apply_ccs_mode(gt);
+	wa_masked_en(wal, XEHP_CCS_MODE, mode);
 }
 
 /*