drm/i915/dg2: Add additional tuning settings

Some additional MMIO tuning settings have appeared in the bspec's
performance tuning guide section.

One of the tuning settings here is also documented as formal workaround
Wa_22012654132 for some steppings of DG2.  However the tuning setting
applies to all DG2 variants and steppings, making it a superset of the
workaround.

v2:
 - Move DRAW_WATERMARK to engine workaround section.  It only moves into
   the engine context on future platforms.  (Lucas)
 - CHICKEN_RASTER_2 needs to be handled as a masked register.  (Lucas)

Bspec: 68331
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220816210601.2041572-2-matthew.d.roper@intel.com

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

@@ -259,6 +259,9 @@
 #define   GEN9_PREEMPT_GPGPU_COMMAND_LEVEL	GEN9_PREEMPT_GPGPU_LEVEL(1, 0)
 #define   GEN9_PREEMPT_GPGPU_LEVEL_MASK		GEN9_PREEMPT_GPGPU_LEVEL(1, 1)
 
+#define DRAW_WATERMARK				_MMIO(0x26c0)
+#define   VERT_WM_VAL				REG_GENMASK(9, 0)
+
 #define GEN12_GLOBAL_MOCS(i)			_MMIO(0x4000 + (i) * 4) /* Global MOCS regs */
 
 #define RENDER_HWS_PGA_GEN7			_MMIO(0x4080)
@@ -374,6 +377,9 @@
 #define CHICKEN_RASTER_1			_MMIO(0x6204)
 #define   DIS_SF_ROUND_NEAREST_EVEN		REG_BIT(8)
 
+#define CHICKEN_RASTER_2			_MMIO(0x6208)
+#define   TBIMR_FAST_CLIP			REG_BIT(5)
+
 #define VFLSKPD					_MMIO(0x62a8)
 #define   DIS_OVER_FETCH_CACHE			REG_BIT(1)
 #define   DIS_MULT_MISS_RD_SQUASH		REG_BIT(0)
@@ -1124,6 +1130,8 @@
 
 #define RT_CTRL					_MMIO(0xe530)
 #define   DIS_NULL_QUERY			REG_BIT(10)
+#define   STACKID_CTRL				REG_GENMASK(6, 5)
+#define   STACKID_CTRL_512			REG_FIELD_PREP(STACKID_CTRL, 0x2)
 
 #define EU_PERF_CNTL1				_MMIO(0xe558)
 #define EU_PERF_CNTL5				_MMIO(0xe55c)

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

@@ -568,6 +568,7 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine,
 static void dg2_ctx_gt_tuning_init(struct intel_engine_cs *engine,
 				   struct i915_wa_list *wal)
 {
+	wa_masked_en(wal, CHICKEN_RASTER_2, TBIMR_FAST_CLIP);
 	wa_write_clr_set(wal, GEN11_L3SQCREG5, L3_PWM_TIMER_INIT_VAL_MASK,
 			 REG_FIELD_PREP(L3_PWM_TIMER_INIT_VAL_MASK, 0x7f));
 	wa_add(wal,
@@ -2195,15 +2196,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		wa_write_or(wal, XEHP_L3NODEARBCFG, XEHP_LNESPARE);
 	}
 
-	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_C0) ||
-	    IS_DG2_G11(i915)) {
-		/* Wa_22012654132:dg2 */
-		wa_add(wal, GEN10_CACHE_MODE_SS, 0,
-		       _MASKED_BIT_ENABLE(ENABLE_PREFETCH_INTO_IC),
-		       0 /* write-only, so skip validation */,
-		       true);
-	}
-
 	/* Wa_14013202645:dg2 */
 	if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) ||
 	    IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0))
@@ -2692,6 +2684,23 @@ add_render_compute_tuning_settings(struct drm_i915_private *i915,
 
 	if (IS_DG2(i915)) {
 		wa_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS);
+		wa_write_clr_set(wal, RT_CTRL, STACKID_CTRL, STACKID_CTRL_512);
+		wa_write_clr_set(wal, DRAW_WATERMARK, VERT_WM_VAL,
+				 REG_FIELD_PREP(VERT_WM_VAL, 0x3FF));
+
+		/*
+		 * This is also listed as Wa_22012654132 for certain DG2
+		 * steppings, but the tuning setting programming is a superset
+		 * since it applies to all DG2 variants and steppings.
+		 *
+		 * Note that register 0xE420 is write-only and cannot be read
+		 * back for verification on DG2 (due to Wa_14012342262), so
+		 * we need to explicitly skip the readback.
+		 */
+		wa_add(wal, GEN10_CACHE_MODE_SS, 0,
+		       _MASKED_BIT_ENABLE(ENABLE_PREFETCH_INTO_IC),
+		       0 /* write-only, so skip validation */,
+		       true);
 	}
 }