drm/i915: Make GT workaround upper bounds exclusive

Workarounds are documented in the bspec with an exclusive upper bound
(i.e., a "fixed" stepping that no longer needs the workaround).  This
makes our driver's use of an inclusive upper bound for stepping ranges
confusing; the differing notation between code and bspec makes it very
easy for mistakes to creep in.

Let's switch the upper bound of our IS_{GT,DISP}_STEP macros over to use
an exclusive upper bound like the bspec does.  This also has the benefit
of helping make sure workarounds are properly handled for new minor
steppings that show up (e.g., an A1 between the A0 and B0 we already
knew about) --- if the new intermediate stepping pulls in hardware fixes
early, there will be an update to the workaround definition which lets
us know we need to change our code.  If the new stepping does not pull a
hardware fix earlier, then the new stepping will already be captured
properly by the "[begin, fix)" range in the code.

We'll probably need to be extra vigilant in code review of new
workarounds for the near future to make sure developers notice the new
semantics of workaround bounds.  But we just migrated a bunch of our
platforms from the IS_REVID bounds over to IS_{GT,DISP}_STEP, so people
are already adjusting to the new macros and now is a good time to make
this change too.

[mattrope: Split out GT changes to apply through gt-next tree]
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210717051426.4120328-8-matthew.d.roper@intel.com

drivers/gpu/drm/i915/gt/gen8_engine_cs.c

@@ -42,7 +42,7 @@ int gen8_emit_flush_rcs(struct i915_request *rq, u32 mode)
 			vf_flush_wa = true;
 
 		/* WaForGAMHang:kbl */
-		if (IS_KBL_GT_STEP(rq->engine->i915, 0, STEP_B0))
+		if (IS_KBL_GT_STEP(rq->engine->i915, 0, STEP_C0))
 			dc_flush_wa = true;
 	}
 

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

@@ -157,7 +157,7 @@ intel_gt_setup_fake_lmem(struct intel_gt *gt)
 static bool get_legacy_lowmem_region(struct intel_uncore *uncore,
 				     u64 *start, u32 *size)
 {
-	if (!IS_DG1_GT_STEP(uncore->i915, STEP_A0, STEP_B0))
+	if (!IS_DG1_GT_STEP(uncore->i915, STEP_A0, STEP_C0))
 		return false;
 
 	*start = 0;

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

@@ -838,7 +838,7 @@ skl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 		    GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE);
 
 	/* WaInPlaceDecompressionHang:skl */
-	if (IS_SKL_GT_STEP(i915, STEP_A0, STEP_H0 - 1))
+	if (IS_SKL_GT_STEP(i915, STEP_A0, STEP_H0))
 		wa_write_or(wal,
 			    GEN9_GAMT_ECO_REG_RW_IA,
 			    GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
@@ -850,7 +850,7 @@ kbl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 	gen9_gt_workarounds_init(i915, wal);
 
 	/* WaDisableDynamicCreditSharing:kbl */
-	if (IS_KBL_GT_STEP(i915, 0, STEP_B0))
+	if (IS_KBL_GT_STEP(i915, 0, STEP_C0))
 		wa_write_or(wal,
 			    GAMT_CHKN_BIT_REG,
 			    GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING);
@@ -961,7 +961,7 @@ icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 
 	/* Wa_1607087056:icl,ehl,jsl */
 	if (IS_ICELAKE(i915) ||
-	    IS_JSL_EHL_GT_STEP(i915, STEP_A0, STEP_A0))
+	    IS_JSL_EHL_GT_STEP(i915, STEP_A0, STEP_B0))
 		wa_write_or(wal,
 			    SLICE_UNIT_LEVEL_CLKGATE,
 			    L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS);
@@ -1015,19 +1015,19 @@ tgl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 	gen12_gt_workarounds_init(i915, wal);
 
 	/* Wa_1409420604:tgl */
-	if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_A0))
+	if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_B0))
 		wa_write_or(wal,
 			    SUBSLICE_UNIT_LEVEL_CLKGATE2,
 			    CPSSUNIT_CLKGATE_DIS);
 
 	/* Wa_1607087056:tgl also know as BUG:1409180338 */
-	if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_A0))
+	if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_B0))
 		wa_write_or(wal,
 			    SLICE_UNIT_LEVEL_CLKGATE,
 			    L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS);
 
 	/* Wa_1408615072:tgl[a0] */
-	if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_A0))
+	if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_B0))
 		wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2,
 			    VSUNIT_CLKGATE_DIS_TGL);
 }
@@ -1038,7 +1038,7 @@ dg1_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 	gen12_gt_workarounds_init(i915, wal);
 
 	/* Wa_1607087056:dg1 */
-	if (IS_DG1_GT_STEP(i915, STEP_A0, STEP_A0))
+	if (IS_DG1_GT_STEP(i915, STEP_A0, STEP_B0))
 		wa_write_or(wal,
 			    SLICE_UNIT_LEVEL_CLKGATE,
 			    L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS);
@@ -1436,7 +1436,7 @@ static void dg1_whitelist_build(struct intel_engine_cs *engine)
 	tgl_whitelist_build(engine);
 
 	/* GEN:BUG:1409280441:dg1 */
-	if (IS_DG1_GT_STEP(engine->i915, STEP_A0, STEP_A0) &&
+	if (IS_DG1_GT_STEP(engine->i915, STEP_A0, STEP_B0) &&
 	    (engine->class == RENDER_CLASS ||
 	     engine->class == COPY_ENGINE_CLASS))
 		whitelist_reg_ext(w, RING_ID(engine->mmio_base),
@@ -1504,8 +1504,8 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 {
 	struct drm_i915_private *i915 = engine->i915;
 
-	if (IS_DG1_GT_STEP(i915, STEP_A0, STEP_A0) ||
-	    IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_A0)) {
+	if (IS_DG1_GT_STEP(i915, STEP_A0, STEP_B0) ||
+	    IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_B0)) {
 		/*
 		 * Wa_1607138336:tgl[a0],dg1[a0]
 		 * Wa_1607063988:tgl[a0],dg1[a0]
@@ -1515,7 +1515,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 			    GEN12_DISABLE_POSH_BUSY_FF_DOP_CG);
 	}
 
-	if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_A0)) {
+	if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_B0)) {
 		/*
 		 * Wa_1606679103:tgl
 		 * (see also Wa_1606682166:icl)
@@ -1550,7 +1550,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 	}
 
 	if (IS_ALDERLAKE_P(i915) || IS_ALDERLAKE_S(i915) ||
-	    IS_DG1_GT_STEP(i915, STEP_A0, STEP_A0) ||
+	    IS_DG1_GT_STEP(i915, STEP_A0, STEP_B0) ||
 	    IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) {
 		/* Wa_1409804808:tgl,rkl,dg1[a0],adl-s,adl-p */
 		wa_masked_en(wal, GEN7_ROW_CHICKEN2,
@@ -1564,7 +1564,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 	}
 
 
-	if (IS_DG1_GT_STEP(i915, STEP_A0, STEP_A0) ||
+	if (IS_DG1_GT_STEP(i915, STEP_A0, STEP_B0) ||
 	    IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) {
 		/*
 		 * Wa_1607030317:tgl
@@ -1925,7 +1925,7 @@ xcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 	struct drm_i915_private *i915 = engine->i915;
 
 	/* WaKBLVECSSemaphoreWaitPoll:kbl */
-	if (IS_KBL_GT_STEP(i915, STEP_A0, STEP_E0)) {
+	if (IS_KBL_GT_STEP(i915, STEP_A0, STEP_F0)) {
 		wa_write(wal,
 			 RING_SEMA_WAIT_POLL(engine->mmio_base),
 			 1);

drivers/gpu/drm/i915/i915_drv.h

@@ -1339,7 +1339,7 @@ static inline struct drm_i915_private *pdev_to_i915(struct pci_dev *pdev)
 
 #define IS_GT_STEP(__i915, since, until) \
 	(drm_WARN_ON(&(__i915)->drm, INTEL_GT_STEP(__i915) == STEP_NONE), \
-	 INTEL_GT_STEP(__i915) >= (since) && INTEL_GT_STEP(__i915) <= (until))
+	 INTEL_GT_STEP(__i915) >= (since) && INTEL_GT_STEP(__i915) < (until))
 
 static __always_inline unsigned int
 __platform_mask_index(const struct intel_runtime_info *info,

drivers/gpu/drm/i915/intel_pm.c

@@ -7377,7 +7377,7 @@ static void dg1_init_clock_gating(struct drm_i915_private *dev_priv)
 	gen12lp_init_clock_gating(dev_priv);
 
 	/* Wa_1409836686:dg1[a0] */
-	if (IS_DG1_GT_STEP(dev_priv, STEP_A0, STEP_A0))
+	if (IS_DG1_GT_STEP(dev_priv, STEP_A0, STEP_B0))
 		intel_uncore_write(&dev_priv->uncore, GEN9_CLKGATE_DIS_3, intel_uncore_read(&dev_priv->uncore, GEN9_CLKGATE_DIS_3) |
 			   DPT_GATING_DIS);
 }
@@ -7462,12 +7462,12 @@ static void kbl_init_clock_gating(struct drm_i915_private *dev_priv)
 		   FBC_LLC_FULLY_OPEN);
 
 	/* WaDisableSDEUnitClockGating:kbl */
-	if (IS_KBL_GT_STEP(dev_priv, 0, STEP_B0))
+	if (IS_KBL_GT_STEP(dev_priv, 0, STEP_C0))
 		intel_uncore_write(&dev_priv->uncore, GEN8_UCGCTL6, intel_uncore_read(&dev_priv->uncore, GEN8_UCGCTL6) |
 			   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
 
 	/* WaDisableGamClockGating:kbl */
-	if (IS_KBL_GT_STEP(dev_priv, 0, STEP_B0))
+	if (IS_KBL_GT_STEP(dev_priv, 0, STEP_C0))
 		intel_uncore_write(&dev_priv->uncore, GEN6_UCGCTL1, intel_uncore_read(&dev_priv->uncore, GEN6_UCGCTL1) |
 			   GEN6_GAMUNIT_CLOCK_GATE_DISABLE);