drm/i915/gt: Move snb GT workarounds from init_clock_gating to workarounds

Rescue the GT workarounds from being buried inside init_clock_gating so
that we remember to apply them after a GT reset, and that they are
included in our verification that the workarounds are applied.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://patchwork.freedesktop.org/patch/msgid/20200611080140.30228-4-chris@chris-wilson.co.uk
(cherry picked from commit c3b93a94)
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>

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

@@ -692,6 +692,45 @@ int intel_engine_emit_ctx_wa(struct i915_request *rq)
 	return 0;
 }
 
+static void
+snb_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
+{
+	/* WaDisableHiZPlanesWhenMSAAEnabled:snb */
+	wa_masked_en(wal,
+		     _3D_CHICKEN,
+		     _3D_CHICKEN_HIZ_PLANE_DISABLE_MSAA_4X_SNB);
+
+	/* WaDisable_RenderCache_OperationalFlush:snb */
+	wa_masked_dis(wal, CACHE_MODE_0, RC_OP_FLUSH_ENABLE);
+
+	/*
+	 * BSpec recommends 8x4 when MSAA is used,
+	 * however in practice 16x4 seems fastest.
+	 *
+	 * Note that PS/WM thread counts depend on the WIZ hashing
+	 * disable bit, which we don't touch here, but it's good
+	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
+	 */
+	wa_add(wal,
+	       GEN6_GT_MODE, 0,
+	       _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4),
+	       GEN6_WIZ_HASHING_16x4);
+
+	wa_masked_dis(wal, CACHE_MODE_0, CM0_STC_EVICT_DISABLE_LRA_SNB);
+
+	wa_masked_en(wal,
+		     _3D_CHICKEN3,
+		     /* WaStripsFansDisableFastClipPerformanceFix:snb */
+		     _3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL |
+		     /*
+		      * Bspec says:
+		      * "This bit must be set if 3DSTATE_CLIP clip mode is set
+		      * to normal and 3DSTATE_SF number of SF output attributes
+		      * is more than 16."
+		      */
+		   _3D_CHICKEN3_SF_DISABLE_PIPELINED_ATTR_FETCH);
+}
+
 static void
 ivb_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal)
 {
@@ -1132,6 +1171,8 @@ gt_init_workarounds(struct drm_i915_private *i915, struct i915_wa_list *wal)
 		vlv_gt_workarounds_init(i915, wal);
 	else if (IS_IVYBRIDGE(i915))
 		ivb_gt_workarounds_init(i915, wal);
+	else if (IS_GEN(i915, 6))
+		snb_gt_workarounds_init(i915, wal);
 	else if (INTEL_GEN(i915) <= 8)
 		return;
 	else

drivers/gpu/drm/i915/intel_pm.c

@@ -6902,27 +6902,6 @@ static void gen6_init_clock_gating(struct drm_i915_private *dev_priv)
 		   I915_READ(ILK_DISPLAY_CHICKEN2) |
 		   ILK_ELPIN_409_SELECT);
 
-	/* WaDisableHiZPlanesWhenMSAAEnabled:snb */
-	I915_WRITE(_3D_CHICKEN,
-		   _MASKED_BIT_ENABLE(_3D_CHICKEN_HIZ_PLANE_DISABLE_MSAA_4X_SNB));
-
-	/* WaDisable_RenderCache_OperationalFlush:snb */
-	I915_WRITE(CACHE_MODE_0, _MASKED_BIT_DISABLE(RC_OP_FLUSH_ENABLE));
-
-	/*
-	 * BSpec recoomends 8x4 when MSAA is used,
-	 * however in practice 16x4 seems fastest.
-	 *
-	 * Note that PS/WM thread counts depend on the WIZ hashing
-	 * disable bit, which we don't touch here, but it's good
-	 * to keep in mind (see 3DSTATE_PS and 3DSTATE_WM).
-	 */
-	I915_WRITE(GEN6_GT_MODE,
-		   _MASKED_FIELD(GEN6_WIZ_HASHING_MASK, GEN6_WIZ_HASHING_16x4));
-
-	I915_WRITE(CACHE_MODE_0,
-		   _MASKED_BIT_DISABLE(CM0_STC_EVICT_DISABLE_LRA_SNB));
-
 	I915_WRITE(GEN6_UCGCTL1,
 		   I915_READ(GEN6_UCGCTL1) |
 		   GEN6_BLBUNIT_CLOCK_GATE_DISABLE |
@@ -6945,18 +6924,6 @@ static void gen6_init_clock_gating(struct drm_i915_private *dev_priv)
 		   GEN6_RCPBUNIT_CLOCK_GATE_DISABLE |
 		   GEN6_RCCUNIT_CLOCK_GATE_DISABLE);
 
-	/* WaStripsFansDisableFastClipPerformanceFix:snb */
-	I915_WRITE(_3D_CHICKEN3,
-		   _MASKED_BIT_ENABLE(_3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL));
-
-	/*
-	 * Bspec says:
-	 * "This bit must be set if 3DSTATE_CLIP clip mode is set to normal and
-	 * 3DSTATE_SF number of SF output attributes is more than 16."
-	 */
-	I915_WRITE(_3D_CHICKEN3,
-		   _MASKED_BIT_ENABLE(_3D_CHICKEN3_SF_DISABLE_PIPELINED_ATTR_FETCH));
-
 	/*
 	 * According to the spec the following bits should be
 	 * set in order to enable memory self-refresh and fbc: