drm/i915: Init some CHV workarounds via LRIs in ring->init_context()

Follow the BDW example and apply the workarounds touching registers
which are saved in the context image through LRIs in the new
ring->init_context() hook.

This makes Mesa much happier and eg. glxgears doesn't hang after
the first frame.

Cc: Arun Siluvery <arun.siluvery@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
[danvet: Add missing wa table initialization to avoid a functional
conflict with Arun's wa table debugfs support.]
Reviewed-by: "Barbalho, Rafael" <rafael.barbalho@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/intel_pm.c

@@ -6011,14 +6011,6 @@ static void cherryview_init_clock_gating(struct drm_device *dev)
 
 	I915_WRITE(MI_ARB_VLV, MI_ARB_DISPLAY_TRICKLE_FEED_DISABLE);
 
-	/* WaDisablePartialInstShootdown:chv */
-	I915_WRITE(GEN8_ROW_CHICKEN,
-		   _MASKED_BIT_ENABLE(PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE));
-
-	/* WaDisableThreadStallDopClockGating:chv */
-	I915_WRITE(GEN8_ROW_CHICKEN,
-		   _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE));
-
 	/* WaVSRefCountFullforceMissDisable:chv */
 	/* WaDSRefCountFullforceMissDisable:chv */
 	I915_WRITE(GEN7_FF_THREAD_MODE,
@@ -6037,10 +6029,6 @@ static void cherryview_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
 		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
 
-	/* WaDisableSamplerPowerBypass:chv (pre-production hw) */
-	I915_WRITE(HALF_SLICE_CHICKEN3,
-		   _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
-
 	/* WaDisableGunitClockGating:chv (pre-production hw) */
 	I915_WRITE(VLV_GUNIT_CLOCK_GATE, I915_READ(VLV_GUNIT_CLOCK_GATE) |
 		   GINT_DIS);
@@ -6050,8 +6038,6 @@ static void cherryview_init_clock_gating(struct drm_device *dev)
 		   _MASKED_BIT_ENABLE(GEN8_FF_DOP_CLOCK_GATE_DISABLE));
 
 	/* WaDisableDopClockGating:chv (pre-production hw) */
-	I915_WRITE(GEN7_ROW_CHICKEN2,
-		   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
 	I915_WRITE(GEN6_UCGCTL1, I915_READ(GEN6_UCGCTL1) |
 		   GEN6_EU_TCUNIT_CLOCK_GATE_DISABLE);
 }

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -681,7 +681,7 @@ static inline void intel_ring_emit_wa(struct intel_engine_cs *ring,
 	return;
 }
 
-static int gen8_init_workarounds(struct intel_engine_cs *ring)
+static int bdw_init_workarounds(struct intel_engine_cs *ring)
 {
 	int ret;
 	struct drm_device *dev = ring->dev;
@@ -758,6 +758,45 @@ static int gen8_init_workarounds(struct intel_engine_cs *ring)
 	return 0;
 }
 
+static int chv_init_workarounds(struct intel_engine_cs *ring)
+{
+	int ret;
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+
+	/*
+	 * workarounds applied in this fn are part of register state context,
+	 * they need to be re-initialized followed by gpu reset, suspend/resume,
+	 * module reload.
+	 */
+	dev_priv->num_wa_regs = 0;
+	memset(dev_priv->intel_wa_regs, 0, sizeof(dev_priv->intel_wa_regs));
+
+	ret = intel_ring_begin(ring, 12);
+	if (ret)
+		return ret;
+
+	/* WaDisablePartialInstShootdown:chv */
+	intel_ring_emit_wa(ring, GEN8_ROW_CHICKEN,
+			   _MASKED_BIT_ENABLE(PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE));
+
+	/* WaDisableThreadStallDopClockGating:chv */
+	intel_ring_emit_wa(ring, GEN8_ROW_CHICKEN,
+			   _MASKED_BIT_ENABLE(STALL_DOP_GATING_DISABLE));
+
+	/* WaDisableDopClockGating:chv (pre-production hw) */
+	intel_ring_emit_wa(ring, GEN7_ROW_CHICKEN2,
+			   _MASKED_BIT_ENABLE(DOP_CLOCK_GATING_DISABLE));
+
+	/* WaDisableSamplerPowerBypass:chv (pre-production hw) */
+	intel_ring_emit_wa(ring, HALF_SLICE_CHICKEN3,
+			   _MASKED_BIT_ENABLE(GEN8_SAMPLER_POWER_BYPASS_DIS));
+
+	intel_ring_advance(ring);
+
+	return 0;
+}
+
 static int init_render_ring(struct intel_engine_cs *ring)
 {
 	struct drm_device *dev = ring->dev;
@@ -2244,7 +2283,10 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
 					dev_priv->semaphore_obj = obj;
 			}
 		}
-		ring->init_context = gen8_init_workarounds;
+		if (IS_CHERRYVIEW(dev))
+			ring->init_context = chv_init_workarounds;
+		else
+			ring->init_context = bdw_init_workarounds;
 		ring->add_request = gen6_add_request;
 		ring->flush = gen8_render_ring_flush;
 		ring->irq_get = gen8_ring_get_irq;