drm/i915/chv: Tune L3 SQC credits based on actual latencies

While browsing BSpec I bumped into a note saying we need to tune these
values based on actual measurements done after initial enabling. I've
checked that it indeed improves things on BXT. I haven't checked this on
CHV, but here it is if someone wants to give it a go.

v2:
- Add note about the discrepancy wrt. to the spec in the formula
  calculating the credit encodings. (Mika, Ville)
- Move the WA comment to the new function. (Ville)
v3:
- Keep the comment about the SQC WA in the caller. (Ville)

CC: Ville Syrjälä <ville.syrjala@linux.intel.com>
CC: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1462280061-1457-4-git-send-email-imre.deak@intel.com

drivers/gpu/drm/i915/i915_reg.h

@@ -6091,6 +6091,12 @@ enum skl_disp_power_wells {
 #define  VLV_B0_WA_L3SQCREG1_VALUE		0x00D30000
 
 #define GEN8_L3SQCREG1				_MMIO(0xB100)
+/*
+ * Note that on CHV the following has an off-by-one error wrt. to BSpec.
+ * Using the formula in BSpec leads to a hang, while the formula here works
+ * fine and matches the formulas for all other platforms. A BSpec change
+ * request has been filed to clarify this.
+ */
 #define  L3_GENERAL_PRIO_CREDITS(x)		(((x) >> 1) << 19)
 #define  L3_HIGH_PRIO_CREDITS(x)		(((x) >> 1) << 14)
 

drivers/gpu/drm/i915/intel_pm.c

@@ -6696,11 +6696,33 @@ static void lpt_suspend_hw(struct drm_device *dev)
 	}
 }
 
+static void gen8_set_l3sqc_credits(struct drm_i915_private *dev_priv,
+				   int general_prio_credits,
+				   int high_prio_credits)
+{
+	u32 misccpctl;
+
+	/* WaTempDisableDOPClkGating:bdw */
+	misccpctl = I915_READ(GEN7_MISCCPCTL);
+	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
+
+	I915_WRITE(GEN8_L3SQCREG1,
+		   L3_GENERAL_PRIO_CREDITS(general_prio_credits) |
+		   L3_HIGH_PRIO_CREDITS(high_prio_credits));
+
+	/*
+	 * Wait at least 100 clocks before re-enabling clock gating.
+	 * See the definition of L3SQCREG1 in BSpec.
+	 */
+	POSTING_READ(GEN8_L3SQCREG1);
+	udelay(1);
+	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
+}
+
 static void broadwell_init_clock_gating(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	enum pipe pipe;
-	uint32_t misccpctl;
 
 	ilk_init_lp_watermarks(dev);
 
@@ -6731,21 +6753,8 @@ static void broadwell_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
 		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
 
-	/*
+	/* WaProgramL3SqcReg1Default:bdw */
-	 * WaProgramL3SqcReg1Default:bdw
+	gen8_set_l3sqc_credits(dev_priv, 30, 2);
-	 * WaTempDisableDOPClkGating:bdw
-	 */
-	misccpctl = I915_READ(GEN7_MISCCPCTL);
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl & ~GEN7_DOP_CLOCK_GATE_ENABLE);
-	I915_WRITE(GEN8_L3SQCREG1, L3_GENERAL_PRIO_CREDITS(30) |
-				   L3_HIGH_PRIO_CREDITS(2));
-	/*
-	 * Wait at least 100 clocks before re-enabling clock gating. See
-	 * the definition of L3SQCREG1 in BSpec.
-	 */
-	POSTING_READ(GEN8_L3SQCREG1);
-	udelay(1);
-	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
 
 	/*
 	 * WaGttCachingOffByDefault:bdw
@@ -7015,6 +7024,13 @@ static void cherryview_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
 		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
 
+	/*
+	 * WaProgramL3SqcReg1Default:chv
+	 * See gfxspecs/Related Documents/Performance Guide/
+	 * LSQC Setting Recommendations.
+	 */
+	gen8_set_l3sqc_credits(dev_priv, 38, 2);
+
 	/*
 	 * GTT cache may not work with big pages, so if those
 	 * are ever enabled GTT cache may need to be disabled.