drm/i915: Enable GTT caching on gen8

GTT caching was disabled by default on gen8 due to not working with
big pages. Some information suggests that it got fixed, but still
GTT caching has been left disabled by default. Or could be it just
meant that the default was changed to off, and hence the problem
got solved.

Enable GTT caching in the hopes of some performance increase.
Whether or not the big pages issue has been fixed is irrelevant
at this stage since we don't use big pages.

This gives me a 1-2% improvement in xonotic on my BSW. Haven't tried
BDW, but supposedly it has larger TLBs so might not benefit as much.
On HSW GTT caching is enabled by default.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/i915_reg.h

@@ -1461,6 +1461,8 @@ enum skl_disp_power_wells {
 #define RING_HWS_PGA(base)	((base)+0x80)
 #define RING_HWS_PGA_GEN6(base)	((base)+0x2080)
 
+#define HSW_GTT_CACHE_EN	0x4024
+#define   GTT_CACHE_EN_ALL	0xF0007FFF
 #define GEN7_WR_WATERMARK	0x4028
 #define GEN7_GFX_PRIO_CTRL	0x402C
 #define ARB_MODE		0x4030

drivers/gpu/drm/i915/intel_pm.c

@@ -6214,6 +6214,13 @@ static void broadwell_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN8_L3SQCREG1, BDW_WA_L3SQCREG1_DEFAULT);
 	I915_WRITE(GEN7_MISCCPCTL, misccpctl);
 
+	/*
+	 * WaGttCachingOffByDefault:bdw
+	 * GTT cache may not work with big pages, so if those
+	 * are ever enabled GTT cache may need to be disabled.
+	 */
+	I915_WRITE(HSW_GTT_CACHE_EN, GTT_CACHE_EN_ALL);
+
 	lpt_init_clock_gating(dev);
 }
 
@@ -6489,6 +6496,12 @@ static void cherryview_init_clock_gating(struct drm_device *dev)
 	/* WaDisableSDEUnitClockGating:chv */
 	I915_WRITE(GEN8_UCGCTL6, I915_READ(GEN8_UCGCTL6) |
 		   GEN8_SDEUNIT_CLOCK_GATE_DISABLE);
+
+	/*
+	 * GTT cache may not work with big pages, so if those
+	 * are ever enabled GTT cache may need to be disabled.
+	 */
+	I915_WRITE(HSW_GTT_CACHE_EN, GTT_CACHE_EN_ALL);
 }
 
 static void g4x_init_clock_gating(struct drm_device *dev)