drm/i915: enable HiZ Raw Stall Optimization on HSW

The optimization is available on Ivy Bridge and later, and is disabled by
default.  Enabling it helps certain workloads such as GLBenchmark TRex test.

No piglit regression.

v2
 - no need to save the register before suspend as init_clock_gating can
   correctly program it after resume
 - split IVB change to another commit
Signed-off-by: NChia-I Wu <olv@lunarg.com>
Reviewed-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/i915_reg.h

@@ -935,6 +935,8 @@
 #define   ECO_GATING_CX_ONLY	(1<<3)
 #define   ECO_FLIP_DONE		(1<<0)
 
+#define CACHE_MODE_0_GEN7	0x7000 /* IVB+ */
+#define   HIZ_RAW_STALL_OPT_DISABLE (1<<2)
 #define CACHE_MODE_1		0x7004 /* IVB+ */
 #define   PIXEL_SUBSPAN_COLLECT_OPT_DISABLE (1<<6)
 

drivers/gpu/drm/i915/intel_pm.c

@@ -4785,6 +4785,10 @@ static void haswell_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(GEN7_FF_THREAD_MODE,
 		   I915_READ(GEN7_FF_THREAD_MODE) & ~GEN7_FF_VS_REF_CNT_FFME);
 
+	/* enable HiZ Raw Stall Optimization */
+	I915_WRITE(CACHE_MODE_0_GEN7,
+		   _MASKED_BIT_DISABLE(HIZ_RAW_STALL_OPT_DISABLE));
+
 	/* WaDisable4x2SubspanOptimization:hsw */
 	I915_WRITE(CACHE_MODE_1,
 		   _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));