drm/i915: Minimize the huge amount of unecessary fbc sw cache clean.

The sw cache clean on BDW is a tempoorary workaround because we cannot
set cache clean on blt ring with risk of hungs. So we are doing the cache clean on sw.
However we are doing much more than needed. Not only when using blt ring.
So, with this extra w/a we minimize the ammount of cache cleans and call it only
on same cases that it was being called on gen7.

The traditional FBC Cache clean happens over LRI on BLT ring when there is a
frontbuffer touch happening. frontbuffer tracking set fbc_dirty variable
to let BLT flush that it must clean FBC cache.

fbc.need_sw_cache_clean works in the opposite information direction
of ring->fbc_dirty telling software on frontbuffer tracking to perform
the cache clean on sw side.

v2: Clean it a little bit and fully check for Broadwell instead of gen8.

v3: Rebase after frontbuffer organization.

v4: Wiggle confused me. So fixing v3!

Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/i915_drv.h

@@ -666,6 +666,14 @@ struct i915_fbc {
 	 * possible. */
 	bool enabled;
 
+	/* On gen8 some rings cannont perform fbc clean operation so for now
+	 * we are doing this on SW with mmio.
+	 * This variable works in the opposite information direction
+	 * of ring->fbc_dirty telling software on frontbuffer tracking
+	 * to perform the cache clean on sw side.
+	 */
+	bool need_sw_cache_clean;
+
 	struct intel_fbc_work {
 		struct delayed_work work;
 		struct drm_crtc *crtc;
@@ -2825,7 +2833,7 @@ extern void intel_modeset_setup_hw_state(struct drm_device *dev,
 extern void i915_redisable_vga(struct drm_device *dev);
 extern void i915_redisable_vga_power_on(struct drm_device *dev);
 extern bool intel_fbc_enabled(struct drm_device *dev);
-extern void gen8_fbc_sw_flush(struct drm_device *dev, u32 value);
+extern void bdw_fbc_sw_flush(struct drm_device *dev, u32 value);
 extern void intel_disable_fbc(struct drm_device *dev);
 extern bool ironlake_set_drps(struct drm_device *dev, u8 val);
 extern void intel_init_pch_refclk(struct drm_device *dev);

drivers/gpu/drm/i915/intel_frontbuffer.c

@@ -189,8 +189,10 @@ void intel_frontbuffer_flush(struct drm_device *dev,
 	 * needs to be reworked into a proper frontbuffer tracking scheme like
 	 * psr employs.
 	 */
-	if (IS_BROADWELL(dev))
-		gen8_fbc_sw_flush(dev, FBC_REND_CACHE_CLEAN);
+	if (dev_priv->fbc.need_sw_cache_clean) {
+		dev_priv->fbc.need_sw_cache_clean = false;
+		bdw_fbc_sw_flush(dev, FBC_REND_CACHE_CLEAN);
+	}
 }
 
 /**

drivers/gpu/drm/i915/intel_pm.c

@@ -356,7 +356,7 @@ bool intel_fbc_enabled(struct drm_device *dev)
 	return dev_priv->fbc.enabled;
 }
 
-void gen8_fbc_sw_flush(struct drm_device *dev, u32 value)
+void bdw_fbc_sw_flush(struct drm_device *dev, u32 value)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -2237,6 +2237,7 @@ static int gen6_ring_flush(struct intel_engine_cs *ring,
 			   u32 invalidate, u32 flush)
 {
 	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t cmd;
 	int ret;
 
@@ -2267,8 +2268,12 @@ static int gen6_ring_flush(struct intel_engine_cs *ring,
 	}
 	intel_ring_advance(ring);
 
-	if (IS_GEN7(dev) && !invalidate && flush)
+	if (!invalidate && flush) {
+		if (IS_GEN7(dev))
 			return gen7_ring_fbc_flush(ring, FBC_REND_CACHE_CLEAN);
+		else if (IS_BROADWELL(dev))
+			dev_priv->fbc.need_sw_cache_clean = true;
+	}
 
 	return 0;
 }