drm/i915: WA: FBC Render Nuke.

WaFbcNukeOn3DBlt for IVB, HSW.

According BSPec: "Workaround: Do not enable Render Command Streamer tracking for FBC.
Instead insert a LRI to address 0x50380 with data 0x00000004 after the PIPE_CONTROL that
follows each render submission."

v2: Chris noticed that flush_domains check was missing here and also suggested to do
    LRI only when fbc is enabled. To avoid do a I915_READ on every flush lets use the
    module parameter check.

v3: Adding Wa name as Damien suggested.

v4: Ville noticed VLV doesn't support fbc at all and comment came wrong from spec.

v5: Ville noticed than on blt a Cache Clean LRI should be used instead the Nuke one.

v6: Check for flush domain on blt (by Ville).
    Check for scanout dirty (by Chris).

v7: Apply proper fbc_dirty implemented by Chris.

v8: remove unused variables.

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@gmail.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/i915_reg.h

@@ -1020,6 +1020,10 @@
 #define IPS_CTL		0x43408
 #define   IPS_ENABLE	(1 << 31)
 
+#define MSG_FBC_REND_STATE	0x50380
+#define   FBC_REND_NUKE		(1<<2)
+#define   FBC_REND_CACHE_CLEAN	(1<<1)
+
 #define _HSW_PIPE_SLICE_CHICKEN_1_A	0x420B0
 #define _HSW_PIPE_SLICE_CHICKEN_1_B	0x420B4
 #define   HSW_BYPASS_FBC_QUEUE		(1<<22)

drivers/gpu/drm/i915/intel_pm.c

@@ -274,7 +274,7 @@ static void gen7_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 	struct drm_i915_gem_object *obj = intel_fb->obj;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 
-	I915_WRITE(IVB_FBC_RT_BASE, obj->gtt_offset | ILK_FBC_RT_VALID);
+	I915_WRITE(IVB_FBC_RT_BASE, obj->gtt_offset);
 
 	I915_WRITE(ILK_DPFC_CONTROL, DPFC_CTL_EN | DPFC_CTL_LIMIT_1X |
 		   IVB_DPFC_CTL_FENCE_EN |

drivers/gpu/drm/i915/intel_ringbuffer.c

@@ -280,6 +280,27 @@ gen7_render_ring_cs_stall_wa(struct intel_ring_buffer *ring)
 	return 0;
 }
 
+static int gen7_ring_fbc_flush(struct intel_ring_buffer *ring, u32 value)
+{
+	int ret;
+
+	if (!ring->fbc_dirty)
+		return 0;
+
+	ret = intel_ring_begin(ring, 4);
+	if (ret)
+		return ret;
+	intel_ring_emit(ring, MI_NOOP);
+	/* WaFbcNukeOn3DBlt:ivb/hsw */
+	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
+	intel_ring_emit(ring, MSG_FBC_REND_STATE);
+	intel_ring_emit(ring, value);
+	intel_ring_advance(ring);
+
+	ring->fbc_dirty = false;
+	return 0;
+}
+
 static int
 gen7_render_ring_flush(struct intel_ring_buffer *ring,
 		       u32 invalidate_domains, u32 flush_domains)
@@ -336,6 +357,9 @@ gen7_render_ring_flush(struct intel_ring_buffer *ring,
 	intel_ring_emit(ring, 0);
 	intel_ring_advance(ring);
 
+	if (flush_domains)
+		return gen7_ring_fbc_flush(ring, FBC_REND_NUKE);
+
 	return 0;
 }
 
@@ -1685,6 +1709,7 @@ gen6_ring_dispatch_execbuffer(struct intel_ring_buffer *ring,
 static int gen6_ring_flush(struct intel_ring_buffer *ring,
 			   u32 invalidate, u32 flush)
 {
+	struct drm_device *dev = ring->dev;
 	uint32_t cmd;
 	int ret;
 
@@ -1707,6 +1732,10 @@ static int gen6_ring_flush(struct intel_ring_buffer *ring,
 	intel_ring_emit(ring, 0);
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_advance(ring);
+
+	if (IS_GEN7(dev) && flush)
+		return gen7_ring_fbc_flush(ring, FBC_REND_CACHE_CLEAN);
+
 	return 0;
 }