drm/i915: Configure SKL+ scaler initial phase correctly

Set up the SKL+ scaler initial phase registers correctly. Otherwise
we start fetching the data from the center of the first pixel instead
of the top-left corner, which obviously then leads to right/bottom edges
replicating data excessively as the data runs out half a pixel too soon.

Cc: Vidya Srinivas <vidya.srinivas@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180521185613.5097-2-ville.syrjala@linux.intel.com
Reviewed-By: Vidya Srinivas <vidya.srinivas@intel.com>

drivers/gpu/drm/i915/i915_reg.h

@@ -6789,6 +6789,10 @@ enum {
 #define _PS_VPHASE_1B       0x68988
 #define _PS_VPHASE_2B       0x68A88
 #define _PS_VPHASE_1C       0x69188
+#define  PS_Y_PHASE(x)		((x) << 16)
+#define  PS_UV_RGB_PHASE(x)	((x) << 0)
+#define   PS_PHASE_MASK	(0x7fff << 1) /* u2.13 */
+#define   PS_PHASE_TRIP	(1 << 0)
 
 #define _PS_HPHASE_1A       0x68194
 #define _PS_HPHASE_2A       0x68294

drivers/gpu/drm/i915/intel_display.c

@@ -4752,6 +4752,39 @@ static void cpt_verify_modeset(struct drm_device *dev, int pipe)
 	}
 }
 
+/*
+ * The hardware phase 0.0 refers to the center of the pixel.
+ * We want to start from the top/left edge which is phase
+ * -0.5. That matches how the hardware calculates the scaling
+ * factors (from top-left of the first pixel to bottom-right
+ * of the last pixel, as opposed to the pixel centers).
+ *
+ * For 4:2:0 subsampled chroma planes we obviously have to
+ * adjust that so that the chroma sample position lands in
+ * the right spot.
+ *
+ * Note that for packed YCbCr 4:2:2 formats there is no way to
+ * control chroma siting. The hardware simply replicates the
+ * chroma samples for both of the luma samples, and thus we don't
+ * actually get the expected MPEG2 chroma siting convention :(
+ * The same behaviour is observed on pre-SKL platforms as well.
+ */
+u16 skl_scaler_calc_phase(int sub, bool chroma_cosited)
+{
+	int phase = -0x8000;
+	u16 trip = 0;
+
+	if (chroma_cosited)
+		phase += (sub - 1) * 0x8000 / sub;
+
+	if (phase < 0)
+		phase = 0x10000 + phase;
+	else
+		trip = PS_PHASE_TRIP;
+
+	return ((phase >> 2) & PS_PHASE_MASK) | trip;
+}
+
 static int
 skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 		  unsigned int scaler_user, int *scaler_id,
@@ -4951,14 +4984,22 @@ static void skylake_pfit_enable(struct intel_crtc *crtc)
 		&crtc->config->scaler_state;
 
 	if (crtc->config->pch_pfit.enabled) {
+		u16 uv_rgb_hphase, uv_rgb_vphase;
 		int id;
 
 		if (WARN_ON(crtc->config->scaler_state.scaler_id < 0))
 			return;
 
+		uv_rgb_hphase = skl_scaler_calc_phase(1, false);
+		uv_rgb_vphase = skl_scaler_calc_phase(1, false);
+
 		id = scaler_state->scaler_id;
 		I915_WRITE(SKL_PS_CTRL(pipe, id), PS_SCALER_EN |
 			PS_FILTER_MEDIUM | scaler_state->scalers[id].mode);
+		I915_WRITE_FW(SKL_PS_VPHASE(pipe, id),
+			      PS_Y_PHASE(0) | PS_UV_RGB_PHASE(uv_rgb_vphase));
+		I915_WRITE_FW(SKL_PS_HPHASE(pipe, id),
+			      PS_Y_PHASE(0) | PS_UV_RGB_PHASE(uv_rgb_hphase));
 		I915_WRITE(SKL_PS_WIN_POS(pipe, id), crtc->config->pch_pfit.pos);
 		I915_WRITE(SKL_PS_WIN_SZ(pipe, id), crtc->config->pch_pfit.size);
 	}

drivers/gpu/drm/i915/intel_drv.h

@@ -1616,6 +1616,7 @@ void intel_mode_from_pipe_config(struct drm_display_mode *mode,
 void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc,
 				  struct intel_crtc_state *crtc_state);
 
+u16 skl_scaler_calc_phase(int sub, bool chroma_center);
 int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state);
 int skl_max_scale(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state,
 		  uint32_t pixel_format);

drivers/gpu/drm/i915/intel_sprite.c

@@ -284,13 +284,35 @@ skl_update_plane(struct intel_plane *plane,
 	/* program plane scaler */
 	if (plane_state->scaler_id >= 0) {
 		int scaler_id = plane_state->scaler_id;
-		const struct intel_scaler *scaler;
+		const struct intel_scaler *scaler =
+			&crtc_state->scaler_state.scalers[scaler_id];
+		u16 y_hphase, uv_rgb_hphase;
+		u16 y_vphase, uv_rgb_vphase;
+
+		/* TODO: handle sub-pixel coordinates */
+		if (fb->format->format == DRM_FORMAT_NV12) {
+			y_hphase = skl_scaler_calc_phase(1, false);
+			y_vphase = skl_scaler_calc_phase(1, false);
+
+			/* MPEG2 chroma siting convention */
+			uv_rgb_hphase = skl_scaler_calc_phase(2, true);
+			uv_rgb_vphase = skl_scaler_calc_phase(2, false);
+		} else {
+			/* not used */
+			y_hphase = 0;
+			y_vphase = 0;
 
-		scaler = &crtc_state->scaler_state.scalers[scaler_id];
+			uv_rgb_hphase = skl_scaler_calc_phase(1, false);
+			uv_rgb_vphase = skl_scaler_calc_phase(1, false);
+		}
 
 		I915_WRITE_FW(SKL_PS_CTRL(pipe, scaler_id),
 			      PS_SCALER_EN | PS_PLANE_SEL(plane_id) | scaler->mode);
 		I915_WRITE_FW(SKL_PS_PWR_GATE(pipe, scaler_id), 0);
+		I915_WRITE_FW(SKL_PS_VPHASE(pipe, scaler_id),
+			      PS_Y_PHASE(y_vphase) | PS_UV_RGB_PHASE(uv_rgb_vphase));
+		I915_WRITE_FW(SKL_PS_HPHASE(pipe, scaler_id),
+			      PS_Y_PHASE(y_hphase) | PS_UV_RGB_PHASE(uv_rgb_hphase));
 		I915_WRITE_FW(SKL_PS_WIN_POS(pipe, scaler_id), (crtc_x << 16) | crtc_y);
 		I915_WRITE_FW(SKL_PS_WIN_SZ(pipe, scaler_id),
 			      ((crtc_w + 1) << 16)|(crtc_h + 1));