openwrt/target/linux/bcm27xx/patches-6.6/950-0830-vc4-hvs-Updates-to-support-D0-alpha-and-csc-changes.patch

From efc0d85363a0e089ec3cdd0fbee58b4320fca449 Mon Sep 17 00:00:00 2001
From: Dom Cobley <popcornmix@gmail.com>
Date: Fri, 12 Jan 2024 15:48:14 +0000
Subject: [PATCH 0830/1085] vc4/hvs: Updates to support D0 alpha and csc
 changes

2712D0 has a simpler colourspace conversion matrix block
so set that up.

Signed-off-by: Dom Cobley <popcornmix@gmail.com>
---
 drivers/gpu/drm/vc4/vc4_hvs.c   | 73 ++++++++++++++++++++++-----------
 drivers/gpu/drm/vc4/vc4_plane.c | 20 +++++++--
 drivers/gpu/drm/vc4/vc4_regs.h  |  3 ++
 3 files changed, 67 insertions(+), 29 deletions(-)

--- a/drivers/gpu/drm/vc4/vc4_hvs.c
+++ b/drivers/gpu/drm/vc4/vc4_hvs.c
@@ -1888,6 +1888,17 @@ static int vc4_hvs_hw_init(struct vc4_hv
 #define CFC1_N_MA_CSC_COEFF_C23(x)	(0xa03c + ((x) * 0x3000))
 #define CFC1_N_MA_CSC_COEFF_C24(x)	(0xa040 + ((x) * 0x3000))
 
+#define SCALER_PI_CMP_CSC_RED0(x)		(0x200 + ((x) * 0x40))
+#define SCALER_PI_CMP_CSC_RED1(x)		(0x204 + ((x) * 0x40))
+#define SCALER_PI_CMP_CSC_RED_CLAMP(x)		(0x208 + ((x) * 0x40))
+#define SCALER_PI_CMP_CSC_CFG(x)		(0x20c + ((x) * 0x40))
+#define SCALER_PI_CMP_CSC_GREEN0(x)		(0x210 + ((x) * 0x40))
+#define SCALER_PI_CMP_CSC_GREEN1(x)		(0x214 + ((x) * 0x40))
+#define SCALER_PI_CMP_CSC_GREEN_CLAMP(x)	(0x218 + ((x) * 0x40))
+#define SCALER_PI_CMP_CSC_BLUE0(x)		(0x220 + ((x) * 0x40))
+#define SCALER_PI_CMP_CSC_BLUE1(x)		(0x224 + ((x) * 0x40))
+#define SCALER_PI_CMP_CSC_BLUE_CLAMP(x)		(0x228 + ((x) * 0x40))
+
 /* 4 S2.22 multiplication factors, and 1 S9.15 addititive element for each of 3
  * output components
  */
@@ -1958,31 +1969,43 @@ static int vc6_hvs_hw_init(struct vc4_hv
 	HVS_WRITE(SCALER6(PRI_MAP0), 0xffffffff);
 	HVS_WRITE(SCALER6(PRI_MAP1), 0xffffffff);
 
-	if (hvs->vc4->step_d0)
-		return;
-
-	for (i = 0; i < 6; i++) {
-		coeffs = &csc_coeffs[i / 3][i % 3];
-
-		HVS_WRITE(CFC1_N_MA_CSC_COEFF_C00(i), coeffs->csc[0][0]);
-		HVS_WRITE(CFC1_N_MA_CSC_COEFF_C01(i), coeffs->csc[0][1]);
-		HVS_WRITE(CFC1_N_MA_CSC_COEFF_C02(i), coeffs->csc[0][2]);
-		HVS_WRITE(CFC1_N_MA_CSC_COEFF_C03(i), coeffs->csc[0][3]);
-		HVS_WRITE(CFC1_N_MA_CSC_COEFF_C04(i), coeffs->csc[0][4]);
-
-		HVS_WRITE(CFC1_N_MA_CSC_COEFF_C10(i), coeffs->csc[1][0]);
-		HVS_WRITE(CFC1_N_MA_CSC_COEFF_C11(i), coeffs->csc[1][1]);
-		HVS_WRITE(CFC1_N_MA_CSC_COEFF_C12(i), coeffs->csc[1][2]);
-		HVS_WRITE(CFC1_N_MA_CSC_COEFF_C13(i), coeffs->csc[1][3]);
-		HVS_WRITE(CFC1_N_MA_CSC_COEFF_C14(i), coeffs->csc[1][4]);
-
-		HVS_WRITE(CFC1_N_MA_CSC_COEFF_C20(i), coeffs->csc[2][0]);
-		HVS_WRITE(CFC1_N_MA_CSC_COEFF_C21(i), coeffs->csc[2][1]);
-		HVS_WRITE(CFC1_N_MA_CSC_COEFF_C22(i), coeffs->csc[2][2]);
-		HVS_WRITE(CFC1_N_MA_CSC_COEFF_C23(i), coeffs->csc[2][3]);
-		HVS_WRITE(CFC1_N_MA_CSC_COEFF_C24(i), coeffs->csc[2][4]);
+	if (hvs->vc4->step_d0) {
+		for (i = 0; i < 8; i++) {
+			HVS_WRITE(SCALER_PI_CMP_CSC_RED0(i), 0x1f002566);
+			HVS_WRITE(SCALER_PI_CMP_CSC_RED1(i), 0x3994);
+			HVS_WRITE(SCALER_PI_CMP_CSC_RED_CLAMP(i), 0xfff00000);
+			HVS_WRITE(SCALER_PI_CMP_CSC_CFG(i), 0x1);
+			HVS_WRITE(SCALER_PI_CMP_CSC_GREEN0(i), 0x18002566);
+			HVS_WRITE(SCALER_PI_CMP_CSC_GREEN1(i), 0xf927eee2);
+			HVS_WRITE(SCALER_PI_CMP_CSC_GREEN_CLAMP(i), 0xfff00000);
+			HVS_WRITE(SCALER_PI_CMP_CSC_BLUE0(i), 0x18002566);
+			HVS_WRITE(SCALER_PI_CMP_CSC_BLUE1(i), 0x43d80000);
+			HVS_WRITE(SCALER_PI_CMP_CSC_BLUE_CLAMP(i), 0xfff00000);
+		}
+	} else {
+		for (i = 0; i < 6; i++) {
+			coeffs = &csc_coeffs[i / 3][i % 3];
+
+			HVS_WRITE(CFC1_N_MA_CSC_COEFF_C00(i), coeffs->csc[0][0]);
+			HVS_WRITE(CFC1_N_MA_CSC_COEFF_C01(i), coeffs->csc[0][1]);
+			HVS_WRITE(CFC1_N_MA_CSC_COEFF_C02(i), coeffs->csc[0][2]);
+			HVS_WRITE(CFC1_N_MA_CSC_COEFF_C03(i), coeffs->csc[0][3]);
+			HVS_WRITE(CFC1_N_MA_CSC_COEFF_C04(i), coeffs->csc[0][4]);
+
+			HVS_WRITE(CFC1_N_MA_CSC_COEFF_C10(i), coeffs->csc[1][0]);
+			HVS_WRITE(CFC1_N_MA_CSC_COEFF_C11(i), coeffs->csc[1][1]);
+			HVS_WRITE(CFC1_N_MA_CSC_COEFF_C12(i), coeffs->csc[1][2]);
+			HVS_WRITE(CFC1_N_MA_CSC_COEFF_C13(i), coeffs->csc[1][3]);
+			HVS_WRITE(CFC1_N_MA_CSC_COEFF_C14(i), coeffs->csc[1][4]);
+
+			HVS_WRITE(CFC1_N_MA_CSC_COEFF_C20(i), coeffs->csc[2][0]);
+			HVS_WRITE(CFC1_N_MA_CSC_COEFF_C21(i), coeffs->csc[2][1]);
+			HVS_WRITE(CFC1_N_MA_CSC_COEFF_C22(i), coeffs->csc[2][2]);
+			HVS_WRITE(CFC1_N_MA_CSC_COEFF_C23(i), coeffs->csc[2][3]);
+			HVS_WRITE(CFC1_N_MA_CSC_COEFF_C24(i), coeffs->csc[2][4]);
 
-		HVS_WRITE(CFC1_N_NL_CSC_CTRL(i), BIT(15));
+			HVS_WRITE(CFC1_N_NL_CSC_CTRL(i), BIT(15));
+		}
 	}
 
 	return 0;
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -1080,6 +1080,12 @@ static u32 vc4_hvs5_get_alpha_blend_mode
 
 	WARN_ON_ONCE(vc4->gen != VC4_GEN_5 && vc4->gen != VC4_GEN_6);
 
+	if (vc4->gen == VC4_GEN_6 && vc4->step_d0) {
+		return state->pixel_blend_mode == DRM_MODE_BLEND_PREMULTI ?
+			SCALER5_CTL2_ALPHA_PREMULT : 0;
+	}
+
+
 	if (!state->fb->format->has_alpha)
 		return VC4_SET_FIELD(SCALER5_CTL2_ALPHA_MODE_FIXED,
 				     SCALER5_CTL2_ALPHA_MODE);
@@ -1595,14 +1601,13 @@ static int vc4_plane_mode_set(struct drm
 static u32 vc6_plane_get_csc_mode(struct vc4_plane_state *vc4_state)
 {
 	struct drm_plane_state *state = &vc4_state->base;
+	struct vc4_dev *vc4 = to_vc4_dev(state->plane->dev);
 	u32 ret = 0;
 
 	if (vc4_state->is_yuv) {
 		enum drm_color_encoding color_encoding = state->color_encoding;
 		enum drm_color_range color_range = state->color_range;
 
-		ret |= SCALER6_CTL2_CSC_ENABLE;
-
 		/* CSC pre-loaded with:
 		 * 0 = BT601 limited range
 		 * 1 = BT709 limited range
@@ -1616,8 +1621,15 @@ static u32 vc6_plane_get_csc_mode(struct
 		if (color_range > DRM_COLOR_YCBCR_FULL_RANGE)
 			color_range = DRM_COLOR_YCBCR_LIMITED_RANGE;
 
-		ret |= VC4_SET_FIELD(color_encoding + (color_range * 3),
-				     SCALER6_CTL2_BRCM_CFC_CONTROL);
+		if (vc4->step_d0) {
+			ret |= SCALER6D0_CTL2_CSC_ENABLE;
+			ret |= VC4_SET_FIELD(color_encoding + (color_range * 3),
+					SCALER6D0_CTL2_BRCM_CFC_CONTROL);
+		} else {
+			ret |= SCALER6_CTL2_CSC_ENABLE;
+			ret |= VC4_SET_FIELD(color_encoding + (color_range * 3),
+					SCALER6_CTL2_BRCM_CFC_CONTROL);
+		}
 	}
 
 	return ret;
--- a/drivers/gpu/drm/vc4/vc4_regs.h
+++ b/drivers/gpu/drm/vc4/vc4_regs.h
@@ -1417,6 +1417,9 @@ enum hvs_pixel_format {
 #define SCALER6_CTL2_BRCM_CFC_CONTROL_MASK	VC4_MASK(18, 16)
 #define SCALER6_CTL2_ALPHA_MASK			VC4_MASK(15, 4)
 
+#define SCALER6D0_CTL2_CSC_ENABLE		BIT(19)
+#define SCALER6D0_CTL2_BRCM_CFC_CONTROL_MASK	VC4_MASK(22, 20)
+
 #define SCALER6_POS1_SCL_LINES_MASK		VC4_MASK(28, 16)
 #define SCALER6_POS1_SCL_WIDTH_MASK		VC4_MASK(12, 0)