Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:5 as permitted sender) client-ip=2620:137:e000::3:5;
From:   AngeloGioacchino Del Regno 
        <angelogioacchino.delregno@collabora.com>
To:     chunkuang.hu@kernel.org
Cc:     p.zabel@pengutronix.de, airlied@gmail.com, daniel@ffwll.ch,
        matthias.bgg@gmail.com, angelogioacchino.delregno@collabora.com,
        dri-devel@lists.freedesktop.org,
        linux-mediatek@lists.infradead.org, linux-kernel@vger.kernel.org,
        linux-arm-kernel@lists.infradead.org, wenst@chromium.org,
        kernel@collabora.com, ehristev@collabora.com,
        nfraprado@collabora.com,
        "Jason-JH . Lin" <jason-jh.lin@mediatek.com>,
        Alexandre Mergnat <amergnat@baylibre.com>,
        CK Hu <ck.hu@mediatek.com>
Subject: [PATCH v11 04/16] drm/mediatek: gamma: Improve and simplify HW LUT calculation
Date:   Thu, 12 Oct 2023 11:57:24 +0200
Message-ID: <20231012095736.100784-5-angelogioacchino.delregno@collabora.com>
In-Reply-To: <20231012095736.100784-1-angelogioacchino.delregno@collabora.com>
References: <20231012095736.100784-1-angelogioacchino.delregno@collabora.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Use drm_color_lut_extract() to avoid open-coding the bits reduction
calculations for each color channel and use a struct drm_color_lut
to temporarily store the information instead of an array of u32.

Also, slightly improve the precision of the HW LUT calculation in the
LUT DIFF case by performing the subtractions on the 16-bits values and
doing the 10 bits conversion later.

Reviewed-by: Jason-JH.Lin <jason-jh.lin@mediatek.com>
Reviewed-by: Alexandre Mergnat <amergnat@baylibre.com>
Reviewed-by: CK Hu <ck.hu@mediatek.com>
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
---
 drivers/gpu/drm/mediatek/mtk_disp_gamma.c | 32 ++++++++++++++---------
 1 file changed, 20 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_disp_gamma.c b/drivers/gpu/drm/mediatek/mtk_disp_gamma.c
index bb237523d4b7..8506b9a0a811 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_gamma.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_gamma.c
@@ -23,8 +23,6 @@
 #define DISP_GAMMA_SIZE				0x0030
 #define DISP_GAMMA_LUT				0x0700
 
-#define LUT_10BIT_MASK				0x03ff
-
 struct mtk_disp_gamma_data {
 	bool has_dither;
 	bool lut_diff;
@@ -73,7 +71,6 @@ void mtk_gamma_set_common(struct device *dev, void __iomem *regs, struct drm_crt
 	bool lut_diff;
 	u16 lut_size;
 	u32 word;
-	u32 diff[3] = {0};
 
 	/* If there's no gamma lut there's nothing to do here. */
 	if (!state->gamma_lut)
@@ -96,18 +93,29 @@ void mtk_gamma_set_common(struct device *dev, void __iomem *regs, struct drm_crt
 	lut_base = regs + DISP_GAMMA_LUT;
 	lut = (struct drm_color_lut *)state->gamma_lut->data;
 	for (i = 0; i < lut_size; i++) {
+		struct drm_color_lut diff, hwlut;
+
+		hwlut.red = drm_color_lut_extract(lut[i].red, 10);
+		hwlut.green = drm_color_lut_extract(lut[i].green, 10);
+		hwlut.blue = drm_color_lut_extract(lut[i].blue, 10);
+
 		if (!lut_diff || (i % 2 == 0)) {
-			word = (((lut[i].red >> 6) & LUT_10BIT_MASK) << 20) +
-				(((lut[i].green >> 6) & LUT_10BIT_MASK) << 10) +
-				((lut[i].blue >> 6) & LUT_10BIT_MASK);
+			word = hwlut.red << 20 +
+			       hwlut.green << 10 +
+			       hwlut.red;
 		} else {
-			diff[0] = (lut[i].red >> 6) - (lut[i - 1].red >> 6);
-			diff[1] = (lut[i].green >> 6) - (lut[i - 1].green >> 6);
-			diff[2] = (lut[i].blue >> 6) - (lut[i - 1].blue >> 6);
+			diff.red = lut[i].red - lut[i - 1].red;
+			diff.red = drm_color_lut_extract(diff.red, 10);
+
+			diff.green = lut[i].green - lut[i - 1].green;
+			diff.green = drm_color_lut_extract(diff.green, 10);
+
+			diff.blue = lut[i].blue - lut[i - 1].blue;
+			diff.blue = drm_color_lut_extract(diff.blue, 10);
 
-			word = ((diff[0] & LUT_10BIT_MASK) << 20) +
-				((diff[1] & LUT_10BIT_MASK) << 10) +
-				(diff[2] & LUT_10BIT_MASK);
+			word = diff.blue << 20 +
+			       diff.green << 10 +
+			       diff.red;
 		}
 		writel(word, (lut_base + i * 4));
 	}
-- 
2.42.0