Received-SPF: pass (google.com: domain of linux-kernel+bounces-144321-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
From: Detlev Casanova <detlev.casanova@collabora.com>
To: linux-kernel@vger.kernel.org
Cc: Sandy Huang <hjc@rock-chips.com>,
	Heiko Stubner <heiko@sntech.de>,
	Andy Yan <andy.yan@rock-chips.com>,
	Maarten Lankhorst <maarten.lankhorst@linux.intel.com>,
	Maxime Ripard <mripard@kernel.org>,
	Thomas Zimmermann <tzimmermann@suse.de>,
	David Airlie <airlied@gmail.com>,
	Daniel Vetter <daniel@ffwll.ch>,
	dri-devel@lists.freedesktop.org,
	linux-arm-kernel@lists.infradead.org,
	linux-rockchip@lists.infradead.org,
	Detlev Casanova <detlev.casanova@collabora.com>
Subject: [PATCH] drm: vop2: Do not divide height twice for YUV
Date: Sun, 14 Apr 2024 14:27:06 -0400
Message-ID: <20240414182706.655270-1-detlev.casanova@collabora.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

For the cbcr format, gt2 and gt4 are computed again after src_h has been
divided by vsub.

As src_h as already been divided by 2 before, introduce cbcr_src_h and
cbcr_src_w to keep a copy of those values to be used for cbcr gt2 and
gt4 computation.

This fixes yuv planes being unaligned vertically when down scaling to
1080 pixels from 2160.

Signed-off-by: Detlev Casanova <detlev.casanova@collabora.com>
Fixes: 604be85547ce ("drm/rockchip: Add VOP2 driver")
---
 drivers/gpu/drm/rockchip/rockchip_drm_vop2.c | 22 +++++++++++---------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
index fdd768bbd487c..62ebbdb16253d 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
@@ -706,6 +706,8 @@ static void vop2_setup_scale(struct vop2 *vop2, const struct vop2_win *win,
 	const struct drm_format_info *info;
 	u16 hor_scl_mode, ver_scl_mode;
 	u16 hscl_filter_mode, vscl_filter_mode;
+	uint16_t cbcr_src_w = src_w;
+	uint16_t cbcr_src_h = src_h;
 	u8 gt2 = 0;
 	u8 gt4 = 0;
 	u32 val;
@@ -763,27 +765,27 @@ static void vop2_setup_scale(struct vop2 *vop2, const struct vop2_win *win,
 	vop2_win_write(win, VOP2_WIN_YRGB_VSCL_FILTER_MODE, vscl_filter_mode);
 
 	if (info->is_yuv) {
-		src_w /= info->hsub;
-		src_h /= info->vsub;
+		cbcr_src_w /= info->hsub;
+		cbcr_src_h /= info->vsub;
 
 		gt4 = 0;
 		gt2 = 0;
 
-		if (src_h >= (4 * dst_h)) {
+		if (cbcr_src_h >= (4 * dst_h)) {
 			gt4 = 1;
-			src_h >>= 2;
-		} else if (src_h >= (2 * dst_h)) {
+			cbcr_src_h >>= 2;
+		} else if (cbcr_src_h >= (2 * dst_h)) {
 			gt2 = 1;
-			src_h >>= 1;
+			cbcr_src_h >>= 1;
 		}
 
-		hor_scl_mode = scl_get_scl_mode(src_w, dst_w);
-		ver_scl_mode = scl_get_scl_mode(src_h, dst_h);
+		hor_scl_mode = scl_get_scl_mode(cbcr_src_w, dst_w);
+		ver_scl_mode = scl_get_scl_mode(cbcr_src_h, dst_h);
 
-		val = vop2_scale_factor(src_w, dst_w);
+		val = vop2_scale_factor(cbcr_src_w, dst_w);
 		vop2_win_write(win, VOP2_WIN_SCALE_CBCR_X, val);
 
-		val = vop2_scale_factor(src_h, dst_h);
+		val = vop2_scale_factor(cbcr_src_h, dst_h);
 		vop2_win_write(win, VOP2_WIN_SCALE_CBCR_Y, val);
 
 		vop2_win_write(win, VOP2_WIN_VSD_CBCR_GT4, gt4);
-- 
2.43.2