Received-SPF: pass (google.com: domain of linux-kernel+bounces-90828-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: Louis Chauvet <louis.chauvet@bootlin.com>
Date: Mon, 04 Mar 2024 16:28:13 +0100
Subject: [PATCH v4 08/14] drm/vkms: Avoid computing blending limits inside
 pre_mul_alpha_blend
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 7bit
Message-Id: <20240304-yuv-v4-8-76beac8e9793@bootlin.com>
References: <20240304-yuv-v4-0-76beac8e9793@bootlin.com>
In-Reply-To: <20240304-yuv-v4-0-76beac8e9793@bootlin.com>
To: Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>, 
 Melissa Wen <melissa.srw@gmail.com>, 
 =?utf-8?q?Ma=C3=ADra_Canal?= <mairacanal@riseup.net>, 
 Haneen Mohammed <hamohammed.sa@gmail.com>, Daniel Vetter <daniel@ffwll.ch>, 
 Maarten Lankhorst <maarten.lankhorst@linux.intel.com>, 
 Maxime Ripard <mripard@kernel.org>, Thomas Zimmermann <tzimmermann@suse.de>, 
 David Airlie <airlied@gmail.com>, arthurgrillo@riseup.net, 
 Jonathan Corbet <corbet@lwn.net>, pekka.paalanen@haloniitty.fi
Cc: dri-devel@lists.freedesktop.org, linux-kernel@vger.kernel.org, 
 jeremie.dautheribes@bootlin.com, miquel.raynal@bootlin.com, 
 thomas.petazzoni@bootlin.com, seanpaul@google.com, marcheu@google.com, 
 nicolejadeyee@google.com, Louis Chauvet <louis.chauvet@bootlin.com>

The pre_mul_alpha_blend is dedicated to blending, so to avoid mixing
different concepts (coordinate calculation and color management), extract
the x_limit and x_dst computation outside of this helper.
It also increases the maintainability by grouping the computation related
to coordinates in the same place: the loop in `blend`.

Signed-off-by: Louis Chauvet <louis.chauvet@bootlin.com>
---
 drivers/gpu/drm/vkms/vkms_composer.c | 43 ++++++++++++++++++------------------
 1 file changed, 22 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/vkms/vkms_composer.c b/drivers/gpu/drm/vkms/vkms_composer.c
index da0651a94c9b..26e8789630bd 100644
--- a/drivers/gpu/drm/vkms/vkms_composer.c
+++ b/drivers/gpu/drm/vkms/vkms_composer.c
@@ -24,34 +24,33 @@ static u16 pre_mul_blend_channel(u16 src, u16 dst, u16 alpha)
 
 /**
  * pre_mul_alpha_blend - alpha blending equation
- * @frame_info: Source framebuffer's metadata
  * @stage_buffer: The line with the pixels from src_plane
  * @output_buffer: A line buffer that receives all the blends output
+ * @x_start: The start offset to avoid useless copy
+ * @count: The number of byte to copy
  *
- * Using the information from the `frame_info`, this blends only the
- * necessary pixels from the `stage_buffer` to the `output_buffer`
- * using premultiplied blend formula.
+ * Using @x_start and @count information, only few pixel can be blended instead of the whole line
+ * each time.
  *
  * The current DRM assumption is that pixel color values have been already
  * pre-multiplied with the alpha channel values. See more
  * drm_plane_create_blend_mode_property(). Also, this formula assumes a
  * completely opaque background.
  */
-static void pre_mul_alpha_blend(struct vkms_frame_info *frame_info,
-				struct line_buffer *stage_buffer,
-				struct line_buffer *output_buffer)
+static void pre_mul_alpha_blend(
+	const struct line_buffer *stage_buffer,
+	struct line_buffer *output_buffer,
+	int x_start,
+	int pixel_count)
 {
-	int x_dst = frame_info->dst.x1;
-	struct pixel_argb_u16 *out = output_buffer->pixels + x_dst;
-	struct pixel_argb_u16 *in = stage_buffer->pixels;
-	int x_limit = min_t(size_t, drm_rect_width(&frame_info->dst),
-			    stage_buffer->n_pixels);
-
-	for (int x = 0; x < x_limit; x++) {
-		out[x].a = (u16)0xffff;
-		out[x].r = pre_mul_blend_channel(in[x].r, out[x].r, in[x].a);
-		out[x].g = pre_mul_blend_channel(in[x].g, out[x].g, in[x].a);
-		out[x].b = pre_mul_blend_channel(in[x].b, out[x].b, in[x].a);
+	struct pixel_argb_u16 *out = &output_buffer->pixels[x_start];
+	const struct pixel_argb_u16 *in = &stage_buffer->pixels[x_start];
+
+	for (int i = 0; i < pixel_count; i++) {
+		out[i].a = (u16)0xffff;
+		out[i].r = pre_mul_blend_channel(in[i].r, out[i].r, in[i].a);
+		out[i].g = pre_mul_blend_channel(in[i].g, out[i].g, in[i].a);
+		out[i].b = pre_mul_blend_channel(in[i].b, out[i].b, in[i].a);
 	}
 }
 
@@ -183,7 +182,7 @@ static void blend(struct vkms_writeback_job *wb,
 {
 	struct vkms_plane_state **plane = crtc_state->active_planes;
 	u32 n_active_planes = crtc_state->num_active_planes;
-	int y_pos;
+	int y_pos, x_dst, x_limit;
 
 	const struct pixel_argb_u16 background_color = { .a = 0xffff };
 
@@ -201,14 +200,16 @@ static void blend(struct vkms_writeback_job *wb,
 
 		/* The active planes are composed associatively in z-order. */
 		for (size_t i = 0; i < n_active_planes; i++) {
+			x_dst = plane[i]->frame_info->dst.x1;
+			x_limit = min_t(size_t, drm_rect_width(&plane[i]->frame_info->dst),
+					stage_buffer->n_pixels);
 			y_pos = get_y_pos(plane[i]->frame_info, y);
 
 			if (!check_limit(plane[i]->frame_info, y_pos))
 				continue;
 
 			vkms_compose_row(stage_buffer, plane[i], y_pos);
-			pre_mul_alpha_blend(plane[i]->frame_info, stage_buffer,
-					    output_buffer);
+			pre_mul_alpha_blend(stage_buffer, output_buffer, x_dst, x_limit);
 		}
 
 		apply_lut(crtc_state, output_buffer);

-- 
2.43.0