drm/vkms: isolate pixel conversion functionality

Currently, the pixel conversion functions repeat the same loop to
iterate the rows. Instead of repeating the same code for each pixel
format, create a function to wrap the loop and isolate the pixel
conversion functionality.
Suggested-by: Arthur Grillo <arthurgrillo@riseup.net>
Signed-off-by: Maíra Canal <mcanal@igalia.com>
Reviewed-by: Arthur Grillo <arthurgrillo@riseup.net>
Signed-off-by: Maíra Canal <mairacanal@riseup.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20230418130525.128733-2-mcanal@igalia.com

drivers/gpu/drm/vkms/vkms_composer.c

@@ -99,7 +99,7 @@ static void blend(struct vkms_writeback_job *wb,
 			if (!check_y_limit(plane[i]->frame_info, y))
 				continue;
 
-			plane[i]->plane_read(stage_buffer, plane[i]->frame_info, y);
+			vkms_compose_row(stage_buffer, plane[i], y);
 			pre_mul_alpha_blend(plane[i]->frame_info, stage_buffer,
 					    output_buffer);
 		}
@@ -118,7 +118,7 @@ static int check_format_funcs(struct vkms_crtc_state *crtc_state,
 	u32 n_active_planes = crtc_state->num_active_planes;
 
 	for (size_t i = 0; i < n_active_planes; i++)
-		if (!planes[i]->plane_read)
+		if (!planes[i]->pixel_read)
 			return -1;
 
 	if (active_wb && !active_wb->wb_write)

drivers/gpu/drm/vkms/vkms_drv.h

@@ -56,8 +56,7 @@ struct vkms_writeback_job {
 struct vkms_plane_state {
 	struct drm_shadow_plane_state base;
 	struct vkms_frame_info *frame_info;
-	void (*plane_read)(struct line_buffer *buffer,
-			   const struct vkms_frame_info *frame_info, int y);
+	void (*pixel_read)(u8 *src_buffer, struct pixel_argb_u16 *out_pixel);
 };
 
 struct vkms_plane {
@@ -155,6 +154,7 @@ int vkms_verify_crc_source(struct drm_crtc *crtc, const char *source_name,
 /* Composer Support */
 void vkms_composer_worker(struct work_struct *work);
 void vkms_set_composer(struct vkms_output *out, bool enabled);
+void vkms_compose_row(struct line_buffer *stage_buffer, struct vkms_plane_state *plane, int y);
 
 /* Writeback */
 int vkms_enable_writeback_connector(struct vkms_device *vkmsdev);

drivers/gpu/drm/vkms/vkms_formats.c

@@ -42,100 +42,75 @@ static void *get_packed_src_addr(const struct vkms_frame_info *frame_info, int y
 	return packed_pixels_addr(frame_info, x_src, y_src);
 }
 
-static void ARGB8888_to_argb_u16(struct line_buffer *stage_buffer,
-				 const struct vkms_frame_info *frame_info, int y)
+static void ARGB8888_to_argb_u16(u8 *src_pixels, struct pixel_argb_u16 *out_pixel)
 {
-	struct pixel_argb_u16 *out_pixels = stage_buffer->pixels;
-	u8 *src_pixels = get_packed_src_addr(frame_info, y);
-	int x_limit = min_t(size_t, drm_rect_width(&frame_info->dst),
-			    stage_buffer->n_pixels);
-
-	for (size_t x = 0; x < x_limit; x++, src_pixels += 4) {
-		/*
-		 * The 257 is the "conversion ratio". This number is obtained by the
-		 * (2^16 - 1) / (2^8 - 1) division. Which, in this case, tries to get
-		 * the best color value in a pixel format with more possibilities.
-		 * A similar idea applies to others RGB color conversions.
-		 */
-		out_pixels[x].a = (u16)src_pixels[3] * 257;
-		out_pixels[x].r = (u16)src_pixels[2] * 257;
-		out_pixels[x].g = (u16)src_pixels[1] * 257;
-		out_pixels[x].b = (u16)src_pixels[0] * 257;
-	}
+	/*
+	 * The 257 is the "conversion ratio". This number is obtained by the
+	 * (2^16 - 1) / (2^8 - 1) division. Which, in this case, tries to get
+	 * the best color value in a pixel format with more possibilities.
+	 * A similar idea applies to others RGB color conversions.
+	 */
+	out_pixel->a = (u16)src_pixels[3] * 257;
+	out_pixel->r = (u16)src_pixels[2] * 257;
+	out_pixel->g = (u16)src_pixels[1] * 257;
+	out_pixel->b = (u16)src_pixels[0] * 257;
 }
 
-static void XRGB8888_to_argb_u16(struct line_buffer *stage_buffer,
-				 const struct vkms_frame_info *frame_info, int y)
+static void XRGB8888_to_argb_u16(u8 *src_pixels, struct pixel_argb_u16 *out_pixel)
 {
-	struct pixel_argb_u16 *out_pixels = stage_buffer->pixels;
-	u8 *src_pixels = get_packed_src_addr(frame_info, y);
-	int x_limit = min_t(size_t, drm_rect_width(&frame_info->dst),
-			    stage_buffer->n_pixels);
-
-	for (size_t x = 0; x < x_limit; x++, src_pixels += 4) {
-		out_pixels[x].a = (u16)0xffff;
-		out_pixels[x].r = (u16)src_pixels[2] * 257;
-		out_pixels[x].g = (u16)src_pixels[1] * 257;
-		out_pixels[x].b = (u16)src_pixels[0] * 257;
-	}
+	out_pixel->a = (u16)0xffff;
+	out_pixel->r = (u16)src_pixels[2] * 257;
+	out_pixel->g = (u16)src_pixels[1] * 257;
+	out_pixel->b = (u16)src_pixels[0] * 257;
 }
 
-static void ARGB16161616_to_argb_u16(struct line_buffer *stage_buffer,
-				     const struct vkms_frame_info *frame_info,
-				     int y)
+static void ARGB16161616_to_argb_u16(u8 *src_pixels, struct pixel_argb_u16 *out_pixel)
 {
-	struct pixel_argb_u16 *out_pixels = stage_buffer->pixels;
-	u16 *src_pixels = get_packed_src_addr(frame_info, y);
-	int x_limit = min_t(size_t, drm_rect_width(&frame_info->dst),
-			    stage_buffer->n_pixels);
+	u16 *pixels = (u16 *)src_pixels;
 
-	for (size_t x = 0; x < x_limit; x++, src_pixels += 4) {
-		out_pixels[x].a = le16_to_cpu(src_pixels[3]);
-		out_pixels[x].r = le16_to_cpu(src_pixels[2]);
-		out_pixels[x].g = le16_to_cpu(src_pixels[1]);
-		out_pixels[x].b = le16_to_cpu(src_pixels[0]);
-	}
+	out_pixel->a = le16_to_cpu(pixels[3]);
+	out_pixel->r = le16_to_cpu(pixels[2]);
+	out_pixel->g = le16_to_cpu(pixels[1]);
+	out_pixel->b = le16_to_cpu(pixels[0]);
 }
 
-static void XRGB16161616_to_argb_u16(struct line_buffer *stage_buffer,
-				     const struct vkms_frame_info *frame_info,
-				     int y)
+static void XRGB16161616_to_argb_u16(u8 *src_pixels, struct pixel_argb_u16 *out_pixel)
 {
-	struct pixel_argb_u16 *out_pixels = stage_buffer->pixels;
-	u16 *src_pixels = get_packed_src_addr(frame_info, y);
-	int x_limit = min_t(size_t, drm_rect_width(&frame_info->dst),
-			    stage_buffer->n_pixels);
+	u16 *pixels = (u16 *)src_pixels;
 
-	for (size_t x = 0; x < x_limit; x++, src_pixels += 4) {
-		out_pixels[x].a = (u16)0xffff;
-		out_pixels[x].r = le16_to_cpu(src_pixels[2]);
-		out_pixels[x].g = le16_to_cpu(src_pixels[1]);
-		out_pixels[x].b = le16_to_cpu(src_pixels[0]);
-	}
+	out_pixel->a = (u16)0xffff;
+	out_pixel->r = le16_to_cpu(pixels[2]);
+	out_pixel->g = le16_to_cpu(pixels[1]);
+	out_pixel->b = le16_to_cpu(pixels[0]);
 }
 
-static void RGB565_to_argb_u16(struct line_buffer *stage_buffer,
-			       const struct vkms_frame_info *frame_info, int y)
+static void RGB565_to_argb_u16(u8 *src_pixels, struct pixel_argb_u16 *out_pixel)
 {
-	struct pixel_argb_u16 *out_pixels = stage_buffer->pixels;
-	u16 *src_pixels = get_packed_src_addr(frame_info, y);
-	int x_limit = min_t(size_t, drm_rect_width(&frame_info->dst),
-			       stage_buffer->n_pixels);
+	u16 *pixels = (u16 *)src_pixels;
 
 	s64 fp_rb_ratio = drm_fixp_div(drm_int2fixp(65535), drm_int2fixp(31));
 	s64 fp_g_ratio = drm_fixp_div(drm_int2fixp(65535), drm_int2fixp(63));
 
-	for (size_t x = 0; x < x_limit; x++, src_pixels++) {
-		u16 rgb_565 = le16_to_cpu(*src_pixels);
-		s64 fp_r = drm_int2fixp((rgb_565 >> 11) & 0x1f);
-		s64 fp_g = drm_int2fixp((rgb_565 >> 5) & 0x3f);
-		s64 fp_b = drm_int2fixp(rgb_565 & 0x1f);
+	u16 rgb_565 = le16_to_cpu(*pixels);
+	s64 fp_r = drm_int2fixp((rgb_565 >> 11) & 0x1f);
+	s64 fp_g = drm_int2fixp((rgb_565 >> 5) & 0x3f);
+	s64 fp_b = drm_int2fixp(rgb_565 & 0x1f);
 
-		out_pixels[x].a = (u16)0xffff;
-		out_pixels[x].r = drm_fixp2int(drm_fixp_mul(fp_r, fp_rb_ratio));
-		out_pixels[x].g = drm_fixp2int(drm_fixp_mul(fp_g, fp_g_ratio));
-		out_pixels[x].b = drm_fixp2int(drm_fixp_mul(fp_b, fp_rb_ratio));
-	}
+	out_pixel->a = (u16)0xffff;
+	out_pixel->r = drm_fixp2int(drm_fixp_mul(fp_r, fp_rb_ratio));
+	out_pixel->g = drm_fixp2int(drm_fixp_mul(fp_g, fp_g_ratio));
+	out_pixel->b = drm_fixp2int(drm_fixp_mul(fp_b, fp_rb_ratio));
+}
+
+void vkms_compose_row(struct line_buffer *stage_buffer, struct vkms_plane_state *plane, int y)
+{
+	struct pixel_argb_u16 *out_pixels = stage_buffer->pixels;
+	struct vkms_frame_info *frame_info = plane->frame_info;
+	u8 *src_pixels = get_packed_src_addr(frame_info, y);
+	int limit = min_t(size_t, drm_rect_width(&frame_info->dst), stage_buffer->n_pixels);
+
+	for (size_t x = 0; x < limit; x++, src_pixels += frame_info->cpp)
+		plane->pixel_read(src_pixels, &out_pixels[x]);
 }
 
 /*
@@ -249,7 +224,7 @@ static void argb_u16_to_RGB565(struct vkms_frame_info *frame_info,
 	}
 }
 
-void *get_frame_to_line_function(u32 format)
+void *get_pixel_conversion_function(u32 format)
 {
 	switch (format) {
 	case DRM_FORMAT_ARGB8888:

drivers/gpu/drm/vkms/vkms_formats.h

@@ -5,7 +5,7 @@
 
 #include "vkms_drv.h"
 
-void *get_frame_to_line_function(u32 format);
+void *get_pixel_conversion_function(u32 format);
 
 void *get_line_to_frame_function(u32 format);
 

drivers/gpu/drm/vkms/vkms_plane.c

@@ -123,7 +123,7 @@ static void vkms_plane_atomic_update(struct drm_plane *plane,
 	frame_info->offset = fb->offsets[0];
 	frame_info->pitch = fb->pitches[0];
 	frame_info->cpp = fb->format->cpp[0];
-	vkms_plane_state->plane_read = get_frame_to_line_function(fmt);
+	vkms_plane_state->pixel_read = get_pixel_conversion_function(fmt);
 }
 
 static int vkms_plane_atomic_check(struct drm_plane *plane,