1 files changed, 138 insertions, 160 deletions

diff --git a/drivers/gpu/drm/vkms/vkms_formats.c b/drivers/gpu/drm/vkms/vkms_formats.c
index d4950688b3f1..36046b12f296 100644
--- a/drivers/gpu/drm/vkms/vkms_formats.c
+++ b/drivers/gpu/drm/vkms/vkms_formats.c
@@ -2,6 +2,8 @@
 
 #include <linux/kernel.h>
 #include <linux/minmax.h>
+
+#include <drm/drm_blend.h>
 #include <drm/drm_rect.h>
 #include <drm/drm_fixed.h>
 
@@ -37,104 +39,106 @@ static void *packed_pixels_addr(const struct vkms_frame_info *frame_info,
 static void *get_packed_src_addr(const struct vkms_frame_info *frame_info, int y)
 {
 	int x_src = frame_info->src.x1 >> 16;
-	int y_src = y - frame_info->dst.y1 + (frame_info->src.y1 >> 16);
+	int y_src = y - frame_info->rotated.y1 + (frame_info->src.y1 >> 16);
 
 	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 int get_x_position(const struct vkms_frame_info *frame_info, int limit, int x)
 {
-	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;
-	}
+	if (frame_info->rotation & (DRM_MODE_REFLECT_X | DRM_MODE_ROTATE_270))
+		return limit - x - 1;
+	return x;
 }
 
-static void XRGB8888_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) {
-		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;
-	}
+	/*
+	 * 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 ARGB16161616_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;
-	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);
-
-	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 = (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 XRGB16161616_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);
-
-	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]);
-	}
+	u16 *pixels = (u16 *)src_pixels;
+
+	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 RGB565_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;
+
+	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(u8 *src_pixels, struct pixel_argb_u16 *out_pixel)
+{
+	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_pixel->a = (u16)0xffff;
+	out_pixel->r = drm_fixp2int_round(drm_fixp_mul(fp_r, fp_rb_ratio));
+	out_pixel->g = drm_fixp2int_round(drm_fixp_mul(fp_g, fp_g_ratio));
+	out_pixel->b = drm_fixp2int_round(drm_fixp_mul(fp_b, fp_rb_ratio));
+}
+
+/**
+ * vkms_compose_row - compose a single row of a plane
+ * @stage_buffer: output line with the composed pixels
+ * @plane: state of the plane that is being composed
+ * @y: y coordinate of the row
+ *
+ * This function composes a single row of a plane. It gets the source pixels
+ * through the y coordinate (see get_packed_src_addr()) and goes linearly
+ * through the source pixel, reading the pixels and converting it to
+ * ARGB16161616 (see the pixel_read() callback). For rotate-90 and rotate-270,
+ * the source pixels are not traversed linearly. The source pixels are queried
+ * on each iteration in order to traverse the pixels vertically.
+ */
+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) {
+		int x_pos = get_x_position(frame_info, limit, x);
+
+		if (drm_rotation_90_or_270(frame_info->rotation))
+			src_pixels = get_packed_src_addr(frame_info, x + frame_info->rotated.y1)
+				+ frame_info->cpp * y;
 
-		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));
+		plane->pixel_read(src_pixels, &out_pixels[x_pos]);
 	}
 }
 
@@ -146,110 +150,84 @@ static void RGB565_to_argb_u16(struct line_buffer *stage_buffer,
  * They are used in the `compose_active_planes` to convert and store a line
  * from the src_buffer to the writeback buffer.
  */
-static void argb_u16_to_ARGB8888(struct vkms_frame_info *frame_info,
-				 const struct line_buffer *src_buffer, int y)
+static void argb_u16_to_ARGB8888(u8 *dst_pixels, struct pixel_argb_u16 *in_pixel)
 {
-	int x_dst = frame_info->dst.x1;
-	u8 *dst_pixels = packed_pixels_addr(frame_info, x_dst, y);
-	struct pixel_argb_u16 *in_pixels = src_buffer->pixels;
-	int x_limit = min_t(size_t, drm_rect_width(&frame_info->dst),
-			    src_buffer->n_pixels);
-
-	for (size_t x = 0; x < x_limit; x++, dst_pixels += 4) {
-		/*
-		 * This sequence below is important because the format's byte order is
-		 * in little-endian. In the case of the ARGB8888 the memory is
-		 * organized this way:
-		 *
-		 * | Addr     | = blue channel
-		 * | Addr + 1 | = green channel
-		 * | Addr + 2 | = Red channel
-		 * | Addr + 3 | = Alpha channel
-		 */
-		dst_pixels[3] = DIV_ROUND_CLOSEST(in_pixels[x].a, 257);
-		dst_pixels[2] = DIV_ROUND_CLOSEST(in_pixels[x].r, 257);
-		dst_pixels[1] = DIV_ROUND_CLOSEST(in_pixels[x].g, 257);
-		dst_pixels[0] = DIV_ROUND_CLOSEST(in_pixels[x].b, 257);
-	}
+	/*
+	 * This sequence below is important because the format's byte order is
+	 * in little-endian. In the case of the ARGB8888 the memory is
+	 * organized this way:
+	 *
+	 * | Addr     | = blue channel
+	 * | Addr + 1 | = green channel
+	 * | Addr + 2 | = Red channel
+	 * | Addr + 3 | = Alpha channel
+	 */
+	dst_pixels[3] = DIV_ROUND_CLOSEST(in_pixel->a, 257);
+	dst_pixels[2] = DIV_ROUND_CLOSEST(in_pixel->r, 257);
+	dst_pixels[1] = DIV_ROUND_CLOSEST(in_pixel->g, 257);
+	dst_pixels[0] = DIV_ROUND_CLOSEST(in_pixel->b, 257);
 }
 
-static void argb_u16_to_XRGB8888(struct vkms_frame_info *frame_info,
-				 const struct line_buffer *src_buffer, int y)
+static void argb_u16_to_XRGB8888(u8 *dst_pixels, struct pixel_argb_u16 *in_pixel)
 {
-	int x_dst = frame_info->dst.x1;
-	u8 *dst_pixels = packed_pixels_addr(frame_info, x_dst, y);
-	struct pixel_argb_u16 *in_pixels = src_buffer->pixels;
-	int x_limit = min_t(size_t, drm_rect_width(&frame_info->dst),
-			    src_buffer->n_pixels);
-
-	for (size_t x = 0; x < x_limit; x++, dst_pixels += 4) {
-		dst_pixels[3] = 0xff;
-		dst_pixels[2] = DIV_ROUND_CLOSEST(in_pixels[x].r, 257);
-		dst_pixels[1] = DIV_ROUND_CLOSEST(in_pixels[x].g, 257);
-		dst_pixels[0] = DIV_ROUND_CLOSEST(in_pixels[x].b, 257);
-	}
+	dst_pixels[3] = 0xff;
+	dst_pixels[2] = DIV_ROUND_CLOSEST(in_pixel->r, 257);
+	dst_pixels[1] = DIV_ROUND_CLOSEST(in_pixel->g, 257);
+	dst_pixels[0] = DIV_ROUND_CLOSEST(in_pixel->b, 257);
 }
 
-static void argb_u16_to_ARGB16161616(struct vkms_frame_info *frame_info,
-				     const struct line_buffer *src_buffer, int y)
+static void argb_u16_to_ARGB16161616(u8 *dst_pixels, struct pixel_argb_u16 *in_pixel)
 {
-	int x_dst = frame_info->dst.x1;
-	u16 *dst_pixels = packed_pixels_addr(frame_info, x_dst, y);
-	struct pixel_argb_u16 *in_pixels = src_buffer->pixels;
-	int x_limit = min_t(size_t, drm_rect_width(&frame_info->dst),
-			    src_buffer->n_pixels);
-
-	for (size_t x = 0; x < x_limit; x++, dst_pixels += 4) {
-		dst_pixels[3] = cpu_to_le16(in_pixels[x].a);
-		dst_pixels[2] = cpu_to_le16(in_pixels[x].r);
-		dst_pixels[1] = cpu_to_le16(in_pixels[x].g);
-		dst_pixels[0] = cpu_to_le16(in_pixels[x].b);
-	}
+	u16 *pixels = (u16 *)dst_pixels;
+
+	pixels[3] = cpu_to_le16(in_pixel->a);
+	pixels[2] = cpu_to_le16(in_pixel->r);
+	pixels[1] = cpu_to_le16(in_pixel->g);
+	pixels[0] = cpu_to_le16(in_pixel->b);
 }
 
-static void argb_u16_to_XRGB16161616(struct vkms_frame_info *frame_info,
-				     const struct line_buffer *src_buffer, int y)
+static void argb_u16_to_XRGB16161616(u8 *dst_pixels, struct pixel_argb_u16 *in_pixel)
 {
-	int x_dst = frame_info->dst.x1;
-	u16 *dst_pixels = packed_pixels_addr(frame_info, x_dst, y);
-	struct pixel_argb_u16 *in_pixels = src_buffer->pixels;
-	int x_limit = min_t(size_t, drm_rect_width(&frame_info->dst),
-			    src_buffer->n_pixels);
-
-	for (size_t x = 0; x < x_limit; x++, dst_pixels += 4) {
-		dst_pixels[3] = 0xffff;
-		dst_pixels[2] = cpu_to_le16(in_pixels[x].r);
-		dst_pixels[1] = cpu_to_le16(in_pixels[x].g);
-		dst_pixels[0] = cpu_to_le16(in_pixels[x].b);
-	}
+	u16 *pixels = (u16 *)dst_pixels;
+
+	pixels[3] = 0xffff;
+	pixels[2] = cpu_to_le16(in_pixel->r);
+	pixels[1] = cpu_to_le16(in_pixel->g);
+	pixels[0] = cpu_to_le16(in_pixel->b);
 }
 
-static void argb_u16_to_RGB565(struct vkms_frame_info *frame_info,
-			       const struct line_buffer *src_buffer, int y)
+static void argb_u16_to_RGB565(u8 *dst_pixels, struct pixel_argb_u16 *in_pixel)
 {
-	int x_dst = frame_info->dst.x1;
-	u16 *dst_pixels = packed_pixels_addr(frame_info, x_dst, y);
-	struct pixel_argb_u16 *in_pixels = src_buffer->pixels;
-	int x_limit = min_t(size_t, drm_rect_width(&frame_info->dst),
-			    src_buffer->n_pixels);
+	u16 *pixels = (u16 *)dst_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++, dst_pixels++) {
-		s64 fp_r = drm_int2fixp(in_pixels[x].r);
-		s64 fp_g = drm_int2fixp(in_pixels[x].g);
-		s64 fp_b = drm_int2fixp(in_pixels[x].b);
+	s64 fp_r = drm_int2fixp(in_pixel->r);
+	s64 fp_g = drm_int2fixp(in_pixel->g);
+	s64 fp_b = drm_int2fixp(in_pixel->b);
 
-		u16 r = drm_fixp2int(drm_fixp_div(fp_r, fp_rb_ratio));
-		u16 g = drm_fixp2int(drm_fixp_div(fp_g, fp_g_ratio));
-		u16 b = drm_fixp2int(drm_fixp_div(fp_b, fp_rb_ratio));
+	u16 r = drm_fixp2int(drm_fixp_div(fp_r, fp_rb_ratio));
+	u16 g = drm_fixp2int(drm_fixp_div(fp_g, fp_g_ratio));
+	u16 b = drm_fixp2int(drm_fixp_div(fp_b, fp_rb_ratio));
 
-		*dst_pixels = cpu_to_le16(r << 11 | g << 5 | b);
-	}
+	*pixels = cpu_to_le16(r << 11 | g << 5 | b);
+}
+
+void vkms_writeback_row(struct vkms_writeback_job *wb,
+			const struct line_buffer *src_buffer, int y)
+{
+	struct vkms_frame_info *frame_info = &wb->wb_frame_info;
+	int x_dst = frame_info->dst.x1;
+	u8 *dst_pixels = packed_pixels_addr(frame_info, x_dst, y);
+	struct pixel_argb_u16 *in_pixels = src_buffer->pixels;
+	int x_limit = min_t(size_t, drm_rect_width(&frame_info->dst), src_buffer->n_pixels);
+
+	for (size_t x = 0; x < x_limit; x++, dst_pixels += frame_info->cpp)
+		wb->pixel_write(dst_pixels, &in_pixels[x]);
 }
 
-void *get_frame_to_line_function(u32 format)
+void *get_pixel_conversion_function(u32 format)
 {
 	switch (format) {
 	case DRM_FORMAT_ARGB8888:
@@ -267,7 +245,7 @@ void *get_frame_to_line_function(u32 format)
 	}
 }
 
-void *get_line_to_frame_function(u32 format)
+void *get_pixel_write_function(u32 format)
 {
 	switch (format) {
 	case DRM_FORMAT_ARGB8888: