Merge tag 'drm-misc-next-2023-07-13' of git://anongit.freedesktop.org/drm/drm-misc into drm-next

drm-misc-next for v6.6:

UAPI Changes:

 * fbdev:
   * Make fbdev userspace interfaces optional; only leaves the
     framebuffer console active

 * prime:
   * Support dma-buf self-import for all drivers automatically: improves
     support for many userspace compositors

Cross-subsystem Changes:

 * backlight:
   * Fix interaction with fbdev in several drivers

 * base: Convert struct platform.remove to return void; part of a larger,
   tree-wide effort

 * dma-buf: Acquire reservation lock for mmap() in exporters; part
   of an on-going effort to simplify locking around dma-bufs

 * fbdev:
   * Use Linux device instead of fbdev device in many places
   * Use deferred-I/O helper macros in various drivers

 * i2c: Convert struct i2c from .probe_new to .probe; part of a larger,
   tree-wide effort

 * video:
   * Avoid including <linux/screen_info.h>

Core Changes:

 * atomic:
   * Improve logging

 * prime:
   * Remove struct drm_driver.gem_prime_mmap plus driver updates: all
     drivers now implement this callback with drm_gem_prime_mmap()

 * gem:
   * Support execution contexts: provides locking over multiple GEM
     objects

 * ttm:
   * Support init_on_free
   * Swapout fixes

Driver Changes:

 * accel:
   * ivpu: MMU updates; Support debugfs

 * ast:
   * Improve device-model detection
   * Cleanups

 * bridge:
   * dw-hdmi: Improve support for YUV420 bus format
   * dw-mipi-dsi: Fix enable/disable of DSI controller
   * lt9611uxc: Use MODULE_FIRMWARE()
   * ps8640: Remove broken EDID code
   * samsung-dsim: Fix command transfer
   * tc358764: Handle HS/VS polarity; Use BIT() macro; Various cleanups
   * Cleanups

 * ingenic:
   * Kconfig REGMAP fixes

 * loongson:
   * Support display controller

 * mgag200:
   * Minor fixes

 * mxsfb:
   * Support disabling overlay planes

 * nouveau:
   * Improve VRAM detection
   * Various fixes and cleanups

 * panel:
   * panel-edp: Support AUO B116XAB01.4
   * Support Visionox R66451 plus DT bindings
   * Cleanups

 * ssd130x:
   * Support per-controller default resolution plus DT bindings
   * Reduce memory-allocation overhead
   * Cleanups

 * tidss:
   * Support TI AM625 plus DT bindings
   * Implement new connector model plus driver updates

 * vkms
   * Improve write-back support
   * Documentation fixes

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
From: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20230713090830.GA23281@linux-uq9g

1 files changed, 70 insertions, 83 deletions

diff --git a/drivers/gpu/drm/vkms/vkms_formats.c b/drivers/gpu/drm/vkms/vkms_formats.c
index 5945da0beba6..36046b12f296 100644
--- a/drivers/gpu/drm/vkms/vkms_formats.c
+++ b/drivers/gpu/drm/vkms/vkms_formats.c
@@ -111,6 +111,19 @@ static void RGB565_to_argb_u16(u8 *src_pixels, struct pixel_argb_u16 *out_pixel)
 	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;
@@ -137,107 +150,81 @@ void vkms_compose_row(struct line_buffer *stage_buffer, struct vkms_plane_state
  * 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_round(drm_fixp_div(fp_r, fp_rb_ratio));
-		u16 g = drm_fixp2int_round(drm_fixp_div(fp_g, fp_g_ratio));
-		u16 b = drm_fixp2int_round(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_pixel_conversion_function(u32 format)
@@ -258,7 +245,7 @@ void *get_pixel_conversion_function(u32 format)
 	}
 }
 
-void *get_line_to_frame_function(u32 format)
+void *get_pixel_write_function(u32 format)
 {
 	switch (format) {
 	case DRM_FORMAT_ARGB8888: