7 files changed, 524 insertions, 217 deletions

diff --git a/drivers/gpu/drm/vkms/Makefile b/drivers/gpu/drm/vkms/Makefile
index 72f779cbfedd..1b28a6a32948 100644
--- a/drivers/gpu/drm/vkms/Makefile
+++ b/drivers/gpu/drm/vkms/Makefile
@@ -3,6 +3,7 @@ vkms-y := \
 	vkms_drv.o \
 	vkms_plane.o \
 	vkms_output.o \
+	vkms_formats.o \
 	vkms_crtc.o \
 	vkms_composer.o \
 	vkms_writeback.o
diff --git a/drivers/gpu/drm/vkms/vkms_composer.c b/drivers/gpu/drm/vkms/vkms_composer.c
index 775b97766e08..8e53fa80742b 100644
--- a/drivers/gpu/drm/vkms/vkms_composer.c
+++ b/drivers/gpu/drm/vkms/vkms_composer.c
@@ -7,203 +7,185 @@
 #include <drm/drm_fourcc.h>
 #include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_vblank.h>
+#include <linux/minmax.h>
 
 #include "vkms_drv.h"
 
-static u32 get_pixel_from_buffer(int x, int y, const u8 *buffer,
-				 const struct vkms_composer *composer)
+static u16 pre_mul_blend_channel(u16 src, u16 dst, u16 alpha)
 {
-	u32 pixel;
-	int src_offset = composer->offset + (y * composer->pitch)
-				      + (x * composer->cpp);
+	u32 new_color;
 
-	pixel = *(u32 *)&buffer[src_offset];
+	new_color = (src * 0xffff + dst * (0xffff - alpha));
 
-	return pixel;
+	return DIV_ROUND_CLOSEST(new_color, 0xffff);
 }
 
 /**
- * compute_crc - Compute CRC value on output frame
+ * pre_mul_alpha_blend - alpha blending equation
+ * @src_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
  *
- * @vaddr: address to final framebuffer
- * @composer: framebuffer's metadata
+ * 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.
  *
- * returns CRC value computed using crc32 on the visible portion of
- * the final framebuffer at vaddr_out
+ * 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 uint32_t compute_crc(const u8 *vaddr,
-			    const struct vkms_composer *composer)
+static void pre_mul_alpha_blend(struct vkms_frame_info *frame_info,
+				struct line_buffer *stage_buffer,
+				struct line_buffer *output_buffer)
 {
-	int x, y;
-	u32 crc = 0, pixel = 0;
-	int x_src = composer->src.x1 >> 16;
-	int y_src = composer->src.y1 >> 16;
-	int h_src = drm_rect_height(&composer->src) >> 16;
-	int w_src = drm_rect_width(&composer->src) >> 16;
-
-	for (y = y_src; y < y_src + h_src; ++y) {
-		for (x = x_src; x < x_src + w_src; ++x) {
-			pixel = get_pixel_from_buffer(x, y, vaddr, composer);
-			crc = crc32_le(crc, (void *)&pixel, sizeof(u32));
-		}
+	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);
 	}
-
-	return crc;
 }
 
-static u8 blend_channel(u8 src, u8 dst, u8 alpha)
+static bool check_y_limit(struct vkms_frame_info *frame_info, int y)
 {
-	u32 pre_blend;
-	u8 new_color;
-
-	pre_blend = (src * 255 + dst * (255 - alpha));
-
-	/* Faster div by 255 */
-	new_color = ((pre_blend + ((pre_blend + 257) >> 8)) >> 8);
+	if (y >= frame_info->dst.y1 && y < frame_info->dst.y2)
+		return true;
 
-	return new_color;
+	return false;
 }
 
-/**
- * alpha_blend - alpha blending equation
- * @argb_src: src pixel on premultiplied alpha mode
- * @argb_dst: dst pixel completely opaque
- *
- * blend pixels using premultiplied blend formula. 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 alpha_blend(const u8 *argb_src, u8 *argb_dst)
+static void fill_background(const struct pixel_argb_u16 *background_color,
+			    struct line_buffer *output_buffer)
 {
-	u8 alpha;
-
-	alpha = argb_src[3];
-	argb_dst[0] = blend_channel(argb_src[0], argb_dst[0], alpha);
-	argb_dst[1] = blend_channel(argb_src[1], argb_dst[1], alpha);
-	argb_dst[2] = blend_channel(argb_src[2], argb_dst[2], alpha);
+	for (size_t i = 0; i < output_buffer->n_pixels; i++)
+		output_buffer->pixels[i] = *background_color;
 }
 
 /**
- * x_blend - blending equation that ignores the pixel alpha
+ * @wb_frame_info: The writeback frame buffer metadata
+ * @crtc_state: The crtc state
+ * @crc32: The crc output of the final frame
+ * @output_buffer: A buffer of a row that will receive the result of the blend(s)
+ * @stage_buffer: The line with the pixels from plane being blend to the output
  *
- * overwrites RGB color value from src pixel to dst pixel.
+ * This function blends the pixels (Using the `pre_mul_alpha_blend`)
+ * from all planes, calculates the crc32 of the output from the former step,
+ * and, if necessary, convert and store the output to the writeback buffer.
  */
-static void x_blend(const u8 *xrgb_src, u8 *xrgb_dst)
+static void blend(struct vkms_writeback_job *wb,
+		  struct vkms_crtc_state *crtc_state,
+		  u32 *crc32, struct line_buffer *stage_buffer,
+		  struct line_buffer *output_buffer, size_t row_size)
 {
-	memcpy(xrgb_dst, xrgb_src, sizeof(u8) * 3);
-}
+	struct vkms_plane_state **plane = crtc_state->active_planes;
+	u32 n_active_planes = crtc_state->num_active_planes;
 
-/**
- * blend - blend value at vaddr_src with value at vaddr_dst
- * @vaddr_dst: destination address
- * @vaddr_src: source address
- * @dst_composer: destination framebuffer's metadata
- * @src_composer: source framebuffer's metadata
- * @pixel_blend: blending equation based on plane format
- *
- * Blend the vaddr_src value with the vaddr_dst value using a pixel blend
- * equation according to the supported plane formats DRM_FORMAT_(A/XRGB8888)
- * and clearing alpha channel to an completely opaque background. This function
- * uses buffer's metadata to locate the new composite values at vaddr_dst.
- *
- * TODO: completely clear the primary plane (a = 0xff) before starting to blend
- * pixel color values
- */
-static void blend(void *vaddr_dst, void *vaddr_src,
-		  struct vkms_composer *dst_composer,
-		  struct vkms_composer *src_composer,
-		  void (*pixel_blend)(const u8 *, u8 *))
-{
-	int i, j, j_dst, i_dst;
-	int offset_src, offset_dst;
-	u8 *pixel_dst, *pixel_src;
-
-	int x_src = src_composer->src.x1 >> 16;
-	int y_src = src_composer->src.y1 >> 16;
-
-	int x_dst = src_composer->dst.x1;
-	int y_dst = src_composer->dst.y1;
-	int h_dst = drm_rect_height(&src_composer->dst);
-	int w_dst = drm_rect_width(&src_composer->dst);
-
-	int y_limit = y_src + h_dst;
-	int x_limit = x_src + w_dst;
-
-	for (i = y_src, i_dst = y_dst; i < y_limit; ++i) {
-		for (j = x_src, j_dst = x_dst; j < x_limit; ++j) {
-			offset_dst = dst_composer->offset
-				     + (i_dst * dst_composer->pitch)
-				     + (j_dst++ * dst_composer->cpp);
-			offset_src = src_composer->offset
-				     + (i * src_composer->pitch)
-				     + (j * src_composer->cpp);
-
-			pixel_src = (u8 *)(vaddr_src + offset_src);
-			pixel_dst = (u8 *)(vaddr_dst + offset_dst);
-			pixel_blend(pixel_src, pixel_dst);
-			/* clearing alpha channel (0xff)*/
-			pixel_dst[3] = 0xff;
+	const struct pixel_argb_u16 background_color = { .a = 0xffff };
+
+	size_t crtc_y_limit = crtc_state->base.crtc->mode.vdisplay;
+
+	for (size_t y = 0; y < crtc_y_limit; y++) {
+		fill_background(&background_color, output_buffer);
+
+		/* The active planes are composed associatively in z-order. */
+		for (size_t i = 0; i < n_active_planes; i++) {
+			if (!check_y_limit(plane[i]->frame_info, y))
+				continue;
+
+			plane[i]->plane_read(stage_buffer, plane[i]->frame_info, y);
+			pre_mul_alpha_blend(plane[i]->frame_info, stage_buffer,
+					    output_buffer);
 		}
-		i_dst++;
+
+		*crc32 = crc32_le(*crc32, (void *)output_buffer->pixels, row_size);
+
+		if (wb)
+			wb->wb_write(&wb->wb_frame_info, output_buffer, y);
 	}
 }
 
-static void compose_plane(struct vkms_composer *primary_composer,
-			  struct vkms_composer *plane_composer,
-			  void *vaddr_out)
+static int check_format_funcs(struct vkms_crtc_state *crtc_state,
+			      struct vkms_writeback_job *active_wb)
 {
-	struct drm_framebuffer *fb = &plane_composer->fb;
-	void *vaddr;
-	void (*pixel_blend)(const u8 *p_src, u8 *p_dst);
+	struct vkms_plane_state **planes = crtc_state->active_planes;
+	u32 n_active_planes = crtc_state->num_active_planes;
 
-	if (WARN_ON(iosys_map_is_null(&plane_composer->map[0])))
-		return;
+	for (size_t i = 0; i < n_active_planes; i++)
+		if (!planes[i]->plane_read)
+			return -1;
 
-	vaddr = plane_composer->map[0].vaddr;
+	if (active_wb && !active_wb->wb_write)
+		return -1;
 
-	if (fb->format->format == DRM_FORMAT_ARGB8888)
-		pixel_blend = &alpha_blend;
-	else
-		pixel_blend = &x_blend;
+	return 0;
+}
+
+static int check_iosys_map(struct vkms_crtc_state *crtc_state)
+{
+	struct vkms_plane_state **plane_state = crtc_state->active_planes;
+	u32 n_active_planes = crtc_state->num_active_planes;
+
+	for (size_t i = 0; i < n_active_planes; i++)
+		if (iosys_map_is_null(&plane_state[i]->frame_info->map[0]))
+			return -1;
 
-	blend(vaddr_out, vaddr, primary_composer, plane_composer, pixel_blend);
+	return 0;
 }
 
-static int compose_active_planes(void **vaddr_out,
-				 struct vkms_composer *primary_composer,
-				 struct vkms_crtc_state *crtc_state)
+static int compose_active_planes(struct vkms_writeback_job *active_wb,
+				 struct vkms_crtc_state *crtc_state,
+				 u32 *crc32)
 {
-	struct drm_framebuffer *fb = &primary_composer->fb;
-	struct drm_gem_object *gem_obj = drm_gem_fb_get_obj(fb, 0);
-	const void *vaddr;
-	int i;
-
-	if (!*vaddr_out) {
-		*vaddr_out = kvzalloc(gem_obj->size, GFP_KERNEL);
-		if (!*vaddr_out) {
-			DRM_ERROR("Cannot allocate memory for output frame.");
-			return -ENOMEM;
-		}
-	}
+	size_t line_width, pixel_size = sizeof(struct pixel_argb_u16);
+	struct line_buffer output_buffer, stage_buffer;
+	int ret = 0;
+
+	/*
+	 * This check exists so we can call `crc32_le` for the entire line
+	 * instead doing it for each channel of each pixel in case
+	 * `struct `pixel_argb_u16` had any gap added by the compiler
+	 * between the struct fields.
+	 */
+	static_assert(sizeof(struct pixel_argb_u16) == 8);
 
-	if (WARN_ON(iosys_map_is_null(&primary_composer->map[0])))
+	if (WARN_ON(check_iosys_map(crtc_state)))
 		return -EINVAL;
 
-	vaddr = primary_composer->map[0].vaddr;
+	if (WARN_ON(check_format_funcs(crtc_state, active_wb)))
+		return -EINVAL;
 
-	memcpy(*vaddr_out, vaddr, gem_obj->size);
+	line_width = crtc_state->base.crtc->mode.hdisplay;
+	stage_buffer.n_pixels = line_width;
+	output_buffer.n_pixels = line_width;
 
-	/* If there are other planes besides primary, we consider the active
-	 * planes should be in z-order and compose them associatively:
-	 * ((primary <- overlay) <- cursor)
-	 */
-	for (i = 1; i < crtc_state->num_active_planes; i++)
-		compose_plane(primary_composer,
-			      crtc_state->active_planes[i]->composer,
-			      *vaddr_out);
+	stage_buffer.pixels = kvmalloc(line_width * pixel_size, GFP_KERNEL);
+	if (!stage_buffer.pixels) {
+		DRM_ERROR("Cannot allocate memory for the output line buffer");
+		return -ENOMEM;
+	}
 
-	return 0;
+	output_buffer.pixels = kvmalloc(line_width * pixel_size, GFP_KERNEL);
+	if (!output_buffer.pixels) {
+		DRM_ERROR("Cannot allocate memory for intermediate line buffer");
+		ret = -ENOMEM;
+		goto free_stage_buffer;
+	}
+
+	blend(active_wb, crtc_state, crc32, &stage_buffer,
+	      &output_buffer, line_width * pixel_size);
+
+	kvfree(output_buffer.pixels);
+free_stage_buffer:
+	kvfree(stage_buffer.pixels);
+
+	return ret;
 }
 
 /**
@@ -221,13 +203,11 @@ void vkms_composer_worker(struct work_struct *work)
 						struct vkms_crtc_state,
 						composer_work);
 	struct drm_crtc *crtc = crtc_state->base.crtc;
+	struct vkms_writeback_job *active_wb = crtc_state->active_writeback;
 	struct vkms_output *out = drm_crtc_to_vkms_output(crtc);
-	struct vkms_composer *primary_composer = NULL;
-	struct vkms_plane_state *act_plane = NULL;
 	bool crc_pending, wb_pending;
-	void *vaddr_out = NULL;
-	u32 crc32 = 0;
 	u64 frame_start, frame_end;
+	u32 crc32 = 0;
 	int ret;
 
 	spin_lock_irq(&out->composer_lock);
@@ -247,35 +227,19 @@ void vkms_composer_worker(struct work_struct *work)
 	if (!crc_pending)
 		return;
 
-	if (crtc_state->num_active_planes >= 1) {
-		act_plane = crtc_state->active_planes[0];
-		if (act_plane->base.base.plane->type == DRM_PLANE_TYPE_PRIMARY)
-			primary_composer = act_plane->composer;
-	}
-
-	if (!primary_composer)
-		return;
-
 	if (wb_pending)
-		vaddr_out = crtc_state->active_writeback->data[0].vaddr;
+		ret = compose_active_planes(active_wb, crtc_state, &crc32);
+	else
+		ret = compose_active_planes(NULL, crtc_state, &crc32);
 
-	ret = compose_active_planes(&vaddr_out, primary_composer,
-				    crtc_state);
-	if (ret) {
-		if (ret == -EINVAL && !wb_pending)
-			kvfree(vaddr_out);
+	if (ret)
 		return;
-	}
-
-	crc32 = compute_crc(vaddr_out, primary_composer);
 
 	if (wb_pending) {
 		drm_writeback_signal_completion(&out->wb_connector, 0);
 		spin_lock_irq(&out->composer_lock);
 		crtc_state->wb_pending = false;
 		spin_unlock_irq(&out->composer_lock);
-	} else {
-		kvfree(vaddr_out);
 	}
 
 	/*
diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h
index 1d60654b553b..0a67b8073f7e 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.h
+++ b/drivers/gpu/drm/vkms/vkms_drv.h
@@ -23,28 +23,41 @@
 
 #define NUM_OVERLAY_PLANES 8
 
-struct vkms_writeback_job {
-	struct iosys_map map[DRM_FORMAT_MAX_PLANES];
-	struct iosys_map data[DRM_FORMAT_MAX_PLANES];
-};
-
-struct vkms_composer {
-	struct drm_framebuffer fb;
+struct vkms_frame_info {
+	struct drm_framebuffer *fb;
 	struct drm_rect src, dst;
-	struct iosys_map map[4];
+	struct iosys_map map[DRM_FORMAT_MAX_PLANES];
 	unsigned int offset;
 	unsigned int pitch;
 	unsigned int cpp;
 };
 
+struct pixel_argb_u16 {
+	u16 a, r, g, b;
+};
+
+struct line_buffer {
+	size_t n_pixels;
+	struct pixel_argb_u16 *pixels;
+};
+
+struct vkms_writeback_job {
+	struct iosys_map data[DRM_FORMAT_MAX_PLANES];
+	struct vkms_frame_info wb_frame_info;
+	void (*wb_write)(struct vkms_frame_info *frame_info,
+			 const struct line_buffer *buffer, int y);
+};
+
 /**
  * vkms_plane_state - Driver specific plane state
  * @base: base plane state
- * @composer: data required for composing computation
+ * @frame_info: data required for composing computation
  */
 struct vkms_plane_state {
 	struct drm_shadow_plane_state base;
-	struct vkms_composer *composer;
+	struct vkms_frame_info *frame_info;
+	void (*plane_read)(struct line_buffer *buffer,
+			   const struct vkms_frame_info *frame_info, int y);
 };
 
 struct vkms_plane {
diff --git a/drivers/gpu/drm/vkms/vkms_formats.c b/drivers/gpu/drm/vkms/vkms_formats.c
new file mode 100644
index 000000000000..d4950688b3f1
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_formats.c
@@ -0,0 +1,286 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#include <linux/kernel.h>
+#include <linux/minmax.h>
+#include <drm/drm_rect.h>
+#include <drm/drm_fixed.h>
+
+#include "vkms_formats.h"
+
+static size_t pixel_offset(const struct vkms_frame_info *frame_info, int x, int y)
+{
+	return frame_info->offset + (y * frame_info->pitch)
+				  + (x * frame_info->cpp);
+}
+
+/*
+ * packed_pixels_addr - Get the pointer to pixel of a given pair of coordinates
+ *
+ * @frame_info: Buffer metadata
+ * @x: The x(width) coordinate of the 2D buffer
+ * @y: The y(Heigth) coordinate of the 2D buffer
+ *
+ * Takes the information stored in the frame_info, a pair of coordinates, and
+ * returns the address of the first color channel.
+ * This function assumes the channels are packed together, i.e. a color channel
+ * comes immediately after another in the memory. And therefore, this function
+ * doesn't work for YUV with chroma subsampling (e.g. YUV420 and NV21).
+ */
+static void *packed_pixels_addr(const struct vkms_frame_info *frame_info,
+				int x, int y)
+{
+	size_t offset = pixel_offset(frame_info, x, y);
+
+	return (u8 *)frame_info->map[0].vaddr + offset;
+}
+
+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);
+
+	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)
+{
+	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;
+	}
+}
+
+static void XRGB8888_to_argb_u16(struct line_buffer *stage_buffer,
+				 const struct vkms_frame_info *frame_info, int y)
+{
+	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;
+	}
+}
+
+static void ARGB16161616_to_argb_u16(struct line_buffer *stage_buffer,
+				     const struct vkms_frame_info *frame_info,
+				     int y)
+{
+	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]);
+	}
+}
+
+static void XRGB16161616_to_argb_u16(struct line_buffer *stage_buffer,
+				     const struct vkms_frame_info *frame_info,
+				     int y)
+{
+	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]);
+	}
+}
+
+static void RGB565_to_argb_u16(struct line_buffer *stage_buffer,
+			       const struct vkms_frame_info *frame_info, int y)
+{
+	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);
+
+	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);
+
+		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));
+	}
+}
+
+/*
+ * The following  functions take an line of argb_u16 pixels from the
+ * src_buffer, convert them to a specific format, and store them in the
+ * destination.
+ *
+ * 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)
+{
+	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);
+	}
+}
+
+static void argb_u16_to_XRGB8888(struct vkms_frame_info *frame_info,
+				 const struct line_buffer *src_buffer, int y)
+{
+	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);
+	}
+}
+
+static void argb_u16_to_ARGB16161616(struct vkms_frame_info *frame_info,
+				     const struct line_buffer *src_buffer, int y)
+{
+	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);
+	}
+}
+
+static void argb_u16_to_XRGB16161616(struct vkms_frame_info *frame_info,
+				     const struct line_buffer *src_buffer, int y)
+{
+	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);
+	}
+}
+
+static void argb_u16_to_RGB565(struct vkms_frame_info *frame_info,
+			       const struct line_buffer *src_buffer, int y)
+{
+	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);
+
+	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);
+
+		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);
+	}
+}
+
+void *get_frame_to_line_function(u32 format)
+{
+	switch (format) {
+	case DRM_FORMAT_ARGB8888:
+		return &ARGB8888_to_argb_u16;
+	case DRM_FORMAT_XRGB8888:
+		return &XRGB8888_to_argb_u16;
+	case DRM_FORMAT_ARGB16161616:
+		return &ARGB16161616_to_argb_u16;
+	case DRM_FORMAT_XRGB16161616:
+		return &XRGB16161616_to_argb_u16;
+	case DRM_FORMAT_RGB565:
+		return &RGB565_to_argb_u16;
+	default:
+		return NULL;
+	}
+}
+
+void *get_line_to_frame_function(u32 format)
+{
+	switch (format) {
+	case DRM_FORMAT_ARGB8888:
+		return &argb_u16_to_ARGB8888;
+	case DRM_FORMAT_XRGB8888:
+		return &argb_u16_to_XRGB8888;
+	case DRM_FORMAT_ARGB16161616:
+		return &argb_u16_to_ARGB16161616;
+	case DRM_FORMAT_XRGB16161616:
+		return &argb_u16_to_XRGB16161616;
+	case DRM_FORMAT_RGB565:
+		return &argb_u16_to_RGB565;
+	default:
+		return NULL;
+	}
+}
diff --git a/drivers/gpu/drm/vkms/vkms_formats.h b/drivers/gpu/drm/vkms/vkms_formats.h
new file mode 100644
index 000000000000..43b7c1979018
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_formats.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _VKMS_FORMATS_H_
+#define _VKMS_FORMATS_H_
+
+#include "vkms_drv.h"
+
+void *get_frame_to_line_function(u32 format);
+
+void *get_line_to_frame_function(u32 format);
+
+#endif /* _VKMS_FORMATS_H_ */
diff --git a/drivers/gpu/drm/vkms/vkms_plane.c b/drivers/gpu/drm/vkms/vkms_plane.c
index d8eb674b49a6..c3a845220e10 100644
--- a/drivers/gpu/drm/vkms/vkms_plane.c
+++ b/drivers/gpu/drm/vkms/vkms_plane.c
@@ -7,37 +7,42 @@
 #include <drm/drm_fourcc.h>
 #include <drm/drm_gem_atomic_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
-#include <drm/drm_plane_helper.h>
 
 #include "vkms_drv.h"
+#include "vkms_formats.h"
 
 static const u32 vkms_formats[] = {
 	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_XRGB16161616,
+	DRM_FORMAT_RGB565
 };
 
 static const u32 vkms_plane_formats[] = {
 	DRM_FORMAT_ARGB8888,
-	DRM_FORMAT_XRGB8888
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_XRGB16161616,
+	DRM_FORMAT_ARGB16161616,
+	DRM_FORMAT_RGB565
 };
 
 static struct drm_plane_state *
 vkms_plane_duplicate_state(struct drm_plane *plane)
 {
 	struct vkms_plane_state *vkms_state;
-	struct vkms_composer *composer;
+	struct vkms_frame_info *frame_info;
 
 	vkms_state = kzalloc(sizeof(*vkms_state), GFP_KERNEL);
 	if (!vkms_state)
 		return NULL;
 
-	composer = kzalloc(sizeof(*composer), GFP_KERNEL);
-	if (!composer) {
-		DRM_DEBUG_KMS("Couldn't allocate composer\n");
+	frame_info = kzalloc(sizeof(*frame_info), GFP_KERNEL);
+	if (!frame_info) {
+		DRM_DEBUG_KMS("Couldn't allocate frame_info\n");
 		kfree(vkms_state);
 		return NULL;
 	}
 
-	vkms_state->composer = composer;
+	vkms_state->frame_info = frame_info;
 
 	__drm_gem_duplicate_shadow_plane_state(plane, &vkms_state->base);
 
@@ -50,16 +55,16 @@ static void vkms_plane_destroy_state(struct drm_plane *plane,
 	struct vkms_plane_state *vkms_state = to_vkms_plane_state(old_state);
 	struct drm_crtc *crtc = vkms_state->base.base.crtc;
 
-	if (crtc) {
+	if (crtc && vkms_state->frame_info->fb) {
 		/* dropping the reference we acquired in
 		 * vkms_primary_plane_update()
 		 */
-		if (drm_framebuffer_read_refcount(&vkms_state->composer->fb))
-			drm_framebuffer_put(&vkms_state->composer->fb);
+		if (drm_framebuffer_read_refcount(vkms_state->frame_info->fb))
+			drm_framebuffer_put(vkms_state->frame_info->fb);
 	}
 
-	kfree(vkms_state->composer);
-	vkms_state->composer = NULL;
+	kfree(vkms_state->frame_info);
+	vkms_state->frame_info = NULL;
 
 	__drm_gem_destroy_shadow_plane_state(&vkms_state->base);
 	kfree(vkms_state);
@@ -99,23 +104,26 @@ static void vkms_plane_atomic_update(struct drm_plane *plane,
 	struct vkms_plane_state *vkms_plane_state;
 	struct drm_shadow_plane_state *shadow_plane_state;
 	struct drm_framebuffer *fb = new_state->fb;
-	struct vkms_composer *composer;
+	struct vkms_frame_info *frame_info;
+	u32 fmt;
 
 	if (!new_state->crtc || !fb)
 		return;
 
+	fmt = fb->format->format;
 	vkms_plane_state = to_vkms_plane_state(new_state);
 	shadow_plane_state = &vkms_plane_state->base;
 
-	composer = vkms_plane_state->composer;
-	memcpy(&composer->src, &new_state->src, sizeof(struct drm_rect));
-	memcpy(&composer->dst, &new_state->dst, sizeof(struct drm_rect));
-	memcpy(&composer->fb, fb, sizeof(struct drm_framebuffer));
-	memcpy(&composer->map, &shadow_plane_state->data, sizeof(composer->map));
-	drm_framebuffer_get(&composer->fb);
-	composer->offset = fb->offsets[0];
-	composer->pitch = fb->pitches[0];
-	composer->cpp = fb->format->cpp[0];
+	frame_info = vkms_plane_state->frame_info;
+	memcpy(&frame_info->src, &new_state->src, sizeof(struct drm_rect));
+	memcpy(&frame_info->dst, &new_state->dst, sizeof(struct drm_rect));
+	frame_info->fb = fb;
+	memcpy(&frame_info->map, &shadow_plane_state->data, sizeof(frame_info->map));
+	drm_framebuffer_get(frame_info->fb);
+	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);
 }
 
 static int vkms_plane_atomic_check(struct drm_plane *plane,
@@ -139,8 +147,8 @@ static int vkms_plane_atomic_check(struct drm_plane *plane,
 		can_position = true;
 
 	ret = drm_atomic_helper_check_plane_state(new_plane_state, crtc_state,
-						  DRM_PLANE_HELPER_NO_SCALING,
-						  DRM_PLANE_HELPER_NO_SCALING,
+						  DRM_PLANE_NO_SCALING,
+						  DRM_PLANE_NO_SCALING,
 						  can_position, true);
 	if (ret != 0)
 		return ret;
diff --git a/drivers/gpu/drm/vkms/vkms_writeback.c b/drivers/gpu/drm/vkms/vkms_writeback.c
index 3b3c1e757ab4..84a51cd281b9 100644
--- a/drivers/gpu/drm/vkms/vkms_writeback.c
+++ b/drivers/gpu/drm/vkms/vkms_writeback.c
@@ -12,9 +12,13 @@
 #include <drm/drm_gem_shmem_helper.h>
 
 #include "vkms_drv.h"
+#include "vkms_formats.h"
 
 static const u32 vkms_wb_formats[] = {
 	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_XRGB16161616,
+	DRM_FORMAT_ARGB16161616,
+	DRM_FORMAT_RGB565
 };
 
 static const struct drm_connector_funcs vkms_wb_connector_funcs = {
@@ -31,6 +35,7 @@ static int vkms_wb_encoder_atomic_check(struct drm_encoder *encoder,
 {
 	struct drm_framebuffer *fb;
 	const struct drm_display_mode *mode = &crtc_state->mode;
+	int ret;
 
 	if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
 		return 0;
@@ -42,11 +47,9 @@ static int vkms_wb_encoder_atomic_check(struct drm_encoder *encoder,
 		return -EINVAL;
 	}
 
-	if (fb->format->format != vkms_wb_formats[0]) {
-		DRM_DEBUG_KMS("Invalid pixel format %p4cc\n",
-			      &fb->format->format);
-		return -EINVAL;
-	}
+	ret = drm_atomic_helper_check_wb_encoder_state(encoder, conn_state);
+	if (ret < 0)
+		return ret;
 
 	return 0;
 }
@@ -76,12 +79,15 @@ static int vkms_wb_prepare_job(struct drm_writeback_connector *wb_connector,
 	if (!vkmsjob)
 		return -ENOMEM;
 
-	ret = drm_gem_fb_vmap(job->fb, vkmsjob->map, vkmsjob->data);
+	ret = drm_gem_fb_vmap(job->fb, vkmsjob->wb_frame_info.map, vkmsjob->data);
 	if (ret) {
 		DRM_ERROR("vmap failed: %d\n", ret);
 		goto err_kfree;
 	}
 
+	vkmsjob->wb_frame_info.fb = job->fb;
+	drm_framebuffer_get(vkmsjob->wb_frame_info.fb);
+
 	job->priv = vkmsjob;
 
 	return 0;
@@ -100,7 +106,9 @@ static void vkms_wb_cleanup_job(struct drm_writeback_connector *connector,
 	if (!job->fb)
 		return;
 
-	drm_gem_fb_vunmap(job->fb, vkmsjob->map);
+	drm_gem_fb_vunmap(job->fb, vkmsjob->wb_frame_info.map);
+
+	drm_framebuffer_put(vkmsjob->wb_frame_info.fb);
 
 	vkmsdev = drm_device_to_vkms_device(job->fb->dev);
 	vkms_set_composer(&vkmsdev->output, false);
@@ -117,17 +125,32 @@ static void vkms_wb_atomic_commit(struct drm_connector *conn,
 	struct drm_writeback_connector *wb_conn = &output->wb_connector;
 	struct drm_connector_state *conn_state = wb_conn->base.state;
 	struct vkms_crtc_state *crtc_state = output->composer_state;
+	struct drm_framebuffer *fb = connector_state->writeback_job->fb;
+	u16 crtc_height = crtc_state->base.crtc->mode.vdisplay;
+	u16 crtc_width = crtc_state->base.crtc->mode.hdisplay;
+	struct vkms_writeback_job *active_wb;
+	struct vkms_frame_info *wb_frame_info;
+	u32 wb_format = fb->format->format;
 
 	if (!conn_state)
 		return;
 
 	vkms_set_composer(&vkmsdev->output, true);
 
+	active_wb = conn_state->writeback_job->priv;
+	wb_frame_info = &active_wb->wb_frame_info;
+
 	spin_lock_irq(&output->composer_lock);
-	crtc_state->active_writeback = conn_state->writeback_job->priv;
+	crtc_state->active_writeback = active_wb;
+	wb_frame_info->offset = fb->offsets[0];
+	wb_frame_info->pitch = fb->pitches[0];
+	wb_frame_info->cpp = fb->format->cpp[0];
 	crtc_state->wb_pending = true;
 	spin_unlock_irq(&output->composer_lock);
 	drm_writeback_queue_job(wb_conn, connector_state);
+	active_wb->wb_write = get_line_to_frame_function(wb_format);
+	drm_rect_init(&wb_frame_info->src, 0, 0, crtc_width, crtc_height);
+	drm_rect_init(&wb_frame_info->dst, 0, 0, crtc_width, crtc_height);
 }
 
 static const struct drm_connector_helper_funcs vkms_wb_conn_helper_funcs = {