1 files changed, 139 insertions, 175 deletions

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);
 	}
 
 	/*