1 files changed, 119 insertions, 52 deletions

diff --git a/drivers/gpu/drm/vkms/vkms_composer.c b/drivers/gpu/drm/vkms/vkms_composer.c
index 4af2f19480f4..33c031f27c2c 100644
--- a/drivers/gpu/drm/vkms/vkms_composer.c
+++ b/drivers/gpu/drm/vkms/vkms_composer.c
@@ -9,60 +9,92 @@
 
 #include "vkms_drv.h"
 
+static u32 get_pixel_from_buffer(int x, int y, const u8 *buffer,
+				 const struct vkms_composer *composer)
+{
+	u32 pixel;
+	int src_offset = composer->offset + (y * composer->pitch)
+				      + (x * composer->cpp);
+
+	pixel = *(u32 *)&buffer[src_offset];
+
+	return pixel;
+}
+
 /**
  * compute_crc - Compute CRC value on output frame
  *
- * @vaddr_out: address to final framebuffer
+ * @vaddr: address to final framebuffer
  * @composer: framebuffer's metadata
  *
  * returns CRC value computed using crc32 on the visible portion of
  * the final framebuffer at vaddr_out
  */
-static uint32_t compute_crc(void *vaddr_out, struct vkms_composer *composer)
+static uint32_t compute_crc(const u8 *vaddr,
+			    const struct vkms_composer *composer)
 {
-	int i, j, src_offset;
+	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;
-	u32 crc = 0;
-
-	for (i = y_src; i < y_src + h_src; ++i) {
-		for (j = x_src; j < x_src + w_src; ++j) {
-			src_offset = composer->offset
-				     + (i * composer->pitch)
-				     + (j * composer->cpp);
-			/* XRGB format ignores Alpha channel */
-			memset(vaddr_out + src_offset + 24, 0,  8);
-			crc = crc32_le(crc, vaddr_out + src_offset,
-				       sizeof(u32));
+
+	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));
 		}
 	}
 
 	return crc;
 }
 
+static u8 blend_channel(u8 src, u8 dst, u8 alpha)
+{
+	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);
+
+	return new_color;
+}
+
+static void alpha_blending(const u8 *argb_src, u8 *argb_dst)
+{
+	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);
+	/* Opaque primary */
+	argb_dst[3] = 0xFF;
+}
+
 /**
  * blend - blend value at vaddr_src with value at vaddr_dst
  * @vaddr_dst: destination address
  * @vaddr_src: source address
- * @dest_composer: destination framebuffer's metadata
+ * @dst_composer: destination framebuffer's metadata
  * @src_composer: source framebuffer's metadata
  *
- * Blend value at vaddr_src with value at vaddr_dst.
- * Currently, this function write value of vaddr_src on value
- * at vaddr_dst using buffer's metadata to locate the new values
- * from vaddr_src and their destination at vaddr_dst.
- *
- * TODO: Use the alpha value to blend vaddr_src with vaddr_dst
- *	 instead of overwriting it.
+ * Blend the vaddr_src value with the vaddr_dst value using the pre-multiplied
+ * alpha blending equation, since DRM currently assumes that the pixel color
+ * values have already been pre-multiplied with the alpha channel values. See
+ * more drm_plane_create_blend_mode_property(). This function uses buffer's
+ * metadata to locate the new composite values at vaddr_dst.
  */
 static void blend(void *vaddr_dst, void *vaddr_src,
-		  struct vkms_composer *dest_composer,
+		  struct vkms_composer *dst_composer,
 		  struct vkms_composer *src_composer)
 {
 	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;
@@ -77,15 +109,16 @@ static void blend(void *vaddr_dst, void *vaddr_src,
 
 	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 = dest_composer->offset
-				     + (i_dst * dest_composer->pitch)
-				     + (j_dst++ * dest_composer->cpp);
+			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);
 
-			memcpy(vaddr_dst + offset_dst,
-			       vaddr_src + offset_src, sizeof(u32));
+			pixel_src = (u8 *)(vaddr_src + offset_src);
+			pixel_dst = (u8 *)(vaddr_dst + offset_dst);
+			alpha_blending(pixel_src, pixel_dst);
 		}
 		i_dst++;
 	}
@@ -108,35 +141,31 @@ static void compose_cursor(struct vkms_composer *cursor_composer,
 	      primary_composer, cursor_composer);
 }
 
-static uint32_t _vkms_get_crc(struct vkms_composer *primary_composer,
-			      struct vkms_composer *cursor_composer)
+static int compose_planes(void **vaddr_out,
+			  struct vkms_composer *primary_composer,
+			  struct vkms_composer *cursor_composer)
 {
 	struct drm_framebuffer *fb = &primary_composer->fb;
 	struct drm_gem_object *gem_obj = drm_gem_fb_get_obj(fb, 0);
 	struct vkms_gem_object *vkms_obj = drm_gem_to_vkms_gem(gem_obj);
-	void *vaddr_out = kzalloc(vkms_obj->gem.size, GFP_KERNEL);
-	u32 crc = 0;
 
-	if (!vaddr_out) {
-		DRM_ERROR("Failed to allocate memory for output frame.");
-		return 0;
+	if (!*vaddr_out) {
+		*vaddr_out = kzalloc(vkms_obj->gem.size, GFP_KERNEL);
+		if (!*vaddr_out) {
+			DRM_ERROR("Cannot allocate memory for output frame.");
+			return -ENOMEM;
+		}
 	}
 
-	if (WARN_ON(!vkms_obj->vaddr)) {
-		kfree(vaddr_out);
-		return crc;
-	}
+	if (WARN_ON(!vkms_obj->vaddr))
+		return -EINVAL;
 
-	memcpy(vaddr_out, vkms_obj->vaddr, vkms_obj->gem.size);
+	memcpy(*vaddr_out, vkms_obj->vaddr, vkms_obj->gem.size);
 
 	if (cursor_composer)
-		compose_cursor(cursor_composer, primary_composer, vaddr_out);
-
-	crc = compute_crc(vaddr_out, primary_composer);
+		compose_cursor(cursor_composer, primary_composer, *vaddr_out);
 
-	kfree(vaddr_out);
-
-	return crc;
+	return 0;
 }
 
 /**
@@ -157,14 +186,17 @@ void vkms_composer_worker(struct work_struct *work)
 	struct vkms_output *out = drm_crtc_to_vkms_output(crtc);
 	struct vkms_composer *primary_composer = NULL;
 	struct vkms_composer *cursor_composer = NULL;
+	bool crc_pending, wb_pending;
+	void *vaddr_out = NULL;
 	u32 crc32 = 0;
 	u64 frame_start, frame_end;
-	bool crc_pending;
+	int ret;
 
 	spin_lock_irq(&out->composer_lock);
 	frame_start = crtc_state->frame_start;
 	frame_end = crtc_state->frame_end;
 	crc_pending = crtc_state->crc_pending;
+	wb_pending = crtc_state->wb_pending;
 	crtc_state->frame_start = 0;
 	crtc_state->frame_end = 0;
 	crtc_state->crc_pending = false;
@@ -183,8 +215,29 @@ void vkms_composer_worker(struct work_struct *work)
 	if (crtc_state->num_active_planes == 2)
 		cursor_composer = crtc_state->active_planes[1]->composer;
 
-	if (primary_composer)
-		crc32 = _vkms_get_crc(primary_composer, cursor_composer);
+	if (!primary_composer)
+		return;
+
+	if (wb_pending)
+		vaddr_out = crtc_state->active_writeback;
+
+	ret = compose_planes(&vaddr_out, primary_composer, cursor_composer);
+	if (ret) {
+		if (ret == -EINVAL && !wb_pending)
+			kfree(vaddr_out);
+		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 {
+		kfree(vaddr_out);
+	}
 
 	/*
 	 * The worker can fall behind the vblank hrtimer, make sure we catch up.
@@ -233,6 +286,22 @@ int vkms_verify_crc_source(struct drm_crtc *crtc, const char *src_name,
 	return 0;
 }
 
+void vkms_set_composer(struct vkms_output *out, bool enabled)
+{
+	bool old_enabled;
+
+	if (enabled)
+		drm_crtc_vblank_get(&out->crtc);
+
+	spin_lock_irq(&out->lock);
+	old_enabled = out->composer_enabled;
+	out->composer_enabled = enabled;
+	spin_unlock_irq(&out->lock);
+
+	if (old_enabled)
+		drm_crtc_vblank_put(&out->crtc);
+}
+
 int vkms_set_crc_source(struct drm_crtc *crtc, const char *src_name)
 {
 	struct vkms_output *out = drm_crtc_to_vkms_output(crtc);
@@ -241,9 +310,7 @@ int vkms_set_crc_source(struct drm_crtc *crtc, const char *src_name)
 
 	ret = vkms_crc_parse_source(src_name, &enabled);
 
-	spin_lock_irq(&out->lock);
-	out->composer_enabled = enabled;
-	spin_unlock_irq(&out->lock);
+	vkms_set_composer(out, enabled);
 
 	return ret;
 }