xref: /openbmc/linux/drivers/gpu/drm/vkms/vkms_composer.c (revision 1645e7b9667f14a37f9ac8c49568b8f979227d20)

// SPDX-License-Identifier: GPL-2.0+

#include <linux/crc32.h>

#include <drm/drm_atomic.h>
#include <drm/drm_atomic_helper.h>
#include <drm/drm_fourcc.h>
#include <drm/drm_gem_framebuffer_helper.h>
#include <drm/drm_vblank.h>

#include "vkms_drv.h"

static u32 get_pixel_from_buffer(int x, int y, const u8 *buffer,
				 const struct vkms_frame_info *frame_info)
{
	u32 pixel;
	int src_offset = frame_info->offset + (y * frame_info->pitch)
					    + (x * frame_info->cpp);

	pixel = *(u32 *)&buffer[src_offset];

	return pixel;
}

/**
 * compute_crc - Compute CRC value on output frame
 *
 * @vaddr: address to final framebuffer
 * @frame_info: 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(const u8 *vaddr,
			    const struct vkms_frame_info *frame_info)
{
	int x, y;
	u32 crc = 0, pixel = 0;
	int x_src = frame_info->src.x1 >> 16;
	int y_src = frame_info->src.y1 >> 16;
	int h_src = drm_rect_height(&frame_info->src) >> 16;
	int w_src = drm_rect_width(&frame_info->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, frame_info);
			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;
}

/**
 * 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)
{
	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);
}

/**
 * x_blend - blending equation that ignores the pixel alpha
 *
 * overwrites RGB color value from src pixel to dst pixel.
 */
static void x_blend(const u8 *xrgb_src, u8 *xrgb_dst)
{
	memcpy(xrgb_dst, xrgb_src, sizeof(u8) * 3);
}

/**
 * blend - blend value at vaddr_src with value at vaddr_dst
 * @vaddr_dst: destination address
 * @vaddr_src: source address
 * @dst_frame_info: destination framebuffer's metadata
 * @src_frame_info: 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_frame_info *dst_frame_info,
		  struct vkms_frame_info *src_frame_info,
		  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_frame_info->src.x1 >> 16;
	int y_src = src_frame_info->src.y1 >> 16;

	int x_dst = src_frame_info->dst.x1;
	int y_dst = src_frame_info->dst.y1;
	int h_dst = drm_rect_height(&src_frame_info->dst);
	int w_dst = drm_rect_width(&src_frame_info->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_frame_info->offset
				     + (i_dst * dst_frame_info->pitch)
				     + (j_dst++ * dst_frame_info->cpp);
			offset_src = src_frame_info->offset
				     + (i * src_frame_info->pitch)
				     + (j * src_frame_info->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;
		}
		i_dst++;
	}
}

static void compose_plane(struct vkms_frame_info *primary_plane_info,
			  struct vkms_frame_info *plane_frame_info,
			  void *vaddr_out)
{
	struct drm_framebuffer *fb = &plane_frame_info->fb;
	void *vaddr;
	void (*pixel_blend)(const u8 *p_src, u8 *p_dst);

	if (WARN_ON(iosys_map_is_null(&plane_frame_info->map[0])))
		return;

	vaddr = plane_frame_info->map[0].vaddr;

	if (fb->format->format == DRM_FORMAT_ARGB8888)
		pixel_blend = &alpha_blend;
	else
		pixel_blend = &x_blend;

	blend(vaddr_out, vaddr, primary_plane_info,
	      plane_frame_info, pixel_blend);
}

static int compose_active_planes(void **vaddr_out,
				 struct vkms_frame_info *primary_plane_info,
				 struct vkms_crtc_state *crtc_state)
{
	struct drm_framebuffer *fb = &primary_plane_info->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;
		}
	}

	if (WARN_ON(iosys_map_is_null(&primary_plane_info->map[0])))
		return -EINVAL;

	vaddr = primary_plane_info->map[0].vaddr;

	memcpy(*vaddr_out, vaddr, gem_obj->size);

	/* 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_plane_info,
			      crtc_state->active_planes[i]->frame_info,
			      *vaddr_out);

	return 0;
}

/**
 * vkms_composer_worker - ordered work_struct to compute CRC
 *
 * @work: work_struct
 *
 * Work handler for composing and computing CRCs. work_struct scheduled in
 * an ordered workqueue that's periodically scheduled to run by
 * vkms_vblank_simulate() and flushed at vkms_atomic_commit_tail().
 */
void vkms_composer_worker(struct work_struct *work)
{
	struct vkms_crtc_state *crtc_state = container_of(work,
						struct vkms_crtc_state,
						composer_work);
	struct drm_crtc *crtc = crtc_state->base.crtc;
	struct vkms_output *out = drm_crtc_to_vkms_output(crtc);
	struct vkms_frame_info *primary_plane_info = 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;
	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;
	spin_unlock_irq(&out->composer_lock);

	/*
	 * We raced with the vblank hrtimer and previous work already computed
	 * the crc, nothing to do.
	 */
	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_plane_info = act_plane->frame_info;
	}

	if (!primary_plane_info)
		return;

	if (wb_pending)
		vaddr_out = crtc_state->active_writeback->data[0].vaddr;

	ret = compose_active_planes(&vaddr_out, primary_plane_info,
				    crtc_state);
	if (ret) {
		if (ret == -EINVAL && !wb_pending)
			kvfree(vaddr_out);
		return;
	}

	crc32 = compute_crc(vaddr_out, primary_plane_info);

	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);
	}

	/*
	 * The worker can fall behind the vblank hrtimer, make sure we catch up.
	 */
	while (frame_start <= frame_end)
		drm_crtc_add_crc_entry(crtc, true, frame_start++, &crc32);
}

static const char * const pipe_crc_sources[] = {"auto"};

const char *const *vkms_get_crc_sources(struct drm_crtc *crtc,
					size_t *count)
{
	*count = ARRAY_SIZE(pipe_crc_sources);
	return pipe_crc_sources;
}

static int vkms_crc_parse_source(const char *src_name, bool *enabled)
{
	int ret = 0;

	if (!src_name) {
		*enabled = false;
	} else if (strcmp(src_name, "auto") == 0) {
		*enabled = true;
	} else {
		*enabled = false;
		ret = -EINVAL;
	}

	return ret;
}

int vkms_verify_crc_source(struct drm_crtc *crtc, const char *src_name,
			   size_t *values_cnt)
{
	bool enabled;

	if (vkms_crc_parse_source(src_name, &enabled) < 0) {
		DRM_DEBUG_DRIVER("unknown source %s\n", src_name);
		return -EINVAL;
	}

	*values_cnt = 1;

	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);
	bool enabled = false;
	int ret = 0;

	ret = vkms_crc_parse_source(src_name, &enabled);

	vkms_set_composer(out, enabled);

	return ret;
}