summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/vkms/vkms_formats.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/vkms/vkms_formats.c')
-rw-r--r--drivers/gpu/drm/vkms/vkms_formats.c467
1 files changed, 466 insertions, 1 deletions
diff --git a/drivers/gpu/drm/vkms/vkms_formats.c b/drivers/gpu/drm/vkms/vkms_formats.c
index 30a64ecca87c..6d0227c6635a 100644
--- a/drivers/gpu/drm/vkms/vkms_formats.c
+++ b/drivers/gpu/drm/vkms/vkms_formats.c
@@ -7,6 +7,8 @@
#include <drm/drm_rect.h>
#include <drm/drm_fixed.h>
+#include <kunit/visibility.h>
+
#include "vkms_formats.h"
/**
@@ -140,6 +142,51 @@ static void packed_pixels_addr_1x1(const struct vkms_frame_info *frame_info,
*addr = (u8 *)frame_info->map[0].vaddr + offset;
}
+/**
+ * get_subsampling() - Get the subsampling divisor value on a specific direction
+ *
+ * @format: format to extarct the subsampling from
+ * @direction: direction of the subsampling requested
+ */
+static int get_subsampling(const struct drm_format_info *format,
+ enum pixel_read_direction direction)
+{
+ switch (direction) {
+ case READ_BOTTOM_TO_TOP:
+ case READ_TOP_TO_BOTTOM:
+ return format->vsub;
+ case READ_RIGHT_TO_LEFT:
+ case READ_LEFT_TO_RIGHT:
+ return format->hsub;
+ }
+ WARN_ONCE(true, "Invalid direction for pixel reading: %d\n", direction);
+ return 1;
+}
+
+/**
+ * get_subsampling_offset() - An offset for keeping the chroma siting consistent regardless of
+ * x_start and y_start values
+ *
+ * @direction: direction of the reading to properly compute this offset
+ * @x_start: x coordinate of the starting point of the readed line
+ * @y_start: y coordinate of the starting point of the readed line
+ */
+static int get_subsampling_offset(enum pixel_read_direction direction, int x_start, int y_start)
+{
+ switch (direction) {
+ case READ_BOTTOM_TO_TOP:
+ return -y_start - 1;
+ case READ_TOP_TO_BOTTOM:
+ return y_start;
+ case READ_RIGHT_TO_LEFT:
+ return -x_start - 1;
+ case READ_LEFT_TO_RIGHT:
+ return x_start;
+ }
+ WARN_ONCE(true, "Invalid direction for pixel reading: %d\n", direction);
+ return 0;
+}
+
/*
* The following functions take pixel data (a, r, g, b, pixel, ...) and convert them to
* &struct pixel_argb_u16
@@ -202,11 +249,54 @@ static struct pixel_argb_u16 argb_u16_from_RGB565(const __le16 *pixel)
return out_pixel;
}
+static struct pixel_argb_u16 argb_u16_from_gray8(u8 gray)
+{
+ return argb_u16_from_u8888(255, gray, gray, gray);
+}
+
+static struct pixel_argb_u16 argb_u16_from_grayu16(u16 gray)
+{
+ return argb_u16_from_u16161616(0xFFFF, gray, gray, gray);
+}
+
+VISIBLE_IF_KUNIT struct pixel_argb_u16 argb_u16_from_yuv888(u8 y, u8 channel_1, u8 channel_2,
+ const struct conversion_matrix *matrix)
+{
+ u16 r, g, b;
+ s64 fp_y, fp_channel_1, fp_channel_2;
+ s64 fp_r, fp_g, fp_b;
+
+ fp_y = drm_int2fixp(((int)y - matrix->y_offset) * 257);
+ fp_channel_1 = drm_int2fixp(((int)channel_1 - 128) * 257);
+ fp_channel_2 = drm_int2fixp(((int)channel_2 - 128) * 257);
+
+ fp_r = drm_fixp_mul(matrix->matrix[0][0], fp_y) +
+ drm_fixp_mul(matrix->matrix[0][1], fp_channel_1) +
+ drm_fixp_mul(matrix->matrix[0][2], fp_channel_2);
+ fp_g = drm_fixp_mul(matrix->matrix[1][0], fp_y) +
+ drm_fixp_mul(matrix->matrix[1][1], fp_channel_1) +
+ drm_fixp_mul(matrix->matrix[1][2], fp_channel_2);
+ fp_b = drm_fixp_mul(matrix->matrix[2][0], fp_y) +
+ drm_fixp_mul(matrix->matrix[2][1], fp_channel_1) +
+ drm_fixp_mul(matrix->matrix[2][2], fp_channel_2);
+
+ fp_r = drm_fixp2int_round(fp_r);
+ fp_g = drm_fixp2int_round(fp_g);
+ fp_b = drm_fixp2int_round(fp_b);
+
+ r = clamp(fp_r, 0, 0xffff);
+ g = clamp(fp_g, 0, 0xffff);
+ b = clamp(fp_b, 0, 0xffff);
+
+ return argb_u16_from_u16161616(0xffff, r, g, b);
+}
+EXPORT_SYMBOL_IF_KUNIT(argb_u16_from_yuv888);
+
/*
* The following functions are read_line function for each pixel format supported by VKMS.
*
* They read a line starting at the point @x_start,@y_start following the @direction. The result
- * is stored in @out_pixel and in the format ARGB16161616.
+ * is stored in @out_pixel and in a 64 bits format, see struct pixel_argb_u16.
*
* These functions are very repetitive, but the innermost pixel loops must be kept inside these
* functions for performance reasons. Some benchmarking was done in [1] where having the innermost
@@ -215,6 +305,96 @@ static struct pixel_argb_u16 argb_u16_from_RGB565(const __le16 *pixel)
* [1]: https://lore.kernel.org/dri-devel/d258c8dc-78e9-4509-9037-a98f7f33b3a3@riseup.net/
*/
+static void Rx_read_line(const struct vkms_plane_state *plane, int x_start,
+ int y_start, enum pixel_read_direction direction, int count,
+ struct pixel_argb_u16 out_pixel[])
+{
+ struct pixel_argb_u16 *end = out_pixel + count;
+ int bits_per_pixel = drm_format_info_bpp(plane->frame_info->fb->format, 0);
+ u8 *src_pixels;
+ int rem_x, rem_y;
+
+ WARN_ONCE(drm_format_info_block_height(plane->frame_info->fb->format, 0) != 1,
+ "%s() only support formats with block_h == 1", __func__);
+
+ packed_pixels_addr(plane->frame_info, x_start, y_start, 0, &src_pixels, &rem_x, &rem_y);
+ int bit_offset = (8 - bits_per_pixel) - rem_x * bits_per_pixel;
+ int step = get_block_step_bytes(plane->frame_info->fb, direction, 0);
+ int mask = (0x1 << bits_per_pixel) - 1;
+ int lum_per_level = 0xFFFF / mask;
+
+ if (direction == READ_LEFT_TO_RIGHT || direction == READ_RIGHT_TO_LEFT) {
+ int restart_bit_offset;
+ int step_bit_offset;
+
+ if (direction == READ_LEFT_TO_RIGHT) {
+ restart_bit_offset = 8 - bits_per_pixel;
+ step_bit_offset = -bits_per_pixel;
+ } else {
+ restart_bit_offset = 0;
+ step_bit_offset = bits_per_pixel;
+ }
+
+ while (out_pixel < end) {
+ u8 val = ((*src_pixels) >> bit_offset) & mask;
+
+ *out_pixel = argb_u16_from_grayu16((int)val * lum_per_level);
+
+ bit_offset += step_bit_offset;
+ if (bit_offset < 0 || 8 <= bit_offset) {
+ bit_offset = restart_bit_offset;
+ src_pixels += step;
+ }
+ out_pixel += 1;
+ }
+ } else if (direction == READ_TOP_TO_BOTTOM || direction == READ_BOTTOM_TO_TOP) {
+ while (out_pixel < end) {
+ u8 val = (*src_pixels >> bit_offset) & mask;
+ *out_pixel = argb_u16_from_grayu16((int)val * lum_per_level);
+ src_pixels += step;
+ out_pixel += 1;
+ }
+ }
+}
+
+static void R1_read_line(const struct vkms_plane_state *plane, int x_start,
+ int y_start, enum pixel_read_direction direction, int count,
+ struct pixel_argb_u16 out_pixel[])
+{
+ Rx_read_line(plane, x_start, y_start, direction, count, out_pixel);
+}
+
+static void R2_read_line(const struct vkms_plane_state *plane, int x_start,
+ int y_start, enum pixel_read_direction direction, int count,
+ struct pixel_argb_u16 out_pixel[])
+{
+ Rx_read_line(plane, x_start, y_start, direction, count, out_pixel);
+}
+
+static void R4_read_line(const struct vkms_plane_state *plane, int x_start,
+ int y_start, enum pixel_read_direction direction, int count,
+ struct pixel_argb_u16 out_pixel[])
+{
+ Rx_read_line(plane, x_start, y_start, direction, count, out_pixel);
+}
+
+static void R8_read_line(const struct vkms_plane_state *plane, int x_start,
+ int y_start, enum pixel_read_direction direction, int count,
+ struct pixel_argb_u16 out_pixel[])
+{
+ struct pixel_argb_u16 *end = out_pixel + count;
+ u8 *src_pixels;
+ int step = get_block_step_bytes(plane->frame_info->fb, direction, 0);
+
+ packed_pixels_addr_1x1(plane->frame_info, x_start, y_start, 0, &src_pixels);
+
+ while (out_pixel < end) {
+ *out_pixel = argb_u16_from_gray8(*src_pixels);
+ src_pixels += step;
+ out_pixel += 1;
+ }
+}
+
static void ARGB8888_read_line(const struct vkms_plane_state *plane, int x_start, int y_start,
enum pixel_read_direction direction, int count,
struct pixel_argb_u16 out_pixel[])
@@ -332,6 +512,92 @@ static void RGB565_read_line(const struct vkms_plane_state *plane, int x_start,
}
/*
+ * This callback can be used for YUV formats where U and V values are
+ * stored in the same plane (often called semi-planar formats). It will
+ * correctly handle subsampling as described in the drm_format_info of the plane.
+ *
+ * The conversion matrix stored in the @plane is used to:
+ * - Apply the correct color range and encoding
+ * - Convert YUV and YVU with the same function (a column swap is needed when setting up
+ * plane->conversion_matrix)
+ */
+static void semi_planar_yuv_read_line(const struct vkms_plane_state *plane, int x_start,
+ int y_start, enum pixel_read_direction direction, int count,
+ struct pixel_argb_u16 out_pixel[])
+{
+ u8 *y_plane;
+ u8 *uv_plane;
+
+ packed_pixels_addr_1x1(plane->frame_info, x_start, y_start, 0,
+ &y_plane);
+ packed_pixels_addr_1x1(plane->frame_info,
+ x_start / plane->frame_info->fb->format->hsub,
+ y_start / plane->frame_info->fb->format->vsub, 1,
+ &uv_plane);
+ int step_y = get_block_step_bytes(plane->frame_info->fb, direction, 0);
+ int step_uv = get_block_step_bytes(plane->frame_info->fb, direction, 1);
+ int subsampling = get_subsampling(plane->frame_info->fb->format, direction);
+ int subsampling_offset = get_subsampling_offset(direction, x_start, y_start);
+ const struct conversion_matrix *conversion_matrix = &plane->conversion_matrix;
+
+ for (int i = 0; i < count; i++) {
+ *out_pixel = argb_u16_from_yuv888(y_plane[0], uv_plane[0], uv_plane[1],
+ conversion_matrix);
+ out_pixel += 1;
+ y_plane += step_y;
+ if ((i + subsampling_offset + 1) % subsampling == 0)
+ uv_plane += step_uv;
+ }
+}
+
+/*
+ * This callback can be used for YUV format where each color component is
+ * stored in a different plane (often called planar formats). It will
+ * correctly handle subsampling as described in the drm_format_info of the plane.
+ *
+ * The conversion matrix stored in the @plane is used to:
+ * - Apply the correct color range and encoding
+ * - Convert YUV and YVU with the same function (a column swap is needed when setting up
+ * plane->conversion_matrix)
+ */
+static void planar_yuv_read_line(const struct vkms_plane_state *plane, int x_start,
+ int y_start, enum pixel_read_direction direction, int count,
+ struct pixel_argb_u16 out_pixel[])
+{
+ u8 *y_plane;
+ u8 *channel_1_plane;
+ u8 *channel_2_plane;
+
+ packed_pixels_addr_1x1(plane->frame_info, x_start, y_start, 0,
+ &y_plane);
+ packed_pixels_addr_1x1(plane->frame_info,
+ x_start / plane->frame_info->fb->format->hsub,
+ y_start / plane->frame_info->fb->format->vsub, 1,
+ &channel_1_plane);
+ packed_pixels_addr_1x1(plane->frame_info,
+ x_start / plane->frame_info->fb->format->hsub,
+ y_start / plane->frame_info->fb->format->vsub, 2,
+ &channel_2_plane);
+ int step_y = get_block_step_bytes(plane->frame_info->fb, direction, 0);
+ int step_channel_1 = get_block_step_bytes(plane->frame_info->fb, direction, 1);
+ int step_channel_2 = get_block_step_bytes(plane->frame_info->fb, direction, 2);
+ int subsampling = get_subsampling(plane->frame_info->fb->format, direction);
+ int subsampling_offset = get_subsampling_offset(direction, x_start, y_start);
+ const struct conversion_matrix *conversion_matrix = &plane->conversion_matrix;
+
+ for (int i = 0; i < count; i++) {
+ *out_pixel = argb_u16_from_yuv888(*y_plane, *channel_1_plane, *channel_2_plane,
+ conversion_matrix);
+ out_pixel += 1;
+ y_plane += step_y;
+ if ((i + subsampling_offset + 1) % subsampling == 0) {
+ channel_1_plane += step_channel_1;
+ channel_2_plane += step_channel_2;
+ }
+ }
+}
+
+/*
* The following functions take one &struct pixel_argb_u16 and convert it to a specific format.
* The result is stored in @out_pixel.
*
@@ -456,6 +722,28 @@ pixel_read_line_t get_pixel_read_line_function(u32 format)
return &XRGB16161616_read_line;
case DRM_FORMAT_RGB565:
return &RGB565_read_line;
+ case DRM_FORMAT_NV12:
+ case DRM_FORMAT_NV16:
+ case DRM_FORMAT_NV24:
+ case DRM_FORMAT_NV21:
+ case DRM_FORMAT_NV61:
+ case DRM_FORMAT_NV42:
+ return &semi_planar_yuv_read_line;
+ case DRM_FORMAT_YUV420:
+ case DRM_FORMAT_YUV422:
+ case DRM_FORMAT_YUV444:
+ case DRM_FORMAT_YVU420:
+ case DRM_FORMAT_YVU422:
+ case DRM_FORMAT_YVU444:
+ return &planar_yuv_read_line;
+ case DRM_FORMAT_R1:
+ return &R1_read_line;
+ case DRM_FORMAT_R2:
+ return &R2_read_line;
+ case DRM_FORMAT_R4:
+ return &R4_read_line;
+ case DRM_FORMAT_R8:
+ return &R8_read_line;
default:
/*
* This is a bug in vkms_plane_atomic_check(). All the supported
@@ -469,6 +757,183 @@ pixel_read_line_t get_pixel_read_line_function(u32 format)
}
}
+/*
+ * Those matrices were generated using the colour python framework
+ *
+ * Below are the function calls used to generate each matrix, go to
+ * https://colour.readthedocs.io/en/develop/generated/colour.matrix_YCbCr.html
+ * for more info:
+ *
+ * numpy.around(colour.matrix_YCbCr(K=colour.WEIGHTS_YCBCR["ITU-R BT.601"],
+ * is_legal = False,
+ * bits = 8) * 2**32).astype(int)
+ */
+static const struct conversion_matrix no_operation = {
+ .matrix = {
+ { 4294967296, 0, 0, },
+ { 0, 4294967296, 0, },
+ { 0, 0, 4294967296, },
+ },
+ .y_offset = 0,
+};
+
+static const struct conversion_matrix yuv_bt601_full = {
+ .matrix = {
+ { 4294967296, 0, 6021544149 },
+ { 4294967296, -1478054095, -3067191994 },
+ { 4294967296, 7610682049, 0 },
+ },
+ .y_offset = 0,
+};
+
+/*
+ * numpy.around(colour.matrix_YCbCr(K=colour.WEIGHTS_YCBCR["ITU-R BT.601"],
+ * is_legal = True,
+ * bits = 8) * 2**32).astype(int)
+ */
+static const struct conversion_matrix yuv_bt601_limited = {
+ .matrix = {
+ { 5020601039, 0, 6881764740 },
+ { 5020601039, -1689204679, -3505362278 },
+ { 5020601039, 8697922339, 0 },
+ },
+ .y_offset = 16,
+};
+
+/*
+ * numpy.around(colour.matrix_YCbCr(K=colour.WEIGHTS_YCBCR["ITU-R BT.709"],
+ * is_legal = False,
+ * bits = 8) * 2**32).astype(int)
+ */
+static const struct conversion_matrix yuv_bt709_full = {
+ .matrix = {
+ { 4294967296, 0, 6763714498 },
+ { 4294967296, -804551626, -2010578443 },
+ { 4294967296, 7969741314, 0 },
+ },
+ .y_offset = 0,
+};
+
+/*
+ * numpy.around(colour.matrix_YCbCr(K=colour.WEIGHTS_YCBCR["ITU-R BT.709"],
+ * is_legal = True,
+ * bits = 8) * 2**32).astype(int)
+ */
+static const struct conversion_matrix yuv_bt709_limited = {
+ .matrix = {
+ { 5020601039, 0, 7729959424 },
+ { 5020601039, -919487572, -2297803934 },
+ { 5020601039, 9108275786, 0 },
+ },
+ .y_offset = 16,
+};
+
+/*
+ * numpy.around(colour.matrix_YCbCr(K=colour.WEIGHTS_YCBCR["ITU-R BT.2020"],
+ * is_legal = False,
+ * bits = 8) * 2**32).astype(int)
+ */
+static const struct conversion_matrix yuv_bt2020_full = {
+ .matrix = {
+ { 4294967296, 0, 6333358775 },
+ { 4294967296, -706750298, -2453942994 },
+ { 4294967296, 8080551471, 0 },
+ },
+ .y_offset = 0,
+};
+
+/*
+ * numpy.around(colour.matrix_YCbCr(K=colour.WEIGHTS_YCBCR["ITU-R BT.2020"],
+ * is_legal = True,
+ * bits = 8) * 2**32).astype(int)
+ */
+static const struct conversion_matrix yuv_bt2020_limited = {
+ .matrix = {
+ { 5020601039, 0, 7238124312 },
+ { 5020601039, -807714626, -2804506279 },
+ { 5020601039, 9234915964, 0 },
+ },
+ .y_offset = 16,
+};
+
+/**
+ * swap_uv_columns() - Swap u and v column of a given matrix
+ *
+ * @matrix: Matrix in which column are swapped
+ */
+static void swap_uv_columns(struct conversion_matrix *matrix)
+{
+ swap(matrix->matrix[0][2], matrix->matrix[0][1]);
+ swap(matrix->matrix[1][2], matrix->matrix[1][1]);
+ swap(matrix->matrix[2][2], matrix->matrix[2][1]);
+}
+
+/**
+ * get_conversion_matrix_to_argb_u16() - Retrieve the correct yuv to rgb conversion matrix for a
+ * given encoding and range.
+ *
+ * @format: DRM_FORMAT_* value for which to obtain a conversion function (see [drm_fourcc.h])
+ * @encoding: DRM_COLOR_* value for which to obtain a conversion matrix
+ * @range: DRM_COLOR_*_RANGE value for which to obtain a conversion matrix
+ * @matrix: Pointer to store the value into
+ */
+void get_conversion_matrix_to_argb_u16(u32 format,
+ enum drm_color_encoding encoding,
+ enum drm_color_range range,
+ struct conversion_matrix *matrix)
+{
+ const struct conversion_matrix *matrix_to_copy;
+ bool limited_range;
+
+ switch (range) {
+ case DRM_COLOR_YCBCR_LIMITED_RANGE:
+ limited_range = true;
+ break;
+ case DRM_COLOR_YCBCR_FULL_RANGE:
+ limited_range = false;
+ break;
+ case DRM_COLOR_RANGE_MAX:
+ limited_range = false;
+ WARN_ONCE(true, "The requested range is not supported.");
+ break;
+ }
+
+ switch (encoding) {
+ case DRM_COLOR_YCBCR_BT601:
+ matrix_to_copy = limited_range ? &yuv_bt601_limited :
+ &yuv_bt601_full;
+ break;
+ case DRM_COLOR_YCBCR_BT709:
+ matrix_to_copy = limited_range ? &yuv_bt709_limited :
+ &yuv_bt709_full;
+ break;
+ case DRM_COLOR_YCBCR_BT2020:
+ matrix_to_copy = limited_range ? &yuv_bt2020_limited :
+ &yuv_bt2020_full;
+ break;
+ case DRM_COLOR_ENCODING_MAX:
+ matrix_to_copy = &no_operation;
+ WARN_ONCE(true, "The requested encoding is not supported.");
+ break;
+ }
+
+ memcpy(matrix, matrix_to_copy, sizeof(*matrix_to_copy));
+
+ switch (format) {
+ case DRM_FORMAT_YVU420:
+ case DRM_FORMAT_YVU422:
+ case DRM_FORMAT_YVU444:
+ case DRM_FORMAT_NV21:
+ case DRM_FORMAT_NV61:
+ case DRM_FORMAT_NV42:
+ swap_uv_columns(matrix);
+ break;
+ default:
+ break;
+ }
+}
+EXPORT_SYMBOL(get_conversion_matrix_to_argb_u16);
+
/**
* get_pixel_write_function() - Retrieve the correct write_pixel function for a specific format.
* The returned pointer is NULL for unsupported pixel formats. The caller must ensure that the
generated by cgit (git 2.34.1) at 2025-08-01 18:58:48 +0000