From 8af5fccd9e8af443efd6f0fec5ba56366f57309a Mon Sep 17 00:00:00 2001 From: Harry Wentland Date: Fri, 14 Aug 2026 17:18:08 -0400 Subject: [PATCH] drm/vkms: Fix limited-range YCbCr to RGB conversion scaling The limited-/studio-range YCbCr to RGB conversion matrices were generated with colour.matrix_YCbCr(is_legal=True, bits=8), which normalises the narrow range by 2^bits (256 for 8-bit) rather than by the full-range maximum 2^bits - 1 (255). As a result the luma scale was 256/219 and the chroma scale 256/224 instead of the correct 255/219 and 255/224. This over-scales every limited-range conversion by a factor of 256/255, producing an error of up to ~3/255 (8-bit) and causing IGT tests that compare software-computed surfaces against VKMS-processed ones to fail. Recompute the three limited-range matrices from first principles rather than relying on colour's is_legal scaling: 1. Start from the standard ITU-R YCbCr -> RGB relations for the luma weights Kr, Kb (Kg = 1 - Kr - Kb) of each encoding (BT.601, BT.709 and BT.2020 non-constant luminance). These are the same relations that produce the existing full-range matrices. 2. Expand the studio input range to full range relative to a full-range maximum of 2^n - 1: the luma coefficient by 255/(235 - 16) and the chroma coefficients by 255/(240 - 16). This matches the DRM UAPI definition and IGT's igt_ycbcr_to_rgb_matrix(). 3. Convert each coefficient to S31.32 fixed point (round(coeff * 2^32)). Update the limited-range reference values in the vkms-format KUnit test accordingly. Provide a python script to show how the kunit test value are calculated. Fixes: fe22d21e9342 ("drm/vkms: Add YUV support") Assisted-by: Copilot:claude-opus-4.8 Signed-off-by: Harry Wentland Reviewed-by: Alex Hung Tested-by: Robert Mader Link: https://patch.msgid.link/20260814211816.1219597-3-harry.wentland@amd.com --- .../gpu/drm/vkms/tests/gen_yuv_conversion.py | 87 +++++++++++++++++++ drivers/gpu/drm/vkms/tests/vkms_format_test.c | 38 ++++---- drivers/gpu/drm/vkms/vkms_formats.c | 55 ++++++++---- 3 files changed, 144 insertions(+), 36 deletions(-) create mode 100755 drivers/gpu/drm/vkms/tests/gen_yuv_conversion.py diff --git a/drivers/gpu/drm/vkms/tests/gen_yuv_conversion.py b/drivers/gpu/drm/vkms/tests/gen_yuv_conversion.py new file mode 100755 index 000000000000..f4d226137cc2 --- /dev/null +++ b/drivers/gpu/drm/vkms/tests/gen_yuv_conversion.py @@ -0,0 +1,87 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0+ +""" +Derive the VKMS YCbCr -> RGB conversion constants and the vkms-format KUnit +reference values. + +It produces: + 1. The S31.32 fixed-point conversion matrices used in + drivers/gpu/drm/vkms/vkms_formats.c and asserted by + vkms_format_test_conversion_matrix. + 2. The 16-bit reference YCbCr inputs for the limited-range + yuv_u16_to_argb_u16 round-trip cases (the values changed by the fix). + +Requires numpy. +""" + +import numpy as np + +FP = 1 << 32 # S31.32 scale: fixed = round(coeff * 2^32) + +# ITU-R luma weights (Kr, Kb); Kg = 1 - Kr - Kb. +ENCODINGS = { + "BT601": (0.299, 0.114), + "BT709": (0.2126, 0.0722), + "BT2020": (0.2627, 0.0593), # non-constant luminance +} + +# 8-bit studio-range levels: luma 16..235 (range 219), chroma 16..240 +# (range 224, neutral 128); full-range maximum is 2^n - 1 = 255. +FULL_MAX = 255 +Y_RANGE = 235 - 16 # 219 +C_RANGE = 240 - 16 # 224 + +# 16-bit RGB test colors. +COLORS = { + "white": (0xffff, 0xffff, 0xffff), + "gray": (0x8080, 0x8080, 0x8080), + "black": (0x0000, 0x0000, 0x0000), + "red": (0xffff, 0x0000, 0x0000), + "green": (0x0000, 0xffff, 0x0000), + "blue": (0x0000, 0x0000, 0xffff), +} + + +def rgb_matrix(kr, kb, limited): + """Normalized YCbCr -> RGB (Y in [0,1], Cb/Cr in [-0.5, 0.5]).""" + kg = 1.0 - kr - kb + # Standard full-range relations. + m = [[1.0, 0.0, 2 * (1 - kr)], + [1.0, -2 * (1 - kb) * kb / kg, -2 * (1 - kr) * kr / kg], + [1.0, 2 * (1 - kb), 0.0]] + if limited: + # Expand studio input range to full range: luma by 255/219, + # chroma by 255/224 (relative to full-range maximum 2^n - 1). + ys, cs = FULL_MAX / Y_RANGE, FULL_MAX / C_RANGE + m = [[r[0] * ys, r[1] * cs, r[2] * cs] for r in m] + return m + + +def ref_yuv(m, y_offset): + """16-bit YCbCr that VKMS decodes back to each RGB color. + + VKMS decode: [R,G,B] = M . [Y - y_offset*257, Cb - 128*257, Cr - 128*257] + (8-bit offsets lifted to 16-bit by *257 = 65535/255), so invert and + re-add the offsets. + """ + inv = np.linalg.inv(np.array(m, float)) + off = np.array([y_offset * 257, 128 * 257, 128 * 257]) + return {name: tuple(int(min(max(round(v), 0), 0xffff)) + for v in inv @ np.array(rgb, float) + off) + for name, rgb in COLORS.items()} + +print(f"== RGB REFERENCE VALUES ==") +for name, rgb in COLORS.items(): + print(f" {name:6} {{ {rgb[0]:#06x}, {rgb[1]:#06x}, {rgb[2]:#06x} }}") +print() + +for enc, (kr, kb) in ENCODINGS.items(): + for limited in (False, True): + m = rgb_matrix(kr, kb, limited) + y_offset = 16 if limited else 0 + print(f"== {enc} {'LIMITED' if limited else 'FULL'} (y_offset={y_offset}) ==") + for row in m: + print(" { " + ", ".join(str(round(v * FP)) for v in row) + " },") + for name, yuv in ref_yuv(m, y_offset).items(): + print(f" {name:6} {{ {yuv[0]:#06x}, {yuv[1]:#06x}, {yuv[2]:#06x} }}") + print() diff --git a/drivers/gpu/drm/vkms/tests/vkms_format_test.c b/drivers/gpu/drm/vkms/tests/vkms_format_test.c index a7788fbc45dc..d2ae6321383b 100644 --- a/drivers/gpu/drm/vkms/tests/vkms_format_test.c +++ b/drivers/gpu/drm/vkms/tests/vkms_format_test.c @@ -54,6 +54,8 @@ struct yuv_u16_to_argb_u16_case { * The YUV color representation were acquired via the colour python framework. * Below are the function calls used for generating each case. * + * The limited-range cases are generated by gen_yuv_conversion.py. + * * For more information got to the docs: * https://colour.readthedocs.io/en/master/generated/colour.RGB_to_YCbCr.html */ @@ -101,12 +103,12 @@ static struct yuv_u16_to_argb_u16_case yuv_u16_to_argb_u16_cases[] = { .range = DRM_COLOR_YCBCR_LIMITED_RANGE, .n_colors = 6, .colors = { - { "white", { 0xeb00, 0x8000, 0x8000 }, { 0xffff, 0xffff, 0xffff, 0xffff }}, - { "gray", { 0x7dee, 0x8000, 0x8000 }, { 0xffff, 0x8080, 0x8080, 0x8080 }}, - { "black", { 0x1000, 0x8000, 0x8000 }, { 0xffff, 0x0000, 0x0000, 0x0000 }}, - { "red", { 0x517b, 0x5a34, 0xf000 }, { 0xffff, 0xffff, 0x0000, 0x0000 }}, - { "green", { 0x908e, 0x35cc, 0x2237 }, { 0xffff, 0x0000, 0xffff, 0x0000 }}, - { "blue", { 0x28f7, 0xf000, 0x6dc9 }, { 0xffff, 0x0000, 0x0000, 0xffff }}, + { "white", { 0xebeb, 0x8080, 0x8080 }, { 0xffff, 0xffff, 0xffff, 0xffff }}, + { "gray", { 0x7e6c, 0x8080, 0x8080 }, { 0xffff, 0x8080, 0x8080, 0x8080 }}, + { "black", { 0x1010, 0x8080, 0x8080 }, { 0xffff, 0x0000, 0x0000, 0x0000 }}, + { "red", { 0x51cd, 0x5a8e, 0xf0f0 }, { 0xffff, 0xffff, 0x0000, 0x0000 }}, + { "green", { 0x911e, 0x3602, 0x2259 }, { 0xffff, 0x0000, 0xffff, 0x0000 }}, + { "blue", { 0x2920, 0xf0f0, 0x6e37 }, { 0xffff, 0x0000, 0x0000, 0xffff }}, } }, /* @@ -151,12 +153,12 @@ static struct yuv_u16_to_argb_u16_case yuv_u16_to_argb_u16_cases[] = { .range = DRM_COLOR_YCBCR_LIMITED_RANGE, .n_colors = 6, .colors = { - { "white", { 0xeb00, 0x8000, 0x8000 }, { 0xffff, 0xffff, 0xffff, 0xffff }}, - { "gray", { 0x7dee, 0x8000, 0x8000 }, { 0xffff, 0x8080, 0x8080, 0x8080 }}, - { "black", { 0x1000, 0x8000, 0x8000 }, { 0xffff, 0x0000, 0x0000, 0x0000 }}, - { "red", { 0x3e8f, 0x6656, 0xf000 }, { 0xffff, 0xffff, 0x0000, 0x0000 }}, - { "green", { 0xaca1, 0x29aa, 0x1a45 }, { 0xffff, 0x0000, 0xffff, 0x0000 }}, - { "blue", { 0x1fd0, 0xf000, 0x75bb }, { 0xffff, 0x0000, 0x0000, 0xffff }}, + { "white", { 0xebeb, 0x8080, 0x8080 }, { 0xffff, 0xffff, 0xffff, 0xffff }}, + { "gray", { 0x7e6c, 0x8080, 0x8080 }, { 0xffff, 0x8080, 0x8080, 0x8080 }}, + { "black", { 0x1010, 0x8080, 0x8080 }, { 0xffff, 0x0000, 0x0000, 0x0000 }}, + { "red", { 0x3ece, 0x66bc, 0xf0f0 }, { 0xffff, 0xffff, 0x0000, 0x0000 }}, + { "green", { 0xad4e, 0x29d4, 0x1a5f }, { 0xffff, 0x0000, 0xffff, 0x0000 }}, + { "blue", { 0x1ff0, 0xf0f0, 0x7631 }, { 0xffff, 0x0000, 0x0000, 0xffff }}, } }, /* @@ -201,12 +203,12 @@ static struct yuv_u16_to_argb_u16_case yuv_u16_to_argb_u16_cases[] = { .range = DRM_COLOR_YCBCR_LIMITED_RANGE, .n_colors = 6, .colors = { - { "white", { 0xeb00, 0x8000, 0x8000 }, { 0xffff, 0xffff, 0xffff, 0xffff }}, - { "gray", { 0x7dee, 0x8000, 0x8000 }, { 0xffff, 0x8080, 0x8080, 0x8080 }}, - { "black", { 0x1000, 0x8000, 0x8000 }, { 0xffff, 0x0000, 0x0000, 0x0000 }}, - { "red", { 0x4988, 0x60b9, 0xf000 }, { 0xffff, 0xffff, 0x0000, 0x0000 }}, - { "green", { 0xa47b, 0x2f47, 0x1902 }, { 0xffff, 0x0000, 0xffff, 0x0000 }}, - { "blue", { 0x1cfd, 0xf000, 0x76fe }, { 0xffff, 0x0000, 0x0000, 0xffff }}, + { "white", { 0xebeb, 0x8080, 0x8080 }, { 0xffff, 0xffff, 0xffff, 0xffff }}, + { "gray", { 0x7e6c, 0x8080, 0x8080 }, { 0xffff, 0x8080, 0x8080, 0x8080 }}, + { "black", { 0x1010, 0x8080, 0x8080 }, { 0xffff, 0x0000, 0x0000, 0x0000 }}, + { "red", { 0x49d2, 0x611a, 0xf0f0 }, { 0xffff, 0xffff, 0x0000, 0x0000 }}, + { "green", { 0xa520, 0x2f76, 0x191b }, { 0xffff, 0x0000, 0xffff, 0x0000 }}, + { "blue", { 0x1d1a, 0xf0f0, 0x7775 }, { 0xffff, 0x0000, 0x0000, 0xffff }}, } }, }; diff --git a/drivers/gpu/drm/vkms/vkms_formats.c b/drivers/gpu/drm/vkms/vkms_formats.c index dfb8e13cba87..4d5fcaeb82c5 100644 --- a/drivers/gpu/drm/vkms/vkms_formats.c +++ b/drivers/gpu/drm/vkms/vkms_formats.c @@ -788,15 +788,36 @@ static const struct conversion_matrix yuv_bt601_full = { }; /* - * numpy.around(colour.matrix_YCbCr(K=colour.WEIGHTS_YCBCR["ITU-R BT.601"], - * is_legal = True, - * bits = 8) * 2**32).astype(int) + * BT.601 limited-/studio-range YCbCr to full-range RGB. + * + * The coefficients are derived as follows: + * + * 1. Take the standard ITU-R YCbCr -> RGB relations for luma weights + * Kr, Kb (Kg = 1 - Kr - Kb), with Y in [0, 1] and Cb, Cr in + * [-0.5, 0.5]. For BT.601 Kr = 0.299 and Kb = 0.114: + * + * R = Y + 2 * (1 - Kr) * Cr + * G = Y - 2 * (1 - Kb) * Kb / Kg * Cb - 2 * (1 - Kr) * Kr / Kg * Cr + * B = Y + 2 * (1 - Kb) * Cb + * + * These are exactly the yuv_bt601_full coefficients above. + * + * 2. Expand the studio input range to full range, relative to a + * full-range maximum of 2^n - 1 (255 for 8-bit): the luma + * coefficient is scaled by 255/(235 - 16) and the chroma + * coefficients by 255/(240 - 16). This matches the DRM UAPI + * definition and IGT's igt_ycbcr_to_rgb_matrix(). Note this differs + * from colour.matrix_YCbCr(is_legal=True), which normalises by 2^n + * and is thus off by a factor of 256/255. + * + * 3. Convert each coefficient to S31.32 fixed point, i.e. + * round(coeff * 2^32). */ static const struct conversion_matrix yuv_bt601_limited = { .matrix = { - { 5020601039, 0, 6881764740 }, - { 5020601039, -1689204679, -3505362278 }, - { 5020601039, 8697922339, 0 }, + { 5000989317, 0, 6854882848 }, + { 5000989317, -1682606224, -3491669458 }, + { 5000989317, 8663946082, 0 }, }, .y_offset = 16, }; @@ -816,15 +837,14 @@ static const struct conversion_matrix yuv_bt709_full = { }; /* - * numpy.around(colour.matrix_YCbCr(K=colour.WEIGHTS_YCBCR["ITU-R BT.709"], - * is_legal = True, - * bits = 8) * 2**32).astype(int) + * BT.709 limited-range YCbCr to full-range RGB (Kr = 0.2126, Kb = 0.0722). + * Derived as described for yuv_bt601_limited. */ static const struct conversion_matrix yuv_bt709_limited = { .matrix = { - { 5020601039, 0, 7729959424 }, - { 5020601039, -919487572, -2297803934 }, - { 5020601039, 9108275786, 0 }, + { 5000989317, 0, 7699764272 }, + { 5000989317, -915895824, -2288828138 }, + { 5000989317, 9072696586, 0 }, }, .y_offset = 16, }; @@ -844,15 +864,14 @@ static const struct conversion_matrix yuv_bt2020_full = { }; /* - * numpy.around(colour.matrix_YCbCr(K=colour.WEIGHTS_YCBCR["ITU-R BT.2020"], - * is_legal = True, - * bits = 8) * 2**32).astype(int) + * BT.2020 non-constant-luminance limited-range YCbCr to full-range RGB + * (Kr = 0.2627, Kb = 0.0593). Derived as described for yuv_bt601_limited. */ static const struct conversion_matrix yuv_bt2020_limited = { .matrix = { - { 5020601039, 0, 7238124312 }, - { 5020601039, -807714626, -2804506279 }, - { 5020601039, 9234915964, 0 }, + { 5000989317, 0, 7209850391 }, + { 5000989317, -804559491, -2793551177 }, + { 5000989317, 9198842076, 0 }, }, .y_offset = 16, };