From 2271e0a20ef795838527815e057f5af206b69c87 Mon Sep 17 00:00:00 2001
From: Robert Mader <robert.mader@collabora.com>
Date: Fri, 9 May 2025 15:35:35 +0200
Subject: [PATCH 3849/5403] drm: drm_fourcc: add 10/12/16bit software decoder
 YCbCr formats

This adds FOURCCs for 3-plane 10/12/16bit YCbCr formats used by software
decoders like ffmpeg, dav1d and libvpx. The intended use-case is buffer
sharing between decoders and GPUs by allocating buffers with e.g. udmabuf
or dma-heaps, avoiding unnecessary copies and format conversions in
various scenarios.

Unlike formats typically used by hardware decoders the 10/12bit formats
use a LSB alignment. In order to allow fast implementations in GL
and Vulkan the padding must contain only zeros, so the float
representation can be calculated by multiplying with 2^6=64 or 2^4=16
respectively.

MRs or branches for Mesa, Vulkan, Gstreamer, Weston and Mutter can be found at:
 - https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/34303
 - https://github.com/rmader/Vulkan-Docs/commits/ycbcr-16bit-lsb-formats/
 - https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/8540
 - https://gitlab.freedesktop.org/wayland/weston/-/merge_requests/1753
 - https://gitlab.gnome.org/GNOME/mutter/-/merge_requests/4348

The naming scheme follows the 'P' and 'Q' formats. The 'S' stands for
'software' and was selected in order to make remembering easy.

The 'Sx16' formats could as well be 'Qx16'. We stick with 'S' as 16bit software
decoders are likely much more common than hardware ones for the foreseeable
future. Note that these formats already have Vulkan equivalents:
 - VK_FORMAT_G16_B16_R16_3PLANE_420_UNORM
 - VK_FORMAT_G16_B16_R16_3PLANE_422_UNORM
 - VK_FORMAT_G16_B16_R16_3PLANE_444_UNORM

Signed-off-by: Robert Mader <robert.mader@collabora.com>
Reviewed-by: Daniel Stone <daniels@collabora.com>
Link: https://lore.kernel.org/r/20250509133535.60330-1-robert.mader@collabora.com
Signed-off-by: Daniel Stone <daniels@collabora.com>
---
 drivers/gpu/drm/drm_fourcc.c  | 27 ++++++++++++++++++++++++++
 include/uapi/drm/drm_fourcc.h | 36 +++++++++++++++++++++++++++++++++++
 2 files changed, 63 insertions(+)

diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c
index 3a94ca211f9c..55ddd99fd7f6 100644
--- a/drivers/gpu/drm/drm_fourcc.c
+++ b/drivers/gpu/drm/drm_fourcc.c
@@ -346,6 +346,33 @@ const struct drm_format_info *__drm_format_info(u32 format)
 		{ .format = DRM_FORMAT_P030,            .depth = 0,  .num_planes = 2,
 		  .char_per_block = { 4, 8, 0 }, .block_w = { 3, 3, 0 }, .block_h = { 1, 1, 0 },
 		  .hsub = 2, .vsub = 2, .is_yuv = true},
+		{ .format = DRM_FORMAT_S010,            .depth = 0,  .num_planes = 3,
+		  .char_per_block = { 2, 2, 2 }, .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 },
+		  .hsub = 2, .vsub = 2, .is_yuv = true},
+		{ .format = DRM_FORMAT_S210,            .depth = 0,  .num_planes = 3,
+		  .char_per_block = { 2, 2, 2 }, .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 },
+		  .hsub = 2, .vsub = 1, .is_yuv = true},
+		{ .format = DRM_FORMAT_S410,            .depth = 0,  .num_planes = 3,
+		  .char_per_block = { 2, 2, 2 }, .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 },
+		  .hsub = 1, .vsub = 1, .is_yuv = true},
+		{ .format = DRM_FORMAT_S012,            .depth = 0,  .num_planes = 3,
+		  .char_per_block = { 2, 2, 2 }, .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 },
+		  .hsub = 2, .vsub = 2, .is_yuv = true},
+		{ .format = DRM_FORMAT_S212,            .depth = 0,  .num_planes = 3,
+		  .char_per_block = { 2, 2, 2 }, .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 },
+		  .hsub = 2, .vsub = 1, .is_yuv = true},
+		{ .format = DRM_FORMAT_S412,            .depth = 0,  .num_planes = 3,
+		  .char_per_block = { 2, 2, 2 }, .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 },
+		  .hsub = 1, .vsub = 1, .is_yuv = true},
+		{ .format = DRM_FORMAT_S016,            .depth = 0,  .num_planes = 3,
+		  .char_per_block = { 2, 2, 2 }, .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 },
+		  .hsub = 2, .vsub = 2, .is_yuv = true},
+		{ .format = DRM_FORMAT_S216,            .depth = 0,  .num_planes = 3,
+		  .char_per_block = { 2, 2, 2 }, .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 },
+		  .hsub = 2, .vsub = 1, .is_yuv = true},
+		{ .format = DRM_FORMAT_S416,            .depth = 0,  .num_planes = 3,
+		  .char_per_block = { 2, 2, 2 }, .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 },
+		  .hsub = 1, .vsub = 1, .is_yuv = true},
 	};
 
 	unsigned int i;
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index 81202a50dc9e..6483f76a2165 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -377,6 +377,42 @@ extern "C" {
  */
 #define DRM_FORMAT_Q401		fourcc_code('Q', '4', '0', '1')
 
+/*
+ * 3 plane YCbCr LSB aligned
+ * In order to use these formats in a similar fashion to MSB aligned ones
+ * implementation can multiply the values by 2^6=64. For that reason the padding
+ * must only contain zeros.
+ * index 0 = Y plane, [15:0] z:Y [6:10] little endian
+ * index 1 = Cr plane, [15:0] z:Cr [6:10] little endian
+ * index 2 = Cb plane, [15:0] z:Cb [6:10] little endian
+ */
+#define DRM_FORMAT_S010	fourcc_code('S', '0', '1', '0') /* 2x2 subsampled Cb (1) and Cr (2) planes 10 bits per channel */
+#define DRM_FORMAT_S210	fourcc_code('S', '2', '1', '0') /* 2x1 subsampled Cb (1) and Cr (2) planes 10 bits per channel */
+#define DRM_FORMAT_S410	fourcc_code('S', '4', '1', '0') /* non-subsampled Cb (1) and Cr (2) planes 10 bits per channel */
+
+/*
+ * 3 plane YCbCr LSB aligned
+ * In order to use these formats in a similar fashion to MSB aligned ones
+ * implementation can multiply the values by 2^4=16. For that reason the padding
+ * must only contain zeros.
+ * index 0 = Y plane, [15:0] z:Y [4:12] little endian
+ * index 1 = Cr plane, [15:0] z:Cr [4:12] little endian
+ * index 2 = Cb plane, [15:0] z:Cb [4:12] little endian
+ */
+#define DRM_FORMAT_S012	fourcc_code('S', '0', '1', '2') /* 2x2 subsampled Cb (1) and Cr (2) planes 12 bits per channel */
+#define DRM_FORMAT_S212	fourcc_code('S', '2', '1', '2') /* 2x1 subsampled Cb (1) and Cr (2) planes 12 bits per channel */
+#define DRM_FORMAT_S412	fourcc_code('S', '4', '1', '2') /* non-subsampled Cb (1) and Cr (2) planes 12 bits per channel */
+
+/*
+ * 3 plane YCbCr
+ * index 0 = Y plane, [15:0] Y little endian
+ * index 1 = Cr plane, [15:0] Cr little endian
+ * index 2 = Cb plane, [15:0] Cb little endian
+ */
+#define DRM_FORMAT_S016	fourcc_code('S', '0', '1', '6') /* 2x2 subsampled Cb (1) and Cr (2) planes 16 bits per channel */
+#define DRM_FORMAT_S216	fourcc_code('S', '2', '1', '6') /* 2x1 subsampled Cb (1) and Cr (2) planes 16 bits per channel */
+#define DRM_FORMAT_S416	fourcc_code('S', '4', '1', '6') /* non-subsampled Cb (1) and Cr (2) planes 16 bits per channel */
+
 /*
  * 3 plane YCbCr
  * index 0: Y plane, [7:0] Y
-- 
2.54.0

