openwrt/target/linux/bcm27xx/patches-5.4/950-0499-media-videodev2.h-Add-a-format-for-column-YUV4-2-0-m.patch

From a8f52dad0ed65192eb880a4a1ca90b236e99711e Mon Sep 17 00:00:00 2001
From: Dave Stevenson <dave.stevenson@raspberrypi.com>
Date: Fri, 24 Jan 2020 14:28:21 +0000
Subject: [PATCH] media: videodev2.h: Add a format for column YUV4:2:0
 modes

Some of the Broadcom codec blocks use a column based YUV4:2:0 image
format, so add the documentation and defines for both 8 and 10 bit
versions.

Signed-off-by: Dave Stevenson <dave.stevenson@raspberrypi.com>
---
 .../media/uapi/v4l/pixfmt-nv12-col128.rst     | 215 ++++++++++++++++++
 Documentation/media/uapi/v4l/pixfmt-nv12.rst  |  14 +-
 Documentation/media/uapi/v4l/yuv-formats.rst  |   1 +
 drivers/media/v4l2-core/v4l2-ioctl.c          |   2 +
 include/uapi/linux/videodev2.h                |   4 +
 5 files changed, 233 insertions(+), 3 deletions(-)
 create mode 100644 Documentation/media/uapi/v4l/pixfmt-nv12-col128.rst

--- /dev/null
+++ b/Documentation/media/uapi/v4l/pixfmt-nv12-col128.rst
@@ -0,0 +1,215 @@
+.. Permission is granted to copy, distribute and/or modify this
+.. document under the terms of the GNU Free Documentation License,
+.. Version 1.1 or any later version published by the Free Software
+.. Foundation, with no Invariant Sections, no Front-Cover Texts
+.. and no Back-Cover Texts. A copy of the license is included at
+.. Documentation/media/uapi/fdl-appendix.rst.
+..
+.. TODO: replace it to GFDL-1.1-or-later WITH no-invariant-sections
+
+.. _V4L2_PIX_FMT_NV12_COL128:
+.. _V4L2_PIX_FMT_NV12_10_COL128:
+
+********************************************************************************
+V4L2_PIX_FMT_NV12_COL128, V4L2_PIX_FMT_NV12_10_COL128
+********************************************************************************
+
+
+V4L2_PIX_FMT_NV21_COL128
+Formats with ½ horizontal and vertical chroma resolution. This format
+has two planes - one for luminance and one for chrominance. Chroma
+samples are interleaved. The difference to ``V4L2_PIX_FMT_NV12`` is the
+memory layout. The image is split into columns of 128 bytes wide rather than
+being in raster order.
+
+V4L2_PIX_FMT_NV12_10_COL128
+Follows the same pattern as ``V4L2_PIX_FMT_NV21_COL128`` with 128 byte, but is
+a 10bit format with 3 10-bit samples being packed into 4 bytes. Each 128 byte
+wide column therefore contains 96 samples.
+
+
+Description
+===========
+
+This is the two-plane versions of the YUV 4:2:0 format where data is
+grouped into 128 byte wide columns. The three components are separated into
+two sub-images or planes. The Y plane has one byte per pixel and pixels
+are grouped into 128 byte wide columns. The CbCr plane has the same width,
+in bytes, as the Y plane (and the image), but is half as tall in pixels.
+The chroma plane is also in 128 byte columns, reflecting 64 Cb and 64 Cr
+samples.
+
+The chroma samples for a column follow the luma samples. If there is any
+paddding, then that will be reflected via the selection API.
+The luma height must be a multiple of 2 lines.
+
+The normal bytesperline is effectively fixed at 128. However the format
+requires knowledge of the stride between columns, therefore the bytesperline
+value has been repurposed to denote the number of 128 byte long lines between
+the start of each column.
+
+**Byte Order.**
+
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+    :widths: 12 12 12 12 12 4 12 12 12 12
+
+    * - start + 0:
+      - Y'\ :sub:`0,0`
+      - Y'\ :sub:`0,1`
+      - Y'\ :sub:`0,2`
+      - Y'\ :sub:`0,3`
+      - ...
+      - Y'\ :sub:`0,124`
+      - Y'\ :sub:`0,125`
+      - Y'\ :sub:`0,126`
+      - Y'\ :sub:`0,127`
+    * - start + 128:
+      - Y'\ :sub:`1,0`
+      - Y'\ :sub:`1,1`
+      - Y'\ :sub:`1,2`
+      - Y'\ :sub:`1,3`
+      - ...
+      - Y'\ :sub:`1,124`
+      - Y'\ :sub:`1,125`
+      - Y'\ :sub:`1,126`
+      - Y'\ :sub:`1,127`
+    * - start + 256:
+      - Y'\ :sub:`2,0`
+      - Y'\ :sub:`2,1`
+      - Y'\ :sub:`2,2`
+      - Y'\ :sub:`2,3`
+      - ...
+      - Y'\ :sub:`2,124`
+      - Y'\ :sub:`2,125`
+      - Y'\ :sub:`2,126`
+      - Y'\ :sub:`2,127`
+    * - ...
+      - ...
+      - ...
+      - ...
+      - ...
+      - ...
+      - ...
+      - ...
+    * - start + ((height-1) * 128):
+      - Y'\ :sub:`height-1,0`
+      - Y'\ :sub:`height-1,1`
+      - Y'\ :sub:`height-1,2`
+      - Y'\ :sub:`height-1,3`
+      - ...
+      - Y'\ :sub:`height-1,124`
+      - Y'\ :sub:`height-1,125`
+      - Y'\ :sub:`height-1,126`
+      - Y'\ :sub:`height-1,127`
+    * - start + ((height) * 128):
+      - Cb\ :sub:`0,0`
+      - Cr\ :sub:`0,0`
+      - Cb\ :sub:`0,1`
+      - Cr\ :sub:`0,1`
+      - ...
+      - Cb\ :sub:`0,62`
+      - Cr\ :sub:`0,62`
+      - Cb\ :sub:`0,63`
+      - Cr\ :sub:`0,63`
+    * - start + ((height+1) * 128):
+      - Cb\ :sub:`1,0`
+      - Cr\ :sub:`1,0`
+      - Cb\ :sub:`1,1`
+      - Cr\ :sub:`1,1`
+      - ...
+      - Cb\ :sub:`1,62`
+      - Cr\ :sub:`1,62`
+      - Cb\ :sub:`1,63`
+      - Cr\ :sub:`1,63`
+    * - ...
+      - ...
+      - ...
+      - ...
+      - ...
+      - ...
+      - ...
+      - ...
+    * - start + ((height+(height/2)-1) * 128):
+      - Cb\ :sub:`(height/2)-1,0`
+      - Cr\ :sub:`(height/2)-1,0`
+      - Cb\ :sub:`(height/2)-1,1`
+      - Cr\ :sub:`(height/2)-1,1`
+      - ...
+      - Cb\ :sub:`(height/2)-1,62`
+      - Cr\ :sub:`(height/2)-1,62`
+      - Cb\ :sub:`(height/2)-1,63`
+      - Cr\ :sub:`(height/2)-1,63`
+    * - start + (bytesperline * 128):
+      - Y'\ :sub:`0,128`
+      - Y'\ :sub:`0,129`
+      - Y'\ :sub:`0,130`
+      - Y'\ :sub:`0,131`
+      - ...
+      - Y'\ :sub:`0,252`
+      - Y'\ :sub:`0,253`
+      - Y'\ :sub:`0,254`
+      - Y'\ :sub:`0,255`
+    * - ...
+      - ...
+      - ...
+      - ...
+      - ...
+      - ...
+      - ...
+      - ...
+
+V4L2_PIX_FMT_NV12_10_COL128 uses the same 128 byte column structure, but
+encodes 10-bit YUV.
+3 10-bit values are packed into 4 bytes as bits 9:0, 19:10, and 29:20, with
+bits 30 & 31 unused. For the luma plane, bits 9:0 are Y0, 19:10 are Y1, and
+29:20 are Y2. For the chroma plane the samples always come in pairs of Cr
+and Cb, so it needs to be considered 6 values packed in 8 bytes.
+
+Bit-packed representation.
+
+.. raw:: latex
+
+    \small
+
+.. tabularcolumns:: |p{1.2cm}||p{1.2cm}||p{1.2cm}||p{1.2cm}|p{3.2cm}|p{3.2cm}|
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+    :widths: 8 8 8 8
+
+    * - Y'\ :sub:`00[7:0]`
+      - Y'\ :sub:`01[5:0] (bits 7--2)` Y'\ :sub:`00[9:8]`\ (bits 1--0)
+      - Y'\ :sub:`02[3:0] (bits 7--4)` Y'\ :sub:`01[9:6]`\ (bits 3--0)
+      - unused (bits 7--6)` Y'\ :sub:`02[9:4]`\ (bits 5--0)
+
+.. raw:: latex
+
+    \small
+
+.. tabularcolumns:: |p{1.2cm}||p{1.2cm}||p{1.2cm}||p{1.2cm}|p{3.2cm}|p{3.2cm}|
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+    :widths: 12 12 12 12 12 12 12 12
+
+    * - Cb\ :sub:`00[7:0]`
+      - Cr\ :sub:`00[5:0]`\ (bits 7--2) Cb\ :sub:`00[9:8]`\ (bits 1--0)
+      - Cb\ :sub:`01[3:0]`\ (bits 7--4) Cr\ :sub:`00[9:6]`\ (bits 3--0)
+      - unused (bits 7--6) Cb\ :sub:`02[9:4]`\ (bits 5--0)
+      - Cr\ :sub:`01[7:0]`
+      - Cb\ :sub:`02[5:0]`\ (bits 7--2) Cr\ :sub:`01[9:8]`\ (bits 1--0)
+      - Cr\ :sub:`02[3:0]`\ (bits 7--4) Cb\ :sub:`02[9:6]`\ (bits 3--0)
+      - unused (bits 7--6) Cr\ :sub:`02[9:4]`\ (bits 5--0)
+
+.. raw:: latex
+
+    \normalsize
+
+
+
+
--- a/Documentation/media/uapi/v4l/pixfmt-nv12.rst
+++ b/Documentation/media/uapi/v4l/pixfmt-nv12.rst
@@ -10,9 +10,9 @@
 .. _V4L2-PIX-FMT-NV12:
 .. _V4L2-PIX-FMT-NV21:
 
-******************************************************
-V4L2_PIX_FMT_NV12 ('NV12'), V4L2_PIX_FMT_NV21 ('NV21')
-******************************************************
+********************************************************************************
+V4L2_PIX_FMT_NV12 ('NV12'), V4L2_PIX_FMT_NV21 ('NV21'), V4L2_PIX_FMT_NV12_COL128
+********************************************************************************
 
 
 V4L2_PIX_FMT_NV21
@@ -38,6 +38,14 @@ with a Cr byte.
 If the Y plane has pad bytes after each row, then the CbCr plane has as
 many pad bytes after its rows.
 
+``V4L2_PIX_FMT_NV12_COL128`` is the tiled version of
+``V4L2_PIX_FMT_NV12`` with the image broken down into 128 pixel wide columns of
+Y followed by the associated combined CbCr plane.
+The normal bytesperline is effectively fixed at 128. However the format
+requires knowledge of the stride between columns, therefore the bytesperline
+value has been repurposed to denote the number of 128 byte long lines between
+the start of each column.
+
 **Byte Order.**
 Each cell is one byte.
 
--- a/Documentation/media/uapi/v4l/yuv-formats.rst
+++ b/Documentation/media/uapi/v4l/yuv-formats.rst
@@ -57,6 +57,7 @@ to brightness information.
     pixfmt-nv12
     pixfmt-nv12m
     pixfmt-nv12mt
+    pixfmt-nv12-col128
     pixfmt-nv16
     pixfmt-nv16m
     pixfmt-nv24
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -1258,6 +1258,8 @@ static void v4l_fill_fmtdesc(struct v4l2
 	case V4L2_PIX_FMT_NV61M:	descr = "Y/CrCb 4:2:2 (N-C)"; break;
 	case V4L2_PIX_FMT_NV12MT:	descr = "Y/CbCr 4:2:0 (64x32 MB, N-C)"; break;
 	case V4L2_PIX_FMT_NV12MT_16X16:	descr = "Y/CbCr 4:2:0 (16x16 MB, N-C)"; break;
+	case V4L2_PIX_FMT_NV12_COL128:	descr = "Y/CbCr 4:2:0 (128b cols)"; break;
+	case V4L2_PIX_FMT_NV12_10_COL128: descr = "10-bit Y/CbCr 4:2:0 (128b cols)"; break;
 	case V4L2_PIX_FMT_YUV420M:	descr = "Planar YUV 4:2:0 (N-C)"; break;
 	case V4L2_PIX_FMT_YVU420M:	descr = "Planar YVU 4:2:0 (N-C)"; break;
 	case V4L2_PIX_FMT_YUV422M:	descr = "Planar YUV 4:2:2 (N-C)"; break;
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -736,6 +736,10 @@ struct v4l2_pix_format {
 #define V4L2_PIX_FMT_INZI     v4l2_fourcc('I', 'N', 'Z', 'I') /* Intel Planar Greyscale 10-bit and Depth 16-bit */
 #define V4L2_PIX_FMT_SUNXI_TILED_NV12 v4l2_fourcc('S', 'T', '1', '2') /* Sunxi Tiled NV12 Format */
 #define V4L2_PIX_FMT_CNF4     v4l2_fourcc('C', 'N', 'F', '4') /* Intel 4-bit packed depth confidence information */
+#define V4L2_PIX_FMT_NV12_COL128 v4l2_fourcc('N', 'C', '1', '2') /* 12  Y/CbCr 4:2:0 128 pixel wide column */
+#define V4L2_PIX_FMT_NV12_10_COL128 v4l2_fourcc('N', 'C', '3', '0')
+								/* Y/CbCr 4:2:0 10bpc, 3x10 packed as 4 bytes in
+								 * a 128 bytes / 96 pixel wide column */
 
 /* 10bit raw bayer packed, 32 bytes for every 25 pixels, last LSB 6 bits unused */
 #define V4L2_PIX_FMT_IPU3_SBGGR10	v4l2_fourcc('i', 'p', '3', 'b') /* IPU3 packed 10-bit BGGR bayer */