media: add nv12m_8l128 and nv12m_10be_8l128 video format.

nv12m_8l128 is 8-bit tiled nv12 format used by amphion decoder.
nv12m_10be_8l128 is 10-bit tiled format used by amphion decoder.
The tile size is 8x128
Signed-off-by: Ming Qian <ming.qian@nxp.com>
Signed-off-by: Shijie Qin <shijie.qin@nxp.com>
Signed-off-by: Zhou Peng <eagle.zhou@nxp.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>

Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst

@@ -257,6 +257,8 @@ of the luma plane.
 .. _V4L2-PIX-FMT-NV12-4L4:
 .. _V4L2-PIX-FMT-NV12-16L16:
 .. _V4L2-PIX-FMT-NV12-32L32:
+.. _V4L2_PIX_FMT_NV12M_8L128:
+.. _V4L2_PIX_FMT_NV12M_10BE_8L128:
 
 Tiled NV12
 ----------
@@ -281,21 +283,41 @@ If the vertical resolution is an odd number of tiles, the last row of
 tiles is stored in linear order. The layouts of the luma and chroma
 planes are identical.
 
-``V4L2_PIX_FMT_NV12_4L4`` stores pixel in 4x4 tiles, and stores
+``V4L2_PIX_FMT_NV12_4L4`` stores pixels in 4x4 tiles, and stores
 tiles linearly in memory. The line stride and image height must be
 aligned to a multiple of 4. The layouts of the luma and chroma planes are
 identical.
 
-``V4L2_PIX_FMT_NV12_16L16`` stores pixel in 16x16 tiles, and stores
+``V4L2_PIX_FMT_NV12_16L16`` stores pixels in 16x16 tiles, and stores
 tiles linearly in memory. The line stride and image height must be
 aligned to a multiple of 16. The layouts of the luma and chroma planes are
 identical.
 
-``V4L2_PIX_FMT_NV12_32L32`` stores pixel in 32x32 tiles, and stores
+``V4L2_PIX_FMT_NV12_32L32`` stores pixels in 32x32 tiles, and stores
 tiles linearly in memory. The line stride and image height must be
 aligned to a multiple of 32. The layouts of the luma and chroma planes are
 identical.
 
+``V4L2_PIX_FMT_NV12M_8L128`` is similar to ``V4L2_PIX_FMT_NV12M`` but stores
+pixels in 2D 8x128 tiles, and stores tiles linearly in memory.
+The image height must be aligned to a multiple of 128.
+The layouts of the luma and chroma planes are identical.
+
+``V4L2_PIX_FMT_NV12M_10BE_8L128`` is similar to ``V4L2_PIX_FMT_NV12M`` but stores
+10 bits pixels in 2D 8x128 tiles, and stores tiles linearly in memory.
+the data is arranged in big endian order.
+The image height must be aligned to a multiple of 128.
+The layouts of the luma and chroma planes are identical.
+Note the tile size is 8bytes multiplied by 128 bytes,
+it means that the low bits and high bits of one pixel may be in different tiles.
+The 10 bit pixels are packed, so 5 bytes contain 4 10-bit pixels layout like
+this (for luma):
+byte 0: Y0(bits 9-2)
+byte 1: Y0(bits 1-0) Y1(bits 9-4)
+byte 2: Y1(bits 3-0) Y2(bits 9-6)
+byte 3: Y2(bits 5-0) Y3(bits 9-8)
+byte 4: Y3(bits 7-0)
+
 ``V4L2_PIX_FMT_MM21`` store luma pixel in 16x32 tiles, and chroma pixels
 in 16x16 tiles. The line stride must be aligned to a multiple of 16 and the
 image height must be aligned to a multiple of 32. The number of luma and chroma

drivers/media/v4l2-core/v4l2-ioctl.c

@@ -1390,6 +1390,8 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt)
 	case V4L2_META_FMT_VIVID:       descr = "Vivid Metadata"; break;
 	case V4L2_META_FMT_RK_ISP1_PARAMS:	descr = "Rockchip ISP1 3A Parameters"; break;
 	case V4L2_META_FMT_RK_ISP1_STAT_3A:	descr = "Rockchip ISP1 3A Statistics"; break;
+	case V4L2_PIX_FMT_NV12M_8L128:	descr = "NV12M (8x128 Linear)"; break;
+	case V4L2_PIX_FMT_NV12M_10BE_8L128:	descr = "10-bit NV12M (8x128 Linear, BE)"; break;
 
 	default:
 		/* Compressed formats */

include/uapi/linux/videodev2.h

@@ -632,6 +632,8 @@ struct v4l2_pix_format {
 /* Tiled YUV formats, non contiguous planes */
 #define V4L2_PIX_FMT_NV12MT  v4l2_fourcc('T', 'M', '1', '2') /* 12  Y/CbCr 4:2:0 64x32 tiles */
 #define V4L2_PIX_FMT_NV12MT_16X16 v4l2_fourcc('V', 'M', '1', '2') /* 12  Y/CbCr 4:2:0 16x16 tiles */
+#define V4L2_PIX_FMT_NV12M_8L128      v4l2_fourcc('N', 'A', '1', '2') /* Y/CbCr 4:2:0 8x128 tiles */
+#define V4L2_PIX_FMT_NV12M_10BE_8L128 v4l2_fourcc_be('N', 'T', '1', '2') /* Y/CbCr 4:2:0 10-bit 8x128 tiles */
 
 /* Bayer formats - see http://www.siliconimaging.com/RGB%20Bayer.htm */
 #define V4L2_PIX_FMT_SBGGR8  v4l2_fourcc('B', 'A', '8', '1') /*  8  BGBG.. GRGR.. */