From 974229575250290e49d004933cb0aade87fa4566 Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Mon, 6 Jul 2020 21:54:33 +0000
Subject: [PATCH 04/18] media: rkvdec: h264: Fix reference frame_num wrap for
 second field

When decoding the second field in a complementary field pair the second
field is sharing the same frame_num with the first field.

Currently the frame_num for the first field is wrapped when it matches the
field being decoded, this cause issues to decode the second field in a
complementary field pair.

Fix this by using inclusive comparison, less than or equal.

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Ezequiel Garcia <ezequiel@collabora.com>
---
 drivers/staging/media/rkvdec/rkvdec-h264.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/media/rkvdec/rkvdec-h264.c b/drivers/staging/media/rkvdec/rkvdec-h264.c
index 7b66e2743a4f..f0cfed84d60d 100644
--- a/drivers/staging/media/rkvdec/rkvdec-h264.c
+++ b/drivers/staging/media/rkvdec/rkvdec-h264.c
@@ -754,7 +754,7 @@ static void assemble_hw_rps(struct rkvdec_ctx *ctx,
 			continue;
 
 		if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM ||
-		    dpb[i].frame_num < dec_params->frame_num) {
+		    dpb[i].frame_num <= dec_params->frame_num) {
 			p[i] = dpb[i].frame_num;
 			continue;
 		}
-- 
2.25.1


From 031ff8b97b208e20b49554c657e8ca9c79a079db Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Mon, 6 Jul 2020 21:54:34 +0000
Subject: [PATCH 05/18] media: rkvdec: Ensure decoded resolution fit coded
 resolution

Ensure decoded CAPTURE buffer resolution is larger or equal to the coded
OPTUPT buffer resolution.

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
---
 drivers/staging/media/rkvdec/rkvdec.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/staging/media/rkvdec/rkvdec.c b/drivers/staging/media/rkvdec/rkvdec.c
index 55dc27171ce4..4ab8f7e0566b 100644
--- a/drivers/staging/media/rkvdec/rkvdec.c
+++ b/drivers/staging/media/rkvdec/rkvdec.c
@@ -235,6 +235,8 @@ static int rkvdec_try_capture_fmt(struct file *file, void *priv,
 		pix_mp->pixelformat = coded_desc->decoded_fmts[0];
 
 	/* Always apply the frmsize constraint of the coded end. */
+	pix_mp->width = max(pix_mp->width, ctx->coded_fmt.fmt.pix_mp.width);
+	pix_mp->height = max(pix_mp->height, ctx->coded_fmt.fmt.pix_mp.height);
 	v4l2_apply_frmsize_constraints(&pix_mp->width,
 				       &pix_mp->height,
 				       &coded_desc->frmsize);
-- 
2.25.1


From 4c7271baa21e2e508593c8e87d77febff68afb6a Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Mon, 6 Jul 2020 21:54:34 +0000
Subject: [PATCH 06/18] media: rkvdec: h264: Validate and use pic width and
 height in mbs

The width and height in mbs is currently configured based on OUTPUT buffer
resolution, this works for frame pictures but can cause issues for field
pictures.

When frame_mbs_only_flag is 0 the height in mbs should be height of
the field instead of height of frame.

Validate pic_width_in_mbs_minus1 and pic_height_in_map_units_minus1
against OUTPUT buffer resolution and use these values to configure HW.

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
---
 drivers/staging/media/rkvdec/rkvdec-h264.c |  4 ++--
 drivers/staging/media/rkvdec/rkvdec.c      | 10 ++++++++++
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/media/rkvdec/rkvdec-h264.c b/drivers/staging/media/rkvdec/rkvdec-h264.c
index f0cfed84d60d..3498e9eec3d8 100644
--- a/drivers/staging/media/rkvdec/rkvdec-h264.c
+++ b/drivers/staging/media/rkvdec/rkvdec-h264.c
@@ -672,8 +672,8 @@ static void assemble_hw_pps(struct rkvdec_ctx *ctx,
 		  LOG2_MAX_PIC_ORDER_CNT_LSB_MINUS4);
 	WRITE_PPS(!!(sps->flags & V4L2_H264_SPS_FLAG_DELTA_PIC_ORDER_ALWAYS_ZERO),
 		  DELTA_PIC_ORDER_ALWAYS_ZERO_FLAG);
-	WRITE_PPS(DIV_ROUND_UP(ctx->coded_fmt.fmt.pix_mp.width, 16), PIC_WIDTH_IN_MBS);
-	WRITE_PPS(DIV_ROUND_UP(ctx->coded_fmt.fmt.pix_mp.height, 16), PIC_HEIGHT_IN_MBS);
+	WRITE_PPS(sps->pic_width_in_mbs_minus1 + 1, PIC_WIDTH_IN_MBS);
+	WRITE_PPS(sps->pic_height_in_map_units_minus1 + 1, PIC_HEIGHT_IN_MBS);
 	WRITE_PPS(!!(sps->flags & V4L2_H264_SPS_FLAG_FRAME_MBS_ONLY),
 		  FRAME_MBS_ONLY_FLAG);
 	WRITE_PPS(!!(sps->flags & V4L2_H264_SPS_FLAG_MB_ADAPTIVE_FRAME_FIELD),
diff --git a/drivers/staging/media/rkvdec/rkvdec.c b/drivers/staging/media/rkvdec/rkvdec.c
index 4ab8f7e0566b..7a9f78bc0a55 100644
--- a/drivers/staging/media/rkvdec/rkvdec.c
+++ b/drivers/staging/media/rkvdec/rkvdec.c
@@ -29,8 +29,11 @@
 
 static int rkvdec_try_ctrl(struct v4l2_ctrl *ctrl)
 {
+	struct rkvdec_ctx *ctx = container_of(ctrl->handler, struct rkvdec_ctx, ctrl_hdl);
+
 	if (ctrl->id == V4L2_CID_MPEG_VIDEO_H264_SPS) {
 		const struct v4l2_ctrl_h264_sps *sps = ctrl->p_new.p_h264_sps;
+		unsigned int width, height;
 		/*
 		 * TODO: The hardware supports 10-bit and 4:2:2 profiles,
 		 * but it's currently broken in the driver.
@@ -45,6 +48,13 @@ static int rkvdec_try_ctrl(struct v4l2_ctrl *ctrl)
 		if (sps->bit_depth_luma_minus8 != 0)
 			/* Only 8-bit is supported */
 			return -EINVAL;
+
+		width = (sps->pic_width_in_mbs_minus1 + 1) * 16;
+		height = (sps->pic_height_in_map_units_minus1 + 1) * 16;
+
+		if (width > ctx->coded_fmt.fmt.pix_mp.width ||
+		    height > ctx->coded_fmt.fmt.pix_mp.height)
+			return -EINVAL;
 	}
 	return 0;
 }
-- 
2.25.1


From d0673c50f58c79198b3c2958beaa8b88e2bdfaef Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Mon, 6 Jul 2020 21:54:35 +0000
Subject: [PATCH 07/18] media: rkvdec: h264: Fix bit depth wrap in pps packet

The luma and chroma bit depth fields in the pps packet is 3 bits wide.
8 is wrongly added to the bit depth value written to these 3-bit fields.
Because only the 3 LSB is written the hardware is configured correctly.

Correct this by not adding 8 to the luma and chroma bit depth value.

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Ezequiel Garcia <ezequiel@collabora.com>
---
 drivers/staging/media/rkvdec/rkvdec-h264.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/media/rkvdec/rkvdec-h264.c b/drivers/staging/media/rkvdec/rkvdec-h264.c
index 3498e9eec3d8..6576b4a101ae 100644
--- a/drivers/staging/media/rkvdec/rkvdec-h264.c
+++ b/drivers/staging/media/rkvdec/rkvdec-h264.c
@@ -662,8 +662,8 @@ static void assemble_hw_pps(struct rkvdec_ctx *ctx,
 	WRITE_PPS(0xff, PROFILE_IDC);
 	WRITE_PPS(1, CONSTRAINT_SET3_FLAG);
 	WRITE_PPS(sps->chroma_format_idc, CHROMA_FORMAT_IDC);
-	WRITE_PPS(sps->bit_depth_luma_minus8 + 8, BIT_DEPTH_LUMA);
-	WRITE_PPS(sps->bit_depth_chroma_minus8 + 8, BIT_DEPTH_CHROMA);
+	WRITE_PPS(sps->bit_depth_luma_minus8, BIT_DEPTH_LUMA);
+	WRITE_PPS(sps->bit_depth_chroma_minus8, BIT_DEPTH_CHROMA);
 	WRITE_PPS(0, QPPRIME_Y_ZERO_TRANSFORM_BYPASS_FLAG);
 	WRITE_PPS(sps->log2_max_frame_num_minus4, LOG2_MAX_FRAME_NUM_MINUS4);
 	WRITE_PPS(sps->max_num_ref_frames, MAX_NUM_REF_FRAMES);
-- 
2.25.1


From c1cb24d82d654583f9b716f8385254d61223aa03 Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Mon, 6 Jul 2020 21:54:35 +0000
Subject: [PATCH 08/18] media: rkvdec: h264: Do not override output buffer
 sizeimage

The output buffer sizeimage is currently forced to 2 bytes per pixel, this
can lead to high memory usage for 4K content when multiple output buffers
is created by userspace.

Do not override output buffer sizeimage and let userspace have control of
output buffer sizeimage by only setting sizeimage if none is provided.

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
---
 drivers/staging/media/rkvdec/rkvdec-h264.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/media/rkvdec/rkvdec-h264.c b/drivers/staging/media/rkvdec/rkvdec-h264.c
index 6576b4a101ae..3a85545bcb38 100644
--- a/drivers/staging/media/rkvdec/rkvdec-h264.c
+++ b/drivers/staging/media/rkvdec/rkvdec-h264.c
@@ -1012,8 +1012,9 @@ static int rkvdec_h264_adjust_fmt(struct rkvdec_ctx *ctx,
 	struct v4l2_pix_format_mplane *fmt = &f->fmt.pix_mp;
 
 	fmt->num_planes = 1;
-	fmt->plane_fmt[0].sizeimage = fmt->width * fmt->height *
-				      RKVDEC_H264_MAX_DEPTH_IN_BYTES;
+	if (!fmt->plane_fmt[0].sizeimage)
+		fmt->plane_fmt[0].sizeimage = fmt->width * fmt->height *
+					      RKVDEC_H264_MAX_DEPTH_IN_BYTES;
 	return 0;
 }
 
-- 
2.25.1


From 1f381d3ddd88174c12846ba93ddd7deb47089a8e Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Mon, 6 Jul 2020 21:54:35 +0000
Subject: [PATCH 09/18] media: v4l2-common: Add helpers to calculate
 bytesperline and sizeimage

Add helper functions to calculate plane bytesperline and sizeimage, these
new helpers consider block width and height when calculating plane
bytesperline and sizeimage.

This prepare support for new pixel formats added in next patch that make
use of block width and height.

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
---
 drivers/media/v4l2-core/v4l2-common.c | 77 +++++++++++++--------------
 1 file changed, 38 insertions(+), 39 deletions(-)

diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c
index 3dc17ebe14fa..4102c373b48a 100644
--- a/drivers/media/v4l2-core/v4l2-common.c
+++ b/drivers/media/v4l2-core/v4l2-common.c
@@ -333,6 +333,33 @@ static inline unsigned int v4l2_format_block_height(const struct v4l2_format_inf
 	return info->block_h[plane];
 }
 
+static inline unsigned int v4l2_format_plane_width(const struct v4l2_format_info *info, int plane,
+						   unsigned int width)
+{
+	unsigned int hdiv = plane ? info->hdiv : 1;
+	unsigned int bytes = DIV_ROUND_UP(width * info->bpp[plane],
+				v4l2_format_block_width(info, plane) *
+				v4l2_format_block_height(info, plane));
+
+	return DIV_ROUND_UP(bytes, hdiv);
+}
+
+static inline unsigned int v4l2_format_plane_height(const struct v4l2_format_info *info, int plane,
+						    unsigned int height)
+{
+	unsigned int vdiv = plane ? info->vdiv : 1;
+	unsigned int lines = ALIGN(height, v4l2_format_block_height(info, plane));
+
+	return DIV_ROUND_UP(lines, vdiv);
+}
+
+static inline unsigned int v4l2_format_plane_size(const struct v4l2_format_info *info, int plane,
+						  unsigned int width, unsigned int height)
+{
+	return v4l2_format_plane_width(info, plane, width) *
+	       v4l2_format_plane_height(info, plane, height);
+}
+
 void v4l2_apply_frmsize_constraints(u32 *width, u32 *height,
 				    const struct v4l2_frmsize_stepwise *frmsize)
 {
@@ -368,37 +395,19 @@ int v4l2_fill_pixfmt_mp(struct v4l2_pix_format_mplane *pixfmt,
 
 	if (info->mem_planes == 1) {
 		plane = &pixfmt->plane_fmt[0];
-		plane->bytesperline = ALIGN(width, v4l2_format_block_width(info, 0)) * info->bpp[0];
+		plane->bytesperline = v4l2_format_plane_width(info, 0, width);
 		plane->sizeimage = 0;
 
-		for (i = 0; i < info->comp_planes; i++) {
-			unsigned int hdiv = (i == 0) ? 1 : info->hdiv;
-			unsigned int vdiv = (i == 0) ? 1 : info->vdiv;
-			unsigned int aligned_width;
-			unsigned int aligned_height;
-
-			aligned_width = ALIGN(width, v4l2_format_block_width(info, i));
-			aligned_height = ALIGN(height, v4l2_format_block_height(info, i));
-
-			plane->sizeimage += info->bpp[i] *
-				DIV_ROUND_UP(aligned_width, hdiv) *
-				DIV_ROUND_UP(aligned_height, vdiv);
-		}
+		for (i = 0; i < info->comp_planes; i++)
+			plane->sizeimage +=
+				v4l2_format_plane_size(info, i, width, height);
 	} else {
 		for (i = 0; i < info->comp_planes; i++) {
-			unsigned int hdiv = (i == 0) ? 1 : info->hdiv;
-			unsigned int vdiv = (i == 0) ? 1 : info->vdiv;
-			unsigned int aligned_width;
-			unsigned int aligned_height;
-
-			aligned_width = ALIGN(width, v4l2_format_block_width(info, i));
-			aligned_height = ALIGN(height, v4l2_format_block_height(info, i));
-
 			plane = &pixfmt->plane_fmt[i];
 			plane->bytesperline =
-				info->bpp[i] * DIV_ROUND_UP(aligned_width, hdiv);
-			plane->sizeimage =
-				plane->bytesperline * DIV_ROUND_UP(aligned_height, vdiv);
+				v4l2_format_plane_width(info, i, width);
+			plane->sizeimage = plane->bytesperline *
+				v4l2_format_plane_height(info, i, height);
 		}
 	}
 	return 0;
@@ -422,22 +431,12 @@ int v4l2_fill_pixfmt(struct v4l2_pix_format *pixfmt, u32 pixelformat,
 	pixfmt->width = width;
 	pixfmt->height = height;
 	pixfmt->pixelformat = pixelformat;
-	pixfmt->bytesperline = ALIGN(width, v4l2_format_block_width(info, 0)) * info->bpp[0];
+	pixfmt->bytesperline = v4l2_format_plane_width(info, 0, width);
 	pixfmt->sizeimage = 0;
 
-	for (i = 0; i < info->comp_planes; i++) {
-		unsigned int hdiv = (i == 0) ? 1 : info->hdiv;
-		unsigned int vdiv = (i == 0) ? 1 : info->vdiv;
-		unsigned int aligned_width;
-		unsigned int aligned_height;
-
-		aligned_width = ALIGN(width, v4l2_format_block_width(info, i));
-		aligned_height = ALIGN(height, v4l2_format_block_height(info, i));
-
-		pixfmt->sizeimage += info->bpp[i] *
-			DIV_ROUND_UP(aligned_width, hdiv) *
-			DIV_ROUND_UP(aligned_height, vdiv);
-	}
+	for (i = 0; i < info->comp_planes; i++)
+		pixfmt->sizeimage +=
+			v4l2_format_plane_size(info, i, width, height);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(v4l2_fill_pixfmt);
-- 
2.25.1


From 778ba4f6cb10b7e4ae2dd71c35dcdd2363d43b21 Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Mon, 6 Jul 2020 21:54:36 +0000
Subject: [PATCH 10/18] media: v4l2: Add NV15 and NV20 pixel formats

Add NV15 and NV20 pixel formats used by the Rockchip Video Decoder for
10-bit buffers.

NV15 and NV20 is a packed 10-bit 4:2:0/4:2:2 semi-planar Y/CbCr format
similar to P010 and P210 but has no padding between components. Instead,
luminance and chrominance samples are grouped into 4s so that each group is
packed into an integer number of bytes:

YYYY = UVUV = 4 * 10 bits = 40 bits = 5 bytes

The '15' and '20' suffix refers to the optimum effective bits per pixel
which is achieved when the total number of luminance samples is a multiple
of 8 for NV15 and 4 for NV20.

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
---
 .../userspace-api/media/v4l/pixfmt-nv15.rst   | 101 ++++++++++++++++++
 .../userspace-api/media/v4l/pixfmt-nv20.rst   |  99 +++++++++++++++++
 .../userspace-api/media/v4l/yuv-formats.rst   |   2 +
 drivers/media/v4l2-core/v4l2-common.c         |   3 +
 drivers/media/v4l2-core/v4l2-ioctl.c          |   2 +
 include/uapi/linux/videodev2.h                |   3 +
 6 files changed, 210 insertions(+)
 create mode 100644 Documentation/userspace-api/media/v4l/pixfmt-nv15.rst
 create mode 100644 Documentation/userspace-api/media/v4l/pixfmt-nv20.rst

diff --git a/Documentation/userspace-api/media/v4l/pixfmt-nv15.rst b/Documentation/userspace-api/media/v4l/pixfmt-nv15.rst
new file mode 100644
index 000000000000..d059db58c6e0
--- /dev/null
+++ b/Documentation/userspace-api/media/v4l/pixfmt-nv15.rst
@@ -0,0 +1,101 @@
+.. 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/userspace-api/media/fdl-appendix.rst.
+..
+.. TODO: replace it to GFDL-1.1-or-later WITH no-invariant-sections
+
+.. _V4L2-PIX-FMT-NV15:
+
+**************************
+V4L2_PIX_FMT_NV15 ('NV15')
+**************************
+
+Format with ½ horizontal and vertical chroma resolution, also known as
+YUV 4:2:0. One luminance and one chrominance plane with alternating
+chroma samples similar to ``V4L2_PIX_FMT_NV12`` but with 10-bit samples
+that are grouped into four and packed into five bytes.
+
+The '15' suffix refers to the optimum effective bits per pixel which is
+achieved when the total number of luminance samples is a multiple of 8.
+
+
+Description
+===========
+
+This is a packed 10-bit two-plane version of the YUV 4:2:0 format. The
+three components are separated into two sub-images or planes. The Y plane
+is first. The Y plane has five bytes per each group of four pixels. A
+combined CbCr plane immediately follows the Y plane in memory. The CbCr
+plane is the same width, in bytes, as the Y plane (and of the image), but
+is half as tall in pixels. Each CbCr pair belongs to four pixels. For
+example, Cb\ :sub:`00`/Cr\ :sub:`00` belongs to Y'\ :sub:`00`,
+Y'\ :sub:`01`, Y'\ :sub:`10`, Y'\ :sub:`11`.
+
+If the Y plane has pad bytes after each row, then the CbCr plane has as
+many pad bytes after its rows.
+
+**Byte Order.**
+Little endian. Each cell is one byte. Pixels cross the byte boundary.
+
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+
+    * - start + 0:
+      - Y'\ :sub:`00[7:0]`
+      - Y'\ :sub:`01[5:0]`\ Y'\ :sub:`00[9:8]`
+      - Y'\ :sub:`02[3:0]`\ Y'\ :sub:`01[9:6]`
+      - Y'\ :sub:`03[1:0]`\ Y'\ :sub:`02[9:4]`
+      - Y'\ :sub:`03[9:2]`
+    * - start + 5:
+      - Y'\ :sub:`10[7:0]`
+      - Y'\ :sub:`11[5:0]`\ Y'\ :sub:`10[9:8]`
+      - Y'\ :sub:`12[3:0]`\ Y'\ :sub:`11[9:6]`
+      - Y'\ :sub:`13[1:0]`\ Y'\ :sub:`12[9:4]`
+      - Y'\ :sub:`13[9:2]`
+    * - start + 10:
+      - Cb'\ :sub:`00[7:0]`
+      - Cr'\ :sub:`00[5:0]`\ Cb'\ :sub:`00[9:8]`
+      - Cb'\ :sub:`01[3:0]`\ Cr'\ :sub:`00[9:6]`
+      - Cr'\ :sub:`01[1:0]`\ Cb'\ :sub:`01[9:4]`
+      - Cr'\ :sub:`01[9:2]`
+
+
+**Color Sample Location:**
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+
+    * -
+      - 0
+      -
+      - 1
+      - 2
+      -
+      - 3
+    * - 0
+      - Y
+      -
+      - Y
+      - Y
+      -
+      - Y
+    * -
+      -
+      - C
+      -
+      -
+      - C
+      -
+    * - 1
+      - Y
+      -
+      - Y
+      - Y
+      -
+      - Y
diff --git a/Documentation/userspace-api/media/v4l/pixfmt-nv20.rst b/Documentation/userspace-api/media/v4l/pixfmt-nv20.rst
new file mode 100644
index 000000000000..a8123be0baa3
--- /dev/null
+++ b/Documentation/userspace-api/media/v4l/pixfmt-nv20.rst
@@ -0,0 +1,99 @@
+.. 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/userspace-api/media/fdl-appendix.rst.
+..
+.. TODO: replace it to GFDL-1.1-or-later WITH no-invariant-sections
+
+.. _V4L2-PIX-FMT-NV20:
+
+**************************
+V4L2_PIX_FMT_NV20 ('NV20')
+**************************
+
+Format with ½ horizontal chroma resolution, also known as YUV 4:2:2.
+One luminance and one chrominance plane with alternating chroma samples
+similar to ``V4L2_PIX_FMT_NV16`` but with 10-bit samples
+that are grouped into four and packed into five bytes.
+
+The '20' suffix refers to the optimum effective bits per pixel which is
+achieved when the total number of luminance samples is a multiple of 4.
+
+
+Description
+===========
+
+This is a packed 10-bit two-plane version of the YUV 4:2:2 format. The
+three components are separated into two sub-images or planes. The Y plane
+is first. The Y plane has five bytes per each group of four pixels. A
+combined CbCr plane immediately follows the Y plane in memory. The CbCr
+plane is the same width and height, in bytes, as the Y plane (and of the
+image). Each CbCr pair belongs to two pixels. For example,
+Cb\ :sub:`00`/Cr\ :sub:`00` belongs to Y'\ :sub:`00`, Y'\ :sub:`01`.
+
+If the Y plane has pad bytes after each row, then the CbCr plane has as
+many pad bytes after its rows.
+
+**Byte Order.**
+Little endian. Each cell is one byte. Pixels cross the byte boundary.
+
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+
+    * - start + 0:
+      - Y'\ :sub:`00[7:0]`
+      - Y'\ :sub:`01[5:0]`\ Y'\ :sub:`00[9:8]`
+      - Y'\ :sub:`02[3:0]`\ Y'\ :sub:`01[9:6]`
+      - Y'\ :sub:`03[1:0]`\ Y'\ :sub:`02[9:4]`
+      - Y'\ :sub:`03[9:2]`
+    * - start + 5:
+      - Y'\ :sub:`10[7:0]`
+      - Y'\ :sub:`11[5:0]`\ Y'\ :sub:`10[9:8]`
+      - Y'\ :sub:`12[3:0]`\ Y'\ :sub:`11[9:6]`
+      - Y'\ :sub:`13[1:0]`\ Y'\ :sub:`12[9:4]`
+      - Y'\ :sub:`13[9:2]`
+    * - start + 10:
+      - Cb'\ :sub:`00[7:0]`
+      - Cr'\ :sub:`00[5:0]`\ Cb'\ :sub:`00[9:8]`
+      - Cb'\ :sub:`01[3:0]`\ Cr'\ :sub:`00[9:6]`
+      - Cr'\ :sub:`01[1:0]`\ Cb'\ :sub:`01[9:4]`
+      - Cr'\ :sub:`01[9:2]`
+    * - start + 15:
+      - Cb'\ :sub:`10[7:0]`
+      - Cr'\ :sub:`10[5:0]`\ Cb'\ :sub:`10[9:8]`
+      - Cb'\ :sub:`11[3:0]`\ Cr'\ :sub:`10[9:6]`
+      - Cr'\ :sub:`11[1:0]`\ Cb'\ :sub:`11[9:4]`
+      - Cr'\ :sub:`11[9:2]`
+
+
+**Color Sample Location:**
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+
+    * -
+      - 0
+      -
+      - 1
+      - 2
+      -
+      - 3
+    * - 0
+      - Y
+      - C
+      - Y
+      - Y
+      - C
+      - Y
+    * - 1
+      - Y
+      - C
+      - Y
+      - Y
+      - C
+      - Y
diff --git a/Documentation/userspace-api/media/v4l/yuv-formats.rst b/Documentation/userspace-api/media/v4l/yuv-formats.rst
index 8ee92d0cd769..7cca883f178a 100644
--- a/Documentation/userspace-api/media/v4l/yuv-formats.rst
+++ b/Documentation/userspace-api/media/v4l/yuv-formats.rst
@@ -61,4 +61,6 @@ to brightness information.
     pixfmt-nv16
     pixfmt-nv16m
     pixfmt-nv24
+    pixfmt-nv15
+    pixfmt-nv20
     pixfmt-m420
diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c
index 4102c373b48a..0caac755d303 100644
--- a/drivers/media/v4l2-core/v4l2-common.c
+++ b/drivers/media/v4l2-core/v4l2-common.c
@@ -267,6 +267,9 @@ const struct v4l2_format_info *v4l2_format_info(u32 format)
 		{ .format = V4L2_PIX_FMT_NV24,    .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 1, .vdiv = 1 },
 		{ .format = V4L2_PIX_FMT_NV42,    .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 1, .vdiv = 1 },
 
+		{ .format = V4L2_PIX_FMT_NV15,    .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 5, 5, 0, 0 }, .hdiv = 2, .vdiv = 2, .block_w = { 4, 2, 0, 0 }, .block_h = { 1, 1, 0, 0 } },
+		{ .format = V4L2_PIX_FMT_NV20,    .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 5, 5, 0, 0 }, .hdiv = 2, .vdiv = 1, .block_w = { 4, 2, 0, 0 }, .block_h = { 1, 1, 0, 0 } },
+
 		{ .format = V4L2_PIX_FMT_YUV410,  .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 4, .vdiv = 4 },
 		{ .format = V4L2_PIX_FMT_YVU410,  .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 4, .vdiv = 4 },
 		{ .format = V4L2_PIX_FMT_YUV411P, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 4, .vdiv = 1 },
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index 02bfef0da76d..4657274bb37a 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -1315,6 +1315,8 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt)
 	case V4L2_PIX_FMT_NV61:		descr = "Y/CrCb 4:2:2"; break;
 	case V4L2_PIX_FMT_NV24:		descr = "Y/CbCr 4:4:4"; break;
 	case V4L2_PIX_FMT_NV42:		descr = "Y/CrCb 4:4:4"; break;
+	case V4L2_PIX_FMT_NV15:		descr = "10-bit Y/CbCr 4:2:0 (Packed)"; break;
+	case V4L2_PIX_FMT_NV20:		descr = "10-bit Y/CbCr 4:2:2 (Packed)"; break;
 	case V4L2_PIX_FMT_NV12M:	descr = "Y/CbCr 4:2:0 (N-C)"; break;
 	case V4L2_PIX_FMT_NV21M:	descr = "Y/CrCb 4:2:0 (N-C)"; break;
 	case V4L2_PIX_FMT_NV16M:	descr = "Y/CbCr 4:2:2 (N-C)"; break;
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 303805438814..bd23aeaf0706 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -610,6 +610,9 @@ struct v4l2_pix_format {
 #define V4L2_PIX_FMT_NV24    v4l2_fourcc('N', 'V', '2', '4') /* 24  Y/CbCr 4:4:4  */
 #define V4L2_PIX_FMT_NV42    v4l2_fourcc('N', 'V', '4', '2') /* 24  Y/CrCb 4:4:4  */
 
+#define V4L2_PIX_FMT_NV15    v4l2_fourcc('N', 'V', '1', '5') /* 15  Y/CbCr 4:2:0 10-bit packed */
+#define V4L2_PIX_FMT_NV20    v4l2_fourcc('N', 'V', '2', '0') /* 20  Y/CbCr 4:2:2 10-bit packed */
+
 /* two non contiguous planes - one Y, one Cr + Cb interleaved  */
 #define V4L2_PIX_FMT_NV12M   v4l2_fourcc('N', 'M', '1', '2') /* 12  Y/CbCr 4:2:0  */
 #define V4L2_PIX_FMT_NV21M   v4l2_fourcc('N', 'M', '2', '1') /* 21  Y/CrCb 4:2:0  */
-- 
2.25.1


From ac18ccac6e1a05ecdffd1eb5e8017d92a5eb6c0f Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Mon, 6 Jul 2020 21:54:36 +0000
Subject: [PATCH 11/18] media: rkvdec: h264: Use bytesperline and buffer height
 to calculate stride

Use bytesperline and buffer height to calculate the strides configured.

This does not really change anything other than ensuring the bytesperline
that is signaled to userspace matches what is configured in HW.

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
---
 drivers/staging/media/rkvdec/rkvdec-h264.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/staging/media/rkvdec/rkvdec-h264.c b/drivers/staging/media/rkvdec/rkvdec-h264.c
index 3a85545bcb38..10756b9d6118 100644
--- a/drivers/staging/media/rkvdec/rkvdec-h264.c
+++ b/drivers/staging/media/rkvdec/rkvdec-h264.c
@@ -891,9 +891,9 @@ static void config_registers(struct rkvdec_ctx *ctx,
 	dma_addr_t rlc_addr;
 	dma_addr_t refer_addr;
 	u32 rlc_len;
-	u32 hor_virstride = 0;
-	u32 ver_virstride = 0;
-	u32 y_virstride = 0;
+	u32 hor_virstride;
+	u32 ver_virstride;
+	u32 y_virstride;
 	u32 yuv_virstride = 0;
 	u32 offset;
 	dma_addr_t dst_addr;
@@ -904,8 +904,8 @@ static void config_registers(struct rkvdec_ctx *ctx,
 
 	f = &ctx->decoded_fmt;
 	dst_fmt = &f->fmt.pix_mp;
-	hor_virstride = (sps->bit_depth_luma_minus8 + 8) * dst_fmt->width / 8;
-	ver_virstride = round_up(dst_fmt->height, 16);
+	hor_virstride = dst_fmt->plane_fmt[0].bytesperline;
+	ver_virstride = dst_fmt->height;
 	y_virstride = hor_virstride * ver_virstride;
 
 	if (sps->chroma_format_idc == 0)
-- 
2.25.1


From 62e313c4f82da894647a166a923c32746c2715ad Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Mon, 6 Jul 2020 21:54:37 +0000
Subject: [PATCH 12/18] media: rkvdec: Extract rkvdec_fill_decoded_pixfmt
 helper method

This extract setting decoded pixfmt into a helper method, current code is
replaced with a call to the new helper method.

The helper method is also called from a new function in next patch.

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
---
 drivers/staging/media/rkvdec/rkvdec.c | 29 ++++++++++++++-------------
 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/drivers/staging/media/rkvdec/rkvdec.c b/drivers/staging/media/rkvdec/rkvdec.c
index 7a9f78bc0a55..911132be6d50 100644
--- a/drivers/staging/media/rkvdec/rkvdec.c
+++ b/drivers/staging/media/rkvdec/rkvdec.c
@@ -27,6 +27,17 @@
 #include "rkvdec.h"
 #include "rkvdec-regs.h"
 
+static void rkvdec_fill_decoded_pixfmt(struct rkvdec_ctx *ctx,
+				       struct v4l2_pix_format_mplane *pix_mp)
+{
+	v4l2_fill_pixfmt_mp(pix_mp, pix_mp->pixelformat,
+			    pix_mp->width, pix_mp->height);
+	pix_mp->plane_fmt[0].sizeimage += 128 *
+		DIV_ROUND_UP(pix_mp->width, 16) *
+		DIV_ROUND_UP(pix_mp->height, 16);
+	pix_mp->field = V4L2_FIELD_NONE;
+}
+
 static int rkvdec_try_ctrl(struct v4l2_ctrl *ctrl)
 {
 	struct rkvdec_ctx *ctx = container_of(ctrl->handler, struct rkvdec_ctx, ctrl_hdl);
@@ -179,13 +190,9 @@ static void rkvdec_reset_decoded_fmt(struct rkvdec_ctx *ctx)
 
 	rkvdec_reset_fmt(ctx, f, ctx->coded_fmt_desc->decoded_fmts[0]);
 	f->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
-	v4l2_fill_pixfmt_mp(&f->fmt.pix_mp,
-			    ctx->coded_fmt_desc->decoded_fmts[0],
-			    ctx->coded_fmt.fmt.pix_mp.width,
-			    ctx->coded_fmt.fmt.pix_mp.height);
-	f->fmt.pix_mp.plane_fmt[0].sizeimage += 128 *
-		DIV_ROUND_UP(f->fmt.pix_mp.width, 16) *
-		DIV_ROUND_UP(f->fmt.pix_mp.height, 16);
+	f->fmt.pix_mp.width = ctx->coded_fmt.fmt.pix_mp.width;
+	f->fmt.pix_mp.height = ctx->coded_fmt.fmt.pix_mp.height;
+	rkvdec_fill_decoded_pixfmt(ctx, &f->fmt.pix_mp);
 }
 
 static int rkvdec_enum_framesizes(struct file *file, void *priv,
@@ -251,13 +258,7 @@ static int rkvdec_try_capture_fmt(struct file *file, void *priv,
 				       &pix_mp->height,
 				       &coded_desc->frmsize);
 
-	v4l2_fill_pixfmt_mp(pix_mp, pix_mp->pixelformat,
-			    pix_mp->width, pix_mp->height);
-	pix_mp->plane_fmt[0].sizeimage +=
-		128 *
-		DIV_ROUND_UP(pix_mp->width, 16) *
-		DIV_ROUND_UP(pix_mp->height, 16);
-	pix_mp->field = V4L2_FIELD_NONE;
+	rkvdec_fill_decoded_pixfmt(ctx, pix_mp);
 
 	return 0;
 }
-- 
2.25.1


From ce2a49e0b4908dbc148df81a053bb3eaf8c28048 Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Mon, 6 Jul 2020 21:54:37 +0000
Subject: [PATCH 13/18] media: rkvdec: Lock capture pixel format in s_ctrl and
 s_fmt

Add an optional valid_fmt operation that should return the valid
pixelformat of CAPTURE buffers.

This is used in next patch to ensure correct pixelformat is used for 10-bit
and 4:2:2 content.

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
---
 drivers/staging/media/rkvdec/rkvdec.c | 59 ++++++++++++++++++++++++---
 drivers/staging/media/rkvdec/rkvdec.h |  2 +
 2 files changed, 55 insertions(+), 6 deletions(-)

diff --git a/drivers/staging/media/rkvdec/rkvdec.c b/drivers/staging/media/rkvdec/rkvdec.c
index 911132be6d50..11a88cb6407d 100644
--- a/drivers/staging/media/rkvdec/rkvdec.c
+++ b/drivers/staging/media/rkvdec/rkvdec.c
@@ -38,6 +38,16 @@ static void rkvdec_fill_decoded_pixfmt(struct rkvdec_ctx *ctx,
 	pix_mp->field = V4L2_FIELD_NONE;
 }
 
+static u32 rkvdec_valid_fmt(struct rkvdec_ctx *ctx, struct v4l2_ctrl *ctrl)
+{
+	const struct rkvdec_coded_fmt_desc *coded_desc = ctx->coded_fmt_desc;
+
+	if (coded_desc->ops->valid_fmt)
+		return coded_desc->ops->valid_fmt(ctx, ctrl);
+
+	return ctx->valid_fmt;
+}
+
 static int rkvdec_try_ctrl(struct v4l2_ctrl *ctrl)
 {
 	struct rkvdec_ctx *ctx = container_of(ctrl->handler, struct rkvdec_ctx, ctrl_hdl);
@@ -60,6 +70,10 @@ static int rkvdec_try_ctrl(struct v4l2_ctrl *ctrl)
 			/* Only 8-bit is supported */
 			return -EINVAL;
 
+		if (ctx->valid_fmt && ctx->valid_fmt != rkvdec_valid_fmt(ctx, ctrl))
+			/* Only current valid format */
+			return -EINVAL;
+
 		width = (sps->pic_width_in_mbs_minus1 + 1) * 16;
 		height = (sps->pic_height_in_map_units_minus1 + 1) * 16;
 
@@ -70,8 +84,27 @@ static int rkvdec_try_ctrl(struct v4l2_ctrl *ctrl)
 	return 0;
 }
 
+static int rkvdec_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct rkvdec_ctx *ctx = container_of(ctrl->handler, struct rkvdec_ctx, ctrl_hdl);
+
+	if (ctrl->id == V4L2_CID_MPEG_VIDEO_H264_SPS && !ctx->valid_fmt) {
+		ctx->valid_fmt = rkvdec_valid_fmt(ctx, ctrl);
+		if (ctx->valid_fmt) {
+			struct v4l2_pix_format_mplane *pix_mp;
+
+			pix_mp = &ctx->decoded_fmt.fmt.pix_mp;
+			pix_mp->pixelformat = ctx->valid_fmt;
+			rkvdec_fill_decoded_pixfmt(ctx, pix_mp);
+		}
+	}
+
+	return 0;
+}
+
 static const struct v4l2_ctrl_ops rkvdec_ctrl_ops = {
 	.try_ctrl = rkvdec_try_ctrl,
+	.s_ctrl = rkvdec_s_ctrl,
 };
 
 static const struct rkvdec_ctrl_desc rkvdec_h264_ctrl_descs[] = {
@@ -188,6 +221,7 @@ static void rkvdec_reset_decoded_fmt(struct rkvdec_ctx *ctx)
 {
 	struct v4l2_format *f = &ctx->decoded_fmt;
 
+	ctx->valid_fmt = 0;
 	rkvdec_reset_fmt(ctx, f, ctx->coded_fmt_desc->decoded_fmts[0]);
 	f->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
 	f->fmt.pix_mp.width = ctx->coded_fmt.fmt.pix_mp.width;
@@ -243,13 +277,17 @@ static int rkvdec_try_capture_fmt(struct file *file, void *priv,
 	if (WARN_ON(!coded_desc))
 		return -EINVAL;
 
-	for (i = 0; i < coded_desc->num_decoded_fmts; i++) {
-		if (coded_desc->decoded_fmts[i] == pix_mp->pixelformat)
-			break;
-	}
+	if (ctx->valid_fmt) {
+		pix_mp->pixelformat = ctx->valid_fmt;
+	} else {
+		for (i = 0; i < coded_desc->num_decoded_fmts; i++) {
+			if (coded_desc->decoded_fmts[i] == pix_mp->pixelformat)
+				break;
+		}
 
-	if (i == coded_desc->num_decoded_fmts)
-		pix_mp->pixelformat = coded_desc->decoded_fmts[0];
+		if (i == coded_desc->num_decoded_fmts)
+			pix_mp->pixelformat = coded_desc->decoded_fmts[0];
+	}
 
 	/* Always apply the frmsize constraint of the coded end. */
 	pix_mp->width = max(pix_mp->width, ctx->coded_fmt.fmt.pix_mp.width);
@@ -324,6 +362,7 @@ static int rkvdec_s_capture_fmt(struct file *file, void *priv,
 		return ret;
 
 	ctx->decoded_fmt = *f;
+	ctx->valid_fmt = f->fmt.pix_mp.pixelformat;
 	return 0;
 }
 
@@ -413,6 +452,14 @@ static int rkvdec_enum_capture_fmt(struct file *file, void *priv,
 	if (WARN_ON(!ctx->coded_fmt_desc))
 		return -EINVAL;
 
+	if (ctx->valid_fmt) {
+		if (f->index)
+			return -EINVAL;
+
+		f->pixelformat = ctx->valid_fmt;
+		return 0;
+	}
+
 	if (f->index >= ctx->coded_fmt_desc->num_decoded_fmts)
 		return -EINVAL;
 
diff --git a/drivers/staging/media/rkvdec/rkvdec.h b/drivers/staging/media/rkvdec/rkvdec.h
index 2fc9f46b6910..50e67401fdbe 100644
--- a/drivers/staging/media/rkvdec/rkvdec.h
+++ b/drivers/staging/media/rkvdec/rkvdec.h
@@ -64,6 +64,7 @@ vb2_to_rkvdec_decoded_buf(struct vb2_buffer *buf)
 struct rkvdec_coded_fmt_ops {
 	int (*adjust_fmt)(struct rkvdec_ctx *ctx,
 			  struct v4l2_format *f);
+	u32 (*valid_fmt)(struct rkvdec_ctx *ctx, struct v4l2_ctrl *ctrl);
 	int (*start)(struct rkvdec_ctx *ctx);
 	void (*stop)(struct rkvdec_ctx *ctx);
 	int (*run)(struct rkvdec_ctx *ctx);
@@ -97,6 +98,7 @@ struct rkvdec_ctx {
 	struct v4l2_fh fh;
 	struct v4l2_format coded_fmt;
 	struct v4l2_format decoded_fmt;
+	u32 valid_fmt;
 	const struct rkvdec_coded_fmt_desc *coded_fmt_desc;
 	struct v4l2_ctrl_handler ctrl_hdl;
 	struct rkvdec_dev *dev;
-- 
2.25.1


From 4a5ebc230d6f6ad93699631f2f55abb6d7bff43f Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Mon, 6 Jul 2020 21:54:37 +0000
Subject: [PATCH 14/18] media: rkvdec: h264: Support High 10 and 4:2:2 profiles

Add support and enable decoding of H264 High 10 and 4:2:2 profiles.

Decoded CAPTURE buffer width is aligned to 64 pixels to accommodate HW
requirement on 10-bit format buffers.

The new valid_fmt operation is implemented and return a valid pixelformat
for the provided SPS control.

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
---
 drivers/staging/media/rkvdec/rkvdec-h264.c | 20 ++++++++++++++++++++
 drivers/staging/media/rkvdec/rkvdec.c      | 19 +++++++++----------
 2 files changed, 29 insertions(+), 10 deletions(-)

diff --git a/drivers/staging/media/rkvdec/rkvdec-h264.c b/drivers/staging/media/rkvdec/rkvdec-h264.c
index 10756b9d6118..0757fc97d1ff 100644
--- a/drivers/staging/media/rkvdec/rkvdec-h264.c
+++ b/drivers/staging/media/rkvdec/rkvdec-h264.c
@@ -1018,6 +1018,25 @@ static int rkvdec_h264_adjust_fmt(struct rkvdec_ctx *ctx,
 	return 0;
 }
 
+static u32 rkvdec_h264_valid_fmt(struct rkvdec_ctx *ctx, struct v4l2_ctrl *ctrl)
+{
+	const struct v4l2_ctrl_h264_sps *sps = ctrl->p_new.p;
+
+	if (sps->bit_depth_luma_minus8 == 0) {
+		if (sps->chroma_format_idc == 2)
+			return V4L2_PIX_FMT_NV16;
+		else
+			return V4L2_PIX_FMT_NV12;
+	} else if (sps->bit_depth_luma_minus8 == 2) {
+		if (sps->chroma_format_idc == 2)
+			return V4L2_PIX_FMT_NV20;
+		else
+			return V4L2_PIX_FMT_NV15;
+	}
+
+	return 0;
+}
+
 static int rkvdec_h264_start(struct rkvdec_ctx *ctx)
 {
 	struct rkvdec_dev *rkvdec = ctx->dev;
@@ -1125,6 +1144,7 @@ static int rkvdec_h264_run(struct rkvdec_ctx *ctx)
 
 const struct rkvdec_coded_fmt_ops rkvdec_h264_fmt_ops = {
 	.adjust_fmt = rkvdec_h264_adjust_fmt,
+	.valid_fmt = rkvdec_h264_valid_fmt,
 	.start = rkvdec_h264_start,
 	.stop = rkvdec_h264_stop,
 	.run = rkvdec_h264_run,
diff --git a/drivers/staging/media/rkvdec/rkvdec.c b/drivers/staging/media/rkvdec/rkvdec.c
index 11a88cb6407d..4faee9262392 100644
--- a/drivers/staging/media/rkvdec/rkvdec.c
+++ b/drivers/staging/media/rkvdec/rkvdec.c
@@ -31,7 +31,7 @@ static void rkvdec_fill_decoded_pixfmt(struct rkvdec_ctx *ctx,
 				       struct v4l2_pix_format_mplane *pix_mp)
 {
 	v4l2_fill_pixfmt_mp(pix_mp, pix_mp->pixelformat,
-			    pix_mp->width, pix_mp->height);
+			    ALIGN(pix_mp->width, 64), pix_mp->height);
 	pix_mp->plane_fmt[0].sizeimage += 128 *
 		DIV_ROUND_UP(pix_mp->width, 16) *
 		DIV_ROUND_UP(pix_mp->height, 16);
@@ -55,19 +55,15 @@ static int rkvdec_try_ctrl(struct v4l2_ctrl *ctrl)
 	if (ctrl->id == V4L2_CID_MPEG_VIDEO_H264_SPS) {
 		const struct v4l2_ctrl_h264_sps *sps = ctrl->p_new.p;
 		unsigned int width, height;
-		/*
-		 * TODO: The hardware supports 10-bit and 4:2:2 profiles,
-		 * but it's currently broken in the driver.
-		 * Reject them for now, until it's fixed.
-		 */
-		if (sps->chroma_format_idc > 1)
-			/* Only 4:0:0 and 4:2:0 are supported */
+
+		if (sps->chroma_format_idc > 2)
+			/* Only 4:0:0, 4:2:0 and 4:2:2 are supported */
 			return -EINVAL;
 		if (sps->bit_depth_luma_minus8 != sps->bit_depth_chroma_minus8)
 			/* Luma and chroma bit depth mismatch */
 			return -EINVAL;
-		if (sps->bit_depth_luma_minus8 != 0)
-			/* Only 8-bit is supported */
+		if (sps->bit_depth_luma_minus8 != 0 && sps->bit_depth_luma_minus8 != 2)
+			/* Only 8-bit and 10-bit is supported */
 			return -EINVAL;
 
 		if (ctx->valid_fmt && ctx->valid_fmt != rkvdec_valid_fmt(ctx, ctrl))
@@ -157,6 +153,9 @@ static const struct rkvdec_ctrls rkvdec_h264_ctrls = {
 
 static const u32 rkvdec_h264_decoded_fmts[] = {
 	V4L2_PIX_FMT_NV12,
+	V4L2_PIX_FMT_NV15,
+	V4L2_PIX_FMT_NV16,
+	V4L2_PIX_FMT_NV20,
 };
 
 static const struct rkvdec_coded_fmt_desc rkvdec_coded_fmts[] = {
-- 
2.25.1


From 4dc94c5df4663d2120faaddfe1c581b4c3f347b9 Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Mon, 6 Jul 2020 21:54:38 +0000
Subject: [PATCH 15/18] media: rkvdec: h264: Support profile and level controls

The Rockchip Video Decoder used in RK3399 supports H.264 profiles from
Baseline to High 4:2:2 up to Level 5.1, except for the Extended profile.

Expose the V4L2_CID_MPEG_VIDEO_H264_PROFILE and the
V4L2_CID_MPEG_VIDEO_H264_LEVEL control, so that userspace can query the
driver for the list of supported profiles and level.

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Ezequiel Garcia <ezequiel@collabora.com>
---
 drivers/staging/media/rkvdec/rkvdec.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/staging/media/rkvdec/rkvdec.c b/drivers/staging/media/rkvdec/rkvdec.c
index 4faee9262392..b21031535330 100644
--- a/drivers/staging/media/rkvdec/rkvdec.c
+++ b/drivers/staging/media/rkvdec/rkvdec.c
@@ -144,6 +144,19 @@ static const struct rkvdec_ctrl_desc rkvdec_h264_ctrl_descs[] = {
 		.cfg.def = V4L2_MPEG_VIDEO_H264_START_CODE_ANNEX_B,
 		.cfg.max = V4L2_MPEG_VIDEO_H264_START_CODE_ANNEX_B,
 	},
+	{
+		.cfg.id = V4L2_CID_MPEG_VIDEO_H264_PROFILE,
+		.cfg.min = V4L2_MPEG_VIDEO_H264_PROFILE_BASELINE,
+		.cfg.max = V4L2_MPEG_VIDEO_H264_PROFILE_HIGH_422,
+		.cfg.menu_skip_mask =
+			BIT(V4L2_MPEG_VIDEO_H264_PROFILE_EXTENDED),
+		.cfg.def = V4L2_MPEG_VIDEO_H264_PROFILE_MAIN,
+	},
+	{
+		.cfg.id = V4L2_CID_MPEG_VIDEO_H264_LEVEL,
+		.cfg.min = V4L2_MPEG_VIDEO_H264_LEVEL_1_0,
+		.cfg.max = V4L2_MPEG_VIDEO_H264_LEVEL_5_1,
+	},
 };
 
 static const struct rkvdec_ctrls rkvdec_h264_ctrls = {
-- 
2.25.1


From 588b8545dda3cd0ef8f066dcafff3fa7a93e4056 Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Mon, 6 Jul 2020 22:30:13 +0000
Subject: [PATCH 17/18] drm: drm_fourcc: add NV20 and NV30 YUV formats

DRM_FORMAT_NV20 and DRM_FORMAT_NV30 formats is the 2x1 and non-subsampled
variant of NV15, a 10-bit 2-plane YUV format that has no padding between
components. Instead, luminance and chrominance samples are grouped into 4s
so that each group is packed into an integer number of bytes:

YYYY = UVUV = 4 * 10 bits = 40 bits = 5 bytes

The '20' and '30' suffix refers to the optimum effective bits per pixel
which is achieved when the total number of luminance samples is a multiple
of 4.

V2: Added NV30 format

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Sandy Huang <hjc@rock-chips.com>
---
 drivers/gpu/drm/drm_fourcc.c  | 8 ++++++++
 include/uapi/drm/drm_fourcc.h | 2 ++
 2 files changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c
index 722c7ebe4e88..2daf8a304b53 100644
--- a/drivers/gpu/drm/drm_fourcc.c
+++ b/drivers/gpu/drm/drm_fourcc.c
@@ -278,6 +278,14 @@ const struct drm_format_info *__drm_format_info(u32 format)
 		  .num_planes = 2, .char_per_block = { 5, 5, 0 },
 		  .block_w = { 4, 2, 0 }, .block_h = { 1, 1, 0 }, .hsub = 2,
 		  .vsub = 2, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV20,		.depth = 0,
+		  .num_planes = 2, .char_per_block = { 5, 5, 0 },
+		  .block_w = { 4, 2, 0 }, .block_h = { 1, 1, 0 }, .hsub = 2,
+		  .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV30,		.depth = 0,
+		  .num_planes = 2, .char_per_block = { 5, 5, 0 },
+		  .block_w = { 4, 2, 0 }, .block_h = { 1, 1, 0 }, .hsub = 1,
+		  .vsub = 1, .is_yuv = true },
 		{ .format = DRM_FORMAT_Q410,		.depth = 0,
 		  .num_planes = 3, .char_per_block = { 2, 2, 2 },
 		  .block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 }, .hsub = 0,
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index 8ba2d9153a94..c3024c82a3e3 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -242,6 +242,8 @@ extern "C" {
  * index 1 = Cr:Cb plane, [39:0] Cr1:Cb1:Cr0:Cb0 little endian
  */
 #define DRM_FORMAT_NV15		fourcc_code('N', 'V', '1', '5') /* 2x2 subsampled Cr:Cb plane */
+#define DRM_FORMAT_NV20		fourcc_code('N', 'V', '2', '0') /* 2x1 subsampled Cr:Cb plane */
+#define DRM_FORMAT_NV30		fourcc_code('N', 'V', '3', '0') /* non-subsampled Cr:Cb plane */
 
 /*
  * 2 plane YCbCr MSB aligned
-- 
2.25.1


From 5e09593745d332f82471e1a763e9b9b2632543eb Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Mon, 6 Jul 2020 22:30:13 +0000
Subject: [PATCH 18/18] drm: rockchip: add NV15, NV20 and NV30 support

Add support for displaying 10-bit 4:2:0 and 4:2:2 formats produced by the
Rockchip Video Decoder on RK322X, RK3288, RK3328, RK3368 and RK3399.
Also add support for 10-bit 4:4:4 format while at it.

V2: Added NV30 support

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Sandy Huang <hjc@rock-chips.com>
---
 drivers/gpu/drm/rockchip/rockchip_drm_vop.c | 29 +++++++++++++++++--
 drivers/gpu/drm/rockchip/rockchip_drm_vop.h |  1 +
 drivers/gpu/drm/rockchip/rockchip_vop_reg.c | 32 +++++++++++++++++----
 3 files changed, 54 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index 33463b79a37b..dc2667cfb575 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -261,6 +261,18 @@ static bool has_rb_swapped(uint32_t format)
 	}
 }
 
+static bool is_fmt_10(uint32_t format)
+{
+	switch (format) {
+	case DRM_FORMAT_NV15:
+	case DRM_FORMAT_NV20:
+	case DRM_FORMAT_NV30:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static enum vop_data_format vop_convert_format(uint32_t format)
 {
 	switch (format) {
@@ -276,10 +288,13 @@ static enum vop_data_format vop_convert_format(uint32_t format)
 	case DRM_FORMAT_BGR565:
 		return VOP_FMT_RGB565;
 	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_NV15:
 		return VOP_FMT_YUV420SP;
 	case DRM_FORMAT_NV16:
+	case DRM_FORMAT_NV20:
 		return VOP_FMT_YUV422SP;
 	case DRM_FORMAT_NV24:
+	case DRM_FORMAT_NV30:
 		return VOP_FMT_YUV444SP;
 	default:
 		DRM_ERROR("unsupported format[%08x]\n", format);
@@ -922,7 +937,12 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
 	dsp_sty = dest->y1 + crtc->mode.vtotal - crtc->mode.vsync_start;
 	dsp_st = dsp_sty << 16 | (dsp_stx & 0xffff);
 
-	offset = (src->x1 >> 16) * fb->format->cpp[0];
+	if (fb->format->block_w[0])
+		offset = (src->x1 >> 16) * fb->format->char_per_block[0] /
+			 fb->format->block_w[0];
+	else
+		offset = (src->x1 >> 16) * fb->format->cpp[0];
+
 	offset += (src->y1 >> 16) * fb->pitches[0];
 	dma_addr = rk_obj->dma_addr + offset + fb->offsets[0];
 
@@ -948,6 +968,7 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
 	}
 
 	VOP_WIN_SET(vop, win, format, format);
+	VOP_WIN_SET(vop, win, fmt_10, is_fmt_10(fb->format->format));
 	VOP_WIN_SET(vop, win, yrgb_vir, DIV_ROUND_UP(fb->pitches[0], 4));
 	VOP_WIN_SET(vop, win, yrgb_mst, dma_addr);
 	VOP_WIN_YUV2YUV_SET(vop, win_yuv2yuv, y2r_en, is_yuv);
@@ -964,7 +985,11 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
 		uv_obj = fb->obj[1];
 		rk_uv_obj = to_rockchip_obj(uv_obj);
 
-		offset = (src->x1 >> 16) * bpp / hsub;
+		if (fb->format->block_w[1])
+			offset = (src->x1 >> 16) * bpp /
+				 fb->format->block_w[1] / hsub;
+		else
+			offset = (src->x1 >> 16) * bpp / hsub;
 		offset += (src->y1 >> 16) * fb->pitches[1] / vsub;
 
 		dma_addr = rk_uv_obj->dma_addr + offset + fb->offsets[1];
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
index d03bdb531ef2..db1138da2bd4 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
@@ -154,6 +154,7 @@ struct vop_win_phy {
 	struct vop_reg enable;
 	struct vop_reg gate;
 	struct vop_reg format;
+	struct vop_reg fmt_10;
 	struct vop_reg rb_swap;
 	struct vop_reg act_info;
 	struct vop_reg dsp_info;
diff --git a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c
index 2413deded22c..475c435d659b 100644
--- a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c
+++ b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c
@@ -50,6 +50,23 @@ static const uint32_t formats_win_full[] = {
 	DRM_FORMAT_NV24,
 };
 
+static const uint32_t formats_win_full_10[] = {
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_RGB888,
+	DRM_FORMAT_BGR888,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_BGR565,
+	DRM_FORMAT_NV12,
+	DRM_FORMAT_NV16,
+	DRM_FORMAT_NV24,
+	DRM_FORMAT_NV15,
+	DRM_FORMAT_NV20,
+	DRM_FORMAT_NV30,
+};
+
 static const uint64_t format_modifiers_win_full[] = {
 	DRM_FORMAT_MOD_LINEAR,
 	DRM_FORMAT_MOD_INVALID,
@@ -570,11 +587,12 @@ static const struct vop_scl_regs rk3288_win_full_scl = {
 
 static const struct vop_win_phy rk3288_win01_data = {
 	.scl = &rk3288_win_full_scl,
-	.data_formats = formats_win_full,
-	.nformats = ARRAY_SIZE(formats_win_full),
+	.data_formats = formats_win_full_10,
+	.nformats = ARRAY_SIZE(formats_win_full_10),
 	.format_modifiers = format_modifiers_win_full,
 	.enable = VOP_REG(RK3288_WIN0_CTRL0, 0x1, 0),
 	.format = VOP_REG(RK3288_WIN0_CTRL0, 0x7, 1),
+	.fmt_10 = VOP_REG(RK3288_WIN0_CTRL0, 0x1, 4),
 	.rb_swap = VOP_REG(RK3288_WIN0_CTRL0, 0x1, 12),
 	.act_info = VOP_REG(RK3288_WIN0_ACT_INFO, 0x1fff1fff, 0),
 	.dsp_info = VOP_REG(RK3288_WIN0_DSP_INFO, 0x0fff0fff, 0),
@@ -704,11 +722,12 @@ static const struct vop_intr rk3368_vop_intr = {
 
 static const struct vop_win_phy rk3368_win01_data = {
 	.scl = &rk3288_win_full_scl,
-	.data_formats = formats_win_full,
-	.nformats = ARRAY_SIZE(formats_win_full),
+	.data_formats = formats_win_full_10,
+	.nformats = ARRAY_SIZE(formats_win_full_10),
 	.format_modifiers = format_modifiers_win_full,
 	.enable = VOP_REG(RK3368_WIN0_CTRL0, 0x1, 0),
 	.format = VOP_REG(RK3368_WIN0_CTRL0, 0x7, 1),
+	.fmt_10 = VOP_REG(RK3368_WIN0_CTRL0, 0x1, 4),
 	.rb_swap = VOP_REG(RK3368_WIN0_CTRL0, 0x1, 12),
 	.x_mir_en = VOP_REG(RK3368_WIN0_CTRL0, 0x1, 21),
 	.y_mir_en = VOP_REG(RK3368_WIN0_CTRL0, 0x1, 22),
@@ -853,11 +872,12 @@ static const struct vop_win_yuv2yuv_data rk3399_vop_big_win_yuv2yuv_data[] = {
 
 static const struct vop_win_phy rk3399_win01_data = {
 	.scl = &rk3288_win_full_scl,
-	.data_formats = formats_win_full,
-	.nformats = ARRAY_SIZE(formats_win_full),
+	.data_formats = formats_win_full_10,
+	.nformats = ARRAY_SIZE(formats_win_full_10),
 	.format_modifiers = format_modifiers_win_full_afbc,
 	.enable = VOP_REG(RK3288_WIN0_CTRL0, 0x1, 0),
 	.format = VOP_REG(RK3288_WIN0_CTRL0, 0x7, 1),
+	.fmt_10 = VOP_REG(RK3288_WIN0_CTRL0, 0x1, 4),
 	.rb_swap = VOP_REG(RK3288_WIN0_CTRL0, 0x1, 12),
 	.y_mir_en = VOP_REG(RK3288_WIN0_CTRL0, 0x1, 22),
 	.act_info = VOP_REG(RK3288_WIN0_ACT_INFO, 0x1fff1fff, 0),
-- 
2.25.1