[FFmpeg-devel,v11] lavu/frame: Add Dolby Vision metadata side data type

From: Niklas Haas <git@haasn.dev>

Yeah, I think I agree that this is probably the best compromise here.

Updated documentation (and also changed one unnecessarily-large uint64_t
to uint16_t)

---
In order to be able to extend this struct later (as the Dolby Vision RPU
evolves), all of the 'container' structs are considered extensible, and
the individual constituent fields must instead be accessed via offsets.
The precedent for this style of access is set in
<libavutil/detection_bbox.h>

Signed-off-by: Niklas Haas <git@haasn.dev>
---
 doc/APIchanges        |   3 +
 libavutil/dovi_meta.c |  25 +++++++
 libavutil/dovi_meta.h | 166 ++++++++++++++++++++++++++++++++++++++++++
 libavutil/frame.c     |   1 +
 libavutil/frame.h     |   9 ++-
 libavutil/version.h   |   2 +-
 6 files changed, 204 insertions(+), 2 deletions(-)

Niklas Haas:
> From: Niklas Haas <git@haasn.dev>
> 
> Yeah, I think I agree that this is probably the best compromise here.
> 
> Updated documentation (and also changed one unnecessarily-large uint64_t
> to uint16_t)
> 
> ---
> In order to be able to extend this struct later (as the Dolby Vision RPU
> evolves), all of the 'container' structs are considered extensible, and
> the individual constituent fields must instead be accessed via offsets.
> The precedent for this style of access is set in
> <libavutil/detection_bbox.h>
> 
> Signed-off-by: Niklas Haas <git@haasn.dev>
> ---
>  doc/APIchanges        |   3 +
>  libavutil/dovi_meta.c |  25 +++++++
>  libavutil/dovi_meta.h | 166 ++++++++++++++++++++++++++++++++++++++++++
>  libavutil/frame.c     |   1 +
>  libavutil/frame.h     |   9 ++-
>  libavutil/version.h   |   2 +-
>  6 files changed, 204 insertions(+), 2 deletions(-)
> 
> diff --git a/doc/APIchanges b/doc/APIchanges
> index 670a59329e..5721486f09 100644
> --- a/doc/APIchanges
> +++ b/doc/APIchanges
> @@ -14,6 +14,9 @@ libavutil:     2021-04-27
>  
>  API changes, most recent first:
>  
> +2021-12-xx - xxxxxxxxxx - lavu 57.14.100 - frame.h
> +  Add AV_FRAME_DATA_DOVI_METADATA.
> +
>  2021-12-xx - xxxxxxxxxx - lavu 57.13.100 - hwcontext_videotoolbox.h
>    Add av_vt_pixbuf_set_attachments
>  
> diff --git a/libavutil/dovi_meta.c b/libavutil/dovi_meta.c
> index 7bd08f6c54..9c50da561e 100644
> --- a/libavutil/dovi_meta.c
> +++ b/libavutil/dovi_meta.c
> @@ -33,3 +33,28 @@ AVDOVIDecoderConfigurationRecord *av_dovi_alloc(size_t *size)
>  
>      return dovi;
>  }
> +
> +typedef struct AVDOVIMetadataInternal {
> +    AVDOVIMetadata metadata;
> +    AVDOVIRpuDataHeader header;
> +    AVDOVIDataMapping mapping;
> +    AVDOVIColorMetadata color;
> +} AVDOVIMetadataInternal;
> +
> +AVDOVIMetadata *av_dovi_metadata_alloc(size_t *size)
> +{
> +    AVDOVIMetadataInternal *dovi = av_mallocz(sizeof(AVDOVIMetadataInternal));
> +    if (!dovi)
> +        return NULL;
> +
> +    if (size)
> +        *size = sizeof(*dovi);
> +
> +    dovi->metadata = (struct AVDOVIMetadata) {
> +        .header_offset  = offsetof(AVDOVIMetadataInternal, header),
> +        .mapping_offset = offsetof(AVDOVIMetadataInternal, mapping),
> +        .color_offset   = offsetof(AVDOVIMetadataInternal, color),
> +    };
> +
> +    return &dovi->metadata;
> +}
> diff --git a/libavutil/dovi_meta.h b/libavutil/dovi_meta.h
> index 299911d434..3d11e02bff 100644
> --- a/libavutil/dovi_meta.h
> +++ b/libavutil/dovi_meta.h
> @@ -29,6 +29,7 @@
>  
>  #include <stdint.h>
>  #include <stddef.h>
> +#include "rational.h"
>  
>  /*
>   * DOVI configuration
> @@ -67,4 +68,169 @@ typedef struct AVDOVIDecoderConfigurationRecord {
>   */
>  AVDOVIDecoderConfigurationRecord *av_dovi_alloc(size_t *size);
>  
> +/**
> + * Dolby Vision RPU data header.
> + *
> + * @note sizeof(AVDOVIRpuDataHeader) is not part of the public ABI.
> + */
> +typedef struct AVDOVIRpuDataHeader {
> +    uint8_t rpu_type;
> +    uint16_t rpu_format;
> +    uint8_t vdr_rpu_profile;
> +    uint8_t vdr_rpu_level;
> +    uint8_t chroma_resampling_explicit_filter_flag;
> +    uint8_t coef_data_type; /* informative, lavc always converts to fixed */
> +    uint8_t coef_log2_denom;
> +    uint8_t vdr_rpu_normalized_idc;
> +    uint8_t bl_video_full_range_flag;
> +    uint8_t bl_bit_depth; /* [8, 16] */
> +    uint8_t el_bit_depth; /* [8, 16] */
> +    uint8_t vdr_bit_depth; /* [8, 16] */
> +    uint8_t spatial_resampling_filter_flag;
> +    uint8_t el_spatial_resampling_filter_flag;
> +    uint8_t disable_residual_flag;
> +} AVDOVIRpuDataHeader;
> +
> +enum AVDOVIMappingMethod {
> +    AV_DOVI_MAPPING_POLYNOMIAL = 0,
> +    AV_DOVI_MAPPING_MMR = 1,
> +};
> +
> +/**
> + * Coefficients of a piece-wise function. The pieces of the function span the
> + * value ranges between two adjacent pivot values.
> + */
> +#define AV_DOVI_MAX_PIECES 8
> +typedef struct AVDOVIReshapingCurve {
> +    uint8_t num_pivots;                         /* [2, 9] */
> +    uint16_t pivots[AV_DOVI_MAX_PIECES + 1];    /* sorted ascending */
> +    enum AVDOVIMappingMethod mapping_idc[AV_DOVI_MAX_PIECES];
> +    /* AV_DOVI_MAPPING_POLYNOMIAL */
> +    uint8_t poly_order[AV_DOVI_MAX_PIECES];     /* [1, 2] */
> +    int64_t poly_coef[AV_DOVI_MAX_PIECES][3];   /* x^0, x^1, x^2 */
> +    /* AV_DOVI_MAPPING_MMR */
> +    uint8_t mmr_order[AV_DOVI_MAX_PIECES];      /* [1, 3] */
> +    int64_t mmr_constant[AV_DOVI_MAX_PIECES];
> +    int64_t mmr_coef[AV_DOVI_MAX_PIECES][3/* order - 1 */][7];
> +} AVDOVIReshapingCurve;
> +
> +enum AVDOVINLQMethod {
> +    AV_DOVI_NLQ_NONE = -1,
> +    AV_DOVI_NLQ_LINEAR_DZ = 0,
> +};
> +
> +/**
> + * Coefficients of the non-linear inverse quantization. For the interpretation
> + * of these, see ETSI GS CCM 001.
> + */
> +typedef struct AVDOVINLQParams {
> +    uint16_t nlq_offset;
> +    uint64_t vdr_in_max;
> +    /* AV_DOVI_NLQ_LINEAR_DZ */
> +    uint64_t linear_deadzone_slope;
> +    uint64_t linear_deadzone_threshold;
> +} AVDOVINLQParams;
> +
> +/**
> + * Dolby Vision RPU data mapping parameters.
> + *
> + * @note sizeof(AVDOVIDataMapping) is not part of the public ABI.
> + */
> +typedef struct AVDOVIDataMapping {
> +    uint8_t vdr_rpu_id;
> +    uint8_t mapping_color_space;
> +    uint8_t mapping_chroma_format_idc;
> +    AVDOVIReshapingCurve curves[3]; /* per component */
> +
> +    /* Non-linear inverse quantization */
> +    enum AVDOVINLQMethod nlq_method_idc;
> +    uint32_t num_x_partitions;
> +    uint32_t num_y_partitions;
> +    AVDOVINLQParams nlq[3]; /* per component */
> +} AVDOVIDataMapping;
> +
> +/**
> + * Dolby Vision RPU colorspace metadata parameters.
> + *
> + * @note sizeof(AVDOVIColorMetadata) is not part of the public ABI.
> + */
> +typedef struct AVDOVIColorMetadata {
> +    uint8_t dm_metadata_id;
> +    uint8_t scene_refresh_flag;
> +
> +    /**
> +     * Coefficients of the custom Dolby Vision IPT-PQ matrices. These are to be
> +     * used instead of the matrices indicated by the frame's colorspace tags.
> +     * The output of rgb_to_lms_matrix is to be fed into a BT.2020 LMS->RGB
> +     * matrix based on a Hunt-Pointer-Estevez transform, but without any
> +     * crosstalk. (See the definition of the ICtCp colorspace for more
> +     * information.)
> +     */
> +    AVRational ycc_to_rgb_matrix[9]; /* before PQ linearization */
> +    AVRational ycc_to_rgb_offset[3]; /* input offset of neutral value */
> +    AVRational rgb_to_lms_matrix[9]; /* after PQ linearization */
> +
> +    /**
> +     * Extra signal metadata (see Dolby patents for more info).
> +     */
> +    uint16_t signal_eotf;
> +    uint16_t signal_eotf_param0;
> +    uint16_t signal_eotf_param1;
> +    uint32_t signal_eotf_param2;
> +    uint8_t signal_bit_depth;
> +    uint8_t signal_color_space;
> +    uint8_t signal_chroma_format;
> +    uint8_t signal_full_range_flag; /* [0, 3] */
> +    uint16_t source_min_pq;
> +    uint16_t source_max_pq;
> +    uint16_t source_diagonal;
> +} AVDOVIColorMetadata;
> +
> +/**
> + * Combined struct representing a combination of header, mapping and color
> + * metadata, for attaching to frames as side data.
> + *
> + * @note The struct must be allocated with av_dovi_metadata_alloc() and
> + *       its size is not a part of the public ABI.
> + */
> +
> +typedef struct AVDOVIMetadata {
> +    /**
> +     * Offset in bytes from the beginning of this structure at which the
> +     * respective structs start.
> +     */
> +    size_t header_offset;   /* AVDOVIRpuDataHeader */
> +    size_t mapping_offset;  /* AVDOVIDataMapping */
> +    size_t color_offset;    /* AVDOVIColorMetadata */
> +} AVDOVIMetadata;
> +
> +static av_always_inline AVDOVIRpuDataHeader *
> +av_dovi_get_header(const AVDOVIMetadata *data)
> +{
> +    return (AVDOVIRpuDataHeader *)((uint8_t *) data + data->header_offset);
> +}
> +
> +static av_always_inline AVDOVIDataMapping *
> +av_dovi_get_mapping(const AVDOVIMetadata *data)
> +{
> +    return (AVDOVIDataMapping *)((uint8_t *) data + data->mapping_offset);
> +}
> +
> +static av_always_inline AVDOVIColorMetadata *
> +av_dovi_get_color(const AVDOVIMetadata *data)
> +{
> +    return (AVDOVIColorMetadata *)((uint8_t *) data + data->color_offset);
> +}
> +
> +/**
> + * Allocate an AVDOVIMetadata structure and initialize its
> + * fields to default values.
> + *
> + * @param size If this parameter is non-NULL, the size in bytes of the
> + *             allocated struct will be written here on success
> + *
> + * @return the newly allocated struct or NULL on failure
> + */
> +AVDOVIMetadata *av_dovi_metadata_alloc(size_t *size);
> +
>  #endif /* AVUTIL_DOVI_META_H */
> diff --git a/libavutil/frame.c b/libavutil/frame.c
> index 0912ad9131..8997c85e35 100644
> --- a/libavutil/frame.c
> +++ b/libavutil/frame.c
> @@ -729,6 +729,7 @@ const char *av_frame_side_data_name(enum AVFrameSideDataType type)
>      case AV_FRAME_DATA_FILM_GRAIN_PARAMS:           return "Film grain parameters";
>      case AV_FRAME_DATA_DETECTION_BBOXES:            return "Bounding boxes for object detection and classification";
>      case AV_FRAME_DATA_DOVI_RPU_BUFFER:             return "Dolby Vision RPU Data";
> +    case AV_FRAME_DATA_DOVI_METADATA:               return "Dolby Vision Metadata";
>      }
>      return NULL;
>  }
> diff --git a/libavutil/frame.h b/libavutil/frame.h
> index 3f295f6b9e..18e239f870 100644
> --- a/libavutil/frame.h
> +++ b/libavutil/frame.h
> @@ -189,11 +189,18 @@ enum AVFrameSideDataType {
>      AV_FRAME_DATA_DETECTION_BBOXES,
>  
>      /**
> -     * Dolby Vision RPU data, suitable for passing to x265
> +     * Dolby Vision RPU raw data, suitable for passing to x265
>       * or other libraries. Array of uint8_t, with NAL emulation
>       * bytes intact.
>       */
>      AV_FRAME_DATA_DOVI_RPU_BUFFER,
> +
> +    /**
> +     * Parsed Dolby Vision metadata, suitable for passing to a software
> +     * implementation. The payload is the AVDOVIMetadata struct defined in
> +     * libavutil/dovi_meta.h.
> +     */
> +    AV_FRAME_DATA_DOVI_METADATA,
>  };
>  
>  enum AVActiveFormatDescription {
> diff --git a/libavutil/version.h b/libavutil/version.h
> index 3cac09cb96..318045d4c4 100644
> --- a/libavutil/version.h
> +++ b/libavutil/version.h
> @@ -79,7 +79,7 @@
>   */
>  
>  #define LIBAVUTIL_VERSION_MAJOR  57
> -#define LIBAVUTIL_VERSION_MINOR  13
> +#define LIBAVUTIL_VERSION_MINOR  14
>  #define LIBAVUTIL_VERSION_MICRO 100
>  
>  #define LIBAVUTIL_VERSION_INT   AV_VERSION_INT(LIBAVUTIL_VERSION_MAJOR, \
> 

No further comment from me.

- Andreas