lavc/hevcdec: Parse DOVI RPU NALs

And expose the parsed values as frame side data. Update FATE results to
match.

It's worth documenting that this relies on the dovi configuration record
being present on the first AVPacket fed to the decoder, which in
practice is the case if if the API user has called something like
av_format_inject_global_side_data, which is unfortunately not the
default.

This commit is not the time and place to change that behavior, though.

Signed-off-by: Niklas Haas <git@haasn.dev>
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>

4 files changed, 256 insertions, 9 deletions

diff --git a/configure b/configure
index 34878117e7..50aa0d596d 100755
--- a/configure
+++ b/configure
@@ -2826,7 +2826,7 @@ h264_decoder_suggest="error_resilience"
 hap_decoder_select="snappy texturedsp"
 hap_encoder_deps="libsnappy"
 hap_encoder_select="texturedspenc"
-hevc_decoder_select="atsc_a53 bswapdsp cabac golomb hevcparse videodsp"
+hevc_decoder_select="atsc_a53 bswapdsp cabac dovi_rpu golomb hevcparse videodsp"
 huffyuv_decoder_select="bswapdsp huffyuvdsp llviddsp"
 huffyuv_encoder_select="bswapdsp huffman huffyuvencdsp llvidencdsp"
 hymt_decoder_select="huffyuv_decoder"
diff --git a/libavcodec/hevcdec.c b/libavcodec/hevcdec.c
index 3aa70e2245..8d7a4f7147 100644
--- a/libavcodec/hevcdec.c
+++ b/libavcodec/hevcdec.c
@@ -2723,6 +2723,7 @@ error:
 static int set_side_data(HEVCContext *s)
 {
     AVFrame *out = s->ref->frame;
+    int ret;
 
     if (s->sei.frame_packing.present &&
         s->sei.frame_packing.arrangement_type >= 3 &&
@@ -2977,6 +2978,9 @@ static int set_side_data(HEVCContext *s)
         s->rpu_buf = NULL;
     }
 
+    if ((ret = ff_dovi_attach_side_data(&s->dovi_ctx, out)) < 0)
+        return ret;
+
     return 0;
 }
 
@@ -3308,16 +3312,23 @@ static int decode_nal_units(HEVCContext *s, const uint8_t *buf, int length)
     if (s->pkt.nb_nals > 1 && s->pkt.nals[s->pkt.nb_nals - 1].type == HEVC_NAL_UNSPEC62 &&
         s->pkt.nals[s->pkt.nb_nals - 1].size > 2 && !s->pkt.nals[s->pkt.nb_nals - 1].nuh_layer_id
         && !s->pkt.nals[s->pkt.nb_nals - 1].temporal_id) {
+        H2645NAL *nal = &s->pkt.nals[s->pkt.nb_nals - 1];
         if (s->rpu_buf) {
             av_buffer_unref(&s->rpu_buf);
             av_log(s->avctx, AV_LOG_WARNING, "Multiple Dolby Vision RPUs found in one AU. Skipping previous.\n");
         }
 
-        s->rpu_buf = av_buffer_alloc(s->pkt.nals[s->pkt.nb_nals - 1].raw_size - 2);
+        s->rpu_buf = av_buffer_alloc(nal->raw_size - 2);
         if (!s->rpu_buf)
             return AVERROR(ENOMEM);
+        memcpy(s->rpu_buf->data, nal->raw_data + 2, nal->raw_size - 2);
 
-        memcpy(s->rpu_buf->data, s->pkt.nals[s->pkt.nb_nals - 1].raw_data + 2, s->pkt.nals[s->pkt.nb_nals - 1].raw_size - 2);
+        ret = ff_dovi_rpu_parse(&s->dovi_ctx, nal->data + 2, nal->size - 2);
+        if (ret < 0) {
+            av_buffer_unref(&s->rpu_buf);
+            av_log(s->avctx, AV_LOG_WARNING, "Error parsing DOVI NAL unit.\n");
+            /* ignore */
+        }
     }
 
     /* decode the NAL units */
@@ -3450,8 +3461,8 @@ static int hevc_decode_frame(AVCodecContext *avctx, void *data, int *got_output,
                              AVPacket *avpkt)
 {
     int ret;
-    size_t new_extradata_size;
-    uint8_t *new_extradata;
+    uint8_t *sd;
+    size_t sd_size;
     HEVCContext *s = avctx->priv_data;
 
     if (!avpkt->size) {
@@ -3463,14 +3474,17 @@ static int hevc_decode_frame(AVCodecContext *avctx, void *data, int *got_output,
         return 0;
     }
 
-    new_extradata = av_packet_get_side_data(avpkt, AV_PKT_DATA_NEW_EXTRADATA,
-                                            &new_extradata_size);
-    if (new_extradata && new_extradata_size > 0) {
-        ret = hevc_decode_extradata(s, new_extradata, new_extradata_size, 0);
+    sd = av_packet_get_side_data(avpkt, AV_PKT_DATA_NEW_EXTRADATA, &sd_size);
+    if (sd && sd_size > 0) {
+        ret = hevc_decode_extradata(s, sd, sd_size, 0);
         if (ret < 0)
             return ret;
     }
 
+    sd = av_packet_get_side_data(avpkt, AV_PKT_DATA_DOVI_CONF, &sd_size);
+    if (sd && sd_size > 0)
+        ff_dovi_update_cfg(&s->dovi_ctx, (AVDOVIDecoderConfigurationRecord *) sd);
+
     s->ref = NULL;
     ret    = decode_nal_units(s, avpkt->data, avpkt->size);
     if (ret < 0)
@@ -3563,6 +3577,7 @@ static av_cold int hevc_decode_free(AVCodecContext *avctx)
 
     pic_arrays_free(s);
 
+    ff_dovi_ctx_unref(&s->dovi_ctx);
     av_buffer_unref(&s->rpu_buf);
 
     av_freep(&s->md5_ctx);
@@ -3647,6 +3662,7 @@ static av_cold int hevc_init_context(AVCodecContext *avctx)
 
     ff_bswapdsp_init(&s->bdsp);
 
+    s->dovi_ctx.logctx = avctx;
     s->context_initialized = 1;
     s->eos = 0;
 
@@ -3755,6 +3771,10 @@ static int hevc_update_thread_context(AVCodecContext *dst,
     if (ret < 0)
         return ret;
 
+    ret = ff_dovi_ctx_replace(&s->dovi_ctx, &s0->dovi_ctx);
+    if (ret < 0)
+        return ret;
+
     s->sei.frame_packing        = s0->sei.frame_packing;
     s->sei.display_orientation  = s0->sei.display_orientation;
     s->sei.mastering_display    = s0->sei.mastering_display;
@@ -3811,6 +3831,7 @@ static void hevc_decode_flush(AVCodecContext *avctx)
     HEVCContext *s = avctx->priv_data;
     ff_hevc_flush_dpb(s);
     ff_hevc_reset_sei(&s->sei);
+    ff_dovi_ctx_flush(&s->dovi_ctx);
     av_buffer_unref(&s->rpu_buf);
     s->max_ra = INT_MAX;
     s->eos = 1;
diff --git a/libavcodec/hevcdec.h b/libavcodec/hevcdec.h
index 870ff178d4..157bc6926f 100644
--- a/libavcodec/hevcdec.h
+++ b/libavcodec/hevcdec.h
@@ -32,6 +32,7 @@
 #include "avcodec.h"
 #include "bswapdsp.h"
 #include "cabac.h"
+#include "dovi_rpu.h"
 #include "get_bits.h"
 #include "hevcpred.h"
 #include "h2645_parse.h"
@@ -574,6 +575,7 @@ typedef struct HEVCContext {
     int nuh_layer_id;
 
     AVBufferRef *rpu_buf;       ///< 0 or 1 Dolby Vision RPUs.
+    DOVIContext dovi_ctx;       ///< Dolby Vision decoding context
 } HEVCContext;
 
 /**
diff --git a/tests/ref/fate/hevc-dv-rpu b/tests/ref/fate/hevc-dv-rpu
index 416d9c51a6..1980ab13ea 100644
--- a/tests/ref/fate/hevc-dv-rpu
+++ b/tests/ref/fate/hevc-dv-rpu
@@ -5,9 +5,233 @@ side_data_type=H.26[45] User Data Unregistered SEI message
 [SIDE_DATA]
 side_data_type=Dolby Vision RPU Data
 [/SIDE_DATA]
+[SIDE_DATA]
+side_data_type=Dolby Vision Metadata
+rpu_type=2
+rpu_format=18
+vdr_rpu_profile=1
+vdr_rpu_level=0
+chroma_resampling_explicit_filter_flag=0
+coef_data_type=0
+coef_log2_denom=23
+vdr_rpu_normalized_idc=1
+bl_video_full_range_flag=0
+bl_bit_depth=10
+el_bit_depth=10
+vdr_bit_depth=12
+spatial_resampling_filter_flag=0
+el_spatial_resampling_filter_flag=0
+disable_residual_flag=1
+vdr_rpu_id=0
+mapping_color_space=0
+mapping_chroma_format_idc=0
+nlq_method_idc=-1
+nlq_method_idc_name=none
+num_x_partitions=1
+num_y_partitions=1
+[COMPONENT]
+pivots=63 132 362 618 874 911 927 935 942
+[SECTION]
+mapping_idc=0
+mapping_idc_name=polynomial
+poly_order=2
+poly_coef=-409680 16721463 -20276640
+[/SECTION]
+[SECTION]
+mapping_idc=0
+mapping_idc_name=polynomial
+poly_order=2
+poly_coef=-119056 13575212 -12867889
+[/SECTION]
+[SECTION]
+mapping_idc=0
+mapping_idc_name=polynomial
+poly_order=2
+poly_coef=1317527 5338528 -948122
+[/SECTION]
+[SECTION]
+mapping_idc=0
+mapping_idc_name=polynomial
+poly_order=2
+poly_coef=2119979 2065496 2288524
+[/SECTION]
+[SECTION]
+mapping_idc=0
+mapping_idc_name=polynomial
+poly_order=2
+poly_coef=7982780 -11367226 9973944
+[/SECTION]
+[SECTION]
+mapping_idc=0
+mapping_idc_name=polynomial
+poly_order=2
+poly_coef=53792084 -114243184 67724328
+[/SECTION]
+[SECTION]
+mapping_idc=0
+mapping_idc_name=polynomial
+poly_order=2
+poly_coef=112973872 -244837568 139764480
+[/SECTION]
+[SECTION]
+mapping_idc=0
+mapping_idc_name=polynomial
+poly_order=2
+poly_coef=236828416 -518849056 291306944
+[/SECTION]
+[/COMPONENT]
+[COMPONENT]
+pivots=0 1023
+[SECTION]
+mapping_idc=1
+mapping_idc_name=mmr
+mmr_order=3
+mmr_constant=-4200453
+mmr_coef=9094176 31944476 739652 -27103344 -3431599 -11015088 22758042 -2028643 -30021218 -906885 26272992 7291404 16488745 -78087176 -1487777 12496543 762460 -4281948 -5768035 -7843163 103636960
+[/SECTION]
+[/COMPONENT]
+[COMPONENT]
+pivots=0 1023
+[SECTION]
+mapping_idc=1
+mapping_idc_name=mmr
+mmr_order=3
+mmr_constant=-10387889
+mmr_coef=29604202 3214133 46206184 -8564340 -53383996 1628407 5426045 -21634202 -5251953 -50812292 19221972 76726656 -425892 -35041240 5917361 2863974 25030554 -14404292 -41230120 1229046 53575140
+[/SECTION]
+[/COMPONENT]
+dm_metadata_id=0
+scene_refresh_flag=1
+ycc_to_rgb_matrix=9574/8192 0/8192 13802/8192 9574/8192 -1540/8192 -5348/8192 9574/8192 17610/8192 0/8192
+ycc_to_rgb_offset=16777216/268435456 134217728/268435456 134217728/268435456
+rgb_to_lms_matrix=7222/16384 8771/16384 390/16384 2654/16384 12430/16384 1300/16384 0/16384 422/16384 15962/16384
+signal_eotf=65535
+signal_eotf_param0=0
+signal_eotf_param1=0
+signal_eotf_param2=0
+signal_bit_depth=12
+signal_color_space=0
+signal_chroma_format=0
+signal_full_range_flag=1
+source_min_pq=0
+source_max_pq=3079
+source_diagonal=42
+[/SIDE_DATA]
 [/FRAME]
 [FRAME]
 [SIDE_DATA]
 side_data_type=Dolby Vision RPU Data
 [/SIDE_DATA]
+[SIDE_DATA]
+side_data_type=Dolby Vision Metadata
+rpu_type=2
+rpu_format=18
+vdr_rpu_profile=1
+vdr_rpu_level=0
+chroma_resampling_explicit_filter_flag=0
+coef_data_type=0
+coef_log2_denom=23
+vdr_rpu_normalized_idc=1
+bl_video_full_range_flag=0
+bl_bit_depth=10
+el_bit_depth=10
+vdr_bit_depth=12
+spatial_resampling_filter_flag=0
+el_spatial_resampling_filter_flag=0
+disable_residual_flag=1
+vdr_rpu_id=0
+mapping_color_space=0
+mapping_chroma_format_idc=0
+nlq_method_idc=-1
+nlq_method_idc_name=none
+num_x_partitions=1
+num_y_partitions=1
+[COMPONENT]
+pivots=63 132 362 618 874 911 927 935 942
+[SECTION]
+mapping_idc=0
+mapping_idc_name=polynomial
+poly_order=2
+poly_coef=-409680 16721463 -20276640
+[/SECTION]
+[SECTION]
+mapping_idc=0
+mapping_idc_name=polynomial
+poly_order=2
+poly_coef=-119056 13575212 -12867889
+[/SECTION]
+[SECTION]
+mapping_idc=0
+mapping_idc_name=polynomial
+poly_order=2
+poly_coef=1317527 5338528 -948122
+[/SECTION]
+[SECTION]
+mapping_idc=0
+mapping_idc_name=polynomial
+poly_order=2
+poly_coef=2119979 2065496 2288524
+[/SECTION]
+[SECTION]
+mapping_idc=0
+mapping_idc_name=polynomial
+poly_order=2
+poly_coef=7982780 -11367226 9973944
+[/SECTION]
+[SECTION]
+mapping_idc=0
+mapping_idc_name=polynomial
+poly_order=2
+poly_coef=53792084 -114243184 67724328
+[/SECTION]
+[SECTION]
+mapping_idc=0
+mapping_idc_name=polynomial
+poly_order=2
+poly_coef=112973872 -244837568 139764480
+[/SECTION]
+[SECTION]
+mapping_idc=0
+mapping_idc_name=polynomial
+poly_order=2
+poly_coef=236828416 -518849056 291306944
+[/SECTION]
+[/COMPONENT]
+[COMPONENT]
+pivots=0 1023
+[SECTION]
+mapping_idc=1
+mapping_idc_name=mmr
+mmr_order=3
+mmr_constant=-4200453
+mmr_coef=9094176 31944476 739652 -27103344 -3431599 -11015088 22758042 -2028643 -30021218 -906885 26272992 7291404 16488745 -78087176 -1487777 12496543 762460 -4281948 -5768035 -7843163 103636960
+[/SECTION]
+[/COMPONENT]
+[COMPONENT]
+pivots=0 1023
+[SECTION]
+mapping_idc=1
+mapping_idc_name=mmr
+mmr_order=3
+mmr_constant=-10387889
+mmr_coef=29604202 3214133 46206184 -8564340 -53383996 1628407 5426045 -21634202 -5251953 -50812292 19221972 76726656 -425892 -35041240 5917361 2863974 25030554 -14404292 -41230120 1229046 53575140
+[/SECTION]
+[/COMPONENT]
+dm_metadata_id=0
+scene_refresh_flag=1
+ycc_to_rgb_matrix=9574/8192 0/8192 13802/8192 9574/8192 -1540/8192 -5348/8192 9574/8192 17610/8192 0/8192
+ycc_to_rgb_offset=16777216/268435456 134217728/268435456 134217728/268435456
+rgb_to_lms_matrix=7222/16384 8771/16384 390/16384 2654/16384 12430/16384 1300/16384 0/16384 422/16384 15962/16384
+signal_eotf=65535
+signal_eotf_param0=0
+signal_eotf_param1=0
+signal_eotf_param2=0
+signal_bit_depth=12
+signal_color_space=0
+signal_chroma_format=0
+signal_full_range_flag=1
+source_min_pq=0
+source_max_pq=3079
+source_diagonal=42
+[/SIDE_DATA]
 [/FRAME]