[FFmpeg-devel] [PATCH 3/4] libavformat/hls: add support for decryption of HLS media segments encrypted using SAMPLE-AES encryption method

[ffmpegandmahanstreamer at e.email]

lgtm after you fix nitpick about if statements in my opinon

August 1, 2021 10:54 AM, "Nachiket Tarate" <nachiket.programmer at gmail.com> wrote:

> Apple HTTP Live Streaming Sample Encryption:
> 
> https://developer.apple.com/library/ios/documentation/AudioVideo/Conceptual/HLS_Sample_Encryption
> 
> Signed-off-by: Nachiket Tarate <nachiket.programmer at gmail.com>
> ---
> libavformat/Makefile | 2 +-
> libavformat/hls.c | 128 +++++++--
> libavformat/hls_sample_encryption.c | 389 ++++++++++++++++++++++++++++
> libavformat/hls_sample_encryption.h | 65 +++++
> libavformat/mpegts.c | 11 +
> 5 files changed, 576 insertions(+), 19 deletions(-)
> create mode 100644 libavformat/hls_sample_encryption.c
> create mode 100644 libavformat/hls_sample_encryption.h
> 
> diff --git a/libavformat/Makefile b/libavformat/Makefile
> index 813ddd3c20..7e3c9c23c6 100644
> --- a/libavformat/Makefile
> +++ b/libavformat/Makefile
> @@ -238,7 +238,7 @@ OBJS-$(CONFIG_HCOM_DEMUXER) += hcom.o pcm.o
> OBJS-$(CONFIG_HDS_MUXER) += hdsenc.o
> OBJS-$(CONFIG_HEVC_DEMUXER) += hevcdec.o rawdec.o
> OBJS-$(CONFIG_HEVC_MUXER) += rawenc.o
> -OBJS-$(CONFIG_HLS_DEMUXER) += hls.o
> +OBJS-$(CONFIG_HLS_DEMUXER) += hls.o hls_sample_encryption.o
> OBJS-$(CONFIG_HLS_MUXER) += hlsenc.o hlsplaylist.o avc.o
> OBJS-$(CONFIG_HNM_DEMUXER) += hnm.o
> OBJS-$(CONFIG_ICO_DEMUXER) += icodec.o
> diff --git a/libavformat/hls.c b/libavformat/hls.c
> index 3c1b80f60c..022dae0391 100644
> --- a/libavformat/hls.c
> +++ b/libavformat/hls.c
> @@ -2,6 +2,7 @@
> * Apple HTTP Live Streaming demuxer
> * Copyright (c) 2010 Martin Storsjo
> * Copyright (c) 2013 Anssi Hannula
> + * Copyright (c) 2021 Nachiket Tarate
> *
> * This file is part of FFmpeg.
> *
> @@ -39,6 +40,8 @@
> #include "avio_internal.h"
> #include "id3v2.h"
> 
> +#include "hls_sample_encryption.h"
> +
> #define INITIAL_BUFFER_SIZE 32768
> 
> #define MAX_FIELD_LEN 64
> @@ -145,6 +148,8 @@ struct playlist {
> int id3_changed; /* ID3 tag data has changed at some point */
> ID3v2ExtraMeta *id3_deferred_extra; /* stored here until subdemuxer is opened */
> 
> + HLSAudioSetupInfo audio_setup_info;
> +
> int64_t seek_timestamp;
> int seek_flags;
> int seek_stream_index; /* into subdemuxer stream array */
> @@ -214,6 +219,7 @@ typedef struct HLSContext {
> int http_multiple;
> int http_seekable;
> AVIOContext *playlist_pb;
> + HLSCryptoContext crypto_ctx;
> } HLSContext;
> 
> static void free_segment_dynarray(struct segment **segments, int n_segments)
> @@ -1006,7 +1012,10 @@ fail:
> 
> static struct segment *current_segment(struct playlist *pls)
> {
> - return pls->segments[pls->cur_seq_no - pls->start_seq_no];
> + int64_t n = pls->cur_seq_no - pls->start_seq_no;
> + if (n >= pls->n_segments)
> + return NULL;
> + return pls->segments[n];
> }
> 
> static struct segment *next_segment(struct playlist *pls)
> @@ -1035,17 +1044,18 @@ static int read_from_url(struct playlist *pls, struct segment *seg,
> 
> /* Parse the raw ID3 data and pass contents to caller */
> static void parse_id3(AVFormatContext *s, AVIOContext *pb,
> - AVDictionary **metadata, int64_t *dts,
> + AVDictionary **metadata, int64_t *dts, HLSAudioSetupInfo *audio_setup_info,
> ID3v2ExtraMetaAPIC **apic, ID3v2ExtraMeta **extra_meta)
> {
> static const char id3_priv_owner_ts[] = "com.apple.streaming.transportStreamTimestamp";
> + static const char id3_priv_owner_audio_setup[] = "com.apple.streaming.audioDescription";
> ID3v2ExtraMeta *meta;
> 
> ff_id3v2_read_dict(pb, metadata, ID3v2_DEFAULT_MAGIC, extra_meta);
> for (meta = *extra_meta; meta; meta = meta->next) {
> if (!strcmp(meta->tag, "PRIV")) {
> ID3v2ExtraMetaPRIV *priv = &meta->data.priv;
> - if (priv->datasize == 8 && !strcmp(priv->owner, id3_priv_owner_ts)) {
> + if (priv->datasize == 8 && !av_strncasecmp(priv->owner, id3_priv_owner_ts, 44)) {
> /* 33-bit MPEG timestamp */
> int64_t ts = AV_RB64(priv->data);
> av_log(s, AV_LOG_DEBUG, "HLS ID3 audio timestamp %"PRId64"\n", ts);
> @@ -1053,6 +1063,8 @@ static void parse_id3(AVFormatContext *s, AVIOContext *pb,
> *dts = ts;
> else
> av_log(s, AV_LOG_ERROR, "Invalid HLS ID3 audio timestamp %"PRId64"\n", ts);
> + } else if (priv->datasize >= 8 && !av_strncasecmp(priv->owner, id3_priv_owner_audio_setup, 36)) {
> + ff_hls_senc_read_audio_setup_info(audio_setup_info, priv->data, priv->datasize);
> }
> } else if (!strcmp(meta->tag, "APIC") && apic)
> *apic = &meta->data.apic;
> @@ -1096,7 +1108,7 @@ static void handle_id3(AVIOContext *pb, struct playlist *pls)
> ID3v2ExtraMeta *extra_meta = NULL;
> int64_t timestamp = AV_NOPTS_VALUE;
> 
> - parse_id3(pls->ctx, pb, &metadata, &timestamp, &apic, &extra_meta);
> + parse_id3(pls->ctx, pb, &metadata, &timestamp, &pls->audio_setup_info, &apic, &extra_meta);
> 
> if (timestamp != AV_NOPTS_VALUE) {
> pls->id3_mpegts_timestamp = timestamp;
> @@ -1250,10 +1262,7 @@ static int open_input(HLSContext *c, struct playlist *pls, struct segment
> *seg,
> av_log(pls->parent, AV_LOG_VERBOSE, "HLS request for url '%s', offset %"PRId64", playlist %d\n",
> seg->url, seg->url_offset, pls->index);
> 
> - if (seg->key_type == KEY_NONE) {
> - ret = open_url(pls->parent, in, seg->url, &c->avio_opts, opts, &is_http);
> - } else if (seg->key_type == KEY_AES_128) {
> - char iv[33], key[33], url[MAX_URL_SIZE];
> + if (seg->key_type == KEY_AES_128 || seg->key_type == KEY_SAMPLE_AES) {
> if (strcmp(seg->key, pls->key_url)) {
> AVIOContext *pb = NULL;
> if (open_url(pls->parent, &pb, seg->key, &c->avio_opts, opts, NULL) == 0) {
> @@ -1269,6 +1278,10 @@ static int open_input(HLSContext *c, struct playlist *pls, struct segment
> *seg,
> }
> av_strlcpy(pls->key_url, seg->key, sizeof(pls->key_url));
> }
> + }
> +
> + if (seg->key_type == KEY_AES_128) {
> + char iv[33], key[33], url[MAX_URL_SIZE];
> ff_data_to_hex(iv, seg->iv, sizeof(seg->iv), 0);
> ff_data_to_hex(key, pls->key, sizeof(pls->key), 0);
> iv[32] = key[32] = '\0';
> @@ -1285,13 +1298,9 @@ static int open_input(HLSContext *c, struct playlist *pls, struct segment
> *seg,
> goto cleanup;
> }
> ret = 0;
> - } else if (seg->key_type == KEY_SAMPLE_AES) {
> - av_log(pls->parent, AV_LOG_ERROR,
> - "SAMPLE-AES encryption is not supported yet\n");
> - ret = AVERROR_PATCHWELCOME;
> + } else {
> + ret = open_url(pls->parent, in, seg->url, &c->avio_opts, opts, &is_http);
> }
> - else
> - ret = AVERROR(ENOSYS);
> 
> /* Seek to the requested position. If this was a HTTP request, the offset
> * should already be where want it to, but this allows e.g. local testing
> @@ -1854,6 +1863,9 @@ static int hls_close(AVFormatContext *s)
> free_variant_list(c);
> free_rendition_list(c);
> 
> + if (c->crypto_ctx.aes_ctx)
> + av_free(c->crypto_ctx.aes_ctx);
> +
> av_dict_free(&c->avio_opts);
> ff_format_io_close(c->ctx, &c->playlist_pb);
> 
> @@ -1959,7 +1971,8 @@ static int hls_read_header(AVFormatContext *s)
> struct playlist *pls = c->playlists[i];
> const AVInputFormat *in_fmt = NULL;
> char *url;
> - AVDictionary *seg_format_opts = NULL;
> + AVDictionary *options = NULL;
> + struct segment *seg = NULL;
> 
> if (!(pls->ctx = avformat_alloc_context()))
> return AVERROR(ENOMEM);
> @@ -1989,8 +2002,55 @@ static int hls_read_header(AVFormatContext *s)
> pls->ctx = NULL;
> return AVERROR(ENOMEM);
> }
> +
> ffio_init_context(&pls->pb, pls->read_buffer, INITIAL_BUFFER_SIZE, 0, pls,
> read_data, NULL, NULL);
> +
> + /*
> + * If encryption scheme is SAMPLE-AES, try to read ID3 tags of
> + * external audio track that contains audio setup information
> + */
> + seg = current_segment(pls);
> + if (seg && seg->key_type == KEY_SAMPLE_AES && pls->n_renditions > 0 &&
> + pls->renditions[0]->type == AVMEDIA_TYPE_AUDIO) {
> + uint8_t buf[HLS_MAX_ID3_TAGS_DATA_LEN];
> + if ((ret = avio_read(&pls->pb, buf, HLS_MAX_ID3_TAGS_DATA_LEN)) < 0) {
> + /* Fail if error was not end of file */
> + if (ret != AVERROR_EOF) {
> + avformat_free_context(pls->ctx);
> + pls->ctx = NULL;
> + return ret;
> + }
> + }
> + ret = 0;
> + /* Reset reading */
> + ff_format_io_close(pls->parent, &pls->input);
> + pls->input = NULL;
> + pls->input_read_done = 0;
> + ff_format_io_close(pls->parent, &pls->input_next);
> + pls->input_next = NULL;
> + pls->input_next_requested = 0;
> + pls->cur_seg_offset = 0;
> + pls->cur_init_section = NULL;
> + /* Reset EOF flag */
> + pls->pb.eof_reached = 0;
> + /* Clear any buffered data */
> + pls->pb.buf_end = pls->pb.buf_ptr = pls->pb.buffer;
> + /* Reset the position */
> + pls->pb.pos = 0;
> + }
> +
> + /*
> + * If encryption scheme is SAMPLE-AES and audio setup information is present in external audio
> track,
> + * use that information to find the media format, otherwise probe input data
> + */
> + if (seg && seg->key_type == KEY_SAMPLE_AES && pls->is_id3_timestamped &&
> + pls->audio_setup_info.codec_id != AV_CODEC_ID_NONE) {
> + void *iter = NULL;
> + while ((in_fmt = (const AVInputFormat *)av_demuxer_iterate(&iter)))
> + if (in_fmt->raw_codec_id == pls->audio_setup_info.codec_id)
> + break;
> + } else {
> pls->ctx->probesize = s->probesize > 0 ? s->probesize : 1024 * 4;
> pls->ctx->max_analyze_duration = s->max_analyze_duration > 0 ? s->max_analyze_duration : 4 *
> AV_TIME_BASE;
> pls->ctx->interrupt_callback = s->interrupt_callback;
> @@ -2008,6 +2068,24 @@ static int hls_read_header(AVFormatContext *s)
> return ret;
> }
> av_free(url);
> + }
> +
> + if (seg && seg->key_type == KEY_SAMPLE_AES) {
> + if (strstr(in_fmt->name, "mov")) {
> + char key[33];
> + ff_data_to_hex(key, pls->key, sizeof(pls->key), 0);
> + key[32] = '\0';
> + av_dict_set(&options, "decryption_key", key, AV_OPT_FLAG_DECODING_PARAM);
> + } else if (!c->crypto_ctx.aes_ctx) {
> + c->crypto_ctx.aes_ctx = av_aes_alloc();
> + if (!c->crypto_ctx.aes_ctx) {
> + avformat_free_context(pls->ctx);
> + pls->ctx = NULL;
> + return AVERROR(ENOMEM);
> + }
> + }
> + }
> +
> pls->ctx->pb = &pls->pb;
> pls->ctx->io_open = nested_io_open;
> pls->ctx->flags |= s->flags & ~AVFMT_FLAG_CUSTOM_IO;
> @@ -2015,10 +2093,10 @@ static int hls_read_header(AVFormatContext *s)
> if ((ret = ff_copy_whiteblacklists(pls->ctx, s)) < 0)
> return ret;
> 
> - av_dict_copy(&seg_format_opts, c->seg_format_opts, 0);
> + av_dict_copy(&options, c->seg_format_opts, 0);
> 
> - ret = avformat_open_input(&pls->ctx, pls->segments[0]->url, in_fmt, &seg_format_opts);
> - av_dict_free(&seg_format_opts);
> + ret = avformat_open_input(&pls->ctx, pls->segments[0]->url, in_fmt, &options);
> + av_dict_free(&options);
> if (ret < 0)
> return ret;
> 
> @@ -2039,7 +2117,12 @@ static int hls_read_header(AVFormatContext *s)
> * on us if they want to.
> */
> if (pls->is_id3_timestamped || (pls->n_renditions > 0 && pls->renditions[0]->type ==
> AVMEDIA_TYPE_AUDIO)) {
> + if (seg && seg->key_type == KEY_SAMPLE_AES && pls->audio_setup_info.setup_data_length > 0 &&
> + pls->ctx->nb_streams == 1)
> + ret = ff_hls_senc_parse_audio_setup_info(pls->ctx->streams[0], &pls->audio_setup_info);
> + else
> ret = avformat_find_stream_info(pls->ctx, NULL);
> +
> if (ret < 0)
> return ret;
> }
> @@ -2166,6 +2249,7 @@ static int hls_read_packet(AVFormatContext *s, AVPacket *pkt)
> while (1) {
> int64_t ts_diff;
> AVRational tb;
> + struct segment *seg = NULL;
> ret = av_read_frame(pls->ctx, pls->pkt);
> if (ret < 0) {
> if (!avio_feof(&pls->pb) && ret != AVERROR_EOF)
> @@ -2184,6 +2268,14 @@ static int hls_read_packet(AVFormatContext *s, AVPacket *pkt)
> get_timebase(pls), AV_TIME_BASE_Q);
> }
> 
> + seg = current_segment(pls);
> + if (seg && seg->key_type == KEY_SAMPLE_AES && !strstr(pls->ctx->iformat->name, "mov")) {
> + enum AVCodecID codec_id = pls->ctx->streams[pls->pkt->stream_index]->codecpar->codec_id;
> + memcpy(c->crypto_ctx.iv, seg->iv, sizeof(seg->iv));
> + memcpy(c->crypto_ctx.key, pls->key, sizeof(pls->key));
> + ff_hls_senc_decrypt_frame(codec_id, &c->crypto_ctx, pls->pkt);
> + }
> +
> if (pls->seek_timestamp == AV_NOPTS_VALUE)
> break;
> 
> diff --git a/libavformat/hls_sample_encryption.c b/libavformat/hls_sample_encryption.c
> new file mode 100644
> index 0000000000..6538c2dceb
> --- /dev/null
> +++ b/libavformat/hls_sample_encryption.c
> @@ -0,0 +1,389 @@
> +/*
> + * Apple HTTP Live Streaming Sample Encryption/Decryption
> + *
> + * Copyright (c) 2021 Nachiket Tarate
> + *
> + * This file is part of FFmpeg.
> + *
> + * FFmpeg is free software; you can redistribute it and/or
> + * modify it under the terms of the GNU Lesser General Public
> + * License as published by the Free Software Foundation; either
> + * version 2.1 of the License, or (at your option) any later version.
> + *
> + * FFmpeg is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
> + * Lesser General Public License for more details.
> + *
> + * You should have received a copy of the GNU Lesser General Public
> + * License along with FFmpeg; if not, write to the Free Software
> + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
> + */
> +
> +/**
> + * @file
> + * Apple HTTP Live Streaming Sample Encryption
> + *
> https://developer.apple.com/library/ios/documentation/AudioVideo/Conceptual/HLS_Sample_Encryption
> + */
> +
> +#include "hls_sample_encryption.h"
> +
> +#include "libavcodec/adts_header.h"
> +#include "libavcodec/adts_parser.h"
> +#include "libavcodec/ac3_parser_internal.h"
> +
> +
> +typedef struct NALUnit {
> + uint8_t *data;
> + int type;
> + int length;
> + int start_code_length;
> +} NALUnit;
> +
> +typedef struct AudioFrame {
> + uint8_t *data;
> + int length;
> + int header_length;
> +} AudioFrame;
> +
> +typedef struct CodecParserContext {
> + const uint8_t *buf_ptr;
> + const uint8_t *buf_end;
> +} CodecParserContext;
> +
> +static const int eac3_sample_rate_tab[] = { 48000, 44100, 32000, 0 };
> +
> +void ff_hls_senc_read_audio_setup_info(HLSAudioSetupInfo *info, const uint8_t *buf, size_t size)
> +{
> + if (size < 8)
> + return;
> +
> + info->codec_tag = AV_RL32(buf);
> +
> + if (info->codec_tag == MKTAG('z','a','a','c'))
> + info->codec_id = AV_CODEC_ID_AAC;
> + else if (info->codec_tag == MKTAG('z','a','c','3'))
> + info->codec_id = AV_CODEC_ID_AC3;
> + else if (info->codec_tag == MKTAG('z','e','c','3'))
> + info->codec_id = AV_CODEC_ID_EAC3;
> + else
> + info->codec_id = AV_CODEC_ID_NONE;
> +
> + buf += 4;
> + info->priming = AV_RL16(buf);
> + buf += 2;
> + info->version = *buf++;
> + info->setup_data_length = *buf++;
> +
> + if (info->setup_data_length > size - 8)
> + info->setup_data_length = size - 8;
> +
> + if (info->setup_data_length > HLS_MAX_AUDIO_SETUP_DATA_LEN)
> + return;
> +
> + memcpy(info->setup_data, buf, info->setup_data_length);
> +}
> +
> +int ff_hls_senc_parse_audio_setup_info(AVStream *st, HLSAudioSetupInfo *info)
> +{
> + int ret = 0;
> +
> + st->codecpar->codec_tag = info->codec_tag;
> +
> + if (st->codecpar->codec_id == AV_CODEC_ID_AAC)
> + return 0;
> +
> + if (st->codecpar->codec_id != AV_CODEC_ID_AC3 && st->codecpar->codec_id != AV_CODEC_ID_EAC3)
> + return AVERROR_INVALIDDATA;
> +
> + if (st->codecpar->codec_id == AV_CODEC_ID_AC3) {
> + AC3HeaderInfo *ac3hdr = NULL;
> +
> + ret = avpriv_ac3_parse_header(&ac3hdr, info->setup_data, info->setup_data_length);
> + if (ret < 0) {
> + if (ret != AVERROR(ENOMEM))
> + av_free(ac3hdr);
> + return ret;
> + }
> +
> + st->codecpar->sample_rate = ac3hdr->sample_rate;
> + st->codecpar->channels = ac3hdr->channels;
> + st->codecpar->channel_layout = ac3hdr->channel_layout;
> + st->codecpar->bit_rate = ac3hdr->bit_rate;
> +
> + av_free(ac3hdr);
> + } else { /* Parse 'dec3' EC3SpecificBox */
> + GetBitContext gb;
> + int data_rate, fscod, acmod, lfeon;
> +
> + ret = init_get_bits8(&gb, info->setup_data, info->setup_data_length);
> + if (ret < 0)
> + return AVERROR_INVALIDDATA;
> +
> + data_rate = get_bits(&gb, 13);
> + skip_bits(&gb, 3);
> + fscod = get_bits(&gb, 2);
> + skip_bits(&gb, 10);
> + acmod = get_bits(&gb, 3);
> + lfeon = get_bits(&gb, 1);
> +
> + st->codecpar->sample_rate = eac3_sample_rate_tab[fscod];
> +
> + st->codecpar->channel_layout = avpriv_ac3_channel_layout_tab[acmod];
> + if (lfeon)
> + st->codecpar->channel_layout |= AV_CH_LOW_FREQUENCY;
> +
> + st->codecpar->channels = av_get_channel_layout_nb_channels(st->codecpar->channel_layout);
> +
> + st->codecpar->bit_rate = data_rate*1000;
> + }
> +
> + return 0;
> +}
> +
> +/*
> + * Remove start code emulation prevention 0x03 bytes
> + */
> +static void remove_scep_3_bytes(NALUnit *nalu)
> +{
> + int i = 0;
> + int j = 0;
> +
> + uint8_t *data = nalu->data;
> +
> + while (i < nalu->length) {
> + if (nalu->length - i > 3 && AV_RB24(&data[i]) == 0x000003) {
> + data[j++] = data[i++];
> + data[j++] = data[i++];
> + i++;
> + } else {
> + data[j++] = data[i++];
> + }
> + }
> +
> + nalu->length = j;
> +}
> +
> +static int get_next_nal_unit(CodecParserContext *ctx, NALUnit *nalu)
> +{
> + const uint8_t *nalu_start = ctx->buf_ptr;
> +
> + if (ctx->buf_end - ctx->buf_ptr >= 4 && AV_RB32(ctx->buf_ptr) == 0x00000001)
> + nalu->start_code_length = 4;
> + else if (ctx->buf_end - ctx->buf_ptr >= 3 && AV_RB24(ctx->buf_ptr) == 0x000001)
> + nalu->start_code_length = 3;
> + else /* No start code at the beginning of the NAL unit */
> + return -1;
> +
> + ctx->buf_ptr += nalu->start_code_length;
> +
> + while (ctx->buf_ptr < ctx->buf_end) {
> + if (ctx->buf_end - ctx->buf_ptr >= 4 && AV_RB32(ctx->buf_ptr) == 0x00000001)
> + break;
> + else if (ctx->buf_end - ctx->buf_ptr >= 3 && AV_RB24(ctx->buf_ptr) == 0x000001)
> + break;
> + ctx->buf_ptr++;
> + }
> +
> + nalu->data = (uint8_t *)nalu_start + nalu->start_code_length;
> + nalu->length = ctx->buf_ptr - nalu->data;
> + nalu->type = *nalu->data & 0x1F;
> +
> + return 0;
> +}
> +
> +static int decrypt_nal_unit(HLSCryptoContext *crypto_ctx, NALUnit *nalu)
> +{
> + int ret = 0;
> + int rem_bytes;
> + uint8_t *data;
> + uint8_t iv[16];
> +
> + ret = av_aes_init(crypto_ctx->aes_ctx, crypto_ctx->key, 16 * 8, 1);
> + if (ret < 0)
> + return ret;
> +
> + /* Remove start code emulation prevention 0x03 bytes */
> + remove_scep_3_bytes(nalu);
> +
> + data = nalu->data + 32;
> + rem_bytes = nalu->length - 32;
> +
> + memcpy(iv, crypto_ctx->iv, 16);
> +
> + while (rem_bytes > 0) {
> + if (rem_bytes > 16) {
> + av_aes_crypt(crypto_ctx->aes_ctx, data, data, 1, iv, 1);
> + data += 16;
> + rem_bytes -= 16;
> + }
> + data += FFMIN(144, rem_bytes);
> + rem_bytes -= FFMIN(144, rem_bytes);
> + }
> +
> + return 0;
> +}
> +
> +static int decrypt_video_frame(HLSCryptoContext *crypto_ctx, AVPacket *pkt)
> +{
> + int ret = 0;
> + CodecParserContext ctx;
> + NALUnit nalu;
> + uint8_t *data_ptr;
> + int move_nalu = 0;
> +
> + memset(&ctx, 0, sizeof(ctx));
> + ctx.buf_ptr = pkt->data;
> + ctx.buf_end = pkt->data + pkt->size;
> +
> + data_ptr = pkt->data;
> +
> + while (ctx.buf_ptr < ctx.buf_end) {
> + memset(&nalu, 0, sizeof(nalu));
> + ret = get_next_nal_unit(&ctx, &nalu);
> + if (ret < 0)
> + return ret;
This should be on same line as if statement for readability and clearity of intent. Or use brackets.
> + if ((nalu.type == 0x01 || nalu.type == 0x05) && nalu.length > 48) {
> + int encrypted_nalu_length = nalu.length;
> + ret = decrypt_nal_unit(crypto_ctx, &nalu);
> + if (ret < 0)
> + return ret;

Same as above.
> + move_nalu = nalu.length != encrypted_nalu_length;
> + }
> + if (move_nalu)
> + memmove(data_ptr, nalu.data - nalu.start_code_length, nalu.start_code_length + nalu.length);
Same thing.
> + data_ptr += nalu.start_code_length + nalu.length;
> + }
> +
> + av_shrink_packet(pkt, data_ptr - pkt->data);
> +
> + return 0;
> +}
> +
> +static int get_next_adts_frame(CodecParserContext *ctx, AudioFrame *frame)
> +{
> + int ret = 0;
> +
> + AACADTSHeaderInfo *adts_hdr = NULL;
> +
> + /* Find next sync word 0xFFF */
> + while (ctx->buf_ptr < ctx->buf_end - 1) {
> + if (*ctx->buf_ptr == 0xFF && *(ctx->buf_ptr + 1) & 0xF0 == 0xF0)
> + break;
> + ctx->buf_ptr++;
> + }
> +
> + if (ctx->buf_ptr >= ctx->buf_end - 1)
> + return -1;
> +
Why stop before minus 1 when you can read the second to last and last byte? Or maybe im reading this wrong.
> + frame->data = (uint8_t*)ctx->buf_ptr;
> +
> + ret = avpriv_adts_header_parse (&adts_hdr, frame->data, ctx->buf_end - frame->data);
> + if (ret < 0)
> + return ret;
> +
> + frame->header_length = adts_hdr->crc_absent ? AV_AAC_ADTS_HEADER_SIZE : AV_AAC_ADTS_HEADER_SIZE +
> 2;
> + frame->length = adts_hdr->frame_length;
> +
> + av_free(adts_hdr);
> +
> + return 0;
> +}
> +
> +static int get_next_ac3_eac3_sync_frame(CodecParserContext *ctx, AudioFrame *frame)
> +{
> + int ret = 0;
> +
> + AC3HeaderInfo *hdr = NULL;
> +
> + /* Find next sync word 0x0B77 */
> + while (ctx->buf_ptr < ctx->buf_end - 1) {
> + if (*ctx->buf_ptr == 0x0B && *(ctx->buf_ptr + 1) == 0x77)
> + break;
> + ctx->buf_ptr++;
> + }
> +
> + if (ctx->buf_ptr >= ctx->buf_end - 1)
> + return -1;
> +
Same critque as above
> + frame->data = (uint8_t*)ctx->buf_ptr;
> + frame->header_length = 0;
> +
> + ret = avpriv_ac3_parse_header(&hdr, frame->data, ctx->buf_end - frame->data);
> + if (ret < 0) {
> + if (ret != AVERROR(ENOMEM))
> + av_free(hdr);
> + return ret;
> + }
> +
> + frame->length = hdr->frame_size;
> +
> + av_free(hdr);
> +
> + return 0;
> +}
> +
> +static int get_next_sync_frame(enum AVCodecID codec_id, CodecParserContext *ctx, AudioFrame
> *frame)
> +{
> + if (codec_id == AV_CODEC_ID_AAC)
> + return get_next_adts_frame(ctx, frame);
> + else if (codec_id == AV_CODEC_ID_AC3 || codec_id == AV_CODEC_ID_EAC3)
> + return get_next_ac3_eac3_sync_frame(ctx, frame);
> + else
> + return AVERROR_INVALIDDATA;
> +}
> +
> +static int decrypt_sync_frame(enum AVCodecID codec_id, HLSCryptoContext *crypto_ctx, AudioFrame
> *frame)
> +{
> + int ret = 0;
> + uint8_t *data;
> + int num_of_encrypted_blocks;
> +
> + ret = av_aes_init(crypto_ctx->aes_ctx, crypto_ctx->key, 16 * 8, 1);
> + if (ret < 0)
> + return ret;
> +
> + data = frame->data + frame->header_length + 16;
> +
> + num_of_encrypted_blocks = (frame->length - frame->header_length - 16)/16;
> +
> + av_aes_crypt(crypto_ctx->aes_ctx, data, data, num_of_encrypted_blocks, crypto_ctx->iv, 1);
> +
> + return 0;
> +}
> +
> +static int decrypt_audio_frame(enum AVCodecID codec_id, HLSCryptoContext *crypto_ctx, AVPacket
> *pkt)
> +{
> + int ret = 0;
> + CodecParserContext ctx;
> + AudioFrame frame;
> +
> + memset(&ctx, 0, sizeof(ctx));
> + ctx.buf_ptr = pkt->data;
> + ctx.buf_end = pkt->data + pkt->size;
> +
> + while (ctx.buf_ptr < ctx.buf_end) {
> + memset(&frame, 0, sizeof(frame));
> + ret = get_next_sync_frame(codec_id, &ctx, &frame);
> + if (ret < 0)
> + return ret;
> + if (frame.length - frame.header_length > 31) {
> + ret = decrypt_sync_frame(codec_id, crypto_ctx, &frame);
> + if (ret < 0)
> + return ret;
> + }
> + ctx.buf_ptr += frame.length;
> + }
> +
> + return 0;
> +}
> +
> +int ff_hls_senc_decrypt_frame(enum AVCodecID codec_id, HLSCryptoContext *crypto_ctx, AVPacket
> *pkt)
> +{
> + if (codec_id == AV_CODEC_ID_H264)
> + return decrypt_video_frame(crypto_ctx, pkt);
> + else if (codec_id == AV_CODEC_ID_AAC || codec_id == AV_CODEC_ID_AC3 || codec_id ==
> AV_CODEC_ID_EAC3)
> + return decrypt_audio_frame(codec_id, crypto_ctx, pkt);
> +
> + return AVERROR_INVALIDDATA;
> +}
> diff --git a/libavformat/hls_sample_encryption.h b/libavformat/hls_sample_encryption.h
> new file mode 100644
> index 0000000000..ff3f9c22f7
> --- /dev/null
> +++ b/libavformat/hls_sample_encryption.h
> @@ -0,0 +1,65 @@
> +/*
> + * Apple HTTP Live Streaming Sample Encryption/Decryption
> + *
> + * Copyright (c) 2021 Nachiket Tarate
> + *
> + * This file is part of FFmpeg.
> + *
> + * FFmpeg is free software; you can redistribute it and/or
> + * modify it under the terms of the GNU Lesser General Public
> + * License as published by the Free Software Foundation; either
> + * version 2.1 of the License, or (at your option) any later version.
> + *
> + * FFmpeg is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
> + * Lesser General Public License for more details.
> + *
> + * You should have received a copy of the GNU Lesser General Public
> + * License along with FFmpeg; if not, write to the Free Software
> + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
> + */
> +
> +/**
> + * @file
> + * Apple HTTP Live Streaming Sample Encryption
> + *
> https://developer.apple.com/library/ios/documentation/AudioVideo/Conceptual/HLS_Sample_Encryption
> + */
> +
> +#ifndef AVFORMAT_HLS_SAMPLE_ENCRYPTION_H
> +#define AVFORMAT_HLS_SAMPLE_ENCRYPTION_H
> +
> +#include <stdint.h>
> +
> +#include "avformat.h"
> +#include "libavcodec/avcodec.h"
> +
> +#include "libavutil/aes.h"
> +
> +#define HLS_MAX_ID3_TAGS_DATA_LEN 138
> +#define HLS_MAX_AUDIO_SETUP_DATA_LEN 10
> +
> +typedef struct HLSCryptoContext {
> + struct AVAES *aes_ctx;
> + uint8_t key[16];
> + uint8_t iv[16];
> +} HLSCryptoContext;
> +
> +typedef struct HLSAudioSetupInfo {
> + enum AVCodecID codec_id;
> + uint32_t codec_tag;
> + uint16_t priming;
> + uint8_t version;
> + uint8_t setup_data_length;
> + uint8_t setup_data[HLS_MAX_AUDIO_SETUP_DATA_LEN];
> +} HLSAudioSetupInfo;
> +
> +
> +void ff_hls_senc_read_audio_setup_info(HLSAudioSetupInfo *info, const uint8_t *buf, size_t size);
> +
> +int ff_hls_senc_parse_audio_setup_info(AVStream *st, HLSAudioSetupInfo *info);
> +
> +int ff_hls_senc_decrypt_frame(enum AVCodecID codec_id, HLSCryptoContext *crypto_ctx, AVPacket
> *pkt);
> +
> +#endif /* AVFORMAT_HLS_SAMPLE_ENCRYPTION_H */
> +
> diff --git a/libavformat/mpegts.c b/libavformat/mpegts.c
> index a02965bacf..25518e3172 100644
> --- a/libavformat/mpegts.c
> +++ b/libavformat/mpegts.c
> @@ -839,6 +839,15 @@ static const StreamType MISC_types[] = {
> { 0 },
> };
> 
> +/* HLS Sample Encryption Types */
> +static const StreamType HLS_SAMPLE_ENC_types[] = {
> + { 0xdb, AVMEDIA_TYPE_VIDEO, AV_CODEC_ID_H264},
> + { 0xcf, AVMEDIA_TYPE_AUDIO, AV_CODEC_ID_AAC },
> + { 0xc1, AVMEDIA_TYPE_AUDIO, AV_CODEC_ID_AC3 },
> + { 0xc2, AVMEDIA_TYPE_AUDIO, AV_CODEC_ID_EAC3},
> + { 0 },
> +};
> +
> static const StreamType REGD_types[] = {
> { MKTAG('d', 'r', 'a', 'c'), AVMEDIA_TYPE_VIDEO, AV_CODEC_ID_DIRAC },
> { MKTAG('A', 'C', '-', '3'), AVMEDIA_TYPE_AUDIO, AV_CODEC_ID_AC3 },
> @@ -948,6 +957,8 @@ static int mpegts_set_stream_info(AVStream *st, PESContext *pes,
> }
> if (st->codecpar->codec_id == AV_CODEC_ID_NONE)
> mpegts_find_stream_type(st, pes->stream_type, MISC_types);
> + if (st->codecpar->codec_id == AV_CODEC_ID_NONE)
> + mpegts_find_stream_type(st, pes->stream_type, HLS_SAMPLE_ENC_types);
> if (st->codecpar->codec_id == AV_CODEC_ID_NONE) {
> st->codecpar->codec_id = old_codec_id;
> st->codecpar->codec_type = old_codec_type;
> -- 
> 2.17.1
> 
> _______________________________________________
> ffmpeg-devel mailing list
> ffmpeg-devel at ffmpeg.org
> https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
> 
> To unsubscribe, visit link above, or email
> ffmpeg-devel-request at ffmpeg.org with subject "unsubscribe".