FFmpeg学习 avcodec软解码函数分析

前言

本文分析ffmpeg软解码流程，相关函数如下，以find_stream_info中的try_decode_frame为例； 相关函数都在libavcodec包下。

基本调用流程如下：

const AVCodec *codec = find_probe_decoder(s, st, st->codecpar->codec_id);
/*
 * Force thread count to 1 since the H.264 decoder will not extract
 * SPS and PPS to extradata during multi-threaded decoding. 
 * 
 * 这块的设置后续会单独写文章梳理，和FFmpeg使用的解码模式有关，Frame threading或Slice threading，很值得研究一番
 */
av_dict_set(options ? options : &thread_opt, "threads", "1", 0);  
avcodec_open2(avctx, codec, options ? options : &thread_opt);

AVPacket pkt = *avpkt; // av_read_frame得到的packet
avcodec_send_packet(avctx, &pkt);
AVFrame *frame = av_frame_alloc();
avcodec_receive_frame(avctx, frame); // 解码获取一帧

软解码结构体介绍

在avformat_find_stream_info#find_probe_decoder方法中找到解码器，具体可以看avformat_find_stream_info函数分析文章，相应codec_id的解码是通过avcodec_register_all注册进来的。

视频

libavcodec包下h264dec.c#ff_h264_decoder

在find_stream_info#read_frame_internal中读取第一个视频包(sps/pps)和第一个音频包(sequenceheader)时会赋值codec_id；打印avcodec_get_name(codecContext->codec_id)可以获取到27，codec_name为h264，找到当前使用的解码器为libavcodec包下h264dec.c。目前一般都使用的h264编码，所以本篇文章也以h264格式来介绍ffmpeg的解码流程；

// h264dec.c
AVCodec ff_h264_decoder = {
    .name                  = "h264",
    .long_name             = NULL_IF_CONFIG_SMALL("H.264 / AVC / MPEG-4 AVC / MPEG-4 part 10"),
    .type                  = AVMEDIA_TYPE_VIDEO,
    .id                    = AV_CODEC_ID_H264,
    .priv_data_size        = sizeof(H264Context),
    .init                  = h264_decode_init,
    .close                 = h264_decode_end,
    .decode                = h264_decode_frame,
    .capabilities          = /*AV_CODEC_CAP_DRAW_HORIZ_BAND |*/ AV_CODEC_CAP_DR1 |
                             AV_CODEC_CAP_DELAY | AV_CODEC_CAP_SLICE_THREADS |
                             AV_CODEC_CAP_FRAME_THREADS,
    .hw_configs            = (const AVCodecHWConfigInternal*[]) {
                               NULL
                           },
    .caps_internal         = FF_CODEC_CAP_INIT_THREADSAFE | FF_CODEC_CAP_EXPORTS_CROPPING |
                             FF_CODEC_CAP_ALLOCATE_PROGRESS | FF_CODEC_CAP_INIT_CLEANUP,
    .flush                 = h264_decode_flush,
    .update_thread_context = ONLY_IF_THREADS_ENABLED(ff_h264_update_thread_context),
    .profiles              = NULL_IF_CONFIG_SMALL(ff_h264_profiles),
    .priv_class            = &h264_class,
};

音频

libavcodec包下aacdec.c#ff_aac_decoder

AVCodec ff_aac_decoder = {
    .name            = "aac",
    .long_name       = NULL_IF_CONFIG_SMALL("AAC (Advanced Audio Coding)"),
    .type            = AVMEDIA_TYPE_AUDIO,
    .id              = AV_CODEC_ID_AAC,
    .priv_data_size  = sizeof(AACContext),
    .init            = aac_decode_init,
    .close           = aac_decode_close,
    .decode          = aac_decode_frame,
    .sample_fmts     = (const enum AVSampleFormat[]) {
        AV_SAMPLE_FMT_FLTP, AV_SAMPLE_FMT_NONE
    },
    .capabilities    = AV_CODEC_CAP_CHANNEL_CONF | AV_CODEC_CAP_DR1,
    .caps_internal   = FF_CODEC_CAP_INIT_THREADSAFE,
    .channel_layouts = aac_channel_layout,
    .flush = flush,
    .priv_class      = &aac_decoder_class,
    .profiles        = NULL_IF_CONFIG_SMALL(ff_aac_profiles),
};

 avcodec_open2

// utils.c
int attribute_align_arg avcodec_open2(AVCodecContext *avctx, const AVCodec *codec, AVDictionary **options) {
    
    // 赋值等一大堆操作
    // ...

    if (HAVE_THREADS
        && !(avctx->internal->frame_thread_encoder && (avctx->active_thread_type&FF_THREAD_FRAME))) {
        ret = ff_thread_init(avctx); // 这块进行初始化Frame threading或Slice threading，之后再写文章梳理
        if (ret < 0) {
            goto free_and_end;
        }
    }

    // 初始化codec
    if (avctx->codec->init && (!(avctx->active_thread_type&FF_THREAD_FRAME)
        || avci->frame_thread_encoder)) {
        ret = avctx->codec->init(avctx);
        if (ret < 0) {
            goto free_and_end;
        }
        codec_init_ok = 1;
    }
    
     // ...
}

avctx->codec->init

走到h264dec.c中的h264_decode_init，此处初始化解码器并调用ff_h264_decode_extradata对sps和pps进行解码，封装出H264ParamSets供后续调用，实际却是在decode第一个真正的视频包时赋值width、profile、level等重要参数，这块需要再研究。

static av_cold int h264_decode_init(AVCodecContext *avctx)
{
    av_log(avctx, AV_LOG_DEBUG, "h264_decode_init");
    H264Context *h = avctx->priv_data;
    int ret;

    ret = h264_init_context(avctx, h);
    if (ret < 0)
        return ret;

    ret = ff_thread_once(&h264_vlc_init, ff_h264_decode_init_vlc);
    if (ret != 0) {
        av_log(avctx, AV_LOG_ERROR, "pthread_once has failed.");
        return AVERROR_UNKNOWN;
    }

    if (avctx->ticks_per_frame == 1) {
        if(h->avctx->time_base.den < INT_MAX/2) {
            h->avctx->time_base.den *= 2;
        } else
            h->avctx->time_base.num /= 2;
    }
    avctx->ticks_per_frame = 2;

    if (avctx->extradata_size > 0 && avctx->extradata) {
        ret = ff_h264_decode_extradata(avctx->extradata, avctx->extradata_size,
                                       &h->ps, &h->is_avc, &h->nal_length_size,
                                       avctx->err_recognition, avctx);
                                       
        av_log(avctx, AV_LOG_DEBUG, "ff_h264_decode_extradata: %d", ret);
        if (ret < 0) {
            h264_decode_end(avctx);
            return ret;
        }
    }

    if (h->ps.sps && h->ps.sps->bitstream_restriction_flag &&
        h->avctx->has_b_frames < h->ps.sps->num_reorder_frames) {
        h->avctx->has_b_frames = h->ps.sps->num_reorder_frames;
    }

    avctx->internal->allocate_progress = 1;

    ff_h264_flush_change(h);

    if (h->enable_er < 0 && (avctx->active_thread_type & FF_THREAD_SLICE))
        h->enable_er = 0;

    if (h->enable_er && (avctx->active_thread_type & FF_THREAD_SLICE)) {
        av_log(avctx, AV_LOG_WARNING,
               "Error resilience with slice threads is enabled. It is unsafe and unsupported and may crash. "
               "Use it at your own risk\n");
    }

    return 0;
}

CSDN站内私信我，领取最新最全C++音视频学习提升资料，内容包括（C/C++，Linux 服务器开发，FFmpeg ，webRTC ，rtmp ，hls ，rtsp ，ffplay ，srs）

 

avcodec_send_packet

向解码器送入一帧，若此时没有帧可用，就触发解码流程；

// decode.c
int attribute_align_arg avcodec_send_packet(AVCodecContext *avctx, const AVPacket *avpkt)
{
    AVCodecInternal *avci = avctx->internal;
    int ret;

    if (!avcodec_is_open(avctx) || !av_codec_is_decoder(avctx->codec))
        return AVERROR(EINVAL);

    if (avctx->internal->draining)
        return AVERROR_EOF;

    if (avpkt && !avpkt->size && avpkt->data)
        return AVERROR(EINVAL);

    ret = bsfs_init(avctx);
    if (ret < 0)
        return ret;
        
    av_packet_unref(avci->buffer_pkt);
    if (avpkt && (avpkt->data || avpkt->side_data_elems)) {
        ret = av_packet_ref(avci->buffer_pkt, avpkt);
        if (ret < 0)
            return ret;
    }
	
    ret = av_bsf_send_packet(avci->bsf, avci->buffer_pkt);
    if (ret < 0) {
        av_packet_unref(avci->buffer_pkt);
        return ret;
    }
  
    // 如果没有解码出来一帧，提前触发解码，往buffer里存；
    if (!avci->buffer_frame->buf[0]) {
        ret = decode_receive_frame_internal(avctx, avci->buffer_frame);
        if (ret < 0 && ret != AVERROR(EAGAIN) && ret != AVERROR_EOF)
            return ret;
    }

    return 0;
}

// utils.c
int avcodec_is_open(AVCodecContext *s) {
    return !!s->internal;
}

// utils.c
int av_codec_is_decoder(const AVCodec *codec) {
    return codec && (codec->decode || codec->receive_frame);
}

avcodec_receive_frame

如果有解码好的帧直接使用；如果没有则触发解码流程；

扫描二维码关注公众号，回复： 14198987 查看本文章

// decode.c
int attribute_align_arg avcodec_receive_frame(AVCodecContext *avctx, AVFrame *frame)
{
    AVCodecInternal *avci = avctx->internal;
    int ret, changed;

    av_frame_unref(frame);

    if (!avcodec_is_open(avctx) || !av_codec_is_decoder(avctx->codec))
        return AVERROR(EINVAL);

    if (avci->buffer_frame->buf[0]) {
        // 有已经解码好的帧，直接取出
        av_frame_move_ref(frame, avci->buffer_frame);
    } else {
        // 没有则进行解码
        ret = decode_receive_frame_internal(avctx, frame);
        if (ret < 0)
            return ret;
    }

    if (avctx->codec_type == AVMEDIA_TYPE_VIDEO) {
        ret = apply_cropping(avctx, frame);
        if (ret < 0) {
            av_frame_unref(frame);
            return ret;
        }
    }

    avctx->frame_number++;
    
    // ...

    return 0;
}

decode_receive_frame_internal

static int decode_receive_frame_internal(AVCodecContext *avctx, AVFrame *frame)
{
    AVCodecInternal *avci = avctx->internal;
    int ret;

    if (avctx->codec->receive_frame) {
        ret = avctx->codec->receive_frame(avctx, frame);
        if (ret != AVERROR(EAGAIN))
            av_packet_unref(avci->last_pkt_props);
    } else {
        // h264走这
        ret = decode_simple_receive_frame(avctx, frame);
    }

    if (ret == AVERROR_EOF)
        avci->draining_done = 1;

    if (!ret) {
        /* the only case where decode data is not set should be decoders
         * that do not call ff_get_buffer() */

        if (frame->private_ref) {
            FrameDecodeData *fdd = (FrameDecodeData*)frame->private_ref->data;

            if (fdd->post_process) {
                ret = fdd->post_process(avctx, frame);
                if (ret < 0) {
                    av_frame_unref(frame);
                    return ret;
                }
            }
        }
    }

    /* free the per-frame decode data */
    av_buffer_unref(&frame->private_ref);

    return ret;
}

decode_simple_receive_frame 

static int decode_simple_receive_frame(AVCodecContext *avctx, AVFrame *frame)
{
    int ret;

    while (!frame->buf[0]) {
       // 填充 frame->buf[0]
        ret = decode_simple_internal(avctx, frame);
        if (ret < 0)
            return ret;
    }

    return 0;
}

decode_simple_internal

获取pkt，然后使用h264dec.c去解码获取frame；

static inline int decode_simple_internal(AVCodecContext *avctx, AVFrame *frame)
{
    AVCodecInternal   *avci = avctx->internal;
    DecodeSimpleContext *ds = &avci->ds;
    AVPacket           *pkt = ds->in_pkt;
    // copy to ensure we do not change pkt
    int got_frame, actual_got_frame;
    int ret;
    
    // pkt data为空
    if (!pkt->data && !avci->draining) {
        av_packet_unref(pkt);
        // 去获取pkt
        ret = ff_decode_get_packet(avctx, pkt);
        if (ret < 0 && ret != AVERROR_EOF)
            return ret;
    }

    // Some codecs (at least wma lossless) will crash when feeding drain packets after EOF was signaled.
    if (avci->draining_done)
        return AVERROR_EOF;

    if (!pkt->data &&
        !(avctx->codec->capabilities & AV_CODEC_CAP_DELAY ||
          avctx->active_thread_type & FF_THREAD_FRAME))
        return AVERROR_EOF;

    got_frame = 0;

    
    // h264解码
    ret = avctx->codec->decode(avctx, frame, &got_frame, pkt);

    if (!(avctx->codec->caps_internal & FF_CODEC_CAP_SETS_PKT_DTS))
        frame->pkt_dts = pkt->dts;
    if (avctx->codec->type == AVMEDIA_TYPE_VIDEO) {
        if(!avctx->has_b_frames)
            frame->pkt_pos = pkt->pos;
    }
    
    actual_got_frame = got_frame;

    if (avctx->codec->type == AVMEDIA_TYPE_VIDEO) {
        if (frame->flags & AV_FRAME_FLAG_DISCARD)
            got_frame = 0;
        if (got_frame)
            frame->best_effort_timestamp = guess_correct_pts(avctx,
                                                             frame->pts,
                                                             frame->pkt_dts);
    } else if (avctx->codec->type == AVMEDIA_TYPE_AUDIO) {
        // ...
    }

    if (!got_frame)
        av_frame_unref(frame);

    if (ret >= 0 && avctx->codec->type == AVMEDIA_TYPE_VIDEO && !(avctx->flags & AV_CODEC_FLAG_TRUNCATED))
        ret = pkt->size;

    if (avci->draining && !actual_got_frame) {
        if (ret < 0) {
            int nb_errors_max = 20 + (HAVE_THREADS && avctx->active_thread_type & FF_THREAD_FRAME ?  avctx->thread_count : 1);

            if (avci->nb_draining_errors++ >= nb_errors_max) {
                avci->draining_done = 1;
                ret = AVERROR_BUG;
            }
        } else {
            avci->draining_done = 1;
        }
    }

    avci->compat_decode_consumed += ret;

    if (ret >= pkt->size || ret < 0) {
        av_packet_unref(pkt);
        av_packet_unref(avci->last_pkt_props);
    } else {
        int consumed = ret;
        pkt->data                += consumed;
        pkt->size                -= consumed;
        avci->last_pkt_props->size -= consumed; // See extract_packet_props() comment.
        pkt->pts                  = AV_NOPTS_VALUE;
        pkt->dts                  = AV_NOPTS_VALUE;
        avci->last_pkt_props->pts = AV_NOPTS_VALUE;
        avci->last_pkt_props->dts = AV_NOPTS_VALUE;
    }

    return ret < 0 ? ret : 0;
}

h264_decode_frame 

// h264dec.c
static int h264_decode_frame(AVCodecContext *avctx, void *data,
                             int *got_frame, AVPacket *avpkt)
{
    const uint8_t *buf = avpkt->data;
    int buf_size       = avpkt->size;
    H264Context *h     = avctx->priv_data;
    AVFrame *pict      = data;
    int buf_index;
    int ret;

    h->flags = avctx->flags;
    h->setup_finished = 0;
    h->nb_slice_ctx_queued = 0;

    ff_h264_unref_picture(h, &h->last_pic_for_ec);

    /* end of stream, output what is still in the buffers */
    if (buf_size == 0)
        return send_next_delayed_frame(h, pict, got_frame, 0);

    if (av_packet_get_side_data(avpkt, AV_PKT_DATA_NEW_EXTRADATA, NULL)) {
        int side_size;
        uint8_t *side = av_packet_get_side_data(avpkt, AV_PKT_DATA_NEW_EXTRADATA, &side_size);
        ff_h264_decode_extradata(side, side_size,
                                 &h->ps, &h->is_avc, &h->nal_length_size,
                                 avctx->err_recognition, avctx);
    }
    if (h->is_avc && buf_size >= 9 && buf[0]==1 && buf[2]==0 && (buf[4]&0xFC)==0xFC) {
        if (is_avcc_extradata(buf, buf_size))
            return ff_h264_decode_extradata(buf, buf_size,
                                            &h->ps, &h->is_avc, &h->nal_length_size,
                                            avctx->err_recognition, avctx);
    }

    buf_index = decode_nal_units(h, buf, buf_size);
    if (buf_index < 0)
        return AVERROR_INVALIDDATA;

    if (!h->cur_pic_ptr && h->nal_unit_type == H264_NAL_END_SEQUENCE) {
        av_assert0(buf_index <= buf_size);
        return send_next_delayed_frame(h, pict, got_frame, buf_index);
    }

    if (!(avctx->flags2 & AV_CODEC_FLAG2_CHUNKS) && (!h->cur_pic_ptr || !h->has_slice)) {
        if (avctx->skip_frame >= AVDISCARD_NONREF ||
            buf_size >= 4 && !memcmp("Q264", buf, 4))
            return buf_size;
        av_log(avctx, AV_LOG_ERROR, "no frame!\n");
        return AVERROR_INVALIDDATA;
    }

    if (!(avctx->flags2 & AV_CODEC_FLAG2_CHUNKS) ||
        (h->mb_y >= h->mb_height && h->mb_height)) {
        if ((ret = ff_h264_field_end(h, &h->slice_ctx[0], 0)) < 0)
            return ret;

        /* Wait for second field. */
        if (h->next_output_pic) {
            ret = finalize_frame(h, pict, h->next_output_pic, got_frame);
            if (ret < 0)
                return ret;
        }
    }

    av_assert0(pict->buf[0] || !*got_frame);

    ff_h264_unref_picture(h, &h->last_pic_for_ec);

    return get_consumed_bytes(buf_index, buf_size);
}

额外的：
h264_decode_frame
–> h264dec.c#decode_nal_units
–> h264_slice.c#ff_h264_queue_decode_slice
–> h264_slice.c#h264_field_start
–> h264_slice.c#h264_init_ps，这里赋值解码参数，find_stream_info的视频参数是在这里赋值的。