FFmpeg源码分析：avcodec_send_packet 和 avcodec_receive_frame

我们以一个acc解码为例看看这两个函数

static void decode(AVCodecContext *dec_ctx, AVPacket *pkt, AVFrame *frame,
                   FILE *outfile)
{
    int i, ch;
    int ret, data_size;

    // pkt是由av_parser_parse2拿到，一帧数据ADTS Frame    ret = avcodec_send_packet(dec_ctx, pkt);
    ret = avcodec_send_packet(dec_ctx, pkt);
    if (ret < 0) {
        fprintf(stderr, "Error submitting the packet to the decoder
");
        exit(1);
    }

    /* read all the output frames (in general there may be any number of them */
    while (ret >= 0) {
        ret = avcodec_receive_frame(dec_ctx, frame);
        if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
            return;
        else if (ret < 0) {
            fprintf(stderr, "Error during decoding
");
            exit(1);
        }
        // 采样位数 4位 
        data_size = av_get_bytes_per_sample(dec_ctx->sample_fmt);
        if (data_size < 0) {
            /* This should not occur, checking just for paranoia */
            fprintf(stderr, "Failed to calculate data size
");
            exit(1);
        }
        // ffmpeg内部存储格式：AV_SAMPLE_FMT_FLTP planar格式 实际文件都是Packed模式
        // 样本数量循环
        for (i = 0; i < frame->nb_samples; i++)
            // 通道数遍历
            for (ch = 0; ch < dec_ctx->channels; ch++)
                fwrite(frame->data[ch] + data_size*i, 1, data_size, outfile);
    }
}

这里分为几步：

1. 拿到原始数据，一般是av_parser_parse2解析得到，这里一般是ADTS格式一帧Frame。
2. 发送数据给解码器，返回使用的大小
3. 从解码器获取pcm数据
4. 按照packet模式写入文件

这里看一下输入的数据：

 可以看到就是原始的aac文件第一帧

 我们看看解析

 avcodec_send_packet 函数

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

    // 检查AVCodecContext是否打开
    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);

    // 数据拷贝到buffer_pkt
    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;
    }

    // 将avci->buffer_pkt移动到avci->filter.bsfs[0]
    ret = av_bsf_send_packet(avci->filter.bsfs[0], avci->buffer_pkt);
    if (ret < 0) {
        av_packet_unref(avci->buffer_pkt);
        return ret;
    }

    // 解码
    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;
}

avcodec_receive_frame函数

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]) {
        // 缓存有数据之间移动到frame，一般有数据都走这里
        av_frame_move_ref(frame, avci->buffer_frame);
    } else {
        // 解码接受数据
        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++;

    if (avctx->flags & AV_CODEC_FLAG_DROPCHANGED) {

        if (avctx->frame_number == 1) {
            avci->initial_format = frame->format;
            switch(avctx->codec_type) {
            case AVMEDIA_TYPE_VIDEO:
                avci->initial_width  = frame->width;
                avci->initial_height = frame->height;
                break;
            case AVMEDIA_TYPE_AUDIO:
                avci->initial_sample_rate = frame->sample_rate ? frame->sample_rate :
                                                                 avctx->sample_rate;
                avci->initial_channels       = frame->channels;
                avci->initial_channel_layout = frame->channel_layout;
                break;
            }
        }

        if (avctx->frame_number > 1) {
            changed = avci->initial_format != frame->format;

           switch(avctx->codec_type) {
            case AVMEDIA_TYPE_VIDEO:
                changed |= avci->initial_width  != frame->width ||
                           avci->initial_height != frame->height;
                break;
            case AVMEDIA_TYPE_AUDIO:
                changed |= avci->initial_sample_rate    != frame->sample_rate ||
                           avci->initial_sample_rate    != avctx->sample_rate ||
                           avci->initial_channels       != frame->channels ||
                           avci->initial_channel_layout != frame->channel_layout;
                break;
            }

            if (changed) {
                avci->changed_frames_dropped++;
                av_log(avctx, AV_LOG_INFO, "dropped changed frame #%d pts %"PRId64
                                            " drop count: %d 
",
                                            avctx->frame_number, frame->pts,
                                            avci->changed_frames_dropped);
                av_frame_unref(frame);
                return AVERROR_INPUT_CHANGED;
            }
        }
    }
    return 0;
}

两个都调用了decode_receive_frame_internal，我们看看实现

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

    av_assert0(!frame->buf[0]);

    if (avctx->codec->receive_frame)
        ret = avctx->codec->receive_frame(avctx, frame);
    else
        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() */
        av_assert0((frame->private_ref && frame->private_ref->size == sizeof(FrameDecodeData)) ||
                   !(avctx->codec->capabilities & AV_CODEC_CAP_DR1));

        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;
}

这里如果解码器有receive_frame就调用，没有就走decode_simple_receive_frame，这里走decode_simple_receive_frame

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

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

    return 0;
}

/*
 * The core of the receive_frame_wrapper for the decoders implementing
 * the simple API. Certain decoders might consume partial packets without
 * returning any output, so this function needs to be called in a loop until it
 * returns EAGAIN.
 **/
static 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;

    // 拿到源数据保存到pkt
    if (!pkt->data && !avci->draining) {
        av_packet_unref(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;

    // 调用解码器解码
    if (HAVE_THREADS && avctx->active_thread_type & FF_THREAD_FRAME) {
        ret = ff_thread_decode_frame(avctx, frame, &got_frame, pkt);
    } else {
        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;
            //FIXME these should be under if(!avctx->has_b_frames)
            /* get_buffer is supposed to set frame parameters */
            if (!(avctx->codec->capabilities & AV_CODEC_CAP_DR1)) {
                if (!frame->sample_aspect_ratio.num)  frame->sample_aspect_ratio = avctx->sample_aspect_ratio;
                if (!frame->width)                    frame->width               = avctx->width;
                if (!frame->height)                   frame->height              = avctx->height;
                if (frame->format == AV_PIX_FMT_NONE) frame->format              = avctx->pix_fmt;
            }
        }
    }
    emms_c();
    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) {
        uint8_t *side;
        int side_size;
        uint32_t discard_padding = 0;
        uint8_t skip_reason = 0;
        uint8_t discard_reason = 0;

        if (ret >= 0 && got_frame) {
            frame->best_effort_timestamp = guess_correct_pts(avctx,
                                                             frame->pts,
                                                             frame->pkt_dts);
            if (frame->format == AV_SAMPLE_FMT_NONE)
                frame->format = avctx->sample_fmt;
            if (!frame->channel_layout)
                frame->channel_layout = avctx->channel_layout;
            if (!frame->channels)
                frame->channels = avctx->channels;
            if (!frame->sample_rate)
                frame->sample_rate = avctx->sample_rate;
        }

        side= av_packet_get_side_data(avci->last_pkt_props, AV_PKT_DATA_SKIP_SAMPLES, &side_size);
        if(side && side_size>=10) {
            avctx->internal->skip_samples = AV_RL32(side) * avctx->internal->skip_samples_multiplier;
            discard_padding = AV_RL32(side + 4);
            av_log(avctx, AV_LOG_DEBUG, "skip %d / discard %d samples due to side data
",
                   avctx->internal->skip_samples, (int)discard_padding);
            skip_reason = AV_RL8(side + 8);
            discard_reason = AV_RL8(side + 9);
        }

        if ((frame->flags & AV_FRAME_FLAG_DISCARD) && got_frame &&
            !(avctx->flags2 & AV_CODEC_FLAG2_SKIP_MANUAL)) {
            avctx->internal->skip_samples = FFMAX(0, avctx->internal->skip_samples - frame->nb_samples);
            got_frame = 0;
        }

        if (avctx->internal->skip_samples > 0 && got_frame &&
            !(avctx->flags2 & AV_CODEC_FLAG2_SKIP_MANUAL)) {
            if(frame->nb_samples <= avctx->internal->skip_samples){
                got_frame = 0;
                avctx->internal->skip_samples -= frame->nb_samples;
                av_log(avctx, AV_LOG_DEBUG, "skip whole frame, skip left: %d
",
                       avctx->internal->skip_samples);
            } else {
                av_samples_copy(frame->extended_data, frame->extended_data, 0, avctx->internal->skip_samples,
                                frame->nb_samples - avctx->internal->skip_samples, avctx->channels, frame->format);
                if(avctx->pkt_timebase.num && avctx->sample_rate) {
                    int64_t diff_ts = av_rescale_q(avctx->internal->skip_samples,
                                                   (AVRational){1, avctx->sample_rate},
                                                   avctx->pkt_timebase);
                    if(frame->pts!=AV_NOPTS_VALUE)
                        frame->pts += diff_ts;
#if FF_API_PKT_PTS
FF_DISABLE_DEPRECATION_WARNINGS
                    if(frame->pkt_pts!=AV_NOPTS_VALUE)
                        frame->pkt_pts += diff_ts;
FF_ENABLE_DEPRECATION_WARNINGS
#endif
                    if(frame->pkt_dts!=AV_NOPTS_VALUE)
                        frame->pkt_dts += diff_ts;
                    if (frame->pkt_duration >= diff_ts)
                        frame->pkt_duration -= diff_ts;
                } else {
                    av_log(avctx, AV_LOG_WARNING, "Could not update timestamps for skipped samples.
");
                }
                av_log(avctx, AV_LOG_DEBUG, "skip %d/%d samples
",
                       avctx->internal->skip_samples, frame->nb_samples);
                frame->nb_samples -= avctx->internal->skip_samples;
                avctx->internal->skip_samples = 0;
            }
        }

        if (discard_padding > 0 && discard_padding <= frame->nb_samples && got_frame &&
            !(avctx->flags2 & AV_CODEC_FLAG2_SKIP_MANUAL)) {
            if (discard_padding == frame->nb_samples) {
                got_frame = 0;
            } else {
                if(avctx->pkt_timebase.num && avctx->sample_rate) {
                    int64_t diff_ts = av_rescale_q(frame->nb_samples - discard_padding,
                                                   (AVRational){1, avctx->sample_rate},
                                                   avctx->pkt_timebase);
                    frame->pkt_duration = diff_ts;
                } else {
                    av_log(avctx, AV_LOG_WARNING, "Could not update timestamps for discarded samples.
");
                }
                av_log(avctx, AV_LOG_DEBUG, "discard %d/%d samples
",
                       (int)discard_padding, frame->nb_samples);
                frame->nb_samples -= discard_padding;
            }
        }

        if ((avctx->flags2 & AV_CODEC_FLAG2_SKIP_MANUAL) && got_frame) {
            AVFrameSideData *fside = av_frame_new_side_data(frame, AV_FRAME_DATA_SKIP_SAMPLES, 10);
            if (fside) {
                AV_WL32(fside->data, avctx->internal->skip_samples);
                AV_WL32(fside->data + 4, discard_padding);
                AV_WL8(fside->data + 8, skip_reason);
                AV_WL8(fside->data + 9, discard_reason);
                avctx->internal->skip_samples = 0;
            }
        }
    }

    if (avctx->codec->type == AVMEDIA_TYPE_AUDIO &&
        !avci->showed_multi_packet_warning &&
        ret >= 0 && ret != pkt->size && !(avctx->codec->capabilities & AV_CODEC_CAP_SUBFRAMES)) {
        av_log(avctx, AV_LOG_WARNING, "Multiple frames in a packet.
");
        avci->showed_multi_packet_warning = 1;
    }

    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 FF_API_AVCTX_TIMEBASE
    if (avctx->framerate.num > 0 && avctx->framerate.den > 0)
        avctx->time_base = av_inv_q(av_mul_q(avctx->framerate, (AVRational){avctx->ticks_per_frame, 1}));
#endif

    /* do not stop draining when actual_got_frame != 0 or ret < 0 */
    /* got_frame == 0 but actual_got_frame != 0 when frame is discarded */
    if (avctx->internal->draining && !actual_got_frame) {
        if (ret < 0) {
            /* prevent infinite loop if a decoder wrongly always return error on draining */
            /* reasonable nb_errors_max = maximum b frames + thread count */
            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) {
                av_log(avctx, AV_LOG_ERROR, "Too many errors when draining, this is a bug. "
                       "Stop draining and force EOF.
");
                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);
    } 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;
    }

    if (got_frame)
        av_assert0(frame->buf[0]);

    return ret < 0 ? ret : 0;
}

到这里发现最终走了aa解码器的aac_decode_frame