avcodec_decode_video2() 的作用是解码一帧视频数据，输入一个压缩编码的结构体 AVPacket，输出一个解码后的结构体 AVFrame

avcodec_decode_video2

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
int attribute_align_arg avcodec_decode_video2(AVCodecContext *avctx, AVFrame *picture,
                                              int *got_picture_ptr,
                                              const AVPacket *avpkt)
{
    return compat_decode(avctx, picture, got_picture_ptr, avpkt);
}

static int compat_decode(AVCodecContext *avctx, AVFrame *frame,
                         int *got_frame, const AVPacket *pkt)
{
    AVCodecInternal *avci = avctx->internal;
    int ret = 0;

    av_assert0(avci->compat_decode_consumed == 0);

    *got_frame = 0;
    avci->compat_decode = 1;

    if (avci->compat_decode_partial_size > 0 &&
        avci->compat_decode_partial_size != pkt->size) {
        av_log(avctx, AV_LOG_ERROR,
               "Got unexpected packet size after a partial decode\n");
        ret = AVERROR(EINVAL);
        goto finish;
    }

    if (!avci->compat_decode_partial_size) {
        ret = avcodec_send_packet(avctx, pkt);
        if (ret == AVERROR_EOF)
            ret = 0;
        else if (ret == AVERROR(EAGAIN)) {
            /* we fully drain all the output in each decode call, so this should not
             * ever happen */
            ret = AVERROR_BUG;
            goto finish;
        } else if (ret < 0)
            goto finish;
    }

    while (ret >= 0) {
        ret = avcodec_receive_frame(avctx, frame);
        if (ret < 0) {
            if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
                ret = 0;
            goto finish;
        }

        if (frame != avci->compat_decode_frame) {
            if (!avctx->refcounted_frames) {
                ret = unrefcount_frame(avci, frame);
                if (ret < 0)
                    goto finish;
            }

            *got_frame = 1;
            frame = avci->compat_decode_frame;
        } else {
            if (!avci->compat_decode_warned) {
                av_log(avctx, AV_LOG_WARNING, "The deprecated avcodec_decode_* "
                       "API cannot return all the frames for this decoder. "
                       "Some frames will be dropped. Update your code to the "
                       "new decoding API to fix this.\n");
                avci->compat_decode_warned = 1;
            }
        }

        if (avci->draining || (!avctx->codec->bsfs && avci->compat_decode_consumed < pkt->size))
            break;
    }

finish:
    if (ret == 0) {
        /* if there are any bsfs then assume full packet is always consumed */
        if (avctx->codec->bsfs)
            ret = pkt->size;
        else
            ret = FFMIN(avci->compat_decode_consumed, pkt->size);
    }
    avci->compat_decode_consumed = 0;
    avci->compat_decode_partial_size = (ret >= 0) ? pkt->size - ret : 0;

    return ret;
}

avcodec_decode_video2() 实际上调用的是 compat_decode()，而在其中调用了 avcodec_send_packet() 来实现了真正的解码，通过 avcodec_receive_frame() 来获得解码之后的 AVFrame

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
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->filter.bsfs[0], avci->buffer_pkt);
    if (ret < 0) {
        av_packet_unref(avci->buffer_pkt);
        return ret;
    }

    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;
}

在 avcodec_send_packet() 中调用了 decode_receive_frame_internal()

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
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;

    return ret;
}

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
    AVPacket tmp;
    int got_frame, actual_got_frame, did_split;
    int ret;

    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;

    tmp = *pkt;
#if FF_API_MERGE_SD
FF_DISABLE_DEPRECATION_WARNINGS
    did_split = avci->compat_decode_partial_size ?
                ff_packet_split_and_drop_side_data(&tmp) :
                av_packet_split_side_data(&tmp);

    if (did_split) {
        ret = extract_packet_props(avctx->internal, &tmp);
        if (ret < 0)
            return ret;

        ret = apply_param_change(avctx, &tmp);
        if (ret < 0)
            return ret;
    }
FF_ENABLE_DEPRECATION_WARNINGS
#endif

    got_frame = 0;

    if (HAVE_THREADS && avctx->active_thread_type & FF_THREAD_FRAME) {
        ret = ff_thread_decode_frame(avctx, frame, &got_frame, &tmp);
    } else {
        ret = avctx->codec->decode(avctx, frame, &got_frame, &tmp);

        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\n",
                   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\n",
                       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.\n");
                }
                av_log(avctx, AV_LOG_DEBUG, "skip %d/%d samples\n",
                       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.\n");
                }
                av_log(avctx, AV_LOG_DEBUG, "discard %d/%d samples\n",
                       (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 FF_API_MERGE_SD
    if (did_split) {
        av_packet_free_side_data(&tmp);
        if(ret == tmp.size)
            ret = pkt->size;
    }
#endif

    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.\n");
        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.\n");
                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;
}

一系列调用下来最重要的是 ret = avctx->codec->decode(avctx, frame, &got_frame, &tmp)，实际上调用了 AVCodec 的 decode() 方法来完成解码，这也是一个指针函数

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
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,
    .caps_internal         = FF_CODEC_CAP_INIT_THREADSAFE | FF_CODEC_CAP_EXPORTS_CROPPING,
    .flush                 = flush_dpb,
    .init_thread_copy      = ONLY_IF_THREADS_ENABLED(decode_init_thread_copy),
    .update_thread_context = ONLY_IF_THREADS_ENABLED(ff_h264_update_thread_context),
    .profiles              = NULL_IF_CONFIG_SMALL(ff_h264_profiles),
    .priv_class            = &h264_class,
};

从 ff_h264_decoder 可以看出 decode() 是指向了 h264_decode_frame() 方法

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
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 (h->is_avc && 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);
        if (is_extra(side, 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 && (buf[5]&0x1F) && buf[8]==0x67){
        if (is_extra(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);
}

调用了 decode_nal_units() 方法来完成解码

参考