aboutsummaryrefslogtreecommitdiffstats
path: root/libavcodec/vda_h264_dec.c
blob: d2ef5dc9a6257f5a724c161e34a1faffb7fb9931 (plain) (blame)
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
/*
 * Copyright (c) 2012, Xidorn Quan
 *
 * 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
 * H.264 decoder via VDA
 * @author Xidorn Quan <quanxunzhen@gmail.com>
 */

#include <string.h>
#include <CoreFoundation/CoreFoundation.h>

#include "vda.h"
#include "h264.h"
#include "avcodec.h"

#ifndef kCFCoreFoundationVersionNumber10_7
#define kCFCoreFoundationVersionNumber10_7      635.00
#endif

extern AVCodec ff_h264_decoder, ff_h264_vda_decoder;

static const enum AVPixelFormat vda_pixfmts_prior_10_7[] = {
    AV_PIX_FMT_UYVY422,
    AV_PIX_FMT_YUV420P,
    AV_PIX_FMT_NONE
};

static const enum AVPixelFormat vda_pixfmts[] = {
    AV_PIX_FMT_UYVY422,
    AV_PIX_FMT_YUYV422,
    AV_PIX_FMT_NV12,
    AV_PIX_FMT_YUV420P,
    AV_PIX_FMT_NONE
};

typedef struct {
    H264Context h264ctx;
    int h264_initialized;
    struct vda_context vda_ctx;
    enum AVPixelFormat pix_fmt;

    /* for backing-up fields set by user.
     * we have to gain full control of such fields here */
    void *hwaccel_context;
    enum AVPixelFormat (*get_format)(struct AVCodecContext *s, const enum AVPixelFormat * fmt);
    int (*get_buffer2)(struct AVCodecContext *s, AVFrame *frame, int flags);
#if FF_API_GET_BUFFER
    int (*get_buffer)(struct AVCodecContext *c, AVFrame *pic);
#endif
} VDADecoderContext;

static enum AVPixelFormat get_format(struct AVCodecContext *avctx,
        const enum AVPixelFormat *fmt)
{
    return AV_PIX_FMT_VDA_VLD;
}

typedef struct {
    CVPixelBufferRef cv_buffer;
} VDABufferContext;

static void release_buffer(void *opaque, uint8_t *data)
{
    VDABufferContext *context = opaque;
    CVPixelBufferUnlockBaseAddress(context->cv_buffer, 0);
    CVPixelBufferRelease(context->cv_buffer);
    av_free(context);
}

static int get_buffer2(AVCodecContext *avctx, AVFrame *pic, int flag)
{
    VDABufferContext *context = av_mallocz(sizeof(VDABufferContext));
    AVBufferRef *buffer = av_buffer_create(NULL, 0, release_buffer, context, 0);
    if (!context || !buffer) {
        av_free(context);
        return AVERROR(ENOMEM);
    }

    pic->buf[0] = buffer;
    pic->data[0] = (void *)1;
    return 0;
}

static inline void set_context(AVCodecContext *avctx)
{
    VDADecoderContext *ctx = avctx->priv_data;
    ctx->hwaccel_context = avctx->hwaccel_context;
    avctx->hwaccel_context = &ctx->vda_ctx;
    ctx->get_format = avctx->get_format;
    avctx->get_format = get_format;
    ctx->get_buffer2 = avctx->get_buffer2;
    avctx->get_buffer2 = get_buffer2;
#if FF_API_GET_BUFFER
    ctx->get_buffer = avctx->get_buffer;
    avctx->get_buffer = NULL;
#endif
}

static inline void restore_context(AVCodecContext *avctx)
{
    VDADecoderContext *ctx = avctx->priv_data;
    avctx->hwaccel_context = ctx->hwaccel_context;
    avctx->get_format = ctx->get_format;
    avctx->get_buffer2 = ctx->get_buffer2;
#if FF_API_GET_BUFFER
    avctx->get_buffer = ctx->get_buffer;
#endif
}

static int vdadec_decode(AVCodecContext *avctx,
        void *data, int *got_frame, AVPacket *avpkt)
{
    VDADecoderContext *ctx = avctx->priv_data;
    AVFrame *pic = data;
    int ret;

    set_context(avctx);
    ret = ff_h264_decoder.decode(avctx, data, got_frame, avpkt);
    restore_context(avctx);
    if (*got_frame) {
        AVBufferRef *buffer = pic->buf[0];
        VDABufferContext *context = av_buffer_get_opaque(buffer);
        CVPixelBufferRef cv_buffer = (CVPixelBufferRef)pic->data[3];

        CVPixelBufferRetain(cv_buffer);
        CVPixelBufferLockBaseAddress(cv_buffer, 0);
        context->cv_buffer = cv_buffer;
        pic->format = ctx->pix_fmt;
        if (CVPixelBufferIsPlanar(cv_buffer)) {
            int i, count = CVPixelBufferGetPlaneCount(cv_buffer);
            av_assert0(count < 4);
            for (i = 0; i < count; i++) {
                pic->data[i] = CVPixelBufferGetBaseAddressOfPlane(cv_buffer, i);
                pic->linesize[i] = CVPixelBufferGetBytesPerRowOfPlane(cv_buffer, i);
            }
        } else {
            pic->data[0] = CVPixelBufferGetBaseAddress(cv_buffer);
            pic->linesize[0] = CVPixelBufferGetBytesPerRow(cv_buffer);
        }
    }
    avctx->pix_fmt = ctx->pix_fmt;

    return ret;
}

static av_cold int vdadec_close(AVCodecContext *avctx)
{
    VDADecoderContext *ctx = avctx->priv_data;
    /* release buffers and decoder */
    ff_vda_destroy_decoder(&ctx->vda_ctx);
    /* close H.264 decoder */
    if (ctx->h264_initialized) {
        set_context(avctx);
        ff_h264_decoder.close(avctx);
        restore_context(avctx);
    }
    return 0;
}

static av_cold int vdadec_init(AVCodecContext *avctx)
{
    VDADecoderContext *ctx = avctx->priv_data;
    struct vda_context *vda_ctx = &ctx->vda_ctx;
    OSStatus status;
    int ret;

    ctx->h264_initialized = 0;

    /* init pix_fmts of codec */
    if (!ff_h264_vda_decoder.pix_fmts) {
        if (kCFCoreFoundationVersionNumber < kCFCoreFoundationVersionNumber10_7)
            ff_h264_vda_decoder.pix_fmts = vda_pixfmts_prior_10_7;
        else
            ff_h264_vda_decoder.pix_fmts = vda_pixfmts;
    }

    /* init vda */
    memset(vda_ctx, 0, sizeof(struct vda_context));
    vda_ctx->width = avctx->width;
    vda_ctx->height = avctx->height;
    vda_ctx->format = 'avc1';
    vda_ctx->use_sync_decoding = 1;
    vda_ctx->use_ref_buffer = 1;
    ctx->pix_fmt = avctx->get_format(avctx, avctx->codec->pix_fmts);
    switch (ctx->pix_fmt) {
    case AV_PIX_FMT_UYVY422:
        vda_ctx->cv_pix_fmt_type = '2vuy';
        break;
    case AV_PIX_FMT_YUYV422:
        vda_ctx->cv_pix_fmt_type = 'yuvs';
        break;
    case AV_PIX_FMT_NV12:
        vda_ctx->cv_pix_fmt_type = '420v';
        break;
    case AV_PIX_FMT_YUV420P:
        vda_ctx->cv_pix_fmt_type = 'y420';
        break;
    default:
        av_log(avctx, AV_LOG_ERROR, "Unsupported pixel format: %d\n", avctx->pix_fmt);
        goto failed;
    }
    status = ff_vda_create_decoder(vda_ctx,
                                   avctx->extradata, avctx->extradata_size);
    if (status != kVDADecoderNoErr) {
        av_log(avctx, AV_LOG_ERROR,
                "Failed to init VDA decoder: %d.\n", status);
        goto failed;
    }

    /* init H.264 decoder */
    set_context(avctx);
    ret = ff_h264_decoder.init(avctx);
    restore_context(avctx);
    if (ret < 0) {
        av_log(avctx, AV_LOG_ERROR, "Failed to open H.264 decoder.\n");
        goto failed;
    }
    ctx->h264_initialized = 1;

    for (int i = 0; i < MAX_SPS_COUNT; i++) {
        SPS *sps = ctx->h264ctx.sps_buffers[i];
        if (sps && (sps->bit_depth_luma != 8 ||
                sps->chroma_format_idc == 2 ||
                sps->chroma_format_idc == 3)) {
            av_log(avctx, AV_LOG_ERROR, "Format is not supported.\n");
            goto failed;
        }
    }

    return 0;

failed:
    vdadec_close(avctx);
    return -1;
}

static void vdadec_flush(AVCodecContext *avctx)
{
    set_context(avctx);
    ff_h264_decoder.flush(avctx);
    restore_context(avctx);
}

AVCodec ff_h264_vda_decoder = {
    .name           = "h264_vda",
    .type           = AVMEDIA_TYPE_VIDEO,
    .id             = AV_CODEC_ID_H264,
    .priv_data_size = sizeof(VDADecoderContext),
    .init           = vdadec_init,
    .close          = vdadec_close,
    .decode         = vdadec_decode,
    .capabilities   = CODEC_CAP_DELAY,
    .flush          = vdadec_flush,
    .long_name      = NULL_IF_CONFIG_SMALL("H.264 (VDA acceleration)"),
};