参考：
雷霄骅博士，x264源代码简单分析：x264_slice_write()

流程分析：
【x264】x264编码主流程简单分析

1.编码帧函数（x264_encoder_encode）

x264_encoder_encode是x264编码器的核心函数，实现了编码一个视频帧的功能。它的工作流程为：

1. 拷贝一帧并移动到buffer中（x264_frame_pop_unused）
2. 拷贝一帧送入队列用于确定帧类型（x264_lookahead_put_frame）
3. 从lookahead获取帧（x264_lookahead_get_frames）
4. 获取要编码的帧（x264_frame_shift）
5. 根据帧的类型初始化数据依赖关系，如I帧，P帧，B帧
6. 构建双向的参考帧列表（reference_build_list）
7. 写入码流文件（x264_sps_write，x264_pps_write等）
8. 开始进行码率控制（x264_ratecontrol_start）
9. 创建帧的头信息（slice_init）
10. 帧编码（slices_write -> slice_write）
11. 处理额外信息且更新编码器状态（encoder_frame_end）

1.1 拷贝一帧并移动到buffer中（x264_frame_pop_unused）

该函数主要的功能是从h中拷贝一帧出来，移动到buffer中，并且初始化这个帧之中的信息。h是encoder的不可视化句柄，横贯上下文

x264_frame_t *x264_frame_pop_unused( x264_t *h, int b_fdec )
{x264_frame_t *frame;// 如果这一帧没有使用，则会取出一帧，否则new一帧if( h->frames.unused[b_fdec][0] )frame = x264_frame_pop( h->frames.unused[b_fdec] );elseframe = frame_new( h, b_fdec );if( !frame )return NULL;// 将帧中的信息初始化frame->b_last_minigop_bframe = 0;frame->i_reference_count = 1;frame->b_intra_calculated = 0;frame->b_scenecut = 1;frame->b_keyframe = 0;frame->b_corrupt = 0;frame->i_slice_count = h->param.b_sliced_threads ? h->param.i_threads : 1;memset( frame->weight, 0, sizeof(frame->weight) );memset( frame->f_weighted_cost_delta, 0, sizeof(frame->f_weighted_cost_delta) );return frame;
}

1.2 拷贝一帧送入队列用于确定帧类型（x264_lookahead_put_frame）

将前面取出的帧送入到lookahead队列中，并确认帧的类型。在x264编码器中，Lookahead队列中存储的帧信息是当前帧的前向参考帧，以及由其后继的参考帧组成的预测帧序列。这个预测帧序列在编码过程中用来评估当前帧的最优编码方式。通过预测帧序列，x264编码器可以提前看到未来的参考帧，从而更准确地决定当前帧的最优编码方式。

Lookahead队列的作用是提高视频编码的质量和效率。通过预测未来的参考帧，可以更准确地选择最优的编码方式，从而达到更好的视频质量。此外，Lookahead队列还可以利用多线程处理技术，在不影响编码速度的情况下提高编码效率。

void x264_lookahead_put_frame( x264_t *h, x264_frame_t *frame )
{if( h->param.i_sync_lookahead )x264_sync_frame_list_push( &h->lookahead->ifbuf, frame ); // 进行预测，将frame推入输入帧列表elsex264_sync_frame_list_push( &h->lookahead->next, frame ); // 不进行预测，将frame推入next列表（下一帧）
}

1.3 从lookahead中获取帧（x264_lookahead_get_frames）

该函数分析lookahead中的帧信息，如果存在lookahead线程，则在这里获取帧；如果不存在lookahead线程，这里会决定slice type信息

void x264_lookahead_get_frames( x264_t *h )
{if( h->param.i_sync_lookahead ){   /* We have a lookahead thread, so get frames from there */x264_pthread_mutex_lock( &h->lookahead->ofbuf.mutex );while( !h->lookahead->ofbuf.i_size && h->lookahead->b_thread_active )x264_pthread_cond_wait( &h->lookahead->ofbuf.cv_fill, &h->lookahead->ofbuf.mutex );lookahead_encoder_shift( h );x264_pthread_mutex_unlock( &h->lookahead->ofbuf.mutex );}else{   /* We are not running a lookahead thread, so perform all the slicetype decide on the fly */if( h->frames.current[0] || !h->lookahead->next.i_size )return;x264_slicetype_decide( h );lookahead_update_last_nonb( h, h->lookahead->next.list[0] );int shift_frames = h->lookahead->next.list[0]->i_bframes + 1;lookahead_shift( &h->lookahead->ofbuf, &h->lookahead->next, shift_frames );/* For MB-tree and VBV lookahead, we have to perform propagation analysis on I-frames too. */if( h->lookahead->b_analyse_keyframe && IS_X264_TYPE_I( h->lookahead->last_nonb->i_type ) )x264_slicetype_analyse( h, shift_frames );lookahead_encoder_shift( h );}
}

1.4 获取要编码的帧（x264_frame_shift）

从frame_list中获取一帧

x264_frame_t *x264_frame_shift( x264_frame_t **list )
{x264_frame_t *frame = list[0];int i;for( i = 0; list[i]; i++ )list[i] = list[i+1];assert(frame);return frame;
}

1.5 根据帧的类型初始化数据依赖关系

判断帧的类型是IDR、I、P或者是B帧，并根据其类型进行参数配置

if( h->fenc->i_type == X264_TYPE_IDR ){/* reset ref pictures */i_nal_type    = NAL_SLICE_IDR;i_nal_ref_idc = NAL_PRIORITY_HIGHEST;h->sh.i_type = SLICE_TYPE_I;reference_reset( h );h->frames.i_poc_last_open_gop = -1;}else if( h->fenc->i_type == X264_TYPE_I ){i_nal_type    = NAL_SLICE;i_nal_ref_idc = NAL_PRIORITY_HIGH; /* Not completely true but for now it is (as all I/P are kept as ref)*/h->sh.i_type = SLICE_TYPE_I;reference_hierarchy_reset( h );if( h->param.b_open_gop )h->frames.i_poc_last_open_gop = h->fenc->b_keyframe ? h->fenc->i_poc : -1;}else if( h->fenc->i_type == X264_TYPE_P ){i_nal_type    = NAL_SLICE;i_nal_ref_idc = NAL_PRIORITY_HIGH; /* Not completely true but for now it is (as all I/P are kept as ref)*/h->sh.i_type = SLICE_TYPE_P;reference_hierarchy_reset( h );h->frames.i_poc_last_open_gop = -1;}else if( h->fenc->i_type == X264_TYPE_BREF ){i_nal_type    = NAL_SLICE;i_nal_ref_idc = h->param.i_bframe_pyramid == X264_B_PYRAMID_STRICT ? NAL_PRIORITY_LOW : NAL_PRIORITY_HIGH;h->sh.i_type = SLICE_TYPE_B;reference_hierarchy_reset( h );}else    /* B frame */{i_nal_type    = NAL_SLICE;i_nal_ref_idc = NAL_PRIORITY_DISPOSABLE;h->sh.i_type = SLICE_TYPE_B;}

1.6 构建双向的参考帧列表（reference_build_list）

根据前面判断的帧的类型，可以确定参考帧的情况；对于IDR帧，没有参考帧；对于P帧，有前向参考帧；对于B帧，有双向参考帧。构建的参考帧列表有二维，第一个维度0记录的是前向参考帧的idx，第二个维度1记录的是后向参考帧的idx。

函数主要工作流程为：

1. 将参考帧存储到队列中
2. 根据与当前帧的距离进行排序
3. 检查我们是否选择了与标准默认值不同的引用列表顺序

static inline void reference_build_list( x264_t *h, int i_poc )
{int b_ok;/* build ref list 0/1 */h->mb.pic.i_fref[0] = h->i_ref[0] = 0;h->mb.pic.i_fref[1] = h->i_ref[1] = 0;if( h->sh.i_type == SLICE_TYPE_I )return;// ----- 1.将参考帧存储到队列中 ----- //for( int i = 0; h->frames.reference[i]; i++ ){if( h->frames.reference[i]->b_corrupt )continue;if( h->frames.reference[i]->i_poc < i_poc )h->fref[0][h->i_ref[0]++] = h->frames.reference[i]; // 存入前向参考队列else if( h->frames.reference[i]->i_poc > i_poc )h->fref[1][h->i_ref[1]++] = h->frames.reference[i]; // 存入后向参考队列}if( h->sh.i_mmco_remove_from_end ){/* Order ref0 for MMCO remove */do{b_ok = 1;for( int i = 0; i < h->i_ref[0] - 1; i++ ){if( h->fref[0][i]->i_frame < h->fref[0][i+1]->i_frame ){XCHG( x264_frame_t*, h->fref[0][i], h->fref[0][i+1] );b_ok = 0;break;}}} while( !b_ok );for( int i = h->i_ref[0]-1; i >= h->i_ref[0] - h->sh.i_mmco_remove_from_end; i-- ){int diff = h->i_frame_num - h->fref[0][i]->i_frame_num;h->sh.mmco[h->sh.i_mmco_command_count].i_poc = h->fref[0][i]->i_poc;h->sh.mmco[h->sh.i_mmco_command_count++].i_difference_of_pic_nums = diff;}}// ----- 2.根据与当前帧的距离排序参考列表 ----- ///* Order reference lists by distance from the current frame. */for( int list = 0; list < 2; list++ ){h->fref_nearest[list] = h->fref[list][0];do{b_ok = 1;for( int i = 0; i < h->i_ref[list] - 1; i++ ){if( list ? h->fref[list][i+1]->i_poc < h->fref_nearest[list]->i_poc: h->fref[list][i+1]->i_poc > h->fref_nearest[list]->i_poc )h->fref_nearest[list] = h->fref[list][i+1];if( reference_distance( h, h->fref[list][i] ) > reference_distance( h, h->fref[list][i+1] ) ){XCHG( x264_frame_t*, h->fref[list][i], h->fref[list][i+1] );b_ok = 0;break;}}} while( !b_ok );}// ----- 3.检查我们是否选择了与标准默认值不同的引用列表顺序 ----- //reference_check_reorder( h );h->i_ref[1] = X264_MIN( h->i_ref[1], h->frames.i_max_ref1 );h->i_ref[0] = X264_MIN( h->i_ref[0], h->frames.i_max_ref0 );h->i_ref[0] = X264_MIN( h->i_ref[0], h->param.i_frame_reference ); // if reconfig() has lowered the limit/* For Blu-ray compliance, don't reference frames outside of the minigop. */if( IS_X264_TYPE_B( h->fenc->i_type ) && h->param.b_bluray_compat )h->i_ref[0] = X264_MIN( h->i_ref[0], IS_X264_TYPE_B( h->fref[0][0]->i_type ) + 1 );/* add duplicates */if( h->fenc->i_type == X264_TYPE_P ){int idx = -1;if( h->param.analyse.i_weighted_pred >= X264_WEIGHTP_SIMPLE ){x264_weight_t w[3];w[1].weightfn = w[2].weightfn = NULL;if( h->param.rc.b_stat_read )x264_ratecontrol_set_weights( h, h->fenc ); // 码率控制设置参数if( !h->fenc->weight[0][0].weightfn ){h->fenc->weight[0][0].i_denom = 0;SET_WEIGHT( w[0], 1, 1, 0, -1 );idx = weighted_reference_duplicate( h, 0, w );}else{if( h->fenc->weight[0][0].i_scale == 1<<h->fenc->weight[0][0].i_denom ){SET_WEIGHT( h->fenc->weight[0][0], 1, 1, 0, h->fenc->weight[0][0].i_offset );}weighted_reference_duplicate( h, 0, x264_weight_none );if( h->fenc->weight[0][0].i_offset > -128 ){w[0] = h->fenc->weight[0][0];w[0].i_offset--;h->mc.weight_cache( h, &w[0] );idx = weighted_reference_duplicate( h, 0, w );}}}h->mb.ref_blind_dupe = idx;}assert( h->i_ref[0] + h->i_ref[1] <= X264_REF_MAX );h->mb.pic.i_fref[0] = h->i_ref[0];h->mb.pic.i_fref[1] = h->i_ref[1];
}

1.7 写入码流文件（x264_sps_write，x264_pps_write等）

如果帧的类型为I帧，则还需要写入SPS和PPS的信息。

if( h->fenc->b_keyframe ){/* Write SPS and PPS */if( h->param.b_repeat_headers ){/* generate sequence parameters */nal_start( h, NAL_SPS, NAL_PRIORITY_HIGHEST );x264_sps_write( &h->out.bs, h->sps ); // 写入SPS信息if( nal_end( h ) )return -1;/* Pad AUD/SPS to 256 bytes like Panasonic */if( h->param.i_avcintra_class )h->out.nal[h->out.i_nal-1].i_padding = 256 - bs_pos( &h->out.bs ) / 8 - 2*NALU_OVERHEAD;overhead += h->out.nal[h->out.i_nal-1].i_payload + h->out.nal[h->out.i_nal-1].i_padding + NALU_OVERHEAD;/* generate picture parameters */nal_start( h, NAL_PPS, NAL_PRIORITY_HIGHEST );x264_pps_write( &h->out.bs, h->sps, h->pps ); // 写入PPS信息if( nal_end( h ) )return -1;if( h->param.i_avcintra_class ){int total_len = 256;/* Sony XAVC uses an oversized PPS instead of SEI padding */if( h->param.i_avcintra_flavor == X264_AVCINTRA_FLAVOR_SONY )total_len += h->param.i_height >= 1080 ? 18*512 : 10*512;h->out.nal[h->out.i_nal-1].i_padding = total_len - h->out.nal[h->out.i_nal-1].i_payload - NALU_OVERHEAD;}overhead += h->out.nal[h->out.i_nal-1].i_payload + h->out.nal[h->out.i_nal-1].i_padding + NALU_OVERHEAD;}/* when frame threading is used, buffering period sei is written in encoder_frame_end */if( h->i_thread_frames == 1 && h->sps->vui.b_nal_hrd_parameters_present ){x264_hrd_fullness( h );nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE );x264_sei_buffering_period_write( h, &h->out.bs );if( nal_end( h ) )return -1;overhead += h->out.nal[h->out.i_nal-1].i_payload + SEI_OVERHEAD;}}

1.8 开始进行码率控制（x264_ratecontrol_start）

开始进行码率控制，为当前的帧选择一个QP。主要的工作流程为：

1. 检查vbv模式
2. 检查abr模式
3. 检查2pass模式
4. 检查CQP模式
5. 将qp进行clip操作，固定在特定范围内
6. 更新pqp

码率控制是编码器当中一个重要的技术思想，使用另外的章节记录

void x264_ratecontrol_start( x264_t *h, int i_force_qp, int overhead )
{x264_ratecontrol_t *rc = h->rc;ratecontrol_entry_t *rce = NULL;x264_zone_t *zone = get_zone( h, h->fenc->i_frame );float q;x264_emms();if( h->param.rc.b_stat_read ){int frame = h->fenc->i_frame;assert( frame >= 0 && frame < rc->num_entries );rce = rc->rce = &rc->entry[frame];if( h->sh.i_type == SLICE_TYPE_B&& h->param.analyse.i_direct_mv_pred == X264_DIRECT_PRED_AUTO ){h->sh.b_direct_spatial_mv_pred = ( rce->direct_mode == 's' );h->mb.b_direct_auto_read = ( rce->direct_mode == 's' || rce->direct_mode == 't' );}}// ----- 1.检查是否使用vbv模式 ----- //// 在VBV模式下，x264允许每个MB有不同的QP值，其他模式下，整帧的QP值是固定的if( rc->b_vbv ){memset( h->fdec->i_row_bits, 0, h->mb.i_mb_height * sizeof(int) );memset( h->fdec->f_row_qp, 0, h->mb.i_mb_height * sizeof(float) );memset( h->fdec->f_row_qscale, 0, h->mb.i_mb_height * sizeof(float) );rc->row_pred = rc->row_preds[h->sh.i_type];rc->buffer_rate = h->fenc->i_cpb_duration * rc->vbv_max_rate * h->sps->vui.i_num_units_in_tick / h->sps->vui.i_time_scale;update_vbv_plan( h, overhead );const x264_level_t *l = x264_levels;while( l->level_idc != 0 && l->level_idc != h->param.i_level_idc )l++;int mincr = l->mincr;if( h->param.b_bluray_compat )mincr = 4;/* Profiles above High don't require minCR, so just set the maximum to a large value. */if( h->sps->i_profile_idc > PROFILE_HIGH )rc->frame_size_maximum = 1e9;else{/* The spec has a bizarre special case for the first frame. */if( h->i_frame == 0 ){//384 * ( Max( PicSizeInMbs, fR * MaxMBPS ) + MaxMBPS * ( tr( 0 ) - tr,n( 0 ) ) ) / MinCRdouble fr = 1. / (h->param.i_level_idc >= 60 ? 300 : 172);int pic_size_in_mbs = h->mb.i_mb_width * h->mb.i_mb_height;rc->frame_size_maximum = 384 * BIT_DEPTH * X264_MAX( pic_size_in_mbs, fr*l->mbps ) / mincr;}else{//384 * MaxMBPS * ( tr( n ) - tr( n - 1 ) ) / MinCRrc->frame_size_maximum = 384 * BIT_DEPTH * ((double)h->fenc->i_cpb_duration * h->sps->vui.i_num_units_in_tick / h->sps->vui.i_time_scale) * l->mbps / mincr;}}}if( h->sh.i_type != SLICE_TYPE_B )rc->bframes = h->fenc->i_bframes;// ----- 2.检查是否是abr模式 ----- //if( rc->b_abr ){q = qscale2qp( rate_estimate_qscale( h ) );}else if( rc->b_2pass ) // ----- 3.检查是否是2pass模式 ----- //{rce->new_qscale = rate_estimate_qscale( h );q = qscale2qp( rce->new_qscale );}else /* CQP */ // ----- 4.CQP模式，QP为固定值 ----- //{if( h->sh.i_type == SLICE_TYPE_B && h->fdec->b_kept_as_ref )q = ( rc->qp_constant[ SLICE_TYPE_B ] + rc->qp_constant[ SLICE_TYPE_P ] ) / 2;elseq = rc->qp_constant[ h->sh.i_type ];if( zone ){if( zone->b_force_qp )q += zone->i_qp - rc->qp_constant[SLICE_TYPE_P];elseq -= 6*log2f( zone->f_bitrate_factor );}}if( i_force_qp != X264_QP_AUTO )q = i_force_qp - 1;// ---- 5.将qp进行clip操作，固定在特定范围内 ----- //q = x264_clip3f( q, h->param.rc.i_qp_min, h->param.rc.i_qp_max );rc->qpa_rc = rc->qpa_rc_prev =rc->qpa_aq = rc->qpa_aq_prev = 0;h->fdec->f_qp_avg_rc =h->fdec->f_qp_avg_aq =rc->qpm = q;if( rce )rce->new_qp = q;// ----- 6.更新pqp ----- //accum_p_qp_update( h, rc->qpm );if( h->sh.i_type != SLICE_TYPE_B )rc->last_non_b_pict_type = h->sh.i_type;
}

1.9 创建帧头信息（slice_init）

创建帧的头部信息，如果是IDR帧，slice的头信息还会包括i_idr_pic_id信息。slice的头信息当中，包括了SPS、PPS、frame_num、qp和delta_qp等等信息。函数主要的工作流程为：

1. 检查是否IDR帧
2. 初始化slice头部信息（根据是否是IDR帧有所区别）
3. 利用slice的信息初始化mb

static inline void slice_init( x264_t *h, int i_nal_type, int i_global_qp )
{/* ------------------------ Create slice header  ----------------------- */// ----- 1.检查是否是IDR帧 ----- //if( i_nal_type == NAL_SLICE_IDR ){	// ----- 2.初始化slice头部信息 ----- //slice_header_init( h, &h->sh, h->sps, h->pps, h->i_idr_pic_id, h->i_frame_num, i_global_qp );/* alternate id */if( h->param.i_avcintra_class ){switch( h->i_idr_pic_id ){case 5:h->i_idr_pic_id = 3;break;case 3:h->i_idr_pic_id = 4;break;case 4:default:h->i_idr_pic_id = 5;break;}}elseh->i_idr_pic_id ^= 1;}else{slice_header_init( h, &h->sh, h->sps, h->pps, -1, h->i_frame_num, i_global_qp );h->sh.i_num_ref_idx_l0_active = h->i_ref[0] <= 0 ? 1 : h->i_ref[0];h->sh.i_num_ref_idx_l1_active = h->i_ref[1] <= 0 ? 1 : h->i_ref[1];if( h->sh.i_num_ref_idx_l0_active != h->pps->i_num_ref_idx_l0_default_active ||(h->sh.i_type == SLICE_TYPE_B && h->sh.i_num_ref_idx_l1_active != h->pps->i_num_ref_idx_l1_default_active) ){h->sh.b_num_ref_idx_override = 1;}}if( h->fenc->i_type == X264_TYPE_BREF && h->param.b_bluray_compat && h->sh.i_mmco_command_count ){h->b_sh_backup = 1;h->sh_backup = h->sh;}h->fdec->i_frame_num = h->sh.i_frame_num;if( h->sps->i_poc_type == 0 ){h->sh.i_poc = h->fdec->i_poc;if( PARAM_INTERLACED ){h->sh.i_delta_poc_bottom = h->param.b_tff ? 1 : -1;h->sh.i_poc += h->sh.i_delta_poc_bottom == -1;}elseh->sh.i_delta_poc_bottom = 0;h->fdec->i_delta_poc[0] = h->sh.i_delta_poc_bottom == -1;h->fdec->i_delta_poc[1] = h->sh.i_delta_poc_bottom ==  1;}else{/* Nothing to do ? */}// ----- 3.将slice的信息拷贝给mb ----- //x264_macroblock_slice_init( h );
}

1.10 帧编码（slices_write -> slice_write）

帧编码函数是对一帧进行分析和编码的核心函数，在进行一些参数的配置之后，直接调用了slice_write进行编码。主要工作流程为：

1. 将analyser中的配置参数初始化给mb
2. 将QP设置为片中的第一个QP，以获得更准确的CABAC初始化
3. 初始化cabac
4. 循环编码slice当中的每个mb
5. 分析mb（预测）
6. 编码mb
7. 收集mb的信息进行更新
8. 是否进行deblock
9. 如果使用多线程，则告知主线程编码一个slice完成

static intptr_t slice_write( x264_t *h )
{int i_skip;int mb_xy, i_mb_x, i_mb_y;/* NALUs other than the first use a 3-byte startcode.* Add one extra byte for the rbsp, and one more for the final CABAC putbyte.* Then add an extra 5 bytes just in case, to account for random NAL escapes and* other inaccuracies. */int overhead_guess = (NALU_OVERHEAD - (h->param.b_annexb && h->out.i_nal)) + 1 + h->param.b_cabac + 5;int slice_max_size = h->param.i_slice_max_size > 0 ? (h->param.i_slice_max_size-overhead_guess)*8 : 0;int back_up_bitstream_cavlc = !h->param.b_cabac && h->sps->i_profile_idc < PROFILE_HIGH;int back_up_bitstream = slice_max_size || back_up_bitstream_cavlc;int starting_bits = bs_pos(&h->out.bs);int b_deblock = h->sh.i_disable_deblocking_filter_idc != 1;int b_hpel = h->fdec->b_kept_as_ref;int orig_last_mb = h->sh.i_last_mb;int thread_last_mb = h->i_threadslice_end * h->mb.i_mb_width - 1;uint8_t *last_emu_check;
#define BS_BAK_SLICE_MAX_SIZE 0
#define BS_BAK_CAVLC_OVERFLOW 1
#define BS_BAK_SLICE_MIN_MBS  2
#define BS_BAK_ROW_VBV        3x264_bs_bak_t bs_bak[4];b_deblock &= b_hpel || h->param.b_full_recon || h->param.psz_dump_yuv;bs_realign( &h->out.bs );/* Slice */nal_start( h, h->i_nal_type, h->i_nal_ref_idc );h->out.nal[h->out.i_nal].i_first_mb = h->sh.i_first_mb;// ----- 1.将analyser中的配置参数初始化给mb ----- ///* Slice header */x264_macroblock_thread_init( h );// ----- 2.将QP设置为片中的第一个QP，以获得更准确的CABAC初始化 ----- ///* Set the QP equal to the first QP in the slice for more accurate CABAC initialization. */h->mb.i_mb_xy = h->sh.i_first_mb;h->sh.i_qp = x264_ratecontrol_mb_qp( h );h->sh.i_qp = SPEC_QP( h->sh.i_qp );h->sh.i_qp_delta = h->sh.i_qp - h->pps->i_pic_init_qp;slice_header_write( &h->out.bs, &h->sh, h->i_nal_ref_idc );// ----- 3.初始化cabac ----- //if( h->param.b_cabac ){/* alignment needed */bs_align_1( &h->out.bs );/* init cabac */x264_cabac_context_init( h, &h->cabac, h->sh.i_type, x264_clip3( h->sh.i_qp-QP_BD_OFFSET, 0, 51 ), h->sh.i_cabac_init_idc );x264_cabac_encode_init ( &h->cabac, h->out.bs.p, h->out.bs.p_end );last_emu_check = h->cabac.p;}elselast_emu_check = h->out.bs.p;h->mb.i_last_qp = h->sh.i_qp;h->mb.i_last_dqp = 0;h->mb.field_decoding_flag = 0;i_mb_y = h->sh.i_first_mb / h->mb.i_mb_width;i_mb_x = h->sh.i_first_mb % h->mb.i_mb_width;i_skip = 0;// ----- 4.循环编码slice当中的每个mb ----- //while( 1 ){mb_xy = i_mb_x + i_mb_y * h->mb.i_mb_width;int mb_spos = bs_pos(&h->out.bs) + x264_cabac_pos(&h->cabac);if( i_mb_x == 0 ){if( bitstream_check_buffer( h ) )return -1;if( !(i_mb_y & SLICE_MBAFF) && h->param.rc.i_vbv_buffer_size )bitstream_backup( h, &bs_bak[BS_BAK_ROW_VBV], i_skip, 1 );if( !h->mb.b_reencode_mb )fdec_filter_row( h, i_mb_y, 0 );}if( back_up_bitstream ){if( back_up_bitstream_cavlc )bitstream_backup( h, &bs_bak[BS_BAK_CAVLC_OVERFLOW], i_skip, 0 );if( slice_max_size && !(i_mb_y & SLICE_MBAFF) ){bitstream_backup( h, &bs_bak[BS_BAK_SLICE_MAX_SIZE], i_skip, 0 );if( (thread_last_mb+1-mb_xy) == h->param.i_slice_min_mbs )bitstream_backup( h, &bs_bak[BS_BAK_SLICE_MIN_MBS], i_skip, 0 );}}if( PARAM_INTERLACED ){if( h->mb.b_adaptive_mbaff ){if( !(i_mb_y&1) ){/* FIXME: VSAD is fast but fairly poor at choosing the best interlace type. */h->mb.b_interlaced = x264_field_vsad( h, i_mb_x, i_mb_y );memcpy( &h->zigzagf, MB_INTERLACED ? &h->zigzagf_interlaced : &h->zigzagf_progressive, sizeof(h->zigzagf) );if( !MB_INTERLACED && (i_mb_y+2) == h->mb.i_mb_height )x264_expand_border_mbpair( h, i_mb_x, i_mb_y );}}h->mb.field[mb_xy] = MB_INTERLACED;}/* load cache */if( SLICE_MBAFF )x264_macroblock_cache_load_interlaced( h, i_mb_x, i_mb_y );elsex264_macroblock_cache_load_progressive( h, i_mb_x, i_mb_y );// ----- 5.分析mb（预测） ----- //x264_macroblock_analyse( h );/* encode this macroblock -> be careful it can change the mb type to P_SKIP if needed */
reencode:// ----- 6.编码mb ----- //x264_macroblock_encode( h );if( h->param.b_cabac ) // 按照CABAC方式写入{if( mb_xy > h->sh.i_first_mb && !(SLICE_MBAFF && (i_mb_y&1)) )x264_cabac_encode_terminal( &h->cabac );if( IS_SKIP( h->mb.i_type ) )x264_cabac_mb_skip( h, 1 );else{if( h->sh.i_type != SLICE_TYPE_I )x264_cabac_mb_skip( h, 0 );x264_macroblock_write_cabac( h, &h->cabac );}}else	// 按照CAVLC方式写入{if( IS_SKIP( h->mb.i_type ) )i_skip++;else{if( h->sh.i_type != SLICE_TYPE_I ){bs_write_ue( &h->out.bs, i_skip );  /* skip run */i_skip = 0;}x264_macroblock_write_cavlc( h );/* If there was a CAVLC level code overflow, try again at a higher QP. */if( h->mb.b_overflow ){h->mb.i_chroma_qp = h->chroma_qp_table[++h->mb.i_qp];h->mb.i_skip_intra = 0;h->mb.b_skip_mc = 0;h->mb.b_overflow = 0;bitstream_restore( h, &bs_bak[BS_BAK_CAVLC_OVERFLOW], &i_skip, 0 );goto reencode;}}}int total_bits = bs_pos(&h->out.bs) + x264_cabac_pos(&h->cabac);int mb_size = total_bits - mb_spos;if( slice_max_size && (!SLICE_MBAFF || (i_mb_y&1)) ){/* Count the skip run, just in case. */if( !h->param.b_cabac )total_bits += bs_size_ue_big( i_skip );/* Check for escape bytes. */uint8_t *end = h->param.b_cabac ? h->cabac.p : h->out.bs.p;for( ; last_emu_check < end - 2; last_emu_check++ )if( last_emu_check[0] == 0 && last_emu_check[1] == 0 && last_emu_check[2] <= 3 ){slice_max_size -= 8;last_emu_check++;}/* We'll just re-encode this last macroblock if we go over the max slice size. */if( total_bits - starting_bits > slice_max_size && !h->mb.b_reencode_mb ){if( !x264_frame_new_slice( h, h->fdec ) ){/* Handle the most obnoxious slice-min-mbs edge case: we need to end the slice* because it's gone over the maximum size, but doing so would violate slice-min-mbs.* If possible, roll back to the last checkpoint and try again.* We could try raising QP, but that would break in the case where a slice spans multiple* rows, which the re-encoding infrastructure can't currently handle. */if( mb_xy <= thread_last_mb && (thread_last_mb+1-mb_xy) < h->param.i_slice_min_mbs ){if( thread_last_mb-h->param.i_slice_min_mbs < h->sh.i_first_mb+h->param.i_slice_min_mbs ){x264_log( h, X264_LOG_WARNING, "slice-max-size violated (frame %d, cause: slice-min-mbs)\n", h->i_frame );slice_max_size = 0;goto cont;}bitstream_restore( h, &bs_bak[BS_BAK_SLICE_MIN_MBS], &i_skip, 0 );h->mb.b_reencode_mb = 1;h->sh.i_last_mb = thread_last_mb-h->param.i_slice_min_mbs;break;}if( mb_xy-SLICE_MBAFF*h->mb.i_mb_stride != h->sh.i_first_mb ){bitstream_restore( h, &bs_bak[BS_BAK_SLICE_MAX_SIZE], &i_skip, 0 );h->mb.b_reencode_mb = 1;if( SLICE_MBAFF ){// set to bottom of previous mbpairif( i_mb_x )h->sh.i_last_mb = mb_xy-1+h->mb.i_mb_stride*(!(i_mb_y&1));elseh->sh.i_last_mb = (i_mb_y-2+!(i_mb_y&1))*h->mb.i_mb_stride + h->mb.i_mb_width - 1;}elseh->sh.i_last_mb = mb_xy-1;break;}elseh->sh.i_last_mb = mb_xy;}elseslice_max_size = 0;}}
cont:h->mb.b_reencode_mb = 0;/* save cache */x264_macroblock_cache_save( h );if( x264_ratecontrol_mb( h, mb_size ) < 0 ){bitstream_restore( h, &bs_bak[BS_BAK_ROW_VBV], &i_skip, 1 );h->mb.b_reencode_mb = 1;i_mb_x = 0;i_mb_y = i_mb_y - SLICE_MBAFF;h->mb.i_mb_prev_xy = i_mb_y * h->mb.i_mb_stride - 1;h->sh.i_last_mb = orig_last_mb;continue;}// ----- 7.收集mb的信息进行更新 ----- ///* accumulate mb stats */h->stat.frame.i_mb_count[h->mb.i_type]++;int b_intra = IS_INTRA( h->mb.i_type );int b_skip = IS_SKIP( h->mb.i_type );if( h->param.i_log_level >= X264_LOG_INFO || h->param.rc.b_stat_write ){if( !b_intra && !b_skip && !IS_DIRECT( h->mb.i_type ) ){if( h->mb.i_partition != D_8x8 )h->stat.frame.i_mb_partition[h->mb.i_partition] += 4;elsefor( int i = 0; i < 4; i++ )h->stat.frame.i_mb_partition[h->mb.i_sub_partition[i]] ++;if( h->param.i_frame_reference > 1 )for( int i_list = 0; i_list <= (h->sh.i_type == SLICE_TYPE_B); i_list++ )for( int i = 0; i < 4; i++ ){int i_ref = h->mb.cache.ref[i_list][ x264_scan8[4*i] ];if( i_ref >= 0 )h->stat.frame.i_mb_count_ref[i_list][i_ref] ++;}}}if( h->param.i_log_level >= X264_LOG_INFO ){if( h->mb.i_cbp_luma | h->mb.i_cbp_chroma ){if( CHROMA444 ){for( int i = 0; i < 4; i++ )if( h->mb.i_cbp_luma & (1 << i) )for( int p = 0; p < 3; p++ ){int s8 = i*4+p*16;int nnz8x8 = M16( &h->mb.cache.non_zero_count[x264_scan8[s8]+0] )| M16( &h->mb.cache.non_zero_count[x264_scan8[s8]+8] );h->stat.frame.i_mb_cbp[!b_intra + p*2] += !!nnz8x8;}}else{int cbpsum = (h->mb.i_cbp_luma&1) + ((h->mb.i_cbp_luma>>1)&1)+ ((h->mb.i_cbp_luma>>2)&1) + (h->mb.i_cbp_luma>>3);h->stat.frame.i_mb_cbp[!b_intra + 0] += cbpsum;h->stat.frame.i_mb_cbp[!b_intra + 2] += !!h->mb.i_cbp_chroma;h->stat.frame.i_mb_cbp[!b_intra + 4] += h->mb.i_cbp_chroma >> 1;}}if( h->mb.i_cbp_luma && !b_intra ){h->stat.frame.i_mb_count_8x8dct[0] ++;h->stat.frame.i_mb_count_8x8dct[1] += h->mb.b_transform_8x8;}if( b_intra && h->mb.i_type != I_PCM ){if( h->mb.i_type == I_16x16 )h->stat.frame.i_mb_pred_mode[0][h->mb.i_intra16x16_pred_mode]++;else if( h->mb.i_type == I_8x8 )for( int i = 0; i < 16; i += 4 )h->stat.frame.i_mb_pred_mode[1][h->mb.cache.intra4x4_pred_mode[x264_scan8[i]]]++;else //if( h->mb.i_type == I_4x4 )for( int i = 0; i < 16; i++ )h->stat.frame.i_mb_pred_mode[2][h->mb.cache.intra4x4_pred_mode[x264_scan8[i]]]++;h->stat.frame.i_mb_pred_mode[3][x264_mb_chroma_pred_mode_fix[h->mb.i_chroma_pred_mode]]++;}h->stat.frame.i_mb_field[b_intra?0:b_skip?2:1] += MB_INTERLACED;}// ----- 8.是否进行deblock ----- ///* calculate deblock strength values (actual deblocking is done per-row along with hpel) */if( b_deblock )x264_macroblock_deblock_strength( h );if( mb_xy == h->sh.i_last_mb )break;if( SLICE_MBAFF ){i_mb_x += i_mb_y & 1;i_mb_y ^= i_mb_x < h->mb.i_mb_width;}elsei_mb_x++;if( i_mb_x == h->mb.i_mb_width ){i_mb_y++;i_mb_x = 0;}}if( h->sh.i_last_mb < h->sh.i_first_mb )return 0;h->out.nal[h->out.i_nal].i_last_mb = h->sh.i_last_mb;if( h->param.b_cabac ){x264_cabac_encode_flush( h, &h->cabac );h->out.bs.p = h->cabac.p;}else{if( i_skip > 0 )bs_write_ue( &h->out.bs, i_skip );  /* last skip run *//* rbsp_slice_trailing_bits */bs_rbsp_trailing( &h->out.bs );bs_flush( &h->out.bs );}if( nal_end( h ) )return -1;if( h->sh.i_last_mb == (h->i_threadslice_end * h->mb.i_mb_width - 1) ){h->stat.frame.i_misc_bits = bs_pos( &h->out.bs )+ (h->out.i_nal*NALU_OVERHEAD * 8)- h->stat.frame.i_tex_bits- h->stat.frame.i_mv_bits;fdec_filter_row( h, h->i_threadslice_end, 0 );// ----- 9.多线程情况下，告知主线程，使用broadcast ----- //if( h->param.b_sliced_threads ) {/* Tell the main thread we're done. */x264_threadslice_cond_broadcast( h, 1 );/* Do hpel now */for( int mb_y = h->i_threadslice_start; mb_y <= h->i_threadslice_end; mb_y++ )fdec_filter_row( h, mb_y, 1 );x264_threadslice_cond_broadcast( h, 2 );/* Do the first row of hpel, now that the previous slice is done */if( h->i_thread_idx > 0 ){x264_threadslice_cond_wait( h->thread[h->i_thread_idx-1], 2 );fdec_filter_row( h, h->i_threadslice_start + (1 << SLICE_MBAFF), 2 );}}/* Free mb info after the last thread's done using it */if( h->fdec->mb_info_free && (!h->param.b_sliced_threads || h->i_thread_idx == (h->param.i_threads-1)) ){h->fdec->mb_info_free( h->fdec->mb_info );h->fdec->mb_info = NULL;h->fdec->mb_info_free = NULL;}}return 0;
}

1.11 处理额外信息且更新编码器状态（encoder_frame_end）

该函数位于编码一帧结束之后，用于处理编码之后的信息，更新编码器状态。主要的工作流程为：

1. List itemstatic int encoder_frame_end( x264_t *h, x264_t *thread_current,x264_nal_t **pp_nal, int *pi_nal,x264_picture_t *pic_out )
{char psz_message[80];if( !h->param.b_sliced_threads && h->b_thread_active ){h->b_thread_active = 0;if( (intptr_t)x264_threadpool_wait( h->threadpool, h ) )return -1;}if( !h->out.i_nal ){pic_out->i_type = X264_TYPE_AUTO;return 0;}x264_emms();/* generate buffering period sei and insert it into place */if( h->i_thread_frames > 1 && h->fenc->b_keyframe && h->sps->vui.b_nal_hrd_parameters_present ){x264_hrd_fullness( h );nal_start( h, NAL_SEI, NAL_PRIORITY_DISPOSABLE );x264_sei_buffering_period_write( h, &h->out.bs );if( nal_end( h ) )return -1;/* buffering period sei must follow AUD, SPS and PPS and precede all other SEIs */int idx = 0;while( h->out.nal[idx].i_type == NAL_AUD ||h->out.nal[idx].i_type == NAL_SPS ||h->out.nal[idx].i_type == NAL_PPS )idx++;x264_nal_t nal_tmp = h->out.nal[h->out.i_nal-1];memmove( &h->out.nal[idx+1], &h->out.nal[idx], (h->out.i_nal-idx-1)*sizeof(x264_nal_t) );h->out.nal[idx] = nal_tmp;}int frame_size = encoder_encapsulate_nals( h, 0 );if( frame_size < 0 )return -1;// ----- 1.设置输出图片格式 ----- ///* Set output picture properties */pic_out->i_type = h->fenc->i_type;pic_out->b_keyframe = h->fenc->b_keyframe;pic_out->i_pic_struct = h->fenc->i_pic_struct;pic_out->i_pts = h->fdec->i_pts;pic_out->i_dts = h->fdec->i_dts;if( pic_out->i_pts < pic_out->i_dts )x264_log( h, X264_LOG_WARNING, "invalid DTS: PTS is less than DTS\n" );pic_out->opaque = h->fenc->opaque;pic_out->img.i_csp = h->fdec->i_csp;
#if HIGH_BIT_DEPTHpic_out->img.i_csp |= X264_CSP_HIGH_DEPTH;
#endifpic_out->img.i_plane = h->fdec->i_plane;for( int i = 0; i < pic_out->img.i_plane; i++ ){pic_out->img.i_stride[i] = h->fdec->i_stride[i] * SIZEOF_PIXEL;pic_out->img.plane[i] = (uint8_t*)h->fdec->plane[i];}x264_frame_push_unused( thread_current, h->fenc );// ----- 2.更新编码器状态 ----- ///* ---------------------- Update encoder state ------------------------- *//* update rc */int filler = 0;if( x264_ratecontrol_end( h, frame_size * 8, &filler ) < 0 )return -1;pic_out->hrd_timing = h->fenc->hrd_timing;pic_out->prop.f_crf_avg = h->fdec->f_crf_avg;/* Filler in AVC-Intra mode is written as zero bytes to the last slice* We don't know the size of the last slice until encapsulation so we add filler to the encapsulated NAL */if( h->param.i_avcintra_class ){if( check_encapsulated_buffer( h, h->thread[0], h->out.i_nal, frame_size, (int64_t)frame_size + filler ) < 0 )return -1;x264_nal_t *nal = &h->out.nal[h->out.i_nal-1];memset( nal->p_payload + nal->i_payload, 0, filler );nal->i_payload += filler;nal->i_padding = filler;frame_size += filler;/* Fix up the size header for mp4/etc */if( !h->param.b_annexb ){/* Size doesn't include the size of the header we're writing now. */uint8_t *nal_data = nal->p_payload;int chunk_size = nal->i_payload - 4;nal_data[0] = chunk_size >> 24;nal_data[1] = chunk_size >> 16;nal_data[2] = chunk_size >> 8;nal_data[3] = chunk_size >> 0;}}else{while( filler > 0 ){int f, overhead = FILLER_OVERHEAD - h->param.b_annexb;if( h->param.i_slice_max_size && filler > h->param.i_slice_max_size ){int next_size = filler - h->param.i_slice_max_size;int overflow = X264_MAX( overhead - next_size, 0 );f = h->param.i_slice_max_size - overhead - overflow;}elsef = X264_MAX( 0, filler - overhead );if( bitstream_check_buffer_filler( h, f ) )return -1;nal_start( h, NAL_FILLER, NAL_PRIORITY_DISPOSABLE );x264_filler_write( h, &h->out.bs, f );if( nal_end( h ) )return -1;int total_size = encoder_encapsulate_nals( h, h->out.i_nal-1 );if( total_size < 0 )return -1;frame_size += total_size;filler -= total_size;}}/* End bitstream, set output  */*pi_nal = h->out.i_nal;*pp_nal = h->out.nal;h->out.i_nal = 0;x264_noise_reduction_update( h );// ----- 3.计算/输出编码信息 ----- ///* ---------------------- Compute/Print statistics --------------------- */thread_sync_stat( h, h->thread[0] );/* Slice stat */h->stat.i_frame_count[h->sh.i_type]++;h->stat.i_frame_size[h->sh.i_type] += frame_size;h->stat.f_frame_qp[h->sh.i_type] += h->fdec->f_qp_avg_aq;// ...psz_message[0] = '\0';double dur = h->fenc->f_duration;h->stat.f_frame_duration[h->sh.i_type] += dur;if( h->param.analyse.b_psnr ) // 计算psnr{int64_t ssd[3] ={h->stat.frame.i_ssd[0],h->stat.frame.i_ssd[1],h->stat.frame.i_ssd[2],};int luma_size = h->param.i_width * h->param.i_height;int chroma_size = CHROMA_SIZE( luma_size );pic_out->prop.f_psnr[0] = calc_psnr( ssd[0], luma_size );pic_out->prop.f_psnr[1] = calc_psnr( ssd[1], chroma_size );pic_out->prop.f_psnr[2] = calc_psnr( ssd[2], chroma_size );pic_out->prop.f_psnr_avg = calc_psnr( ssd[0] + ssd[1] + ssd[2], luma_size + chroma_size*2 );h->stat.f_ssd_global[h->sh.i_type]   += dur * (ssd[0] + ssd[1] + ssd[2]);h->stat.f_psnr_average[h->sh.i_type] += dur * pic_out->prop.f_psnr_avg;h->stat.f_psnr_mean_y[h->sh.i_type]  += dur * pic_out->prop.f_psnr[0];h->stat.f_psnr_mean_u[h->sh.i_type]  += dur * pic_out->prop.f_psnr[1];h->stat.f_psnr_mean_v[h->sh.i_type]  += dur * pic_out->prop.f_psnr[2];snprintf( psz_message, 80, " PSNR Y:%5.2f U:%5.2f V:%5.2f", pic_out->prop.f_psnr[0],pic_out->prop.f_psnr[1],pic_out->prop.f_psnr[2] );}if( h->param.analyse.b_ssim ) // 计算ssim{pic_out->prop.f_ssim = h->stat.frame.f_ssim / h->stat.frame.i_ssim_cnt;h->stat.f_ssim_mean_y[h->sh.i_type] += pic_out->prop.f_ssim * dur;int msg_len = strlen(psz_message);snprintf( psz_message + msg_len, 80 - msg_len, " SSIM Y:%.5f", pic_out->prop.f_ssim );}psz_message[79] = '\0';... 
}

2.小结

x264_encoder_encode中实现了实际编码一帧的功能，其中涉及到了编码器中诸多方面的内容，大体可以归类如下：

1. 码流存储的方式
2. 码率控制的实现
3. 预测模块（帧内预测，帧间预测）
4. 实际编码（DCT变换，Quant量化）
5. 熵编码（CABAC，CAVLC）
6. 滤波模块

在视频编码当中，工作的大致流程是，输入一帧，经过mb块划分之后，对每一个mb进行参考帧预测（帧内或帧间）获得残差，对残差进行实际编码（变换量化）获得系数，系数通过熵编码进行编码并写入码流。滤波模块应用于重建帧之后，为了降低重建帧和原始帧之间的差异，对重建帧进行滤波处理，将滤波之后的重建帧作为下一帧的参考帧。

此外，还需要了解码流存储的方式和结构，比如不同的信息使用几个比特进行存储，存储在哪个位置，使用的是算术编码还是哥伦布编码，这些都值得思考和探索。

CSDN : https://blog.csdn.net/weixin_42877471
Github : https://github.com/DoFulangChen