decodframe.c

/*
 *  Copyright (c) 2010 The WebM project authors. All Rights Reserved.
 *
 *  Use of this source code is governed by a BSD-style license
 *  that can be found in the LICENSE file in the root of the source
 *  tree. An additional intellectual property rights grant can be found
 *  in the file PATENTS.  All contributing project authors may
 *  be found in the AUTHORS file in the root of the source tree.
 */


#include "onyxd_int.h"
#include "vp8/common/header.h"
#include "vp8/common/reconintra.h"
#include "vp8/common/reconintra4x4.h"
#include "vp8/common/recon.h"
#include "vp8/common/reconinter.h"
#include "dequantize.h"
#include "detokenize.h"
#include "vp8/common/invtrans.h"
#include "vp8/common/alloccommon.h"
#include "vp8/common/entropymode.h"
#include "vp8/common/quant_common.h"
#include "vpx_scale/vpxscale.h"
#include "vpx_scale/yv12extend.h"
#include "vp8/common/setupintrarecon.h"

#include "decodemv.h"
#include "vp8/common/extend.h"
#include "vp8/common/modecont.h"
#include "vpx_mem/vpx_mem.h"
#include "vp8/common/idct.h"
#include "dequantize.h"
#include "dboolhuff.h"

#include "vp8/common/seg_common.h"

#include <assert.h>
#include <stdio.h>


#ifdef DEC_DEBUG
int dec_debug = 0;
#endif

void vp8cx_init_de_quantizer(VP8D_COMP *pbi)
{
    int i;
    int Q;
    VP8_COMMON *const pc = & pbi->common;

    for (Q = 0; Q < QINDEX_RANGE; Q++)
    {
        pc->Y1dequant[Q][0] = (short)vp8_dc_quant(Q, pc->y1dc_delta_q);
        pc->Y2dequant[Q][0] = (short)vp8_dc2quant(Q, pc->y2dc_delta_q);
        pc->UVdequant[Q][0] = (short)vp8_dc_uv_quant(Q, pc->uvdc_delta_q);

        /* all the ac values = ; */
        for (i = 1; i < 16; i++)
        {
            int rc = vp8_default_zig_zag1d[i];

            pc->Y1dequant[Q][rc] = (short)vp8_ac_yquant(Q);
            pc->Y2dequant[Q][rc] = (short)vp8_ac2quant(Q, pc->y2ac_delta_q);
            pc->UVdequant[Q][rc] = (short)vp8_ac_uv_quant(Q, pc->uvac_delta_q);
        }
    }
}

void mb_init_dequantizer(VP8D_COMP *pbi, MACROBLOCKD *xd)
{
    int i;
    int QIndex;
    VP8_COMMON *const pc = & pbi->common;
    int segment_id = xd->mode_info_context->mbmi.segment_id;

    // Set the Q baseline allowing for any segment level adjustment
    if ( segfeature_active( xd, segment_id, SEG_LVL_ALT_Q ) )
    {
        /* Abs Value */
        if (xd->mb_segement_abs_delta == SEGMENT_ABSDATA)
            QIndex = get_segdata( xd, segment_id, SEG_LVL_ALT_Q );

        /* Delta Value */
        else
        {
            QIndex = pc->base_qindex +
                     get_segdata( xd, segment_id, SEG_LVL_ALT_Q );
            QIndex = (QIndex >= 0) ? ((QIndex <= MAXQ) ? QIndex : MAXQ) : 0;    /* Clamp to valid range */
        }
    }
    else
        QIndex = pc->base_qindex;

    /* Set up the block level dequant pointers */
    for (i = 0; i < 16; i++)
    {
        xd->block[i].dequant = pc->Y1dequant[QIndex];
    }

    for (i = 16; i < 24; i++)
    {
        xd->block[i].dequant = pc->UVdequant[QIndex];
    }

    xd->block[24].dequant = pc->Y2dequant[QIndex];

}

#if CONFIG_RUNTIME_CPU_DETECT
#define RTCD_VTABLE(x) (&(pbi)->common.rtcd.x)
#else
#define RTCD_VTABLE(x) NULL
#endif

/* skip_recon_mb() is Modified: Instead of writing the result to predictor buffer and then copying it
 *  to dst buffer, we can write the result directly to dst buffer. This eliminates unnecessary copy.
 */
static void skip_recon_mb(VP8D_COMP *pbi, MACROBLOCKD *xd)
{
    if (xd->mode_info_context->mbmi.ref_frame == INTRA_FRAME)
    {
        RECON_INVOKE(&pbi->common.rtcd.recon, build_intra_predictors_mbuv_s)(xd);
        RECON_INVOKE(&pbi->common.rtcd.recon,
                     build_intra_predictors_mby_s)(xd);
    }
    else
    {
        vp8_build_inter16x16_predictors_mb(xd, xd->dst.y_buffer,
                                           xd->dst.u_buffer, xd->dst.v_buffer,
                                           xd->dst.y_stride, xd->dst.uv_stride);

        if (xd->mode_info_context->mbmi.second_ref_frame)
        {
            vp8_build_2nd_inter16x16_predictors_mb(xd, xd->dst.y_buffer,
                                                   xd->dst.u_buffer, xd->dst.v_buffer,
                                                   xd->dst.y_stride, xd->dst.uv_stride);
        }
    }
#ifdef DEC_DEBUG
        if (dec_debug) {
          int i, j;
          printf("Generating predictors\n");
          for (i=0;i<16;i++) {
            for (j=0;j<16;j++) printf("%3d ", xd->dst.y_buffer[i*xd->dst.y_stride+j]);
            printf("\n");
          }
        }
#endif

}

extern const int vp8_i8x8_block[4];
static void decode_macroblock(VP8D_COMP *pbi, MACROBLOCKD *xd,
                              unsigned int mb_idx)
{
    int eobtotal = 0;
    int throw_residual = 0;
    MB_PREDICTION_MODE mode;
    int i;

#if CONFIG_T8X8
    int tx_type;
    if( pbi->common.txfm_mode==ONLY_4X4 )
    {
        xd->mode_info_context->mbmi.txfm_size = TX_4X4;
    }
    else if( pbi->common.txfm_mode == ALLOW_8X8 )
    {
        if( xd->mode_info_context->mbmi.mode ==B_PRED
            ||xd->mode_info_context->mbmi.mode ==I8X8_PRED
            ||xd->mode_info_context->mbmi.mode ==SPLITMV)
            xd->mode_info_context->mbmi.txfm_size = TX_4X4;
        else
            xd->mode_info_context->mbmi.txfm_size = TX_8X8;
    }

    tx_type = xd->mode_info_context->mbmi.txfm_size;
#endif

    if (xd->mode_info_context->mbmi.mb_skip_coeff)
    {
        vp8_reset_mb_tokens_context(xd);
    }
    else if (!vp8dx_bool_error(xd->current_bc))
    {

#if CONFIG_T8X8
        for(i = 0; i < 25; i++)
        {
            xd->block[i].eob = 0;
            xd->eobs[i] = 0;
        }
        if ( tx_type == TX_8X8 )
        {
            eobtotal = vp8_decode_mb_tokens_8x8(pbi, xd);
        }
        else
#endif
            eobtotal = vp8_decode_mb_tokens(pbi, xd);
#ifdef DEC_DEBUG
        if (dec_debug) {
            printf("\nTokens (%d)\n", eobtotal);
            for (i =0; i<400; i++) {
                printf("%3d ", xd->qcoeff[i]);
                if (i%16 == 15) printf("\n");
            }
            printf("\n");
        }
#endif
    }

    mode = xd->mode_info_context->mbmi.mode;

    if (eobtotal == 0 && mode != B_PRED && mode != SPLITMV
        && mode != I8X8_PRED
        &&!vp8dx_bool_error(xd->current_bc)
        )
    {
        /* Special case:  Force the loopfilter to skip when eobtotal and
         * mb_skip_coeff are zero.
         * */
        xd->mode_info_context->mbmi.mb_skip_coeff = 1;

        skip_recon_mb(pbi, xd);
        return;
    }

#ifdef DEC_DEBUG
        if (dec_debug) {
          int i, j;
          printf("Generating predictors\n");
          for (i=0;i<16;i++) {
            for (j=0;j<16;j++) printf("%3d ", xd->dst.y_buffer[i*xd->dst.y_stride+j]);
            printf("\n");
          }
        }
#endif



    if (xd->segmentation_enabled)
        mb_init_dequantizer(pbi, xd);

    /* do prediction */
    if (xd->mode_info_context->mbmi.ref_frame == INTRA_FRAME)
    {
        if(mode != I8X8_PRED)
        {
            RECON_INVOKE(&pbi->common.rtcd.recon, build_intra_predictors_mbuv)(xd);
            if (mode != B_PRED)
            {
                RECON_INVOKE(&pbi->common.rtcd.recon,
                    build_intra_predictors_mby)(xd);
            } else {
#if !CONFIG_SUPERBLOCKS
                vp8_intra_prediction_down_copy(xd);
#endif
            }
        }
    }
    else
    {
        vp8_build_inter_predictors_mb(xd);
    }
    /* When we have independent partitions we can apply residual even
     * though other partitions within the frame are corrupt.
     */
    throw_residual = (!pbi->independent_partitions &&
                      pbi->frame_corrupt_residual);
    throw_residual = (throw_residual || vp8dx_bool_error(xd->current_bc));

    /* dequantization and idct */
    if (mode == I8X8_PRED)
    {
        for (i = 0; i < 4; i++)
        {
            int ib = vp8_i8x8_block[i];
            const int iblock[4]={0,1,4,5};
            int j;
            int i8x8mode;
            BLOCKD *b;

            b = &xd->block[ib];
            i8x8mode= b->bmi.as_mode;
            RECON_INVOKE(RTCD_VTABLE(recon), intra8x8_predict)
                          (b, i8x8mode, b->predictor);

            for(j = 0; j < 4; j++)
            {
                b = &xd->block[ib+iblock[j]];
                if (xd->eobs[ib+iblock[j]] > 1)
                {
                    DEQUANT_INVOKE(&pbi->dequant, idct_add)
                        (b->qcoeff, b->dequant,  b->predictor,
                        *(b->base_dst) + b->dst, 16, b->dst_stride);
                }
                else
                {
                    IDCT_INVOKE(RTCD_VTABLE(idct), idct1_scalar_add)
                        (b->qcoeff[0] * b->dequant[0], b->predictor,
                        *(b->base_dst) + b->dst, 16, b->dst_stride);
                    ((int *)b->qcoeff)[0] = 0;
                }
            }

            b = &xd->block[16+i];
            RECON_INVOKE(RTCD_VTABLE(recon), intra_uv4x4_predict)
                          (b, i8x8mode, b->predictor);
            DEQUANT_INVOKE(&pbi->dequant, idct_add)
                (b->qcoeff, b->dequant,  b->predictor,
                *(b->base_dst) + b->dst, 8, b->dst_stride);
            b = &xd->block[20+i];
            RECON_INVOKE(RTCD_VTABLE(recon), intra_uv4x4_predict)
                          (b, i8x8mode, b->predictor);
            DEQUANT_INVOKE(&pbi->dequant, idct_add)
                (b->qcoeff, b->dequant,  b->predictor,
                *(b->base_dst) + b->dst, 8, b->dst_stride);
        }
    }
    else if (mode == B_PRED)
    {
        for (i = 0; i < 16; i++)
        {
            BLOCKD *b = &xd->block[i];
            int b_mode = xd->mode_info_context->bmi[i].as_mode;

            RECON_INVOKE(RTCD_VTABLE(recon), intra4x4_predict)
                          (b, b_mode, b->predictor);

            if (xd->eobs[i] > 1)
            {
                DEQUANT_INVOKE(&pbi->dequant, idct_add)
                    (b->qcoeff, b->dequant,  b->predictor,
                    *(b->base_dst) + b->dst, 16, b->dst_stride);
            }
            else
            {
                IDCT_INVOKE(RTCD_VTABLE(idct), idct1_scalar_add)
                    (b->qcoeff[0] * b->dequant[0], b->predictor,
                    *(b->base_dst) + b->dst, 16, b->dst_stride);
                ((int *)b->qcoeff)[0] = 0;
            }
        }
    }
    else if (mode == SPLITMV)
    {
        DEQUANT_INVOKE (&pbi->dequant, idct_add_y_block)
            (xd->qcoeff, xd->block[0].dequant,
            xd->predictor, xd->dst.y_buffer,
            xd->dst.y_stride, xd->eobs);
    }
    else
    {
        BLOCKD *b = &xd->block[24];

#if CONFIG_T8X8
        if( tx_type == TX_8X8 )
        {
            DEQUANT_INVOKE(&pbi->dequant, block_2x2)(b);
#ifdef DEC_DEBUG
            if (dec_debug)
            {
                int j;
                printf("DQcoeff Haar\n");
                for (j=0;j<16;j++) {
                    printf("%d ", b->dqcoeff[j]);
                }
                printf("\n");
            }
#endif
            IDCT_INVOKE(RTCD_VTABLE(idct), ihaar2)(&b->dqcoeff[0], b->diff, 8);
            ((int *)b->qcoeff)[0] = 0;//2nd order block are set to 0 after inverse transform
            ((int *)b->qcoeff)[1] = 0;
            ((int *)b->qcoeff)[2] = 0;
            ((int *)b->qcoeff)[3] = 0;
            ((int *)b->qcoeff)[4] = 0;
            ((int *)b->qcoeff)[5] = 0;
            ((int *)b->qcoeff)[6] = 0;
            ((int *)b->qcoeff)[7] = 0;
            DEQUANT_INVOKE (&pbi->dequant, dc_idct_add_y_block_8x8)
                (xd->qcoeff, xd->block[0].dequant,
                xd->predictor, xd->dst.y_buffer,
                xd->dst.y_stride, xd->eobs, xd->block[24].diff, xd);

        }

        else
#endif
        {
            DEQUANT_INVOKE(&pbi->dequant, block)(b);
            if (xd->eobs[24] > 1)
            {
                IDCT_INVOKE(RTCD_VTABLE(idct), iwalsh16)(&b->dqcoeff[0], b->diff);
                ((int *)b->qcoeff)[0] = 0;
                ((int *)b->qcoeff)[1] = 0;
                ((int *)b->qcoeff)[2] = 0;
                ((int *)b->qcoeff)[3] = 0;
                ((int *)b->qcoeff)[4] = 0;
                ((int *)b->qcoeff)[5] = 0;
                ((int *)b->qcoeff)[6] = 0;
                ((int *)b->qcoeff)[7] = 0;
            }
            else
            {
                IDCT_INVOKE(RTCD_VTABLE(idct), iwalsh1)(&b->dqcoeff[0], b->diff);
                ((int *)b->qcoeff)[0] = 0;
            }

            DEQUANT_INVOKE (&pbi->dequant, dc_idct_add_y_block)
                (xd->qcoeff, xd->block[0].dequant,
                xd->predictor, xd->dst.y_buffer,
                xd->dst.y_stride, xd->eobs, xd->block[24].diff);
        }
    }
#if CONFIG_T8X8
    if( tx_type == TX_8X8 )
    {
        DEQUANT_INVOKE (&pbi->dequant, idct_add_uv_block_8x8)//
            (xd->qcoeff+16*16, xd->block[16].dequant,
            xd->predictor+16*16, xd->dst.u_buffer, xd->dst.v_buffer,
            xd->dst.uv_stride, xd->eobs+16, xd);//

    }
    else
#endif
    if(xd->mode_info_context->mbmi.mode!=I8X8_PRED)
        DEQUANT_INVOKE (&pbi->dequant, idct_add_uv_block)
                (xd->qcoeff+16*16, xd->block[16].dequant,
                xd->predictor+16*16, xd->dst.u_buffer, xd->dst.v_buffer,
                xd->dst.uv_stride, xd->eobs+16);

}


static int get_delta_q(vp8_reader *bc, int prev, int *q_update)
{
    int ret_val = 0;

    if (vp8_read_bit(bc))
    {
        ret_val = vp8_read_literal(bc, 4);

        if (vp8_read_bit(bc))
            ret_val = -ret_val;
    }

    /* Trigger a quantizer update if the delta-q value has changed */
    if (ret_val != prev)
        *q_update = 1;

    return ret_val;
}

#ifdef PACKET_TESTING
#include <stdio.h>
FILE *vpxlog = 0;
#endif

#if CONFIG_SUPERBLOCKS
static void
decode_sb_row(VP8D_COMP *pbi, VP8_COMMON *pc, int mbrow, MACROBLOCKD *xd)
{
    int i;
    int recon_yoffset, recon_uvoffset;
    int mb_row, mb_col;
    int ref_fb_idx = pc->lst_fb_idx;
    int dst_fb_idx = pc->new_fb_idx;
    int recon_y_stride = pc->yv12_fb[ref_fb_idx].y_stride;
    int recon_uv_stride = pc->yv12_fb[ref_fb_idx].uv_stride;
    int sb_col;
    int row_delta[4] = { 0, +1,  0, -1};
    int col_delta[4] = {+1, -1, +1, +1};
    int sb_cols = (pc->mb_cols + 1)>>1;
    ENTROPY_CONTEXT_PLANES left_context[2];

    vpx_memset(left_context, 0, sizeof(left_context));

    mb_row = mbrow;
    mb_col = 0;

    for (sb_col=0; sb_col<sb_cols; sb_col++)
    {
        for ( i=0; i<4; i++ )
        {
            int dy = row_delta[i];
            int dx = col_delta[i];
            int offset_extended = dy * xd->mode_info_stride + dx;

            if ((mb_row >= pc->mb_rows) || (mb_col >= pc->mb_cols))
            {
                // Skip on to the next MB
                mb_row += dy;
                mb_col += dx;
                xd->mode_info_context += offset_extended;
                continue;
            }

            // Copy in the appropriate left context
            vpx_memcpy (&pc->left_context,
                        &left_context[(i>>1) & 0x1],
                        sizeof(ENTROPY_CONTEXT_PLANES));

            // reset above block coeffs
            xd->above_context = pc->above_context + mb_col;

            /* Distance of Mb to the various image edges.
             * These are specified to 8th pel as they are always compared to
             * values that are in 1/8th pel units
             */
            xd->mb_to_top_edge = -((mb_row * 16)) << 3;
            xd->mb_to_bottom_edge = ((pc->mb_rows - 1 - mb_row) * 16) << 3;

            xd->mb_to_left_edge = -((mb_col * 16) << 3);
            xd->mb_to_right_edge = ((pc->mb_cols - 1 - mb_col) * 16) << 3;

            xd->up_available = (mb_row != 0);
            xd->left_available = (mb_col != 0);

            update_blockd_bmi(xd);

            recon_yoffset = (mb_row * recon_y_stride * 16) + (mb_col * 16);
            recon_uvoffset = (mb_row * recon_uv_stride * 8) + (mb_col * 8);

            xd->dst.y_buffer = pc->yv12_fb[dst_fb_idx].y_buffer + recon_yoffset;
            xd->dst.u_buffer = pc->yv12_fb[dst_fb_idx].u_buffer + recon_uvoffset;
            xd->dst.v_buffer = pc->yv12_fb[dst_fb_idx].v_buffer + recon_uvoffset;

            /* Select the appropriate reference frame for this MB */
            if (xd->mode_info_context->mbmi.ref_frame == LAST_FRAME)
                ref_fb_idx = pc->lst_fb_idx;
            else if (xd->mode_info_context->mbmi.ref_frame == GOLDEN_FRAME)
                ref_fb_idx = pc->gld_fb_idx;
            else
                ref_fb_idx = pc->alt_fb_idx;

            xd->pre.y_buffer = pc->yv12_fb[ref_fb_idx].y_buffer +recon_yoffset;
            xd->pre.u_buffer = pc->yv12_fb[ref_fb_idx].u_buffer +recon_uvoffset;
            xd->pre.v_buffer = pc->yv12_fb[ref_fb_idx].v_buffer +recon_uvoffset;

            if (xd->mode_info_context->mbmi.second_ref_frame)
            {
                int second_ref_fb_idx;

                /* Select the appropriate reference frame for this MB */
                if (xd->mode_info_context->mbmi.second_ref_frame == LAST_FRAME)
                    second_ref_fb_idx = pc->lst_fb_idx;
                else if (xd->mode_info_context->mbmi.second_ref_frame ==
                                                                   GOLDEN_FRAME)
                    second_ref_fb_idx = pc->gld_fb_idx;
                else
                    second_ref_fb_idx = pc->alt_fb_idx;

                xd->second_pre.y_buffer =
                       pc->yv12_fb[second_ref_fb_idx].y_buffer + recon_yoffset;
                xd->second_pre.u_buffer =
                       pc->yv12_fb[second_ref_fb_idx].u_buffer + recon_uvoffset;
                xd->second_pre.v_buffer =
                       pc->yv12_fb[second_ref_fb_idx].v_buffer + recon_uvoffset;
            }

            if (xd->mode_info_context->mbmi.ref_frame != INTRA_FRAME)
            {
                /* propagate errors from reference frames */
                xd->corrupted |= pc->yv12_fb[ref_fb_idx].corrupted;
            }

            decode_macroblock(pbi, xd, mb_row * pc->mb_cols + mb_col);

            /* check if the boolean decoder has suffered an error */
            xd->corrupted |= vp8dx_bool_error(xd->current_bc);

            // Copy in the appropriate left context
            vpx_memcpy (&left_context[(i>>1) & 0x1],
                        &pc->left_context,
                        sizeof(ENTROPY_CONTEXT_PLANES));

            // skip to next MB
            xd->mode_info_context += offset_extended;
            mb_row += dy;
            mb_col += dx;
        }
    }

    /* skip prediction column */
    xd->mode_info_context += 1 - (pc->mb_cols & 0x1) + xd->mode_info_stride;
}
#else
static void
decode_mb_row(VP8D_COMP *pbi, VP8_COMMON *pc, int mb_row, MACROBLOCKD *xd)
{
    int recon_yoffset, recon_uvoffset;
    int mb_col;
    int ref_fb_idx = pc->lst_fb_idx;
    int dst_fb_idx = pc->new_fb_idx;
    int recon_y_stride = pc->yv12_fb[ref_fb_idx].y_stride;
    int recon_uv_stride = pc->yv12_fb[ref_fb_idx].uv_stride;

    vpx_memset(&pc->left_context, 0, sizeof(pc->left_context));
    recon_yoffset = mb_row * recon_y_stride * 16;
    recon_uvoffset = mb_row * recon_uv_stride * 8;
    /* reset above block coeffs */

    xd->above_context = pc->above_context;
    xd->up_available = (mb_row != 0);

    xd->mb_to_top_edge = -((mb_row * 16)) << 3;
    xd->mb_to_bottom_edge = ((pc->mb_rows - 1 - mb_row) * 16) << 3;

    for (mb_col = 0; mb_col < pc->mb_cols; mb_col++)
    {
        /* Distance of Mb to the various image edges.
         * These are specified to 8th pel as they are always compared to values
         * that are in 1/8th pel units
         */
        xd->mb_to_left_edge = -((mb_col * 16) << 3);
        xd->mb_to_right_edge = ((pc->mb_cols - 1 - mb_col) * 16) << 3;

        update_blockd_bmi(xd);

        xd->dst.y_buffer = pc->yv12_fb[dst_fb_idx].y_buffer + recon_yoffset;
        xd->dst.u_buffer = pc->yv12_fb[dst_fb_idx].u_buffer + recon_uvoffset;
        xd->dst.v_buffer = pc->yv12_fb[dst_fb_idx].v_buffer + recon_uvoffset;

        xd->left_available = (mb_col != 0);

        /* Select the appropriate reference frame for this MB */
        if (xd->mode_info_context->mbmi.ref_frame == LAST_FRAME)
            ref_fb_idx = pc->lst_fb_idx;
        else if (xd->mode_info_context->mbmi.ref_frame == GOLDEN_FRAME)
            ref_fb_idx = pc->gld_fb_idx;
        else
            ref_fb_idx = pc->alt_fb_idx;

        xd->pre.y_buffer = pc->yv12_fb[ref_fb_idx].y_buffer + recon_yoffset;
        xd->pre.u_buffer = pc->yv12_fb[ref_fb_idx].u_buffer + recon_uvoffset;
        xd->pre.v_buffer = pc->yv12_fb[ref_fb_idx].v_buffer + recon_uvoffset;

        if (xd->mode_info_context->mbmi.second_ref_frame)
        {
            int second_ref_fb_idx;

            /* Select the appropriate reference frame for this MB */
            if (xd->mode_info_context->mbmi.second_ref_frame == LAST_FRAME)
                second_ref_fb_idx = pc->lst_fb_idx;
            else if (xd->mode_info_context->mbmi.second_ref_frame == GOLDEN_FRAME)
                second_ref_fb_idx = pc->gld_fb_idx;
            else
                second_ref_fb_idx = pc->alt_fb_idx;

            xd->second_pre.y_buffer = pc->yv12_fb[second_ref_fb_idx].y_buffer + recon_yoffset;
            xd->second_pre.u_buffer = pc->yv12_fb[second_ref_fb_idx].u_buffer + recon_uvoffset;
            xd->second_pre.v_buffer = pc->yv12_fb[second_ref_fb_idx].v_buffer + recon_uvoffset;
        }

        if (xd->mode_info_context->mbmi.ref_frame != INTRA_FRAME)
        {
            /* propagate errors from reference frames */
            xd->corrupted |= pc->yv12_fb[ref_fb_idx].corrupted;
        }

#ifdef DEC_DEBUG
        dec_debug = (pc->current_video_frame==1 && mb_row==4 && mb_col==0);
#endif
        decode_macroblock(pbi, xd, mb_row * pc->mb_cols  + mb_col);

        /* check if the boolean decoder has suffered an error */
        xd->corrupted |= vp8dx_bool_error(xd->current_bc);
        recon_yoffset += 16;
        recon_uvoffset += 8;

        ++xd->mode_info_context;  /* next mb */

        xd->above_context++;

    }

    /* adjust to the next row of mbs */
    vp8_extend_mb_row(
        &pc->yv12_fb[dst_fb_idx],
        xd->dst.y_buffer + 16, xd->dst.u_buffer + 8, xd->dst.v_buffer + 8
    );

    ++xd->mode_info_context;      /* skip prediction column */
}
#endif // CONFIG_SUPERBLOCKS

static unsigned int read_partition_size(const unsigned char *cx_size)
{
    const unsigned int size =
        cx_size[0] + (cx_size[1] << 8) + (cx_size[2] << 16);
    return size;
}

static void setup_token_decoder_partition_input(VP8D_COMP *pbi)
{
    vp8_reader *bool_decoder = &pbi->bc2;
    int part_idx = 1;
    int num_token_partitions;

    TOKEN_PARTITION multi_token_partition =
            (TOKEN_PARTITION)vp8_read_literal(&pbi->bc, 2);
    if (!vp8dx_bool_error(&pbi->bc))
        pbi->common.multi_token_partition = multi_token_partition;
    num_token_partitions = 1 << pbi->common.multi_token_partition;
    if (num_token_partitions + 1 > pbi->num_partitions)
        vpx_internal_error(&pbi->common.error, VPX_CODEC_CORRUPT_FRAME,
                           "Partitions missing");
    assert(vp8dx_bool_error(&pbi->bc) ||
           multi_token_partition == pbi->common.multi_token_partition);
    if (pbi->num_partitions > 2)
    {
        CHECK_MEM_ERROR(pbi->mbc, vpx_malloc((pbi->num_partitions - 1) *
                                             sizeof(vp8_reader)));
        bool_decoder = pbi->mbc;
    }

    for (; part_idx < pbi->num_partitions; ++part_idx)
    {
        if (vp8dx_start_decode(bool_decoder,
                               pbi->partitions[part_idx],
                               pbi->partition_sizes[part_idx]))
            vpx_internal_error(&pbi->common.error, VPX_CODEC_MEM_ERROR,
                               "Failed to allocate bool decoder %d",
                               part_idx);

        bool_decoder++;
    }
}


static int read_is_valid(const unsigned char *start,
                         size_t               len,
                         const unsigned char *end)
{
    return (start + len > start && start + len <= end);
}


static void setup_token_decoder(VP8D_COMP *pbi,
                                const unsigned char *cx_data)
{
    int num_part;
    int i;
    VP8_COMMON          *pc = &pbi->common;
    const unsigned char *user_data_end = pbi->Source + pbi->source_sz;
    vp8_reader          *bool_decoder;
    const unsigned char *partition;

    /* Parse number of token partitions to use */
    const TOKEN_PARTITION multi_token_partition =
            (TOKEN_PARTITION)vp8_read_literal(&pbi->bc, 2);
    /* Only update the multi_token_partition field if we are sure the value
     * is correct. */
    if (!vp8dx_bool_error(&pbi->bc))
        pc->multi_token_partition = multi_token_partition;

    num_part = 1 << pc->multi_token_partition;

    /* Set up pointers to the first partition */
    partition = cx_data;
    bool_decoder = &pbi->bc2;

    if (num_part > 1)
    {
        CHECK_MEM_ERROR(pbi->mbc, vpx_malloc(num_part * sizeof(vp8_reader)));
        bool_decoder = pbi->mbc;
        partition += 3 * (num_part - 1);
    }

    for (i = 0; i < num_part; i++)
    {
        const unsigned char *partition_size_ptr = cx_data + i * 3;
        ptrdiff_t            partition_size, bytes_left;

        bytes_left = user_data_end - partition;

        /* Calculate the length of this partition. The last partition
         * size is implicit. If the partition size can't be read, then
         * either use the remaining data in the buffer (for EC mode)
         * or throw an error.
         */
        if (i < num_part - 1)
        {
            if (read_is_valid(partition_size_ptr, 3, user_data_end))
                partition_size = read_partition_size(partition_size_ptr);
            else
                vpx_internal_error(&pc->error, VPX_CODEC_CORRUPT_FRAME,
                                   "Truncated partition size data");
        }
        else
            partition_size = bytes_left;

        /* Validate the calculated partition length. If the buffer
         * described by the partition can't be fully read, then restrict
         * it to the portion that can be (for EC mode) or throw an error.
         */
        if (!read_is_valid(partition, partition_size, user_data_end))
        {
            vpx_internal_error(&pc->error, VPX_CODEC_CORRUPT_FRAME,
                               "Truncated packet or corrupt partition "
                               "%d length", i + 1);
        }

        if (vp8dx_start_decode(bool_decoder, partition, partition_size))
            vpx_internal_error(&pc->error, VPX_CODEC_MEM_ERROR,
                               "Failed to allocate bool decoder %d", i + 1);

        /* Advance to the next partition */
        partition += partition_size;
        bool_decoder++;
    }
}


static void stop_token_decoder(VP8D_COMP *pbi)
{
    VP8_COMMON *pc = &pbi->common;

    if (pc->multi_token_partition != ONE_PARTITION)
    {
        vpx_free(pbi->mbc);
        pbi->mbc = NULL;
    }
}

static void init_frame(VP8D_COMP *pbi)
{
    VP8_COMMON *const pc = & pbi->common;
    MACROBLOCKD *const xd  = & pbi->mb;

    if (pc->frame_type == KEY_FRAME)
    {
        /* Various keyframe initializations */
        vpx_memcpy(pc->fc.mvc, vp8_default_mv_context, sizeof(vp8_default_mv_context));

        vp8_init_mbmode_probs(pc);

        vp8_default_coef_probs(pc);
        vp8_kf_default_bmode_probs(pc->kf_bmode_prob);

        // Reset the segment feature data to the default stats:
        // Features disabled, 0, with delta coding (Default state).
        clearall_segfeatures( xd );

        xd->mb_segement_abs_delta = SEGMENT_DELTADATA;

        /* reset the mode ref deltasa for loop filter */
        vpx_memset(xd->ref_lf_deltas, 0, sizeof(xd->ref_lf_deltas));
        vpx_memset(xd->mode_lf_deltas, 0, sizeof(xd->mode_lf_deltas));

        /* All buffers are implicitly updated on key frames. */
        pc->refresh_golden_frame = 1;
        pc->refresh_alt_ref_frame = 1;
        pc->copy_buffer_to_gf = 0;
        pc->copy_buffer_to_arf = 0;

        /* Note that Golden and Altref modes cannot be used on a key frame so
         * ref_frame_sign_bias[] is undefined and meaningless
         */
        pc->ref_frame_sign_bias[GOLDEN_FRAME] = 0;
        pc->ref_frame_sign_bias[ALTREF_FRAME] = 0;

        vpx_memcpy(&pc->lfc, &pc->fc, sizeof(pc->fc));
        vpx_memcpy(&pc->lfc_a, &pc->fc, sizeof(pc->fc));

        vp8_init_mode_contexts(&pbi->common);
        vpx_memcpy( pbi->common.vp8_mode_contexts,
                    pbi->common.mode_context,
                    sizeof(pbi->common.mode_context));
    }
    else
    {

        if (!pc->use_bilinear_mc_filter)
            pc->mcomp_filter_type = SIXTAP;
        else
            pc->mcomp_filter_type = BILINEAR;

        /* To enable choice of different interploation filters */
        if (pc->mcomp_filter_type == SIXTAP)
        {
            xd->subpixel_predict      = SUBPIX_INVOKE(RTCD_VTABLE(subpix), sixtap4x4);
            xd->subpixel_predict8x4   = SUBPIX_INVOKE(RTCD_VTABLE(subpix), sixtap8x4);
            xd->subpixel_predict8x8   = SUBPIX_INVOKE(RTCD_VTABLE(subpix), sixtap8x8);
            xd->subpixel_predict16x16 = SUBPIX_INVOKE(RTCD_VTABLE(subpix), sixtap16x16);
            xd->subpixel_predict_avg8x8 = SUBPIX_INVOKE(RTCD_VTABLE(subpix), sixtap_avg8x8);
            xd->subpixel_predict_avg16x16 = SUBPIX_INVOKE(RTCD_VTABLE(subpix), sixtap_avg16x16);
        }
        else
        {
            xd->subpixel_predict      = SUBPIX_INVOKE(RTCD_VTABLE(subpix), bilinear4x4);
            xd->subpixel_predict8x4   = SUBPIX_INVOKE(RTCD_VTABLE(subpix), bilinear8x4);
            xd->subpixel_predict8x8   = SUBPIX_INVOKE(RTCD_VTABLE(subpix), bilinear8x8);
            xd->subpixel_predict16x16 = SUBPIX_INVOKE(RTCD_VTABLE(subpix), bilinear16x16);
            xd->subpixel_predict_avg8x8 = SUBPIX_INVOKE(RTCD_VTABLE(subpix), bilinear_avg8x8);
            xd->subpixel_predict_avg16x16 = SUBPIX_INVOKE(RTCD_VTABLE(subpix), bilinear_avg16x16);
        }
    }

    xd->left_context = &pc->left_context;
    xd->mode_info_context = pc->mi;
    xd->frame_type = pc->frame_type;
    xd->mode_info_context->mbmi.mode = DC_PRED;
    xd->mode_info_stride = pc->mode_info_stride;
    xd->corrupted = 0; /* init without corruption */

    xd->fullpixel_mask = 0xffffffff;
    if(pc->full_pixel)
        xd->fullpixel_mask = 0xfffffff8;

}

int vp8_decode_frame(VP8D_COMP *pbi)
{
    vp8_reader *const bc = & pbi->bc;
    VP8_COMMON *const pc = & pbi->common;
    MACROBLOCKD *const xd  = & pbi->mb;
    const unsigned char *data = (const unsigned char *)pbi->Source;
    const unsigned char *data_end = data + pbi->source_sz;
    ptrdiff_t first_partition_length_in_bytes;

    int mb_row;
    int i, j, k, l;
    int corrupt_tokens = 0;
    int prev_independent_partitions = pbi->independent_partitions;

    if (pbi->input_partition)
    {
        data = pbi->partitions[0];
        data_end =  data + pbi->partition_sizes[0];
    }

    /* start with no corruption of current frame */
    xd->corrupted = 0;
    pc->yv12_fb[pc->new_fb_idx].corrupted = 0;

    if (data_end - data < 3)
    {
        vpx_internal_error(&pc->error, VPX_CODEC_CORRUPT_FRAME,
                           "Truncated packet");
    }
    else
    {
        pc->frame_type = (FRAME_TYPE)(data[0] & 1);
        pc->version = (data[0] >> 1) & 7;
        pc->show_frame = (data[0] >> 4) & 1;
        first_partition_length_in_bytes =
            (data[0] | (data[1] << 8) | (data[2] << 16)) >> 5;

        if ((data + first_partition_length_in_bytes > data_end
            || data + first_partition_length_in_bytes < data))
            vpx_internal_error(&pc->error, VPX_CODEC_CORRUPT_FRAME,
                               "Truncated packet or corrupt partition 0 length");

        data += 3;

        vp8_setup_version(pc);

        if (pc->frame_type == KEY_FRAME)
        {
            const int Width = pc->Width;
            const int Height = pc->Height;

            /* vet via sync code */
            /* When error concealment is enabled we should only check the sync
             * code if we have enough bits available
             */
            if (data + 3 < data_end)
            {
                if (data[0] != 0x9d || data[1] != 0x01 || data[2] != 0x2a)
                    vpx_internal_error(&pc->error, VPX_CODEC_UNSUP_BITSTREAM,
                                   "Invalid frame sync code");
            }

            /* If error concealment is enabled we should only parse the new size
             * if we have enough data. Otherwise we will end up with the wrong
             * size.
             */
            if (data + 6 < data_end)
            {
                pc->Width = (data[3] | (data[4] << 8)) & 0x3fff;
                pc->horiz_scale = data[4] >> 6;
                pc->Height = (data[5] | (data[6] << 8)) & 0x3fff;
                pc->vert_scale = data[6] >> 6;
            }
            data += 7;

            if (Width != pc->Width  ||  Height != pc->Height)
            {
                int prev_mb_rows = pc->mb_rows;

                if (pc->Width <= 0)
                {
                    pc->Width = Width;
                    vpx_internal_error(&pc->error, VPX_CODEC_CORRUPT_FRAME,
                                       "Invalid frame width");
                }

                if (pc->Height <= 0)