xbuf0[rgroup*(M+2) + i] = xbuf0[i];
      xbuf1[rgroup*(M+2) + i] = xbuf1[i];
    }
  }
}


LOCAL(void)
set_bottom_pointers (j_decompress_ptr cinfo)
/* Change the pointer lists to duplicate the last sample row at the bottom
 * of the image.  whichptr indicates which xbuffer holds the final iMCU row.
 * Also sets rowgroups_avail to indicate number of nondummy row groups in row.
 */
{
  my_main_ptr main = (my_main_ptr) cinfo->main;
  int ci, i, rgroup, iMCUheight, rows_left;
  jpeg_component_info *compptr;
  JSAMPARRAY xbuf;

  for (ci = 0, compptr = cinfo->comp_info; ci < cinfo->num_components;
       ci++, compptr++) {
    /* Count sample rows in one iMCU row and in one row group */
    iMCUheight = compptr->v_samp_factor * compptr->DCT_scaled_size;
    rgroup = iMCUheight / cinfo->min_DCT_scaled_size;
    /* Count nondummy sample rows remaining for this component */
    rows_left = (int) (compptr->downsampled_height % (JDIMENSION) iMCUheight);
    if (rows_left == 0) rows_left = iMCUheight;
    /* Count nondummy row groups.  Should get same answer for each component,
     * so we need only do it once.
     */
    if (ci == 0) {
      main->rowgroups_avail = (JDIMENSION) ((rows_left-1) / rgroup + 1);
    }
    /* Duplicate the last real sample row rgroup*2 times; this pads out the
     * last partial rowgroup and ensures at least one full rowgroup of context.
     */
    xbuf = main->xbuffer[main->whichptr][ci];
    for (i = 0; i < rgroup * 2; i++) {
      xbuf[rows_left + i] = xbuf[rows_left-1];
    }
  }
}


/*
 * Initialize for a processing pass.
 */

METHODDEF(void)
start_pass_main (j_decompress_ptr cinfo, J_BUF_MODE pass_mode)
{
  my_main_ptr main = (my_main_ptr) cinfo->main;

  switch (pass_mode) {
  case JBUF_PASS_THRU:
    if (cinfo->upsample->need_context_rows) {
      main->pub.process_data = process_data_context_main;
      make_funny_pointers(cinfo); /* Create the xbuffer[] lists */
      main->whichptr = 0;	/* Read first iMCU row into xbuffer[0] */
      main->context_state = CTX_PREPARE_FOR_IMCU;
      main->iMCU_row_ctr = 0;
    } else {
      /* Simple case with no context needed */
      main->pub.process_data = process_data_simple_main;
    }
    main->buffer_full = FALSE;	/* Mark buffer empty */
    main->rowgroup_ctr = 0;
    break;
#ifdef QUANT_2PASS_SUPPORTED
  case JBUF_CRANK_DEST:
    /* For last pass of 2-pass quantization, just crank the postprocessor */
    main->pub.process_data = process_data_crank_post;
    break;
#endif
  default:
    ERREXIT(cinfo, JERR_BAD_BUFFER_MODE);
    break;
  }
}


/*
 * Process some data.
 * This handles the simple case where no context is required.
 */

METHODDEF(void)
process_data_simple_main (j_decompress_ptr cinfo,
			  JSAMPARRAY output_buf, JDIMENSION *out_row_ctr,
			  JDIMENSION out_rows_avail)
{
  my_main_ptr main = (my_main_ptr) cinfo->main;
  JDIMENSION rowgroups_avail;

  /* Read input data if we haven't filled the main buffer yet */
  if (! main->buffer_full) {
    if (! (*cinfo->coef->decompress_data) (cinfo, main->buffer))
      return;			/* suspension forced, can do nothing more */
    main->buffer_full = TRUE;	/* OK, we have an iMCU row to work with */
  }

  /* There are always min_DCT_scaled_size row groups in an iMCU row. */
  rowgroups_avail = (JDIMENSION) cinfo->min_DCT_scaled_size;
  /* Note: at the bottom of the image, we may pass extra garbage row groups
   * to the postprocessor.  The postprocessor has to check for bottom
   * of image anyway (at row resolution), so no point in us doing it too.
   */

  /* Feed the postprocessor */
  (*cinfo->post->post_process_data) (cinfo, main->buffer,
				     &main->rowgroup_ctr, rowgroups_avail,
				     output_buf, out_row_ctr, out_rows_avail);

  /* Has postprocessor consumed all the data yet? If so, mark buffer empty */
  if (main->rowgroup_ctr >= rowgroups_avail) {
    main->buffer_full = FALSE;
    main->rowgroup_ctr = 0;
  }
}


/*
 * Process some data.
 * This handles the case where context rows must be provided.
 */

METHODDEF(void)
process_data_context_main (j_decompress_ptr cinfo,
			   JSAMPARRAY output_buf, JDIMENSION *out_row_ctr,
			   JDIMENSION out_rows_avail)
{
  my_main_ptr main = (my_main_ptr) cinfo->main;

  /* Read input data if we haven't filled the main buffer yet */
  if (! main->buffer_full) {
    if (! (*cinfo->coef->decompress_data) (cinfo,
					   main->xbuffer[main->whichptr]))
      return;			/* suspension forced, can do nothing more */
    main->buffer_full = TRUE;	/* OK, we have an iMCU row to work with */
    main->iMCU_row_ctr++;	/* count rows received */
  }

  /* Postprocessor typically will not swallow all the input data it is handed
   * in one call (due to filling the output buffer first).  Must be prepared
   * to exit and restart.  This switch lets us keep track of how far we got.
   * Note that each case falls through to the next on successful completion.
   */
  switch (main->context_state) {
  case CTX_POSTPONED_ROW:
    /* Call postprocessor using previously set pointers for postponed row */
    (*cinfo->post->post_process_data) (cinfo, main->xbuffer[main->whichptr],
			&main->rowgroup_ctr, main->rowgroups_avail,
			output_buf, out_row_ctr, out_rows_avail);
    if (main->rowgroup_ctr < main->rowgroups_avail)
      return;			/* Need to suspend */
    main->context_state = CTX_PREPARE_FOR_IMCU;
    if (*out_row_ctr >= out_rows_avail)
      return;			/* Postprocessor exactly filled output buf */
    /*FALLTHROUGH*/
  case CTX_PREPARE_FOR_IMCU:
    /* Prepare to process first M-1 row groups of this iMCU row */
    main->rowgroup_ctr = 0;
    main->rowgroups_avail = (JDIMENSION) (cinfo->min_DCT_scaled_size - 1);
    /* Check for bottom of image: if so, tweak pointers to "duplicate"
     * the last sample row, and adjust rowgroups_avail to ignore padding rows.
     */
    if (main->iMCU_row_ctr == cinfo->total_iMCU_rows)
      set_bottom_pointers(cinfo);
    main->context_state = CTX_PROCESS_IMCU;
    /*FALLTHROUGH*/
  case CTX_PROCESS_IMCU:
    /* Call postprocessor using previously set pointers */
    (*cinfo->post->post_process_data) (cinfo, main->xbuffer[main->whichptr],
			&main->rowgroup_ctr, main->rowgroups_avail,
			output_buf, out_row_ctr, out_rows_avail);
    if (main->rowgroup_ctr < main->rowgroups_avail)
      return;			/* Need to suspend */
    /* After the first iMCU, change wraparound pointers to normal state */
    if (main->iMCU_row_ctr == 1)
      set_wraparound_pointers(cinfo);
    /* Prepare to load new iMCU row using other xbuffer list */
    main->whichptr ^= 1;	/* 0=>1 or 1=>0 */
    main->buffer_full = FALSE;
    /* Still need to process last row group of this iMCU row, */
    /* which is saved at index M+1 of the other xbuffer */
    main->rowgroup_ctr = (JDIMENSION) (cinfo->min_DCT_scaled_size + 1);
    main->rowgroups_avail = (JDIMENSION) (cinfo->min_DCT_scaled_size + 2);
    main->context_state = CTX_POSTPONED_ROW;
  }
}


/*
 * Process some data.
 * Final pass of two-pass quantization: just call the postprocessor.
 * Source data will be the postprocessor controller's internal buffer.
 */

#ifdef QUANT_2PASS_SUPPORTED

METHODDEF(void)
process_data_crank_post (j_decompress_ptr cinfo,
			 JSAMPARRAY output_buf, JDIMENSION *out_row_ctr,
			 JDIMENSION out_rows_avail)
{
  (*cinfo->post->post_process_data) (cinfo, (JSAMPIMAGE) NULL,
				     (JDIMENSION *) NULL, (JDIMENSION) 0,
				     output_buf, out_row_ctr, out_rows_avail);
}

#endif /* QUANT_2PASS_SUPPORTED */


/*
 * Initialize main buffer controller.
 */

GLOBAL(void)
jinit_d_main_controller (j_decompress_ptr cinfo, boolean need_full_buffer)
{
  my_main_ptr main;
  int ci, rgroup, ngroups;
  jpeg_component_info *compptr;

  main = (my_main_ptr)
    (*cinfo->mem->alloc_small) ((j_common_ptr) cinfo, JPOOL_IMAGE,
				SIZEOF(my_main_controller));
  cinfo->main = (struct jpeg_d_main_controller *) main;
  main->pub.start_pass = start_pass_main;

  if (need_full_buffer)		/* shouldn't happen */
    ERREXIT(cinfo, JERR_BAD_BUFFER_MODE);

  /* Allocate the workspace.
   * ngroups is the number of row groups we need.
   */
  if (cinfo->upsample->need_context_rows) {
    if (cinfo->min_DCT_scaled_size < 2) /* unsupported, see comments above */
      ERREXIT(cinfo, JERR_NOTIMPL);
    alloc_funny_pointers(cinfo); /* Alloc space for xbuffer[] lists */
    ngroups = cinfo->min_DCT_scaled_size + 2;
  } else {
    ngroups = cinfo->min_DCT_scaled_size;
  }

  for (ci = 0, compptr = cinfo->comp_info; ci < cinfo->num_components;
       ci++, compptr++) {
    rgroup = (compptr->v_samp_factor * compptr->DCT_scaled_size) /
      cinfo->min_DCT_scaled_size; /* height of a row group of component */
    main->buffer[ci] = (*cinfo->mem->alloc_sarray)
			((j_common_ptr) cinfo, JPOOL_IMAGE,
			 compptr->width_in_blocks * compptr->DCT_scaled_size,
			 (JDIMENSION) (rgroup * ngroups));
  }
}