/*	$OpenBSD: inffast.c,v 1.7 2005/07/20 15:56:41 millert Exp $	*/

/* inffast.c -- fast decoding

 * Copyright (C) 1995-2004 Mark Adler

 * For conditions of distribution and use, see copyright notice in zlib.h

 */

#include "zutil.h"

#include "inftrees.h"

#include "inflate.h"

#include "inffast.h"

#ifndef ASMINF

/* Allow machine dependent optimization for post-increment or pre-increment.

   Based on testing to date,

   Pre-increment preferred for:

   - PowerPC G3 (Adler)

   - MIPS R5000 (Randers-Pehrson)

   Post-increment preferred for:

   - none

   No measurable difference:

   - Pentium III (Anderson)

   - M68060 (Nikl)

 */

#ifdef POSTINC

#  define OFF 0

#  define PUP(a) *(a)++

#else

#  define OFF 1

#  define PUP(a) *++(a)

#endif

/*

   Decode literal, length, and distance codes and write out the resulting

   literal and match bytes until either not enough input or output is

   available, an end-of-block is encountered, or a data error is encountered.

   When large enough input and output buffers are supplied to inflate(), for

   example, a 16K input buffer and a 64K output buffer, more than 95% of the

   inflate execution time is spent in this routine.

   Entry assumptions:

        state->mode == LEN

        strm->avail_in >= 6

        strm->avail_out >= 258

        start >= strm->avail_out

        state->bits < 8

   On return, state->mode is one of:

        LEN -- ran out of enough output space or enough available input

        TYPE -- reached end of block code, inflate() to interpret next block

        BAD -- error in block data

   Notes:

    - The maximum input bits used by a length/distance pair is 15 bits for the

      length code, 5 bits for the length extra, 15 bits for the distance code,

      and 13 bits for the distance extra.  This totals 48 bits, or six bytes.

      Therefore if strm->avail_in >= 6, then there is enough input to avoid

      checking for available input while decoding.

    - The maximum bytes that a single length/distance pair can output is 258

      bytes, which is the maximum length that can be coded.  inflate_fast()

      requires strm->avail_out >= 258 for each loop to avoid checking for

      output space.

 */

void inflate_fast(strm, start)

z_streamp strm;

unsigned start;         /* inflate()'s starting value for strm->avail_out */

{

    struct inflate_state FAR *state;

    unsigned char FAR *in;      /* local strm->next_in */

    unsigned char FAR *last;    /* while in < last, enough input available */

    unsigned char FAR *out;     /* local strm->next_out */

    unsigned char FAR *beg;     /* inflate()'s initial strm->next_out */

    unsigned char FAR *end;     /* while out < end, enough space available */

#ifdef INFLATE_STRICT

    unsigned dmax;              /* maximum distance from zlib header */

#endif

    unsigned wsize;             /* window size or zero if not using window */

    unsigned whave;             /* valid bytes in the window */

    unsigned write;             /* window write index */

    unsigned char FAR *window;  /* allocated sliding window, if wsize != 0 */

    unsigned long hold;         /* local strm->hold */

    unsigned bits;              /* local strm->bits */

    code const FAR *lcode;      /* local strm->lencode */

    code const FAR *dcode;      /* local strm->distcode */

    unsigned lmask;             /* mask for first level of length codes */

    unsigned dmask;             /* mask for first level of distance codes */

    code this;                  /* retrieved table entry */

    unsigned op;                /* code bits, operation, extra bits, or */

                                /*  window position, window bytes to copy */

    unsigned len;               /* match length, unused bytes */

    unsigned dist;              /* match distance */

    unsigned char FAR *from;    /* where to copy match from */

    /* copy state to local variables */

#ifdef INFLATE_STRICT

    dmax = state->dmax;

#endif

    /* decode literals and length/distances until end-of-block or not enough

       input data or output space */

        }

      dolen:

            Tracevv((stderr, this.val >= 0x20 && this.val < 0x7f ?

                    "inflate:         literal '%c'\n" :

                    "inflate:         literal 0x%02x\n", this.val));

        }

                }

            }

            Tracevv((stderr, "inflate:         length %u\n", len));

            }

          dodist:

                    }

                }

#ifdef INFLATE_STRICT

                if (dist > dmax) {

                    strm->msg = (char *)"invalid distance too far back";

                    state->mode = BAD;

                    break;

                }

#endif

                Tracevv((stderr, "inflate:         distance %u\n", dist));

#ifdef SMALL

			strm->msg = "error";

#else

#endif

                        state->mode = BAD;

                    }

                        }

                    }

                            from = window - OFF;

                                op = write;

                            }

                        }

                    }

                    else {                      /* contiguous in window */

                        }

                    }

                    }

                    }

                }

                else {

                    }

                }

            }

            }

            else {

#ifdef SMALL

		strm->msg = "error";

#else

#endif

                state->mode = BAD;

            }

        }

        }

            Tracevv((stderr, "inflate:         end of block\n"));

            state->mode = TYPE;

        }

        else {

#ifdef SMALL

	    strm->msg = "error";

#else

#endif

            state->mode = BAD;

        }

    /* return unused bytes (on entry, bits < 8, so in won't go too far back) */

    /* update state and return */

    return;

}

/*

   inflate_fast() speedups that turned out slower (on a PowerPC G3 750CXe):

   - Using bit fields for code structure

   - Different op definition to avoid & for extra bits (do & for table bits)

   - Three separate decoding do-loops for direct, window, and write == 0

   - Special case for distance > 1 copies to do overlapped load and store copy

   - Explicit branch predictions (based on measured branch probabilities)

   - Deferring match copy and interspersed it with decoding subsequent codes

   - Swapping literal/length else

   - Swapping window/direct else

   - Larger unrolled copy loops (three is about right)

   - Moving len -= 3 statement into middle of loop

 */

#endif /* !ASMINF */