/* inffas86.c is a hand tuned assembler version of

 *

 * inffast.c -- fast decoding

 * Copyright (C) 1995-2003 Mark Adler

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

 *

 * Copyright (C) 2003 Chris Anderson <christop@charm.net>

 * Please use the copyright conditions above.

 *

 * Dec-29-2003 -- I added AMD64 inflate asm support.  This version is also

 * slightly quicker on x86 systems because, instead of using rep movsb to copy

 * data, it uses rep movsw, which moves data in 2-byte chunks instead of single

 * bytes.  I've tested the AMD64 code on a Fedora Core 1 + the x86_64 updates

 * from http://fedora.linux.duke.edu/fc1_x86_64

 * which is running on an Athlon 64 3000+ / Gigabyte GA-K8VT800M system with

 * 1GB ram.  The 64-bit version is about 4% faster than the 32-bit version,

 * when decompressing mozilla-source-1.3.tar.gz.

 *

 * Mar-13-2003 -- Most of this is derived from inffast.S which is derived from

 * the gcc -S output of zlib-1.2.0/inffast.c.  Zlib-1.2.0 is in beta release at

 * the moment.  I have successfully compiled and tested this code with gcc2.96,

 * gcc3.2, icc5.0, msvc6.0.  It is very close to the speed of inffast.S

 * compiled with gcc -DNO_MMX, but inffast.S is still faster on the P3 with MMX

 * enabled.  I will attempt to merge the MMX code into this version.  Newer

 * versions of this and inffast.S can be found at

 * http://www.eetbeetee.com/zlib/ and http://www.charm.net/~christop/zlib/

 */

#include "zutil.h"

#include "inftrees.h"

#include "inflate.h"

#include "inffast.h"

/* Mark Adler's comments from inffast.c: */

/*

   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;

    struct inffast_ar {

/* 64   32                               x86  x86_64 */

/* ar offset                              register */

/*  0    0 */ void *esp;                /* esp save */

/*  8    4 */ void *ebp;                /* ebp save */

/* 16    8 */ unsigned char FAR *in;    /* esi rsi  local strm->next_in */

/* 24   12 */ unsigned char FAR *last;  /*     r9   while in < last */

/* 32   16 */ unsigned char FAR *out;   /* edi rdi  local strm->next_out */

/* 40   20 */ unsigned char FAR *beg;   /*          inflate()'s init next_out */

/* 48   24 */ unsigned char FAR *end;   /*     r10  while out < end */

/* 56   28 */ unsigned char FAR *window;/*          size of window, wsize!=0 */

/* 64   32 */ code const FAR *lcode;    /* ebp rbp  local strm->lencode */

/* 72   36 */ code const FAR *dcode;    /*     r11  local strm->distcode */

/* 80   40 */ unsigned long hold;       /* edx rdx  local strm->hold */

/* 88   44 */ unsigned bits;            /* ebx rbx  local strm->bits */

/* 92   48 */ unsigned wsize;           /*          window size */

/* 96   52 */ unsigned write;           /*          window write index */

/*100   56 */ unsigned lmask;           /*     r12  mask for lcode */

/*104   60 */ unsigned dmask;           /*     r13  mask for dcode */

/*108   64 */ unsigned len;             /*     r14  match length */

/*112   68 */ unsigned dist;            /*     r15  match distance */

/*116   72 */ unsigned status;          /*          set when state chng*/

    } ar;

#if defined( __GNUC__ ) && defined( __amd64__ ) && ! defined( __i386 )

#define PAD_AVAIL_IN 6

#define PAD_AVAIL_OUT 258

#else

#define PAD_AVAIL_IN 5

#define PAD_AVAIL_OUT 257

#endif

    /* copy state to local variables */

    state = (struct inflate_state FAR *)strm->state;

    ar.in = strm->next_in;

    ar.last = ar.in + (strm->avail_in - PAD_AVAIL_IN);

    ar.out = strm->next_out;

    ar.beg = ar.out - (start - strm->avail_out);

    ar.end = ar.out + (strm->avail_out - PAD_AVAIL_OUT);

    ar.wsize = state->wsize;

    ar.write = state->write;

    ar.window = state->window;

    ar.hold = state->hold;

    ar.bits = state->bits;

    ar.lcode = state->lencode;

    ar.dcode = state->distcode;

    ar.lmask = (1U << state->lenbits) - 1;

    ar.dmask = (1U << state->distbits) - 1;

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

       input data or output space */

    /* align in on 1/2 hold size boundary */

    while (((unsigned long)(void *)ar.in & (sizeof(ar.hold) / 2 - 1)) != 0) {

        ar.hold += (unsigned long)*ar.in++ << ar.bits;

        ar.bits += 8;

    }

#if defined( __GNUC__ ) && defined( __amd64__ ) && ! defined( __i386 )

    __asm__ __volatile__ (

"        leaq    %0, %%rax\n"

"        movq    %%rbp, 8(%%rax)\n"       /* save regs rbp and rsp */

"        movq    %%rsp, (%%rax)\n"

"        movq    %%rax, %%rsp\n"          /* make rsp point to &ar */

"        movq    16(%%rsp), %%rsi\n"      /* rsi  = in */

"        movq    32(%%rsp), %%rdi\n"      /* rdi  = out */

"        movq    24(%%rsp), %%r9\n"       /* r9   = last */

"        movq    48(%%rsp), %%r10\n"      /* r10  = end */

"        movq    64(%%rsp), %%rbp\n"      /* rbp  = lcode */

"        movq    72(%%rsp), %%r11\n"      /* r11  = dcode */

"        movq    80(%%rsp), %%rdx\n"      /* rdx  = hold */

"        movl    88(%%rsp), %%ebx\n"      /* ebx  = bits */

"        movl    100(%%rsp), %%r12d\n"    /* r12d = lmask */

"        movl    104(%%rsp), %%r13d\n"    /* r13d = dmask */

                                          /* r14d = len */

                                          /* r15d = dist */

"        cld\n"

"        cmpq    %%rdi, %%r10\n"

"        je      .L_one_time\n"           /* if only one decode left */

"        cmpq    %%rsi, %%r9\n"

"        je      .L_one_time\n"

"        jmp     .L_do_loop\n"

".L_one_time:\n"

"        movq    %%r12, %%r8\n"           /* r8 = lmask */

"        cmpb    $32, %%bl\n"

"        ja      .L_get_length_code_one_time\n"

"        lodsl\n"                         /* eax = *(uint *)in++ */

"        movb    %%bl, %%cl\n"            /* cl = bits, needs it for shifting */

"        addb    $32, %%bl\n"             /* bits += 32 */

"        shlq    %%cl, %%rax\n"

"        orq     %%rax, %%rdx\n"          /* hold |= *((uint *)in)++ << bits */

"        jmp     .L_get_length_code_one_time\n"

".align 32,0x90\n"

".L_while_test:\n"

"        cmpq    %%rdi, %%r10\n"

"        jbe     .L_break_loop\n"

"        cmpq    %%rsi, %%r9\n"

"        jbe     .L_break_loop\n"

".L_do_loop:\n"

"        movq    %%r12, %%r8\n"           /* r8 = lmask */

"        cmpb    $32, %%bl\n"

"        ja      .L_get_length_code\n"    /* if (32 < bits) */

"        lodsl\n"                         /* eax = *(uint *)in++ */

"        movb    %%bl, %%cl\n"            /* cl = bits, needs it for shifting */

"        addb    $32, %%bl\n"             /* bits += 32 */

"        shlq    %%cl, %%rax\n"

"        orq     %%rax, %%rdx\n"          /* hold |= *((uint *)in)++ << bits */

".L_get_length_code:\n"

"        andq    %%rdx, %%r8\n"            /* r8 &= hold */

"        movl    (%%rbp,%%r8,4), %%eax\n"  /* eax = lcode[hold & lmask] */

"        movb    %%ah, %%cl\n"            /* cl = this.bits */

"        subb    %%ah, %%bl\n"            /* bits -= this.bits */

"        shrq    %%cl, %%rdx\n"           /* hold >>= this.bits */

"        testb   %%al, %%al\n"

"        jnz     .L_test_for_length_base\n" /* if (op != 0) 45.7% */

"        movq    %%r12, %%r8\n"            /* r8 = lmask */

"        shrl    $16, %%eax\n"            /* output this.val char */

"        stosb\n"

".L_get_length_code_one_time:\n"

"        andq    %%rdx, %%r8\n"            /* r8 &= hold */

"        movl    (%%rbp,%%r8,4), %%eax\n" /* eax = lcode[hold & lmask] */

".L_dolen:\n"

"        movb    %%ah, %%cl\n"            /* cl = this.bits */

"        subb    %%ah, %%bl\n"            /* bits -= this.bits */

"        shrq    %%cl, %%rdx\n"           /* hold >>= this.bits */

"        testb   %%al, %%al\n"

"        jnz     .L_test_for_length_base\n" /* if (op != 0) 45.7% */

"        shrl    $16, %%eax\n"            /* output this.val char */

"        stosb\n"

"        jmp     .L_while_test\n"

".align 32,0x90\n"

".L_test_for_length_base:\n"

"        movl    %%eax, %%r14d\n"         /* len = this */

"        shrl    $16, %%r14d\n"           /* len = this.val */

"        movb    %%al, %%cl\n"

"        testb   $16, %%al\n"

"        jz      .L_test_for_second_level_length\n" /* if ((op & 16) == 0) 8% */

"        andb    $15, %%cl\n"             /* op &= 15 */

"        jz      .L_decode_distance\n"    /* if (!op) */

".L_add_bits_to_len:\n"

"        subb    %%cl, %%bl\n"

"        xorl    %%eax, %%eax\n"

"        incl    %%eax\n"

"        shll    %%cl, %%eax\n"

"        decl    %%eax\n"

"        andl    %%edx, %%eax\n"          /* eax &= hold */

"        shrq    %%cl, %%rdx\n"

"        addl    %%eax, %%r14d\n"         /* len += hold & mask[op] */

".L_decode_distance:\n"

"        movq    %%r13, %%r8\n"           /* r8 = dmask */

"        cmpb    $32, %%bl\n"

"        ja      .L_get_distance_code\n"  /* if (32 < bits) */

"        lodsl\n"                         /* eax = *(uint *)in++ */

"        movb    %%bl, %%cl\n"            /* cl = bits, needs it for shifting */

"        addb    $32, %%bl\n"             /* bits += 32 */

"        shlq    %%cl, %%rax\n"

"        orq     %%rax, %%rdx\n"          /* hold |= *((uint *)in)++ << bits */

".L_get_distance_code:\n"

"        andq    %%rdx, %%r8\n"           /* r8 &= hold */

"        movl    (%%r11,%%r8,4), %%eax\n" /* eax = dcode[hold & dmask] */

".L_dodist:\n"

"        movl    %%eax, %%r15d\n"         /* dist = this */

"        shrl    $16, %%r15d\n"           /* dist = this.val */

"        movb    %%ah, %%cl\n"

"        subb    %%ah, %%bl\n"            /* bits -= this.bits */

"        shrq    %%cl, %%rdx\n"           /* hold >>= this.bits */

"        movb    %%al, %%cl\n"            /* cl = this.op */

"        testb   $16, %%al\n"             /* if ((op & 16) == 0) */

"        jz      .L_test_for_second_level_dist\n"

"        andb    $15, %%cl\n"             /* op &= 15 */

"        jz      .L_check_dist_one\n"

".L_add_bits_to_dist:\n"

"        subb    %%cl, %%bl\n"

"        xorl    %%eax, %%eax\n"

"        incl    %%eax\n"

"        shll    %%cl, %%eax\n"

"        decl    %%eax\n"                 /* (1 << op) - 1 */

"        andl    %%edx, %%eax\n"          /* eax &= hold */

"        shrq    %%cl, %%rdx\n"

"        addl    %%eax, %%r15d\n"         /* dist += hold & ((1 << op) - 1) */

".L_check_window:\n"

"        movq    %%rsi, %%r8\n"           /* save in so from can use it's reg */

"        movq    %%rdi, %%rax\n"

"        subq    40(%%rsp), %%rax\n"      /* nbytes = out - beg */

"        cmpl    %%r15d, %%eax\n"

"        jb      .L_clip_window\n"        /* if (dist > nbytes) 4.2% */

"        movl    %%r14d, %%ecx\n"         /* ecx = len */

"        movq    %%rdi, %%rsi\n"

"        subq    %%r15, %%rsi\n"          /* from = out - dist */

"        sarl    %%ecx\n"

"        jnc     .L_copy_two\n"           /* if len % 2 == 0 */

"        rep     movsw\n"

"        movb    (%%rsi), %%al\n"

"        movb    %%al, (%%rdi)\n"

"        incq    %%rdi\n"

"        movq    %%r8, %%rsi\n"           /* move in back to %rsi, toss from */

"        jmp     .L_while_test\n"

".L_copy_two:\n"

"        rep     movsw\n"

"        movq    %%r8, %%rsi\n"           /* move in back to %rsi, toss from */

"        jmp     .L_while_test\n"

".align 32,0x90\n"

".L_check_dist_one:\n"

"        cmpl    $1, %%r15d\n"            /* if dist 1, is a memset */

"        jne     .L_check_window\n"

"        cmpq    %%rdi, 40(%%rsp)\n"      /* if out == beg, outside window */

"        je      .L_check_window\n"

"        movl    %%r14d, %%ecx\n"         /* ecx = len */

"        movb    -1(%%rdi), %%al\n"

"        movb    %%al, %%ah\n"

"        sarl    %%ecx\n"

"        jnc     .L_set_two\n"

"        movb    %%al, (%%rdi)\n"

"        incq    %%rdi\n"

".L_set_two:\n"

"        rep     stosw\n"

"        jmp     .L_while_test\n"

".align 32,0x90\n"

".L_test_for_second_level_length:\n"

"        testb   $64, %%al\n"

"        jnz     .L_test_for_end_of_block\n" /* if ((op & 64) != 0) */

"        xorl    %%eax, %%eax\n"

"        incl    %%eax\n"

"        shll    %%cl, %%eax\n"

"        decl    %%eax\n"

"        andl    %%edx, %%eax\n"         /* eax &= hold */

"        addl    %%r14d, %%eax\n"        /* eax += len */

"        movl    (%%rbp,%%rax,4), %%eax\n" /* eax = lcode[val+(hold&mask[op])]*/

"        jmp     .L_dolen\n"

".align 32,0x90\n"

".L_test_for_second_level_dist:\n"

"        testb   $64, %%al\n"

"        jnz     .L_invalid_distance_code\n" /* if ((op & 64) != 0) */

"        xorl    %%eax, %%eax\n"

"        incl    %%eax\n"

"        shll    %%cl, %%eax\n"

"        decl    %%eax\n"

"        andl    %%edx, %%eax\n"         /* eax &= hold */

"        addl    %%r15d, %%eax\n"        /* eax += dist */

"        movl    (%%r11,%%rax,4), %%eax\n" /* eax = dcode[val+(hold&mask[op])]*/

"        jmp     .L_dodist\n"

".align 32,0x90\n"

".L_clip_window:\n"

"        movl    %%eax, %%ecx\n"         /* ecx = nbytes */

"        movl    92(%%rsp), %%eax\n"     /* eax = wsize, prepare for dist cmp */

"        negl    %%ecx\n"                /* nbytes = -nbytes */

"        cmpl    %%r15d, %%eax\n"

"        jb      .L_invalid_distance_too_far\n" /* if (dist > wsize) */

"        addl    %%r15d, %%ecx\n"         /* nbytes = dist - nbytes */

"        cmpl    $0, 96(%%rsp)\n"

"        jne     .L_wrap_around_window\n" /* if (write != 0) */

"        movq    56(%%rsp), %%rsi\n"     /* from  = window */

"        subl    %%ecx, %%eax\n"         /* eax  -= nbytes */

"        addq    %%rax, %%rsi\n"         /* from += wsize - nbytes */

"        movl    %%r14d, %%eax\n"        /* eax = len */

"        cmpl    %%ecx, %%r14d\n"

"        jbe     .L_do_copy\n"           /* if (nbytes >= len) */

"        subl    %%ecx, %%eax\n"         /* eax -= nbytes */

"        rep     movsb\n"

"        movq    %%rdi, %%rsi\n"

"        subq    %%r15, %%rsi\n"         /* from = &out[ -dist ] */

"        jmp     .L_do_copy\n"

".align 32,0x90\n"

".L_wrap_around_window:\n"

"        movl    96(%%rsp), %%eax\n"     /* eax = write */

"        cmpl    %%eax, %%ecx\n"

"        jbe     .L_contiguous_in_window\n" /* if (write >= nbytes) */

"        movl    92(%%rsp), %%esi\n"     /* from  = wsize */

"        addq    56(%%rsp), %%rsi\n"     /* from += window */

"        addq    %%rax, %%rsi\n"         /* from += write */

"        subq    %%rcx, %%rsi\n"         /* from -= nbytes */

"        subl    %%eax, %%ecx\n"         /* nbytes -= write */

"        movl    %%r14d, %%eax\n"        /* eax = len */

"        cmpl    %%ecx, %%eax\n"

"        jbe     .L_do_copy\n"           /* if (nbytes >= len) */

"        subl    %%ecx, %%eax\n"         /* len -= nbytes */

"        rep     movsb\n"

"        movq    56(%%rsp), %%rsi\n"     /* from = window */

"        movl    96(%%rsp), %%ecx\n"     /* nbytes = write */

"        cmpl    %%ecx, %%eax\n"

"        jbe     .L_do_copy\n"           /* if (nbytes >= len) */

"        subl    %%ecx, %%eax\n"         /* len -= nbytes */

"        rep     movsb\n"

"        movq    %%rdi, %%rsi\n"

"        subq    %%r15, %%rsi\n"         /* from = out - dist */

"        jmp     .L_do_copy\n"

".align 32,0x90\n"

".L_contiguous_in_window:\n"

"        movq    56(%%rsp), %%rsi\n"     /* rsi = window */

"        addq    %%rax, %%rsi\n"

"        subq    %%rcx, %%rsi\n"         /* from += write - nbytes */

"        movl    %%r14d, %%eax\n"        /* eax = len */

"        cmpl    %%ecx, %%eax\n"

"        jbe     .L_do_copy\n"           /* if (nbytes >= len) */

"        subl    %%ecx, %%eax\n"         /* len -= nbytes */

"        rep     movsb\n"

"        movq    %%rdi, %%rsi\n"

"        subq    %%r15, %%rsi\n"         /* from = out - dist */

"        jmp     .L_do_copy\n"           /* if (nbytes >= len) */

".align 32,0x90\n"

".L_do_copy:\n"

"        movl    %%eax, %%ecx\n"         /* ecx = len */

"        rep     movsb\n"

"        movq    %%r8, %%rsi\n"          /* move in back to %esi, toss from */

"        jmp     .L_while_test\n"

".L_test_for_end_of_block:\n"

"        testb   $32, %%al\n"

"        jz      .L_invalid_literal_length_code\n"

"        movl    $1, 116(%%rsp)\n"

"        jmp     .L_break_loop_with_status\n"

".L_invalid_literal_length_code:\n"

"        movl    $2, 116(%%rsp)\n"

"        jmp     .L_break_loop_with_status\n"

".L_invalid_distance_code:\n"

"        movl    $3, 116(%%rsp)\n"

"        jmp     .L_break_loop_with_status\n"

".L_invalid_distance_too_far:\n"

"        movl    $4, 116(%%rsp)\n"

"        jmp     .L_break_loop_with_status\n"

".L_break_loop:\n"

"        movl    $0, 116(%%rsp)\n"

".L_break_loop_with_status:\n"

/* put in, out, bits, and hold back into ar and pop esp */

"        movq    %%rsi, 16(%%rsp)\n"     /* in */

"        movq    %%rdi, 32(%%rsp)\n"     /* out */

"        movl    %%ebx, 88(%%rsp)\n"     /* bits */

"        movq    %%rdx, 80(%%rsp)\n"     /* hold */

"        movq    (%%rsp), %%rax\n"       /* restore rbp and rsp */

"        movq    8(%%rsp), %%rbp\n"

"        movq    %%rax, %%rsp\n"

          :

          : "m" (ar)

          : "memory", "%rax", "%rbx", "%rcx", "%rdx", "%rsi", "%rdi",

            "%r8", "%r9", "%r10", "%r11", "%r12", "%r13", "%r14", "%r15"

    );

#elif ( defined( __GNUC__ ) || defined( __ICC ) ) && defined( __i386 )

    __asm__ __volatile__ (

"        leal    %0, %%eax\n"

"        movl    %%esp, (%%eax)\n"        /* save esp, ebp */

"        movl    %%ebp, 4(%%eax)\n"

"        movl    %%eax, %%esp\n"

"        movl    8(%%esp), %%esi\n"       /* esi = in */

"        movl    16(%%esp), %%edi\n"      /* edi = out */

"        movl    40(%%esp), %%edx\n"      /* edx = hold */

"        movl    44(%%esp), %%ebx\n"      /* ebx = bits */

"        movl    32(%%esp), %%ebp\n"      /* ebp = lcode */

"        cld\n"

"        jmp     .L_do_loop\n"

".align 32,0x90\n"

".L_while_test:\n"

"        cmpl    %%edi, 24(%%esp)\n"      /* out < end */

"        jbe     .L_break_loop\n"

"        cmpl    %%esi, 12(%%esp)\n"      /* in < last */

"        jbe     .L_break_loop\n"

".L_do_loop:\n"

"        cmpb    $15, %%bl\n"

"        ja      .L_get_length_code\n"    /* if (15 < bits) */

"        xorl    %%eax, %%eax\n"

"        lodsw\n"                         /* al = *(ushort *)in++ */

"        movb    %%bl, %%cl\n"            /* cl = bits, needs it for shifting */

"        addb    $16, %%bl\n"             /* bits += 16 */

"        shll    %%cl, %%eax\n"

"        orl     %%eax, %%edx\n"        /* hold |= *((ushort *)in)++ << bits */

".L_get_length_code:\n"

"        movl    56(%%esp), %%eax\n"      /* eax = lmask */

"        andl    %%edx, %%eax\n"          /* eax &= hold */

"        movl    (%%ebp,%%eax,4), %%eax\n" /* eax = lcode[hold & lmask] */

".L_dolen:\n"

"        movb    %%ah, %%cl\n"            /* cl = this.bits */

"        subb    %%ah, %%bl\n"            /* bits -= this.bits */

"        shrl    %%cl, %%edx\n"           /* hold >>= this.bits */

"        testb   %%al, %%al\n"

"        jnz     .L_test_for_length_base\n" /* if (op != 0) 45.7% */

"        shrl    $16, %%eax\n"            /* output this.val char */

"        stosb\n"

"        jmp     .L_while_test\n"

".align 32,0x90\n"

".L_test_for_length_base:\n"

"        movl    %%eax, %%ecx\n"          /* len = this */

"        shrl    $16, %%ecx\n"            /* len = this.val */

"        movl    %%ecx, 64(%%esp)\n"      /* save len */

"        movb    %%al, %%cl\n"

"        testb   $16, %%al\n"

"        jz      .L_test_for_second_level_length\n" /* if ((op & 16) == 0) 8% */

"        andb    $15, %%cl\n"             /* op &= 15 */