/*
 * Copyright (c) 2008 Apple Inc. All rights reserved.
 *
 * @APPLE_OSREFERENCE_LICENSE_HEADER_START@
 * 
 * This file contains Original Code and/or Modifications of Original Code
 * as defined in and that are subject to the Apple Public Source License
 * Version 2.0 (the 'License'). You may not use this file except in
 * compliance with the License. The rights granted to you under the License
 * may not be used to create, or enable the creation or redistribution of,
 * unlawful or unlicensed copies of an Apple operating system, or to
 * circumvent, violate, or enable the circumvention or violation of, any
 * terms of an Apple operating system software license agreement.
 * 
 * Please obtain a copy of the License at
 * http://www.opensource.apple.com/apsl/ and read it before using this file.
 * 
 * The Original Code and all software distributed under the License are
 * distributed on an 'AS IS' basis, WITHOUT WARRANTY OF ANY KIND, EITHER
 * EXPRESS OR IMPLIED, AND APPLE HEREBY DISCLAIMS ALL SUCH WARRANTIES,
 * INCLUDING WITHOUT LIMITATION, ANY WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE, QUIET ENJOYMENT OR NON-INFRINGEMENT.
 * Please see the License for the specific language governing rights and
 * limitations under the License.
 * 
 * @APPLE_OSREFERENCE_LICENSE_HEADER_END@
 */
/* adler32.c -- compute the Adler-32 checksum of a data stream
 * Copyright (C) 1995-2004 Mark Adler
 * For conditions of distribution and use, see copyright notice in zlib.h
 */

/* @(#) $Id$ */

#include <stdint.h> // For uintptr_t.


#define ZLIB_INTERNAL
#if KERNEL
    #include <libkern/zlib.h>
#else
    #include "zlib.h"
#endif /* KERNEL */

#if defined _ARM_ARCH_6
	extern uLong adler32_vec(uLong adler, uLong sum2, const Bytef *buf, uInt len);
#endif

#define BASE 65521UL    /* largest prime smaller than 65536 */
#define NMAX 5552
/* NMAX is the largest n such that 255n(n+1)/2 + (n+1)(BASE-1) <= 2^32-1 */

#define DO1(buf,i)  {adler += (buf)[i]; sum2 += adler;}
#define DO2(buf,i)  DO1(buf,i); DO1(buf,i+1);
#define DO4(buf,i)  DO2(buf,i); DO2(buf,i+2);
#define DO8(buf,i)  DO4(buf,i); DO4(buf,i+4);
#define DO16(buf)   DO8(buf,0); DO8(buf,8);

/* use NO_DIVIDE if your processor does not do division in hardware */
#ifdef NO_DIVIDE
#  define MOD(a) \
    do { \
        if (a >= (BASE << 16)) a -= (BASE << 16); \
        if (a >= (BASE << 15)) a -= (BASE << 15); \
        if (a >= (BASE << 14)) a -= (BASE << 14); \
        if (a >= (BASE << 13)) a -= (BASE << 13); \
        if (a >= (BASE << 12)) a -= (BASE << 12); \
        if (a >= (BASE << 11)) a -= (BASE << 11); \
        if (a >= (BASE << 10)) a -= (BASE << 10); \
        if (a >= (BASE << 9)) a -= (BASE << 9); \
        if (a >= (BASE << 8)) a -= (BASE << 8); \
        if (a >= (BASE << 7)) a -= (BASE << 7); \
        if (a >= (BASE << 6)) a -= (BASE << 6); \
        if (a >= (BASE << 5)) a -= (BASE << 5); \
        if (a >= (BASE << 4)) a -= (BASE << 4); \
        if (a >= (BASE << 3)) a -= (BASE << 3); \
        if (a >= (BASE << 2)) a -= (BASE << 2); \
        if (a >= (BASE << 1)) a -= (BASE << 1); \
        if (a >= BASE) a -= BASE; \
    } while (0)
#  define MOD4(a) \
    do { \
        if (a >= (BASE << 4)) a -= (BASE << 4); \
        if (a >= (BASE << 3)) a -= (BASE << 3); \
        if (a >= (BASE << 2)) a -= (BASE << 2); \
        if (a >= (BASE << 1)) a -= (BASE << 1); \
        if (a >= BASE) a -= BASE; \
    } while (0)
#else
#  define MOD(a) a %= BASE
#  define MOD4(a) a %= BASE
#endif

/* ========================================================================= */
uLong ZEXPORT adler32(adler, buf, len)
    uLong adler;
    const Bytef *buf;
    uInt len;
{
    unsigned long sum2;
#if !defined _ARM_ARCH_6
    unsigned n;
#endif

    /* split Adler-32 into component sums */
    sum2 = (adler >> 16) & 0xffff;
    adler &= 0xffff;

    /* in case user likes doing a byte at a time, keep it fast */
    if (len == 1) {
        adler += buf[0];
        if (adler >= BASE)
            adler -= BASE;
        sum2 += adler;
        if (sum2 >= BASE)
            sum2 -= BASE;
        return adler | (sum2 << 16);
    }

    /* initial Adler-32 value (deferred check for len == 1 speed) */
    if (buf == Z_NULL)
        return 1L;

    /* in case short lengths are provided, keep it somewhat fast */
    if (len < 16) {
        while (len--) {
            adler += *buf++;
            sum2 += adler;
        }
        if (adler >= BASE)
            adler -= BASE;
        MOD4(sum2);             /* only added so many BASE's */
        return adler | (sum2 << 16);
    }

#if defined _ARM_ARCH_6
    /* align buf to 16-byte boundary */
    while (((uintptr_t)buf)&15) { /* not on a 16-byte boundary */
        len--;
        adler += *buf++;
        sum2 += adler;
        if (adler >= BASE) adler -= BASE;
        MOD4(sum2);             /* only added so many BASE's */
    }

    return adler32_vec(adler, sum2, buf, len);      // armv7 neon vectorized implementation

#else   //  _ARM_ARCH_6

    /* do length NMAX blocks -- requires just one modulo operation */
    while (len >= NMAX) {
        len -= NMAX;
        n = NMAX / 16;          /* NMAX is divisible by 16 */
        do {
            DO16(buf);          /* 16 sums unrolled */
            buf += 16;
        } while (--n);
        MOD(adler);
        MOD(sum2);
    }

    /* do remaining bytes (less than NMAX, still just one modulo) */
    if (len) {                  /* avoid modulos if none remaining */
        while (len >= 16) {
            len -= 16;
            DO16(buf);
            buf += 16;
        }
        while (len--) {
            adler += *buf++;
            sum2 += adler;
        }
        MOD(adler);
        MOD(sum2);
    }

    /* return recombined sums */
    return adler | (sum2 << 16);

#endif  // _ARM_ARCH_6
}

/* ========================================================================= */
uLong ZEXPORT adler32_combine(adler1, adler2, len2)
    uLong adler1;
    uLong adler2;
    z_off_t len2;
{
    unsigned long sum1;
    unsigned long sum2;
    unsigned rem;

    /* the derivation of this formula is left as an exercise for the reader */
    rem = (unsigned)(len2 % BASE);
    sum1 = adler1 & 0xffff;
    sum2 = rem * sum1;
    MOD(sum2);
    sum1 += (adler2 & 0xffff) + BASE - 1;
    sum2 += ((adler1 >> 16) & 0xffff) + ((adler2 >> 16) & 0xffff) + BASE - rem;
    if (sum1 > BASE) sum1 -= BASE;
    if (sum1 > BASE) sum1 -= BASE;
    if (sum2 > (BASE << 1)) sum2 -= (BASE << 1);
    if (sum2 > BASE) sum2 -= BASE;
    return sum1 | (sum2 << 16);
}