/*
 * include/asm-xtensa/checksum.h
 *
 * This file is subject to the terms and conditions of the GNU General Public
 * License.  See the file "COPYING" in the main directory of this archive
 * for more details.
 *
 * Copyright (C) 2001 - 2005 Tensilica Inc.
 */

#ifndef _XTENSA_CHECKSUM_H
#define _XTENSA_CHECKSUM_H

#include <linux/in6.h>
#include <linux/uaccess.h>
#include <asm/core.h>

/*
 * computes the checksum of a memory block at buff, length len,
 * and adds in "sum" (32-bit)
 *
 * returns a 32-bit number suitable for feeding into itself
 * or csum_tcpudp_magic
 *
 * this function must be called with even lengths, except
 * for the last fragment, which may be odd
 *
 * it's best to have buff aligned on a 32-bit boundary
 */
asmlinkage __wsum csum_partial(const void *buff, int len, __wsum sum);

/*
 * the same as csum_partial, but copies from src while it
 * checksums, and handles user-space pointer exceptions correctly, when needed.
 *
 * here even more important to align src and dst on a 32-bit (or even
 * better 64-bit) boundary
 */

asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst, int len);

#define _HAVE_ARCH_CSUM_AND_COPY
/*
 *      Note: when you get a NULL pointer exception here this means someone
 *      passed in an incorrect kernel address to one of these functions.
 */
static inline
__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len)
{
        return csum_partial_copy_generic(src, dst, len);
}

#define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
static inline
__wsum csum_and_copy_from_user(const void __user *src, void *dst,
                                   int len)
{
        if (!access_ok(src, len))
                return 0;
        return csum_partial_copy_generic((__force const void *)src, dst, len);
}

/*
 *      Fold a partial checksum
 */

static __inline__ __sum16 csum_fold(__wsum sum)
{
        unsigned int __dummy;
        __asm__("extui  %1, %0, 16, 16\n\t"
                "extui  %0 ,%0, 0, 16\n\t"
                "add    %0, %0, %1\n\t"
                "slli   %1, %0, 16\n\t"
                "add    %0, %0, %1\n\t"
                "extui  %0, %0, 16, 16\n\t"
                "neg    %0, %0\n\t"
                "addi   %0, %0, -1\n\t"
                "extui  %0, %0, 0, 16\n\t"
                : "=r" (sum), "=&r" (__dummy)
                : "0" (sum));
        return (__force __sum16)sum;
}

/*
 *      This is a version of ip_compute_csum() optimized for IP headers,
 *      which always checksum on 4 octet boundaries.
 */
static __inline__ __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
{
        unsigned int sum, tmp, endaddr;

        __asm__ __volatile__(
                "sub            %0, %0, %0\n\t"
#if XCHAL_HAVE_LOOPS
                "loopgtz        %2, 2f\n\t"
#else
                "beqz           %2, 2f\n\t"
                "slli           %4, %2, 2\n\t"
                "add            %4, %4, %1\n\t"
                "0:\t"
#endif
                "l32i           %3, %1, 0\n\t"
                "add            %0, %0, %3\n\t"
                "bgeu           %0, %3, 1f\n\t"
                "addi           %0, %0, 1\n\t"
                "1:\t"
                "addi           %1, %1, 4\n\t"
#if !XCHAL_HAVE_LOOPS
                "blt            %1, %4, 0b\n\t"
#endif
                "2:\t"
        /* Since the input registers which are loaded with iph and ihl
           are modified, we must also specify them as outputs, or gcc
           will assume they contain their original values. */
                : "=r" (sum), "=r" (iph), "=r" (ihl), "=&r" (tmp),
                  "=&r" (endaddr)
                : "1" (iph), "2" (ihl)
                : "memory");

        return  csum_fold(sum);
}

static __inline__ __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
                                            __u32 len, __u8 proto,
                                            __wsum sum)
{

#ifdef __XTENSA_EL__
        unsigned long len_proto = (len + proto) << 8;
#elif defined(__XTENSA_EB__)
        unsigned long len_proto = len + proto;
#else
# error processor byte order undefined!
#endif
        __asm__("add    %0, %0, %1\n\t"
                "bgeu   %0, %1, 1f\n\t"
                "addi   %0, %0, 1\n\t"
                "1:\t"
                "add    %0, %0, %2\n\t"
                "bgeu   %0, %2, 1f\n\t"
                "addi   %0, %0, 1\n\t"
                "1:\t"
                "add    %0, %0, %3\n\t"
                "bgeu   %0, %3, 1f\n\t"
                "addi   %0, %0, 1\n\t"
                "1:\t"
                : "=r" (sum), "=r" (len_proto)
                : "r" (daddr), "r" (saddr), "1" (len_proto), "0" (sum));
        return sum;
}

/*
 * computes the checksum of the TCP/UDP pseudo-header
 * returns a 16-bit checksum, already complemented
 */
static __inline__ __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
                                            __u32 len, __u8 proto,
                                            __wsum sum)
{
        return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
}

/*
 * this routine is used for miscellaneous IP-like checksums, mainly
 * in icmp.c
 */

static __inline__ __sum16 ip_compute_csum(const void *buff, int len)
{
        return csum_fold (csum_partial(buff, len, 0));
}

#define _HAVE_ARCH_IPV6_CSUM
static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
                                          const struct in6_addr *daddr,
                                          __u32 len, __u8 proto,
                                          __wsum sum)
{
        unsigned int __dummy;
        __asm__("l32i   %1, %2, 0\n\t"
                "add    %0, %0, %1\n\t"
                "bgeu   %0, %1, 1f\n\t"
                "addi   %0, %0, 1\n\t"
                "1:\t"
                "l32i   %1, %2, 4\n\t"
                "add    %0, %0, %1\n\t"
                "bgeu   %0, %1, 1f\n\t"
                "addi   %0, %0, 1\n\t"
                "1:\t"
                "l32i   %1, %2, 8\n\t"
                "add    %0, %0, %1\n\t"
                "bgeu   %0, %1, 1f\n\t"
                "addi   %0, %0, 1\n\t"
                "1:\t"
                "l32i   %1, %2, 12\n\t"
                "add    %0, %0, %1\n\t"
                "bgeu   %0, %1, 1f\n\t"
                "addi   %0, %0, 1\n\t"
                "1:\t"
                "l32i   %1, %3, 0\n\t"
                "add    %0, %0, %1\n\t"
                "bgeu   %0, %1, 1f\n\t"
                "addi   %0, %0, 1\n\t"
                "1:\t"
                "l32i   %1, %3, 4\n\t"
                "add    %0, %0, %1\n\t"
                "bgeu   %0, %1, 1f\n\t"
                "addi   %0, %0, 1\n\t"
                "1:\t"
                "l32i   %1, %3, 8\n\t"
                "add    %0, %0, %1\n\t"
                "bgeu   %0, %1, 1f\n\t"
                "addi   %0, %0, 1\n\t"
                "1:\t"
                "l32i   %1, %3, 12\n\t"
                "add    %0, %0, %1\n\t"
                "bgeu   %0, %1, 1f\n\t"
                "addi   %0, %0, 1\n\t"
                "1:\t"
                "add    %0, %0, %4\n\t"
                "bgeu   %0, %4, 1f\n\t"
                "addi   %0, %0, 1\n\t"
                "1:\t"
                "add    %0, %0, %5\n\t"
                "bgeu   %0, %5, 1f\n\t"
                "addi   %0, %0, 1\n\t"
                "1:\t"
                : "=r" (sum), "=&r" (__dummy)
                : "r" (saddr), "r" (daddr),
                  "r" (htonl(len)), "r" (htonl(proto)), "0" (sum)
                : "memory");

        return csum_fold(sum);
}

/*
 *      Copy and checksum to user
 */
#define HAVE_CSUM_COPY_USER
static __inline__ __wsum csum_and_copy_to_user(const void *src,
                                               void __user *dst, int len)
{
        if (!access_ok(dst, len))
                return 0;
        return csum_partial_copy_generic(src, (__force void *)dst, len);
}
#endif