linux_dsm_epyc7002/lib/div64.c
Brian Behlendorf 658716d19f div64_u64(): improve precision on 32bit platforms
The current implementation of div64_u64 for 32bit systems returns an
approximately correct result when the divisor exceeds 32bits.  Since doing
64bit division using 32bit hardware is a long since solved problem we just
use one of the existing proven methods.

Additionally, add a div64_s64 function to correctly handle doing signed
64bit division.

Addresses https://bugzilla.redhat.com/show_bug.cgi?id=616105

Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Cc: Ben Woodard <bwoodard@llnl.gov>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Mark Grondona <mgrondona@llnl.gov>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2010-10-26 16:52:19 -07:00

143 lines
3.1 KiB
C

/*
* Copyright (C) 2003 Bernardo Innocenti <bernie@develer.com>
*
* Based on former do_div() implementation from asm-parisc/div64.h:
* Copyright (C) 1999 Hewlett-Packard Co
* Copyright (C) 1999 David Mosberger-Tang <davidm@hpl.hp.com>
*
*
* Generic C version of 64bit/32bit division and modulo, with
* 64bit result and 32bit remainder.
*
* The fast case for (n>>32 == 0) is handled inline by do_div().
*
* Code generated for this function might be very inefficient
* for some CPUs. __div64_32() can be overridden by linking arch-specific
* assembly versions such as arch/ppc/lib/div64.S and arch/sh/lib/div64.S.
*/
#include <linux/module.h>
#include <linux/math64.h>
/* Not needed on 64bit architectures */
#if BITS_PER_LONG == 32
uint32_t __attribute__((weak)) __div64_32(uint64_t *n, uint32_t base)
{
uint64_t rem = *n;
uint64_t b = base;
uint64_t res, d = 1;
uint32_t high = rem >> 32;
/* Reduce the thing a bit first */
res = 0;
if (high >= base) {
high /= base;
res = (uint64_t) high << 32;
rem -= (uint64_t) (high*base) << 32;
}
while ((int64_t)b > 0 && b < rem) {
b = b+b;
d = d+d;
}
do {
if (rem >= b) {
rem -= b;
res += d;
}
b >>= 1;
d >>= 1;
} while (d);
*n = res;
return rem;
}
EXPORT_SYMBOL(__div64_32);
#ifndef div_s64_rem
s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder)
{
u64 quotient;
if (dividend < 0) {
quotient = div_u64_rem(-dividend, abs(divisor), (u32 *)remainder);
*remainder = -*remainder;
if (divisor > 0)
quotient = -quotient;
} else {
quotient = div_u64_rem(dividend, abs(divisor), (u32 *)remainder);
if (divisor < 0)
quotient = -quotient;
}
return quotient;
}
EXPORT_SYMBOL(div_s64_rem);
#endif
/**
* div64_u64 - unsigned 64bit divide with 64bit divisor
* @dividend: 64bit dividend
* @divisor: 64bit divisor
*
* This implementation is a modified version of the algorithm proposed
* by the book 'Hacker's Delight'. The original source and full proof
* can be found here and is available for use without restriction.
*
* 'http://www.hackersdelight.org/HDcode/newCode/divDouble.c'
*/
#ifndef div64_u64
u64 div64_u64(u64 dividend, u64 divisor)
{
u32 high = divisor >> 32;
u64 quot;
if (high == 0) {
quot = div_u64(dividend, divisor);
} else {
int n = 1 + fls(high);
quot = div_u64(dividend >> n, divisor >> n);
if (quot != 0)
quot--;
if ((dividend - quot * divisor) >= divisor)
quot++;
}
return quot;
}
EXPORT_SYMBOL(div64_u64);
#endif
/**
* div64_s64 - signed 64bit divide with 64bit divisor
* @dividend: 64bit dividend
* @divisor: 64bit divisor
*/
#ifndef div64_s64
s64 div64_s64(s64 dividend, s64 divisor)
{
s64 quot, t;
quot = div64_u64(abs64(dividend), abs64(divisor));
t = (dividend ^ divisor) >> 63;
return (quot ^ t) - t;
}
EXPORT_SYMBOL(div64_s64);
#endif
#endif /* BITS_PER_LONG == 32 */
/*
* Iterative div/mod for use when dividend is not expected to be much
* bigger than divisor.
*/
u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder)
{
return __iter_div_u64_rem(dividend, divisor, remainder);
}
EXPORT_SYMBOL(iter_div_u64_rem);