Mirrors/u-boot
2
0
Fork 0
mirror of https://github.com/AsahiLinux/u-boot synced 2024-11-24 21:54:01 +00:00
Code Issues Projects Releases Packages Wiki Activity

lib: div64: sync with Linux

Browse source 
Sync with Linux commit ad0376eb1483b ("Merge tag 'edac_for_4.11_2'").

Signed-off-by: Peng Fan <peng.fan@nxp.com>
Cc: Tom Rini <trini@konsulko.com>
This commit is contained in:
Peng Fan 2017-04-10 13:39:48 +08:00 committed by Tom Rini
parent 6823e6fe66
commit 0342e335ba
3 changed files with 508 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

205
include/div64.h
View file

@ -4,13 +4,16 @@
* Copyright (C) 2003 Bernardo Innocenti <bernie@develer.com>
* Based on former asm-ppc/div64.h and asm-m68knommu/div64.h
*
* Optimization for constant divisors on 32-bit machines:
* Copyright (C) 2006-2015 Nicolas Pitre
*
* The semantics of do_div() are:
*
* uint32_t do_div(uint64_t *n, uint32_t base)
* {
* uint32_t remainder = *n % base;
* *n = *n / base;
* return remainder;
* uint32_t remainder = *n % base;
* *n = *n / base;
* return remainder;
* }
*
* NOTE: macro parameter n is evaluated multiple times,
@ -18,8 +21,182 @@
*/
#include <linux/types.h>
#include <linux/compiler.h>
#if BITS_PER_LONG == 64
# define do_div(n,base) ({ \
uint32_t __base = (base); \
uint32_t __rem; \
__rem = ((uint64_t)(n)) % __base; \
(n) = ((uint64_t)(n)) / __base; \
__rem; \
})
#elif BITS_PER_LONG == 32
#include <linux/log2.h>
/*
* If the divisor happens to be constant, we determine the appropriate
* inverse at compile time to turn the division into a few inline
* multiplications which ought to be much faster. And yet only if compiling
* with a sufficiently recent gcc version to perform proper 64-bit constant
* propagation.
*
* (It is unfortunate that gcc doesn't perform all this internally.)
*/
#ifndef __div64_const32_is_OK
#define __div64_const32_is_OK (__GNUC__ >= 4)
#endif
#define __div64_const32(n, ___b) \
({ \
/* \
* Multiplication by reciprocal of b: n / b = n * (p / b) / p \
* \
* We rely on the fact that most of this code gets optimized \
* away at compile time due to constant propagation and only \
* a few multiplication instructions should remain. \
* Hence this monstrous macro (static inline doesn't always \
* do the trick here). \
*/ \
uint64_t ___res, ___x, ___t, ___m, ___n = (n); \
uint32_t ___p, ___bias; \
\
/* determine MSB of b */ \
___p = 1 << ilog2(___b); \
\
/* compute m = ((p << 64) + b - 1) / b */ \
___m = (~0ULL / ___b) * ___p; \
___m += (((~0ULL % ___b + 1) * ___p) + ___b - 1) / ___b; \
\
/* one less than the dividend with highest result */ \
___x = ~0ULL / ___b * ___b - 1; \
\
/* test our ___m with res = m * x / (p << 64) */ \
___res = ((___m & 0xffffffff) * (___x & 0xffffffff)) >> 32; \
___t = ___res += (___m & 0xffffffff) * (___x >> 32); \
___res += (___x & 0xffffffff) * (___m >> 32); \
___t = (___res < ___t) ? (1ULL << 32) : 0; \
___res = (___res >> 32) + ___t; \
___res += (___m >> 32) * (___x >> 32); \
___res /= ___p; \
\
/* Now sanitize and optimize what we've got. */ \
if (~0ULL % (___b / (___b & -___b)) == 0) { \
/* special case, can be simplified to ... */ \
___n /= (___b & -___b); \
___m = ~0ULL / (___b / (___b & -___b)); \
___p = 1; \
___bias = 1; \
} else if (___res != ___x / ___b) { \
/* \
* We can't get away without a bias to compensate \
* for bit truncation errors. To avoid it we'd need an \
* additional bit to represent m which would overflow \
* a 64-bit variable. \
* \
* Instead we do m = p / b and n / b = (n * m + m) / p. \
*/ \
___bias = 1; \
/* Compute m = (p << 64) / b */ \
___m = (~0ULL / ___b) * ___p; \
___m += ((~0ULL % ___b + 1) * ___p) / ___b; \
} else { \
/* \
* Reduce m / p, and try to clear bit 31 of m when \
* possible, otherwise that'll need extra overflow \
* handling later. \
*/ \
uint32_t ___bits = -(___m & -___m); \
___bits |= ___m >> 32; \
___bits = (~___bits) << 1; \
/* \
* If ___bits == 0 then setting bit 31 is unavoidable. \
* Simply apply the maximum possible reduction in that \
* case. Otherwise the MSB of ___bits indicates the \
* best reduction we should apply. \
*/ \
if (!___bits) { \
___p /= (___m & -___m); \
___m /= (___m & -___m); \
} else { \
___p >>= ilog2(___bits); \
___m >>= ilog2(___bits); \
} \
/* No bias needed. */ \
___bias = 0; \
} \
\
/* \
* Now we have a combination of 2 conditions: \
* \
* 1) whether or not we need to apply a bias, and \
* \
* 2) whether or not there might be an overflow in the cross \
* product determined by (___m & ((1 << 63) | (1 << 31))). \
* \
* Select the best way to do (m_bias + m * n) / (1 << 64). \
* From now on there will be actual runtime code generated. \
*/ \
___res = __arch_xprod_64(___m, ___n, ___bias); \
\
___res /= ___p; \
})
#ifndef __arch_xprod_64
/*
* Default C implementation for __arch_xprod_64()
*
* Prototype: uint64_t __arch_xprod_64(const uint64_t m, uint64_t n, bool bias)
* Semantic: retval = ((bias ? m : 0) + m * n) >> 64
*
* The product is a 128-bit value, scaled down to 64 bits.
* Assuming constant propagation to optimize away unused conditional code.
* Architectures may provide their own optimized assembly implementation.
*/
static inline uint64_t __arch_xprod_64(const uint64_t m, uint64_t n, bool bias)
{
uint32_t m_lo = m;
uint32_t m_hi = m >> 32;
uint32_t n_lo = n;
uint32_t n_hi = n >> 32;
uint64_t res, tmp;
if (!bias) {
res = ((uint64_t)m_lo * n_lo) >> 32;
} else if (!(m & ((1ULL << 63) | (1ULL << 31)))) {
/* there can't be any overflow here */
res = (m + (uint64_t)m_lo * n_lo) >> 32;
} else {
res = m + (uint64_t)m_lo * n_lo;
tmp = (res < m) ? (1ULL << 32) : 0;
res = (res >> 32) + tmp;
}
if (!(m & ((1ULL << 63) | (1ULL << 31)))) {
/* there can't be any overflow here */
res += (uint64_t)m_lo * n_hi;
res += (uint64_t)m_hi * n_lo;
res >>= 32;
} else {
tmp = res += (uint64_t)m_lo * n_hi;
res += (uint64_t)m_hi * n_lo;
tmp = (res < tmp) ? (1ULL << 32) : 0;
res = (res >> 32) + tmp;
}
res += (uint64_t)m_hi * n_hi;
return res;
}
#endif
#ifndef __div64_32
extern uint32_t __div64_32(uint64_t *dividend, uint32_t divisor);
#endif
/* The unnecessary pointer compare is there
* to check for type safety (n must be 64bit)
@ -28,14 +205,32 @@ extern uint32_t __div64_32(uint64_t *dividend, uint32_t divisor);
uint32_t __base = (base); \
uint32_t __rem; \
(void)(((typeof((n)) *)0) == ((uint64_t *)0)); \
if (((n) >> 32) == 0) { \
if (__builtin_constant_p(__base) && \
is_power_of_2(__base)) { \
__rem = (n) & (__base - 1); \
(n) >>= ilog2(__base); \
} else if (__div64_const32_is_OK && \
__builtin_constant_p(__base) && \
__base != 0) { \
uint32_t __res_lo, __n_lo = (n); \
(n) = __div64_const32(n, __base); \
/* the remainder can be computed with 32-bit regs */ \
__res_lo = (n); \
__rem = __n_lo - __res_lo * __base; \
} else if (likely(((n) >> 32) == 0)) { \
__rem = (uint32_t)(n) % __base; \
(n) = (uint32_t)(n) / __base; \
} else \
} else \
__rem = __div64_32(&(n), __base); \
__rem; \
})
#else /* BITS_PER_LONG == ?? */
# error do_div() does not yet support the C64
#endif /* BITS_PER_LONG */
/* Wrapper for do_div(). Doesn't modify dividend and returns
* the result, not reminder.
*/

172
include/linux/math64.h
View file

@ -1,10 +1,15 @@
#ifndef _LINUX_MATH64_H
#define _LINUX_MATH64_H
#include <div64.h>
#include <linux/bitops.h>
#include <linux/types.h>
#if BITS_PER_LONG == 64
#define div64_long(x, y) div64_s64((x), (y))
#define div64_ul(x, y) div64_u64((x), (y))
/**
* div_u64_rem - unsigned 64bit divide with 32bit divisor with remainder
*
@ -26,6 +31,15 @@ static inline s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder)
return dividend / divisor;
}
/**
* div64_u64_rem - unsigned 64bit divide with 64bit divisor and remainder
*/
static inline u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder)
{
*remainder = dividend % divisor;
return dividend / divisor;
}
/**
* div64_u64 - unsigned 64bit divide with 64bit divisor
*/
@ -34,8 +48,19 @@ static inline u64 div64_u64(u64 dividend, u64 divisor)
return dividend / divisor;
}
/**
* div64_s64 - signed 64bit divide with 64bit divisor
*/
static inline s64 div64_s64(s64 dividend, s64 divisor)
{
return dividend / divisor;
}
#elif BITS_PER_LONG == 32
#define div64_long(x, y) div_s64((x), (y))
#define div64_ul(x, y) div_u64((x), (y))
#ifndef div_u64_rem
static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder)
{
@ -48,10 +73,18 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder)
extern s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder);
#endif
#ifndef div64_u64_rem
extern u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder);
#endif
#ifndef div64_u64
extern u64 div64_u64(u64 dividend, u64 divisor);
#endif
#ifndef div64_s64
extern s64 div64_s64(s64 dividend, s64 divisor);
#endif
#endif /* BITS_PER_LONG */
/**
@ -82,4 +115,143 @@ static inline s64 div_s64(s64 dividend, s32 divisor)
u32 iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder);
static __always_inline u32
__iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder)
{
u32 ret = 0;
while (dividend >= divisor) {
/* The following asm() prevents the compiler from
optimising this loop into a modulo operation. */
asm("" : "+rm"(dividend));
dividend -= divisor;
ret++;
}
*remainder = dividend;
return ret;
}
#ifndef mul_u32_u32
/*
* Many a GCC version messes this up and generates a 64x64 mult :-(
*/
static inline u64 mul_u32_u32(u32 a, u32 b)
{
return (u64)a * b;
}
#endif
#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
#ifndef mul_u64_u32_shr
static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift)
{
return (u64)(((unsigned __int128)a * mul) >> shift);
}
#endif /* mul_u64_u32_shr */
#ifndef mul_u64_u64_shr
static inline u64 mul_u64_u64_shr(u64 a, u64 mul, unsigned int shift)
{
return (u64)(((unsigned __int128)a * mul) >> shift);
}
#endif /* mul_u64_u64_shr */
#else
#ifndef mul_u64_u32_shr
static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift)
{
u32 ah, al;
u64 ret;
al = a;
ah = a >> 32;
ret = mul_u32_u32(al, mul) >> shift;
if (ah)
ret += mul_u32_u32(ah, mul) << (32 - shift);
return ret;
}
#endif /* mul_u64_u32_shr */
#ifndef mul_u64_u64_shr
static inline u64 mul_u64_u64_shr(u64 a, u64 b, unsigned int shift)
{
union {
u64 ll;
struct {
#ifdef __BIG_ENDIAN
u32 high, low;
#else
u32 low, high;
#endif
} l;
} rl, rm, rn, rh, a0, b0;
u64 c;
a0.ll = a;
b0.ll = b;
rl.ll = mul_u32_u32(a0.l.low, b0.l.low);
rm.ll = mul_u32_u32(a0.l.low, b0.l.high);
rn.ll = mul_u32_u32(a0.l.high, b0.l.low);
rh.ll = mul_u32_u32(a0.l.high, b0.l.high);
/*
* Each of these lines computes a 64-bit intermediate result into "c",
* starting at bits 32-95. The low 32-bits go into the result of the
* multiplication, the high 32-bits are carried into the next step.
*/
rl.l.high = c = (u64)rl.l.high + rm.l.low + rn.l.low;
rh.l.low = c = (c >> 32) + rm.l.high + rn.l.high + rh.l.low;
rh.l.high = (c >> 32) + rh.l.high;
/*
* The 128-bit result of the multiplication is in rl.ll and rh.ll,
* shift it right and throw away the high part of the result.
*/
if (shift == 0)
return rl.ll;
if (shift < 64)
return (rl.ll >> shift) | (rh.ll << (64 - shift));
return rh.ll >> (shift & 63);
}
#endif /* mul_u64_u64_shr */
#endif
#ifndef mul_u64_u32_div
static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor)
{
union {
u64 ll;
struct {
#ifdef __BIG_ENDIAN
u32 high, low;
#else
u32 low, high;
#endif
} l;
} u, rl, rh;
u.ll = a;
rl.ll = mul_u32_u32(u.l.low, mul);
rh.ll = mul_u32_u32(u.l.high, mul) + rl.l.high;
/* Bits 32-63 of the result will be in rh.l.low. */
rl.l.high = do_div(rh.ll, divisor);
/* Bits 0-31 of the result will be in rl.l.low. */
do_div(rl.ll, divisor);
rl.l.high = rh.l.low;
return rl.ll;
}
#endif /* mul_u64_u32_div */
#endif /* _LINUX_MATH64_H */

141
lib/div64.c
View file

@ -13,14 +13,19 @@
*
* 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/powerpc/lib/div64.S and arch/sh/lib/div64.S.
* assembly versions such as arch/ppc/lib/div64.S and arch/sh/lib/div64.S
* or by defining a preprocessor macro in arch/include/asm/div64.h.
*/
#include <div64.h>
#include <linux/types.h>
#include <linux/compiler.h>
#include <linux/compat.h>
#include <linux/kernel.h>
#include <linux/math64.h>
uint32_t notrace __div64_32(uint64_t *n, uint32_t base)
/* Not needed on 64bit architectures */
#if BITS_PER_LONG == 32
#ifndef __div64_32
uint32_t __attribute__((weak)) __div64_32(uint64_t *n, uint32_t base)
{
uint64_t rem = *n;
uint64_t b = base;
@ -52,3 +57,129 @@ uint32_t notrace __div64_32(uint64_t *n, uint32_t base)
*n = res;
return rem;
}
EXPORT_SYMBOL(__div64_32);
#endif
#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_rem - unsigned 64bit divide with 64bit divisor and remainder
* @dividend: 64bit dividend
* @divisor: 64bit divisor
* @remainder: 64bit remainder
*
* This implementation is a comparable to algorithm used by div64_u64.
* But this operation, which includes math for calculating the remainder,
* is kept distinct to avoid slowing down the div64_u64 operation on 32bit
* systems.
*/
#ifndef div64_u64_rem
u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder)
{
u32 high = divisor >> 32;
u64 quot;
if (high == 0) {
u32 rem32;
quot = div_u64_rem(dividend, divisor, &rem32);
*remainder = rem32;
} else {
int n = 1 + fls(high);
quot = div_u64(dividend >> n, divisor >> n);
if (quot != 0)
quot--;
*remainder = dividend - quot * divisor;
if (*remainder >= divisor) {
quot++;
*remainder -= divisor;
}
}
return quot;
}
EXPORT_SYMBOL(div64_u64_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/hdcodetxt/divDouble.c.txt'
*/
#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(abs(dividend), abs(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);