Synchronize with the implementation from v3.18 tag. This allows us to use a standardized 64 bit ops on architectures that do not natively support 64 bit (example: 32bit ARM)

Signed-off-by: Nishanth Menon nm@ti.com --- include/linux/math64.h | 81 ++++++++++++++++++++++++++++++ lib/div64.c | 132 +++++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 209 insertions(+), 4 deletions(-)

diff --git a/include/linux/math64.h b/include/linux/math64.h index 6d760d7..a10ccbb 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -2,9 +2,13 @@ #define _LINUX_MATH64_H

#include <linux/types.h> +#include <div64.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 * @@ -27,6 +31,15 @@ static inline s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder) }

/** + * 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 */ static inline u64 div64_u64(u64 dividend, u64 divisor) @@ -34,8 +47,19 @@ 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 +72,18 @@ 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 +114,53 @@ 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; +} + +#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 */ + +#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 = ((u64)al * mul) >> shift; + if (ah) + ret += ((u64)ah * mul) << (32 - shift); + + return ret; +} +#endif /* mul_u64_u32_shr */ + +#endif + #endif /* _LINUX_MATH64_H */ diff --git a/lib/div64.c b/lib/div64.c index 795ef0e..9b53faf 100644 --- a/lib/div64.c +++ b/lib/div64.c @@ -9,17 +9,21 @@ * 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(). + * 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/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. */

+#include <common.h> #include <div64.h> -#include <linux/types.h> +#include <linux/math64.h>

-uint32_t __div64_32(uint64_t *n, uint32_t base) +/* 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; @@ -51,3 +55,123 @@ uint32_t __div64_32(uint64_t *n, uint32_t base) *n = res; return rem; } + + +#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; +} +#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; +} +#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.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; +} +#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; +} +#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); +}