mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-27 09:05:12 +07:00
668b448466
In the target code I have a do_div(x, PAGE_SIZE). The x86-64 version of it was doing a shift and a mask which is clever. The 32bit version of it had a div operation in it which made me think. After digging I noticed that x86 has an optimized version of it. This patch adds this shift and mask optimization if base is constant so we don't have any runtime "checking" overhead since most users use a power of ten. Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/1322649814-544-1-git-send-email-bigeasy@linutronix.de Signed-off-by: Ingo Molnar <mingo@elte.hu>
67 lines
1.5 KiB
C
67 lines
1.5 KiB
C
#ifndef _ASM_X86_DIV64_H
|
|
#define _ASM_X86_DIV64_H
|
|
|
|
#ifdef CONFIG_X86_32
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/log2.h>
|
|
|
|
/*
|
|
* do_div() is NOT a C function. It wants to return
|
|
* two values (the quotient and the remainder), but
|
|
* since that doesn't work very well in C, what it
|
|
* does is:
|
|
*
|
|
* - modifies the 64-bit dividend _in_place_
|
|
* - returns the 32-bit remainder
|
|
*
|
|
* This ends up being the most efficient "calling
|
|
* convention" on x86.
|
|
*/
|
|
#define do_div(n, base) \
|
|
({ \
|
|
unsigned long __upper, __low, __high, __mod, __base; \
|
|
__base = (base); \
|
|
if (__builtin_constant_p(__base) && is_power_of_2(__base)) { \
|
|
__mod = n & (__base - 1); \
|
|
n >>= ilog2(__base); \
|
|
} else { \
|
|
asm("" : "=a" (__low), "=d" (__high) : "A" (n));\
|
|
__upper = __high; \
|
|
if (__high) { \
|
|
__upper = __high % (__base); \
|
|
__high = __high / (__base); \
|
|
} \
|
|
asm("divl %2" : "=a" (__low), "=d" (__mod) \
|
|
: "rm" (__base), "0" (__low), "1" (__upper)); \
|
|
asm("" : "=A" (n) : "a" (__low), "d" (__high)); \
|
|
} \
|
|
__mod; \
|
|
})
|
|
|
|
static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder)
|
|
{
|
|
union {
|
|
u64 v64;
|
|
u32 v32[2];
|
|
} d = { dividend };
|
|
u32 upper;
|
|
|
|
upper = d.v32[1];
|
|
d.v32[1] = 0;
|
|
if (upper >= divisor) {
|
|
d.v32[1] = upper / divisor;
|
|
upper %= divisor;
|
|
}
|
|
asm ("divl %2" : "=a" (d.v32[0]), "=d" (*remainder) :
|
|
"rm" (divisor), "0" (d.v32[0]), "1" (upper));
|
|
return d.v64;
|
|
}
|
|
#define div_u64_rem div_u64_rem
|
|
|
|
#else
|
|
# include <asm-generic/div64.h>
|
|
#endif /* CONFIG_X86_32 */
|
|
|
|
#endif /* _ASM_X86_DIV64_H */
|