mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-27 13:45:13 +07:00
db4e919d9a
On x86_64 we can do a u64 * u64 -> u128 widening multiply followed by a u128 / u64 -> u64 division to implement a sane version of mul_u64_u32_div(). Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Ingo Molnar <mingo@kernel.org>
92 lines
2.0 KiB
C
92 lines
2.0 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#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
|
|
|
|
static inline u64 mul_u32_u32(u32 a, u32 b)
|
|
{
|
|
u32 high, low;
|
|
|
|
asm ("mull %[b]" : "=a" (low), "=d" (high)
|
|
: [a] "a" (a), [b] "rm" (b) );
|
|
|
|
return low | ((u64)high) << 32;
|
|
}
|
|
#define mul_u32_u32 mul_u32_u32
|
|
|
|
#else
|
|
# include <asm-generic/div64.h>
|
|
|
|
static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 div)
|
|
{
|
|
u64 q;
|
|
|
|
asm ("mulq %2; divq %3" : "=a" (q)
|
|
: "a" (a), "rm" ((u64)mul), "rm" ((u64)div)
|
|
: "rdx");
|
|
|
|
return q;
|
|
}
|
|
#define mul_u64_u32_div mul_u64_u32_div
|
|
|
|
#endif /* CONFIG_X86_32 */
|
|
|
|
#endif /* _ASM_X86_DIV64_H */
|