d0fdc20b04
DCACHE_WORD_ACCESS uses the word-at-a-time API for optimised string
comparisons in the vfs layer.
This patch implements support for load_unaligned_zeropad in much the
same way as has been done for arm64.
Here is the test program and step:
$ cat tt.c
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
#define ITERATIONS 1000000
#define PATH "123456781234567812345678123456781"
int main(void)
{
unsigned long i;
struct stat buf;
for (i = 0; i < ITERATIONS; i++)
stat(PATH, &buf);
return 0;
}
$ gcc -O2 tt.c
$ touch 123456781234567812345678123456781
$ time ./a.out
Per my test on T-HEAD C910 platforms, the above test performance is
improved by about 7.5%.
Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
Link: https://lore.kernel.org/r/20231225044207.3821-3-jszhang@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
76 lines
1.7 KiB
C
76 lines
1.7 KiB
C
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* Copyright (C) 2012 Regents of the University of California
|
|
*
|
|
* Derived from arch/x86/include/asm/word-at-a-time.h
|
|
*/
|
|
|
|
#ifndef _ASM_RISCV_WORD_AT_A_TIME_H
|
|
#define _ASM_RISCV_WORD_AT_A_TIME_H
|
|
|
|
|
|
#include <asm/asm-extable.h>
|
|
#include <linux/kernel.h>
|
|
|
|
struct word_at_a_time {
|
|
const unsigned long one_bits, high_bits;
|
|
};
|
|
|
|
#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
|
|
|
|
static inline unsigned long has_zero(unsigned long val,
|
|
unsigned long *bits, const struct word_at_a_time *c)
|
|
{
|
|
unsigned long mask = ((val - c->one_bits) & ~val) & c->high_bits;
|
|
*bits = mask;
|
|
return mask;
|
|
}
|
|
|
|
static inline unsigned long prep_zero_mask(unsigned long val,
|
|
unsigned long bits, const struct word_at_a_time *c)
|
|
{
|
|
return bits;
|
|
}
|
|
|
|
static inline unsigned long create_zero_mask(unsigned long bits)
|
|
{
|
|
bits = (bits - 1) & ~bits;
|
|
return bits >> 7;
|
|
}
|
|
|
|
static inline unsigned long find_zero(unsigned long mask)
|
|
{
|
|
return fls64(mask) >> 3;
|
|
}
|
|
|
|
/* The mask we created is directly usable as a bytemask */
|
|
#define zero_bytemask(mask) (mask)
|
|
|
|
#ifdef CONFIG_DCACHE_WORD_ACCESS
|
|
|
|
/*
|
|
* Load an unaligned word from kernel space.
|
|
*
|
|
* In the (very unlikely) case of the word being a page-crosser
|
|
* and the next page not being mapped, take the exception and
|
|
* return zeroes in the non-existing part.
|
|
*/
|
|
static inline unsigned long load_unaligned_zeropad(const void *addr)
|
|
{
|
|
unsigned long ret;
|
|
|
|
/* Load word from unaligned pointer addr */
|
|
asm(
|
|
"1: " REG_L " %0, %2\n"
|
|
"2:\n"
|
|
_ASM_EXTABLE_LOAD_UNALIGNED_ZEROPAD(1b, 2b, %0, %1)
|
|
: "=&r" (ret)
|
|
: "r" (addr), "m" (*(unsigned long *)addr));
|
|
|
|
return ret;
|
|
}
|
|
|
|
#endif /* CONFIG_DCACHE_WORD_ACCESS */
|
|
|
|
#endif /* _ASM_RISCV_WORD_AT_A_TIME_H */
|