mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-26 15:30:54 +07:00
b9a50f7490
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 for ARM CPUs with native support for unaligned memory accesses (v6+) when running little-endian. Reviewed-by: Nicolas Pitre <nico@linaro.org> Signed-off-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
97 lines
2.0 KiB
C
97 lines
2.0 KiB
C
#ifndef __ASM_ARM_WORD_AT_A_TIME_H
|
|
#define __ASM_ARM_WORD_AT_A_TIME_H
|
|
|
|
#ifndef __ARMEB__
|
|
|
|
/*
|
|
* Little-endian word-at-a-time zero byte handling.
|
|
* Heavily based on the x86 algorithm.
|
|
*/
|
|
#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 a, unsigned long *bits,
|
|
const struct word_at_a_time *c)
|
|
{
|
|
unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits;
|
|
*bits = mask;
|
|
return mask;
|
|
}
|
|
|
|
#define prep_zero_mask(a, bits, c) (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)
|
|
{
|
|
unsigned long ret;
|
|
|
|
#if __LINUX_ARM_ARCH__ >= 5
|
|
/* We have clz available. */
|
|
ret = fls(mask) >> 3;
|
|
#else
|
|
/* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
|
|
ret = (0x0ff0001 + mask) >> 23;
|
|
/* Fix the 1 for 00 case */
|
|
ret &= mask;
|
|
#endif
|
|
|
|
return ret;
|
|
}
|
|
|
|
#ifdef CONFIG_DCACHE_WORD_ACCESS
|
|
|
|
#define zero_bytemask(mask) (mask)
|
|
|
|
/*
|
|
* 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, offset;
|
|
|
|
/* Load word from unaligned pointer addr */
|
|
asm(
|
|
"1: ldr %0, [%2]\n"
|
|
"2:\n"
|
|
" .pushsection .fixup,\"ax\"\n"
|
|
" .align 2\n"
|
|
"3: and %1, %2, #0x3\n"
|
|
" bic %2, %2, #0x3\n"
|
|
" ldr %0, [%2]\n"
|
|
" lsl %1, %1, #0x3\n"
|
|
" lsr %0, %0, %1\n"
|
|
" b 2b\n"
|
|
" .popsection\n"
|
|
" .pushsection __ex_table,\"a\"\n"
|
|
" .align 3\n"
|
|
" .long 1b, 3b\n"
|
|
" .popsection"
|
|
: "=&r" (ret), "=&r" (offset)
|
|
: "r" (addr), "Qo" (*(unsigned long *)addr));
|
|
|
|
return ret;
|
|
}
|
|
|
|
|
|
#endif /* DCACHE_WORD_ACCESS */
|
|
|
|
#else /* __ARMEB__ */
|
|
#include <asm-generic/word-at-a-time.h>
|
|
#endif
|
|
|
|
#endif /* __ASM_ARM_WORD_AT_A_TIME_H */
|