OpenCloudOS-Kernel/arch/loongarch/lib/memset.S

163 lines
2.3 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2020-2022 Loongson Technology Corporation Limited
*/
#include <asm/alternative-asm.h>
#include <asm/asm.h>
#include <asm/asmmacro.h>
#include <asm/cpu.h>
#include <asm/export.h>
#include <asm/regdef.h>
.macro fill_to_64 r0
bstrins.d \r0, \r0, 15, 8
bstrins.d \r0, \r0, 31, 16
bstrins.d \r0, \r0, 63, 32
.endm
SYM_FUNC_START(memset)
/*
* Some CPUs support hardware unaligned access
*/
ALTERNATIVE "b __memset_generic", \
"b __memset_fast", CPU_FEATURE_UAL
SYM_FUNC_END(memset)
_ASM_NOKPROBE(memset)
EXPORT_SYMBOL(memset)
/*
* void *__memset_generic(void *s, int c, size_t n)
*
* a0: s
* a1: c
* a2: n
*/
SYM_FUNC_START(__memset_generic)
move a3, a0
beqz a2, 2f
1: st.b a1, a0, 0
addi.d a0, a0, 1
addi.d a2, a2, -1
bgt a2, zero, 1b
2: move a0, a3
jr ra
SYM_FUNC_END(__memset_generic)
_ASM_NOKPROBE(__memset_generic)
/*
* void *__memset_fast(void *s, int c, size_t n)
*
* a0: s
* a1: c
* a2: n
*/
SYM_FUNC_START(__memset_fast)
/* fill a1 to 64 bits */
fill_to_64 a1
sltui t0, a2, 9
bnez t0, .Lsmall
add.d a2, a0, a2
st.d a1, a0, 0
/* align up address */
addi.d a3, a0, 8
bstrins.d a3, zero, 2, 0
addi.d a4, a2, -64
bgeu a3, a4, .Llt64
/* set 64 bytes at a time */
.Lloop64:
st.d a1, a3, 0
st.d a1, a3, 8
st.d a1, a3, 16
st.d a1, a3, 24
st.d a1, a3, 32
st.d a1, a3, 40
st.d a1, a3, 48
st.d a1, a3, 56
addi.d a3, a3, 64
bltu a3, a4, .Lloop64
/* set the remaining bytes */
.Llt64:
addi.d a4, a2, -32
bgeu a3, a4, .Llt32
st.d a1, a3, 0
st.d a1, a3, 8
st.d a1, a3, 16
st.d a1, a3, 24
addi.d a3, a3, 32
.Llt32:
addi.d a4, a2, -16
bgeu a3, a4, .Llt16
st.d a1, a3, 0
st.d a1, a3, 8
addi.d a3, a3, 16
.Llt16:
addi.d a4, a2, -8
bgeu a3, a4, .Llt8
st.d a1, a3, 0
.Llt8:
st.d a1, a2, -8
/* return */
jr ra
.align 4
.Lsmall:
pcaddi t0, 4
slli.d a2, a2, 4
add.d t0, t0, a2
jr t0
.align 4
0: jr ra
.align 4
1: st.b a1, a0, 0
jr ra
.align 4
2: st.h a1, a0, 0
jr ra
.align 4
3: st.h a1, a0, 0
st.b a1, a0, 2
jr ra
.align 4
4: st.w a1, a0, 0
jr ra
.align 4
5: st.w a1, a0, 0
st.b a1, a0, 4
jr ra
.align 4
6: st.w a1, a0, 0
st.h a1, a0, 4
jr ra
.align 4
7: st.w a1, a0, 0
st.w a1, a0, 3
jr ra
.align 4
8: st.d a1, a0, 0
jr ra
SYM_FUNC_END(__memset_fast)
_ASM_NOKPROBE(__memset_fast)