142 lines
2.4 KiB
ArmAsm
142 lines
2.4 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>
|
|
|
|
SYM_FUNC_START(memmove)
|
|
blt a0, a1, memcpy /* dst < src, memcpy */
|
|
blt a1, a0, rmemcpy /* src < dst, rmemcpy */
|
|
jr ra /* dst == src, return */
|
|
SYM_FUNC_END(memmove)
|
|
_ASM_NOKPROBE(memmove)
|
|
|
|
EXPORT_SYMBOL(memmove)
|
|
|
|
SYM_FUNC_START(rmemcpy)
|
|
/*
|
|
* Some CPUs support hardware unaligned access
|
|
*/
|
|
ALTERNATIVE "b __rmemcpy_generic", \
|
|
"b __rmemcpy_fast", CPU_FEATURE_UAL
|
|
SYM_FUNC_END(rmemcpy)
|
|
_ASM_NOKPROBE(rmemcpy)
|
|
|
|
/*
|
|
* void *__rmemcpy_generic(void *dst, const void *src, size_t n)
|
|
*
|
|
* a0: dst
|
|
* a1: src
|
|
* a2: n
|
|
*/
|
|
SYM_FUNC_START(__rmemcpy_generic)
|
|
move a3, a0
|
|
beqz a2, 2f
|
|
|
|
add.d a0, a0, a2
|
|
add.d a1, a1, a2
|
|
|
|
1: ld.b t0, a1, -1
|
|
st.b t0, a0, -1
|
|
addi.d a0, a0, -1
|
|
addi.d a1, a1, -1
|
|
addi.d a2, a2, -1
|
|
bgt a2, zero, 1b
|
|
|
|
2: move a0, a3
|
|
jr ra
|
|
SYM_FUNC_END(__rmemcpy_generic)
|
|
_ASM_NOKPROBE(__rmemcpy_generic)
|
|
|
|
/*
|
|
* void *__rmemcpy_fast(void *dst, const void *src, size_t n)
|
|
*
|
|
* a0: dst
|
|
* a1: src
|
|
* a2: n
|
|
*/
|
|
SYM_FUNC_START(__rmemcpy_fast)
|
|
sltui t0, a2, 9
|
|
bnez t0, __memcpy_small
|
|
|
|
add.d a3, a1, a2
|
|
add.d a2, a0, a2
|
|
ld.d a6, a1, 0
|
|
ld.d a7, a3, -8
|
|
|
|
/* align up destination address */
|
|
andi t1, a2, 7
|
|
sub.d a3, a3, t1
|
|
sub.d a5, a2, t1
|
|
|
|
addi.d a4, a1, 64
|
|
bgeu a4, a3, .Llt64
|
|
|
|
/* copy 64 bytes at a time */
|
|
.Lloop64:
|
|
ld.d t0, a3, -8
|
|
ld.d t1, a3, -16
|
|
ld.d t2, a3, -24
|
|
ld.d t3, a3, -32
|
|
ld.d t4, a3, -40
|
|
ld.d t5, a3, -48
|
|
ld.d t6, a3, -56
|
|
ld.d t7, a3, -64
|
|
addi.d a3, a3, -64
|
|
st.d t0, a5, -8
|
|
st.d t1, a5, -16
|
|
st.d t2, a5, -24
|
|
st.d t3, a5, -32
|
|
st.d t4, a5, -40
|
|
st.d t5, a5, -48
|
|
st.d t6, a5, -56
|
|
st.d t7, a5, -64
|
|
addi.d a5, a5, -64
|
|
bltu a4, a3, .Lloop64
|
|
|
|
/* copy the remaining bytes */
|
|
.Llt64:
|
|
addi.d a4, a1, 32
|
|
bgeu a4, a3, .Llt32
|
|
ld.d t0, a3, -8
|
|
ld.d t1, a3, -16
|
|
ld.d t2, a3, -24
|
|
ld.d t3, a3, -32
|
|
addi.d a3, a3, -32
|
|
st.d t0, a5, -8
|
|
st.d t1, a5, -16
|
|
st.d t2, a5, -24
|
|
st.d t3, a5, -32
|
|
addi.d a5, a5, -32
|
|
|
|
.Llt32:
|
|
addi.d a4, a1, 16
|
|
bgeu a4, a3, .Llt16
|
|
ld.d t0, a3, -8
|
|
ld.d t1, a3, -16
|
|
addi.d a3, a3, -16
|
|
st.d t0, a5, -8
|
|
st.d t1, a5, -16
|
|
addi.d a5, a5, -16
|
|
|
|
.Llt16:
|
|
addi.d a4, a1, 8
|
|
bgeu a4, a3, .Llt8
|
|
ld.d t0, a3, -8
|
|
st.d t0, a5, -8
|
|
|
|
.Llt8:
|
|
st.d a6, a0, 0
|
|
st.d a7, a2, -8
|
|
|
|
/* return */
|
|
jr ra
|
|
SYM_FUNC_END(__rmemcpy_fast)
|
|
_ASM_NOKPROBE(__rmemcpy_fast)
|