summaryrefslogtreecommitdiffstats
path: root/arch/loongarch/lib/memmove.S
blob: 7dc76d1484b6a84252a76c5f334a69d252d24465 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
/* SPDX-License-Identifier: GPL-2.0 */
/*
 * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
 */

#include <linux/export.h>
#include <asm/alternative-asm.h>
#include <asm/asm.h>
#include <asm/asmmacro.h>
#include <asm/cpu.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)