summaryrefslogtreecommitdiffstats
path: root/arch/loongarch/lib/memcpy.S
blob: fa1148878d2b9d06ccdfcf6f2c14fd302fd14114 (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
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
/* 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>

.section .noinstr.text, "ax"

SYM_FUNC_START(memcpy)
	/*
	 * Some CPUs support hardware unaligned access
	 */
	ALTERNATIVE	"b __memcpy_generic", \
			"b __memcpy_fast", CPU_FEATURE_UAL
SYM_FUNC_END(memcpy)
SYM_FUNC_ALIAS(__memcpy, memcpy)

EXPORT_SYMBOL(memcpy)
EXPORT_SYMBOL(__memcpy)

_ASM_NOKPROBE(memcpy)
_ASM_NOKPROBE(__memcpy)

/*
 * void *__memcpy_generic(void *dst, const void *src, size_t n)
 *
 * a0: dst
 * a1: src
 * a2: n
 */
SYM_FUNC_START(__memcpy_generic)
	move	a3, a0
	beqz	a2, 2f

1:	ld.b	t0, a1, 0
	st.b	t0, a0, 0
	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(__memcpy_generic)
_ASM_NOKPROBE(__memcpy_generic)

	.align	5
SYM_FUNC_START_NOALIGN(__memcpy_small)
	pcaddi	t0, 8
	slli.d	a2, a2, 5
	add.d	t0, t0, a2
	jr	t0

	.align	5
0:	jr	ra

	.align	5
1:	ld.b	t0, a1, 0
	st.b	t0, a0, 0
	jr	ra

	.align	5
2:	ld.h	t0, a1, 0
	st.h	t0, a0, 0
	jr	ra

	.align	5
3:	ld.h	t0, a1, 0
	ld.b	t1, a1, 2
	st.h	t0, a0, 0
	st.b	t1, a0, 2
	jr	ra

	.align	5
4:	ld.w	t0, a1, 0
	st.w	t0, a0, 0
	jr	ra

	.align	5
5:	ld.w	t0, a1, 0
	ld.b	t1, a1, 4
	st.w	t0, a0, 0
	st.b	t1, a0, 4
	jr	ra

	.align	5
6:	ld.w	t0, a1, 0
	ld.h	t1, a1, 4
	st.w	t0, a0, 0
	st.h	t1, a0, 4
	jr	ra

	.align	5
7:	ld.w	t0, a1, 0
	ld.w	t1, a1, 3
	st.w	t0, a0, 0
	st.w	t1, a0, 3
	jr	ra

	.align	5
8:	ld.d	t0, a1, 0
	st.d	t0, a0, 0
	jr	ra
SYM_FUNC_END(__memcpy_small)
_ASM_NOKPROBE(__memcpy_small)

/*
 * void *__memcpy_fast(void *dst, const void *src, size_t n)
 *
 * a0: dst
 * a1: src
 * a2: n
 */
SYM_FUNC_START(__memcpy_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, a0, 7
	sub.d	t0, zero, t1
	addi.d	t0, t0, 8
	add.d	a1, a1, t0
	add.d	a5, a0, t0

	addi.d	a4, a3, -64
	bgeu	a1, a4, .Llt64

	/* copy 64 bytes at a time */
.Lloop64:
	ld.d	t0, a1, 0
	ld.d	t1, a1, 8
	ld.d	t2, a1, 16
	ld.d	t3, a1, 24
	ld.d	t4, a1, 32
	ld.d	t5, a1, 40
	ld.d	t6, a1, 48
	ld.d	t7, a1, 56
	addi.d	a1, a1, 64
	st.d	t0, a5, 0
	st.d	t1, a5, 8
	st.d	t2, a5, 16
	st.d	t3, a5, 24
	st.d	t4, a5, 32
	st.d	t5, a5, 40
	st.d	t6, a5, 48
	st.d	t7, a5, 56
	addi.d	a5, a5, 64
	bltu	a1, a4, .Lloop64

	/* copy the remaining bytes */
.Llt64:
	addi.d	a4, a3, -32
	bgeu	a1, a4, .Llt32
	ld.d	t0, a1, 0
	ld.d	t1, a1, 8
	ld.d	t2, a1, 16
	ld.d	t3, a1, 24
	addi.d	a1, a1, 32
	st.d	t0, a5, 0
	st.d	t1, a5, 8
	st.d	t2, a5, 16
	st.d	t3, a5, 24
	addi.d	a5, a5, 32

.Llt32:
	addi.d	a4, a3, -16
	bgeu	a1, a4, .Llt16
	ld.d	t0, a1, 0
	ld.d	t1, a1, 8
	addi.d	a1, a1, 16
	st.d	t0, a5, 0
	st.d	t1, a5, 8
	addi.d	a5, a5, 16

.Llt16:
	addi.d	a4, a3, -8
	bgeu	a1, a4, .Llt8
	ld.d	t0, a1, 0
	st.d	t0, a5, 0

.Llt8:
	st.d	a6, a0, 0
	st.d	a7, a2, -8

	/* return */
	jr	ra
SYM_FUNC_END(__memcpy_fast)
_ASM_NOKPROBE(__memcpy_fast)