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
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
|
/* Copyright (C) 2006, 2009 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by MontaVista Software, Inc. (written by Nicolas Pitre)
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C Library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with the GNU C Library. If not, see
<http://www.gnu.org/licenses/>. */
#include <sysdep.h>
/*
* Data preload for architectures that support it (ARM V5TE and above)
*/
#if (!defined (__ARM_ARCH_2__) && !defined (__ARM_ARCH_3__) \
&& !defined (__ARM_ARCH_3M__) && !defined (__ARM_ARCH_4__) \
&& !defined (__ARM_ARCH_4T__) && !defined (__ARM_ARCH_5__) \
&& !defined (__ARM_ARCH_5T__))
#define PLD(code...) code
#else
#define PLD(code...)
#endif
/*
* This can be used to enable code to cacheline align the source pointer.
* Experiments on tested architectures (StrongARM and XScale) didn't show
* this a worthwhile thing to do. That might be different in the future.
*/
//#define CALGN(code...) code
#define CALGN(code...)
/*
* Endian independent macros for shifting bytes within registers.
*/
#ifndef __ARMEB__
#define pull lsr
#define push lsl
#else
#define pull lsl
#define push lsr
#endif
.text
/* Prototype: void *memcpy(void *dest, const void *src, size_t n); */
ENTRY(memcpy)
stmfd sp!, {r0, r4, lr}
cfi_adjust_cfa_offset (12)
cfi_rel_offset (r4, 4)
cfi_rel_offset (lr, 8)
cfi_remember_state
subs r2, r2, #4
blt 8f
ands ip, r0, #3
PLD( pld [r1, #0] )
bne 9f
ands ip, r1, #3
bne 10f
1: subs r2, r2, #(28)
stmfd sp!, {r5 - r8}
cfi_adjust_cfa_offset (16)
cfi_rel_offset (r5, 0)
cfi_rel_offset (r6, 4)
cfi_rel_offset (r7, 8)
cfi_rel_offset (r8, 12)
blt 5f
CALGN( ands ip, r1, #31 )
CALGN( rsb r3, ip, #32 )
CALGN( sbcnes r4, r3, r2 ) @ C is always set here
CALGN( bcs 2f )
CALGN( adr r4, 6f )
CALGN( subs r2, r2, r3 ) @ C gets set
CALGN( add pc, r4, ip )
PLD( pld [r1, #0] )
2: PLD( subs r2, r2, #96 )
PLD( pld [r1, #28] )
PLD( blt 4f )
PLD( pld [r1, #60] )
PLD( pld [r1, #92] )
3: PLD( pld [r1, #124] )
4: ldmia r1!, {r3, r4, r5, r6, r7, r8, ip, lr}
subs r2, r2, #32
stmia r0!, {r3, r4, r5, r6, r7, r8, ip, lr}
bge 3b
PLD( cmn r2, #96 )
PLD( bge 4b )
5: ands ip, r2, #28
rsb ip, ip, #32
addne pc, pc, ip @ C is always clear here
b 7f
6: nop
ldr r3, [r1], #4
ldr r4, [r1], #4
ldr r5, [r1], #4
ldr r6, [r1], #4
ldr r7, [r1], #4
ldr r8, [r1], #4
ldr lr, [r1], #4
add pc, pc, ip
nop
nop
str r3, [r0], #4
str r4, [r0], #4
str r5, [r0], #4
str r6, [r0], #4
str r7, [r0], #4
str r8, [r0], #4
str lr, [r0], #4
CALGN( bcs 2b )
7: ldmfd sp!, {r5 - r8}
cfi_adjust_cfa_offset (-16)
cfi_restore (r5)
cfi_restore (r6)
cfi_restore (r7)
cfi_restore (r8)
8: movs r2, r2, lsl #31
ldrneb r3, [r1], #1
ldrcsb r4, [r1], #1
ldrcsb ip, [r1]
strneb r3, [r0], #1
strcsb r4, [r0], #1
strcsb ip, [r0]
#if defined (__ARM_ARCH_4T__) && defined(__THUMB_INTERWORK__)
ldmfd sp!, {r0, r4, lr}
cfi_adjust_cfa_offset (-12)
cfi_restore (r4)
cfi_restore (lr)
bx lr
#else
ldmfd sp!, {r0, r4, pc}
#endif
cfi_restore_state
9: rsb ip, ip, #4
cmp ip, #2
ldrgtb r3, [r1], #1
ldrgeb r4, [r1], #1
ldrb lr, [r1], #1
strgtb r3, [r0], #1
strgeb r4, [r0], #1
subs r2, r2, ip
strb lr, [r0], #1
blt 8b
ands ip, r1, #3
beq 1b
10: bic r1, r1, #3
cmp ip, #2
ldr lr, [r1], #4
beq 17f
bgt 18f
.macro forward_copy_shift pull push
subs r2, r2, #28
blt 14f
CALGN( ands ip, r1, #31 )
CALGN( rsb ip, ip, #32 )
CALGN( sbcnes r4, ip, r2 ) @ C is always set here
CALGN( subcc r2, r2, ip )
CALGN( bcc 15f )
11: stmfd sp!, {r5 - r9}
cfi_adjust_cfa_offset (20)
cfi_rel_offset (r5, 0)
cfi_rel_offset (r6, 4)
cfi_rel_offset (r7, 8)
cfi_rel_offset (r8, 12)
cfi_rel_offset (r9, 16)
PLD( pld [r1, #0] )
PLD( subs r2, r2, #96 )
PLD( pld [r1, #28] )
PLD( blt 13f )
PLD( pld [r1, #60] )
PLD( pld [r1, #92] )
12: PLD( pld [r1, #124] )
13: ldmia r1!, {r4, r5, r6, r7}
mov r3, lr, pull #\pull
subs r2, r2, #32
ldmia r1!, {r8, r9, ip, lr}
orr r3, r3, r4, push #\push
mov r4, r4, pull #\pull
orr r4, r4, r5, push #\push
mov r5, r5, pull #\pull
orr r5, r5, r6, push #\push
mov r6, r6, pull #\pull
orr r6, r6, r7, push #\push
mov r7, r7, pull #\pull
orr r7, r7, r8, push #\push
mov r8, r8, pull #\pull
orr r8, r8, r9, push #\push
mov r9, r9, pull #\pull
orr r9, r9, ip, push #\push
mov ip, ip, pull #\pull
orr ip, ip, lr, push #\push
stmia r0!, {r3, r4, r5, r6, r7, r8, r9, ip}
bge 12b
PLD( cmn r2, #96 )
PLD( bge 13b )
ldmfd sp!, {r5 - r9}
cfi_adjust_cfa_offset (-20)
cfi_restore (r5)
cfi_restore (r6)
cfi_restore (r7)
cfi_restore (r8)
cfi_restore (r9)
14: ands ip, r2, #28
beq 16f
15: mov r3, lr, pull #\pull
ldr lr, [r1], #4
subs ip, ip, #4
orr r3, r3, lr, push #\push
str r3, [r0], #4
bgt 15b
CALGN( cmp r2, #0 )
CALGN( bge 11b )
16: sub r1, r1, #(\push / 8)
b 8b
.endm
forward_copy_shift pull=8 push=24
17: forward_copy_shift pull=16 push=16
18: forward_copy_shift pull=24 push=8
END(memcpy)
libc_hidden_builtin_def (memcpy)
|
