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
|
/*
* Copyright (C) 2013 ARM Ltd.
* Copyright (C) 2013 Linaro.
*
* This code is based on glibc cortex strings work originally authored by Linaro
* and re-licensed under GPLv2 for the Linux kernel. The original code can
* be found @
*
* http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
* files/head:/src/aarch64/
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* This program 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 General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
#include <asm/cache.h>
/*
* Move a buffer from src to test (alignment handled by the hardware).
* If dest <= src, call memcpy, otherwise copy in reverse order.
*
* Parameters:
* x0 - dest
* x1 - src
* x2 - n
* Returns:
* x0 - dest
*/
dstin .req x0
src .req x1
count .req x2
tmp1 .req x3
tmp1w .req w3
tmp2 .req x4
tmp2w .req w4
tmp3 .req x5
tmp3w .req w5
dst .req x6
A_l .req x7
A_h .req x8
B_l .req x9
B_h .req x10
C_l .req x11
C_h .req x12
D_l .req x13
D_h .req x14
ENTRY(__memmove)
WEAK(memmove)
cmp dstin, src
b.lo __memcpy
add tmp1, src, count
cmp dstin, tmp1
b.hs __memcpy /* No overlap. */
add dst, dstin, count
add src, src, count
cmp count, #16
b.lo .Ltail15 /*probably non-alignment accesses.*/
ands tmp2, src, #15 /* Bytes to reach alignment. */
b.eq .LSrcAligned
sub count, count, tmp2
/*
* process the aligned offset length to make the src aligned firstly.
* those extra instructions' cost is acceptable. It also make the
* coming accesses are based on aligned address.
*/
tbz tmp2, #0, 1f
ldrb tmp1w, [src, #-1]!
strb tmp1w, [dst, #-1]!
1:
tbz tmp2, #1, 2f
ldrh tmp1w, [src, #-2]!
strh tmp1w, [dst, #-2]!
2:
tbz tmp2, #2, 3f
ldr tmp1w, [src, #-4]!
str tmp1w, [dst, #-4]!
3:
tbz tmp2, #3, .LSrcAligned
ldr tmp1, [src, #-8]!
str tmp1, [dst, #-8]!
.LSrcAligned:
cmp count, #64
b.ge .Lcpy_over64
/*
* Deal with small copies quickly by dropping straight into the
* exit block.
*/
.Ltail63:
/*
* Copy up to 48 bytes of data. At this point we only need the
* bottom 6 bits of count to be accurate.
*/
ands tmp1, count, #0x30
b.eq .Ltail15
cmp tmp1w, #0x20
b.eq 1f
b.lt 2f
ldp A_l, A_h, [src, #-16]!
stp A_l, A_h, [dst, #-16]!
1:
ldp A_l, A_h, [src, #-16]!
stp A_l, A_h, [dst, #-16]!
2:
ldp A_l, A_h, [src, #-16]!
stp A_l, A_h, [dst, #-16]!
.Ltail15:
tbz count, #3, 1f
ldr tmp1, [src, #-8]!
str tmp1, [dst, #-8]!
1:
tbz count, #2, 2f
ldr tmp1w, [src, #-4]!
str tmp1w, [dst, #-4]!
2:
tbz count, #1, 3f
ldrh tmp1w, [src, #-2]!
strh tmp1w, [dst, #-2]!
3:
tbz count, #0, .Lexitfunc
ldrb tmp1w, [src, #-1]
strb tmp1w, [dst, #-1]
.Lexitfunc:
ret
.Lcpy_over64:
subs count, count, #128
b.ge .Lcpy_body_large
/*
* Less than 128 bytes to copy, so handle 64 bytes here and then jump
* to the tail.
*/
ldp A_l, A_h, [src, #-16]
stp A_l, A_h, [dst, #-16]
ldp B_l, B_h, [src, #-32]
ldp C_l, C_h, [src, #-48]
stp B_l, B_h, [dst, #-32]
stp C_l, C_h, [dst, #-48]
ldp D_l, D_h, [src, #-64]!
stp D_l, D_h, [dst, #-64]!
tst count, #0x3f
b.ne .Ltail63
ret
/*
* Critical loop. Start at a new cache line boundary. Assuming
* 64 bytes per line this ensures the entire loop is in one line.
*/
.p2align L1_CACHE_SHIFT
.Lcpy_body_large:
/* pre-load 64 bytes data. */
ldp A_l, A_h, [src, #-16]
ldp B_l, B_h, [src, #-32]
ldp C_l, C_h, [src, #-48]
ldp D_l, D_h, [src, #-64]!
1:
/*
* interlace the load of next 64 bytes data block with store of the last
* loaded 64 bytes data.
*/
stp A_l, A_h, [dst, #-16]
ldp A_l, A_h, [src, #-16]
stp B_l, B_h, [dst, #-32]
ldp B_l, B_h, [src, #-32]
stp C_l, C_h, [dst, #-48]
ldp C_l, C_h, [src, #-48]
stp D_l, D_h, [dst, #-64]!
ldp D_l, D_h, [src, #-64]!
subs count, count, #64
b.ge 1b
stp A_l, A_h, [dst, #-16]
stp B_l, B_h, [dst, #-32]
stp C_l, C_h, [dst, #-48]
stp D_l, D_h, [dst, #-64]!
tst count, #0x3f
b.ne .Ltail63
ret
ENDPIPROC(memmove)
ENDPROC(__memmove)
|
