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
|
/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* or http://www.opensolaris.org/os/licensing.
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
* Copyright (c) 1988, 2010, Oracle and/or its affiliates. All rights reserved.
*/
.file "memcpy.s"
/*
* memcpy(s1, s2, len)
*
* Copy s2 to s1, always copy n bytes.
* Note: this does not work for overlapped copies, bcopy() does
*
* Fast assembler language version of the following C-program for memcpy
* which represents the `standard' for the C-library.
*
* void *
* memcpy(void *s, const void *s0, size_t n)
* {
* if (n != 0) {
* char *s1 = s;
* const char *s2 = s0;
* do {
* *s1++ = *s2++;
* } while (--n != 0);
* }
* return (s);
* }
*/
#include "SYS.h"
ANSI_PRAGMA_WEAK(memcpy,function)
ENTRY(memcpy)
ENTRY(__align_cpy_1)
st %o0, [%sp + 68] ! save des address for return val
cmp %o2, 17 ! for small counts copy bytes
bleu .dbytecp
andcc %o1, 3, %o5 ! is src word aligned
bz .aldst
cmp %o5, 2 ! is src half-word aligned
be .s2algn
cmp %o5, 3 ! src is byte aligned
.s1algn:ldub [%o1], %o3 ! move 1 or 3 bytes to align it
inc 1, %o1
stb %o3, [%o0] ! move a byte to align src
inc 1, %o0
bne .s2algn
dec %o2
b .ald ! now go align dest
andcc %o0, 3, %o5
.s2algn:lduh [%o1], %o3 ! know src is 2 byte alinged
inc 2, %o1
srl %o3, 8, %o4
stb %o4, [%o0] ! have to do bytes,
stb %o3, [%o0 + 1] ! don't know dst alingment
inc 2, %o0
dec 2, %o2
.aldst: andcc %o0, 3, %o5 ! align the destination address
.ald: bz .w4cp
cmp %o5, 2
bz .w2cp
cmp %o5, 3
.w3cp: ld [%o1], %o4
inc 4, %o1
srl %o4, 24, %o5
stb %o5, [%o0]
bne .w1cp
inc %o0
dec 1, %o2
andn %o2, 3, %o3 ! o3 is aligned word count
dec 4, %o3 ! avoid reading beyond tail of src
sub %o1, %o0, %o1 ! o1 gets the difference
1: sll %o4, 8, %g1 ! save residual bytes
ld [%o1+%o0], %o4
deccc 4, %o3
srl %o4, 24, %o5 ! merge with residual
or %o5, %g1, %g1
st %g1, [%o0]
bnz 1b
inc 4, %o0
sub %o1, 3, %o1 ! used one byte of last word read
and %o2, 3, %o2
b 7f
inc 4, %o2
.w1cp: srl %o4, 8, %o5
sth %o5, [%o0]
inc 2, %o0
dec 3, %o2
andn %o2, 3, %o3 ! o3 is aligned word count
dec 4, %o3 ! avoid reading beyond tail of src
sub %o1, %o0, %o1 ! o1 gets the difference
2: sll %o4, 24, %g1 ! save residual bytes
ld [%o1+%o0], %o4
deccc 4, %o3
srl %o4, 8, %o5 ! merge with residual
or %o5, %g1, %g1
st %g1, [%o0]
bnz 2b
inc 4, %o0
sub %o1, 1, %o1 ! used three bytes of last word read
and %o2, 3, %o2
b 7f
inc 4, %o2
.w2cp: ld [%o1], %o4
inc 4, %o1
srl %o4, 16, %o5
sth %o5, [%o0]
inc 2, %o0
dec 2, %o2
andn %o2, 3, %o3 ! o3 is aligned word count
dec 4, %o3 ! avoid reading beyond tail of src
sub %o1, %o0, %o1 ! o1 gets the difference
3: sll %o4, 16, %g1 ! save residual bytes
ld [%o1+%o0], %o4
deccc 4, %o3
srl %o4, 16, %o5 ! merge with residual
or %o5, %g1, %g1
st %g1, [%o0]
bnz 3b
inc 4, %o0
sub %o1, 2, %o1 ! used two bytes of last word read
and %o2, 3, %o2
b 7f
inc 4, %o2
.w4cp: andn %o2, 3, %o3 ! o3 is aligned word count
sub %o1, %o0, %o1 ! o1 gets the difference
1: ld [%o1+%o0], %o4 ! read from address
deccc 4, %o3 ! decrement count
st %o4, [%o0] ! write at destination address
bgu 1b
inc 4, %o0 ! increment to address
b 7f
and %o2, 3, %o2 ! number of leftover bytes, if any
!
! differenced byte copy, works with any alignment
!
.dbytecp:
b 7f
sub %o1, %o0, %o1 ! o1 gets the difference
4: stb %o4, [%o0] ! write to address
inc %o0 ! inc to address
7: deccc %o2 ! decrement count
bgeu,a 4b ! loop till done
ldub [%o1+%o0], %o4 ! read from address
retl
ld [%sp + 68], %o0 ! return s1, destination address
SET_SIZE(memcpy)
|
