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
|
// Derived from Inferno's libkern/memmove-386.s (adapted for amd64)
// http://code.google.com/p/inferno-os/source/browse/libkern/memmove-386.s
//
// Copyright © 1994-1999 Lucent Technologies Inc. All rights reserved.
// Revisions Copyright © 2000-2007 Vita Nuova Holdings Limited (www.vitanuova.com). All rights reserved.
// Portions Copyright 2009 The Go Authors. All rights reserved.
//
// Permission is hereby granted, free of charge, to any person obtaining a copy
// of this software and associated documentation files (the "Software"), to deal
// in the Software without restriction, including without limitation the rights
// to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
// copies of the Software, and to permit persons to whom the Software is
// furnished to do so, subject to the following conditions:
//
// The above copyright notice and this permission notice shall be included in
// all copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
// AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
// OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
// THE SOFTWARE.
#include "textflag.h"
// void runtime·memmove(void*, void*, uintptr)
TEXT runtime·memmove(SB), NOSPLIT, $0-24
MOVQ to+0(FP), DI
MOVQ from+8(FP), SI
MOVQ n+16(FP), BX
// REP instructions have a high startup cost, so we handle small sizes
// with some straightline code. The REP MOVSQ instruction is really fast
// for large sizes. The cutover is approximately 1K.
tail:
TESTQ BX, BX
JEQ move_0
CMPQ BX, $2
JBE move_1or2
CMPQ BX, $4
JBE move_3or4
CMPQ BX, $8
JBE move_5through8
CMPQ BX, $16
JBE move_9through16
/*
* check and set for backwards
*/
CMPQ SI, DI
JLS back
/*
* forward copy loop
*/
forward:
MOVQ BX, CX
SHRQ $3, CX
ANDQ $7, BX
REP; MOVSQ
JMP tail
back:
/*
* check overlap
*/
MOVQ SI, CX
ADDQ BX, CX
CMPQ CX, DI
JLS forward
/*
* whole thing backwards has
* adjusted addresses
*/
ADDQ BX, DI
ADDQ BX, SI
STD
/*
* copy
*/
MOVQ BX, CX
SHRQ $3, CX
ANDQ $7, BX
SUBQ $8, DI
SUBQ $8, SI
REP; MOVSQ
CLD
ADDQ $8, DI
ADDQ $8, SI
SUBQ BX, DI
SUBQ BX, SI
JMP tail
move_1or2:
MOVB (SI), AX
MOVB -1(SI)(BX*1), CX
MOVB AX, (DI)
MOVB CX, -1(DI)(BX*1)
RET
move_0:
RET
move_3or4:
MOVW (SI), AX
MOVW -2(SI)(BX*1), CX
MOVW AX, (DI)
MOVW CX, -2(DI)(BX*1)
RET
move_5through8:
MOVL (SI), AX
MOVL -4(SI)(BX*1), CX
MOVL AX, (DI)
MOVL CX, -4(DI)(BX*1)
RET
move_9through16:
MOVQ (SI), AX
MOVQ -8(SI)(BX*1), CX
MOVQ AX, (DI)
MOVQ CX, -8(DI)(BX*1)
RET
|
