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
|
/*
* linux/arch/arm/lib/memset.S
*
* Copyright (C) 1995-2000 Russell King
*
* 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.
*
* ASM optimised string functions
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
.text
.align 5
.word 0
1: subs r2, r2, #4 @ 1 do we have enough
blt 5f @ 1 bytes to align with?
cmp r3, #2 @ 1
it lt
strltb r1, [r0], #1 @ 1
it le
strleb r1, [r0], #1 @ 1
strb r1, [r0], #1 @ 1
add r2, r2, r3 @ 1 (r2 = r2 - (4 - r3))
/*
* The pointer is now aligned and the length is adjusted. Try doing the
* memset again.
*/
ENTRY(memset)
ands r3, r0, #3 @ 1 unaligned?
bne 1b @ 1
/*
* we know that the pointer in r0 is aligned to a word boundary.
*/
orr r1, r1, r1, lsl #8
orr r1, r1, r1, lsl #16
mov r3, r1
cmp r2, #16
blt 4f
#if ! CALGN(1)+0
/*
* We need an extra register for this loop - save the return address and
* use the LR
*/
str lr, [sp, #-4]!
mov ip, r1
mov lr, r1
2: subs r2, r2, #64
itttt ge
stmgeia r0!, {r1, r3, ip, lr} @ 64 bytes at a time.
stmgeia r0!, {r1, r3, ip, lr}
stmgeia r0!, {r1, r3, ip, lr}
stmgeia r0!, {r1, r3, ip, lr}
bgt 2b
it eq
ldmeqfd sp!, {pc} @ Now <64 bytes to go.
/*
* No need to correct the count; we're only testing bits from now on
*/
tst r2, #32
itt ne
stmneia r0!, {r1, r3, ip, lr}
stmneia r0!, {r1, r3, ip, lr}
tst r2, #16
it ne
stmneia r0!, {r1, r3, ip, lr}
ldr lr, [sp], #4
#else
/*
* This version aligns the destination pointer in order to write
* whole cache lines at once.
*/
stmfd sp!, {r4-r7, lr}
mov r4, r1
mov r5, r1
mov r6, r1
mov r7, r1
mov ip, r1
mov lr, r1
cmp r2, #96
tstgt r0, #31
ble 3f
and ip, r0, #31
rsb ip, ip, #32
sub r2, r2, ip
movs ip, ip, lsl #(32 - 4)
stmcsia r0!, {r4, r5, r6, r7}
stmmiia r0!, {r4, r5}
tst ip, #(1 << 30)
mov ip, r1
strne r1, [r0], #4
3: subs r2, r2, #64
stmgeia r0!, {r1, r3-r7, ip, lr}
stmgeia r0!, {r1, r3-r7, ip, lr}
bgt 3b
ldmeqfd sp!, {r4-r7, pc}
tst r2, #32
stmneia r0!, {r1, r3-r7, ip, lr}
tst r2, #16
stmneia r0!, {r4-r7}
ldmfd sp!, {r4-r7, lr}
#endif
4: tst r2, #8
it ne
stmneia r0!, {r1, r3}
tst r2, #4
it ne
strne r1, [r0], #4
/*
* When we get here, we've got less than 4 bytes to zero. We
* may have an unaligned pointer as well.
*/
5: tst r2, #2
itt ne
strneb r1, [r0], #1
strneb r1, [r0], #1
tst r2, #1
it ne
strneb r1, [r0], #1
mov pc, lr
ENDPROC(memset)
|
