summaryrefslogtreecommitdiffstats
path: root/utils/hwstub/stmp/memmove.S
blob: d8cab048be2af8d4e8e4f24fad1b41abe6f7b479 (plain)
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
/***************************************************************************
 *             __________               __   ___.
 *   Open      \______   \ ____   ____ |  | _\_ |__   _______  ___
 *   Source     |       _//  _ \_/ ___\|  |/ /| __ \ /  _ \  \/  /
 *   Jukebox    |    |   (  <_> )  \___|    < | \_\ (  <_> > <  <
 *   Firmware   |____|_  /\____/ \___  >__|_ \|___  /\____/__/\_ \
 *                     \/            \/     \/    \/            \/
 * $Id$
 *
 * Copyright (C) 2006 Free Software Foundation, Inc.
 * This file was originally part of the GNU C Library
 * Contributed to glibc by MontaVista Software, Inc. (written by Nicolas Pitre)
 * Adapted for Rockbox by Daniel Ankers
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version 2
 * of the License, or (at your option) any later version.
 *
 * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
 * KIND, either express or implied.
 *
 ****************************************************************************/

#include "config.h"

/*
 * 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 *memmove(void *dest, const void *src, size_t n);
 *
 * Note:
 *
 * If the memory regions don't overlap, we simply branch to memcpy which is
 * normally a bit faster. Otherwise the copy is done going downwards.
 */

    .section    .icode,"ax",%progbits

    .align      2
    .global     memmove
    .type       memmove,%function

memmove:

        subs    ip, r0, r1
        cmphi   r2, ip
        bls memcpy

        stmfd   sp!, {r0, r4, lr}
        add r1, r1, r2
        add r0, r0, r2
        subs    r2, r2, #4
        blt 8f
        ands    ip, r0, #3
        bne 9f
        ands    ip, r1, #3
        bne 10f

1:      subs    r2, r2, #(28)
        stmfd   sp!, {r5 - r8}
        blt 5f

2:
3:
4:      ldmdb   r1!, {r3, r4, r5, r6, r7, r8, ip, lr}
        subs    r2, r2, #32
        stmdb   r0!, {r3, r4, r5, r6, r7, r8, ip, lr}
        bge 3b

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]!

7:      ldmfd   sp!, {r5 - r8}

8:      movs    r2, r2, lsl #31
        ldrneb  r3, [r1, #-1]!
        ldrcsb  r4, [r1, #-1]!
        ldrcsb  ip, [r1, #-1]
        strneb  r3, [r0, #-1]!
        strcsb  r4, [r0, #-1]!
        strcsb  ip, [r0, #-1]
        ldmpc   regs="r0, r4"

9:      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 r3, [r1, #0]
        beq 17f
        blt 18f


        .macro  backward_copy_shift push pull

        subs    r2, r2, #28
        blt 14f

11:     stmfd   sp!, {r5 - r9}

12:
13:     ldmdb   r1!, {r7, r8, r9, ip}
        mov     lr, r3, push #\push
        subs    r2, r2, #32
        ldmdb   r1!, {r3, r4, r5, r6}
        orr     lr, lr, ip, pull #\pull
        mov     ip, ip, push #\push
        orr     ip, ip, r9, pull #\pull
        mov     r9, r9, push #\push
        orr     r9, r9, r8, pull #\pull
        mov     r8, r8, push #\push
        orr     r8, r8, r7, pull #\pull
        mov     r7, r7, push #\push
        orr     r7, r7, r6, pull #\pull
        mov     r6, r6, push #\push
        orr     r6, r6, r5, pull #\pull
        mov     r5, r5, push #\push
        orr     r5, r5, r4, pull #\pull
        mov     r4, r4, push #\push
        orr     r4, r4, r3, pull #\pull
        stmdb   r0!, {r4 - r9, ip, lr}
        bge 12b

        ldmfd   sp!, {r5 - r9}

14:     ands    ip, r2, #28
        beq 16f

15:     mov     lr, r3, push #\push
        ldr r3, [r1, #-4]!
        subs    ip, ip, #4
        orr lr, lr, r3, pull #\pull
        str lr, [r0, #-4]!
        bgt 15b

16:     add r1, r1, #(\pull / 8)
        b   8b

        .endm


        backward_copy_shift push=8  pull=24

17:     backward_copy_shift push=16 pull=16

18:     backward_copy_shift push=24 pull=8