Gitiles
Code Review Sign In
review.evervolv.com / android_kernel_htc_msm8960 / ac6c2bc592b90c7f140fc87c49e21bc82376e2aa / . / arch / arm / lib / memmove.S
blob: ef7fddc14ac989bd6dca30f204cadeb92317b133 [file] [log] [blame]
Nicolas Pitre75494232005-11-01 19:52:23 +0000[diff] [blame]1/*
2 * linux/arch/arm/lib/memmove.S
3 *
4 * Author: Nicolas Pitre
5 * Created: Sep 28, 2005
6 * Copyright: (C) MontaVista Software Inc.
7 *
8 * This program is free software; you can redistribute it and/or modify
9 * it under the terms of the GNU General Public License version 2 as
10 * published by the Free Software Foundation.
11 */
12
13#include <linux/linkage.h>
14#include <asm/assembler.h>
15
16/*
17 * This can be used to enable code to cacheline align the source pointer.
18 * Experiments on tested architectures (StrongARM and XScale) didn't show
19 * this a worthwhile thing to do. That might be different in the future.
20 */
21//#define CALGN(code...) code
22#define CALGN(code...)
23
24 .text
25
26/*
27 * Prototype: void *memmove(void *dest, const void *src, size_t n);
28 *
29 * Note:
30 *
31 * If the memory regions don't overlap, we simply branch to memcpy which is
32 * normally a bit faster. Otherwise the copy is done going downwards. This
33 * is a transposition of the code from copy_template.S but with the copy
34 * occurring in the opposite direction.
35 */
36
37ENTRY(memmove)
38
39 subs ip, r0, r1
40 cmphi r2, ip
41 bls memcpy
42
43 stmfd sp!, {r0, r4, lr}
44 add r1, r1, r2
45 add r0, r0, r2
46 subs r2, r2, #4
47 blt 8f
48 ands ip, r0, #3
49 PLD( pld [r1, #-4] )
50 bne 9f
51 ands ip, r1, #3
52 bne 10f
53
541: subs r2, r2, #(28)
55 stmfd sp!, {r5 - r8}
56 blt 5f
57
58 CALGN( ands ip, r1, #31 )
59 CALGN( sbcnes r4, ip, r2 ) @ C is always set here
60 CALGN( bcs 2f )
61 CALGN( adr r4, 6f )
62 CALGN( subs r2, r2, ip ) @ C is set here
63 CALGN( add pc, r4, ip )
64
65 PLD( pld [r1, #-4] )
662: PLD( subs r2, r2, #96 )
67 PLD( pld [r1, #-32] )
68 PLD( blt 4f )
69 PLD( pld [r1, #-64] )
70 PLD( pld [r1, #-96] )
71
723: PLD( pld [r1, #-128] )
734: ldmdb r1!, {r3, r4, r5, r6, r7, r8, ip, lr}
74 subs r2, r2, #32
75 stmdb r0!, {r3, r4, r5, r6, r7, r8, ip, lr}
76 bge 3b
77 PLD( cmn r2, #96 )
78 PLD( bge 4b )
79
805: ands ip, r2, #28
81 rsb ip, ip, #32
82 addne pc, pc, ip @ C is always clear here
83 b 7f
846: nop
85 ldr r3, [r1, #-4]!
86 ldr r4, [r1, #-4]!
87 ldr r5, [r1, #-4]!
88 ldr r6, [r1, #-4]!
89 ldr r7, [r1, #-4]!
90 ldr r8, [r1, #-4]!
91 ldr lr, [r1, #-4]!
92
93 add pc, pc, ip
94 nop
95 nop
96 str r3, [r0, #-4]!
97 str r4, [r0, #-4]!
98 str r5, [r0, #-4]!
99 str r6, [r0, #-4]!
100 str r7, [r0, #-4]!
101 str r8, [r0, #-4]!
102 str lr, [r0, #-4]!
103
104 CALGN( bcs 2b )
105
1067: ldmfd sp!, {r5 - r8}
107
1088: movs r2, r2, lsl #31
109 ldrneb r3, [r1, #-1]!
110 ldrcsb r4, [r1, #-1]!
111 ldrcsb ip, [r1, #-1]
112 strneb r3, [r0, #-1]!
113 strcsb r4, [r0, #-1]!
114 strcsb ip, [r0, #-1]
115 ldmfd sp!, {r0, r4, pc}
116
1179: cmp ip, #2
118 ldrgtb r3, [r1, #-1]!
119 ldrgeb r4, [r1, #-1]!
120 ldrb lr, [r1, #-1]!
121 strgtb r3, [r0, #-1]!
122 strgeb r4, [r0, #-1]!
123 subs r2, r2, ip
124 strb lr, [r0, #-1]!
125 blt 8b
126 ands ip, r1, #3
127 beq 1b
128
12910: bic r1, r1, #3
130 cmp ip, #2
131 ldr r3, [r1, #0]
132 beq 17f
133 blt 18f
134
135
136 .macro backward_copy_shift push pull
137
138 subs r2, r2, #28
139 blt 14f
140
141 CALGN( ands ip, r1, #31 )
142 CALGN( rsb ip, ip, #32 )
143 CALGN( sbcnes r4, ip, r2 ) @ C is always set here
144 CALGN( subcc r2, r2, ip )
145 CALGN( bcc 15f )
146
14711: stmfd sp!, {r5 - r9}
148
149 PLD( pld [r1, #-4] )
150 PLD( subs r2, r2, #96 )
151 PLD( pld [r1, #-32] )
152 PLD( blt 13f )
153 PLD( pld [r1, #-64] )
154 PLD( pld [r1, #-96] )
155
15612: PLD( pld [r1, #-128] )
15713: ldmdb r1!, {r7, r8, r9, ip}
158 mov lr, r3, push #\push
159 subs r2, r2, #32
160 ldmdb r1!, {r3, r4, r5, r6}
161 orr lr, lr, ip, pull #\pull
162 mov ip, ip, push #\push
163 orr ip, ip, r9, pull #\pull
164 mov r9, r9, push #\push
165 orr r9, r9, r8, pull #\pull
166 mov r8, r8, push #\push
167 orr r8, r8, r7, pull #\pull
168 mov r7, r7, push #\push
169 orr r7, r7, r6, pull #\pull
170 mov r6, r6, push #\push
171 orr r6, r6, r5, pull #\pull
172 mov r5, r5, push #\push
173 orr r5, r5, r4, pull #\pull
174 mov r4, r4, push #\push
175 orr r4, r4, r3, pull #\pull
176 stmdb r0!, {r4 - r9, ip, lr}
177 bge 12b
178 PLD( cmn r2, #96 )
179 PLD( bge 13b )
180
181 ldmfd sp!, {r5 - r9}
182
18314: ands ip, r2, #28
184 beq 16f
185
18615: mov lr, r3, push #\push
187 ldr r3, [r1, #-4]!
188 subs ip, ip, #4
189 orr lr, lr, r3, pull #\pull
190 str lr, [r0, #-4]!
191 bgt 15b
192 CALGN( cmp r2, #0 )
193 CALGN( bge 11b )
194
19516: add r1, r1, #(\pull / 8)
196 b 8b
197
198 .endm
199
200
201 backward_copy_shift push=8 pull=24
202
20317: backward_copy_shift push=16 pull=16
204
20518: backward_copy_shift push=24 pull=8
206