summaryrefslogtreecommitdiff
path: root/arch/arm/lib/memmove.S
blob: 6fecc12a1f51ad4df71fd2f825d0e4d283b7dc5b (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
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 *  linux/arch/arm/lib/memmove.S
 *
 *  Author:	Nicolas Pitre
 *  Created:	Sep 28, 2005
 *  Copyright:	(C) MontaVista Software Inc.
 */

#include <linux/linkage.h>
#include <asm/assembler.h>
#include <asm/unwind.h>

		.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.  This
 * is a transposition of the code from copy_template.S but with the copy
 * occurring in the opposite direction.
 */

ENTRY(__memmove)
WEAK(memmove)
	UNWIND(	.fnstart			)

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

		stmfd	sp!, {r0, r4, lr}
	UNWIND(	.fnend				)

	UNWIND(	.fnstart			)
	UNWIND(	.save	{r0, r4, lr}		) @ in first stmfd block
		add	r1, r1, r2
		add	r0, r0, r2
		subs	r2, r2, #4
		blt	8f
		ands	ip, r0, #3
	PLD(	pld	[r1, #-4]		)
		bne	9f
		ands	ip, r1, #3
		bne	10f

1:		subs	r2, r2, #(28)
		stmfd	sp!, {r5 - r8}
	UNWIND(	.fnend				)

	UNWIND(	.fnstart			)
	UNWIND(	.save	{r0, r4, lr}		)
	UNWIND(	.save	{r5 - r8}		) @ in second stmfd block
		blt	5f

	CALGN(	ands	ip, r0, #31		)
	CALGN(	sbcsne	r4, ip, r2		)  @ C is always set here
	CALGN(	bcs	2f			)
	CALGN(	adr	r4, 6f			)
	CALGN(	subs	r2, r2, ip		)  @ C is set here
	CALGN(	rsb	ip, ip, #32		)
	CALGN(	add	pc, r4, ip		)

	PLD(	pld	[r1, #-4]		)
2:	PLD(	subs	r2, r2, #96		)
	PLD(	pld	[r1, #-32]		)
	PLD(	blt	4f			)
	PLD(	pld	[r1, #-64]		)
	PLD(	pld	[r1, #-96]		)

3:	PLD(	pld	[r1, #-128]		)
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
	PLD(	cmn	r2, #96			)
	PLD(	bge	4b			)

5:		ands	ip, r2, #28
		rsb	ip, ip, #32
		addne	pc, pc, ip		@ C is always clear here
		b	7f
6:		W(nop)
		W(ldr)	r3, [r1, #-4]!
		W(ldr)	r4, [r1, #-4]!
		W(ldr)	r5, [r1, #-4]!
		W(ldr)	r6, [r1, #-4]!
		W(ldr)	r7, [r1, #-4]!
		W(ldr)	r8, [r1, #-4]!
		W(ldr)	lr, [r1, #-4]!

		add	pc, pc, ip
		nop
		W(nop)
		W(str)	r3, [r0, #-4]!
		W(str)	r4, [r0, #-4]!
		W(str)	r5, [r0, #-4]!
		W(str)	r6, [r0, #-4]!
		W(str)	r7, [r0, #-4]!
		W(str)	r8, [r0, #-4]!
		W(str)	lr, [r0, #-4]!

	CALGN(	bcs	2b			)

7:		ldmfd	sp!, {r5 - r8}
	UNWIND(	.fnend				) @ end of second stmfd block

	UNWIND(	.fnstart			)
	UNWIND(	.save	{r0, r4, lr}		) @ still in first stmfd block

8:		movs	r2, r2, lsl #31
		ldrbne	r3, [r1, #-1]!
		ldrbcs	r4, [r1, #-1]!
		ldrbcs	ip, [r1, #-1]
		strbne	r3, [r0, #-1]!
		strbcs	r4, [r0, #-1]!
		strbcs	ip, [r0, #-1]
		ldmfd	sp!, {r0, r4, pc}

9:		cmp	ip, #2
		ldrbgt	r3, [r1, #-1]!
		ldrbge	r4, [r1, #-1]!
		ldrb	lr, [r1, #-1]!
		strbgt	r3, [r0, #-1]!
		strbge	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
	UNWIND(	.fnend				)


		.macro	backward_copy_shift push pull

	UNWIND(	.fnstart			)
	UNWIND(	.save	{r0, r4, lr}		) @ still in first stmfd block
		subs	r2, r2, #28
		blt	14f

	CALGN(	ands	ip, r0, #31		)
	CALGN(	sbcsne	r4, ip, r2		)  @ C is always set here
	CALGN(	subcc	r2, r2, ip		)
	CALGN(	bcc	15f			)

11:		stmfd	sp!, {r5 - r9}
	UNWIND(	.fnend				)

	UNWIND(	.fnstart			)
	UNWIND(	.save	{r0, r4, lr}		)
	UNWIND(	.save	{r5 - r9}		) @ in new second stmfd block

	PLD(	pld	[r1, #-4]		)
	PLD(	subs	r2, r2, #96		)
	PLD(	pld	[r1, #-32]		)
	PLD(	blt	13f			)
	PLD(	pld	[r1, #-64]		)
	PLD(	pld	[r1, #-96]		)

12:	PLD(	pld	[r1, #-128]		)
13:		ldmdb   r1!, {r7, r8, r9, ip}
		mov     lr, r3, lspush #\push
		subs    r2, r2, #32
		ldmdb   r1!, {r3, r4, r5, r6}
		orr     lr, lr, ip, lspull #\pull
		mov     ip, ip, lspush #\push
		orr     ip, ip, r9, lspull #\pull
		mov     r9, r9, lspush #\push
		orr     r9, r9, r8, lspull #\pull
		mov     r8, r8, lspush #\push
		orr     r8, r8, r7, lspull #\pull
		mov     r7, r7, lspush #\push
		orr     r7, r7, r6, lspull #\pull
		mov     r6, r6, lspush #\push
		orr     r6, r6, r5, lspull #\pull
		mov     r5, r5, lspush #\push
		orr     r5, r5, r4, lspull #\pull
		mov     r4, r4, lspush #\push
		orr     r4, r4, r3, lspull #\pull
		stmdb   r0!, {r4 - r9, ip, lr}
		bge	12b
	PLD(	cmn	r2, #96			)
	PLD(	bge	13b			)

		ldmfd	sp!, {r5 - r9}
	UNWIND(	.fnend				) @ end of the second stmfd block

	UNWIND(	.fnstart			)
	UNWIND(	.save {r0, r4, lr}		) @ still in first stmfd block

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

15:		mov     lr, r3, lspush #\push
		ldr	r3, [r1, #-4]!
		subs	ip, ip, #4
		orr	lr, lr, r3, lspull #\pull
		str	lr, [r0, #-4]!
		bgt	15b
	CALGN(	cmp	r2, #0			)
	CALGN(	bge	11b			)

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

		.endm


		backward_copy_shift	push=8	pull=24

17:		backward_copy_shift	push=16	pull=16

18:		backward_copy_shift	push=24	pull=8

ENDPROC(memmove)
ENDPROC(__memmove)