[net-next-2.6.git] / arch / arm / lib / memmove.S

/*
 *  linux/arch/arm/lib/memmove.S
 *
 *  Author:	Nicolas Pitre
 *  Created:	Sep 28, 2005
 *  Copyright:	(C) MontaVista Software Inc.
 *
 *  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.
 */

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

		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
	PLD(	pld	[r1, #-4]		)
		bne	9f
		ands	ip, r1, #3
		bne	10f

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

	CALGN(	ands	ip, r0, #31		)
	CALGN(	sbcnes	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}

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]
		ldmfd	sp!, {r0, r4, pc}

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

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

11:		stmfd	sp!, {r5 - r9}

	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, 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
	PLD(	cmn	r2, #96			)
	PLD(	bge	13b			)

		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
	CALGN(	cmp	r2, #0			)
	CALGN(	bge	11b			)

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

ENDPROC(memmove)
Commit	Line	Data
75494230 NP	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
75494230 NP	16	.text
	17
	18	/*
	19	* Prototype: void memmove(void dest, const void *src, size_t n);
	20	*
	21	* Note:
	22	*
	23	* If the memory regions don't overlap, we simply branch to memcpy which is
	24	* normally a bit faster. Otherwise the copy is done going downwards. This
	25	* is a transposition of the code from copy_template.S but with the copy
	26	* occurring in the opposite direction.
	27	*/
	28
	29	ENTRY(memmove)
	30
	31	subs ip, r0, r1
	32	cmphi r2, ip
	33	bls memcpy
	34
	35	stmfd sp!, {r0, r4, lr}
	36	add r1, r1, r2
	37	add r0, r0, r2
	38	subs r2, r2, #4
	39	blt 8f
	40	ands ip, r0, #3
	41	PLD( pld [r1, #-4] )
	42	bne 9f
	43	ands ip, r1, #3
	44	bne 10f
	45
	46	1: subs r2, r2, #(28)
	47	stmfd sp!, {r5 - r8}
	48	blt 5f
	49
2239aff6	50	CALGN( ands ip, r0, #31 )
75494230 NP	51	CALGN( sbcnes r4, ip, r2 ) @ C is always set here
	52	CALGN( bcs 2f )
	53	CALGN( adr r4, 6f )
	54	CALGN( subs r2, r2, ip ) @ C is set here
4c4925c1	55	CALGN( rsb ip, ip, #32 )
75494230 NP	56	CALGN( add pc, r4, ip )
	57
	58	PLD( pld [r1, #-4] )
	59	2: PLD( subs r2, r2, #96 )
	60	PLD( pld [r1, #-32] )
	61	PLD( blt 4f )
	62	PLD( pld [r1, #-64] )
	63	PLD( pld [r1, #-96] )
	64
	65	3: PLD( pld [r1, #-128] )
	66	4: ldmdb r1!, {r3, r4, r5, r6, r7, r8, ip, lr}
	67	subs r2, r2, #32
	68	stmdb r0!, {r3, r4, r5, r6, r7, r8, ip, lr}
	69	bge 3b
	70	PLD( cmn r2, #96 )
	71	PLD( bge 4b )
	72
	73	5: ands ip, r2, #28
	74	rsb ip, ip, #32
	75	addne pc, pc, ip @ C is always clear here
	76	b 7f
fd522a8d	77	6: W(nop)
8b592783 CM	78	W(ldr) r3, [r1, #-4]!
	79	W(ldr) r4, [r1, #-4]!
	80	W(ldr) r5, [r1, #-4]!
	81	W(ldr) r6, [r1, #-4]!
	82	W(ldr) r7, [r1, #-4]!
	83	W(ldr) r8, [r1, #-4]!
	84	W(ldr) lr, [r1, #-4]!
75494230 NP	85
	86	add pc, pc, ip
	87	nop
fd522a8d	88	W(nop)
8b592783 CM	89	W(str) r3, [r0, #-4]!
	90	W(str) r4, [r0, #-4]!
	91	W(str) r5, [r0, #-4]!
	92	W(str) r6, [r0, #-4]!
	93	W(str) r7, [r0, #-4]!
	94	W(str) r8, [r0, #-4]!
	95	W(str) lr, [r0, #-4]!
75494230 NP	96
	97	CALGN( bcs 2b )
	98
	99	7: ldmfd sp!, {r5 - r8}
	100
	101	8: movs r2, r2, lsl #31
	102	ldrneb r3, [r1, #-1]!
	103	ldrcsb r4, [r1, #-1]!
	104	ldrcsb ip, [r1, #-1]
	105	strneb r3, [r0, #-1]!
	106	strcsb r4, [r0, #-1]!
	107	strcsb ip, [r0, #-1]
	108	ldmfd sp!, {r0, r4, pc}
	109
	110	9: cmp ip, #2
	111	ldrgtb r3, [r1, #-1]!
	112	ldrgeb r4, [r1, #-1]!
	113	ldrb lr, [r1, #-1]!
	114	strgtb r3, [r0, #-1]!
	115	strgeb r4, [r0, #-1]!
	116	subs r2, r2, ip
	117	strb lr, [r0, #-1]!
	118	blt 8b
	119	ands ip, r1, #3
	120	beq 1b
	121
	122	10: bic r1, r1, #3
	123	cmp ip, #2
	124	ldr r3, [r1, #0]
	125	beq 17f
	126	blt 18f
	127
	128
	129	.macro backward_copy_shift push pull
	130
	131	subs r2, r2, #28
	132	blt 14f
	133
2239aff6	134	CALGN( ands ip, r0, #31 )
75494230 NP	135	CALGN( sbcnes r4, ip, r2 ) @ C is always set here
	136	CALGN( subcc r2, r2, ip )
	137	CALGN( bcc 15f )
	138
	139	11: stmfd sp!, {r5 - r9}
	140
	141	PLD( pld [r1, #-4] )
	142	PLD( subs r2, r2, #96 )
	143	PLD( pld [r1, #-32] )
	144	PLD( blt 13f )
	145	PLD( pld [r1, #-64] )
	146	PLD( pld [r1, #-96] )
	147
	148	12: PLD( pld [r1, #-128] )
	149	13: ldmdb r1!, {r7, r8, r9, ip}
	150	mov lr, r3, push #\push
	151	subs r2, r2, #32
	152	ldmdb r1!, {r3, r4, r5, r6}
	153	orr lr, lr, ip, pull #\pull
	154	mov ip, ip, push #\push
	155	orr ip, ip, r9, pull #\pull
	156	mov r9, r9, push #\push
	157	orr r9, r9, r8, pull #\pull
	158	mov r8, r8, push #\push
	159	orr r8, r8, r7, pull #\pull
	160	mov r7, r7, push #\push
	161	orr r7, r7, r6, pull #\pull
	162	mov r6, r6, push #\push
	163	orr r6, r6, r5, pull #\pull
	164	mov r5, r5, push #\push
	165	orr r5, r5, r4, pull #\pull
	166	mov r4, r4, push #\push
	167	orr r4, r4, r3, pull #\pull
	168	stmdb r0!, {r4 - r9, ip, lr}
	169	bge 12b
	170	PLD( cmn r2, #96 )
	171	PLD( bge 13b )
	172
	173	ldmfd sp!, {r5 - r9}
	174
	175	14: ands ip, r2, #28
	176	beq 16f
	177
	178	15: mov lr, r3, push #\push
	179	ldr r3, [r1, #-4]!
	180	subs ip, ip, #4
	181	orr lr, lr, r3, pull #\pull
	182	str lr, [r0, #-4]!
	183	bgt 15b
	184	CALGN( cmp r2, #0 )
	185	CALGN( bge 11b )
	186
	187	16: add r1, r1, #(\pull / 8)
	188	b 8b
	189
	190	.endm
	191
	192
	193	backward_copy_shift push=8 pull=24
	194
	195	17: backward_copy_shift push=16 pull=16
	196
	197	18: backward_copy_shift push=24 pull=8
	198
93ed3970	199	ENDPROC(memmove)