[thirdparty/glibc.git] / ports / sysdeps / arm / memmove.S

/* Copyright (C) 2006, 2008, 2009 Free Software Foundation, Inc.
   This file is part of the GNU C Library.

   Contributed by MontaVista Software, Inc. (written by Nicolas Pitre)

   The GNU C Library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Lesser General Public
   License as published by the Free Software Foundation; either
   version 2.1 of the License, or (at your option) any later version.

   The GNU C Library is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   Lesser General Public License for more details.

   You should have received a copy of the GNU Lesser General Public
   License along with the GNU C Library.  If not, see
   <http://www.gnu.org/licenses/>.  */

#include <sysdep.h>

/*
 * Data preload for architectures that support it (ARM V5TE and above)
 */
#if (!defined (__ARM_ARCH_2__) && !defined (__ARM_ARCH_3__) \
     && !defined (__ARM_ARCH_3M__) && !defined (__ARM_ARCH_4__) \
     && !defined (__ARM_ARCH_4T__) && !defined (__ARM_ARCH_5__) \
     && !defined (__ARM_ARCH_5T__))
#define PLD(code...)    code
#else
#define PLD(code...)
#endif

/*
 * This can be used to enable code to cacheline align the source pointer.
 * Experiments on tested architectures (StrongARM and XScale) didn't show
 * this a worthwhile thing to do.  That might be different in the future.
 */
//#define CALGN(code...)        code
#define CALGN(code...)

/*
 * 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.
 */

ENTRY(memmove)

		subs	ip, r0, r1
		cmphi	r2, ip
#ifdef NOT_IN_libc
		bls	memcpy
#else
		bls	HIDDEN_JUMPTARGET(memcpy)
#endif

		stmfd	sp!, {r0, r4, lr}
		cfi_adjust_cfa_offset (12)
		cfi_rel_offset (r4, 4)
		cfi_rel_offset (lr, 8)

		cfi_remember_state

		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}
		cfi_adjust_cfa_offset (16)
		cfi_rel_offset (r5, 0)
		cfi_rel_offset (r6, 4)
		cfi_rel_offset (r7, 8)
		cfi_rel_offset (r8, 12)
		blt	5f

	CALGN(	ands	ip, r1, #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(	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:		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]!

	CALGN(	bcs	2b			)

7:		ldmfd	sp!, {r5 - r8}
		cfi_adjust_cfa_offset (-16)
		cfi_restore (r5)
		cfi_restore (r6)
		cfi_restore (r7)
		cfi_restore (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]

#if defined (__ARM_ARCH_4T__) && defined (__THUMB_INTERWORK__)
		ldmfd	sp!, {r0, r4, lr}
		cfi_adjust_cfa_offset (-12)
		cfi_restore (r4)
		cfi_restore (lr)
		bx      lr
#else
		ldmfd	sp!, {r0, r4, pc}
#endif

		cfi_restore_state

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, r1, #31		)
	CALGN(	rsb	ip, ip, #32		)
	CALGN(	sbcnes	r4, ip, r2		)  @ C is always set here
	CALGN(	subcc	r2, r2, ip		)
	CALGN(	bcc	15f			)

11:		stmfd	sp!, {r5 - r9}
		cfi_adjust_cfa_offset (20)
		cfi_rel_offset (r5, 0)
		cfi_rel_offset (r6, 4)
		cfi_rel_offset (r7, 8)
		cfi_rel_offset (r8, 12)
		cfi_rel_offset (r9, 16)

	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}
		cfi_adjust_cfa_offset (-20)
		cfi_restore (r5)
		cfi_restore (r6)
		cfi_restore (r7)
		cfi_restore (r8)
		cfi_restore (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


END(memmove)
libc_hidden_builtin_def (memmove)
Commit	Line	Data
b2b2415f	1	/* Copyright (C) 2006, 2008, 2009 Free Software Foundation, Inc.
0572b91b DJ	2	This file is part of the GNU C Library.
	3
	4	Contributed by MontaVista Software, Inc. (written by Nicolas Pitre)
	5
	6	The GNU C Library is free software; you can redistribute it and/or
	7	modify it under the terms of the GNU Lesser General Public
	8	License as published by the Free Software Foundation; either
	9	version 2.1 of the License, or (at your option) any later version.
	10
	11	The GNU C Library is distributed in the hope that it will be useful,
	12	but WITHOUT ANY WARRANTY; without even the implied warranty of
	13	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
	14	Lesser General Public License for more details.
	15
	16	You should have received a copy of the GNU Lesser General Public
ab84e3ff PE	17	License along with the GNU C Library. If not, see
ab84e3ff PE	18	<http://www.gnu.org/licenses/>. */
0572b91b DJ	19
	20	#include <sysdep.h>
	21
	22	/*
	23	* Data preload for architectures that support it (ARM V5TE and above)
	24	*/
	25	#if (!defined (__ARM_ARCH_2__) && !defined (__ARM_ARCH_3__) \
	26	&& !defined (__ARM_ARCH_3M__) && !defined (__ARM_ARCH_4__) \
	27	&& !defined (__ARM_ARCH_4T__) && !defined (__ARM_ARCH_5__) \
	28	&& !defined (__ARM_ARCH_5T__))
	29	#define PLD(code...) code
	30	#else
	31	#define PLD(code...)
	32	#endif
	33
	34	/*
	35	* This can be used to enable code to cacheline align the source pointer.
	36	* Experiments on tested architectures (StrongARM and XScale) didn't show
	37	* this a worthwhile thing to do. That might be different in the future.
	38	*/
	39	//#define CALGN(code...) code
	40	#define CALGN(code...)
	41
	42	/*
	43	* Endian independent macros for shifting bytes within registers.
	44	*/
	45	#ifndef __ARMEB__
	46	#define pull lsr
	47	#define push lsl
	48	#else
	49	#define pull lsl
	50	#define push lsr
	51	#endif
	52
	53	.text
	54
	55	/*
	56	* Prototype: void memmove(void dest, const void *src, size_t n);
	57	*
	58	* Note:
	59	*
	60	* If the memory regions don't overlap, we simply branch to memcpy which is
	61	* normally a bit faster. Otherwise the copy is done going downwards.
	62	*/
	63
	64	ENTRY(memmove)
	65
	66	subs ip, r0, r1
	67	cmphi r2, ip
5de92c17	68	#ifdef NOT_IN_libc
0572b91b	69	bls memcpy
5de92c17 JM	70	#else
	71	bls HIDDEN_JUMPTARGET(memcpy)
	72	#endif
0572b91b DJ	73
0572b91b DJ	74	stmfd sp!, {r0, r4, lr}
01b32e73 TS	75	cfi_adjust_cfa_offset (12)
	76	cfi_rel_offset (r4, 4)
	77	cfi_rel_offset (lr, 8)
	78
	79	cfi_remember_state
	80
0572b91b DJ	81	add r1, r1, r2
	82	add r0, r0, r2
	83	subs r2, r2, #4
	84	blt 8f
	85	ands ip, r0, #3
	86	PLD( pld [r1, #-4] )
	87	bne 9f
	88	ands ip, r1, #3
	89	bne 10f
	90
	91	1: subs r2, r2, #(28)
	92	stmfd sp!, {r5 - r8}
01b32e73 TS	93	cfi_adjust_cfa_offset (16)
	94	cfi_rel_offset (r5, 0)
	95	cfi_rel_offset (r6, 4)
	96	cfi_rel_offset (r7, 8)
	97	cfi_rel_offset (r8, 12)
0572b91b DJ	98	blt 5f
	99
	100	CALGN( ands ip, r1, #31 )
	101	CALGN( sbcnes r4, ip, r2 ) @ C is always set here
	102	CALGN( bcs 2f )
	103	CALGN( adr r4, 6f )
	104	CALGN( subs r2, r2, ip ) @ C is set here
	105	CALGN( add pc, r4, ip )
	106
	107	PLD( pld [r1, #-4] )
	108	2: PLD( subs r2, r2, #96 )
	109	PLD( pld [r1, #-32] )
	110	PLD( blt 4f )
	111	PLD( pld [r1, #-64] )
	112	PLD( pld [r1, #-96] )
	113
	114	3: PLD( pld [r1, #-128] )
	115	4: ldmdb r1!, {r3, r4, r5, r6, r7, r8, ip, lr}
	116	subs r2, r2, #32
	117	stmdb r0!, {r3, r4, r5, r6, r7, r8, ip, lr}
	118	bge 3b
	119	PLD( cmn r2, #96 )
	120	PLD( bge 4b )
	121
	122	5: ands ip, r2, #28
	123	rsb ip, ip, #32
	124	addne pc, pc, ip @ C is always clear here
	125	b 7f
	126	6: nop
	127	ldr r3, [r1, #-4]!
	128	ldr r4, [r1, #-4]!
	129	ldr r5, [r1, #-4]!
	130	ldr r6, [r1, #-4]!
	131	ldr r7, [r1, #-4]!
	132	ldr r8, [r1, #-4]!
	133	ldr lr, [r1, #-4]!
	134
	135	add pc, pc, ip
	136	nop
	137	nop
	138	str r3, [r0, #-4]!
	139	str r4, [r0, #-4]!
	140	str r5, [r0, #-4]!
	141	str r6, [r0, #-4]!
	142	str r7, [r0, #-4]!
	143	str r8, [r0, #-4]!
	144	str lr, [r0, #-4]!
	145
	146	CALGN( bcs 2b )
	147
	148	7: ldmfd sp!, {r5 - r8}
01b32e73 TS	149	cfi_adjust_cfa_offset (-16)
	150	cfi_restore (r5)
	151	cfi_restore (r6)
	152	cfi_restore (r7)
	153	cfi_restore (r8)
0572b91b DJ	154
	155	8: movs r2, r2, lsl #31
	156	ldrneb r3, [r1, #-1]!
	157	ldrcsb r4, [r1, #-1]!
	158	ldrcsb ip, [r1, #-1]
	159	strneb r3, [r0, #-1]!
	160	strcsb r4, [r0, #-1]!
	161	strcsb ip, [r0, #-1]
01b32e73	162
b2b2415f PB	163	#if defined (__ARM_ARCH_4T__) && defined (__THUMB_INTERWORK__)
b2b2415f PB	164	ldmfd sp!, {r0, r4, lr}
01b32e73 TS	165	cfi_adjust_cfa_offset (-12)
	166	cfi_restore (r4)
	167	cfi_restore (lr)
b2b2415f PB	168	bx lr
b2b2415f PB	169	#else
0572b91b	170	ldmfd sp!, {r0, r4, pc}
b2b2415f	171	#endif
0572b91b	172
01b32e73 TS	173	cfi_restore_state
01b32e73 TS	174
0572b91b DJ	175	9: cmp ip, #2
	176	ldrgtb r3, [r1, #-1]!
	177	ldrgeb r4, [r1, #-1]!
	178	ldrb lr, [r1, #-1]!
	179	strgtb r3, [r0, #-1]!
	180	strgeb r4, [r0, #-1]!
	181	subs r2, r2, ip
	182	strb lr, [r0, #-1]!
	183	blt 8b
	184	ands ip, r1, #3
	185	beq 1b
	186
	187	10: bic r1, r1, #3
	188	cmp ip, #2
	189	ldr r3, [r1, #0]
	190	beq 17f
	191	blt 18f
	192
	193
	194	.macro backward_copy_shift push pull
	195
	196	subs r2, r2, #28
	197	blt 14f
	198
	199	CALGN( ands ip, r1, #31 )
	200	CALGN( rsb ip, ip, #32 )
	201	CALGN( sbcnes r4, ip, r2 ) @ C is always set here
	202	CALGN( subcc r2, r2, ip )
	203	CALGN( bcc 15f )
	204
	205	11: stmfd sp!, {r5 - r9}
01b32e73 TS	206	cfi_adjust_cfa_offset (20)
	207	cfi_rel_offset (r5, 0)
	208	cfi_rel_offset (r6, 4)
	209	cfi_rel_offset (r7, 8)
	210	cfi_rel_offset (r8, 12)
	211	cfi_rel_offset (r9, 16)
0572b91b DJ	212
	213	PLD( pld [r1, #-4] )
	214	PLD( subs r2, r2, #96 )
	215	PLD( pld [r1, #-32] )
	216	PLD( blt 13f )
	217	PLD( pld [r1, #-64] )
	218	PLD( pld [r1, #-96] )
	219
	220	12: PLD( pld [r1, #-128] )
	221	13: ldmdb r1!, {r7, r8, r9, ip}
	222	mov lr, r3, push #\push
	223	subs r2, r2, #32
	224	ldmdb r1!, {r3, r4, r5, r6}
	225	orr lr, lr, ip, pull #\pull
	226	mov ip, ip, push #\push
	227	orr ip, ip, r9, pull #\pull
	228	mov r9, r9, push #\push
	229	orr r9, r9, r8, pull #\pull
	230	mov r8, r8, push #\push
	231	orr r8, r8, r7, pull #\pull
	232	mov r7, r7, push #\push
	233	orr r7, r7, r6, pull #\pull
	234	mov r6, r6, push #\push
	235	orr r6, r6, r5, pull #\pull
	236	mov r5, r5, push #\push
	237	orr r5, r5, r4, pull #\pull
	238	mov r4, r4, push #\push
	239	orr r4, r4, r3, pull #\pull
	240	stmdb r0!, {r4 - r9, ip, lr}
	241	bge 12b
	242	PLD( cmn r2, #96 )
	243	PLD( bge 13b )
	244
	245	ldmfd sp!, {r5 - r9}
01b32e73 TS	246	cfi_adjust_cfa_offset (-20)
	247	cfi_restore (r5)
	248	cfi_restore (r6)
	249	cfi_restore (r7)
	250	cfi_restore (r8)
	251	cfi_restore (r9)
0572b91b DJ	252
	253	14: ands ip, r2, #28
	254	beq 16f
	255
	256	15: mov lr, r3, push #\push
	257	ldr r3, [r1, #-4]!
	258	subs ip, ip, #4
	259	orr lr, lr, r3, pull #\pull
	260	str lr, [r0, #-4]!
	261	bgt 15b
	262	CALGN( cmp r2, #0 )
	263	CALGN( bge 11b )
	264
	265	16: add r1, r1, #(\pull / 8)
	266	b 8b
	267
	268	.endm
	269
	270
	271	backward_copy_shift push=8 pull=24
	272
	273	17: backward_copy_shift push=16 pull=16
	274
	275	18: backward_copy_shift push=24 pull=8
	276
	277
	278	END(memmove)
	279	libc_hidden_builtin_def (memmove)