/* Copyright (C) 2006-2014 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/>.  */

/* Thumb requires excessive IT insns here.  */
#define NO_THUMB
#include <sysdep.h>
#include <arm-features.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
		.syntax unified

/*
 * 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

		push	{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(	sfi_pld	r1, #-4			)
		bne	9f
		ands	ip, r1, #3
		bne	10f

1:		subs	r2, r2, #(28)
		push	{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(	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
#ifndef ARM_ALWAYS_BX
	CALGN(	add	pc, r4, ip, lsl	#(ARM_BX_ALIGN_LOG2 - 2))
#else
	CALGN(	add	r4, r4, ip, lsl	#(ARM_BX_ALIGN_LOG2 - 2))
	CALGN(	bx	r4			)
#endif

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

3:	PLD(	sfi_pld	r1, #-128		)
4:		sfi_breg r1, \
		ldmdb	\B!, {r3, r4, r5, r6, r7, r8, ip, lr}
		subs	r2, r2, #32
		sfi_breg r0, \
		stmdb	\B!, {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
#ifndef ARM_ALWAYS_BX
		/* C is always clear here.  */
		addne	pc, pc, ip, lsl #(ARM_BX_ALIGN_LOG2 - 2)
		b	7f
#else
		beq	7f
		push	{r10}
		cfi_adjust_cfa_offset (4)
		cfi_rel_offset (r10, 0)
		add	r10, pc, ip, lsl #(ARM_BX_ALIGN_LOG2 - 2)
		bx	r10
#endif
		.p2align ARM_BX_ALIGN_LOG2
6:		nop
		.p2align ARM_BX_ALIGN_LOG2
		sfi_breg r1, \
		ldr	r3, [\B, #-4]!
		.p2align ARM_BX_ALIGN_LOG2
		sfi_breg r1, \
		ldr	r4, [\B, #-4]!
		.p2align ARM_BX_ALIGN_LOG2
		sfi_breg r1, \
		ldr	r5, [\B, #-4]!
		.p2align ARM_BX_ALIGN_LOG2
		sfi_breg r1, \
		ldr	r6, [\B, #-4]!
		.p2align ARM_BX_ALIGN_LOG2
		sfi_breg r1, \
		ldr	r7, [\B, #-4]!
		.p2align ARM_BX_ALIGN_LOG2
		sfi_breg r1, \
		ldr	r8, [\B, #-4]!
		.p2align ARM_BX_ALIGN_LOG2
		sfi_breg r1, \
		ldr	lr, [\B, #-4]!

#ifndef ARM_ALWAYS_BX
		add	pc, pc, ip, lsl #(ARM_BX_ALIGN_LOG2 - 2)
		nop
#else
		add	r10, pc, ip, lsl #(ARM_BX_ALIGN_LOG2 - 2)
		bx	r10
#endif
		.p2align ARM_BX_ALIGN_LOG2
		nop
		.p2align ARM_BX_ALIGN_LOG2
		sfi_breg r0, \
		str	r3, [\B, #-4]!
		.p2align ARM_BX_ALIGN_LOG2
		sfi_breg r0, \
		str	r4, [\B, #-4]!
		.p2align ARM_BX_ALIGN_LOG2
		sfi_breg r0, \
		str	r5, [\B, #-4]!
		.p2align ARM_BX_ALIGN_LOG2
		sfi_breg r0, \
		str	r6, [\B, #-4]!
		.p2align ARM_BX_ALIGN_LOG2
		sfi_breg r0, \
		str	r7, [\B, #-4]!
		.p2align ARM_BX_ALIGN_LOG2
		sfi_breg r0, \
		str	r8, [\B, #-4]!
		.p2align ARM_BX_ALIGN_LOG2
		sfi_breg r0, \
		str	lr, [\B, #-4]!

#ifdef ARM_ALWAYS_BX
		pop	{r10}
		cfi_adjust_cfa_offset (-4)
		cfi_restore (r10)
#endif

	CALGN(	bcs	2b			)

7:		pop	{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
		sfi_breg r1, \
		ldrbne	r3, [\B, #-1]!
		sfi_breg r1, \
		ldrbcs	r4, [\B, #-1]!
		sfi_breg r1, \
		ldrbcs	ip, [\B, #-1]
		sfi_breg r0, \
		strbne	r3, [\B, #-1]!
		sfi_breg r0, \
		strbcs	r4, [\B, #-1]!
		sfi_breg r0, \
		strbcs	ip, [\B, #-1]

#if ((defined (__ARM_ARCH_4T__) && defined (__THUMB_INTERWORK__)) \
     || defined (ARM_ALWAYS_BX))
		pop	{r0, r4, lr}
		cfi_adjust_cfa_offset (-12)
		cfi_restore (r4)
		cfi_restore (lr)
		bx      lr
#else
		pop	{r0, r4, pc}
#endif

		cfi_restore_state

9:		cmp	ip, #2
		sfi_breg r1, \
		ldrbgt	r3, [\B, #-1]!
		sfi_breg r1, \
		ldrbge	r4, [\B, #-1]!
		sfi_breg r1, \
		ldrb	lr, [\B, #-1]!
		sfi_breg r0, \
		strbgt	r3, [\B, #-1]!
		sfi_breg r0, \
		strbge	r4, [\B, #-1]!
		subs	r2, r2, ip
		sfi_breg r0, \
		strb	lr, [\B, #-1]!
		blt	8b
		ands	ip, r1, #3
		beq	1b

10:		bic	r1, r1, #3
		cmp	ip, #2
		sfi_breg r1, \
		ldr	r3, [\B, #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(	sbcsne	r4, ip, r2		)  @ C is always set here
	CALGN(	subcc	r2, r2, ip		)
	CALGN(	bcc	15f			)

11:		push	{r5 - r8, r10}
		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 (r10, 16)

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

12:	PLD(	sfi_pld	r1, #-128		)
13:		sfi_breg r1, \
		ldmdb   \B!, {r7, r8, r10, ip}
		mov     lr, r3, PUSH #\push
		subs    r2, r2, #32
		sfi_breg r1, \
		ldmdb   \B!, {r3, r4, r5, r6}
		orr     lr, lr, ip, PULL #\pull
		mov     ip, ip, PUSH #\push
		orr     ip, ip, r10, PULL #\pull
		mov     r10, r10, PUSH #\push
		orr     r10, r10, 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
		sfi_breg r0, \
		stmdb   \B!, {r4 - r8, r10, ip, lr}
		bge	12b
	PLD(	cmn	r2, #96			)
	PLD(	bge	13b			)

		pop	{r5 - r8, r10}
		cfi_adjust_cfa_offset (-20)
		cfi_restore (r5)
		cfi_restore (r6)
		cfi_restore (r7)
		cfi_restore (r8)
		cfi_restore (r10)

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

15:		mov     lr, r3, PUSH #\push
		sfi_breg r1, \
		ldr	r3, [\B, #-4]!
		subs	ip, ip, #4
		orr	lr, lr, r3, PULL #\pull
		sfi_breg r0, \
		str	lr, [\B, #-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)