/* SPDX-License-Identifier: GPL-2.0+ */
/*
 * linux/arch/arm/lib/lib1funcs.S: Optimized ARM division routines
 *
 * Author: Nicolas Pitre <nico@fluxnic.net>
 *   - contributed to gcc-3.4 on Sep 30, 2003
 *   - adapted for the Linux kernel on Oct 2, 2003
 */
/*
 * Copyright 1995, 1996, 1998, 1999, 2000, 2003 Free Software Foundation, Inc.
 */

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

/*
 * U-Boot compatibility bit, define empty UNWIND() macro as, since we
 * do not support stack unwinding to make all of the functions available
 * without diverging from Linux code.
 */
#ifdef __UBOOT__
#define UNWIND(x...)
#endif

.macro ARM_DIV_BODY dividend, divisor, result, curbit

#if __LINUX_ARM_ARCH__ >= 5

	clz	\curbit, \divisor
	clz	\result, \dividend
	sub	\result, \curbit, \result
	mov	\curbit, #1
	mov	\divisor, \divisor, lsl \result
	mov	\curbit, \curbit, lsl \result
	mov	\result, #0

#else

	@ Initially shift the divisor left 3 bits if possible,
	@ set curbit accordingly.  This allows for curbit to be located
	@ at the left end of each 4 bit nibbles in the division loop
	@ to save one loop in most cases.
	tst	\divisor, #0xe0000000
	moveq	\divisor, \divisor, lsl #3
	moveq	\curbit, #8
	movne	\curbit, #1

	@ Unless the divisor is very big, shift it up in multiples of
	@ four bits, since this is the amount of unwinding in the main
	@ division loop.  Continue shifting until the divisor is
	@ larger than the dividend.
1:	cmp	\divisor, #0x10000000
	cmplo	\divisor, \dividend
	movlo	\divisor, \divisor, lsl #4
	movlo	\curbit, \curbit, lsl #4
	blo	1b

	@ For very big divisors, we must shift it a bit at a time, or
	@ we will be in danger of overflowing.
1:	cmp	\divisor, #0x80000000
	cmplo	\divisor, \dividend
	movlo	\divisor, \divisor, lsl #1
	movlo	\curbit, \curbit, lsl #1
	blo	1b

	mov	\result, #0

#endif

	@ Division loop
1:	cmp	\dividend, \divisor
	subhs	\dividend, \dividend, \divisor
	orrhs	\result,   \result,   \curbit
	cmp	\dividend, \divisor,  lsr #1
	subhs	\dividend, \dividend, \divisor, lsr #1
	orrhs	\result,   \result,   \curbit,  lsr #1
	cmp	\dividend, \divisor,  lsr #2
	subhs	\dividend, \dividend, \divisor, lsr #2
	orrhs	\result,   \result,   \curbit,  lsr #2
	cmp	\dividend, \divisor,  lsr #3
	subhs	\dividend, \dividend, \divisor, lsr #3
	orrhs	\result,   \result,   \curbit,  lsr #3
	cmp	\dividend, #0			@ Early termination?
	movsne	\curbit,   \curbit,  lsr #4	@ No, any more bits to do?
	movne	\divisor,  \divisor, lsr #4
	bne	1b

.endm


.macro ARM_DIV2_ORDER divisor, order

#if __LINUX_ARM_ARCH__ >= 5

	clz	\order, \divisor
	rsb	\order, \order, #31

#else

	cmp	\divisor, #(1 << 16)
	movhs	\divisor, \divisor, lsr #16
	movhs	\order, #16
	movlo	\order, #0

	cmp	\divisor, #(1 << 8)
	movhs	\divisor, \divisor, lsr #8
	addhs	\order, \order, #8

	cmp	\divisor, #(1 << 4)
	movhs	\divisor, \divisor, lsr #4
	addhs	\order, \order, #4

	cmp	\divisor, #(1 << 2)
	addhi	\order, \order, #3
	addls	\order, \order, \divisor, lsr #1

#endif

.endm


.macro ARM_MOD_BODY dividend, divisor, order, spare

#if __LINUX_ARM_ARCH__ >= 5

	clz	\order, \divisor
	clz	\spare, \dividend
	sub	\order, \order, \spare
	mov	\divisor, \divisor, lsl \order

#else

	mov	\order, #0

	@ Unless the divisor is very big, shift it up in multiples of
	@ four bits, since this is the amount of unwinding in the main
	@ division loop.  Continue shifting until the divisor is
	@ larger than the dividend.
1:	cmp	\divisor, #0x10000000
	cmplo	\divisor, \dividend
	movlo	\divisor, \divisor, lsl #4
	addlo	\order, \order, #4
	blo	1b

	@ For very big divisors, we must shift it a bit at a time, or
	@ we will be in danger of overflowing.
1:	cmp	\divisor, #0x80000000
	cmplo	\divisor, \dividend
	movlo	\divisor, \divisor, lsl #1
	addlo	\order, \order, #1
	blo	1b

#endif

	@ Perform all needed subtractions to keep only the reminder.
	@ Do comparisons in batch of 4 first.
	subs	\order, \order, #3		@ yes, 3 is intended here
	blt	2f

1:	cmp	\dividend, \divisor
	subhs	\dividend, \dividend, \divisor
	cmp	\dividend, \divisor,  lsr #1
	subhs	\dividend, \dividend, \divisor, lsr #1
	cmp	\dividend, \divisor,  lsr #2
	subhs	\dividend, \dividend, \divisor, lsr #2
	cmp	\dividend, \divisor,  lsr #3
	subhs	\dividend, \dividend, \divisor, lsr #3
	cmp	\dividend, #1
	mov	\divisor, \divisor, lsr #4
	subsge	\order, \order, #4
	bge	1b

	tst	\order, #3
	teqne	\dividend, #0
	beq	5f

	@ Either 1, 2 or 3 comparison/subtractions are left.
2:	cmn	\order, #2
	blt	4f
	beq	3f
	cmp	\dividend, \divisor
	subhs	\dividend, \dividend, \divisor
	mov	\divisor,  \divisor,  lsr #1
3:	cmp	\dividend, \divisor
	subhs	\dividend, \dividend, \divisor
	mov	\divisor,  \divisor,  lsr #1
4:	cmp	\dividend, \divisor
	subhs	\dividend, \dividend, \divisor
5:
.endm


.pushsection .text.__udivsi3, "ax"
ENTRY(__udivsi3)
ENTRY(__aeabi_uidiv)
UNWIND(.fnstart)

	subs	r2, r1, #1
	reteq	lr
	bcc	Ldiv0
	cmp	r0, r1
	bls	11f
	tst	r1, r2
	beq	12f

	ARM_DIV_BODY r0, r1, r2, r3

	mov	r0, r2
	ret	lr

11:	moveq	r0, #1
	movne	r0, #0
	ret	lr

12:	ARM_DIV2_ORDER r1, r2

	mov	r0, r0, lsr r2
	ret	lr

UNWIND(.fnend)
ENDPROC(__udivsi3)
ENDPROC(__aeabi_uidiv)
.popsection

.pushsection .text.__umodsi3, "ax"
ENTRY(__umodsi3)
UNWIND(.fnstart)

	subs	r2, r1, #1			@ compare divisor with 1
	bcc	Ldiv0
	cmpne	r0, r1				@ compare dividend with divisor
	moveq   r0, #0
	tsthi	r1, r2				@ see if divisor is power of 2
	andeq	r0, r0, r2
	retls	lr

	ARM_MOD_BODY r0, r1, r2, r3

	ret	lr

UNWIND(.fnend)
ENDPROC(__umodsi3)
.popsection

.pushsection .text.__divsi3, "ax"
ENTRY(__divsi3)
ENTRY(__aeabi_idiv)
UNWIND(.fnstart)

	cmp	r1, #0
	eor	ip, r0, r1			@ save the sign of the result.
	beq	Ldiv0
	rsbmi	r1, r1, #0			@ loops below use unsigned.
	subs	r2, r1, #1			@ division by 1 or -1 ?
	beq	10f
	movs	r3, r0
	rsbmi	r3, r0, #0			@ positive dividend value
	cmp	r3, r1
	bls	11f
	tst	r1, r2				@ divisor is power of 2 ?
	beq	12f

	ARM_DIV_BODY r3, r1, r0, r2

	cmp	ip, #0
	rsbmi	r0, r0, #0
	ret	lr

10:	teq	ip, r0				@ same sign ?
	rsbmi	r0, r0, #0
	ret	lr

11:	movlo	r0, #0
	moveq	r0, ip, asr #31
	orreq	r0, r0, #1
	ret	lr

12:	ARM_DIV2_ORDER r1, r2

	cmp	ip, #0
	mov	r0, r3, lsr r2
	rsbmi	r0, r0, #0
	ret	lr

UNWIND(.fnend)
ENDPROC(__divsi3)
ENDPROC(__aeabi_idiv)
.popsection

.pushsection .text.__modsi3, "ax"
ENTRY(__modsi3)
UNWIND(.fnstart)

	cmp	r1, #0
	beq	Ldiv0
	rsbmi	r1, r1, #0			@ loops below use unsigned.
	movs	ip, r0				@ preserve sign of dividend
	rsbmi	r0, r0, #0			@ if negative make positive
	subs	r2, r1, #1			@ compare divisor with 1
	cmpne	r0, r1				@ compare dividend with divisor
	moveq	r0, #0
	tsthi	r1, r2				@ see if divisor is power of 2
	andeq	r0, r0, r2
	bls	10f

	ARM_MOD_BODY r0, r1, r2, r3

10:	cmp	ip, #0
	rsbmi	r0, r0, #0
	ret	lr

UNWIND(.fnend)
ENDPROC(__modsi3)
.popsection

.pushsection .text.__aeabi_uidivmod, "ax"
ENTRY(__aeabi_uidivmod)
UNWIND(.fnstart)
UNWIND(.save {r0, r1, ip, lr}	)

	stmfd	sp!, {r0, r1, ip, lr}
	bl	__aeabi_uidiv
	ldmfd	sp!, {r1, r2, ip, lr}
	mul	r3, r0, r2
	sub	r1, r1, r3
	ret	lr

UNWIND(.fnend)
ENDPROC(__aeabi_uidivmod)
.popsection

.pushsection .text.__aeabi_uidivmod, "ax"
ENTRY(__aeabi_idivmod)
UNWIND(.fnstart)
UNWIND(.save {r0, r1, ip, lr}	)

	stmfd	sp!, {r0, r1, ip, lr}
	bl	__aeabi_idiv
	ldmfd	sp!, {r1, r2, ip, lr}
	mul	r3, r0, r2
	sub	r1, r1, r3
	ret	lr

UNWIND(.fnend)
ENDPROC(__aeabi_idivmod)
.popsection

.pushsection .text.Ldiv0, "ax"
Ldiv0:
UNWIND(.fnstart)
UNWIND(.pad #4)
UNWIND(.save {lr})

	str	lr, [sp, #-8]!
	bl	__div0
	mov	r0, #0			@ About as wrong as it could be.
	ldr	pc, [sp], #8

UNWIND(.fnend)
ENDPROC(Ldiv0)
.popsection

/* Thumb-1 specialities */
#if CONFIG_IS_ENABLED(SYS_THUMB_BUILD) && !defined(CONFIG_HAS_THUMB2)
.pushsection .text.__gnu_thumb1_case_sqi, "ax"
ENTRY(__gnu_thumb1_case_sqi)
	push	{r1}
	mov	r1, lr
	lsrs	r1, r1, #1
	lsls	r1, r1, #1
	ldrsb	r1, [r1, r0]
	lsls	r1, r1, #1
	add	lr, lr, r1
	pop	{r1}
	ret	lr
ENDPROC(__gnu_thumb1_case_sqi)
.popsection

.pushsection .text.__gnu_thumb1_case_uqi, "ax"
ENTRY(__gnu_thumb1_case_uqi)
	push	{r1}
	mov	r1, lr
	lsrs	r1, r1, #1
	lsls	r1, r1, #1
	ldrb	r1, [r1, r0]
	lsls	r1, r1, #1
	add	lr, lr, r1
	pop	{r1}
	ret	lr
ENDPROC(__gnu_thumb1_case_uqi)
.popsection

.pushsection .text.__gnu_thumb1_case_shi, "ax"
ENTRY(__gnu_thumb1_case_shi)
	push	{r0, r1}
	mov	r1, lr
	lsrs	r1, r1, #1
	lsls	r0, r0, #1
	lsls	r1, r1, #1
	ldrsh	r1, [r1, r0]
	lsls	r1, r1, #1
	add	lr, lr, r1
	pop	{r0, r1}
	ret	lr
ENDPROC(__gnu_thumb1_case_shi)
.popsection

.pushsection .text.__gnu_thumb1_case_uhi, "ax"
ENTRY(__gnu_thumb1_case_uhi)
	push	{r0, r1}
	mov	r1, lr
	lsrs	r1, r1, #1
	lsls	r0, r0, #1
	lsls	r1, r1, #1
	ldrh	r1, [r1, r0]
	lsls	r1, r1, #1
	add	lr, lr, r1
	pop	{r0, r1}
	ret	lr
ENDPROC(__gnu_thumb1_case_uhi)
.popsection

/* Taken and adapted from: https://github.com/gcc-mirror/gcc/blob/4f181f9c7ee3efc509d185fdfda33be9018f1611/libgcc/config/arm/lib1funcs.S#L2156 */
.pushsection .text.__gnu_thumb1_case_si, "ax"
ENTRY(__gnu_thumb1_case_si)
	push	{r0, r1}
	mov	r1, lr
	adds	r1, r1, #2	/* Align to word.  */
	lsrs	r1, r1, #2
	lsls	r0, r0, #2
	lsls	r1, r1, #2
	ldr	r0, [r1, r0]
	adds	r0, r0, r1
	mov	lr, r0
	pop	{r0, r1}
	mov	pc, lr		/* We know we were called from thumb code.  */
ENDPROC(__gnu_thumb1_case_si)
.popsection
#endif