u-boot/arch/arm/lib/_divsi3.S

.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?
	movnes	\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

	.align	5
.globl __divsi3
.globl __aeabi_idiv
__divsi3:
__aeabi_idiv:
	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
	mov	pc, lr

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

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

12:	ARM_DIV2_ORDER r1, r2

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

Ldiv0:

	str	lr, [sp, #-4]!
	bl	__div0
	mov	r0, #0			@ About as wrong as it could be.
	ldr	pc, [sp], #4