fernly: Fix printf("%d") > 99999

This adds lots of divison code, which fixes, among other things,
calling printf() with %d greater than 99999.

Makefile

@@ -3,6 +3,7 @@ include magic.mk
 
 CFLAGS = -march=armv5te -mfloat-abi=soft -Wall \
 	 -Os -ggdb -Iinclude
+AFLAGS = -D__ASSEMBLY__
 
 LDFLAGS = --nostdlib -T fernvale.ld
 LIBS =
@@ -12,12 +13,17 @@ SRC_C = \
 	cmd-irq.c \
 	irq.c \
 	main.c \
+	scriptic.c \
 	serial.c \
 	utils.c \
 	vectors.c \
 	vsprintf.c
 
 SRC_S = \
+	scriptic/set-plls.S \
+	scriptic/enable-psram.S \
+	_udivsi3.S \
+	_divsi3.S \
 	start.S
 
 OBJ = $(addprefix $(BUILD)/, $(SRC_S:.S=.o) $(SRC_C:.c=.o))
@@ -52,9 +58,9 @@ $(OBJ): $(HEADER_BUILD)/generated.h | $(OBJ_DIRS)
 $(HEADER_BUILD)/generated.h: | $(HEADER_BUILD)
 	  touch $@
 
-OBJ_DIRS = $(sort $(dir $(OBJ)))
+OBJ_DIRS = $(sort $(dir $(OBJ))) scriptic
 $(OBJ_DIRS):
-	$(MKDIR) -p $@
+	$(MKDIR) -p $@ $@/scriptic
 $(HEADER_BUILD):
-	$(MKDIR) -p $@
+	$(MKDIR) -p $@ build/scriptic
 -include $(OBJ:.o=.P)

_divsi3.S

@@ -0,0 +1,142 @@
+
+.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

_udivsi3.S

@@ -0,0 +1,93 @@
+/* # 1 "libgcc1.S" */
+@ libgcc1 routines for ARM cpu.
+@ Division routines, written by Richard Earnshaw, (rearnsha@armltd.co.uk)
+dividend	.req	r0
+divisor		.req	r1
+result		.req	r2
+curbit		.req	r3
+/* ip		.req	r12	*/
+/* sp		.req	r13	*/
+/* lr		.req	r14	*/
+/* pc		.req	r15	*/
+	.text
+	.globl	 __udivsi3
+	.type	__udivsi3 ,function
+	.globl	__aeabi_uidiv
+	.type	__aeabi_uidiv ,function
+	.align	0
+ __udivsi3:
+ __aeabi_uidiv:
+	cmp	divisor, #0
+	beq	Ldiv0
+	mov	curbit, #1
+	mov	result, #0
+	cmp	dividend, divisor
+	bcc	Lgot_result
+Loop1:
+	@ 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.
+	cmp	divisor, #0x10000000
+	cmpcc	divisor, dividend
+	movcc	divisor, divisor, lsl #4
+	movcc	curbit, curbit, lsl #4
+	bcc	Loop1
+Lbignum:
+	@ For very big divisors, we must shift it a bit at a time, or
+	@ we will be in danger of overflowing.
+	cmp	divisor, #0x80000000
+	cmpcc	divisor, dividend
+	movcc	divisor, divisor, lsl #1
+	movcc	curbit, curbit, lsl #1
+	bcc	Lbignum
+Loop3:
+	@ Test for possible subtractions, and note which bits
+	@ are done in the result.  On the final pass, this may subtract
+	@ too much from the dividend, but the result will be ok, since the
+	@ "bit" will have been shifted out at the bottom.
+	cmp	dividend, divisor
+	subcs	dividend, dividend, divisor
+	orrcs	result, result, curbit
+	cmp	dividend, divisor, lsr #1
+	subcs	dividend, dividend, divisor, lsr #1
+	orrcs	result, result, curbit, lsr #1
+	cmp	dividend, divisor, lsr #2
+	subcs	dividend, dividend, divisor, lsr #2
+	orrcs	result, result, curbit, lsr #2
+	cmp	dividend, divisor, lsr #3
+	subcs	dividend, dividend, divisor, lsr #3
+	orrcs	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	Loop3
+Lgot_result:
+	mov	r0, result
+	mov	pc, lr
+Ldiv0:
+	str	lr, [sp, #-4]!
+	bl	 __div0       (PLT)
+	mov	r0, #0			@ about as wrong as it could be
+	ldmia	sp!, {pc}
+	.size  __udivsi3       , . -  __udivsi3
+
+.globl __aeabi_uidivmod
+__aeabi_uidivmod:
+
+	stmfd	sp!, {r0, r1, ip, lr}
+	bl	__aeabi_uidiv
+	ldmfd	sp!, {r1, r2, ip, lr}
+	mul	r3, r0, r2
+	sub	r1, r1, r3
+	mov	pc, lr
+
+.globl __aeabi_idivmod
+__aeabi_idivmod:
+
+	stmfd	sp!, {r0, r1, ip, lr}
+	bl	__aeabi_idiv
+	ldmfd	sp!, {r1, r2, ip, lr}
+	mul	r3, r0, r2
+	sub	r1, r1, r3
+	mov	pc, lr

start.S

@@ -89,24 +89,6 @@ rv_end:
 .text
 
 
-.global __udiv64
-__udiv64:
-	adds	r0,r0,r0
-	adc	r1,r1,r1
-
-	.rept 31
-		cmp	r1,r2
-		subcs	r1,r1,r2
-		adcs	r0,r0,r0
-		adc	r1,r1,r1
-	.endr
-
-	cmp	r1,r2
-	subcs	r1,r1,r2
-	adcs	r0,r0,r0
-
-	bx	lr
-
 .global ram_memcpy
 ram_memcpy: 
 	ldr	r0, =ram_memcpy_addr

vsprintf.c

@@ -251,7 +251,7 @@ static noinline char* put_dec(char *buf, unsigned NUM_TYPE num)
 		unsigned rem;
 		if (num < 100000)
 			return put_dec_trunc(buf, num);
-		rem = _udiv64(num, 100000);
+		rem = do_div(num, 100000);
 		buf = put_dec_full(buf, rem);
 	}
 }