lib1funcs.asm

gcc-you can use this code to learn something about gcc, and inquire further into linux,

@ libgcc routines for ARM cpu.
@ Division routines, written by Richard Earnshaw, ([e-mail])

/* Copyright 1995, 1996, 1998, 1999, 2000 Free Software Foundation, Inc.

This file is free software; you can redistribute it and/or modify it
under the terms of the GNU General Public License as published by the
Free Software Foundation; either version 2, or (at your option) any
later version.

In addition to the permissions in the GNU General Public License, the
Free Software Foundation gives you unlimited permission to link the
compiled version of this file into combinations with other programs,
and to distribute those combinations without any restriction coming
from the use of this file.  (The General Public License restrictions
do apply in other respects; for example, they cover modification of
the file, and distribution when not linked into a combine
executable.)

This file 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
General Public License for more details.

You should have received a copy of the GNU General Public License
along with this program; see the file COPYING.  If not, write to
the Free Software Foundation, 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA.  */
/* ------------------------------------------------------------------------ */

/* We need to know what prefix to add to function names.  */

#ifndef __USER_LABEL_PREFIX__
#error  __USER_LABEL_PREFIX__ not defined
#endif

/* ANSI concatenation macros.  */

#define CONCAT1(a, b) CONCAT2(a, b)
#define CONCAT2(a, b) a ## b

/* Use the right prefix for global labels.  */

#define SYM(x) CONCAT1 (__USER_LABEL_PREFIX__, x)

#ifdef __ELF__
#ifdef __thumb__
#define __PLT__  /* Not supported in Thumb assembler (for now).  */
#else
#define __PLT__ (PLT)
#endif
#define TYPE(x) .type SYM(x),function
#define SIZE(x) .size SYM(x), . - SYM(x)
#else
#define __PLT__
#define TYPE(x)
#define SIZE(x)
#endif

/* Function end macros.  Variants for 26 bit APCS and interworking.  */

#ifdef __APCS_26__
# define RET		movs	pc, lr
# define RETc(x)	mov##x##s	pc, lr
# define RETCOND 	^
.macro ARM_LDIV0
Ldiv0:
	str	lr, [sp, #-4]!
	bl	SYM (__div0) __PLT__
	mov	r0, #0			@ About as wrong as it could be.
	ldmia	sp!, {pc}^
.endm
#else
# ifdef __THUMB_INTERWORK__
#  define RET		bx	lr
#  define RETc(x)	bx##x	lr
.macro THUMB_LDIV0
Ldiv0:
	push	{ lr }
	bl	SYM (__div0)
	mov	r0, #0			@ About as wrong as it could be.
	pop	{ r1 }
	bx	r1
.endm
.macro ARM_LDIV0
Ldiv0:
	str	lr, [sp, #-4]!
	bl	SYM (__div0) __PLT__
	mov	r0, #0			@ About as wrong as it could be.
	ldr	lr, [sp], #4
	bx	lr
.endm	
# else
#  define RET		mov	pc, lr
#  define RETc(x)	mov##x	pc, lr
.macro THUMB_LDIV0
Ldiv0:
	push	{ lr }
	bl	SYM (__div0)
	mov	r0, #0			@ About as wrong as it could be.
	pop	{ pc }
.endm
.macro ARM_LDIV0
Ldiv0:
	str	lr, [sp, #-4]!
	bl	SYM (__div0) __PLT__
	mov	r0, #0			@ About as wrong as it could be.
	ldmia	sp!, {pc}
.endm	
# endif
# define RETCOND
#endif

.macro FUNC_END name
Ldiv0:
#ifdef __thumb__
	THUMB_LDIV0
#else
	ARM_LDIV0
#endif
	SIZE (__\name)	
.endm

.macro THUMB_FUNC_START name
	.globl	SYM (\name)
	TYPE	(\name)
	.thumb_func
SYM (\name):
.endm

/* Function start macros.  Variants for ARM and Thumb.  */

#ifdef __thumb__
#define THUMB_FUNC .thumb_func
#define THUMB_CODE .force_thumb
#else
#define THUMB_FUNC
#define THUMB_CODE
#endif
	
.macro FUNC_START name
	.text
	.globl SYM (__\name)
	TYPE (__\name)
	.align 0
	THUMB_CODE
	THUMB_FUNC
SYM (__\name):
.endm
		
/* Register aliases.  */

work		.req	r4	@ XXXX is this safe ?
dividend	.req	r0
divisor		.req	r1
overdone	.req	r2
result		.req	r2
curbit		.req	r3
ip		.req	r12
sp		.req	r13
lr		.req	r14
pc		.req	r15

/* ------------------------------------------------------------------------ */
/*		Bodies of the divsion and modulo routines.		    */
/* ------------------------------------------------------------------------ */	
.macro ARM_DIV_MOD_BODY modulo
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
	cmplo	divisor, dividend
	movlo	divisor, divisor, lsl #4
	movlo	curbit,  curbit,  lsl #4
	blo	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
	cmplo	divisor, dividend
	movlo	divisor, divisor, lsl #1
	movlo	curbit,  curbit,  lsl #1
	blo	Lbignum

Loop3:
	@ Test for possible subtractions.  On the final pass, this may 
	@ subtract too much from the dividend ...
	
  .if \modulo
	@ ... so keep track of which subtractions are done in OVERDONE.
	@ We can fix them up afterwards.
	mov	overdone, #0
	cmp	dividend, divisor
	subhs	dividend, dividend, divisor
	cmp	dividend, divisor,  lsr #1
	subhs	dividend, dividend, divisor, lsr #1
	orrhs	overdone, overdone, curbit,  ror #1
	cmp	dividend, divisor,  lsr #2
	subhs	dividend, dividend, divisor, lsr #2
	orrhs	overdone, overdone, curbit,  ror #2
	cmp	dividend, divisor,  lsr #3
	subhs	dividend, dividend, divisor, lsr #3
	orrhs	overdone, overdone, curbit,  ror #3
	mov	ip,       curbit
  .else
	@ ... so keep track of which subtractions are done in RESULT.
	@ The result will be ok, since the "bit" will have been 
	@ shifted out at the bottom.
	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
  .endif

	cmp	dividend, #0			@ Early termination?
	movnes	curbit,   curbit,  lsr #4	@ No, any more bits to do?
	movne	divisor,  divisor, lsr #4
	bne	Loop3

  .if \modulo
Lfixup_dividend:	
	@ Any subtractions that we should not have done will be recorded in
	@ the top three bits of OVERDONE.  Exactly which were not needed
	@ are governed by the position of the bit, stored in IP.
	ands	overdone, overdone, #0xe0000000
	@ If we terminated early, because dividend became zero, then the 
	@ bit in ip will not be in the bottom nibble, and we should not
	@ perform the additions below.  We must test for this though
	@ (rather relying upon the TSTs to prevent the additions) since
	@ the bit in ip could be in the top two bits which might then match
	@ with one of the smaller RORs.
	tstne	ip, #0x7
	beq	Lgot_result
	tst	overdone, ip, ror #3
	addne	dividend, dividend, divisor, lsr #3
	tst	overdone, ip, ror #2
	addne	dividend, dividend, divisor, lsr #2
	tst	overdone, ip, ror #1
	addne	dividend, dividend, divisor, lsr #1
  .endif

Lgot_result:
.endm
/* ------------------------------------------------------------------------ */
.macro THUMB_DIV_MOD_BODY modulo
	@ Load the constant 0x10000000 into our work register.
	mov	work, #1
	lsl	work, #28
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, work
	bhs	Lbignum
	cmp	divisor, dividend
	bhs	Lbignum
	lsl	divisor, #4
	lsl	curbit,  #4
	b	Loop1
Lbignum:
	@ Set work to 0x80000000
	lsl	work, #3
Loop2:
	@ For very big divisors, we must shift it a bit at a time, or
	@ we will be in danger of overflowing.
	cmp	divisor, work
	bhs	Loop3
	cmp	divisor, dividend
	bhs	Loop3
	lsl	divisor, #1
	lsl	curbit,  #1
	b	Loop2
Loop3:
	@ Test for possible subtractions ...
  .if \modulo
	@ ... On the final pass, this may subtract too much from the dividend, 
	@ so keep track of which subtractions are done, we can fix them up 
	@ afterwards.
	mov	overdone, #0
	cmp	dividend, divisor
	blo	Lover1
	sub	dividend, dividend, divisor
Lover1:
	lsr	work, divisor, #1
	cmp	dividend, work
	blo	Lover2
	sub	dividend, dividend, work
	mov	ip, curbit
	mov	work, #1
	ror	curbit, work
	orr	overdone, curbit
	mov	curbit, ip
Lover2:
	lsr	work, divisor, #2
	cmp	dividend, work
	blo	Lover3
	sub	dividend, dividend, work
	mov	ip, curbit
	mov	work, #2
	ror	curbit, work
	orr	overdone, curbit
	mov	curbit, ip
Lover3:
	lsr	work, divisor, #3
	cmp	dividend, work
	blo	Lover4
	sub	dividend, dividend, work
	mov	ip, curbit
	mov	work, #3
	ror	curbit, work
	orr	overdone, curbit
	mov	curbit, ip
Lover4:
	mov	ip, curbit
  .else
	@ ... 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
	blo	Lover1
	sub	dividend, dividend, divisor
	orr	result, result, curbit
Lover1:
	lsr	work, divisor, #1
	cmp	dividend, work
	blo	Lover2
	sub	dividend, dividend, work
	lsr	work, curbit, #1
	orr	result, work
Lover2:
	lsr	work, divisor, #2
	cmp	dividend, work
	blo	Lover3
	sub	dividend, dividend, work
	lsr	work, curbit, #2
	orr	result, work
Lover3:
	lsr	work, divisor, #3
	cmp	dividend, work
	blo	Lover4
	sub	dividend, dividend, work
	lsr	work, curbit, #3
	orr	result, work
Lover4:
  .endif
	
	cmp	dividend, #0			@ Early termination?
	beq	Lover5
	lsr	curbit,  #4			@ No, any more bits to do?
	beq	Lover5
	lsr	divisor, #4
	b	Loop3
Lover5:
  .if \modulo
	@ Any subtractions that we should not have done will be recorded in
	@ the top three bits of "overdone".  Exactly which were not needed
	@ are governed by the position of the bit, stored in ip.
	mov	work, #0xe
	lsl	work, #28
	and	overdone, work
	beq	Lgot_result
	
	@ If we terminated early, because dividend became zero, then the 
	@ bit in ip will not be in the bottom nibble, and we should not
	@ perform the additions below.  We must test for this though
	@ (rather relying upon the TSTs to prevent the additions) since
	@ the bit in ip could be in the top two bits which might then match
	@ with one of the smaller RORs.
	mov	curbit, ip
	mov	work, #0x7
	tst	curbit, work
	beq	Lgot_result
	
	mov	curbit, ip
	mov	work, #3
	ror	curbit, work
	tst	overdone, curbit
	beq	Lover6
	lsr	work, divisor, #3