| /* $Id: memmove.S,v 1.2 2001/07/27 11:51:09 gniibe Exp $ | 
 |  * | 
 |  * "memmove" implementation of SuperH | 
 |  * | 
 |  * Copyright (C) 1999  Niibe Yutaka | 
 |  * | 
 |  */ | 
 |  | 
 | /* | 
 |  * void *memmove(void *dst, const void *src, size_t n); | 
 |  * The memory areas may overlap. | 
 |  */ | 
 |  | 
 | #include <linux/linkage.h> | 
 | ENTRY(memmove) | 
 | 	! if dest > src, call memcpy (it copies in decreasing order) | 
 | 	cmp/hi	r5,r4 | 
 | 	bf	1f | 
 | 	mov.l	2f,r0 | 
 | 	jmp	@r0 | 
 | 	 nop | 
 | 	.balign 4 | 
 | 2:	.long	memcpy | 
 | 1: | 
 | 	sub	r5,r4		! From here, r4 has the distance to r0 | 
 | 	tst	r6,r6 | 
 | 	bt/s	9f		! if n=0, do nothing | 
 | 	 mov	r5,r0 | 
 | 	add	r6,r5 | 
 | 	mov	#12,r1 | 
 | 	cmp/gt	r6,r1 | 
 | 	bt/s	8f		! if it's too small, copy a byte at once | 
 | 	 add	#-1,r4 | 
 | 	add	#1,r4 | 
 | 	! | 
 | 	!                [ ...  ] DST             [ ...  ] SRC | 
 | 	!	         [ ...  ]                 [ ...  ] | 
 | 	!	           :                        : | 
 | 	!      r0+r4-->  [ ...  ]       r0    --> [ ...  ] | 
 | 	!	           :                        : | 
 | 	!	         [ ...  ]                 [ ...  ] | 
 | 	!			        r5    --> | 
 | 	! | 
 | 	mov	r4,r1 | 
 | 	mov	#3,r2 | 
 | 	and	r2,r1 | 
 | 	shll2	r1 | 
 | 	mov	r0,r3		! Save the value on R0 to R3 | 
 | 	mova	jmptable,r0 | 
 | 	add	r1,r0 | 
 | 	mov.l	@r0,r1 | 
 | 	jmp	@r1 | 
 | 	 mov	r3,r0		! and back to R0 | 
 | 	.balign	4 | 
 | jmptable: | 
 | 	.long	case0 | 
 | 	.long	case1 | 
 | 	.long	case2 | 
 | 	.long	case3 | 
 |  | 
 | 	! copy a byte at once | 
 | 8:	mov.b	@r0+,r1 | 
 | 	cmp/hs	r5,r0 | 
 | 	bf/s	8b			! while (r0<r5) | 
 | 	 mov.b	r1,@(r0,r4) | 
 | 	add	#1,r4 | 
 | 9: | 
 | 	add	r4,r0 | 
 | 	rts | 
 | 	 sub	r6,r0 | 
 |  | 
 | case_none: | 
 | 	bra	8b | 
 | 	 add	#-1,r4 | 
 |  | 
 | case0: | 
 | 	! | 
 | 	!	GHIJ KLMN OPQR -->  GHIJ KLMN OPQR | 
 | 	! | 
 | 	! First, align to long word boundary | 
 | 	mov	r0,r3 | 
 | 	and	r2,r3 | 
 | 	tst	r3,r3 | 
 | 	bt/s	2f | 
 | 	 add	#-1,r4 | 
 | 	mov	#4,r2 | 
 | 	sub	r3,r2 | 
 | 1:	dt	r2 | 
 | 	mov.b	@r0+,r1 | 
 | 	bf/s	1b | 
 | 	 mov.b	r1,@(r0,r4) | 
 | 	! | 
 | 2:	! Second, copy a long word at once | 
 | 	add	#-3,r4 | 
 | 	add	#-3,r5 | 
 | 3:	mov.l	@r0+,r1 | 
 | 	cmp/hs	r5,r0 | 
 | 	bf/s	3b | 
 | 	 mov.l	r1,@(r0,r4) | 
 | 	add	#3,r5 | 
 | 	! | 
 | 	! Third, copy a byte at once, if necessary | 
 | 	cmp/eq	r5,r0 | 
 | 	bt/s	9b | 
 | 	 add	#4,r4 | 
 | 	bra	8b | 
 | 	 add	#-1,r4 | 
 |  | 
 | case3: | 
 | 	! | 
 | 	!	GHIJ KLMN OPQR -->  ...G HIJK LMNO PQR. | 
 | 	! | 
 | 	! First, align to long word boundary | 
 | 	mov	r0,r3 | 
 | 	and	r2,r3 | 
 | 	tst	r3,r3 | 
 | 	bt/s	2f | 
 | 	 add	#-1,r4 | 
 | 	mov	#4,r2 | 
 | 	sub	r3,r2 | 
 | 1:	dt	r2 | 
 | 	mov.b	@r0+,r1 | 
 | 	bf/s	1b | 
 | 	 mov.b	r1,@(r0,r4) | 
 | 	! | 
 | 2:	! Second, read a long word and write a long word at once | 
 | 	add	#-2,r4 | 
 | 	mov.l	@(r0,r4),r1 | 
 | 	add	#-7,r5 | 
 | 	add	#-4,r4 | 
 | 	! | 
 | #ifdef __LITTLE_ENDIAN__ | 
 | 	shll8	r1 | 
 | 3:	mov	r1,r3		! JIHG | 
 | 	shlr8	r3		! xJIH | 
 | 	mov.l	@r0+,r1		! NMLK | 
 | 	mov	r1,r2 | 
 | 	shll16	r2 | 
 | 	shll8	r2		! Kxxx | 
 | 	or	r2,r3		! KJIH | 
 | 	cmp/hs	r5,r0 | 
 | 	bf/s	3b | 
 | 	 mov.l	r3,@(r0,r4) | 
 | #else | 
 | 	shlr8	r1 | 
 | 3:	mov	r1,r3		! GHIJ | 
 | 	shll8	r3		! HIJx | 
 | 	mov.l	@r0+,r1		! KLMN | 
 | 	mov	r1,r2 | 
 | 	shlr16	r2 | 
 | 	shlr8	r2		! xxxK | 
 | 	or	r2,r3		! HIJK | 
 | 	cmp/hs	r5,r0 | 
 | 	bf/s	3b | 
 | 	 mov.l	r3,@(r0,r4) | 
 | #endif | 
 | 	add	#7,r5 | 
 | 	! | 
 | 	! Third, copy a byte at once, if necessary | 
 | 	cmp/eq	r5,r0 | 
 | 	bt/s	9b | 
 | 	 add	#7,r4 | 
 | 	add	#-3,r0 | 
 | 	bra	8b | 
 | 	 add	#-1,r4 | 
 |  | 
 | case2: | 
 | 	! | 
 | 	!	GHIJ KLMN OPQR -->  ..GH IJKL MNOP QR.. | 
 | 	! | 
 | 	! First, align to word boundary | 
 | 	tst	#1,r0 | 
 | 	bt/s	2f | 
 | 	 add	#-1,r4 | 
 | 	mov.b	@r0+,r1 | 
 | 	mov.b	r1,@(r0,r4) | 
 | 	! | 
 | 2:	! Second, read a word and write a word at once | 
 | 	add	#-1,r4 | 
 | 	add	#-1,r5 | 
 | 	! | 
 | 3:	mov.w	@r0+,r1 | 
 | 	cmp/hs	r5,r0 | 
 | 	bf/s	3b | 
 | 	 mov.w	r1,@(r0,r4) | 
 | 	add	#1,r5 | 
 | 	! | 
 | 	! Third, copy a byte at once, if necessary | 
 | 	cmp/eq	r5,r0 | 
 | 	bt/s	9b | 
 | 	 add	#2,r4 | 
 | 	mov.b	@r0,r1 | 
 | 	mov.b	r1,@(r0,r4) | 
 | 	bra	9b | 
 | 	 add	#1,r0 | 
 |  | 
 | case1: | 
 | 	! | 
 | 	!	GHIJ KLMN OPQR -->  .GHI JKLM NOPQ R... | 
 | 	! | 
 | 	! First, align to long word boundary | 
 | 	mov	r0,r3 | 
 | 	and	r2,r3 | 
 | 	tst	r3,r3 | 
 | 	bt/s	2f | 
 | 	 add	#-1,r4 | 
 | 	mov	#4,r2 | 
 | 	sub	r3,r2 | 
 | 1:	dt	r2 | 
 | 	mov.b	@r0+,r1 | 
 | 	bf/s	1b | 
 | 	 mov.b	r1,@(r0,r4) | 
 | 	! | 
 | 2:	! Second, read a long word and write a long word at once | 
 | 	mov.l	@(r0,r4),r1 | 
 | 	add	#-7,r5 | 
 | 	add	#-4,r4 | 
 | 	! | 
 | #ifdef __LITTLE_ENDIAN__ | 
 | 	shll16	r1 | 
 | 	shll8	r1 | 
 | 3:	mov	r1,r3		! JIHG | 
 | 	shlr16	r3 | 
 | 	shlr8	r3		! xxxJ | 
 | 	mov.l	@r0+,r1		! NMLK | 
 | 	mov	r1,r2 | 
 | 	shll8	r2		! MLKx | 
 | 	or	r2,r3		! MLKJ | 
 | 	cmp/hs	r5,r0 | 
 | 	bf/s	3b | 
 | 	 mov.l	r3,@(r0,r4) | 
 | #else | 
 | 	shlr16	r1 | 
 | 	shlr8	r1 | 
 | 3:	mov	r1,r3		! GHIJ | 
 | 	shll16	r3 | 
 | 	shll8	r3		! Jxxx | 
 | 	mov.l	@r0+,r1		! KLMN | 
 | 	mov	r1,r2 | 
 | 	shlr8	r2		! xKLM | 
 | 	or	r2,r3		! JKLM | 
 | 	cmp/hs	r5,r0 | 
 | 	bf/s	3b		! while(r0<r5) | 
 | 	 mov.l	r3,@(r0,r4) | 
 | #endif | 
 | 	add	#7,r5 | 
 | 	! | 
 | 	! Third, copy a byte at once, if necessary | 
 | 	cmp/eq	r5,r0 | 
 | 	bt/s	9b | 
 | 	 add	#5,r4 | 
 | 	add	#-3,r0 | 
 | 	bra	8b | 
 | 	 add	#-1,r4 |