path: root/arch/sparc/lib/memcpy.S

/* memcpy.S: Sparc optimized memcpy and memmove code
 * Hand optimized from GNU libc's memcpy and memmove
 * Copyright (C) 1991,1996 Free Software Foundation
 * Copyright (C) 1995 Linus Torvalds (Linus.Torvalds@helsinki.fi)
 * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
 * Copyright (C) 1996 Eddie C. Dost (ecd@skynet.be)
 * Copyright (C) 1996 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
 */

#ifdef __KERNEL__

#define FUNC(x) 											\
	.globl	x;		\
	.type	x,@function;	\
	.align	4;											\
x:

#undef FASTER_REVERSE
#undef FASTER_NONALIGNED
#define FASTER_ALIGNED

/* In kernel these functions don't return a value.
 * One should use macros in asm/string.h for that purpose.
 * We return 0, so that bugs are more apparent.
 */
#define SETUP_RETL
#define RETL_INSN	clr	%o0

#else

/* libc */

#include "DEFS.h"

#define FASTER_REVERSE
#define FASTER_NONALIGNED
#define FASTER_ALIGNED

#define SETUP_RETL	mov	%o0, %g6
#define RETL_INSN	mov	%g6, %o0

#endif

/* Both these macros have to start with exactly the same insn */
#define MOVE_BIGCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \
	ldd	[%src + (offset) + 0x00], %t0; \
	ldd	[%src + (offset) + 0x08], %t2; \
	ldd	[%src + (offset) + 0x10], %t4; \
	ldd	[%src + (offset) + 0x18], %t6; \
	st	%t0, [%dst + (offset) + 0x00]; \
	st	%t1, [%dst + (offset) + 0x04]; \
	st	%t2, [%dst + (offset) + 0x08]; \
	st	%t3, [%dst + (offset) + 0x0c]; \
	st	%t4, [%dst + (offset) + 0x10]; \
	st	%t5, [%dst + (offset) + 0x14]; \
	st	%t6, [%dst + (offset) + 0x18]; \
	st	%t7, [%dst + (offset) + 0x1c];

#define MOVE_BIGALIGNCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \
	ldd	[%src + (offset) + 0x00], %t0; \
	ldd	[%src + (offset) + 0x08], %t2; \
	ldd	[%src + (offset) + 0x10], %t4; \
	ldd	[%src + (offset) + 0x18], %t6; \
	std	%t0, [%dst + (offset) + 0x00]; \
	std	%t2, [%dst + (offset) + 0x08]; \
	std	%t4, [%dst + (offset) + 0x10]; \
	std	%t6, [%dst + (offset) + 0x18];

#define MOVE_LASTCHUNK(src, dst, offset, t0, t1, t2, t3) \
	ldd	[%src - (offset) - 0x10], %t0; \
	ldd	[%src - (offset) - 0x08], %t2; \
	st	%t0, [%dst - (offset) - 0x10]; \
	st	%t1, [%dst - (offset) - 0x0c]; \
	st	%t2, [%dst - (offset) - 0x08]; \
	st	%t3, [%dst - (offset) - 0x04];

#define MOVE_LASTALIGNCHUNK(src, dst, offset, t0, t1, t2, t3) \
	ldd	[%src - (offset) - 0x10], %t0; \
	ldd	[%src - (offset) - 0x08], %t2; \
	std	%t0, [%dst - (offset) - 0x10]; \
	std	%t2, [%dst - (offset) - 0x08];

#define MOVE_SHORTCHUNK(src, dst, offset, t0, t1) \
	ldub