mirror of
https://github.com/torvalds/linux.git
synced 2024-11-10 22:21:40 +00:00
6c70b6fc7b
Check the cpu type in the OBP device tree before committing to using the optimized Niagara memcpy and memset implementation. If we don't recognize the cpu type, use a completely generic version. Signed-off-by: David S. Miller <davem@davemloft.net>
122 lines
1.9 KiB
ArmAsm
122 lines
1.9 KiB
ArmAsm
/* GENmemcpy.S: Generic sparc64 memcpy.
|
|
*
|
|
* Copyright (C) 2007 David S. Miller (davem@davemloft.net)
|
|
*/
|
|
|
|
#ifdef __KERNEL__
|
|
#define GLOBAL_SPARE %g7
|
|
#else
|
|
#define GLOBAL_SPARE %g5
|
|
#endif
|
|
|
|
#ifndef EX_LD
|
|
#define EX_LD(x) x
|
|
#endif
|
|
|
|
#ifndef EX_ST
|
|
#define EX_ST(x) x
|
|
#endif
|
|
|
|
#ifndef EX_RETVAL
|
|
#define EX_RETVAL(x) x
|
|
#endif
|
|
|
|
#ifndef LOAD
|
|
#define LOAD(type,addr,dest) type [addr], dest
|
|
#endif
|
|
|
|
#ifndef STORE
|
|
#define STORE(type,src,addr) type src, [addr]
|
|
#endif
|
|
|
|
#ifndef FUNC_NAME
|
|
#define FUNC_NAME GENmemcpy
|
|
#endif
|
|
|
|
#ifndef PREAMBLE
|
|
#define PREAMBLE
|
|
#endif
|
|
|
|
#ifndef XCC
|
|
#define XCC xcc
|
|
#endif
|
|
|
|
.register %g2,#scratch
|
|
.register %g3,#scratch
|
|
|
|
.text
|
|
.align 64
|
|
|
|
.globl FUNC_NAME
|
|
.type FUNC_NAME,#function
|
|
FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */
|
|
srlx %o2, 31, %g2
|
|
cmp %g2, 0
|
|
tne %XCC, 5
|
|
PREAMBLE
|
|
mov %o0, GLOBAL_SPARE
|
|
|
|
cmp %o2, 0
|
|
be,pn %XCC, 85f
|
|
or %o0, %o1, %o3
|
|
cmp %o2, 16
|
|
blu,a,pn %XCC, 80f
|
|
or %o3, %o2, %o3
|
|
|
|
xor %o0, %o1, %o4
|
|
andcc %o4, 0x7, %g0
|
|
bne,a,pn %XCC, 90f
|
|
sub %o0, %o1, %o3
|
|
|
|
and %o0, 0x7, %o4
|
|
sub %o4, 0x8, %o4
|
|
sub %g0, %o4, %o4
|
|
sub %o2, %o4, %o2
|
|
1: subcc %o4, 1, %o4
|
|
EX_LD(LOAD(ldub, %o1, %g1))
|
|
EX_ST(STORE(stb, %g1, %o0))
|
|
add %o1, 1, %o1
|
|
bne,pt %XCC, 1b
|
|
add %o0, 1, %o0
|
|
|
|
andn %o2, 0x7, %g1
|
|
sub %o2, %g1, %o2
|
|
1: subcc %g1, 0x8, %g1
|
|
EX_LD(LOAD(ldx, %o1, %g2))
|
|
EX_ST(STORE(stx, %g2, %o0))
|
|
add %o1, 0x8, %o1
|
|
bne,pt %XCC, 1b
|
|
add %o0, 0x8, %o0
|
|
|
|
brz,pt %o2, 85f
|
|
sub %o0, %o1, %o3
|
|
ba,a,pt %XCC, 90f
|
|
|
|
.align 64
|
|
80: /* 0 < len <= 16 */
|
|
andcc %o3, 0x3, %g0
|
|
bne,pn %XCC, 90f
|
|
sub %o0, %o1, %o3
|
|
|
|
1:
|
|
subcc %o2, 4, %o2
|
|
EX_LD(LOAD(lduw, %o1, %g1))
|
|
EX_ST(STORE(stw, %g1, %o1 + %o3))
|
|
bgu,pt %XCC, 1b
|
|
add %o1, 4, %o1
|
|
|
|
85: retl
|
|
mov EX_RETVAL(GLOBAL_SPARE), %o0
|
|
|
|
.align 32
|
|
90:
|
|
subcc %o2, 1, %o2
|
|
EX_LD(LOAD(ldub, %o1, %g1))
|
|
EX_ST(STORE(stb, %g1, %o1 + %o3))
|
|
bgu,pt %XCC, 90b
|
|
add %o1, 1, %o1
|
|
retl
|
|
mov EX_RETVAL(GLOBAL_SPARE), %o0
|
|
|
|
.size FUNC_NAME, .-FUNC_NAME
|