kernel_optimize_test/arch/x86/lib/atomic64_386_32.S
Jan Beulich cb8095bba6 x86: atomic64 assembly improvements
In the "xchg" implementation, %ebx and %ecx don't need to be copied
into %eax and %edx respectively (this is only necessary when desiring
to only read the stored value).

In the "add_unless" implementation, swapping the use of %ecx and %esi
for passing arguments allows %esi to become an input only (i.e.
permitting the register to be re-used to address the same object
without reload).

In "{add,sub}_return", doing the initial read64 through the passed in
%ecx decreases a register dependency.

In "inc_not_zero", a branch can be eliminated by or-ing together the
two halves of the current (64-bit) value, and code size can be further
reduced by adjusting the arithmetic slightly.

v2: Undo the folding of "xchg" and "set".

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Link: http://lkml.kernel.org/r/4F19A2BC020000780006E0DC@nat28.tlf.novell.com
Cc: Luca Barbieri <luca@luca-barbieri.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2012-01-20 17:29:49 -08:00

195 lines
2.6 KiB
ArmAsm

/*
* atomic64_t for 386/486
*
* Copyright © 2010 Luca Barbieri
*
* This program 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 of the License, or
* (at your option) any later version.
*/
#include <linux/linkage.h>
#include <asm/alternative-asm.h>
#include <asm/dwarf2.h>
/* if you want SMP support, implement these with real spinlocks */
.macro LOCK reg
pushfl_cfi
cli
.endm
.macro UNLOCK reg
popfl_cfi
.endm
#define BEGIN(op) \
.macro endp; \
CFI_ENDPROC; \
ENDPROC(atomic64_##op##_386); \
.purgem endp; \
.endm; \
ENTRY(atomic64_##op##_386); \
CFI_STARTPROC; \
LOCK v;
#define ENDP endp
#define RET \
UNLOCK v; \
ret
#define RET_ENDP \
RET; \
ENDP
#define v %ecx
BEGIN(read)
movl (v), %eax
movl 4(v), %edx
RET_ENDP
#undef v
#define v %esi
BEGIN(set)
movl %ebx, (v)
movl %ecx, 4(v)
RET_ENDP
#undef v
#define v %esi
BEGIN(xchg)
movl (v), %eax
movl 4(v), %edx
movl %ebx, (v)
movl %ecx, 4(v)
RET_ENDP
#undef v
#define v %ecx
BEGIN(add)
addl %eax, (v)
adcl %edx, 4(v)
RET_ENDP
#undef v
#define v %ecx
BEGIN(add_return)
addl (v), %eax
adcl 4(v), %edx
movl %eax, (v)
movl %edx, 4(v)
RET_ENDP
#undef v
#define v %ecx
BEGIN(sub)
subl %eax, (v)
sbbl %edx, 4(v)
RET_ENDP
#undef v
#define v %ecx
BEGIN(sub_return)
negl %edx
negl %eax
sbbl $0, %edx
addl (v), %eax
adcl 4(v), %edx
movl %eax, (v)
movl %edx, 4(v)
RET_ENDP
#undef v
#define v %esi
BEGIN(inc)
addl $1, (v)
adcl $0, 4(v)
RET_ENDP
#undef v
#define v %esi
BEGIN(inc_return)
movl (v), %eax
movl 4(v), %edx
addl $1, %eax
adcl $0, %edx
movl %eax, (v)
movl %edx, 4(v)
RET_ENDP
#undef v
#define v %esi
BEGIN(dec)
subl $1, (v)
sbbl $0, 4(v)
RET_ENDP
#undef v
#define v %esi
BEGIN(dec_return)
movl (v), %eax
movl 4(v), %edx
subl $1, %eax
sbbl $0, %edx
movl %eax, (v)
movl %edx, 4(v)
RET_ENDP
#undef v
#define v %esi
BEGIN(add_unless)
addl %eax, %ecx
adcl %edx, %edi
addl (v), %eax
adcl 4(v), %edx
cmpl %eax, %ecx
je 3f
1:
movl %eax, (v)
movl %edx, 4(v)
movl $1, %eax
2:
RET
3:
cmpl %edx, %edi
jne 1b
xorl %eax, %eax
jmp 2b
ENDP
#undef v
#define v %esi
BEGIN(inc_not_zero)
movl (v), %eax
movl 4(v), %edx
testl %eax, %eax
je 3f
1:
addl $1, %eax
adcl $0, %edx
movl %eax, (v)
movl %edx, 4(v)
movl $1, %eax
2:
RET
3:
testl %edx, %edx
jne 1b
jmp 2b
ENDP
#undef v
#define v %esi
BEGIN(dec_if_positive)
movl (v), %eax
movl 4(v), %edx
subl $1, %eax
sbbl $0, %edx
js 1f
movl %eax, (v)
movl %edx, 4(v)
1:
RET_ENDP
#undef v