mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-30 19:36:44 +07:00
cb8095bba6
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>
216 lines
3.1 KiB
ArmAsm
216 lines
3.1 KiB
ArmAsm
/*
|
|
* atomic64_t for 586+
|
|
*
|
|
* 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>
|
|
|
|
.macro SAVE reg
|
|
pushl_cfi %\reg
|
|
CFI_REL_OFFSET \reg, 0
|
|
.endm
|
|
|
|
.macro RESTORE reg
|
|
popl_cfi %\reg
|
|
CFI_RESTORE \reg
|
|
.endm
|
|
|
|
.macro read64 reg
|
|
movl %ebx, %eax
|
|
movl %ecx, %edx
|
|
/* we need LOCK_PREFIX since otherwise cmpxchg8b always does the write */
|
|
LOCK_PREFIX
|
|
cmpxchg8b (\reg)
|
|
.endm
|
|
|
|
ENTRY(atomic64_read_cx8)
|
|
CFI_STARTPROC
|
|
|
|
read64 %ecx
|
|
ret
|
|
CFI_ENDPROC
|
|
ENDPROC(atomic64_read_cx8)
|
|
|
|
ENTRY(atomic64_set_cx8)
|
|
CFI_STARTPROC
|
|
|
|
1:
|
|
/* we don't need LOCK_PREFIX since aligned 64-bit writes
|
|
* are atomic on 586 and newer */
|
|
cmpxchg8b (%esi)
|
|
jne 1b
|
|
|
|
ret
|
|
CFI_ENDPROC
|
|
ENDPROC(atomic64_set_cx8)
|
|
|
|
ENTRY(atomic64_xchg_cx8)
|
|
CFI_STARTPROC
|
|
|
|
1:
|
|
LOCK_PREFIX
|
|
cmpxchg8b (%esi)
|
|
jne 1b
|
|
|
|
ret
|
|
CFI_ENDPROC
|
|
ENDPROC(atomic64_xchg_cx8)
|
|
|
|
.macro addsub_return func ins insc
|
|
ENTRY(atomic64_\func\()_return_cx8)
|
|
CFI_STARTPROC
|
|
SAVE ebp
|
|
SAVE ebx
|
|
SAVE esi
|
|
SAVE edi
|
|
|
|
movl %eax, %esi
|
|
movl %edx, %edi
|
|
movl %ecx, %ebp
|
|
|
|
read64 %ecx
|
|
1:
|
|
movl %eax, %ebx
|
|
movl %edx, %ecx
|
|
\ins\()l %esi, %ebx
|
|
\insc\()l %edi, %ecx
|
|
LOCK_PREFIX
|
|
cmpxchg8b (%ebp)
|
|
jne 1b
|
|
|
|
10:
|
|
movl %ebx, %eax
|
|
movl %ecx, %edx
|
|
RESTORE edi
|
|
RESTORE esi
|
|
RESTORE ebx
|
|
RESTORE ebp
|
|
ret
|
|
CFI_ENDPROC
|
|
ENDPROC(atomic64_\func\()_return_cx8)
|
|
.endm
|
|
|
|
addsub_return add add adc
|
|
addsub_return sub sub sbb
|
|
|
|
.macro incdec_return func ins insc
|
|
ENTRY(atomic64_\func\()_return_cx8)
|
|
CFI_STARTPROC
|
|
SAVE ebx
|
|
|
|
read64 %esi
|
|
1:
|
|
movl %eax, %ebx
|
|
movl %edx, %ecx
|
|
\ins\()l $1, %ebx
|
|
\insc\()l $0, %ecx
|
|
LOCK_PREFIX
|
|
cmpxchg8b (%esi)
|
|
jne 1b
|
|
|
|
10:
|
|
movl %ebx, %eax
|
|
movl %ecx, %edx
|
|
RESTORE ebx
|
|
ret
|
|
CFI_ENDPROC
|
|
ENDPROC(atomic64_\func\()_return_cx8)
|
|
.endm
|
|
|
|
incdec_return inc add adc
|
|
incdec_return dec sub sbb
|
|
|
|
ENTRY(atomic64_dec_if_positive_cx8)
|
|
CFI_STARTPROC
|
|
SAVE ebx
|
|
|
|
read64 %esi
|
|
1:
|
|
movl %eax, %ebx
|
|
movl %edx, %ecx
|
|
subl $1, %ebx
|
|
sbb $0, %ecx
|
|
js 2f
|
|
LOCK_PREFIX
|
|
cmpxchg8b (%esi)
|
|
jne 1b
|
|
|
|
2:
|
|
movl %ebx, %eax
|
|
movl %ecx, %edx
|
|
RESTORE ebx
|
|
ret
|
|
CFI_ENDPROC
|
|
ENDPROC(atomic64_dec_if_positive_cx8)
|
|
|
|
ENTRY(atomic64_add_unless_cx8)
|
|
CFI_STARTPROC
|
|
SAVE ebp
|
|
SAVE ebx
|
|
/* these just push these two parameters on the stack */
|
|
SAVE edi
|
|
SAVE ecx
|
|
|
|
movl %eax, %ebp
|
|
movl %edx, %edi
|
|
|
|
read64 %esi
|
|
1:
|
|
cmpl %eax, 0(%esp)
|
|
je 4f
|
|
2:
|
|
movl %eax, %ebx
|
|
movl %edx, %ecx
|
|
addl %ebp, %ebx
|
|
adcl %edi, %ecx
|
|
LOCK_PREFIX
|
|
cmpxchg8b (%esi)
|
|
jne 1b
|
|
|
|
movl $1, %eax
|
|
3:
|
|
addl $8, %esp
|
|
CFI_ADJUST_CFA_OFFSET -8
|
|
RESTORE ebx
|
|
RESTORE ebp
|
|
ret
|
|
4:
|
|
cmpl %edx, 4(%esp)
|
|
jne 2b
|
|
xorl %eax, %eax
|
|
jmp 3b
|
|
CFI_ENDPROC
|
|
ENDPROC(atomic64_add_unless_cx8)
|
|
|
|
ENTRY(atomic64_inc_not_zero_cx8)
|
|
CFI_STARTPROC
|
|
SAVE ebx
|
|
|
|
read64 %esi
|
|
1:
|
|
movl %eax, %ecx
|
|
orl %edx, %ecx
|
|
jz 3f
|
|
movl %eax, %ebx
|
|
xorl %ecx, %ecx
|
|
addl $1, %ebx
|
|
adcl %edx, %ecx
|
|
LOCK_PREFIX
|
|
cmpxchg8b (%esi)
|
|
jne 1b
|
|
|
|
movl $1, %eax
|
|
3:
|
|
RESTORE ebx
|
|
ret
|
|
CFI_ENDPROC
|
|
ENDPROC(atomic64_inc_not_zero_cx8)
|