mirror of
https://github.com/torvalds/linux.git
synced 2024-11-07 04:32:03 +00:00
e365c9df2f
Intel processors are adding enhancements to REP MOVSB/STOSB and the use of REP MOVSB/STOSB for optimal memcpy/memset or similar functions is recommended. Enhancement availability is indicated by CPUID.7.0.EBX[9] (Enhanced REP MOVSB/ STOSB). Support clear_page() with rep stosb for processor supporting enhanced REP MOVSB /STOSB. On processors supporting enhanced REP MOVSB/STOSB, the alternative clear_page_c_e function using enhanced REP STOSB overrides the original function and the fast string function. Signed-off-by: Fenghua Yu <fenghua.yu@intel.com> Link: http://lkml.kernel.org/r/1305671358-14478-6-git-send-email-fenghua.yu@intel.com Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
74 lines
1.4 KiB
ArmAsm
74 lines
1.4 KiB
ArmAsm
#include <linux/linkage.h>
|
|
#include <asm/dwarf2.h>
|
|
#include <asm/alternative-asm.h>
|
|
|
|
/*
|
|
* Zero a page.
|
|
* rdi page
|
|
*/
|
|
ENTRY(clear_page_c)
|
|
CFI_STARTPROC
|
|
movl $4096/8,%ecx
|
|
xorl %eax,%eax
|
|
rep stosq
|
|
ret
|
|
CFI_ENDPROC
|
|
ENDPROC(clear_page_c)
|
|
|
|
ENTRY(clear_page_c_e)
|
|
CFI_STARTPROC
|
|
movl $4096,%ecx
|
|
xorl %eax,%eax
|
|
rep stosb
|
|
ret
|
|
CFI_ENDPROC
|
|
ENDPROC(clear_page_c_e)
|
|
|
|
ENTRY(clear_page)
|
|
CFI_STARTPROC
|
|
xorl %eax,%eax
|
|
movl $4096/64,%ecx
|
|
.p2align 4
|
|
.Lloop:
|
|
decl %ecx
|
|
#define PUT(x) movq %rax,x*8(%rdi)
|
|
movq %rax,(%rdi)
|
|
PUT(1)
|
|
PUT(2)
|
|
PUT(3)
|
|
PUT(4)
|
|
PUT(5)
|
|
PUT(6)
|
|
PUT(7)
|
|
leaq 64(%rdi),%rdi
|
|
jnz .Lloop
|
|
nop
|
|
ret
|
|
CFI_ENDPROC
|
|
.Lclear_page_end:
|
|
ENDPROC(clear_page)
|
|
|
|
/*
|
|
* Some CPUs support enhanced REP MOVSB/STOSB instructions.
|
|
* It is recommended to use this when possible.
|
|
* If enhanced REP MOVSB/STOSB is not available, try to use fast string.
|
|
* Otherwise, use original function.
|
|
*
|
|
*/
|
|
|
|
#include <asm/cpufeature.h>
|
|
|
|
.section .altinstr_replacement,"ax"
|
|
1: .byte 0xeb /* jmp <disp8> */
|
|
.byte (clear_page_c - clear_page) - (2f - 1b) /* offset */
|
|
2: .byte 0xeb /* jmp <disp8> */
|
|
.byte (clear_page_c_e - clear_page) - (3f - 2b) /* offset */
|
|
3:
|
|
.previous
|
|
.section .altinstructions,"a"
|
|
altinstruction_entry clear_page,1b,X86_FEATURE_REP_GOOD,\
|
|
.Lclear_page_end-clear_page, 2b-1b
|
|
altinstruction_entry clear_page,2b,X86_FEATURE_ERMS, \
|
|
.Lclear_page_end-clear_page,3b-2b
|
|
.previous
|