linux/arch/x86/lib/clear_page_64.S
H. Peter Anvin 83a7a2ad2a x86, alternatives: Use 16-bit numbers for cpufeature index
We already have cpufeature indicies above 255, so use a 16-bit number
for the alternatives index.  This consumes a padding field and so
doesn't add any size, but it means that abusing the padding field to
create assembly errors on overflow no longer works.  We can retain the
test simply by redirecting it to the .discard section, however.

[ v3: updated to include open-coded locations ]

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
LKML-Reference: <tip-f88731e3068f9d1392ba71cc9f50f035d26a0d4f@git.kernel.org>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-07-07 10:36:28 -07:00

59 lines
970 B
ArmAsm

#include <linux/linkage.h>
#include <asm/dwarf2.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)
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 run faster using the string instructions.
It is also a lot simpler. Use this when possible */
#include <asm/cpufeature.h>
.section .altinstr_replacement,"ax"
1: .byte 0xeb /* jmp <disp8> */
.byte (clear_page_c - clear_page) - (2f - 1b) /* offset */
2:
.previous
.section .altinstructions,"a"
.align 8
.quad clear_page
.quad 1b
.word X86_FEATURE_REP_GOOD
.byte .Lclear_page_end - clear_page
.byte 2b - 1b
.previous