linux/arch/x86/lib/copy_page_64.S
Borislav Petkov cd4d09ec6f x86/cpufeature: Carve out X86_FEATURE_*
Move them to a separate header and have the following
dependency:

  x86/cpufeatures.h <- x86/processor.h <- x86/cpufeature.h

This makes it easier to use the header in asm code and not
include the whole cpufeature.h and add guards for asm.

Suggested-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1453842730-28463-5-git-send-email-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-01-30 11:22:17 +01:00

87 lines
1.7 KiB
ArmAsm

/* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */
#include <linux/linkage.h>
#include <asm/cpufeatures.h>
#include <asm/alternative-asm.h>
/*
* Some CPUs run faster using the string copy instructions (sane microcode).
* It is also a lot simpler. Use this when possible. But, don't use streaming
* copy unless the CPU indicates X86_FEATURE_REP_GOOD. Could vary the
* prefetch distance based on SMP/UP.
*/
ALIGN
ENTRY(copy_page)
ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD
movl $4096/8, %ecx
rep movsq
ret
ENDPROC(copy_page)
ENTRY(copy_page_regs)
subq $2*8, %rsp
movq %rbx, (%rsp)
movq %r12, 1*8(%rsp)
movl $(4096/64)-5, %ecx
.p2align 4
.Loop64:
dec %rcx
movq 0x8*0(%rsi), %rax
movq 0x8*1(%rsi), %rbx
movq 0x8*2(%rsi), %rdx
movq 0x8*3(%rsi), %r8
movq 0x8*4(%rsi), %r9
movq 0x8*5(%rsi), %r10
movq 0x8*6(%rsi), %r11
movq 0x8*7(%rsi), %r12
prefetcht0 5*64(%rsi)
movq %rax, 0x8*0(%rdi)
movq %rbx, 0x8*1(%rdi)
movq %rdx, 0x8*2(%rdi)
movq %r8, 0x8*3(%rdi)
movq %r9, 0x8*4(%rdi)
movq %r10, 0x8*5(%rdi)
movq %r11, 0x8*6(%rdi)
movq %r12, 0x8*7(%rdi)
leaq 64 (%rsi), %rsi
leaq 64 (%rdi), %rdi
jnz .Loop64
movl $5, %ecx
.p2align 4
.Loop2:
decl %ecx
movq 0x8*0(%rsi), %rax
movq 0x8*1(%rsi), %rbx
movq 0x8*2(%rsi), %rdx
movq 0x8*3(%rsi), %r8
movq 0x8*4(%rsi), %r9
movq 0x8*5(%rsi), %r10
movq 0x8*6(%rsi), %r11
movq 0x8*7(%rsi), %r12
movq %rax, 0x8*0(%rdi)
movq %rbx, 0x8*1(%rdi)
movq %rdx, 0x8*2(%rdi)
movq %r8, 0x8*3(%rdi)
movq %r9, 0x8*4(%rdi)
movq %r10, 0x8*5(%rdi)
movq %r11, 0x8*6(%rdi)
movq %r12, 0x8*7(%rdi)
leaq 64(%rdi), %rdi
leaq 64(%rsi), %rsi
jnz .Loop2
movq (%rsp), %rbx
movq 1*8(%rsp), %r12
addq $2*8, %rsp
ret
ENDPROC(copy_page_regs)