From: Ma Ling <[email protected]>
Modern CPU use fast-string instruction to accelerate copy performance,
by combining data into 128bit, so we modify comments and code style.
Thanks
Ling
---
arch/x86/lib/copy_page_64.S | 124 +++++++++++++++++++++---------------------
1 files changed, 62 insertions(+), 62 deletions(-)
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index 6fec2d1..45f7db7 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -2,97 +2,98 @@
#include <linux/linkage.h>
#include <asm/dwarf2.h>
+#include <asm/cpufeature.h>
ALIGN
-copy_page_c:
+copy_page_rep:
CFI_STARTPROC
- movl $4096/8,%ecx
- rep movsq
+ movl $4096/8, %ecx
+ rep movsq
ret
CFI_ENDPROC
-ENDPROC(copy_page_c)
+ENDPROC(copy_page_rep)
-/* Don't use streaming store because it's better when the target
- ends up in cache. */
-
-/* Could vary the prefetch distance based on SMP/UP */
+/*
+ Don't use streaming copy unless cpu indicate X86_FEATURE_REP_GOOD
+ Could vary the prefetch distance based on SMP/UP
+*/
ENTRY(copy_page)
CFI_STARTPROC
- subq $3*8,%rsp
+ subq $3*8, %rsp
CFI_ADJUST_CFA_OFFSET 3*8
- movq %rbx,(%rsp)
+ movq %rbx, (%rsp)
CFI_REL_OFFSET rbx, 0
- movq %r12,1*8(%rsp)
+ movq %r12, 1*8(%rsp)
CFI_REL_OFFSET r12, 1*8
- movq %r13,2*8(%rsp)
+ movq %r13, 2*8(%rsp)
CFI_REL_OFFSET r13, 2*8
- movl $(4096/64)-5,%ecx
+ movl $(4096/64)-5, %ecx
.p2align 4
.Loop64:
- dec %rcx
+ dec %rcx
- movq (%rsi), %rax
- movq 8 (%rsi), %rbx
- movq 16 (%rsi), %rdx
- movq 24 (%rsi), %r8
- movq 32 (%rsi), %r9
- movq 40 (%rsi), %r10
- movq 48 (%rsi), %r11
- movq 56 (%rsi), %r12
+ 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, (%rdi)
- movq %rbx, 8 (%rdi)
- movq %rdx, 16 (%rdi)
- movq %r8, 24 (%rdi)
- movq %r9, 32 (%rdi)
- movq %r10, 40 (%rdi)
- movq %r11, 48 (%rdi)
- movq %r12, 56 (%rdi)
+ 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
+ leaq 64 (%rsi), %rsi
+ leaq 64 (%rdi), %rdi
- jnz .Loop64
+ jnz .Loop64
- movl $5,%ecx
+ movl $5, %ecx
.p2align 4
.Loop2:
- decl %ecx
-
- movq (%rsi), %rax
- movq 8 (%rsi), %rbx
- movq 16 (%rsi), %rdx
- movq 24 (%rsi), %r8
- movq 32 (%rsi), %r9
- movq 40 (%rsi), %r10
- movq 48 (%rsi), %r11
- movq 56 (%rsi), %r12
-
- movq %rax, (%rdi)
- movq %rbx, 8 (%rdi)
- movq %rdx, 16 (%rdi)
- movq %r8, 24 (%rdi)
- movq %r9, 32 (%rdi)
- movq %r10, 40 (%rdi)
- movq %r11, 48 (%rdi)
- movq %r12, 56 (%rdi)
-
- leaq 64(%rdi),%rdi
- leaq 64(%rsi),%rsi
+ 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 (%rsp), %rbx
CFI_RESTORE rbx
- movq 1*8(%rsp),%r12
+ movq 1*8(%rsp), %r12
CFI_RESTORE r12
- movq 2*8(%rsp),%r13
+ movq 2*8(%rsp), %r13
CFI_RESTORE r13
- addq $3*8,%rsp
+ addq $3*8, %rsp
CFI_ADJUST_CFA_OFFSET -3*8
ret
.Lcopy_page_end:
@@ -102,11 +103,10 @@ ENDPROC(copy_page)
/* Some CPUs run faster using the string copy 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 (copy_page_c - copy_page) - (2f - 1b) /* offset */
+ .byte (copy_page_rep - copy_page) - (2f - 1b) /* offset */
2:
.previous
.section .altinstructions,"a"
--
1.6.5.2