1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
| /* SPDX-License-Identifier: GPL-2.0 */
| /* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */
|
| #include <linux/linkage.h>
| #include <asm/cpufeatures.h>
| #include <asm/alternative.h>
| #include <asm/export.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
| SYM_FUNC_START(copy_page)
| ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD
| movl $4096/8, %ecx
| rep movsq
| RET
| SYM_FUNC_END(copy_page)
| EXPORT_SYMBOL(copy_page)
|
| SYM_FUNC_START_LOCAL(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
| SYM_FUNC_END(copy_page_regs)
|
|
