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
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
|
/*
* linux/arch/i386/kernel/sysenter.c
*
* (C) Copyright 2002 Linus Torvalds
*
* This file contains the needed initializations to support sysenter.
*/
#include <linux/init.h>
#include <linux/smp.h>
#include <linux/thread_info.h>
#include <linux/sched.h>
#include <linux/gfp.h>
#include <linux/string.h>
#include <linux/elf.h>
#include <linux/mm.h>
#include <asm/cpufeature.h>
#include <asm/msr.h>
#include <asm/pgtable.h>
#include <asm/unistd.h>
#ifdef CONFIG_XEN
#include <xen/interface/callback.h>
#endif
extern asmlinkage void sysenter_entry(void);
void enable_sep_cpu(void)
{
#ifndef CONFIG_X86_NO_TSS
int cpu = get_cpu();
struct tss_struct *tss = &per_cpu(init_tss, cpu);
if (!boot_cpu_has(X86_FEATURE_SEP)) {
put_cpu();
return;
}
tss->ss1 = __KERNEL_CS;
tss->esp1 = sizeof(struct tss_struct) + (unsigned long) tss;
wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
wrmsr(MSR_IA32_SYSENTER_ESP, tss->esp1, 0);
wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long) sysenter_entry, 0);
put_cpu();
#endif
}
/*
* These symbols are defined by vsyscall.o to mark the bounds
* of the ELF DSO images included therein.
*/
extern const char vsyscall_int80_start, vsyscall_int80_end;
extern const char vsyscall_sysenter_start, vsyscall_sysenter_end;
static void *syscall_page;
int __init sysenter_setup(void)
{
syscall_page = (void *)get_zeroed_page(GFP_ATOMIC);
#ifdef CONFIG_XEN
if (boot_cpu_has(X86_FEATURE_SEP)) {
struct callback_register sysenter = {
.type = CALLBACKTYPE_sysenter,
.address = { __KERNEL_CS, (unsigned long)sysenter_entry },
};
if (HYPERVISOR_callback_op(CALLBACKOP_register, &sysenter) < 0)
clear_bit(X86_FEATURE_SEP, boot_cpu_data.x86_capability);
}
#endif
if (boot_cpu_has(X86_FEATURE_SEP)) {
memcpy(syscall_page,
&vsyscall_sysenter_start,
&vsyscall_sysenter_end - &vsyscall_sysenter_start);
return 0;
}
memcpy(syscall_page,
&vsyscall_int80_start,
&vsyscall_int80_end - &vsyscall_int80_start);
return 0;
}
static struct page*
syscall_nopage(struct vm_area_struct *vma, unsigned long adr, int *type)
{
struct page *p = virt_to_page(adr - vma->vm_start + syscall_page);
get_page(p);
return p;
}
/* Prevent VMA merging */
static void syscall_vma_close(struct vm_area_struct *vma)
{
}
static struct vm_operations_struct syscall_vm_ops = {
.close = syscall_vma_close,
.nopage = syscall_nopage,
};
/* Setup a VMA at program startup for the vsyscall page */
int arch_setup_additional_pages(struct linux_binprm *bprm, int exstack)
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
int ret;
vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
if (!vma)
return -ENOMEM;
memset(vma, 0, sizeof(struct vm_area_struct));
/* Could randomize here */
vma->vm_start = VSYSCALL_BASE;
vma->vm_end = VSYSCALL_BASE + PAGE_SIZE;
/* MAYWRITE to allow gdb to COW and set breakpoints */
vma->vm_flags = VM_READ|VM_EXEC|VM_MAYREAD|VM_MAYEXEC|VM_MAYWRITE;
vma->vm_flags |= mm->def_flags;
vma->vm_page_prot = protection_map[vma->vm_flags & 7];
vma->vm_ops = &syscall_vm_ops;
vma->vm_mm = mm;
down_write(&mm->mmap_sem);
if ((ret = insert_vm_struct(mm, vma))) {
up_write(&mm->mmap_sem);
kmem_cache_free(vm_area_cachep, vma);
return ret;
}
mm->total_vm++;
up_write(&mm->mmap_sem);
return 0;
}
struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
{
return NULL;
}
int in_gate_area(struct task_struct *task, unsigned long addr)
{
return 0;
}
int in_gate_area_no_task(unsigned long addr)
{
return 0;
}
|
