summaryrefslogtreecommitdiff
path: root/arch/i386/kernel/sysenter.c
blob: 7de9117b5a3ada15bf9e401afc9695e849bac8af (plain)
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
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
/*
 * linux/arch/i386/kernel/sysenter.c
 *
 * (C) Copyright 2002 Linus Torvalds
 * Portions based on the vdso-randomization code from exec-shield:
 * Copyright(C) 2005-2006, Red Hat, Inc., Ingo Molnar
 *
 * 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 <linux/module.h>

#include <asm/cpufeature.h>
#include <asm/msr.h>
#include <asm/pgtable.h>
#include <asm/unistd.h>

/*
 * Should the kernel map a VDSO page into processes and pass its
 * address down to glibc upon exec()?
 */
#ifdef CONFIG_PARAVIRT
unsigned int __read_mostly vdso_enabled = 0;
#else
unsigned int __read_mostly vdso_enabled = 1;
#endif

EXPORT_SYMBOL_GPL(vdso_enabled);

static int __init vdso_setup(char *s)
{
	vdso_enabled = simple_strtoul(s, NULL, 0);

	return 1;
}

__setup("vdso=", vdso_setup);

extern asmlinkage void sysenter_entry(void);

void enable_sep_cpu(void)
{
	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();	
}

/*
 * 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_COMPAT_VDSO
	__set_fixmap(FIX_VDSO, __pa(syscall_page), PAGE_READONLY);
	printk("Compat vDSO mapped to %08lx.\n", __fix_to_virt(FIX_VDSO));
#else
	/*
	 * In the non-compat case the ELF coredumping code needs the fixmap:
	 */
	__set_fixmap(FIX_VDSO, __pa(syscall_page), PAGE_KERNEL_RO);
#endif

	if (!boot_cpu_has(X86_FEATURE_SEP)) {
		memcpy(syscall_page,
		       &vsyscall_int80_start,
		       &vsyscall_int80_end - &vsyscall_int80_start);
		return 0;
	}

	memcpy(syscall_page,
	       &vsyscall_sysenter_start,
	       &vsyscall_sysenter_end - &vsyscall_sysenter_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,
};

/* Defined in vsyscall-sysenter.S */
extern void SYSENTER_RETURN;

/* 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;
	unsigned long addr;
	int ret;

	down_write(&mm->mmap_sem);
	addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
	if (IS_ERR_VALUE(addr)) {
		ret = addr;
		goto up_fail;
	}

	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
	if (!vma) {
		ret = -ENOMEM;
		goto up_fail;
	}

	vma->vm_start = addr;
	vma->vm_end = addr + 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;

	ret = insert_vm_struct(mm, vma);
	if (unlikely(ret)) {
		kmem_cache_free(vm_area_cachep, vma);
		goto up_fail;
	}

	current->mm->context.vdso = (void *)addr;
	current_thread_info()->sysenter_return =
				    (void *)VDSO_SYM(&SYSENTER_RETURN);
	mm->total_vm++;
up_fail:
	up_write(&mm->mmap_sem);
	return ret;
}

const char *arch_vma_name(struct vm_area_struct *vma)
{
	if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso)
		return "[vdso]";
	return NULL;
}

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;
}