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
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
|
/*
* Set up the VMAs to tell the VM about the vDSO.
* Copyright 2007 Andi Kleen, SUSE Labs.
* Subject to the GPL, v.2
*/
#include <linux/mm.h>
#include <linux/err.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/random.h>
#include <linux/elf.h>
#include <linux/cpu.h>
#include <asm/vsyscall.h>
#include <asm/vgtod.h>
#include <asm/proto.h>
#include <asm/vdso.h>
#include <asm/page.h>
#include <asm/hpet.h>
#include <asm/desc.h>
#if defined(CONFIG_X86_64)
unsigned int __read_mostly vdso64_enabled = 1;
extern unsigned short vdso_sync_cpuid;
#endif
void __init init_vdso_image(const struct vdso_image *image)
{
int i;
int npages = (image->size) / PAGE_SIZE;
BUG_ON(image->size % PAGE_SIZE != 0);
for (i = 0; i < npages; i++)
image->text_mapping.pages[i] =
virt_to_page(image->data + i*PAGE_SIZE);
apply_alternatives((struct alt_instr *)(image->data + image->alt),
(struct alt_instr *)(image->data + image->alt +
image->alt_len));
}
#if defined(CONFIG_X86_64)
static int __init init_vdso(void)
{
init_vdso_image(&vdso_image_64);
#ifdef CONFIG_X86_X32_ABI
init_vdso_image(&vdso_image_x32);
#endif
return 0;
}
subsys_initcall(init_vdso);
#endif
struct linux_binprm;
/* Put the vdso above the (randomized) stack with another randomized offset.
This way there is no hole in the middle of address space.
To save memory make sure it is still in the same PTE as the stack top.
This doesn't give that many random bits.
Only used for the 64-bit and x32 vdsos. */
static unsigned long vdso_addr(unsigned long start, unsigned len)
{
#ifdef CONFIG_X86_32
return 0;
#else
unsigned long addr, end;
unsigned offset;
end = (start + PMD_SIZE - 1) & PMD_MASK;
if (end >= TASK_SIZE_MAX)
end = TASK_SIZE_MAX;
end -= len;
/* This loses some more bits than a modulo, but is cheaper */
offset = get_random_int() & (PTRS_PER_PTE - 1);
addr = start + (offset << PAGE_SHIFT);
if (addr >= end)
addr = end;
/*
* page-align it here so that get_unmapped_area doesn't
* align it wrongfully again to the next page. addr can come in 4K
* unaligned here as a result of stack start randomization.
*/
addr = PAGE_ALIGN(addr);
addr = align_vdso_addr(addr);
return addr;
#endif
}
static int map_vdso(const struct vdso_image *image, bool calculate_addr)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
unsigned long addr, text_start;
int ret = 0;
static struct page *no_pages[] = {NULL};
static struct vm_special_mapping vvar_mapping = {
.name = "[vvar]",
.pages = no_pages,
};
if (calculate_addr) {
addr = vdso_addr(current->mm->start_stack,
image->size - image->sym_vvar_start);
} else {
addr = 0;
}
down_write(&mm->mmap_sem);
addr = get_unmapped_area(NULL, addr,
image->size - image->sym_vvar_start, 0, 0);
if (IS_ERR_VALUE(addr)) {
ret = addr;
goto up_fail;
}
text_start = addr - image->sym_vvar_start;
current->mm->context.vdso = (void __user *)text_start;
/*
* MAYWRITE to allow gdb to COW and set breakpoints
*/
vma = _install_special_mapping(mm,
text_start,
image->size,
VM_READ|VM_EXEC|
VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
&image->text_mapping);
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
goto up_fail;
}
vma = _install_special_mapping(mm,
addr,
-image->sym_vvar_start,
VM_READ|VM_MAYREAD,
&vvar_mapping);
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
goto up_fail;
}
if (image->sym_vvar_page)
ret = remap_pfn_range(vma,
text_start + image->sym_vvar_page,
__pa_symbol(&__vvar_page) >> PAGE_SHIFT,
PAGE_SIZE,
PAGE_READONLY);
if (ret)
goto up_fail;
#ifdef CONFIG_HPET_TIMER
if (hpet_address && image->sym_hpet_page) {
ret = io_remap_pfn_range(vma,
text_start + image->sym_hpet_page,
hpet_address >> PAGE_SHIFT,
PAGE_SIZE,
pgprot_noncached(PAGE_READONLY));
if (ret)
goto up_fail;
}
#endif
up_fail:
if (ret)
current->mm->context.vdso = NULL;
up_write(&mm->mmap_sem);
return ret;
}
#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT)
static int load_vdso32(void)
{
int ret;
if (vdso32_enabled != 1) /* Other values all mean "disabled" */
return 0;
ret = map_vdso(selected_vdso32, false);
if (ret)
return ret;
if (selected_vdso32->sym_VDSO32_SYSENTER_RETURN)
current_thread_info()->sysenter_return =
current->mm->context.vdso +
selected_vdso32->sym_VDSO32_SYSENTER_RETURN;
return 0;
}
#endif
#ifdef CONFIG_X86_64
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
if (!vdso64_enabled)
return 0;
return map_vdso(&vdso_image_64, true);
}
#ifdef CONFIG_COMPAT
int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
int uses_interp)
{
#ifdef CONFIG_X86_X32_ABI
if (test_thread_flag(TIF_X32)) {
if (!vdso64_enabled)
return 0;
return map_vdso(&vdso_image_x32, true);
}
#endif
return load_vdso32();
}
#endif
#else
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
return load_vdso32();
}
#endif
#ifdef CONFIG_X86_64
static __init int vdso_setup(char *s)
{
vdso64_enabled = simple_strtoul(s, NULL, 0);
return 0;
}
__setup("vdso=", vdso_setup);
#endif
#ifdef CONFIG_X86_64
/*
* Assume __initcall executes before all user space. Hopefully kmod
* doesn't violate that. We'll find out if it does.
*/
static void vsyscall_set_cpu(int cpu)
{
struct desc_struct d;
unsigned long node = 0;
#ifdef CONFIG_NUMA
node = cpu_to_node(cpu);
#endif
if (cpu_has(&cpu_data(cpu), X86_FEATURE_RDTSCP))
write_rdtscp_aux((node << 12) | cpu);
/*
* Store cpu number in limit so that it can be loaded
* quickly in user space in vgetcpu. (12 bits for the CPU
* and 8 bits for the node)
*/
d = (struct desc_struct) {
.limit0 = cpu | ((node & 0xf) << 12),
.limit = node >> 4,
.type = 5, /* RO data, expand down, accessed */
.dpl = 3, /* Visible to user code */
.s = 1, /* Not a system segment */
.p = 1, /* Present */
.d = 1, /* 32-bit */
};
write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
}
static void cpu_vsyscall_init(void *arg)
{
/* preemption should be already off */
vsyscall_set_cpu(raw_smp_processor_id());
}
static int
cpu_vsyscall_notifier(struct notifier_block *n, unsigned long action, void *arg)
{
long cpu = (long)arg;
if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN)
smp_call_function_single(cpu, cpu_vsyscall_init, NULL, 1);
return NOTIFY_DONE;
}
static int __init vsyscall_init(void)
{
cpu_notifier_register_begin();
on_each_cpu(cpu_vsyscall_init, NULL, 1);
/* notifier priority > KVM */
__hotcpu_notifier(cpu_vsyscall_notifier, 30);
cpu_notifier_register_done();
return 0;
}
__initcall(vsyscall_init);
#endif
|