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
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
|
/*
* Copyright 2007 Andi Kleen, SUSE Labs.
* Subject to the GPL, v.2
*
* This contains most of the x86 vDSO kernel-side code.
*/
#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 <linux/ptrace.h>
#include <asm/pvclock.h>
#include <asm/vgtod.h>
#include <asm/proto.h>
#include <asm/vdso.h>
#include <asm/vvar.h>
#include <asm/page.h>
#include <asm/desc.h>
#include <asm/cpufeature.h>
#if defined(CONFIG_X86_64)
unsigned int __read_mostly vdso64_enabled = 1;
#endif
void __init init_vdso_image(const struct vdso_image *image)
{
BUG_ON(image->size % PAGE_SIZE != 0);
apply_alternatives((struct alt_instr *)(image->data + image->alt),
(struct alt_instr *)(image->data + image->alt +
image->alt_len));
}
struct linux_binprm;
static int vdso_fault(const struct vm_special_mapping *sm,
struct vm_area_struct *vma, struct vm_fault *vmf)
{
const struct vdso_image *image = vma->vm_mm->context.vdso_image;
if (!image || (vmf->pgoff << PAGE_SHIFT) >= image->size)
return VM_FAULT_SIGBUS;
vmf->page = virt_to_page(image->data + (vmf->pgoff << PAGE_SHIFT));
get_page(vmf->page);
return 0;
}
static void vdso_fix_landing(const struct vdso_image *image,
struct vm_area_struct *new_vma)
{
#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
if (in_ia32_syscall() && image == &vdso_image_32) {
struct pt_regs *regs = current_pt_regs();
unsigned long vdso_land = image->sym_int80_landing_pad;
unsigned long old_land_addr = vdso_land +
(unsigned long)current->mm->context.vdso;
/* Fixing userspace landing - look at do_fast_syscall_32 */
if (regs->ip == old_land_addr)
regs->ip = new_vma->vm_start + vdso_land;
}
#endif
}
static int vdso_mremap(const struct vm_special_mapping *sm,
struct vm_area_struct *new_vma)
{
unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
const struct vdso_image *image = current->mm->context.vdso_image;
if (image->size != new_size)
return -EINVAL;
if (WARN_ON_ONCE(current->mm != new_vma->vm_mm))
return -EFAULT;
vdso_fix_landing(image, new_vma);
current->mm->context.vdso = (void __user *)new_vma->vm_start;
return 0;
}
static int vvar_fault(const struct vm_special_mapping *sm,
struct vm_area_struct *vma, struct vm_fault *vmf)
{
const struct vdso_image *image = vma->vm_mm->context.vdso_image;
long sym_offset;
int ret = -EFAULT;
if (!image)
return VM_FAULT_SIGBUS;
sym_offset = (long)(vmf->pgoff << PAGE_SHIFT) +
image->sym_vvar_start;
/*
* Sanity check: a symbol offset of zero means that the page
* does not exist for this vdso image, not that the page is at
* offset zero relative to the text mapping. This should be
* impossible here, because sym_offset should only be zero for
* the page past the end of the vvar mapping.
*/
if (sym_offset == 0)
return VM_FAULT_SIGBUS;
if (sym_offset == image->sym_vvar_page) {
ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address,
__pa_symbol(&__vvar_page) >> PAGE_SHIFT);
} else if (sym_offset == image->sym_pvclock_page) {
struct pvclock_vsyscall_time_info *pvti =
pvclock_pvti_cpu0_va();
if (pvti && vclock_was_used(VCLOCK_PVCLOCK)) {
ret = vm_insert_pfn(
vma,
(unsigned long)vmf->virtual_address,
__pa(pvti) >> PAGE_SHIFT);
}
}
if (ret == 0 || ret == -EBUSY)
return VM_FAULT_NOPAGE;
return VM_FAULT_SIGBUS;
}
static const struct vm_special_mapping vdso_mapping = {
.name = "[vdso]",
.fault = vdso_fault,
.mremap = vdso_mremap,
};
static const struct vm_special_mapping vvar_mapping = {
.name = "[vvar]",
.fault = vvar_fault,
};
/*
* Add vdso and vvar mappings to current process.
* @image - blob to map
* @addr - request a specific address (zero to map at free addr)
*/
static int map_vdso(const struct vdso_image *image, unsigned long addr)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
unsigned long text_start;
int ret = 0;
if (down_write_killable(&mm->mmap_sem))
return -EINTR;
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;
/*
* 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,
&vdso_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|VM_IO|VM_DONTDUMP|
VM_PFNMAP,
&vvar_mapping);
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
do_munmap(mm, text_start, image->size);
} else {
current->mm->context.vdso = (void __user *)text_start;
current->mm->context.vdso_image = image;
}
up_fail:
up_write(&mm->mmap_sem);
return ret;
}
#ifdef CONFIG_X86_64
/*
* 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.
*
* Note that this algorithm is imperfect: the distribution of the vdso
* start address within a PMD is biased toward the end.
*
* Only used for the 64-bit and x32 vdsos.
*/
static unsigned long vdso_addr(unsigned long start, unsigned len)
{
unsigned long addr, end;
unsigned offset;
/*
* Round up the start address. It can start out unaligned as a result
* of stack start randomization.
*/
start = PAGE_ALIGN(start);
/* Round the lowest possible end address up to a PMD boundary. */
end = (start + len + PMD_SIZE - 1) & PMD_MASK;
if (end >= TASK_SIZE_MAX)
end = TASK_SIZE_MAX;
end -= len;
if (end > start) {
offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1);
addr = start + (offset << PAGE_SHIFT);
} else {
addr = start;
}
/*
* Forcibly align the final address in case we have a hardware
* issue that requires alignment for performance reasons.
*/
addr = align_vdso_addr(addr);
return addr;
}
static int map_vdso_randomized(const struct vdso_image *image)
{
unsigned long addr = vdso_addr(current->mm->start_stack, image->size-image->sym_vvar_start);
return map_vdso(image, addr);
}
#endif
int map_vdso_once(const struct vdso_image *image, unsigned long addr)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
down_write(&mm->mmap_sem);
/*
* Check if we have already mapped vdso blob - fail to prevent
* abusing from userspace install_speciall_mapping, which may
* not do accounting and rlimit right.
* We could search vma near context.vdso, but it's a slowpath,
* so let's explicitely check all VMAs to be completely sure.
*/
for (vma = mm->mmap; vma; vma = vma->vm_next) {
if (vma_is_special_mapping(vma, &vdso_mapping) ||
vma_is_special_mapping(vma, &vvar_mapping
|