summaryrefslogtreecommitdiffstats
path: root/arch/s390/kernel/vdso.c
blob: bbaefd84f15e4f37efeee0123d0be9ef122f8886 (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
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
// SPDX-License-Identifier: GPL-2.0
/*
 * vdso setup for s390
 *
 *  Copyright IBM Corp. 2008
 *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
 */

#include <linux/binfmts.h>
#include <linux/compat.h>
#include <linux/elf.h>
#include <linux/errno.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/smp.h>
#include <linux/time_namespace.h>
#include <linux/random.h>
#include <vdso/datapage.h>
#include <asm/vdso.h>

extern char vdso64_start[], vdso64_end[];
extern char vdso32_start[], vdso32_end[];

static struct vm_special_mapping vvar_mapping;

static union {
	struct vdso_data	data[CS_BASES];
	u8			page[PAGE_SIZE];
} vdso_data_store __page_aligned_data;

struct vdso_data *vdso_data = vdso_data_store.data;

enum vvar_pages {
	VVAR_DATA_PAGE_OFFSET,
	VVAR_TIMENS_PAGE_OFFSET,
	VVAR_NR_PAGES,
};

#ifdef CONFIG_TIME_NS
struct vdso_data *arch_get_vdso_data(void *vvar_page)
{
	return (struct vdso_data *)(vvar_page);
}

/*
 * The VVAR page layout depends on whether a task belongs to the root or
 * non-root time namespace. Whenever a task changes its namespace, the VVAR
 * page tables are cleared and then they will be re-faulted with a
 * corresponding layout.
 * See also the comment near timens_setup_vdso_data() for details.
 */
int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
{
	struct mm_struct *mm = task->mm;
	VMA_ITERATOR(vmi, mm, 0);
	struct vm_area_struct *vma;

	mmap_read_lock(mm);
	for_each_vma(vmi, vma) {
		if (!vma_is_special_mapping(vma, &vvar_mapping))
			continue;
		zap_vma_pages(vma);
		break;
	}
	mmap_read_unlock(mm);
	return 0;
}
#endif

static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
			     struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct page *timens_page = find_timens_vvar_page(vma);
	unsigned long addr, pfn;
	vm_fault_t err;

	switch (vmf->pgoff) {
	case VVAR_DATA_PAGE_OFFSET:
		pfn = virt_to_pfn(vdso_data);
		if (timens_page) {
			/*
			 * Fault in VVAR page too, since it will be accessed
			 * to get clock data anyway.
			 */
			addr = vmf->address + VVAR_TIMENS_PAGE_OFFSET * PAGE_SIZE;
			err = vmf_insert_pfn(vma, addr, pfn);
			if (unlikely(err & VM_FAULT_ERROR))
				return err;
			pfn = page_to_pfn(timens_page);
		}
		break;
#ifdef CONFIG_TIME_NS
	case VVAR_TIMENS_PAGE_OFFSET:
		/*
		 * If a task belongs to a time namespace then a namespace
		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
		 * offset.
		 * See also the comment near timens_setup_vdso_data().
		 */
		if (!timens_page)
			return VM_FAULT_SIGBUS;
		pfn = virt_to_pfn(vdso_data);
		break;
#endif /* CONFIG_TIME_NS */
	default:
		return VM_FAULT_SIGBUS;
	}
	return vmf_insert_pfn(vma, vmf->address, pfn);
}

static int vdso_mremap(const struct vm_special_mapping *sm,
		       struct vm_area_struct *vma)
{
	current->mm->context.vdso_base = vma->vm_start;
	return 0;
}

static struct vm_special_mapping vvar_mapping = {
	.name = "[vvar]",
	.fault = vvar_fault,
};

static struct vm_special_mapping vdso64_mapping = {
	.name = "[vdso]",
	.mremap = vdso_mremap,
};

static struct vm_special_mapping vdso32_mapping = {
	.name = "[vdso]",
	.mremap = vdso_mremap,
};

int vdso_getcpu_init(void)
{
	set_tod_programmable_field(smp_processor_id());
	return 0;
}
early_initcall(vdso_getcpu_init); /* Must be called before SMP init */

static int map_vdso(unsigned long addr, unsigned long vdso_mapping_len)
{
	unsigned long vvar_start, vdso_text_start, vdso_text_len;
	struct vm_special_mapping *vdso_mapping;
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	int rc;

	BUILD_BUG_ON(VVAR_NR_PAGES != __VVAR_PAGES);
	if (mmap_write_lock_killable(mm))
		return -EINTR;

	if (is_compat_task()) {
		vdso_text_len = vdso32_end - vdso32_start;
		vdso_mapping = &vdso32_mapping;
	} else {
		vdso_text_len = vdso64_end - vdso64_start;
		vdso_mapping = &vdso64_mapping;
	}
	vvar_start = get_unmapped_area(NULL, addr, vdso_mapping_len, 0, 0);
	rc = vvar_start;
	if (IS_ERR_VALUE(vvar_start))
		goto out;
	vma = _install_special_mapping(mm, vvar_start, VVAR_NR_PAGES*PAGE_SIZE,
				       VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
				       VM_PFNMAP,
				       &vvar_mapping);
	rc = PTR_ERR(vma);
	if (IS_ERR(vma))
		goto out;
	vdso_text_start = vvar_start + VVAR_NR_PAGES * PAGE_SIZE;
	/* VM_MAYWRITE for COW so gdb can set breakpoints */
	vma = _install_special_mapping(mm, vdso_text_start, vdso_text_len,
				       VM_READ|VM_EXEC|
				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
				       vdso_mapping);
	if (IS_ERR(vma)) {
		do_munmap(mm, vvar_start, PAGE_SIZE, NULL);
		rc = PTR_ERR(vma);
	} else {
		current->mm->context.vdso_base = vdso_text_start;
		rc = 0;
	}
out:
	mmap_write_unlock(mm);
	return rc;
}

static unsigned long vdso_addr(unsigned long start, unsigned long len)
{
	unsigned long addr, end, 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 >= VDSO_BASE)
		end = VDSO_BASE;
	end -= len;

	if (end > start) {
		offset = get_random_u32_below(((end - start) >> PAGE_SHIFT) + 1);
		addr = start + (offset << PAGE_SHIFT);
	} else {
		addr = start;
	}
	return addr;
}

unsigned long vdso_size(void)
{
	unsigned long size = VVAR_NR_PAGES * PAGE_SIZE;

	if (is_compat_task())
		size += vdso32_end - vdso32_start;
	else
		size += vdso64_end - vdso64_start;
	return PAGE_ALIGN(size);
}

int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
	unsigned long addr = VDSO_BASE;
	unsigned long size = vdso_size();

	if (current->flags & PF_RANDOMIZE)
		addr = vdso_addr(current->mm->start_stack + PAGE_SIZE, size);
	return map_vdso(addr, size);
}

static struct page ** __init vdso_setup_pages(void *start, void *end)
{
	int pages = (end - start) >> PAGE_SHIFT;
	struct page **pagelist;
	int i;

	pagelist = kcalloc(pages + 1, sizeof(struct page *), GFP_KERNEL);
	if (!pagelist)
		panic("%s: Cannot allocate page list for VDSO", __func__);
	for (i = 0; i < pages; i++)
		pagelist[i] = virt_to_page(start + i * PAGE_SIZE);
	return pagelist;
}

static int __init vdso_init(void)
{
	vdso64_mapping.pages = vdso_setup_pages(vdso64_start, vdso64_end);
	if (IS_ENABLED(CONFIG_COMPAT))
		vdso32_mapping.pages = vdso_setup_pages(vdso32_start, vdso32_end);
	return 0;
}
arch_initcall(vdso_init);