summaryrefslogtreecommitdiff
path: root/arch/arm64/kernel/vdso.c
blob: 8074cbd3a3a854f293d7145e98fe725fd1d9229f (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
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
/*
 * VDSO implementations.
 *
 * Copyright (C) 2012 ARM Limited
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 *
 * Author: Will Deacon <will.deacon@arm.com>
 */

#include <linux/cache.h>
#include <linux/clocksource.h>
#include <linux/elf.h>
#include <linux/err.h>
#include <linux/errno.h>
#include <linux/gfp.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/signal.h>
#include <linux/slab.h>
#include <linux/timekeeper_internal.h>
#include <linux/vmalloc.h>

#include <asm/cacheflush.h>
#include <asm/signal32.h>
#include <asm/vdso.h>
#include <asm/vdso_datapage.h>

extern char vdso_start[], vdso_end[];
static unsigned long vdso_pages __ro_after_init;

/*
 * The vDSO data page.
 */
static union {
	struct vdso_data	data;
	u8			page[PAGE_SIZE];
} vdso_data_store __page_aligned_data;
struct vdso_data *vdso_data = &vdso_data_store.data;

#ifdef CONFIG_COMPAT
/*
 * Create and map the vectors page for AArch32 tasks.
 */
#define C_VECTORS	0
#define C_SIGPAGE	1
#define C_PAGES		(C_SIGPAGE + 1)
static struct page *aarch32_vdso_pages[C_PAGES] __ro_after_init;
static const struct vm_special_mapping aarch32_vdso_spec[C_PAGES] = {
	{
		.name	= "[vectors]", /* ABI */
		.pages	= &aarch32_vdso_pages[C_VECTORS],
	},
	{
		.name	= "[sigpage]", /* ABI */
		.pages	= &aarch32_vdso_pages[C_SIGPAGE],
	},
};

static int aarch32_alloc_kuser_vdso_page(void)
{
	extern char __kuser_helper_start[], __kuser_helper_end[];
	int kuser_sz = __kuser_helper_end - __kuser_helper_start;
	unsigned long vdso_page;

	if (!IS_ENABLED(CONFIG_KUSER_HELPERS))
		return 0;

	vdso_page = get_zeroed_page(GFP_ATOMIC);
	if (!vdso_page)
		return -ENOMEM;

	memcpy((void *)(vdso_page + 0x1000 - kuser_sz), __kuser_helper_start,
	       kuser_sz);
	aarch32_vdso_pages[C_VECTORS] = virt_to_page(vdso_page);
	flush_dcache_page(aarch32_vdso_pages[C_VECTORS]);
	return 0;
}

static int __init aarch32_alloc_vdso_pages(void)
{
	extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
	int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
	unsigned long sigpage;
	int ret;

	sigpage = get_zeroed_page(GFP_ATOMIC);
	if (!sigpage)
		return -ENOMEM;

	memcpy((void *)sigpage, __aarch32_sigret_code_start, sigret_sz);
	aarch32_vdso_pages[C_SIGPAGE] = virt_to_page(sigpage);
	flush_dcache_page(aarch32_vdso_pages[C_SIGPAGE]);

	ret = aarch32_alloc_kuser_vdso_page();
	if (ret)
		free_page(sigpage);

	return ret;
}
arch_initcall(aarch32_alloc_vdso_pages);

static int aarch32_kuser_helpers_setup(struct mm_struct *mm)
{
	void *ret;

	if (!IS_ENABLED(CONFIG_KUSER_HELPERS))
		return 0;

	/*
	 * Avoid VM_MAYWRITE for compatibility with arch/arm/, where it's
	 * not safe to CoW the page containing the CPU exception vectors.
	 */
	ret = _install_special_mapping(mm, AARCH32_VECTORS_BASE, PAGE_SIZE,
				       VM_READ | VM_EXEC |
				       VM_MAYREAD | VM_MAYEXEC,
				       &aarch32_vdso_spec[C_VECTORS]);

	return PTR_ERR_OR_ZERO(ret);
}

static int aarch32_sigreturn_setup(struct mm_struct *mm)
{
	unsigned long addr;
	void *ret;

	addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
	if (IS_ERR_VALUE(addr)) {
		ret = ERR_PTR(addr);
		goto out;
	}

	/*
	 * VM_MAYWRITE is required to allow gdb to Copy-on-Write and
	 * set breakpoints.
	 */
	ret = _install_special_mapping(mm, addr, PAGE_SIZE,
				       VM_READ | VM_EXEC | VM_MAYREAD |
				       VM_MAYWRITE | VM_MAYEXEC,
				       &aarch32_vdso_spec[C_SIGPAGE]);
	if (IS_ERR(ret))
		goto out;

	mm->context.vdso = (void *)addr;

out:
	return PTR_ERR_OR_ZERO(ret);
}

int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
	struct mm_struct *mm = current->mm;
	int ret;

	if (down_write_killable(&mm->mmap_sem))
		return -EINTR;

	ret = aarch32_kuser_helpers_setup(mm);
	if (ret)
		goto out;

	ret = aarch32_sigreturn_setup(mm);

out:
	up_write(&mm->mmap_sem);
	return ret;
}
#endif /* CONFIG_COMPAT */

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;
	unsigned long vdso_size = vdso_end - vdso_start;

	if (vdso_size != new_size)
		return -EINVAL;

	current->mm->context.vdso = (void *)new_vma->vm_start;

	return 0;
}

static struct vm_special_mapping vdso_spec[2] __ro_after_init = {
	{
		.name	= "[vvar]",
	},
	{
		.name	= "[vdso]",
		.mremap = vdso_mremap,
	},
};

static int __init vdso_init(void)
{
	int i;
	struct page **vdso_pagelist;
	unsigned long pfn;

	if (memcmp(vdso_start, "\177ELF", 4)) {
		pr_err("vDSO is not a valid ELF object!\n");
		return -EINVAL;
	}

	vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;

	/* Allocate the vDSO pagelist, plus a page for the data. */
	vdso_pagelist = kcalloc(vdso_pages + 1, sizeof(struct page *),
				GFP_KERNEL);
	if (vdso_pagelist == NULL)
		return -ENOMEM;

	/* Grab the vDSO data page. */
	vdso_pagelist[0] = phys_to_page(__pa_symbol(vdso_data));


	/* Grab the vDSO code pages. */
	pfn = sym_to_pfn(vdso_start);

	for (i = 0; i < vdso_pages; i++)
		vdso_pagelist[i + 1] = pfn_to_page(pfn + i);

	vdso_spec[0].pages = &vdso_pagelist[0];
	vdso_spec[1].pages = &vdso_pagelist[1];

	return 0;
}
arch_initcall(vdso_init);

int arch_setup_additional_pages(struct linux_binprm *bprm,
				int uses_interp)
{
	struct mm_struct *mm = current->mm;
	unsigned long vdso_base, vdso_text_len, vdso_mapping_len;
	void *ret;

	vdso_text_len = vdso_pages << PAGE_SHIFT;
	/* Be sure to map the data page */
	vdso_mapping_len = vdso_text_len + PAGE_SIZE;

	if (down_write_killable(&mm->mmap_sem))
		return -EINTR;
	vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0);
	if (IS_ERR_VALUE(vdso_base)) {
		ret = ERR_PTR(vdso_base);
		goto up_fail;
	}
	ret = _install_special_mapping(mm, vdso_base, PAGE_SIZE,
				       VM_READ|VM_MAYREAD,
				       &vdso_spec[0]);
	if (IS_ERR(ret))
		goto up_fail;

	vdso_base += PAGE_SIZE;
	mm->context.vdso = (void *)vdso_base;
	ret = _install_special_mapping(mm, vdso_base, vdso_text_len,
				       VM_READ|VM_EXEC|
				       VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
				       &vdso_spec[1]);
	if (IS_ERR(ret))
		goto up_fail;


	up_write(&mm->mmap_sem);
	return 0;

up_fail:
	mm->context.vdso = NULL;
	up_write(&mm->mmap_sem);
	return PTR_ERR(ret);
}

/*
 * Update the vDSO data page to keep in sync with kernel timekeeping.
 */
void update_vsyscall(struct timekeeper *tk)
{
	u32 use_syscall = !tk->tkr_mono.clock->archdata.vdso_direct;

	++vdso_data->tb_seq_count;
	smp_wmb();

	vdso_data->use_syscall			= use_syscall;
	vdso_data->xtime_coarse_sec		= tk->xtime_sec;
	vdso_data->xtime_coarse_nsec		= tk->tkr_mono.xtime_nsec >>
							tk->tkr_mono.shift;
	vdso_data->wtm_clock_sec		= tk->wall_to_monotonic.tv_sec;
	vdso_data->wtm_clock_nsec		= tk->wall_to_monotonic.tv_nsec;

	/* Read without the seqlock held by clock_getres() */
	WRITE_ONCE(vdso_data->hrtimer_res, hrtimer_resolution);

	if (!use_syscall) {
		/* tkr_mono.cycle_last == tkr_raw.cycle_last */
		vdso_data->cs_cycle_last	= tk->tkr_mono.cycle_last;
		vdso_data->raw_time_sec         = tk->raw_sec;
		vdso_data->raw_time_nsec        = tk->tkr_raw.xtime_nsec;
		vdso_data->xtime_clock_sec	= tk->xtime_sec;
		vdso_data->xtime_clock_nsec	= tk->tkr_mono.xtime_nsec;
		vdso_data->cs_mono_mult		= tk->tkr_mono.mult;
		vdso_data->cs_raw_mult		= tk->tkr_raw.mult;
		/* tkr_mono.shift == tkr_raw.shift */
		vdso_data->cs_shift		= tk->tkr_mono.shift;
	}

	smp_wmb();
	++vdso_data->tb_seq_count;
}

void update_vsyscall_tz(void)
{
	vdso_data->tz_minuteswest	= sys_tz.tz_minuteswest;
	vdso_data->tz_dsttime		= sys_tz.tz_dsttime;
}