aboutsummaryrefslogtreecommitdiffstats
path: root/arch/s390/kernel/vdso.c
blob: f438d74dedbd171fa151f234a96e4f173358403a (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
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
/*
 * vdso setup for s390
 *
 *  Copyright IBM Corp. 2008
 *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License (version 2 only)
 * as published by the Free Software Foundation.
 */

#include <linux/module.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/slab.h>
#include <linux/user.h>
#include <linux/elf.h>
#include <linux/security.h>
#include <linux/bootmem.h>
#include <linux/compat.h>
#include <asm/asm-offsets.h>
#include <asm/pgtable.h>
#include <asm/system.h>
#include <asm/processor.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
#include <asm/sections.h>
#include <asm/vdso.h>

#if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT)
extern char vdso32_start, vdso32_end;
static void *vdso32_kbase = &vdso32_start;
static unsigned int vdso32_pages;
static struct page **vdso32_pagelist;
#endif

#ifdef CONFIG_64BIT
extern char vdso64_start, vdso64_end;
static void *vdso64_kbase = &vdso64_start;
static unsigned int vdso64_pages;
static struct page **vdso64_pagelist;
#endif /* CONFIG_64BIT */

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

static int __init vdso_setup(char *s)
{
	unsigned long val;
	int rc;

	rc = 0;
	if (strncmp(s, "on", 3) == 0)
		vdso_enabled = 1;
	else if (strncmp(s, "off", 4) == 0)
		vdso_enabled = 0;
	else {
		rc = strict_strtoul(s, 0, &val);
		vdso_enabled = rc ? 0 : !!val;
	}
	return !rc;
}
__setup("vdso=", vdso_setup);

/*
 * 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;

/*
 * Setup vdso data page.
 */
static void vdso_init_data(struct vdso_data *vd)
{
	vd->ectg_available = user_mode != HOME_SPACE_MODE && test_facility(31);
}

#ifdef CONFIG_64BIT
/*
 * Setup per cpu vdso data page.
 */
static void vdso_init_per_cpu_data(int cpu, struct vdso_per_cpu_data *vpcd)
{
}

/*
 * Allocate/free per cpu vdso data.
 */
#define SEGMENT_ORDER	2

int vdso_alloc_per_cpu(int cpu, struct _lowcore *lowcore)
{
	unsigned long segment_table, page_table, page_frame;
	u32 *psal, *aste;
	int i;

	lowcore->vdso_per_cpu_data = __LC_PASTE;

	if (user_mode == HOME_SPACE_MODE || !vdso_enabled)
		return 0;

	segment_table = __get_free_pages(GFP_KERNEL, SEGMENT_ORDER);
	page_table = get_zeroed_page(GFP_KERNEL | GFP_DMA);
	page_frame = get_zeroed_page(GFP_KERNEL);
	if (!segment_table || !page_table || !page_frame)
		goto out;

	clear_table((unsigned long *) segment_table, _SEGMENT_ENTRY_EMPTY,
		    PAGE_SIZE << SEGMENT_ORDER);
	clear_table((unsigned long *) page_table, _PAGE_TYPE_EMPTY,
		    256*sizeof(unsigned long));

	*(unsigned long *) segment_table = _SEGMENT_ENTRY + page_table;
	*(unsigned long *) page_table = _PAGE_RO + page_frame;

	psal = (u32 *) (page_table + 256*sizeof(unsigned long));
	aste = psal + 32;

	for (i = 4; i < 32; i += 4)
		psal[i] = 0x80000000;

	lowcore->paste[4] = (u32)(addr_t) psal;
	psal[0] = 0x20000000;
	psal[2] = (u32)(addr_t) aste;
	*(unsigned long *) (aste + 2) = segment_table +
		_ASCE_TABLE_LENGTH + _ASCE_USER_BITS + _ASCE_TYPE_SEGMENT;
	aste[4] = (u32)(addr_t) psal;
	lowcore->vdso_per_cpu_data = page_frame;

	vdso_init_per_cpu_data(cpu, (struct vdso_per_cpu_data *) page_frame);
	return 0;

out:
	free_page(page_frame);
	free_page(page_table);
	free_pages(segment_table, SEGMENT_ORDER);
	return -ENOMEM;
}

void vdso_free_per_cpu(int cpu, struct _lowcore *lowcore)
{
	unsigned long segment_table, page_table, page_frame;
	u32 *psal, *aste;

	if (user_mode == HOME_SPACE_MODE || !vdso_enabled)
		return;

	psal = (u32 *)(addr_t) lowcore->paste[4];
	aste = (u32 *)(addr_t) psal[2];
	segment_table = *(unsigned long *)(aste + 2) & PAGE_MASK;
	page_table = *(unsigned long *) segment_table;
	page_frame = *(unsigned long *) page_table;

	free_page(page_frame);
	free_page(page_table);
	free_pages(segment_table, SEGMENT_ORDER);
}

static void __vdso_init_cr5(void *dummy)
{
	unsigned long cr5;

	cr5 = offsetof(struct _lowcore, paste);
	__ctl_load(cr5, 5, 5);
}

static void vdso_init_cr5(void)
{
	if (user_mode != HOME_SPACE_MODE && vdso_enabled)
		on_each_cpu(__vdso_init_cr5, NULL, 1);
}
#endif /* CONFIG_64BIT */

/*
 * This is called from binfmt_elf, we create the special vma for the
 * vDSO and insert it into the mm struct tree
 */
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
	struct mm_struct *mm = current->mm;
	struct page **vdso_pagelist;
	unsigned long vdso_pages;
	unsigned long vdso_base;
	int rc;

	if (!vdso_enabled)
		return 0;
	/*
	 * Only map the vdso for dynamically linked elf binaries.
	 */
	if (!uses_interp)
		return 0;

#ifdef CONFIG_64BIT
	vdso_pagelist = vdso64_pagelist;
	vdso_pages = vdso64_pages;
#ifdef CONFIG_COMPAT
	if (is_compat_task()) {
		vdso_pagelist = vdso32_pagelist;
		vdso_pages = vdso32_pages;
	}
#endif
#else
	vdso_pagelist = vdso32_pagelist;
	vdso_pages = vdso32_pages;
#endif

	/*
	 * vDSO has a problem and was disabled, just don't "enable" it for
	 * the process
	 */
	if (vdso_pages == 0)
		return 0;

	current->mm->context.vdso_base = 0;

	/*
	 * pick a base address for the vDSO in process space. We try to put
	 * it at vdso_base which is the "natural" base for it, but we might
	 * fail and end up putting it elsewhere.
	 */
	down_write(&mm->mmap_sem);
	vdso_base = get_unmapped_area(NULL, 0, vdso_pages << PAGE_SHIFT, 0, 0);
	if (IS_ERR_VALUE(vdso_base)) {
		rc = vdso_base;
		goto out_up;
	}

	/*
	 * Put vDSO base into mm struct. We need to do this before calling
	 * install_special_mapping or the perf counter mmap tracking code
	 * will fail to recognise it as a vDSO (since arch_vma_name fails).
	 */
	current->mm->context.vdso_base = vdso_base;

	/*
	 * our vma flags don't have VM_WRITE so by default, the process
	 * isn't allowed to write those pages.
	 * gdb can break that with ptrace interface, and thus trigger COW
	 * on those pages but it's then your responsibility to never do that
	 * on the "data" page of the vDSO or you'll stop getting kernel
	 * updates and your nice userland gettimeofday will be totally dead.
	 * It's fine to use that for setting breakpoints in the vDSO code
	 * pages though
	 *
	 * Make sure the vDSO gets into every core dump.
	 * Dumping its contents makes post-mortem fully interpretable later
	 * without matching up the same kernel and hardware config to see
	 * what PC values meant.
	 */
	rc = install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
				     VM_READ|VM_EXEC|
				     VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
				     VM_ALWAYSDUMP,
				     vdso_pagelist);
	if (rc)
		current->mm->context.vdso_base = 0;
out_up:
	up_write(&mm->mmap_sem);
	return rc;
}

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

static int __init vdso_init(void)
{
	int i;

	if (!vdso_enabled)
		return 0;
	vdso_init_data(vdso_data);
#if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT)
	/* Calculate the size of the 32 bit vDSO */
	vdso32_pages = ((&vdso32_end - &vdso32_start
			 + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;

	/* Make sure pages are in the correct state */
	vdso32_pagelist = kzalloc(sizeof(struct page *) * (vdso32_pages + 1),
				  GFP_KERNEL);
	BUG_ON(vdso32_pagelist == NULL);
	for (i = 0; i < vdso32_pages - 1; i++) {
		struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE);
		ClearPageReserved(pg);
		get_page(pg);
		vdso32_pagelist[i] = pg;
	}
	vdso32_pagelist[vdso32_pages - 1] = virt_to_page(vdso_data);
	vdso32_pagelist[vdso32_pages] = NULL;
#endif

#ifdef CONFIG_64BIT
	/* Calculate the size of the 64 bit vDSO */
	vdso64_pages = ((&vdso64_end - &vdso64_start
			 + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;

	/* Make sure pages are in the correct state */
	vdso64_pagelist = kzalloc(sizeof(struct page *) * (vdso64_pages + 1),
				  GFP_KERNEL);
	BUG_ON(vdso64_pagelist == NULL);
	for (i = 0; i < vdso64_pages - 1; i++) {
		struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE);
		ClearPageReserved(pg);
		get_page(pg);
		vdso64_pagelist[i] = pg;
	}
	vdso64_pagelist[vdso64_pages - 1] = virt_to_page(vdso_data);
	vdso64_pagelist[vdso64_pages] = NULL;
#ifndef CONFIG_SMP
	if (vdso_alloc_per_cpu(0, &S390_lowcore))
		BUG();
#endif
	vdso_init_cr5();
#endif /* CONFIG_64BIT */

	get_page(virt_to_page(vdso_data));

	smp_wmb();

	return 0;
}
arch_initcall(vdso_init);

int in_gate_area_no_task(unsigned long addr)
{
	return 0;
}

int in_gate_area(struct task_struct *task, unsigned long addr)
{
	return 0;
}

struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
{
	return NULL;
}