summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kernel/vdso.c
blob: 4abc0194970208713f428ec0eb4545d8016ea481 (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
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
// SPDX-License-Identifier: GPL-2.0-or-later

/*
 *    Copyright (C) 2004 Benjamin Herrenschmidt, IBM Corp.
 *			 <benh@kernel.crashing.org>
 */

#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/memblock.h>
#include <linux/syscalls.h>
#include <linux/time_namespace.h>
#include <vdso/datapage.h>

#include <asm/syscall.h>
#include <asm/processor.h>
#include <asm/mmu.h>
#include <asm/mmu_context.h>
#include <asm/machdep.h>
#include <asm/cputable.h>
#include <asm/sections.h>
#include <asm/firmware.h>
#include <asm/vdso.h>
#include <asm/vdso_datapage.h>
#include <asm/setup.h>

/* The alignment of the vDSO */
#define VDSO_ALIGNMENT	(1 << 16)

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

long sys_ni_syscall(void);

/*
 * The vdso data page (aka. systemcfg for old ppc64 fans) is here.
 * Once the early boot kernel code no longer needs to muck around
 * with it, it will become dynamically allocated
 */
static union {
	struct vdso_arch_data	data;
	u8			page[PAGE_SIZE];
} vdso_data_store __page_aligned_data;
struct vdso_arch_data *vdso_data = &vdso_data_store.data;

enum vvar_pages {
	VVAR_DATA_PAGE_OFFSET,
	VVAR_TIMENS_PAGE_OFFSET,
	VVAR_NR_PAGES,
};

static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma,
		       unsigned long text_size)
{
	unsigned long new_size = new_vma->vm_end - new_vma->vm_start;

	if (new_size != text_size)
		return -EINVAL;

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

	return 0;
}

static int vdso32_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma)
{
	return vdso_mremap(sm, new_vma, &vdso32_end - &vdso32_start);
}

static int vdso64_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma)
{
	return vdso_mremap(sm, new_vma, &vdso64_end - &vdso64_start);
}

static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
			     struct vm_area_struct *vma, struct vm_fault *vmf);

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

static struct vm_special_mapping vdso32_spec __ro_after_init = {
	.name = "[vdso]",
	.mremap = vdso32_mremap,
};

static struct vm_special_mapping vdso64_spec __ro_after_init = {
	.name = "[vdso]",
	.mremap = vdso64_mremap,
};

#ifdef CONFIG_TIME_NS
struct vdso_data *arch_get_vdso_data(void *vvar_page)
{
	return ((struct vdso_arch_data *)vvar_page)->data;
}

/*
 * The vvar mapping contains data for a specific time namespace, so when a task
 * changes namespace we must unmap its vvar data for the old namespace.
 * Subsequent faults will map in data for the new namespace.
 *
 * For more details see timens_setup_vdso_data().
 */
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) {
		unsigned long size = vma->vm_end - vma->vm_start;

		if (vma_is_special_mapping(vma, &vvar_spec))
			zap_page_range(vma, vma->vm_start, size);
	}
	mmap_read_unlock(mm);

	return 0;
}

static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
{
	if (likely(vma->vm_mm == current->mm))
		return current->nsproxy->time_ns->vvar_page;

	/*
	 * VM_PFNMAP | VM_IO protect .fault() handler from being called
	 * through interfaces like /proc/$pid/mem or
	 * process_vm_{readv,writev}() as long as there's no .access()
	 * in special_mapping_vmops.
	 * For more details check_vma_flags() and __access_remote_vm()
	 */
	WARN(1, "vvar_page accessed remotely");

	return NULL;
}
#else
static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
{
	return NULL;
}
#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 pfn;

	switch (vmf->pgoff) {
	case VVAR_DATA_PAGE_OFFSET:
		if (timens_page)
			pfn = page_to_pfn(timens_page);
		else
			pfn = virt_to_pfn(vdso_data);
		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);
}

/*
 * This is called from binfmt_elf, we create the special vma for the
 * vDSO and insert it into the mm struct tree
 */
static int __arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
	unsigned long vdso_size, vdso_base, mappings_size;
	struct vm_special_mapping *vdso_spec;
	unsigned long vvar_size = VVAR_NR_PAGES * PAGE_SIZE;
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;

	if (is_32bit_task()) {
		vdso_spec = &vdso32_spec;
		vdso_size = &vdso32_end - &vdso32_start;
	} else {
		vdso_spec = &vdso64_spec;
		vdso_size = &vdso64_end - &vdso64_start;
	}

	mappings_size = vdso_size + vvar_size;
	mappings_size += (VDSO_ALIGNMENT - 1) & PAGE_MASK;

	/*
	 * Pick a base address for the vDSO in process space.
	 * Add enough to the size so that the result can be aligned.
	 */
	vdso_base = get_unmapped_area(NULL, 0, mappings_size, 0, 0);
	if (IS_ERR_VALUE(vdso_base))
		return vdso_base;

	/* Add required alignment. */
	vdso_base = ALIGN(vdso_base, VDSO_ALIGNMENT);

	/*
	 * 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.
	 */
	mm->context.vdso = (void __user *)vdso_base + vvar_size;

	vma = _install_special_mapping(mm, vdso_base, vvar_size,
				       VM_READ | VM_MAYREAD | VM_IO |
				       VM_DONTDUMP | VM_PFNMAP, &vvar_spec);
	if (IS_ERR(vma))
		return PTR_ERR(vma);

	/*
	 * 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.
	 */
	vma = _install_special_mapping(mm, vdso_base + vvar_size, vdso_size,
				       VM_READ | VM_EXEC | VM_MAYREAD |
				       VM_MAYWRITE | VM_MAYEXEC, vdso_spec);
	if (IS_ERR(vma))
		do_munmap(mm, vdso_base, vvar_size, NULL);

	return PTR_ERR_OR_ZERO(vma);
}

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

	mm->context.vdso = NULL;

	if (mmap_write_lock_killable(mm))
		return -EINTR;

	rc = __arch_setup_additional_pages(bprm, uses_interp);
	if (rc)
		mm->context.vdso = NULL;

	mmap_write_unlock(mm);
	return rc;
}

#define VDSO_DO_FIXUPS(type, value, bits, sec) do {					\
	void *__start = (void *)VDSO##bits##_SYMBOL(&vdso##bits##_start, sec##_start);	\
	void *__end = (void *)VDSO##bits##_SYMBOL(&vdso##bits##_start, sec##_end);	\
											\
	do_##type##_fixups((value), __start, __end);					\
} while (0)

static void __init vdso_fixup_features(void)
{
#ifdef CONFIG_PPC64
	VDSO_DO_FIXUPS(feature, cur_cpu_spec->cpu_features, 64, ftr_fixup);
	VDSO_DO_FIXUPS(feature, cur_cpu_spec->mmu_features, 64, mmu_ftr_fixup);
	VDSO_DO_FIXUPS(feature, powerpc_firmware_features, 64, fw_ftr_fixup);
	VDSO_DO_FIXUPS(lwsync, cur_cpu_spec->cpu_features, 64, lwsync_fixup);
#endif /* CONFIG_PPC64 */

#ifdef CONFIG_VDSO32
	VDSO_DO_FIXUPS(feature, cur_cpu_spec->cpu_features, 32, ftr_fixup);
	VDSO_DO_FIXUPS(feature, cur_cpu_spec->mmu_features, 32, mmu_ftr_fixup);
#ifdef CONFIG_PPC64
	VDSO_DO_FIXUPS(feature, powerpc_firmware_features, 32, fw_ftr_fixup);
#endif /* CONFIG_PPC64 */
	VDSO_DO_FIXUPS(lwsync, cur_cpu_spec->cpu_features, 32, lwsync_fixup);
#endif
}

/*
 * Called from setup_arch to initialize the bitmap of available
 * syscalls in the systemcfg page
 */
static void __init vdso_setup_syscall_map(void)
{
	unsigned int i;

	for (i = 0; i < NR_syscalls; i++) {
		if (sys_call_table[i] != (void *)&sys_ni_syscall)
			vdso_data->syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
		if (IS_ENABLED(CONFIG_COMPAT) &&
		    compat_sys_call_table[i] != (void *)&sys_ni_syscall)
			vdso_data->compat_syscall_map[i >> 5] |= 0x80000000UL >> (i & 0x1f);
	}
}

#ifdef CONFIG_PPC64
int vdso_getcpu_init(void)
{
	unsigned long cpu, node, val;

	/*
	 * SPRG_VDSO contains the CPU in the bottom 16 bits and the NUMA node
	 * in the next 16 bits.  The VDSO uses this to implement getcpu().
	 */
	cpu = get_cpu();
	WARN_ON_ONCE(cpu > 0xffff);

	node = cpu_to_node(cpu);
	WARN_ON_ONCE(node > 0xffff);

	val = (cpu & 0xffff) | ((node & 0xffff) << 16);
	mtspr(SPRN_SPRG_VDSO_WRITE, val);
	get_paca()->sprg_vdso = val;

	put_cpu();

	return 0;
}
/* We need to call this before SMP init */
early_initcall(vdso_getcpu_init);
#endif

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

	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)
{
#ifdef CONFIG_PPC64
	/*
	 * Fill up the "systemcfg" stuff for backward compatibility
	 */
	strcpy((char *)vdso_data->eye_catcher, "SYSTEMCFG:PPC64");
	vdso_data->version.major = SYSTEMCFG_MAJOR;
	vdso_data->version.minor = SYSTEMCFG_MINOR;
	vdso_data->processor = mfspr(SPRN_PVR);
	/*
	 * Fake the old platform number for pSeries and add
	 * in LPAR bit if necessary
	 */
	vdso_data->platform = 0x100;
	if (firmware_has_feature(FW_FEATURE_LPAR))
		vdso_data->platform |= 1;
	vdso_data->physicalMemorySize = memblock_phys_mem_size();
	vdso_data->dcache_size = ppc64_caches.l1d.size;
	vdso_data->dcache_line_size = ppc64_caches.l1d.line_size;
	vdso_data->icache_size = ppc64_caches.l1i.size;
	vdso_data->icache_line_size = ppc64_caches.l1i.line_size;
	vdso_data->dcache_block_size = ppc64_caches.l1d.block_size;
	vdso_data->icache_block_size = ppc64_caches.l1i.block_size;
	vdso_data->dcache_log_block_size = ppc64_caches.l1d.log_block_size;
	vdso_data->icache_log_block_size = ppc64_caches.l1i.log_block_size;
#endif /* CONFIG_PPC64 */

	vdso_setup_syscall_map();

	vdso_fixup_features();

	if (IS_ENABLED(CONFIG_VDSO32))
		vdso32_spec.pages = vdso_setup_pages(&vdso32_start, &vdso32_end);

	if (IS_ENABLED(CONFIG_PPC64))
		vdso64_spec.pages = vdso_setup_pages(&vdso64_start, &vdso64_end);

	smp_wmb();

	return 0;
}
arch_initcall(vdso_init);