summaryrefslogtreecommitdiff
path: root/arch/arm64/mm/pageattr.c
blob: d107c3d434e224552ae34011a4df3319cc977516 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (c) 2014, The Linux Foundation. All rights reserved.
 */
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/vmalloc.h>

#include <asm/cacheflush.h>
#include <asm/set_memory.h>
#include <asm/tlbflush.h>

struct page_change_data {
	pgprot_t set_mask;
	pgprot_t clear_mask;
};

bool rodata_full __ro_after_init = IS_ENABLED(CONFIG_RODATA_FULL_DEFAULT_ENABLED);

bool can_set_direct_map(void)
{
	/*
	 * rodata_full, DEBUG_PAGEALLOC and KFENCE require linear map to be
	 * mapped at page granularity, so that it is possible to
	 * protect/unprotect single pages.
	 */
	return rodata_full || debug_pagealloc_enabled() ||
		IS_ENABLED(CONFIG_KFENCE);
}

static int change_page_range(pte_t *ptep, unsigned long addr, void *data)
{
	struct page_change_data *cdata = data;
	pte_t pte = READ_ONCE(*ptep);

	pte = clear_pte_bit(pte, cdata->clear_mask);
	pte = set_pte_bit(pte, cdata->set_mask);

	set_pte(ptep, pte);
	return 0;
}

/*
 * This function assumes that the range is mapped with PAGE_SIZE pages.
 */
static int __change_memory_common(unsigned long start, unsigned long size,
				pgprot_t set_mask, pgprot_t clear_mask)
{
	struct page_change_data data;
	int ret;

	data.set_mask = set_mask;
	data.clear_mask = clear_mask;

	ret = apply_to_page_range(&init_mm, start, size, change_page_range,
					&data);

	flush_tlb_kernel_range(start, start + size);
	return ret;
}

static int change_memory_common(unsigned long addr, int numpages,
				pgprot_t set_mask, pgprot_t clear_mask)
{
	unsigned long start = addr;
	unsigned long size = PAGE_SIZE * numpages;
	unsigned long end = start + size;
	struct vm_struct *area;
	int i;

	if (!PAGE_ALIGNED(addr)) {
		start &= PAGE_MASK;
		end = start + size;
		WARN_ON_ONCE(1);
	}

	/*
	 * Kernel VA mappings are always live, and splitting live section
	 * mappings into page mappings may cause TLB conflicts. This means
	 * we have to ensure that changing the permission bits of the range
	 * we are operating on does not result in such splitting.
	 *
	 * Let's restrict ourselves to mappings created by vmalloc (or vmap).
	 * Those are guaranteed to consist entirely of page mappings, and
	 * splitting is never needed.
	 *
	 * So check whether the [addr, addr + size) interval is entirely
	 * covered by precisely one VM area that has the VM_ALLOC flag set.
	 */
	area = find_vm_area((void *)addr);
	if (!area ||
	    end > (unsigned long)kasan_reset_tag(area->addr) + area->size ||
	    !(area->flags & VM_ALLOC))
		return -EINVAL;

	if (!numpages)
		return 0;

	/*
	 * If we are manipulating read-only permissions, apply the same
	 * change to the linear mapping of the pages that back this VM area.
	 */
	if (rodata_full && (pgprot_val(set_mask) == PTE_RDONLY ||
			    pgprot_val(clear_mask) == PTE_RDONLY)) {
		for (i = 0; i < area->nr_pages; i++) {
			__change_memory_common((u64)page_address(area->pages[i]),
					       PAGE_SIZE, set_mask, clear_mask);
		}
	}

	/*
	 * Get rid of potentially aliasing lazily unmapped vm areas that may
	 * have permissions set that deviate from the ones we are setting here.
	 */
	vm_unmap_aliases();

	return __change_memory_common(start, size, set_mask, clear_mask);
}

int set_memory_ro(unsigned long addr, int numpages)
{
	return change_memory_common(addr, numpages,
					__pgprot(PTE_RDONLY),
					__pgprot(PTE_WRITE));
}

int set_memory_rw(unsigned long addr, int numpages)
{
	return change_memory_common(addr, numpages,
					__pgprot(PTE_WRITE),
					__pgprot(PTE_RDONLY));
}

int set_memory_nx(unsigned long addr, int numpages)
{
	return change_memory_common(addr, numpages,
					__pgprot(PTE_PXN),
					__pgprot(PTE_MAYBE_GP));
}

int set_memory_x(unsigned long addr, int numpages)
{
	return change_memory_common(addr, numpages,
					__pgprot(PTE_MAYBE_GP),
					__pgprot(PTE_PXN));
}

int set_memory_valid(unsigned long addr, int numpages, int enable)
{
	if (enable)
		return __change_memory_common(addr, PAGE_SIZE * numpages,
					__pgprot(PTE_VALID),
					__pgprot(0));
	else
		return __change_memory_common(addr, PAGE_SIZE * numpages,
					__pgprot(0),
					__pgprot(PTE_VALID));
}

int set_direct_map_invalid_noflush(struct page *page)
{
	struct page_change_data data = {
		.set_mask = __pgprot(0),
		.clear_mask = __pgprot(PTE_VALID),
	};

	if (!can_set_direct_map())
		return 0;

	return apply_to_page_range(&init_mm,
				   (unsigned long)page_address(page),
				   PAGE_SIZE, change_page_range, &data);
}

int set_direct_map_default_noflush(struct page *page)
{
	struct page_change_data data = {
		.set_mask = __pgprot(PTE_VALID | PTE_WRITE),
		.clear_mask = __pgprot(PTE_RDONLY),
	};

	if (!can_set_direct_map())
		return 0;

	return apply_to_page_range(&init_mm,
				   (unsigned long)page_address(page),
				   PAGE_SIZE, change_page_range, &data);
}

#ifdef CONFIG_DEBUG_PAGEALLOC
void __kernel_map_pages(struct page *page, int numpages, int enable)
{
	if (!can_set_direct_map())
		return;

	set_memory_valid((unsigned long)page_address(page), numpages, enable);
}
#endif /* CONFIG_DEBUG_PAGEALLOC */

/*
 * This function is used to determine if a linear map page has been marked as
 * not-valid. Walk the page table and check the PTE_VALID bit. This is based
 * on kern_addr_valid(), which almost does what we need.
 *
 * Because this is only called on the kernel linear map,  p?d_sect() implies
 * p?d_present(). When debug_pagealloc is enabled, sections mappings are
 * disabled.
 */
bool kernel_page_present(struct page *page)
{
	pgd_t *pgdp;
	p4d_t *p4dp;
	pud_t *pudp, pud;
	pmd_t *pmdp, pmd;
	pte_t *ptep;
	unsigned long addr = (unsigned long)page_address(page);

	if (!can_set_direct_map())
		return true;

	pgdp = pgd_offset_k(addr);
	if (pgd_none(READ_ONCE(*pgdp)))
		return false;

	p4dp = p4d_offset(pgdp, addr);
	if (p4d_none(READ_ONCE(*p4dp)))
		return false;

	pudp = pud_offset(p4dp, addr);
	pud = READ_ONCE(*pudp);
	if (pud_none(pud))
		return false;
	if (pud_sect(pud))
		return true;

	pmdp = pmd_offset(pudp, addr);
	pmd = READ_ONCE(*pmdp);
	if (pmd_none(pmd))
		return false;
	if (pmd_sect(pmd))
		return true;

	ptep = pte_offset_kernel(pmdp, addr);
	return pte_valid(READ_ONCE(*ptep));
}