summaryrefslogtreecommitdiffstats
path: root/arch/arm64/mm/trans_pgd.c
blob: 527f0a39c3da55261e678f94b1e505b709f3a2a4 (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
// SPDX-License-Identifier: GPL-2.0

/*
 * Transitional page tables for kexec and hibernate
 *
 * This file derived from: arch/arm64/kernel/hibernate.c
 *
 * Copyright (c) 2020, Microsoft Corporation.
 * Pavel Tatashin <pasha.tatashin@soleen.com>
 *
 */

/*
 * Transitional tables are used during system transferring from one world to
 * another: such as during hibernate restore, and kexec reboots. During these
 * phases one cannot rely on page table not being overwritten. This is because
 * hibernate and kexec can overwrite the current page tables during transition.
 */

#include <asm/trans_pgd.h>
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
#include <linux/suspend.h>
#include <linux/bug.h>
#include <linux/mm.h>
#include <linux/mmzone.h>

static void *trans_alloc(struct trans_pgd_info *info)
{
	return info->trans_alloc_page(info->trans_alloc_arg);
}

static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
{
	pte_t pte = READ_ONCE(*src_ptep);

	if (pte_valid(pte)) {
		/*
		 * Resume will overwrite areas that may be marked
		 * read only (code, rodata). Clear the RDONLY bit from
		 * the temporary mappings we use during restore.
		 */
		set_pte(dst_ptep, pte_mkwrite(pte));
	} else if (debug_pagealloc_enabled() && !pte_none(pte)) {
		/*
		 * debug_pagealloc will removed the PTE_VALID bit if
		 * the page isn't in use by the resume kernel. It may have
		 * been in use by the original kernel, in which case we need
		 * to put it back in our copy to do the restore.
		 *
		 * Before marking this entry valid, check the pfn should
		 * be mapped.
		 */
		BUG_ON(!pfn_valid(pte_pfn(pte)));

		set_pte(dst_ptep, pte_mkpresent(pte_mkwrite(pte)));
	}
}

static int copy_pte(struct trans_pgd_info *info, pmd_t *dst_pmdp,
		    pmd_t *src_pmdp, unsigned long start, unsigned long end)
{
	pte_t *src_ptep;
	pte_t *dst_ptep;
	unsigned long addr = start;

	dst_ptep = trans_alloc(info);
	if (!dst_ptep)
		return -ENOMEM;
	pmd_populate_kernel(NULL, dst_pmdp, dst_ptep);
	dst_ptep = pte_offset_kernel(dst_pmdp, start);

	src_ptep = pte_offset_kernel(src_pmdp, start);
	do {
		_copy_pte(dst_ptep, src_ptep, addr);
	} while (dst_ptep++, src_ptep++, addr += PAGE_SIZE, addr != end);

	return 0;
}

static int copy_pmd(struct trans_pgd_info *info, pud_t *dst_pudp,
		    pud_t *src_pudp, unsigned long start, unsigned long end)
{
	pmd_t *src_pmdp;
	pmd_t *dst_pmdp;
	unsigned long next;
	unsigned long addr = start;

	if (pud_none(READ_ONCE(*dst_pudp))) {
		dst_pmdp = trans_alloc(info);
		if (!dst_pmdp)
			return -ENOMEM;
		pud_populate(NULL, dst_pudp, dst_pmdp);
	}
	dst_pmdp = pmd_offset(dst_pudp, start);

	src_pmdp = pmd_offset(src_pudp, start);
	do {
		pmd_t pmd = READ_ONCE(*src_pmdp);

		next = pmd_addr_end(addr, end);
		if (pmd_none(pmd))
			continue;
		if (pmd_table(pmd)) {
			if (copy_pte(info, dst_pmdp, src_pmdp, addr, next))
				return -ENOMEM;
		} else {
			set_pmd(dst_pmdp,
				__pmd(pmd_val(pmd) & ~PMD_SECT_RDONLY));
		}
	} while (dst_pmdp++, src_pmdp++, addr = next, addr != end);

	return 0;
}

static int copy_pud(struct trans_pgd_info *info, p4d_t *dst_p4dp,
		    p4d_t *src_p4dp, unsigned long start,
		    unsigned long end)
{
	pud_t *dst_pudp;
	pud_t *src_pudp;
	unsigned long next;
	unsigned long addr = start;

	if (p4d_none(READ_ONCE(*dst_p4dp))) {
		dst_pudp = trans_alloc(info);
		if (!dst_pudp)
			return -ENOMEM;
		p4d_populate(NULL, dst_p4dp, dst_pudp);
	}
	dst_pudp = pud_offset(dst_p4dp, start);

	src_pudp = pud_offset(src_p4dp, start);
	do {
		pud_t pud = READ_ONCE(*src_pudp);

		next = pud_addr_end(addr, end);
		if (pud_none(pud))
			continue;
		if (pud_table(pud)) {
			if (copy_pmd(info, dst_pudp, src_pudp, addr, next))
				return -ENOMEM;
		} else {
			set_pud(dst_pudp,
				__pud(pud_val(pud) & ~PUD_SECT_RDONLY));
		}
	} while (dst_pudp++, src_pudp++, addr = next, addr != end);

	return 0;
}

static int copy_p4d(struct trans_pgd_info *info, pgd_t *dst_pgdp,
		    pgd_t *src_pgdp, unsigned long start,
		    unsigned long end)
{
	p4d_t *dst_p4dp;
	p4d_t *src_p4dp;
	unsigned long next;
	unsigned long addr = start;

	dst_p4dp = p4d_offset(dst_pgdp, start);
	src_p4dp = p4d_offset(src_pgdp, start);
	do {
		next = p4d_addr_end(addr, end);
		if (p4d_none(READ_ONCE(*src_p4dp)))
			continue;
		if (copy_pud(info, dst_p4dp, src_p4dp, addr, next))
			return -ENOMEM;
	} while (dst_p4dp++, src_p4dp++, addr = next, addr != end);

	return 0;
}

static int copy_page_tables(struct trans_pgd_info *info, pgd_t *dst_pgdp,
			    unsigned long start, unsigned long end)
{
	unsigned long next;
	unsigned long addr = start;
	pgd_t *src_pgdp = pgd_offset_k(start);

	dst_pgdp = pgd_offset_pgd(dst_pgdp, start);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none(READ_ONCE(*src_pgdp)))
			continue;
		if (copy_p4d(info, dst_pgdp, src_pgdp, addr, next))
			return -ENOMEM;
	} while (dst_pgdp++, src_pgdp++, addr = next, addr != end);

	return 0;
}

/*
 * Create trans_pgd and copy linear map.
 * info:	contains allocator and its argument
 * dst_pgdp:	new page table that is created, and to which map is copied.
 * start:	Start of the interval (inclusive).
 * end:		End of the interval (exclusive).
 *
 * Returns 0 on success, and -ENOMEM on failure.
 */
int trans_pgd_create_copy(struct trans_pgd_info *info, pgd_t **dst_pgdp,
			  unsigned long start, unsigned long end)
{
	int rc;
	pgd_t *trans_pgd = trans_alloc(info);

	if (!trans_pgd) {
		pr_err("Failed to allocate memory for temporary page tables.\n");
		return -ENOMEM;
	}

	rc = copy_page_tables(info, trans_pgd, start, end);
	if (!rc)
		*dst_pgdp = trans_pgd;

	return rc;
}

/*
 * Add map entry to trans_pgd for a base-size page at PTE level.
 * info:	contains allocator and its argument
 * trans_pgd:	page table in which new map is added.
 * page:	page to be mapped.
 * dst_addr:	new VA address for the page
 * pgprot:	protection for the page.
 *
 * Returns 0 on success, and -ENOMEM on failure.
 */
int trans_pgd_map_page(struct trans_pgd_info *info, pgd_t *trans_pgd,
		       void *page, unsigned long dst_addr, pgprot_t pgprot)
{
	pgd_t *pgdp;
	p4d_t *p4dp;
	pud_t *pudp;
	pmd_t *pmdp;
	pte_t *ptep;

	pgdp = pgd_offset_pgd(trans_pgd, dst_addr);
	if (pgd_none(READ_ONCE(*pgdp))) {
		p4dp = trans_alloc(info);
		if (!pgdp)
			return -ENOMEM;
		pgd_populate(NULL, pgdp, p4dp);
	}

	p4dp = p4d_offset(pgdp, dst_addr);
	if (p4d_none(READ_ONCE(*p4dp))) {
		pudp = trans_alloc(info);
		if (!pudp)
			return -ENOMEM;
		p4d_populate(NULL, p4dp, pudp);
	}

	pudp = pud_offset(p4dp, dst_addr);
	if (pud_none(READ_ONCE(*pudp))) {
		pmdp = trans_alloc(info);
		if (!pmdp)
			return -ENOMEM;
		pud_populate(NULL, pudp, pmdp);
	}

	pmdp = pmd_offset(pudp, dst_addr);
	if (pmd_none(READ_ONCE(*pmdp))) {
		ptep = trans_alloc(info);
		if (!ptep)
			return -ENOMEM;
		pmd_populate_kernel(NULL, pmdp, ptep);
	}

	ptep = pte_offset_kernel(pmdp, dst_addr);
	set_pte(ptep, pfn_pte(virt_to_pfn(page), pgprot));

	return 0;
}

/*
 * The page we want to idmap may be outside the range covered by VA_BITS that
 * can be built using the kernel's p?d_populate() helpers. As a one off, for a
 * single page, we build these page tables bottom up and just assume that will
 * need the maximum T0SZ.
 *
 * Returns 0 on success, and -ENOMEM on failure.
 * On success trans_ttbr0 contains page table with idmapped page, t0sz is set to
 * maximum T0SZ for this page.
 */
int trans_pgd_idmap_page(struct trans_pgd_info *info, phys_addr_t *trans_ttbr0,
			 unsigned long *t0sz, void *page)
{
	phys_addr_t dst_addr = virt_to_phys(page);
	unsigned long pfn = __phys_to_pfn(dst_addr);
	int max_msb = (dst_addr & GENMASK(52, 48)) ? 51 : 47;
	int bits_mapped = PAGE_SHIFT - 4;
	unsigned long level_mask, prev_level_entry, *levels[4];
	int this_level, index, level_lsb, level_msb;

	dst_addr &= PAGE_MASK;
	prev_level_entry = pte_val(pfn_pte(pfn, PAGE_KERNEL_EXEC));

	for (this_level = 3; this_level >= 0; this_level--) {
		levels[this_level] = trans_alloc(info);
		if (!levels[this_level])
			return -ENOMEM;

		level_lsb = ARM64_HW_PGTABLE_LEVEL_SHIFT(this_level);
		level_msb = min(level_lsb + bits_mapped, max_msb);
		level_mask = GENMASK_ULL(level_msb, level_lsb);

		index = (dst_addr & level_mask) >> level_lsb;
		*(levels[this_level] + index) = prev_level_entry;

		pfn = virt_to_pfn(levels[this_level]);
		prev_level_entry = pte_val(pfn_pte(pfn,
						   __pgprot(PMD_TYPE_TABLE)));

		if (level_msb == max_msb)
			break;
	}

	*trans_ttbr0 = phys_to_ttbr(__pfn_to_phys(pfn));
	*t0sz = TCR_T0SZ(max_msb + 1);

	return 0;
}