summaryrefslogtreecommitdiffstats
path: root/mm/debug_vm_pgtable.c
blob: e45623016aea101c4234c0c207b63d76b3ae358f (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * This kernel test validates architecture page table helpers and
 * accessors and helps in verifying their continued compliance with
 * expected generic MM semantics.
 *
 * Copyright (C) 2019 ARM Ltd.
 *
 * Author: Anshuman Khandual <anshuman.khandual@arm.com>
 */
#define pr_fmt(fmt) "debug_vm_pgtable: %s: " fmt, __func__

#include <linux/gfp.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
#include <linux/kernel.h>
#include <linux/kconfig.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/mm_types.h>
#include <linux/module.h>
#include <linux/pfn_t.h>
#include <linux/printk.h>
#include <linux/random.h>
#include <linux/spinlock.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/start_kernel.h>
#include <linux/sched/mm.h>
#include <asm/pgalloc.h>

#define VMFLAGS	(VM_READ|VM_WRITE|VM_EXEC)

/*
 * On s390 platform, the lower 4 bits are used to identify given page table
 * entry type. But these bits might affect the ability to clear entries with
 * pxx_clear() because of how dynamic page table folding works on s390. So
 * while loading up the entries do not change the lower 4 bits. It does not
 * have affect any other platform.
 */
#define S390_MASK_BITS	4
#define RANDOM_ORVALUE	GENMASK(BITS_PER_LONG - 1, S390_MASK_BITS)
#define RANDOM_NZVALUE	GENMASK(7, 0)

static void __init pte_basic_tests(unsigned long pfn, pgprot_t prot)
{
	pte_t pte = pfn_pte(pfn, prot);

	WARN_ON(!pte_same(pte, pte));
	WARN_ON(!pte_young(pte_mkyoung(pte_mkold(pte))));
	WARN_ON(!pte_dirty(pte_mkdirty(pte_mkclean(pte))));
	WARN_ON(!pte_write(pte_mkwrite(pte_wrprotect(pte))));
	WARN_ON(pte_young(pte_mkold(pte_mkyoung(pte))));
	WARN_ON(pte_dirty(pte_mkclean(pte_mkdirty(pte))));
	WARN_ON(pte_write(pte_wrprotect(pte_mkwrite(pte))));
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static void __init pmd_basic_tests(unsigned long pfn, pgprot_t prot)
{
	pmd_t pmd = pfn_pmd(pfn, prot);

	if (!has_transparent_hugepage())
		return;

	WARN_ON(!pmd_same(pmd, pmd));
	WARN_ON(!pmd_young(pmd_mkyoung(pmd_mkold(pmd))));
	WARN_ON(!pmd_dirty(pmd_mkdirty(pmd_mkclean(pmd))));
	WARN_ON(!pmd_write(pmd_mkwrite(pmd_wrprotect(pmd))));
	WARN_ON(pmd_young(pmd_mkold(pmd_mkyoung(pmd))));
	WARN_ON(pmd_dirty(pmd_mkclean(pmd_mkdirty(pmd))));
	WARN_ON(pmd_write(pmd_wrprotect(pmd_mkwrite(pmd))));
	/*
	 * A huge page does not point to next level page table
	 * entry. Hence this must qualify as pmd_bad().
	 */
	WARN_ON(!pmd_bad(pmd_mkhuge(pmd)));
}

#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
static void __init pud_basic_tests(unsigned long pfn, pgprot_t prot)
{
	pud_t pud = pfn_pud(pfn, prot);

	if (!has_transparent_hugepage())
		return;

	WARN_ON(!pud_same(pud, pud));
	WARN_ON(!pud_young(pud_mkyoung(pud_mkold(pud))));
	WARN_ON(!pud_write(pud_mkwrite(pud_wrprotect(pud))));
	WARN_ON(pud_write(pud_wrprotect(pud_mkwrite(pud))));
	WARN_ON(pud_young(pud_mkold(pud_mkyoung(pud))));

	if (mm_pmd_folded(mm))
		return;

	/*
	 * A huge page does not point to next level page table
	 * entry. Hence this must qualify as pud_bad().
	 */
	WARN_ON(!pud_bad(pud_mkhuge(pud)));
}
#else  /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
static void __init pud_basic_tests(unsigned long pfn, pgprot_t prot) { }
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
#else  /* !CONFIG_TRANSPARENT_HUGEPAGE */
static void __init pmd_basic_tests(unsigned long pfn, pgprot_t prot) { }
static void __init pud_basic_tests(unsigned long pfn, pgprot_t prot) { }
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

static void __init p4d_basic_tests(unsigned long pfn, pgprot_t prot)
{
	p4d_t p4d;

	memset(&p4d, RANDOM_NZVALUE, sizeof(p4d_t));
	WARN_ON(!p4d_same(p4d, p4d));
}

static void __init pgd_basic_tests(unsigned long pfn, pgprot_t prot)
{
	pgd_t pgd;

	memset(&pgd, RANDOM_NZVALUE, sizeof(pgd_t));
	WARN_ON(!pgd_same(pgd, pgd));
}

#ifndef __PAGETABLE_PUD_FOLDED
static void __init pud_clear_tests(struct mm_struct *mm, pud_t *pudp)
{
	pud_t pud = READ_ONCE(*pudp);

	if (mm_pmd_folded(mm))
		return;

	pud = __pud(pud_val(pud) | RANDOM_ORVALUE);
	WRITE_ONCE(*pudp, pud);
	pud_clear(pudp);
	pud = READ_ONCE(*pudp);
	WARN_ON(!pud_none(pud));
}

static void __init pud_populate_tests(struct mm_struct *mm, pud_t *pudp,
				      pmd_t *pmdp)
{
	pud_t pud;

	if (mm_pmd_folded(mm))
		return;
	/*
	 * This entry points to next level page table page.
	 * Hence this must not qualify as pud_bad().
	 */
	pmd_clear(pmdp);
	pud_clear(pudp);
	pud_populate(mm, pudp, pmdp);
	pud = READ_ONCE(*pudp);
	WARN_ON(pud_bad(pud));
}
#else  /* !__PAGETABLE_PUD_FOLDED */
static void __init pud_clear_tests(struct mm_struct *mm, pud_t *pudp) { }
static void __init pud_populate_tests(struct mm_struct *mm, pud_t *pudp,
				      pmd_t *pmdp)
{
}
#endif /* PAGETABLE_PUD_FOLDED */

#ifndef __PAGETABLE_P4D_FOLDED
static void __init p4d_clear_tests(struct mm_struct *mm, p4d_t *p4dp)
{
	p4d_t p4d = READ_ONCE(*p4dp);

	if (mm_pud_folded(mm))
		return;

	p4d = __p4d(p4d_val(p4d) | RANDOM_ORVALUE);
	WRITE_ONCE(*p4dp, p4d);
	p4d_clear(p4dp);
	p4d = READ_ONCE(*p4dp);
	WARN_ON(!p4d_none(p4d));
}

static void __init p4d_populate_tests(struct mm_struct *mm, p4d_t *p4dp,
				      pud_t *pudp)
{
	p4d_t p4d;

	if (mm_pud_folded(mm))
		return;

	/*
	 * This entry points to next level page table page.
	 * Hence this must not qualify as p4d_bad().
	 */
	pud_clear(pudp);
	p4d_clear(p4dp);
	p4d_populate(mm, p4dp, pudp);
	p4d = READ_ONCE(*p4dp);
	WARN_ON(p4d_bad(p4d));
}

static void __init pgd_clear_tests(struct mm_struct *mm, pgd_t *pgdp)
{
	pgd_t pgd = READ_ONCE(*pgdp);

	if (mm_p4d_folded(mm))
		return;

	pgd = __pgd(pgd_val(pgd) | RANDOM_ORVALUE);
	WRITE_ONCE(*pgdp, pgd);
	pgd_clear(pgdp);
	pgd = READ_ONCE(*pgdp);
	WARN_ON(!pgd_none(pgd));
}

static void __init pgd_populate_tests(struct mm_struct *mm, pgd_t *pgdp,
				      p4d_t *p4dp)
{
	pgd_t pgd;

	if (mm_p4d_folded(mm))
		return;

	/*
	 * This entry points to next level page table page.
	 * Hence this must not qualify as pgd_bad().
	 */
	p4d_clear(p4dp);
	pgd_clear(pgdp);
	pgd_populate(mm, pgdp, p4dp);
	pgd = READ_ONCE(*pgdp);
	WARN_ON(pgd_bad(pgd));
}
#else  /* !__PAGETABLE_P4D_FOLDED */
static void __init p4d_clear_tests(struct mm_struct *mm, p4d_t *p4dp) { }
static void __init pgd_clear_tests(struct mm_struct *mm, pgd_t *pgdp) { }
static void __init p4d_populate_tests(struct mm_struct *mm, p4d_t *p4dp,
				      pud_t *pudp)
{
}
static void __init pgd_populate_tests(struct mm_struct *mm, pgd_t *pgdp,
				      p4d_t *p4dp)
{
}
#endif /* PAGETABLE_P4D_FOLDED */

static void __init pte_clear_tests(struct mm_struct *mm, pte_t *ptep,
				   unsigned long vaddr)
{
	pte_t pte = READ_ONCE(*ptep);

	pte = __pte(pte_val(pte) | RANDOM_ORVALUE);
	set_pte_at(mm, vaddr, ptep, pte);
	barrier();
	pte_clear(mm, vaddr, ptep);
	pte = READ_ONCE(*ptep);
	WARN_ON(!pte_none(pte));
}

static void __init pmd_clear_tests(struct mm_struct *mm, pmd_t *pmdp)
{
	pmd_t pmd = READ_ONCE(*pmdp);

	pmd = __pmd(pmd_val(pmd) | RANDOM_ORVALUE);
	WRITE_ONCE(*pmdp, pmd);
	pmd_clear(pmdp);
	pmd = READ_ONCE(*pmdp);
	WARN_ON(!pmd_none(pmd));
}

static void __init pmd_populate_tests(struct mm_struct *mm, pmd_t *pmdp,
				      pgtable_t pgtable)
{
	pmd_t pmd;

	/*
	 * This entry points to next level page table page.
	 * Hence this must not qualify as pmd_bad().
	 */
	pmd_clear(pmdp);
	pmd_populate(mm, pmdp, pgtable);
	pmd = READ_ONCE(*pmdp);
	WARN_ON(pmd_bad(pmd));
}

static unsigned long __init get_random_vaddr(void)
{
	unsigned long random_vaddr, random_pages, total_user_pages;

	total_user_pages = (TASK_SIZE - FIRST_USER_ADDRESS) / PAGE_SIZE;

	random_pages = get_random_long() % total_user_pages;
	random_vaddr = FIRST_USER_ADDRESS + random_pages * PAGE_SIZE;

	return random_vaddr;
}

static int __init debug_vm_pgtable(void)
{
	struct mm_struct *mm;
	pgd_t *pgdp;
	p4d_t *p4dp, *saved_p4dp;
	pud_t *pudp, *saved_pudp;
	pmd_t *pmdp, *saved_pmdp, pmd;
	pte_t *ptep;
	pgtable_t saved_ptep;
	pgprot_t prot;
	phys_addr_t paddr;
	unsigned long vaddr, pte_aligned, pmd_aligned;
	unsigned long pud_aligned, p4d_aligned, pgd_aligned;
	spinlock_t *uninitialized_var(ptl);

	pr_info("Validating architecture page table helpers\n");
	prot = vm_get_page_prot(VMFLAGS);
	vaddr = get_random_vaddr();
	mm = mm_alloc();
	if (!mm) {
		pr_err("mm_struct allocation failed\n");
		return 1;
	}

	/*
	 * PFN for mapping at PTE level is determined from a standard kernel
	 * text symbol. But pfns for higher page table levels are derived by
	 * masking lower bits of this real pfn. These derived pfns might not
	 * exist on the platform but that does not really matter as pfn_pxx()
	 * helpers will still create appropriate entries for the test. This
	 * helps avoid large memory block allocations to be used for mapping
	 * at higher page table levels.
	 */
	paddr = __pa_symbol(&start_kernel);

	pte_aligned = (paddr & PAGE_MASK) >> PAGE_SHIFT;
	pmd_aligned = (paddr & PMD_MASK) >> PAGE_SHIFT;
	pud_aligned = (paddr & PUD_MASK) >> PAGE_SHIFT;
	p4d_aligned = (paddr & P4D_MASK) >> PAGE_SHIFT;
	pgd_aligned = (paddr & PGDIR_MASK) >> PAGE_SHIFT;
	WARN_ON(!pfn_valid(pte_aligned));

	pgdp = pgd_offset(mm, vaddr);
	p4dp = p4d_alloc(mm, pgdp, vaddr);
	pudp = pud_alloc(mm, p4dp, vaddr);
	pmdp = pmd_alloc(mm, pudp, vaddr);
	ptep = pte_alloc_map_lock(mm, pmdp, vaddr, &ptl);

	/*
	 * Save all the page table page addresses as the page table
	 * entries will be used for testing with random or garbage
	 * values. These saved addresses will be used for freeing
	 * page table pages.
	 */
	pmd = READ_ONCE(*pmdp);
	saved_p4dp = p4d_offset(pgdp, 0UL);
	saved_pudp = pud_offset(p4dp, 0UL);
	saved_pmdp = pmd_offset(pudp, 0UL);
	saved_ptep = pmd_pgtable(pmd);

	pte_basic_tests(pte_aligned, prot);
	pmd_basic_tests(pmd_aligned, prot);
	pud_basic_tests(pud_aligned, prot);
	p4d_basic_tests(p4d_aligned, prot);
	pgd_basic_tests(pgd_aligned, prot);

	pte_clear_tests(mm, ptep, vaddr);
	pmd_clear_tests(mm, pmdp);
	pud_clear_tests(mm, pudp);
	p4d_clear_tests(mm, p4dp);
	pgd_clear_tests(mm, pgdp);

	pte_unmap_unlock(ptep, ptl);

	pmd_populate_tests(mm, pmdp, saved_ptep);
	pud_populate_tests(mm, pudp, saved_pmdp);
	p4d_populate_tests(mm, p4dp, saved_pudp);
	pgd_populate_tests(mm, pgdp, saved_p4dp);

	p4d_free(mm, saved_p4dp);
	pud_free(mm, saved_pudp);
	pmd_free(mm, saved_pmdp);
	pte_free(mm, saved_ptep);

	mm_dec_nr_puds(mm);
	mm_dec_nr_pmds(mm);
	mm_dec_nr_ptes(mm);
	mmdrop(mm);
	return 0;
}
late_initcall(debug_vm_pgtable);