summaryrefslogtreecommitdiff
path: root/arch/x86/mm/pgtable.c
blob: d526b46ae1883aa6f13286f6c70b4e964b4da06a (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
#include <linux/mm.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>

pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
{
	return (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
}

pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
{
	struct page *pte;

#ifdef CONFIG_HIGHPTE
	pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT|__GFP_ZERO, 0);
#else
	pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0);
#endif
	if (pte)
		pgtable_page_ctor(pte);
	return pte;
}

#ifdef CONFIG_X86_64
static inline void pgd_list_add(pgd_t *pgd)
{
	struct page *page = virt_to_page(pgd);
	unsigned long flags;

	spin_lock_irqsave(&pgd_lock, flags);
	list_add(&page->lru, &pgd_list);
	spin_unlock_irqrestore(&pgd_lock, flags);
}

static inline void pgd_list_del(pgd_t *pgd)
{
	struct page *page = virt_to_page(pgd);
	unsigned long flags;

	spin_lock_irqsave(&pgd_lock, flags);
	list_del(&page->lru);
	spin_unlock_irqrestore(&pgd_lock, flags);
}

pgd_t *pgd_alloc(struct mm_struct *mm)
{
	unsigned boundary;
	pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
	if (!pgd)
		return NULL;
	pgd_list_add(pgd);
	/*
	 * Copy kernel pointers in from init.
	 * Could keep a freelist or slab cache of those because the kernel
	 * part never changes.
	 */
	boundary = pgd_index(__PAGE_OFFSET);
	memset(pgd, 0, boundary * sizeof(pgd_t));
	memcpy(pgd + boundary,
	       init_level4_pgt + boundary,
	       (PTRS_PER_PGD - boundary) * sizeof(pgd_t));
	return pgd;
}

void pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
	BUG_ON((unsigned long)pgd & (PAGE_SIZE-1));
	pgd_list_del(pgd);
	free_page((unsigned long)pgd);
}
#else
/*
 * List of all pgd's needed for non-PAE so it can invalidate entries
 * in both cached and uncached pgd's; not needed for PAE since the
 * kernel pmd is shared. If PAE were not to share the pmd a similar
 * tactic would be needed. This is essentially codepath-based locking
 * against pageattr.c; it is the unique case in which a valid change
 * of kernel pagetables can't be lazily synchronized by vmalloc faults.
 * vmalloc faults work because attached pagetables are never freed.
 * -- wli
 */
static inline void pgd_list_add(pgd_t *pgd)
{
	struct page *page = virt_to_page(pgd);

	list_add(&page->lru, &pgd_list);
}

static inline void pgd_list_del(pgd_t *pgd)
{
	struct page *page = virt_to_page(pgd);

	list_del(&page->lru);
}

#define UNSHARED_PTRS_PER_PGD				\
	(SHARED_KERNEL_PMD ? USER_PTRS_PER_PGD : PTRS_PER_PGD)

static void pgd_ctor(void *p)
{
	pgd_t *pgd = p;
	unsigned long flags;

	/* Clear usermode parts of PGD */
	memset(pgd, 0, USER_PTRS_PER_PGD*sizeof(pgd_t));

	spin_lock_irqsave(&pgd_lock, flags);

	/* If the pgd points to a shared pagetable level (either the
	   ptes in non-PAE, or shared PMD in PAE), then just copy the
	   references from swapper_pg_dir. */
	if (PAGETABLE_LEVELS == 2 ||
	    (PAGETABLE_LEVELS == 3 && SHARED_KERNEL_PMD)) {
		clone_pgd_range(pgd + USER_PTRS_PER_PGD,
				swapper_pg_dir + USER_PTRS_PER_PGD,
				KERNEL_PGD_PTRS);
		paravirt_alloc_pd_clone(__pa(pgd) >> PAGE_SHIFT,
					__pa(swapper_pg_dir) >> PAGE_SHIFT,
					USER_PTRS_PER_PGD,
					KERNEL_PGD_PTRS);
	}

	/* list required to sync kernel mapping updates */
	if (!SHARED_KERNEL_PMD)
		pgd_list_add(pgd);

	spin_unlock_irqrestore(&pgd_lock, flags);
}

static void pgd_dtor(void *pgd)
{
	unsigned long flags; /* can be called from interrupt context */

	if (SHARED_KERNEL_PMD)
		return;

	spin_lock_irqsave(&pgd_lock, flags);
	pgd_list_del(pgd);
	spin_unlock_irqrestore(&pgd_lock, flags);
}

#ifdef CONFIG_X86_PAE
/*
 * Mop up any pmd pages which may still be attached to the pgd.
 * Normally they will be freed by munmap/exit_mmap, but any pmd we
 * preallocate which never got a corresponding vma will need to be
 * freed manually.
 */
static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
{
	int i;

	for(i = 0; i < UNSHARED_PTRS_PER_PGD; i++) {
		pgd_t pgd = pgdp[i];

		if (pgd_val(pgd) != 0) {
			pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd);

			pgdp[i] = native_make_pgd(0);

			paravirt_release_pd(pgd_val(pgd) >> PAGE_SHIFT);
			pmd_free(mm, pmd);
		}
	}
}

/*
 * In PAE mode, we need to do a cr3 reload (=tlb flush) when
 * updating the top-level pagetable entries to guarantee the
 * processor notices the update.  Since this is expensive, and
 * all 4 top-level entries are used almost immediately in a
 * new process's life, we just pre-populate them here.
 *
 * Also, if we're in a paravirt environment where the kernel pmd is
 * not shared between pagetables (!SHARED_KERNEL_PMDS), we allocate
 * and initialize the kernel pmds here.
 */
static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd)
{
	pud_t *pud;
	unsigned long addr;
	int i;

	pud = pud_offset(pgd, 0);
 	for (addr = i = 0; i < UNSHARED_PTRS_PER_PGD;
	     i++, pud++, addr += PUD_SIZE) {
		pmd_t *pmd = pmd_alloc_one(mm, addr);

		if (!pmd) {
			pgd_mop_up_pmds(mm, pgd);
			return 0;
		}

		if (i >= USER_PTRS_PER_PGD)
			memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]),
			       sizeof(pmd_t) * PTRS_PER_PMD);

		pud_populate(mm, pud, pmd);
	}

	return 1;
}
#else  /* !CONFIG_X86_PAE */
/* No need to prepopulate any pagetable entries in non-PAE modes. */
static int pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd)
{
	return 1;
}

static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgd)
{
}
#endif	/* CONFIG_X86_PAE */

pgd_t *pgd_alloc(struct mm_struct *mm)
{
	pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);

	/* so that alloc_pd can use it */
	mm->pgd = pgd;
	if (pgd)
		pgd_ctor(pgd);

	if (pgd && !pgd_prepopulate_pmd(mm, pgd)) {
		pgd_dtor(pgd);
		free_page((unsigned long)pgd);
		pgd = NULL;
	}

	return pgd;
}

void pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
	pgd_mop_up_pmds(mm, pgd);
	pgd_dtor(pgd);
	free_page((unsigned long)pgd);
}
#endif