aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/mm/pgtable.c
blob: af8f9650058cfcf59ab46476ac174ec86e41de49 (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
#include <linux/mm.h>
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
#include <asm/tlb.h>
#include <asm/fixmap.h>

#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO

pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
{
	return (pte_t *)__get_free_page(PGALLOC_GFP);
}

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

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

void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
{
	pgtable_page_dtor(pte);
	paravirt_release_pte(page_to_pfn(pte));
	tlb_remove_page(tlb, pte);
}

#if PAGETABLE_LEVELS > 2
void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
{
	paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT);
	tlb_remove_page(tlb, virt_to_page(pmd));
}

#if PAGETABLE_LEVELS > 3
void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
{
	paravirt_release_pud(__pa(pud) >> PAGE_SHIFT);
	tlb_remove_page(tlb, virt_to_page(pud));
}
#endif	/* PAGETABLE_LEVELS > 3 */
#endif	/* PAGETABLE_LEVELS > 2 */

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 ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD)

static void pgd_ctor(pgd_t *pgd)
{
	/* 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) ||
	    PAGETABLE_LEVELS == 4) {
		clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY,
				swapper_pg_dir + KERNEL_PGD_BOUNDARY,
				KERNEL_PGD_PTRS);
		paravirt_alloc_pmd_clone(__pa(pgd) >> PAGE_SHIFT,
					 __pa(swapper_pg_dir) >> PAGE_SHIFT,
					 KERNEL_PGD_BOUNDARY,
					 KERNEL_PGD_PTRS);
	}

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

static void pgd_dtor(pgd_t *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);
}

/*
 * 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
 */

#ifdef CONFIG_X86_PAE
/*
 * 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.
 */
#define PREALLOCATED_PMDS	UNSHARED_PTRS_PER_PGD

void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
{
	paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT);

	/* Note: almost everything apart from _PAGE_PRESENT is
	   reserved at the pmd (PDPT) level. */
	set_pud(pudp, __pud(__pa(pmd) | _PAGE_PRESENT));

	/*
	 * According to Intel App note "TLBs, Paging-Structure Caches,
	 * and Their Invalidation", April 2007, document 317080-001,
	 * section 8.1: in PAE mode we explicitly have to flush the
	 * TLB via cr3 if the top-level pgd is changed...
	 */
	if (mm == current->active_mm)
		write_cr3(read_cr3());
}
#else  /* !CONFIG_X86_PAE */

/* No need to prepopulate any pagetable entries in non-PAE modes. */
#define PREALLOCATED_PMDS	0

#endif	/* CONFIG_X86_PAE */

static void free_pmds(pmd_t *pmds[])
{
	int i;

	for(i = 0; i < PREALLOCATED_PMDS; i++)
		if (pmds[i])
			free_page((unsigned long)pmds[i]);
}

static int preallocate_pmds(pmd_t *pmds[])
{
	int i;
	bool failed = false;

	for(i = 0; i < PREALLOCATED_PMDS; i++) {
		pmd_t *pmd = (pmd_t *)__get_free_page(PGALLOC_GFP);
		if (pmd == NULL)
			failed = true;
		pmds[i] = pmd;
	}

	if (failed) {
		free_pmds(pmds);
		return -ENOMEM;
	}

	return 0;
}

/*
 * 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 < PREALLOCATED_PMDS; 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_pmd(pgd_val(pgd) >> PAGE_SHIFT);
			pmd_free(mm, pmd);
		}
	}
}

static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[])
{
	pud_t *pud;
	unsigned long addr;
	int i;

	if (PREALLOCATED_PMDS == 0) /* Work around gcc-3.4.x bug */
		return;

	pud = pud_offset(pgd, 0);

 	for (addr = i = 0; i < PREALLOCATED_PMDS;
	     i++, pud++, addr += PUD_SIZE) {
		pmd_t *pmd = pmds[i];

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

		pud_populate(mm, pud, pmd);
	}
}

pgd_t *pgd_alloc(struct mm_struct *mm)
{
	pgd_t *pgd;
	pmd_t *pmds[PREALLOCATED_PMDS];
	unsigned long flags;

	pgd = (pgd_t *)__get_free_page(PGALLOC_GFP);

	if (pgd == NULL)
		goto out;

	mm->pgd = pgd;

	if (preallocate_pmds(pmds) != 0)
		goto out_free_pgd;

	if (paravirt_pgd_alloc(mm) != 0)
		goto out_free_pmds;

	/*
	 * Make sure that pre-populating the pmds is atomic with
	 * respect to anything walking the pgd_list, so that they
	 * never see a partially populated pgd.
	 */
	spin_lock_irqsave(&pgd_lock, flags);

	pgd_ctor(pgd);
	pgd_prepopulate_pmd(mm, pgd, pmds);

	spin_unlock_irqrestore(&pgd_lock, flags);

	return pgd;

out_free_pmds:
	free_pmds(pmds);
out_free_pgd:
	free_page((unsigned long)pgd);
out:
	return NULL;
}

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

int ptep_set_access_flags(struct vm_area_struct *vma,
			  unsigned long address, pte_t *ptep,
			  pte_t entry, int dirty)
{
	int changed = !pte_same(*ptep, entry);

	if (changed && dirty) {
		*ptep = entry;
		pte_update_defer(vma->vm_mm, address, ptep);
		flush_tlb_page(vma, address);
	}

	return changed;
}

int ptep_test_and_clear_young(struct vm_area_struct *vma,
			      unsigned long addr, pte_t *ptep)
{
	int ret = 0;

	if (pte_young(*ptep))
		ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,
					 (unsigned long *) &ptep->pte);

	if (ret)
		pte_update(vma->vm_mm, addr, ptep);

	return ret;
}

int ptep_clear_flush_young(struct vm_area_struct *vma,
			   unsigned long address, pte_t *ptep)
{
	int young;

	young = ptep_test_and_clear_young(vma, address, ptep);
	if (young)
		flush_tlb_page(vma, address);

	return young;
}

/**
 * reserve_top_address - reserves a hole in the top of kernel address space
 * @reserve - size of hole to reserve
 *
 * Can be used to relocate the fixmap area and poke a hole in the top
 * of kernel address space to make room for a hypervisor.
 */
void __init reserve_top_address(unsigned long reserve)
{
#ifdef CONFIG_X86_32
	BUG_ON(fixmaps_set > 0);
	printk(KERN_INFO "Reserving virtual address space above 0x%08x\n",
	       (int)-reserve);
	__FIXADDR_TOP = -reserve - PAGE_SIZE;
	__VMALLOC_RESERVE += reserve;
#endif
}

int fixmaps_set;

void __native_set_fixmap(enum fixed_addresses idx, pte_t pte)
{
	unsigned long address = __fix_to_virt(idx);

	if (idx >= __end_of_fixed_addresses) {
		BUG();
		return;
	}
	set_pte_vaddr(address, pte);
	fixmaps_set++;
}

void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys,
		       pgprot_t flags)
{
	__native_set_fixmap(idx, pfn_pte(phys >> PAGE_SHIFT, flags));
}