summaryrefslogtreecommitdiff
path: root/mm/pgtable-generic.c
blob: a78a4adf711ac2e4a842174dee50c2efbdde57bf (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
// SPDX-License-Identifier: GPL-2.0
/*
 *  mm/pgtable-generic.c
 *
 *  Generic pgtable methods declared in linux/pgtable.h
 *
 *  Copyright (C) 2010  Linus Torvalds
 */

#include <linux/pagemap.h>
#include <linux/hugetlb.h>
#include <linux/pgtable.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/mm_inline.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>

/*
 * If a p?d_bad entry is found while walking page tables, report
 * the error, before resetting entry to p?d_none.  Usually (but
 * very seldom) called out from the p?d_none_or_clear_bad macros.
 */

void pgd_clear_bad(pgd_t *pgd)
{
	pgd_ERROR(*pgd);
	pgd_clear(pgd);
}

#ifndef __PAGETABLE_P4D_FOLDED
void p4d_clear_bad(p4d_t *p4d)
{
	p4d_ERROR(*p4d);
	p4d_clear(p4d);
}
#endif

#ifndef __PAGETABLE_PUD_FOLDED
void pud_clear_bad(pud_t *pud)
{
	pud_ERROR(*pud);
	pud_clear(pud);
}
#endif

/*
 * Note that the pmd variant below can't be stub'ed out just as for p4d/pud
 * above. pmd folding is special and typically pmd_* macros refer to upper
 * level even when folded
 */
void pmd_clear_bad(pmd_t *pmd)
{
	pmd_ERROR(*pmd);
	pmd_clear(pmd);
}

#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
/*
 * Only sets the access flags (dirty, accessed), as well as write
 * permission. Furthermore, we know it always gets set to a "more
 * permissive" setting, which allows most architectures to optimize
 * this. We return whether the PTE actually changed, which in turn
 * instructs the caller to do things like update__mmu_cache.  This
 * used to be done in the caller, but sparc needs minor faults to
 * force that call on sun4c so we changed this macro slightly
 */
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_get(ptep), entry);
	if (changed) {
		set_pte_at(vma->vm_mm, address, ptep, entry);
		flush_tlb_fix_spurious_fault(vma, address, ptep);
	}
	return changed;
}
#endif

#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
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;
}
#endif

#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH
pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
		       pte_t *ptep)
{
	struct mm_struct *mm = (vma)->vm_mm;
	pte_t pte;
	pte = ptep_get_and_clear(mm, address, ptep);
	if (pte_accessible(mm, pte))
		flush_tlb_page(vma, address);
	return pte;
}
#endif

#ifdef CONFIG_TRANSPARENT_HUGEPAGE

#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
int pmdp_set_access_flags(struct vm_area_struct *vma,
			  unsigned long address, pmd_t *pmdp,
			  pmd_t entry, int dirty)
{
	int changed = !pmd_same(*pmdp, entry);
	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
	if (changed) {
		set_pmd_at(vma->vm_mm, address, pmdp, entry);
		flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
	}
	return changed;
}
#endif

#ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
int pmdp_clear_flush_young(struct vm_area_struct *vma,
			   unsigned long address, pmd_t *pmdp)
{
	int young;
	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
	young = pmdp_test_and_clear_young(vma, address, pmdp);
	if (young)
		flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
	return young;
}
#endif

#ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH
pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
			    pmd_t *pmdp)
{
	pmd_t pmd;
	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
	VM_BUG_ON(pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) &&
			   !pmd_devmap(*pmdp));
	pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
	return pmd;
}

#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
			    pud_t *pudp)
{
	pud_t pud;

	VM_BUG_ON(address & ~HPAGE_PUD_MASK);
	VM_BUG_ON(!pud_trans_huge(*pudp) && !pud_devmap(*pudp));
	pud = pudp_huge_get_and_clear(vma->vm_mm, address, pudp);
	flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE);
	return pud;
}
#endif
#endif

#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
				pgtable_t pgtable)
{
	assert_spin_locked(pmd_lockptr(mm, pmdp));

	/* FIFO */
	if (!pmd_huge_pte(mm, pmdp))
		INIT_LIST_HEAD(&pgtable->lru);
	else
		list_add(&pgtable->lru, &pmd_huge_pte(mm, pmdp)->lru);
	pmd_huge_pte(mm, pmdp) = pgtable;
}
#endif

#ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
/* no "address" argument so destroys page coloring of some arch */
pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
{
	pgtable_t pgtable;

	assert_spin_locked(pmd_lockptr(mm, pmdp));

	/* FIFO */
	pgtable = pmd_huge_pte(mm, pmdp);
	pmd_huge_pte(mm, pmdp) = list_first_entry_or_null(&pgtable->lru,
							  struct page, lru);
	if (pmd_huge_pte(mm, pmdp))
		list_del(&pgtable->lru);
	return pgtable;
}
#endif

#ifndef __HAVE_ARCH_PMDP_INVALIDATE
pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
		     pmd_t *pmdp)
{
	VM_WARN_ON_ONCE(!pmd_present(*pmdp));
	pmd_t old = pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp));
	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
	return old;
}
#endif

#ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD
pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address,
			 pmd_t *pmdp)
{
	VM_WARN_ON_ONCE(!pmd_present(*pmdp));
	return pmdp_invalidate(vma, address, pmdp);
}
#endif

#ifndef pmdp_collapse_flush
pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address,
			  pmd_t *pmdp)
{
	/*
	 * pmd and hugepage pte format are same. So we could
	 * use the same function.
	 */
	pmd_t pmd;

	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
	VM_BUG_ON(pmd_trans_huge(*pmdp));
	pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);

	/* collapse entails shooting down ptes not pmd */
	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
	return pmd;
}
#endif

/* arch define pte_free_defer in asm/pgalloc.h for its own implementation */
#ifndef pte_free_defer
static void pte_free_now(struct rcu_head *head)
{
	struct page *page;

	page = container_of(head, struct page, rcu_head);
	pte_free(NULL /* mm not passed and not used */, (pgtable_t)page);
}

void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable)
{
	struct page *page;

	page = pgtable;
	call_rcu(&page->rcu_head, pte_free_now);
}
#endif /* pte_free_defer */
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

#if defined(CONFIG_GUP_GET_PXX_LOW_HIGH) && \
	(defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RCU))
/*
 * See the comment above ptep_get_lockless() in include/linux/pgtable.h:
 * the barriers in pmdp_get_lockless() cannot guarantee that the value in
 * pmd_high actually belongs with the value in pmd_low; but holding interrupts
 * off blocks the TLB flush between present updates, which guarantees that a
 * successful __pte_offset_map() points to a page from matched halves.
 */
static unsigned long pmdp_get_lockless_start(void)
{
	unsigned long irqflags;

	local_irq_save(irqflags);
	return irqflags;
}
static void pmdp_get_lockless_end(unsigned long irqflags)
{
	local_irq_restore(irqflags);
}
#else
static unsigned long pmdp_get_lockless_start(void) { return 0; }
static void pmdp_get_lockless_end(unsigned long irqflags) { }
#endif

pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp)
{
	unsigned long irqflags;
	pmd_t pmdval;

	rcu_read_lock();
	irqflags = pmdp_get_lockless_start();
	pmdval = pmdp_get_lockless(pmd);
	pmdp_get_lockless_end(irqflags);

	if (pmdvalp)
		*pmdvalp = pmdval;
	if (unlikely(pmd_none(pmdval) || is_pmd_migration_entry(pmdval)))
		goto nomap;
	if (unlikely(pmd_trans_huge(pmdval) || pmd_devmap(pmdval)))
		goto nomap;
	if (unlikely(pmd_bad(pmdval))) {
		pmd_clear_bad(pmd);
		goto nomap;
	}
	return __pte_map(&pmdval, addr);
nomap:
	rcu_read_unlock();
	return NULL;
}

pte_t *pte_offset_map_nolock(struct mm_struct *mm, pmd_t *pmd,
			     unsigned long addr, spinlock_t **ptlp)
{
	pmd_t pmdval;
	pte_t *pte;

	pte = __pte_offset_map(pmd, addr, &pmdval);
	if (likely(pte))
		*ptlp = pte_lockptr(mm, &pmdval);
	return pte;
}

/*
 * pte_offset_map_lock(mm, pmd, addr, ptlp), and its internal implementation
 * __pte_offset_map_lock() below, is usually called with the pmd pointer for
 * addr, reached by walking down the mm's pgd, p4d, pud for addr: either while
 * holding mmap_lock or vma lock for read or for write; or in truncate or rmap
 * context, while holding file's i_mmap_lock or anon_vma lock for read (or for
 * write). In a few cases, it may be used with pmd pointing to a pmd_t already
 * copied to or constructed on the stack.
 *
 * When successful, it returns the pte pointer for addr, with its page table
 * kmapped if necessary (when CONFIG_HIGHPTE), and locked against concurrent
 * modification by software, with a pointer to that spinlock in ptlp (in some
 * configs mm->page_table_lock, in SPLIT_PTLOCK configs a spinlock in table's
 * struct page).  pte_unmap_unlock(pte, ptl) to unlock and unmap afterwards.
 *
 * But it is unsuccessful, returning NULL with *ptlp unchanged, if there is no
 * page table at *pmd: if, for example, the page table has just been removed,
 * or replaced by the huge pmd of a THP.  (When successful, *pmd is rechecked
 * after acquiring the ptlock, and retried internally if it changed: so that a
 * page table can be safely removed or replaced by THP while holding its lock.)
 *
 * pte_offset_map(pmd, addr), and its internal helper __pte_offset_map() above,
 * just returns the pte pointer for addr, its page table kmapped if necessary;
 * or NULL if there is no page table at *pmd.  It does not attempt to lock the
 * page table, so cannot normally be used when the page table is to be updated,
 * or when entries read must be stable.  But it does take rcu_read_lock(): so
 * that even when page table is racily removed, it remains a valid though empty
 * and disconnected table.  Until pte_unmap(pte) unmaps and rcu_read_unlock()s
 * afterwards.
 *
 * pte_offset_map_nolock(mm, pmd, addr, ptlp), above, is like pte_offset_map();
 * but when successful, it also outputs a pointer to the spinlock in ptlp - as
 * pte_offset_map_lock() does, but in this case without locking it.  This helps
 * the caller to avoid a later pte_lockptr(mm, *pmd), which might by that time
 * act on a changed *pmd: pte_offset_map_nolock() provides the correct spinlock
 * pointer for the page table that it returns.  In principle, the caller should
 * recheck *pmd once the lock is taken; in practice, no callsite needs that -
 * either the mmap_lock for write, or pte_same() check on contents, is enough.
 *
 * Note that free_pgtables(), used after unmapping detached vmas, or when
 * exiting the whole mm, does not take page table lock before freeing a page
 * table, and may not use RCU at all: "outsiders" like khugepaged should avoid
 * pte_offset_map() and co once the vma is detached from mm or mm_users is zero.
 */
pte_t *__pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd,
			     unsigned long addr, spinlock_t **ptlp)
{
	spinlock_t *ptl;
	pmd_t pmdval;
	pte_t *pte;
again:
	pte = __pte_offset_map(pmd, addr, &pmdval);
	if (unlikely(!pte))
		return pte;
	ptl = pte_lockptr(mm, &pmdval);
	spin_lock(ptl);
	if (likely(pmd_same(pmdval, pmdp_get_lockless(pmd)))) {
		*ptlp = ptl;
		return pte;
	}
	pte_unmap_unlock(pte, ptl);
	goto again;
}