aboutsummaryrefslogtreecommitdiff
path: root/arch/arm64/mm/gup.c
blob: 45dd908e4d0e743afd10e6a55a2597317dc7c820 (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
/*
 * arch/arm64/mm/gup.c
 *
 * Copyright (C) 2014 Linaro Ltd.
 *
 * Based on arch/powerpc/mm/gup.c which is:
 * Copyright (C) 2008 Nick Piggin
 * Copyright (C) 2008 Novell Inc.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 */

#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/rwsem.h>
#include <linux/hugetlb.h>
#include <asm/pgtable.h>

static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
			 int write, struct page **pages, int *nr)
{
	pte_t *ptep, *ptem;
	int ret = 0;

	ptem = ptep = pte_offset_map(&pmd, addr);
	do {
		pte_t pte = ACCESS_ONCE(*ptep);
		struct page *page;

		if (!pte_valid_user(pte) || (write && !pte_write(pte)))
			goto pte_unmap;

		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
		page = pte_page(pte);

		if (!page_cache_get_speculative(page))
			goto pte_unmap;

		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
			put_page(page);
			goto pte_unmap;
		}

		pages[*nr] = page;
		(*nr)++;

	} while (ptep++, addr += PAGE_SIZE, addr != end);

	ret = 1;

pte_unmap:
	pte_unmap(ptem);
	return ret;
}

static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
		unsigned long end, int write, struct page **pages, int *nr)
{
	struct page *head, *page, *tail;
	int refs;

	if (!pmd_present(orig) || (write && !pmd_write(orig)))
		return 0;

	refs = 0;
	head = pmd_page(orig);
	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
	tail = page;
	do {
		VM_BUG_ON(compound_head(page) != head);
		pages[*nr] = page;
		(*nr)++;
		page++;
		refs++;
	} while (addr += PAGE_SIZE, addr != end);

	if (!page_cache_add_speculative(head, refs)) {
		*nr -= refs;
		return 0;
	}

	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
		*nr -= refs;
		while (refs--)
			put_page(head);
		return 0;
	}

	/*
	 * Any tail pages need their mapcount reference taken before we
	 * return. (This allows the THP code to bump their ref count when
	 * they are split into base pages).
	 */
	while (refs--) {
		if (PageTail(tail))
			get_huge_page_tail(tail);
		tail++;
	}

	return 1;
}

static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
		unsigned long end, int write, struct page **pages, int *nr)
{
	struct page *head, *page, *tail;
	pmd_t origpmd = __pmd(pud_val(orig));
	int refs;

	if (!pmd_present(origpmd) || (write && !pmd_write(origpmd)))
		return 0;

	refs = 0;
	head = pmd_page(origpmd);
	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
	tail = page;
	do {
		VM_BUG_ON(compound_head(page) != head);
		pages[*nr] = page;
		(*nr)++;
		page++;
		refs++;
	} while (addr += PAGE_SIZE, addr != end);

	if (!page_cache_add_speculative(head, refs)) {
		*nr -= refs;
		return 0;
	}

	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
		*nr -= refs;
		while (refs--)
			put_page(head);
		return 0;
	}

	while (refs--) {
		if (PageTail(tail))
			get_huge_page_tail(tail);
		tail++;
	}

	return 1;
}

static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
		int write, struct page **pages, int *nr)
{
	unsigned long next;
	pmd_t *pmdp;

	pmdp = pmd_offset(&pud, addr);
	do {
		pmd_t pmd = ACCESS_ONCE(*pmdp);
		next = pmd_addr_end(addr, end);
		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
			return 0;

		if (unlikely(pmd_huge(pmd) || pmd_trans_huge(pmd))) {
			if (!gup_huge_pmd(pmd, pmdp, addr, next, write,
					pages, nr))
				return 0;
		} else {
			if (!gup_pte_range(pmd, addr, next, write, pages, nr))
				return 0;
		}
	} while (pmdp++, addr = next, addr != end);

	return 1;
}

static int gup_pud_range(pgd_t *pgdp, unsigned long addr, unsigned long end,
		int write, struct page **pages, int *nr)
{
	unsigned long next;
	pud_t *pudp;

	pudp = pud_offset(pgdp, addr);
	do {
		pud_t pud = ACCESS_ONCE(*pudp);
		next = pud_addr_end(addr, end);
		if (pud_none(pud))
			return 0;
		if (pud_huge(pud)) {
			if (!gup_huge_pud(pud, pudp, addr, next, write,
					pages, nr))
				return 0;
		}
		else if (!gup_pmd_range(pud, addr, next, write, pages, nr))
			return 0;
	} while (pudp++, addr = next, addr != end);

	return 1;
}

/*
 * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
 * back to the regular GUP.
 */
int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
			  struct page **pages)
{
	struct mm_struct *mm = current->mm;
	unsigned long addr, len, end;
	unsigned long next, flags;
	pgd_t *pgdp;
	int nr = 0;

	start &= PAGE_MASK;
	addr = start;
	len = (unsigned long) nr_pages << PAGE_SHIFT;
	end = start + len;

	if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
					start, len)))
		return 0;

	/*
	 * Disable interrupts, we use the nested form as we can already
	 * have interrupts disabled by get_futex_key.
	 *
	 * With interrupts disabled, we block page table pages from being
	 * freed from under us. See mmu_gather_tlb in asm-generic/tlb.h
	 * for more details.
	 */

	local_irq_save(flags);
	pgdp = pgd_offset(mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none(*pgdp))
			break;
		else if (!gup_pud_range(pgdp, addr, next, write, pages, &nr))
			break;
	} while (pgdp++, addr = next, addr != end);
	local_irq_restore(flags);

	return nr;
}

int get_user_pages_fast(unsigned long start, int nr_pages, int write,
			struct page **pages)
{
	struct mm_struct *mm = current->mm;
	int nr, ret;

	start &= PAGE_MASK;
	nr = __get_user_pages_fast(start, nr_pages, write, pages);
	ret = nr;

	if (nr < nr_pages) {
		/* Try to get the remaining pages with get_user_pages */
		start += nr << PAGE_SHIFT;
		pages += nr;

		down_read(&mm->mmap_sem);
		ret = get_user_pages(current, mm, start,
				     nr_pages - nr, write, 0, pages, NULL);
		up_read(&mm->mmap_sem);

		/* Have to be a bit careful with return values */
		if (nr > 0) {
			if (ret < 0)
				ret = nr;
			else
				ret += nr;
		}
	}

	return ret;
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static void thp_splitting_flush_sync(void *arg)
{
}

void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
			  pmd_t *pmdp)
{
	pmd_t pmd = pmd_mksplitting(*pmdp);
	VM_BUG_ON(address & ~PMD_MASK);
	set_pmd_at(vma->vm_mm, address, pmdp, pmd);

	/* dummy IPI to serialise against fast_gup */
	smp_call_function(thp_splitting_flush_sync, NULL, 1);
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */