summaryrefslogtreecommitdiffstats
path: root/arch/s390/mm/gup.c
blob: 60acb93a46809065b0d454e65f3837aa37e70aee (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
/*
 *  Lockless get_user_pages_fast for s390
 *
 *  Copyright IBM Corp. 2010
 *  Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
 */
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/vmstat.h>
#include <linux/pagemap.h>
#include <linux/rwsem.h>
#include <asm/pgtable.h>

/*
 * The performance critical leaf functions are made noinline otherwise gcc
 * inlines everything into a single function which results in too much
 * register pressure.
 */
static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
		unsigned long end, int write, struct page **pages, int *nr)
{
	unsigned long mask;
	pte_t *ptep, pte;
	struct page *page;

	mask = (write ? _PAGE_RO : 0) | _PAGE_INVALID | _PAGE_SPECIAL;

	ptep = ((pte_t *) pmd_deref(pmd)) + pte_index(addr);
	do {
		pte = *ptep;
		barrier();
		if ((pte_val(pte) & mask) != 0)
			return 0;
		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
		page = pte_page(pte);
		if (!page_cache_get_speculative(page))
			return 0;
		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
			put_page(page);
			return 0;
		}
		pages[*nr] = page;
		(*nr)++;

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

	return 1;
}

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

	result = write ? 0 : _SEGMENT_ENTRY_RO;
	mask = result | _SEGMENT_ENTRY_INV;
	if ((pmd_val(pmd) & mask) != result)
		return 0;
	VM_BUG_ON(!pfn_valid(pmd_val(pmd) >> PAGE_SHIFT));

	refs = 0;
	head = pmd_page(pmd);
	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(pmd) != pmd_val(*pmdp))) {
		*nr -= refs;
		while (refs--)
			put_page(head);
		return 0;
	}

	/*
	 * Any tail page need their mapcount reference taken before we
	 * return.
	 */
	while (refs--) {
		if (PageTail(tail))
			get_huge_page_tail(tail);
		tail++;
	}

	return 1;
}


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

	pmdp = (pmd_t *) pudp;
#ifdef CONFIG_64BIT
	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
		pmdp = (pmd_t *) pud_deref(pud);
	pmdp += pmd_index(addr);
#endif
	do {
		pmd = *pmdp;
		barrier();
		next = pmd_addr_end(addr, end);
		/*
		 * The pmd_trans_splitting() check below explains why
		 * pmdp_splitting_flush() has to serialize with
		 * smp_call_function() against our disabled IRQs, to stop
		 * this gup-fast code from running while we set the
		 * splitting bit in the pmd. Returning zero will take
		 * the slow path that will call wait_split_huge_page()
		 * if the pmd is still in splitting state.
		 */
		if (pmd_none(pmd) || pmd_trans_splitting(pmd))
			return 0;
		if (unlikely(pmd_huge(pmd))) {
			if (!gup_huge_pmd(pmdp, pmd, addr, next,
					  write, pages, nr))
				return 0;
		} else if (!gup_pte_range(pmdp, pmd, addr, next,
					  write, pages, nr))
			return 0;
	} while (pmdp++, addr = next, addr != end);

	return 1;
}

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

	pudp = (pud_t *) pgdp;
#ifdef CONFIG_64BIT
	if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
		pudp = (pud_t *) pgd_deref(pgd);
	pudp += pud_index(addr);
#endif
	do {
		pud = *pudp;
		barrier();
		next = pud_addr_end(addr, end);
		if (pud_none(pud))
			return 0;
		if (!gup_pmd_range(pudp, 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, pgd;
	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,
					(void __user *)start, len)))
		return 0;

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

	return nr;
}

/**
 * get_user_pages_fast() - pin user pages in memory
 * @start:	starting user address
 * @nr_pages:	number of pages from start to pin
 * @write:	whether pages will be written to
 * @pages:	array that receives pointers to the pages pinned.
 *		Should be at least nr_pages long.
 *
 * Attempt to pin user pages in memory without taking mm->mmap_sem.
 * If not successful, it will fall back to taking the lock and
 * calling get_user_pages().
 *
 * Returns number of pages pinned. This may be fewer than the number
 * requested. If nr_pages is 0 or negative, returns 0. If no pages
 * were pinned, returns -errno.
 */
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;
	pgd_t *pgdp, pgd;
	int nr = 0;

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

	/*
	 * local_irq_disable() doesn't prevent pagetable teardown, but does
	 * prevent the pagetables from being freed on s390.
	 *
	 * So long as we atomically load page table pointers versus teardown,
	 * we can follow the address down to the the page and take a ref on it.
	 */
	local_irq_disable();
	pgdp = pgd_offset(mm, addr);
	do {
		pgd = *pgdp;
		barrier();
		next = pgd_addr_end(addr, end);
		if (pgd_none(pgd))
			goto slow;
		if (!gup_pud_range(pgdp, pgd, addr, next, write, pages, &nr))
			goto slow;
	} while (pgdp++, addr = next, addr != end);
	local_irq_enable();

	VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT);
	return nr;

	{
		int ret;
slow:
		local_irq_enable();
slow_irqon:
		/* 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,
			(end - start) >> PAGE_SHIFT, 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;
	}
}