aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/mm/gup.c
blob: 28a114db3ba0d9a405fbd743b3b6b86359201795 (plain) (blame)
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
/*
 * Lockless get_user_pages_fast for powerpc
 *
 * Copyright (C) 2008 Nick Piggin
 * Copyright (C) 2008 Novell Inc.
 */
#undef DEBUG

#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 noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
		unsigned long end, int write, struct page **pages, int *nr)
{
	unsigned long mask, result;
	pte_t *ptep;

	result = _PAGE_PRESENT|_PAGE_USER;
	if (write)
		result |= _PAGE_RW;
	mask = result | _PAGE_SPECIAL;

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

		if ((pte_val(pte) & mask) != result)
			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;
}

#ifdef CONFIG_HUGETLB_PAGE
static noinline int gup_huge_pte(pte_t *ptep, struct hstate *hstate,
				 unsigned long *addr, unsigned long end,
				 int write, struct page **pages, int *nr)
{
	unsigned long mask;
	unsigned long pte_end;
	struct page *head, *page;
	pte_t pte;
	int refs;

	pte_end = (*addr + huge_page_size(hstate)) & huge_page_mask(hstate);
	if (pte_end < end)
		end = pte_end;

	pte = *ptep;
	mask = _PAGE_PRESENT|_PAGE_USER;
	if (write)
		mask |= _PAGE_RW;
	if ((pte_val(pte) & mask) != mask)
		return 0;
	/* hugepages are never "special" */
	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));

	refs = 0;
	head = pte_page(pte);
	page = head + ((*addr & ~huge_page_mask(hstate)) >> PAGE_SHIFT);
	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(pte_val(pte) != pte_val(*ptep))) {
		/* Could be optimized better */
		while (*nr) {
			put_page(page);
			(*nr)--;
		}
	}

	return 1;
}
#endif /* CONFIG_HUGETLB_PAGE */

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 = *pmdp;

		next = pmd_addr_end(addr, end);
		if (pmd_none(pmd))
			return 0;
		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 pgd, unsigned long addr, unsigned long end,
		int write, struct page **pages, int *nr)
{
	unsigned long next;
	pud_t *pudp;

	pudp = pud_offset(&pgd, addr);
	do {
		pud_t pud = *pudp;

		next = pud_addr_end(addr, end);
		if (pud_none(pud))
			return 0;
		if (!gup_pmd_range(pud, addr, next, write, pages, nr))
			return 0;
	} while (pudp++, addr = next, addr != end);

	return 1;
}

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;
	int psize, nr = 0;
	unsigned int shift;

	pr_debug("%s(%lx,%x,%s)\n", __func__, start, nr_pages, write ? "write" : "read");

	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)))
		goto slow_irqon;

	pr_debug("  aligned: %lx .. %lx\n", start, end);

#ifdef CONFIG_HUGETLB_PAGE
	/* We bail out on slice boundary crossing when hugetlb is
	 * enabled in order to not have to deal with two different
	 * page table formats
	 */
	if (addr < SLICE_LOW_TOP) {
		if (end > SLICE_LOW_TOP)
			goto slow_irqon;

		if (unlikely(GET_LOW_SLICE_INDEX(addr) !=
			     GET_LOW_SLICE_INDEX(end - 1)))
			goto slow_irqon;
	} else {
		if (unlikely(GET_HIGH_SLICE_INDEX(addr) !=
			     GET_HIGH_SLICE_INDEX(end - 1)))
			goto slow_irqon;
	}
#endif /* CONFIG_HUGETLB_PAGE */

	/*
	 * XXX: batch / limit 'nr', to avoid large irq off latency
	 * needs some instrumenting to determine the common sizes used by
	 * important workloads (eg. DB2), and whether limiting the batch size
	 * will decrease performance.
	 *
	 * It seems like we're in the clear for the moment. Direct-IO is
	 * the main guy that batches up lots of get_user_pages, and even
	 * they are limited to 64-at-a-time which is not so many.
	 */
	/*
	 * This doesn't prevent pagetable teardown, but does prevent
	 * the pagetables from being freed on powerpc.
	 *
	 * 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();

	psize = get_slice_psize(mm, addr);
	shift = mmu_psize_defs[psize].shift;

#ifdef CONFIG_HUGETLB_PAGE
	if (unlikely(mmu_huge_psizes[psize])) {
		pte_t *ptep;
		unsigned long a = addr;
		unsigned long sz = ((1UL) << shift);
		struct hstate *hstate = size_to_hstate(sz);

		BUG_ON(!hstate);
		/*
		 * XXX: could be optimized to avoid hstate
		 * lookup entirely (just use shift)
		 */

		do {
			VM_BUG_ON(shift != mmu_psize_defs[get_slice_psize(mm, a)].shift);
			ptep = huge_pte_offset(mm, a);
			pr_debug(" %016lx: huge ptep %p\n", a, ptep);
			if (!ptep || !gup_huge_pte(ptep, hstate, &a, end, write, pages,
						   &nr))
				goto slow;
		} while (a != end);
	} else
#endif /* CONFIG_HUGETLB_PAGE */
	{
		pgdp = pgd_offset(mm, addr);
		do {
			pgd_t pgd = *pgdp;

			VM_BUG_ON(shift != mmu_psize_defs[get_slice_psize(mm, addr)].shift);
			pr_debug("  %016lx: normal pgd %p\n", addr,
				 (void *)pgd_val(pgd));
			next = pgd_addr_end(addr, end);
			if (pgd_none(pgd))
				goto slow;
			if (!gup_pud_range(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:
		pr_debug("  slow path ! nr = %d\n", nr);

		/* 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;
	}
}