userfaultfd.c 7.17 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
/*
 *  mm/userfaultfd.c
 *
 *  Copyright (C) 2015  Red Hat, Inc.
 *
 *  This work is licensed under the terms of the GNU GPL, version 2. See
 *  the COPYING file in the top-level directory.
 */

#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/userfaultfd_k.h>
#include <linux/mmu_notifier.h>
#include <asm/tlbflush.h>
#include "internal.h"

static int mcopy_atomic_pte(struct mm_struct *dst_mm,
			    pmd_t *dst_pmd,
			    struct vm_area_struct *dst_vma,
			    unsigned long dst_addr,
24
25
			    unsigned long src_addr,
			    struct page **pagep)
26
27
28
29
30
31
{
	struct mem_cgroup *memcg;
	pte_t _dst_pte, *dst_pte;
	spinlock_t *ptl;
	void *page_kaddr;
	int ret;
32
	struct page *page;
33

34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
	if (!*pagep) {
		ret = -ENOMEM;
		page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, dst_vma, dst_addr);
		if (!page)
			goto out;

		page_kaddr = kmap_atomic(page);
		ret = copy_from_user(page_kaddr,
				     (const void __user *) src_addr,
				     PAGE_SIZE);
		kunmap_atomic(page_kaddr);

		/* fallback to copy_from_user outside mmap_sem */
		if (unlikely(ret)) {
			ret = -EFAULT;
			*pagep = page;
			/* don't free the page */
			goto out;
		}
	} else {
		page = *pagep;
		*pagep = NULL;
	}
57
58
59
60
61
62
63
64
65

	/*
	 * The memory barrier inside __SetPageUptodate makes sure that
	 * preceeding stores to the page contents become visible before
	 * the set_pte_at() write.
	 */
	__SetPageUptodate(page);

	ret = -ENOMEM;
66
	if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg, false))
67
68
69
70
71
72
73
74
75
76
77
78
		goto out_release;

	_dst_pte = mk_pte(page, dst_vma->vm_page_prot);
	if (dst_vma->vm_flags & VM_WRITE)
		_dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));

	ret = -EEXIST;
	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
	if (!pte_none(*dst_pte))
		goto out_release_uncharge_unlock;

	inc_mm_counter(dst_mm, MM_ANONPAGES);
79
	page_add_new_anon_rmap(page, dst_vma, dst_addr, false);
80
	mem_cgroup_commit_charge(page, memcg, false, false);
81
82
83
84
85
86
87
88
89
90
91
92
93
	lru_cache_add_active_or_unevictable(page, dst_vma);

	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);

	/* No need to invalidate - it was non-present before */
	update_mmu_cache(dst_vma, dst_addr, dst_pte);

	pte_unmap_unlock(dst_pte, ptl);
	ret = 0;
out:
	return ret;
out_release_uncharge_unlock:
	pte_unmap_unlock(dst_pte, ptl);
94
	mem_cgroup_cancel_charge(page, memcg, false);
95
out_release:
96
	put_page(page);
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
	goto out;
}

static int mfill_zeropage_pte(struct mm_struct *dst_mm,
			      pmd_t *dst_pmd,
			      struct vm_area_struct *dst_vma,
			      unsigned long dst_addr)
{
	pte_t _dst_pte, *dst_pte;
	spinlock_t *ptl;
	int ret;

	_dst_pte = pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr),
					 dst_vma->vm_page_prot));
	ret = -EEXIST;
	dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
	if (!pte_none(*dst_pte))
		goto out_unlock;
	set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
	/* No need to invalidate - it was non-present before */
	update_mmu_cache(dst_vma, dst_addr, dst_pte);
	ret = 0;
out_unlock:
	pte_unmap_unlock(dst_pte, ptl);
	return ret;
}

static pmd_t *mm_alloc_pmd(struct mm_struct *mm, unsigned long address)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd = NULL;

	pgd = pgd_offset(mm, address);
	pud = pud_alloc(mm, pgd, address);
	if (pud)
		/*
		 * Note that we didn't run this because the pmd was
		 * missing, the *pmd may be already established and in
		 * turn it may also be a trans_huge_pmd.
		 */
		pmd = pmd_alloc(mm, pud, address);
	return pmd;
}

static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
					      unsigned long dst_start,
					      unsigned long src_start,
					      unsigned long len,
					      bool zeropage)
{
	struct vm_area_struct *dst_vma;
	ssize_t err;
	pmd_t *dst_pmd;
	unsigned long src_addr, dst_addr;
152
153
	long copied;
	struct page *page;
154
155
156
157
158
159
160
161
162
163
164

	/*
	 * Sanitize the command parameters:
	 */
	BUG_ON(dst_start & ~PAGE_MASK);
	BUG_ON(len & ~PAGE_MASK);

	/* Does the address range wrap, or is the span zero-sized? */
	BUG_ON(src_start + len <= src_start);
	BUG_ON(dst_start + len <= dst_start);

165
166
167
168
169
	src_addr = src_start;
	dst_addr = dst_start;
	copied = 0;
	page = NULL;
retry:
170
171
172
173
174
175
176
177
178
	down_read(&dst_mm->mmap_sem);

	/*
	 * Make sure the vma is not shared, that the dst range is
	 * both valid and fully within a single existing vma.
	 */
	err = -EINVAL;
	dst_vma = find_vma(dst_mm, dst_start);
	if (!dst_vma || (dst_vma->vm_flags & VM_SHARED))
179
		goto out_unlock;
180
181
	if (dst_start < dst_vma->vm_start ||
	    dst_start + len > dst_vma->vm_end)
182
		goto out_unlock;
183
184
185
186
187
188
189
190
191
192
193

	/*
	 * Be strict and only allow __mcopy_atomic on userfaultfd
	 * registered ranges to prevent userland errors going
	 * unnoticed. As far as the VM consistency is concerned, it
	 * would be perfectly safe to remove this check, but there's
	 * no useful usage for __mcopy_atomic ouside of userfaultfd
	 * registered ranges. This is after all why these are ioctls
	 * belonging to the userfaultfd and not syscalls.
	 */
	if (!dst_vma->vm_userfaultfd_ctx.ctx)
194
		goto out_unlock;
195
196
197
198
199

	/*
	 * FIXME: only allow copying on anonymous vmas, tmpfs should
	 * be added.
	 */
200
	if (!vma_is_anonymous(dst_vma))
201
		goto out_unlock;
202
203
204
205
206
207
208
209

	/*
	 * Ensure the dst_vma has a anon_vma or this page
	 * would get a NULL anon_vma when moved in the
	 * dst_vma.
	 */
	err = -ENOMEM;
	if (unlikely(anon_vma_prepare(dst_vma)))
210
		goto out_unlock;
211

212
	while (src_addr < src_start + len) {
213
		pmd_t dst_pmdval;
214

215
		BUG_ON(dst_addr >= dst_start + len);
216

217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
		dst_pmd = mm_alloc_pmd(dst_mm, dst_addr);
		if (unlikely(!dst_pmd)) {
			err = -ENOMEM;
			break;
		}

		dst_pmdval = pmd_read_atomic(dst_pmd);
		/*
		 * If the dst_pmd is mapped as THP don't
		 * override it and just be strict.
		 */
		if (unlikely(pmd_trans_huge(dst_pmdval))) {
			err = -EEXIST;
			break;
		}
		if (unlikely(pmd_none(dst_pmdval)) &&
233
		    unlikely(__pte_alloc(dst_mm, dst_pmd, dst_addr))) {
234
235
236
237
238
239
240
241
242
243
244
245
246
247
			err = -ENOMEM;
			break;
		}
		/* If an huge pmd materialized from under us fail */
		if (unlikely(pmd_trans_huge(*dst_pmd))) {
			err = -EFAULT;
			break;
		}

		BUG_ON(pmd_none(*dst_pmd));
		BUG_ON(pmd_trans_huge(*dst_pmd));

		if (!zeropage)
			err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma,
248
					       dst_addr, src_addr, &page);
249
250
251
252
253
254
		else
			err = mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma,
						 dst_addr);

		cond_resched();

255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
		if (unlikely(err == -EFAULT)) {
			void *page_kaddr;

			up_read(&dst_mm->mmap_sem);
			BUG_ON(!page);

			page_kaddr = kmap(page);
			err = copy_from_user(page_kaddr,
					     (const void __user *) src_addr,
					     PAGE_SIZE);
			kunmap(page);
			if (unlikely(err)) {
				err = -EFAULT;
				goto out;
			}
			goto retry;
		} else
			BUG_ON(page);

274
275
276
277
278
279
280
281
282
283
284
285
		if (!err) {
			dst_addr += PAGE_SIZE;
			src_addr += PAGE_SIZE;
			copied += PAGE_SIZE;

			if (fatal_signal_pending(current))
				err = -EINTR;
		}
		if (err)
			break;
	}

286
out_unlock:
287
	up_read(&dst_mm->mmap_sem);
288
289
out:
	if (page)
290
		put_page(page);
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
	BUG_ON(copied < 0);
	BUG_ON(err > 0);
	BUG_ON(!copied && !err);
	return copied ? copied : err;
}

ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start,
		     unsigned long src_start, unsigned long len)
{
	return __mcopy_atomic(dst_mm, dst_start, src_start, len, false);
}

ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long start,
		       unsigned long len)
{
	return __mcopy_atomic(dst_mm, start, 0, len, true);
}