userfaultfd.c 15.5 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
/*
 *  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>
11
#include <linux/sched/signal.h>
12
13
14
15
16
17
#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>
18
#include <linux/hugetlb.h>
19
#include <linux/shmem_fs.h>
20
21
22
23
24
25
26
#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,
27
28
			    unsigned long src_addr,
			    struct page **pagep)
29
30
31
32
33
34
{
	struct mem_cgroup *memcg;
	pte_t _dst_pte, *dst_pte;
	spinlock_t *ptl;
	void *page_kaddr;
	int ret;
35
	struct page *page;
36

37
38
39
40
41
42
43
44
45
46
47
48
49
50
	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)) {
51
			ret = -ENOENT;
52
53
54
55
56
57
58
59
			*pagep = page;
			/* don't free the page */
			goto out;
		}
	} else {
		page = *pagep;
		*pagep = NULL;
	}
60
61
62
63
64
65
66
67
68

	/*
	 * 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;
69
	if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg, false))
70
71
72
73
74
75
76
77
78
79
80
81
		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);
82
	page_add_new_anon_rmap(page, dst_vma, dst_addr, false);
83
	mem_cgroup_commit_charge(page, memcg, false, false);
84
85
86
87
88
89
90
91
92
93
94
95
96
	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);
97
	mem_cgroup_cancel_charge(page, memcg, false);
98
out_release:
99
	put_page(page);
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
	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;
130
	p4d_t *p4d;
131
132
133
	pud_t *pud;

	pgd = pgd_offset(mm, address);
134
135
136
137
138
139
140
141
142
143
144
145
	p4d = p4d_alloc(mm, pgd, address);
	if (!p4d)
		return NULL;
	pud = pud_alloc(mm, p4d, address);
	if (!pud)
		return NULL;
	/*
	 * 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.
	 */
	return pmd_alloc(mm, pud, address);
146
147
}

148
149
150
151
152
153
154
155
156
157
158
159
#ifdef CONFIG_HUGETLB_PAGE
/*
 * __mcopy_atomic processing for HUGETLB vmas.  Note that this routine is
 * called with mmap_sem held, it will release mmap_sem before returning.
 */
static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm,
					      struct vm_area_struct *dst_vma,
					      unsigned long dst_start,
					      unsigned long src_start,
					      unsigned long len,
					      bool zeropage)
{
160
161
	int vm_alloc_shared = dst_vma->vm_flags & VM_SHARED;
	int vm_shared = dst_vma->vm_flags & VM_SHARED;
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
	ssize_t err;
	pte_t *dst_pte;
	unsigned long src_addr, dst_addr;
	long copied;
	struct page *page;
	struct hstate *h;
	unsigned long vma_hpagesize;
	pgoff_t idx;
	u32 hash;
	struct address_space *mapping;

	/*
	 * There is no default zero huge page for all huge page sizes as
	 * supported by hugetlb.  A PMD_SIZE huge pages may exist as used
	 * by THP.  Since we can not reliably insert a zero page, this
	 * feature is not supported.
	 */
	if (zeropage) {
		up_read(&dst_mm->mmap_sem);
		return -EINVAL;
	}

	src_addr = src_start;
	dst_addr = dst_start;
	copied = 0;
	page = NULL;
	vma_hpagesize = vma_kernel_pagesize(dst_vma);

	/*
	 * Validate alignment based on huge page size
	 */
	err = -EINVAL;
	if (dst_start & (vma_hpagesize - 1) || len & (vma_hpagesize - 1))
		goto out_unlock;

retry:
	/*
	 * On routine entry dst_vma is set.  If we had to drop mmap_sem and
	 * retry, dst_vma will be set to NULL and we must lookup again.
	 */
	if (!dst_vma) {
203
		err = -ENOENT;
204
205
206
207
		dst_vma = find_vma(dst_mm, dst_start);
		if (!dst_vma || !is_vm_hugetlb_page(dst_vma))
			goto out_unlock;
		/*
208
209
		 * Only allow __mcopy_atomic_hugetlb on userfaultfd
		 * registered ranges.
210
		 */
211
212
213
		if (!dst_vma->vm_userfaultfd_ctx.ctx)
			goto out_unlock;

214
215
216
		if (dst_start < dst_vma->vm_start ||
		    dst_start + len > dst_vma->vm_end)
			goto out_unlock;
217

218
219
220
221
		err = -EINVAL;
		if (vma_hpagesize != vma_kernel_pagesize(dst_vma))
			goto out_unlock;

222
		vm_shared = dst_vma->vm_flags & VM_SHARED;
223
224
225
226
227
228
229
	}

	if (WARN_ON(dst_addr & (vma_hpagesize - 1) ||
		    (len - copied) & (vma_hpagesize - 1)))
		goto out_unlock;

	/*
230
	 * If not shared, ensure the dst_vma has a anon_vma.
231
232
	 */
	err = -ENOMEM;
233
234
235
236
	if (!vm_shared) {
		if (unlikely(anon_vma_prepare(dst_vma)))
			goto out_unlock;
	}
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

	h = hstate_vma(dst_vma);

	while (src_addr < src_start + len) {
		pte_t dst_pteval;

		BUG_ON(dst_addr >= dst_start + len);
		VM_BUG_ON(dst_addr & ~huge_page_mask(h));

		/*
		 * Serialize via hugetlb_fault_mutex
		 */
		idx = linear_page_index(dst_vma, dst_addr);
		mapping = dst_vma->vm_file->f_mapping;
		hash = hugetlb_fault_mutex_hash(h, dst_mm, dst_vma, mapping,
								idx, dst_addr);
		mutex_lock(&hugetlb_fault_mutex_table[hash]);

		err = -ENOMEM;
		dst_pte = huge_pte_alloc(dst_mm, dst_addr, huge_page_size(h));
		if (!dst_pte) {
			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
			goto out_unlock;
		}

		err = -EEXIST;
		dst_pteval = huge_ptep_get(dst_pte);
		if (!huge_pte_none(dst_pteval)) {
			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
			goto out_unlock;
		}

		err = hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma,
						dst_addr, src_addr, &page);

		mutex_unlock(&hugetlb_fault_mutex_table[hash]);
273
		vm_alloc_shared = vm_shared;
274
275
276

		cond_resched();

277
		if (unlikely(err == -ENOENT)) {
278
279
280
281
282
			up_read(&dst_mm->mmap_sem);
			BUG_ON(!page);

			err = copy_huge_page_from_user(page,
						(const void __user *)src_addr,
283
						pages_per_huge_page(h), true);
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
			if (unlikely(err)) {
				err = -EFAULT;
				goto out;
			}
			down_read(&dst_mm->mmap_sem);

			dst_vma = NULL;
			goto retry;
		} else
			BUG_ON(page);

		if (!err) {
			dst_addr += vma_hpagesize;
			src_addr += vma_hpagesize;
			copied += vma_hpagesize;

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

out_unlock:
	up_read(&dst_mm->mmap_sem);
out:
310
311
312
	if (page) {
		/*
		 * We encountered an error and are about to free a newly
313
314
315
316
317
318
319
320
321
322
323
324
		 * allocated huge page.
		 *
		 * Reservation handling is very subtle, and is different for
		 * private and shared mappings.  See the routine
		 * restore_reserve_on_error for details.  Unfortunately, we
		 * can not call restore_reserve_on_error now as it would
		 * require holding mmap_sem.
		 *
		 * If a reservation for the page existed in the reservation
		 * map of a private mapping, the map was modified to indicate
		 * the reservation was consumed when the page was allocated.
		 * We clear the PagePrivate flag now so that the global
325
326
327
		 * reserve count will not be incremented in free_huge_page.
		 * The reservation map will still indicate the reservation
		 * was consumed and possibly prevent later page allocation.
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
		 * This is better than leaking a global reservation.  If no
		 * reservation existed, it is still safe to clear PagePrivate
		 * as no adjustments to reservation counts were made during
		 * allocation.
		 *
		 * The reservation map for shared mappings indicates which
		 * pages have reservations.  When a huge page is allocated
		 * for an address with a reservation, no change is made to
		 * the reserve map.  In this case PagePrivate will be set
		 * to indicate that the global reservation count should be
		 * incremented when the page is freed.  This is the desired
		 * behavior.  However, when a huge page is allocated for an
		 * address without a reservation a reservation entry is added
		 * to the reservation map, and PagePrivate will not be set.
		 * When the page is freed, the global reserve count will NOT
		 * be incremented and it will appear as though we have leaked
		 * reserved page.  In this case, set PagePrivate so that the
		 * global reserve count will be incremented to match the
		 * reservation map entry which was created.
		 *
		 * Note that vm_alloc_shared is based on the flags of the vma
		 * for which the page was originally allocated.  dst_vma could
		 * be different or NULL on error.
351
		 */
352
353
354
355
		if (vm_alloc_shared)
			SetPagePrivate(page);
		else
			ClearPagePrivate(page);
356
		put_page(page);
357
	}
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
	BUG_ON(copied < 0);
	BUG_ON(err > 0);
	BUG_ON(!copied && !err);
	return copied ? copied : err;
}
#else /* !CONFIG_HUGETLB_PAGE */
/* fail at build time if gcc attempts to use this */
extern ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm,
				      struct vm_area_struct *dst_vma,
				      unsigned long dst_start,
				      unsigned long src_start,
				      unsigned long len,
				      bool zeropage);
#endif /* CONFIG_HUGETLB_PAGE */

373
374
375
376
377
378
379
380
381
382
static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm,
						pmd_t *dst_pmd,
						struct vm_area_struct *dst_vma,
						unsigned long dst_addr,
						unsigned long src_addr,
						struct page **page,
						bool zeropage)
{
	ssize_t err;

383
384
385
386
387
388
389
390
391
392
393
	/*
	 * The normal page fault path for a shmem will invoke the
	 * fault, fill the hole in the file and COW it right away. The
	 * result generates plain anonymous memory. So when we are
	 * asked to fill an hole in a MAP_PRIVATE shmem mapping, we'll
	 * generate anonymous memory directly without actually filling
	 * the hole. For the MAP_PRIVATE case the robustness check
	 * only happens in the pagetable (to verify it's still none)
	 * and not in the radix tree.
	 */
	if (!(dst_vma->vm_flags & VM_SHARED)) {
394
395
396
397
398
399
400
		if (!zeropage)
			err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma,
					       dst_addr, src_addr, page);
		else
			err = mfill_zeropage_pte(dst_mm, dst_pmd,
						 dst_vma, dst_addr);
	} else {
401
		if (!zeropage)
402
403
404
			err = shmem_mcopy_atomic_pte(dst_mm, dst_pmd,
						     dst_vma, dst_addr,
						     src_addr, page);
405
406
407
		else
			err = shmem_mfill_zeropage_pte(dst_mm, dst_pmd,
						       dst_vma, dst_addr);
408
409
410
411
412
	}

	return err;
}

413
414
415
416
static __always_inline ssize_t __mcopy_atomic(struct mm_struct *dst_mm,
					      unsigned long dst_start,
					      unsigned long src_start,
					      unsigned long len,
417
418
					      bool zeropage,
					      bool *mmap_changing)
419
420
421
422
423
{
	struct vm_area_struct *dst_vma;
	ssize_t err;
	pmd_t *dst_pmd;
	unsigned long src_addr, dst_addr;
424
425
	long copied;
	struct page *page;
426
427
428
429
430
431
432
433
434
435
436

	/*
	 * 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);

437
438
439
440
441
	src_addr = src_start;
	dst_addr = dst_start;
	copied = 0;
	page = NULL;
retry:
442
443
	down_read(&dst_mm->mmap_sem);

444
445
446
447
448
449
450
451
452
	/*
	 * If memory mappings are changing because of non-cooperative
	 * operation (e.g. mremap) running in parallel, bail out and
	 * request the user to retry later
	 */
	err = -EAGAIN;
	if (mmap_changing && READ_ONCE(*mmap_changing))
		goto out_unlock;

453
454
455
456
	/*
	 * Make sure the vma is not shared, that the dst range is
	 * both valid and fully within a single existing vma.
	 */
457
	err = -ENOENT;
458
	dst_vma = find_vma(dst_mm, dst_start);
459
460
	if (!dst_vma)
		goto out_unlock;
461
	/*
462
463
464
465
466
467
468
	 * 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.
469
	 */
470
	if (!dst_vma->vm_userfaultfd_ctx.ctx)
471
		goto out_unlock;
472

473
474
	if (dst_start < dst_vma->vm_start ||
	    dst_start + len > dst_vma->vm_end)
475
		goto out_unlock;
476

477
478
479
480
481
482
483
484
485
	err = -EINVAL;
	/*
	 * shmem_zero_setup is invoked in mmap for MAP_ANONYMOUS|MAP_SHARED but
	 * it will overwrite vm_ops, so vma_is_anonymous must return false.
	 */
	if (WARN_ON_ONCE(vma_is_anonymous(dst_vma) &&
	    dst_vma->vm_flags & VM_SHARED))
		goto out_unlock;

486
487
488
489
490
491
492
	/*
	 * If this is a HUGETLB vma, pass off to appropriate routine
	 */
	if (is_vm_hugetlb_page(dst_vma))
		return  __mcopy_atomic_hugetlb(dst_mm, dst_vma, dst_start,
						src_start, len, zeropage);

493
	if (!vma_is_anonymous(dst_vma) && !vma_is_shmem(dst_vma))
494
		goto out_unlock;
495
496
497
498
499
500
501

	/*
	 * 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;
502
503
	if (!(dst_vma->vm_flags & VM_SHARED) &&
	    unlikely(anon_vma_prepare(dst_vma)))
504
		goto out_unlock;
505

506
	while (src_addr < src_start + len) {
507
		pmd_t dst_pmdval;
508

509
		BUG_ON(dst_addr >= dst_start + len);
510

511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
		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)) &&
527
		    unlikely(__pte_alloc(dst_mm, dst_pmd, dst_addr))) {
528
529
530
531
532
533
534
535
536
537
538
539
			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));

540
541
		err = mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
				       src_addr, &page, zeropage);
542
543
		cond_resched();

544
		if (unlikely(err == -ENOENT)) {
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
			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);

563
564
565
566
567
568
569
570
571
572
573
574
		if (!err) {
			dst_addr += PAGE_SIZE;
			src_addr += PAGE_SIZE;
			copied += PAGE_SIZE;

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

575
out_unlock:
576
	up_read(&dst_mm->mmap_sem);
577
578
out:
	if (page)
579
		put_page(page);
580
581
582
583
584
585
586
	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,
587
588
		     unsigned long src_start, unsigned long len,
		     bool *mmap_changing)
589
{
590
591
	return __mcopy_atomic(dst_mm, dst_start, src_start, len, false,
			      mmap_changing);
592
593
594
}

ssize_t mfill_zeropage(struct mm_struct *dst_mm, unsigned long start,
595
		       unsigned long len, bool *mmap_changing)
596
{
597
	return __mcopy_atomic(dst_mm, start, 0, len, true, mmap_changing);
598
}