summaryrefslogtreecommitdiffstats
path: root/virt/kvm/guest_memfd.c
blob: 747fe251e445bbe30034603632ae501909180a02 (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
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
// SPDX-License-Identifier: GPL-2.0
#include <linux/backing-dev.h>
#include <linux/falloc.h>
#include <linux/kvm_host.h>
#include <linux/pagemap.h>
#include <linux/anon_inodes.h>

#include "kvm_mm.h"

struct kvm_gmem {
	struct kvm *kvm;
	struct xarray bindings;
	struct list_head entry;
};

static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index)
{
	struct folio *folio;

	/* TODO: Support huge pages. */
	folio = filemap_grab_folio(inode->i_mapping, index);
	if (IS_ERR_OR_NULL(folio))
		return NULL;

	/*
	 * Use the up-to-date flag to track whether or not the memory has been
	 * zeroed before being handed off to the guest.  There is no backing
	 * storage for the memory, so the folio will remain up-to-date until
	 * it's removed.
	 *
	 * TODO: Skip clearing pages when trusted firmware will do it when
	 * assigning memory to the guest.
	 */
	if (!folio_test_uptodate(folio)) {
		unsigned long nr_pages = folio_nr_pages(folio);
		unsigned long i;

		for (i = 0; i < nr_pages; i++)
			clear_highpage(folio_page(folio, i));

		folio_mark_uptodate(folio);
	}

	/*
	 * Ignore accessed, referenced, and dirty flags.  The memory is
	 * unevictable and there is no storage to write back to.
	 */
	return folio;
}

static void kvm_gmem_invalidate_begin(struct kvm_gmem *gmem, pgoff_t start,
				      pgoff_t end)
{
	bool flush = false, found_memslot = false;
	struct kvm_memory_slot *slot;
	struct kvm *kvm = gmem->kvm;
	unsigned long index;

	xa_for_each_range(&gmem->bindings, index, slot, start, end - 1) {
		pgoff_t pgoff = slot->gmem.pgoff;

		struct kvm_gfn_range gfn_range = {
			.start = slot->base_gfn + max(pgoff, start) - pgoff,
			.end = slot->base_gfn + min(pgoff + slot->npages, end) - pgoff,
			.slot = slot,
			.may_block = true,
		};

		if (!found_memslot) {
			found_memslot = true;

			KVM_MMU_LOCK(kvm);
			kvm_mmu_invalidate_begin(kvm);
		}

		flush |= kvm_mmu_unmap_gfn_range(kvm, &gfn_range);
	}

	if (flush)
		kvm_flush_remote_tlbs(kvm);

	if (found_memslot)
		KVM_MMU_UNLOCK(kvm);
}

static void kvm_gmem_invalidate_end(struct kvm_gmem *gmem, pgoff_t start,
				    pgoff_t end)
{
	struct kvm *kvm = gmem->kvm;

	if (xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) {
		KVM_MMU_LOCK(kvm);
		kvm_mmu_invalidate_end(kvm);
		KVM_MMU_UNLOCK(kvm);
	}
}

static long kvm_gmem_punch_hole(struct inode *inode, loff_t offset, loff_t len)
{
	struct list_head *gmem_list = &inode->i_mapping->i_private_list;
	pgoff_t start = offset >> PAGE_SHIFT;
	pgoff_t end = (offset + len) >> PAGE_SHIFT;
	struct kvm_gmem *gmem;

	/*
	 * Bindings must be stable across invalidation to ensure the start+end
	 * are balanced.
	 */
	filemap_invalidate_lock(inode->i_mapping);

	list_for_each_entry(gmem, gmem_list, entry)
		kvm_gmem_invalidate_begin(gmem, start, end);

	truncate_inode_pages_range(inode->i_mapping, offset, offset + len - 1);

	list_for_each_entry(gmem, gmem_list, entry)
		kvm_gmem_invalidate_end(gmem, start, end);

	filemap_invalidate_unlock(inode->i_mapping);

	return 0;
}

static long kvm_gmem_allocate(struct inode *inode, loff_t offset, loff_t len)
{
	struct address_space *mapping = inode->i_mapping;
	pgoff_t start, index, end;
	int r;

	/* Dedicated guest is immutable by default. */
	if (offset + len > i_size_read(inode))
		return -EINVAL;

	filemap_invalidate_lock_shared(mapping);

	start = offset >> PAGE_SHIFT;
	end = (offset + len) >> PAGE_SHIFT;

	r = 0;
	for (index = start; index < end; ) {
		struct folio *folio;

		if (signal_pending(current)) {
			r = -EINTR;
			break;
		}

		folio = kvm_gmem_get_folio(inode, index);
		if (!folio) {
			r = -ENOMEM;
			break;
		}

		index = folio_next_index(folio);

		folio_unlock(folio);
		folio_put(folio);

		/* 64-bit only, wrapping the index should be impossible. */
		if (WARN_ON_ONCE(!index))
			break;

		cond_resched();
	}

	filemap_invalidate_unlock_shared(mapping);

	return r;
}

static long kvm_gmem_fallocate(struct file *file, int mode, loff_t offset,
			       loff_t len)
{
	int ret;

	if (!(mode & FALLOC_FL_KEEP_SIZE))
		return -EOPNOTSUPP;

	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
		return -EOPNOTSUPP;

	if (!PAGE_ALIGNED(offset) || !PAGE_ALIGNED(len))
		return -EINVAL;

	if (mode & FALLOC_FL_PUNCH_HOLE)
		ret = kvm_gmem_punch_hole(file_inode(file), offset, len);
	else
		ret = kvm_gmem_allocate(file_inode(file), offset, len);

	if (!ret)
		file_modified(file);
	return ret;
}

static int kvm_gmem_release(struct inode *inode, struct file *file)
{
	struct kvm_gmem *gmem = file->private_data;
	struct kvm_memory_slot *slot;
	struct kvm *kvm = gmem->kvm;
	unsigned long index;

	/*
	 * Prevent concurrent attempts to *unbind* a memslot.  This is the last
	 * reference to the file and thus no new bindings can be created, but
	 * dereferencing the slot for existing bindings needs to be protected
	 * against memslot updates, specifically so that unbind doesn't race
	 * and free the memslot (kvm_gmem_get_file() will return NULL).
	 */
	mutex_lock(&kvm->slots_lock);

	filemap_invalidate_lock(inode->i_mapping);

	xa_for_each(&gmem->bindings, index, slot)
		rcu_assign_pointer(slot->gmem.file, NULL);

	synchronize_rcu();

	/*
	 * All in-flight operations are gone and new bindings can be created.
	 * Zap all SPTEs pointed at by this file.  Do not free the backing
	 * memory, as its lifetime is associated with the inode, not the file.
	 */
	kvm_gmem_invalidate_begin(gmem, 0, -1ul);
	kvm_gmem_invalidate_end(gmem, 0, -1ul);

	list_del(&gmem->entry);

	filemap_invalidate_unlock(inode->i_mapping);

	mutex_unlock(&kvm->slots_lock);

	xa_destroy(&gmem->bindings);
	kfree(gmem);

	kvm_put_kvm(kvm);

	return 0;
}

static inline struct file *kvm_gmem_get_file(struct kvm_memory_slot *slot)
{
	/*
	 * Do not return slot->gmem.file if it has already been closed;
	 * there might be some time between the last fput() and when
	 * kvm_gmem_release() clears slot->gmem.file, and you do not
	 * want to spin in the meanwhile.
	 */
	return get_file_active(&slot->gmem.file);
}

static struct file_operations kvm_gmem_fops = {
	.open		= generic_file_open,
	.release	= kvm_gmem_release,
	.fallocate	= kvm_gmem_fallocate,
};

void kvm_gmem_init(struct module *module)
{
	kvm_gmem_fops.owner = module;
}

static int kvm_gmem_migrate_folio(struct address_space *mapping,
				  struct folio *dst, struct folio *src,
				  enum migrate_mode mode)
{
	WARN_ON_ONCE(1);
	return -EINVAL;
}

static int kvm_gmem_error_folio(struct address_space *mapping, struct folio *folio)
{
	struct list_head *gmem_list = &mapping->i_private_list;
	struct kvm_gmem *gmem;
	pgoff_t start, end;

	filemap_invalidate_lock_shared(mapping);

	start = folio->index;
	end = start + folio_nr_pages(folio);

	list_for_each_entry(gmem, gmem_list, entry)
		kvm_gmem_invalidate_begin(gmem, start, end);

	/*
	 * Do not truncate the range, what action is taken in response to the
	 * error is userspace's decision (assuming the architecture supports
	 * gracefully handling memory errors).  If/when the guest attempts to
	 * access a poisoned page, kvm_gmem_get_pfn() will return -EHWPOISON,
	 * at which point KVM can either terminate the VM or propagate the
	 * error to userspace.
	 */

	list_for_each_entry(gmem, gmem_list, entry)
		kvm_gmem_invalidate_end(gmem, start, end);

	filemap_invalidate_unlock_shared(mapping);

	return MF_DELAYED;
}

static const struct address_space_operations kvm_gmem_aops = {
	.dirty_folio = noop_dirty_folio,
	.migrate_folio	= kvm_gmem_migrate_folio,
	.error_remove_folio = kvm_gmem_error_folio,
};

static int kvm_gmem_getattr(struct mnt_idmap *idmap, const struct path *path,
			    struct kstat *stat, u32 request_mask,
			    unsigned int query_flags)
{
	struct inode *inode = path->dentry->d_inode;

	generic_fillattr(idmap, request_mask, inode, stat);
	return 0;
}

static int kvm_gmem_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
			    struct iattr *attr)
{
	return -EINVAL;
}
static const struct inode_operations kvm_gmem_iops = {
	.getattr	= kvm_gmem_getattr,
	.setattr	= kvm_gmem_setattr,
};

static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags)
{
	const char *anon_name = "[kvm-gmem]";
	struct kvm_gmem *gmem;
	struct inode *inode;
	struct file *file;
	int fd, err;

	fd = get_unused_fd_flags(0);
	if (fd < 0)
		return fd;

	gmem = kzalloc(sizeof(*gmem), GFP_KERNEL);
	if (!gmem) {
		err = -ENOMEM;
		goto err_fd;
	}

	file = anon_inode_create_getfile(anon_name, &kvm_gmem_fops, gmem,
					 O_RDWR, NULL);
	if (IS_ERR(file)) {
		err = PTR_ERR(file);
		goto err_gmem;
	}

	file->f_flags |= O_LARGEFILE;

	inode = file->f_inode;
	WARN_ON(file->f_mapping != inode->i_mapping);

	inode->i_private = (void *)(unsigned long)flags;
	inode->i_op = &kvm_gmem_iops;
	inode->i_mapping->a_ops = &kvm_gmem_aops;
	inode->i_mode |= S_IFREG;
	inode->i_size = size;
	mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
	mapping_set_unmovable(inode->i_mapping);
	/* Unmovable mappings are supposed to be marked unevictable as well. */
	WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping));

	kvm_get_kvm(kvm);
	gmem->kvm = kvm;
	xa_init(&gmem->bindings);
	list_add(&gmem->entry, &inode->i_mapping->i_private_list);

	fd_install(fd, file);
	return fd;

err_gmem:
	kfree(gmem);
err_fd:
	put_unused_fd(fd);
	return err;
}

int kvm_gmem_create(struct kvm *kvm, struct kvm_create_guest_memfd *args)
{
	loff_t size = args->size;
	u64 flags = args->flags;
	u64 valid_flags = 0;

	if (flags & ~valid_flags)
		return -EINVAL;

	if (size <= 0 || !PAGE_ALIGNED(size))
		return -EINVAL;

	return __kvm_gmem_create(kvm, size, flags);
}

int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot,
		  unsigned int fd, loff_t offset)
{
	loff_t size = slot->npages << PAGE_SHIFT;
	unsigned long start, end;
	struct kvm_gmem *gmem;
	struct inode *inode;
	struct file *file;
	int r = -EINVAL;

	BUILD_BUG_ON(sizeof(gfn_t) != sizeof(slot->gmem.pgoff));

	file = fget(fd);
	if (!file)
		return -EBADF;

	if (file->f_op != &kvm_gmem_fops)
		goto err;

	gmem = file->private_data;
	if (gmem->kvm != kvm)
		goto err;

	inode = file_inode(file);

	if (offset < 0 || !PAGE_ALIGNED(offset) ||
	    offset + size > i_size_read(inode))
		goto err;

	filemap_invalidate_lock(inode->i_mapping);

	start = offset >> PAGE_SHIFT;
	end = start + slot->npages;

	if (!xa_empty(&gmem->bindings) &&
	    xa_find(&gmem->bindings, &start, end - 1, XA_PRESENT)) {
		filemap_invalidate_unlock(inode->i_mapping);
		goto err;
	}

	/*
	 * No synchronize_rcu() needed, any in-flight readers are guaranteed to
	 * be see either a NULL file or this new file, no need for them to go
	 * away.
	 */
	rcu_assign_pointer(slot->gmem.file, file);
	slot->gmem.pgoff = start;

	xa_store_range(&gmem->bindings, start, end - 1, slot, GFP_KERNEL);
	filemap_invalidate_unlock(inode->i_mapping);

	/*
	 * Drop the reference to the file, even on success.  The file pins KVM,
	 * not the other way 'round.  Active bindings are invalidated if the
	 * file is closed before memslots are destroyed.
	 */
	r = 0;
err:
	fput(file);
	return r;
}

void kvm_gmem_unbind(struct kvm_memory_slot *slot)
{
	unsigned long start = slot->gmem.pgoff;
	unsigned long end = start + slot->npages;
	struct kvm_gmem *gmem;
	struct file *file;

	/*
	 * Nothing to do if the underlying file was already closed (or is being
	 * closed right now), kvm_gmem_release() invalidates all bindings.
	 */
	file = kvm_gmem_get_file(slot);
	if (!file)
		return;

	gmem = file->private_data;

	filemap_invalidate_lock(file->f_mapping);
	xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL);
	rcu_assign_pointer(slot->gmem.file, NULL);
	synchronize_rcu();
	filemap_invalidate_unlock(file->f_mapping);

	fput(file);
}

int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
		     gfn_t gfn, kvm_pfn_t *pfn, int *max_order)
{
	pgoff_t index = gfn - slot->base_gfn + slot->gmem.pgoff;
	struct kvm_gmem *gmem;
	struct folio *folio;
	struct page *page;
	struct file *file;
	int r;

	file = kvm_gmem_get_file(slot);
	if (!file)
		return -EFAULT;

	gmem = file->private_data;

	if (WARN_ON_ONCE(xa_load(&gmem->bindings, index) != slot)) {
		r = -EIO;
		goto out_fput;
	}

	folio = kvm_gmem_get_folio(file_inode(file), index);
	if (!folio) {
		r = -ENOMEM;
		goto out_fput;
	}

	if (folio_test_hwpoison(folio)) {
		folio_unlock(folio);
		folio_put(folio);
		r = -EHWPOISON;
		goto out_fput;
	}

	page = folio_file_page(folio, index);

	*pfn = page_to_pfn(page);
	if (max_order)
		*max_order = 0;

	r = 0;

	folio_unlock(folio);
out_fput:
	fput(file);

	return r;
}
EXPORT_SYMBOL_GPL(kvm_gmem_get_pfn);