summaryrefslogtreecommitdiff
path: root/virt/kvm/pfncache.c
blob: 10842f1eeeae9baecbd937d186dfe6418c26f2f8 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * This module enables kernel and guest-mode vCPU access to guest physical
 * memory with suitable invalidation mechanisms.
 *
 * Copyright © 2021 Amazon.com, Inc. or its affiliates.
 *
 * Authors:
 *   David Woodhouse <dwmw2@infradead.org>
 */

#include <linux/kvm_host.h>
#include <linux/kvm.h>
#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/errno.h>

#include "kvm_mm.h"

/*
 * MMU notifier 'invalidate_range_start' hook.
 */
void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start,
				       unsigned long end, bool may_block)
{
	DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS);
	struct gfn_to_pfn_cache *gpc;
	bool evict_vcpus = false;

	spin_lock(&kvm->gpc_lock);
	list_for_each_entry(gpc, &kvm->gpc_list, list) {
		write_lock_irq(&gpc->lock);

		/* Only a single page so no need to care about length */
		if (gpc->valid && !is_error_noslot_pfn(gpc->pfn) &&
		    gpc->uhva >= start && gpc->uhva < end) {
			gpc->valid = false;

			/*
			 * If a guest vCPU could be using the physical address,
			 * it needs to be forced out of guest mode.
			 */
			if (gpc->usage & KVM_GUEST_USES_PFN) {
				if (!evict_vcpus) {
					evict_vcpus = true;
					bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS);
				}
				__set_bit(gpc->vcpu->vcpu_idx, vcpu_bitmap);
			}
		}
		write_unlock_irq(&gpc->lock);
	}
	spin_unlock(&kvm->gpc_lock);

	if (evict_vcpus) {
		/*
		 * KVM needs to ensure the vCPU is fully out of guest context
		 * before allowing the invalidation to continue.
		 */
		unsigned int req = KVM_REQ_OUTSIDE_GUEST_MODE;
		bool called;

		/*
		 * If the OOM reaper is active, then all vCPUs should have
		 * been stopped already, so perform the request without
		 * KVM_REQUEST_WAIT and be sad if any needed to be IPI'd.
		 */
		if (!may_block)
			req &= ~KVM_REQUEST_WAIT;

		called = kvm_make_vcpus_request_mask(kvm, req, vcpu_bitmap);

		WARN_ON_ONCE(called && !may_block);
	}
}

bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len)
{
	struct kvm_memslots *slots = kvm_memslots(gpc->kvm);

	if (!gpc->active)
		return false;

	if ((gpc->gpa & ~PAGE_MASK) + len > PAGE_SIZE)
		return false;

	if (gpc->generation != slots->generation || kvm_is_error_hva(gpc->uhva))
		return false;

	if (!gpc->valid)
		return false;

	return true;
}
EXPORT_SYMBOL_GPL(kvm_gpc_check);

static void *gpc_map(kvm_pfn_t pfn)
{
	if (pfn_valid(pfn))
		return kmap(pfn_to_page(pfn));

#ifdef CONFIG_HAS_IOMEM
	return memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
#else
	return NULL;
#endif
}

static void gpc_unmap(kvm_pfn_t pfn, void *khva)
{
	/* Unmap the old pfn/page if it was mapped before. */
	if (is_error_noslot_pfn(pfn) || !khva)
		return;

	if (pfn_valid(pfn)) {
		kunmap(pfn_to_page(pfn));
		return;
	}

#ifdef CONFIG_HAS_IOMEM
	memunmap(khva);
#endif
}

static inline bool mmu_notifier_retry_cache(struct kvm *kvm, unsigned long mmu_seq)
{
	/*
	 * mn_active_invalidate_count acts for all intents and purposes
	 * like mmu_invalidate_in_progress here; but the latter cannot
	 * be used here because the invalidation of caches in the
	 * mmu_notifier event occurs _before_ mmu_invalidate_in_progress
	 * is elevated.
	 *
	 * Note, it does not matter that mn_active_invalidate_count
	 * is not protected by gpc->lock.  It is guaranteed to
	 * be elevated before the mmu_notifier acquires gpc->lock, and
	 * isn't dropped until after mmu_invalidate_seq is updated.
	 */
	if (kvm->mn_active_invalidate_count)
		return true;

	/*
	 * Ensure mn_active_invalidate_count is read before
	 * mmu_invalidate_seq.  This pairs with the smp_wmb() in
	 * mmu_notifier_invalidate_range_end() to guarantee either the
	 * old (non-zero) value of mn_active_invalidate_count or the
	 * new (incremented) value of mmu_invalidate_seq is observed.
	 */
	smp_rmb();
	return kvm->mmu_invalidate_seq != mmu_seq;
}

static kvm_pfn_t hva_to_pfn_retry(struct gfn_to_pfn_cache *gpc)
{
	/* Note, the new page offset may be different than the old! */
	void *old_khva = gpc->khva - offset_in_page(gpc->khva);
	kvm_pfn_t new_pfn = KVM_PFN_ERR_FAULT;
	void *new_khva = NULL;
	unsigned long mmu_seq;

	lockdep_assert_held(&gpc->refresh_lock);

	lockdep_assert_held_write(&gpc->lock);

	/*
	 * Invalidate the cache prior to dropping gpc->lock, the gpa=>uhva
	 * assets have already been updated and so a concurrent check() from a
	 * different task may not fail the gpa/uhva/generation checks.
	 */
	gpc->valid = false;

	do {
		mmu_seq = gpc->kvm->mmu_invalidate_seq;
		smp_rmb();

		write_unlock_irq(&gpc->lock);

		/*
		 * If the previous iteration "failed" due to an mmu_notifier
		 * event, release the pfn and unmap the kernel virtual address
		 * from the previous attempt.  Unmapping might sleep, so this
		 * needs to be done after dropping the lock.  Opportunistically
		 * check for resched while the lock isn't held.
		 */
		if (new_pfn != KVM_PFN_ERR_FAULT) {
			/*
			 * Keep the mapping if the previous iteration reused
			 * the existing mapping and didn't create a new one.
			 */
			if (new_khva != old_khva)
				gpc_unmap(new_pfn, new_khva);

			kvm_release_pfn_clean(new_pfn);

			cond_resched();
		}

		/* We always request a writeable mapping */
		new_pfn = hva_to_pfn(gpc->uhva, false, false, NULL, true, NULL);
		if (is_error_noslot_pfn(new_pfn))
			goto out_error;

		/*
		 * Obtain a new kernel mapping if KVM itself will access the
		 * pfn.  Note, kmap() and memremap() can both sleep, so this
		 * too must be done outside of gpc->lock!
		 */
		if (gpc->usage & KVM_HOST_USES_PFN) {
			if (new_pfn == gpc->pfn)
				new_khva = old_khva;
			else
				new_khva = gpc_map(new_pfn);

			if (!new_khva) {
				kvm_release_pfn_clean(new_pfn);
				goto out_error;
			}
		}

		write_lock_irq(&gpc->lock);

		/*
		 * Other tasks must wait for _this_ refresh to complete before
		 * attempting to refresh.
		 */
		WARN_ON_ONCE(gpc->valid);
	} while (mmu_notifier_retry_cache(gpc->kvm, mmu_seq));

	gpc->valid = true;
	gpc->pfn = new_pfn;
	gpc->khva = new_khva + (gpc->gpa & ~PAGE_MASK);

	/*
	 * Put the reference to the _new_ pfn.  The pfn is now tracked by the
	 * cache and can be safely migrated, swapped, etc... as the cache will
	 * invalidate any mappings in response to relevant mmu_notifier events.
	 */
	kvm_release_pfn_clean(new_pfn);

	return 0;

out_error:
	write_lock_irq(&gpc->lock);

	return -EFAULT;
}

static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa,
			     unsigned long len)
{
	struct kvm_memslots *slots = kvm_memslots(gpc->kvm);
	unsigned long page_offset = gpa & ~PAGE_MASK;
	bool unmap_old = false;
	unsigned long old_uhva;
	kvm_pfn_t old_pfn;
	void *old_khva;
	int ret;

	/*
	 * If must fit within a single page. The 'len' argument is
	 * only to enforce that.
	 */
	if (page_offset + len > PAGE_SIZE)
		return -EINVAL;

	/*
	 * If another task is refreshing the cache, wait for it to complete.
	 * There is no guarantee that concurrent refreshes will see the same
	 * gpa, memslots generation, etc..., so they must be fully serialized.
	 */
	mutex_lock(&gpc->refresh_lock);

	write_lock_irq(&gpc->lock);

	if (!gpc->active) {
		ret = -EINVAL;
		goto out_unlock;
	}

	old_pfn = gpc->pfn;
	old_khva = gpc->khva - offset_in_page(gpc->khva);
	old_uhva = gpc->uhva;

	/* If the userspace HVA is invalid, refresh that first */
	if (gpc->gpa != gpa || gpc->generation != slots->generation ||
	    kvm_is_error_hva(gpc->uhva)) {
		gfn_t gfn = gpa_to_gfn(gpa);

		gpc->gpa = gpa;
		gpc->generation = slots->generation;
		gpc->memslot = __gfn_to_memslot(slots, gfn);
		gpc->uhva = gfn_to_hva_memslot(gpc->memslot, gfn);

		if (kvm_is_error_hva(gpc->uhva)) {
			ret = -EFAULT;
			goto out;
		}
	}

	/*
	 * If the userspace HVA changed or the PFN was already invalid,
	 * drop the lock and do the HVA to PFN lookup again.
	 */
	if (!gpc->valid || old_uhva != gpc->uhva) {
		ret = hva_to_pfn_retry(gpc);
	} else {
		/*
		 * If the HVA→PFN mapping was already valid, don't unmap it.
		 * But do update gpc->khva because the offset within the page
		 * may have changed.
		 */
		gpc->khva = old_khva + page_offset;
		ret = 0;
		goto out_unlock;
	}

 out:
	/*
	 * Invalidate the cache and purge the pfn/khva if the refresh failed.
	 * Some/all of the uhva, gpa, and memslot generation info may still be
	 * valid, leave it as is.
	 */
	if (ret) {
		gpc->valid = false;
		gpc->pfn = KVM_PFN_ERR_FAULT;
		gpc->khva = NULL;
	}

	/* Detect a pfn change before dropping the lock! */
	unmap_old = (old_pfn != gpc->pfn);

out_unlock:
	write_unlock_irq(&gpc->lock);

	mutex_unlock(&gpc->refresh_lock);

	if (unmap_old)
		gpc_unmap(old_pfn, old_khva);

	return ret;
}

int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len)
{
	return __kvm_gpc_refresh(gpc, gpc->gpa, len);
}
EXPORT_SYMBOL_GPL(kvm_gpc_refresh);

void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm,
		  struct kvm_vcpu *vcpu, enum pfn_cache_usage usage)
{
	WARN_ON_ONCE(!usage || (usage & KVM_GUEST_AND_HOST_USE_PFN) != usage);
	WARN_ON_ONCE((usage & KVM_GUEST_USES_PFN) && !vcpu);

	rwlock_init(&gpc->lock);
	mutex_init(&gpc->refresh_lock);

	gpc->kvm = kvm;
	gpc->vcpu = vcpu;
	gpc->usage = usage;
	gpc->pfn = KVM_PFN_ERR_FAULT;
	gpc->uhva = KVM_HVA_ERR_BAD;
}
EXPORT_SYMBOL_GPL(kvm_gpc_init);

int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len)
{
	struct kvm *kvm = gpc->kvm;

	if (!gpc->active) {
		if (KVM_BUG_ON(gpc->valid, kvm))
			return -EIO;

		spin_lock(&kvm->gpc_lock);
		list_add(&gpc->list, &kvm->gpc_list);
		spin_unlock(&kvm->gpc_lock);

		/*
		 * Activate the cache after adding it to the list, a concurrent
		 * refresh must not establish a mapping until the cache is
		 * reachable by mmu_notifier events.
		 */
		write_lock_irq(&gpc->lock);
		gpc->active = true;
		write_unlock_irq(&gpc->lock);
	}
	return __kvm_gpc_refresh(gpc, gpa, len);
}
EXPORT_SYMBOL_GPL(kvm_gpc_activate);

void kvm_gpc_deactivate(struct gfn_to_pfn_cache *gpc)
{
	struct kvm *kvm = gpc->kvm;
	kvm_pfn_t old_pfn;
	void *old_khva;

	if (gpc->active) {
		/*
		 * Deactivate the cache before removing it from the list, KVM
		 * must stall mmu_notifier events until all users go away, i.e.
		 * until gpc->lock is dropped and refresh is guaranteed to fail.
		 */
		write_lock_irq(&gpc->lock);
		gpc->active = false;
		gpc->valid = false;

		/*
		 * Leave the GPA => uHVA cache intact, it's protected by the
		 * memslot generation.  The PFN lookup needs to be redone every
		 * time as mmu_notifier protection is lost when the cache is
		 * removed from the VM's gpc_list.
		 */
		old_khva = gpc->khva - offset_in_page(gpc->khva);
		gpc->khva = NULL;

		old_pfn = gpc->pfn;
		gpc->pfn = KVM_PFN_ERR_FAULT;
		write_unlock_irq(&gpc->lock);

		spin_lock(&kvm->gpc_lock);
		list_del(&gpc->list);
		spin_unlock(&kvm->gpc_lock);

		gpc_unmap(old_pfn, old_khva);
	}
}
EXPORT_SYMBOL_GPL(kvm_gpc_deactivate);