summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm/mmu/page_track.c
blob: 269f11f92fd052d5dcf2f6ed53d6f55bad21eecd (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Support KVM gust page tracking
 *
 * This feature allows us to track page access in guest. Currently, only
 * write access is tracked.
 *
 * Copyright(C) 2015 Intel Corporation.
 *
 * Author:
 *   Xiao Guangrong <guangrong.xiao@linux.intel.com>
 */

#include <linux/kvm_host.h>
#include <linux/rculist.h>

#include <asm/kvm_page_track.h>

#include "mmu.h"
#include "mmu_internal.h"

void kvm_page_track_free_memslot(struct kvm_memory_slot *slot)
{
	int i;

	for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) {
		kvfree(slot->arch.gfn_track[i]);
		slot->arch.gfn_track[i] = NULL;
	}
}

int kvm_page_track_create_memslot(struct kvm_memory_slot *slot,
				  unsigned long npages)
{
	int  i;

	for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) {
		slot->arch.gfn_track[i] =
			kvcalloc(npages, sizeof(*slot->arch.gfn_track[i]),
				 GFP_KERNEL_ACCOUNT);
		if (!slot->arch.gfn_track[i])
			goto track_free;
	}

	return 0;

track_free:
	kvm_page_track_free_memslot(slot);
	return -ENOMEM;
}

static inline bool page_track_mode_is_valid(enum kvm_page_track_mode mode)
{
	if (mode < 0 || mode >= KVM_PAGE_TRACK_MAX)
		return false;

	return true;
}

static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn,
			     enum kvm_page_track_mode mode, short count)
{
	int index, val;

	index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K);

	val = slot->arch.gfn_track[mode][index];

	if (WARN_ON(val + count < 0 || val + count > USHRT_MAX))
		return;

	slot->arch.gfn_track[mode][index] += count;
}

/*
 * add guest page to the tracking pool so that corresponding access on that
 * page will be intercepted.
 *
 * It should be called under the protection both of mmu-lock and kvm->srcu
 * or kvm->slots_lock.
 *
 * @kvm: the guest instance we are interested in.
 * @slot: the @gfn belongs to.
 * @gfn: the guest page.
 * @mode: tracking mode, currently only write track is supported.
 */
void kvm_slot_page_track_add_page(struct kvm *kvm,
				  struct kvm_memory_slot *slot, gfn_t gfn,
				  enum kvm_page_track_mode mode)
{

	if (WARN_ON(!page_track_mode_is_valid(mode)))
		return;

	update_gfn_track(slot, gfn, mode, 1);

	/*
	 * new track stops large page mapping for the
	 * tracked page.
	 */
	kvm_mmu_gfn_disallow_lpage(slot, gfn);

	if (mode == KVM_PAGE_TRACK_WRITE)
		if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K))
			kvm_flush_remote_tlbs(kvm);
}
EXPORT_SYMBOL_GPL(kvm_slot_page_track_add_page);

/*
 * remove the guest page from the tracking pool which stops the interception
 * of corresponding access on that page. It is the opposed operation of
 * kvm_slot_page_track_add_page().
 *
 * It should be called under the protection both of mmu-lock and kvm->srcu
 * or kvm->slots_lock.
 *
 * @kvm: the guest instance we are interested in.
 * @slot: the @gfn belongs to.
 * @gfn: the guest page.
 * @mode: tracking mode, currently only write track is supported.
 */
void kvm_slot_page_track_remove_page(struct kvm *kvm,
				     struct kvm_memory_slot *slot, gfn_t gfn,
				     enum kvm_page_track_mode mode)
{
	if (WARN_ON(!page_track_mode_is_valid(mode)))
		return;

	update_gfn_track(slot, gfn, mode, -1);

	/*
	 * allow large page mapping for the tracked page
	 * after the tracker is gone.
	 */
	kvm_mmu_gfn_allow_lpage(slot, gfn);
}
EXPORT_SYMBOL_GPL(kvm_slot_page_track_remove_page);

/*
 * check if the corresponding access on the specified guest page is tracked.
 */
bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn,
			      enum kvm_page_track_mode mode)
{
	struct kvm_memory_slot *slot;
	int index;

	if (WARN_ON(!page_track_mode_is_valid(mode)))
		return false;

	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
	if (!slot)
		return false;

	index = gfn_to_index(gfn, slot->base_gfn, PG_LEVEL_4K);
	return !!READ_ONCE(slot->arch.gfn_track[mode][index]);
}

void kvm_page_track_cleanup(struct kvm *kvm)
{
	struct kvm_page_track_notifier_head *head;

	head = &kvm->arch.track_notifier_head;
	cleanup_srcu_struct(&head->track_srcu);
}

void kvm_page_track_init(struct kvm *kvm)
{
	struct kvm_page_track_notifier_head *head;

	head = &kvm->arch.track_notifier_head;
	init_srcu_struct(&head->track_srcu);
	INIT_HLIST_HEAD(&head->track_notifier_list);
}

/*
 * register the notifier so that event interception for the tracked guest
 * pages can be received.
 */
void
kvm_page_track_register_notifier(struct kvm *kvm,
				 struct kvm_page_track_notifier_node *n)
{
	struct kvm_page_track_notifier_head *head;

	head = &kvm->arch.track_notifier_head;

	write_lock(&kvm->mmu_lock);
	hlist_add_head_rcu(&n->node, &head->track_notifier_list);
	write_unlock(&kvm->mmu_lock);
}
EXPORT_SYMBOL_GPL(kvm_page_track_register_notifier);

/*
 * stop receiving the event interception. It is the opposed operation of
 * kvm_page_track_register_notifier().
 */
void
kvm_page_track_unregister_notifier(struct kvm *kvm,
				   struct kvm_page_track_notifier_node *n)
{
	struct kvm_page_track_notifier_head *head;

	head = &kvm->arch.track_notifier_head;

	write_lock(&kvm->mmu_lock);
	hlist_del_rcu(&n->node);
	write_unlock(&kvm->mmu_lock);
	synchronize_srcu(&head->track_srcu);
}
EXPORT_SYMBOL_GPL(kvm_page_track_unregister_notifier);

/*
 * Notify the node that write access is intercepted and write emulation is
 * finished at this time.
 *
 * The node should figure out if the written page is the one that node is
 * interested in by itself.
 */
void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
			  int bytes)
{
	struct kvm_page_track_notifier_head *head;
	struct kvm_page_track_notifier_node *n;
	int idx;

	head = &vcpu->kvm->arch.track_notifier_head;

	if (hlist_empty(&head->track_notifier_list))
		return;

	idx = srcu_read_lock(&head->track_srcu);
	hlist_for_each_entry_srcu(n, &head->track_notifier_list, node,
				srcu_read_lock_held(&head->track_srcu))
		if (n->track_write)
			n->track_write(vcpu, gpa, new, bytes, n);
	srcu_read_unlock(&head->track_srcu, idx);
}

/*
 * Notify the node that memory slot is being removed or moved so that it can
 * drop write-protection for the pages in the memory slot.
 *
 * The node should figure out it has any write-protected pages in this slot
 * by itself.
 */
void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
{
	struct kvm_page_track_notifier_head *head;
	struct kvm_page_track_notifier_node *n;
	int idx;

	head = &kvm->arch.track_notifier_head;

	if (hlist_empty(&head->track_notifier_list))
		return;

	idx = srcu_read_lock(&head->track_srcu);
	hlist_for_each_entry_srcu(n, &head->track_notifier_list, node,
				srcu_read_lock_held(&head->track_srcu))
		if (n->track_flush_slot)
			n->track_flush_slot(kvm, slot, n);
	srcu_read_unlock(&head->track_srcu, idx);
}