summaryrefslogtreecommitdiffstats
path: root/virt/kvm/async_pf.c
blob: 99a63bad0306c5699c8282b175f203bdc7bfba0a (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * kvm asynchronous fault support
 *
 * Copyright 2010 Red Hat, Inc.
 *
 * Author:
 *      Gleb Natapov <gleb@redhat.com>
 */

#include <linux/kvm_host.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/mmu_context.h>
#include <linux/sched/mm.h>

#include "async_pf.h"
#include <trace/events/kvm.h>

static struct kmem_cache *async_pf_cache;

int kvm_async_pf_init(void)
{
	async_pf_cache = KMEM_CACHE(kvm_async_pf, 0);

	if (!async_pf_cache)
		return -ENOMEM;

	return 0;
}

void kvm_async_pf_deinit(void)
{
	kmem_cache_destroy(async_pf_cache);
	async_pf_cache = NULL;
}

void kvm_async_pf_vcpu_init(struct kvm_vcpu *vcpu)
{
	INIT_LIST_HEAD(&vcpu->async_pf.done);
	INIT_LIST_HEAD(&vcpu->async_pf.queue);
	spin_lock_init(&vcpu->async_pf.lock);
}

static void async_pf_execute(struct work_struct *work)
{
	struct kvm_async_pf *apf =
		container_of(work, struct kvm_async_pf, work);
	struct kvm_vcpu *vcpu = apf->vcpu;
	struct mm_struct *mm = vcpu->kvm->mm;
	unsigned long addr = apf->addr;
	gpa_t cr2_or_gpa = apf->cr2_or_gpa;
	int locked = 1;
	bool first;

	might_sleep();

	/*
	 * Attempt to pin the VM's host address space, and simply skip gup() if
	 * acquiring a pin fail, i.e. if the process is exiting.  Note, KVM
	 * holds a reference to its associated mm_struct until the very end of
	 * kvm_destroy_vm(), i.e. the struct itself won't be freed before this
	 * work item is fully processed.
	 */
	if (mmget_not_zero(mm)) {
		mmap_read_lock(mm);
		get_user_pages_remote(mm, addr, 1, FOLL_WRITE, NULL, &locked);
		if (locked)
			mmap_read_unlock(mm);
		mmput(mm);
	}

	/*
	 * Notify and kick the vCPU even if faulting in the page failed, e.g.
	 * so that the vCPU can retry the fault synchronously.
	 */
	if (IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC))
		kvm_arch_async_page_present(vcpu, apf);

	spin_lock(&vcpu->async_pf.lock);
	first = list_empty(&vcpu->async_pf.done);
	list_add_tail(&apf->link, &vcpu->async_pf.done);
	apf->vcpu = NULL;
	spin_unlock(&vcpu->async_pf.lock);

	/*
	 * The apf struct may be freed by kvm_check_async_pf_completion() as
	 * soon as the lock is dropped.  Nullify it to prevent improper usage.
	 */
	apf = NULL;

	if (!IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC) && first)
		kvm_arch_async_page_present_queued(vcpu);

	trace_kvm_async_pf_completed(addr, cr2_or_gpa);

	__kvm_vcpu_wake_up(vcpu);
}

static void kvm_flush_and_free_async_pf_work(struct kvm_async_pf *work)
{
	/*
	 * The async #PF is "done", but KVM must wait for the work item itself,
	 * i.e. async_pf_execute(), to run to completion.  If KVM is a module,
	 * KVM must ensure *no* code owned by the KVM (the module) can be run
	 * after the last call to module_put().  Note, flushing the work item
	 * is always required when the item is taken off the completion queue.
	 * E.g. even if the vCPU handles the item in the "normal" path, the VM
	 * could be terminated before async_pf_execute() completes.
	 *
	 * Wake all events skip the queue and go straight done, i.e. don't
	 * need to be flushed (but sanity check that the work wasn't queued).
	 */
	if (work->wakeup_all)
		WARN_ON_ONCE(work->work.func);
	else
		flush_work(&work->work);
	kmem_cache_free(async_pf_cache, work);
}

void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
{
	spin_lock(&vcpu->async_pf.lock);

	/* cancel outstanding work queue item */
	while (!list_empty(&vcpu->async_pf.queue)) {
		struct kvm_async_pf *work =
			list_first_entry(&vcpu->async_pf.queue,
					 typeof(*work), queue);
		list_del(&work->queue);

		/*
		 * We know it's present in vcpu->async_pf.done, do
		 * nothing here.
		 */
		if (!work->vcpu)
			continue;

		spin_unlock(&vcpu->async_pf.lock);
#ifdef CONFIG_KVM_ASYNC_PF_SYNC
		flush_work(&work->work);
#else
		if (cancel_work_sync(&work->work))
			kmem_cache_free(async_pf_cache, work);
#endif
		spin_lock(&vcpu->async_pf.lock);
	}

	while (!list_empty(&vcpu->async_pf.done)) {
		struct kvm_async_pf *work =
			list_first_entry(&vcpu->async_pf.done,
					 typeof(*work), link);
		list_del(&work->link);

		spin_unlock(&vcpu->async_pf.lock);
		kvm_flush_and_free_async_pf_work(work);
		spin_lock(&vcpu->async_pf.lock);
	}
	spin_unlock(&vcpu->async_pf.lock);

	vcpu->async_pf.queued = 0;
}

void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
{
	struct kvm_async_pf *work;

	while (!list_empty_careful(&vcpu->async_pf.done) &&
	      kvm_arch_can_dequeue_async_page_present(vcpu)) {
		spin_lock(&vcpu->async_pf.lock);
		work = list_first_entry(&vcpu->async_pf.done, typeof(*work),
					      link);
		list_del(&work->link);
		spin_unlock(&vcpu->async_pf.lock);

		kvm_arch_async_page_ready(vcpu, work);
		if (!IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC))
			kvm_arch_async_page_present(vcpu, work);

		list_del(&work->queue);
		vcpu->async_pf.queued--;
		kvm_flush_and_free_async_pf_work(work);
	}
}

/*
 * Try to schedule a job to handle page fault asynchronously. Returns 'true' on
 * success, 'false' on failure (page fault has to be handled synchronously).
 */
bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
			unsigned long hva, struct kvm_arch_async_pf *arch)
{
	struct kvm_async_pf *work;

	if (vcpu->async_pf.queued >= ASYNC_PF_PER_VCPU)
		return false;

	/* Arch specific code should not do async PF in this case */
	if (unlikely(kvm_is_error_hva(hva)))
		return false;

	/*
	 * do alloc nowait since if we are going to sleep anyway we
	 * may as well sleep faulting in page
	 */
	work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT | __GFP_NOWARN);
	if (!work)
		return false;

	work->wakeup_all = false;
	work->vcpu = vcpu;
	work->cr2_or_gpa = cr2_or_gpa;
	work->addr = hva;
	work->arch = *arch;

	INIT_WORK(&work->work, async_pf_execute);

	list_add_tail(&work->queue, &vcpu->async_pf.queue);
	vcpu->async_pf.queued++;
	work->notpresent_injected = kvm_arch_async_page_not_present(vcpu, work);

	schedule_work(&work->work);

	return true;
}

int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)
{
	struct kvm_async_pf *work;
	bool first;

	if (!list_empty_careful(&vcpu->async_pf.done))
		return 0;

	work = kmem_cache_zalloc(async_pf_cache, GFP_ATOMIC);
	if (!work)
		return -ENOMEM;

	work->wakeup_all = true;
	INIT_LIST_HEAD(&work->queue); /* for list_del to work */

	spin_lock(&vcpu->async_pf.lock);
	first = list_empty(&vcpu->async_pf.done);
	list_add_tail(&work->link, &vcpu->async_pf.done);
	spin_unlock(&vcpu->async_pf.lock);

	if (!IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC) && first)
		kvm_arch_async_page_present_queued(vcpu);

	vcpu->async_pf.queued++;
	return 0;
}