summaryrefslogtreecommitdiff
path: root/virt/kvm/dirty_ring.c
blob: 88f4683198ea757c1ce43781a08b5b59fac345cf (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
/* SPDX-License-Identifier: GPL-2.0-only */
/*
 * KVM dirty ring implementation
 *
 * Copyright 2019 Red Hat, Inc.
 */
#include <linux/kvm_host.h>
#include <linux/kvm.h>
#include <linux/vmalloc.h>
#include <linux/kvm_dirty_ring.h>
#include <trace/events/kvm.h>
#include "mmu_lock.h"

int __weak kvm_cpu_dirty_log_size(void)
{
	return 0;
}

u32 kvm_dirty_ring_get_rsvd_entries(void)
{
	return KVM_DIRTY_RING_RSVD_ENTRIES + kvm_cpu_dirty_log_size();
}

static u32 kvm_dirty_ring_used(struct kvm_dirty_ring *ring)
{
	return READ_ONCE(ring->dirty_index) - READ_ONCE(ring->reset_index);
}

bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring)
{
	return kvm_dirty_ring_used(ring) >= ring->soft_limit;
}

static bool kvm_dirty_ring_full(struct kvm_dirty_ring *ring)
{
	return kvm_dirty_ring_used(ring) >= ring->size;
}

struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm)
{
	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();

	WARN_ON_ONCE(vcpu->kvm != kvm);

	return &vcpu->dirty_ring;
}

static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask)
{
	struct kvm_memory_slot *memslot;
	int as_id, id;

	as_id = slot >> 16;
	id = (u16)slot;

	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
		return;

	memslot = id_to_memslot(__kvm_memslots(kvm, as_id), id);

	if (!memslot || (offset + __fls(mask)) >= memslot->npages)
		return;

	KVM_MMU_LOCK(kvm);
	kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask);
	KVM_MMU_UNLOCK(kvm);
}

int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size)
{
	ring->dirty_gfns = vzalloc(size);
	if (!ring->dirty_gfns)
		return -ENOMEM;

	ring->size = size / sizeof(struct kvm_dirty_gfn);
	ring->soft_limit = ring->size - kvm_dirty_ring_get_rsvd_entries();
	ring->dirty_index = 0;
	ring->reset_index = 0;
	ring->index = index;

	return 0;
}

static inline void kvm_dirty_gfn_set_invalid(struct kvm_dirty_gfn *gfn)
{
	gfn->flags = 0;
}

static inline void kvm_dirty_gfn_set_dirtied(struct kvm_dirty_gfn *gfn)
{
	gfn->flags = KVM_DIRTY_GFN_F_DIRTY;
}

static inline bool kvm_dirty_gfn_harvested(struct kvm_dirty_gfn *gfn)
{
	return gfn->flags & KVM_DIRTY_GFN_F_RESET;
}

int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring)
{
	u32 cur_slot, next_slot;
	u64 cur_offset, next_offset;
	unsigned long mask;
	int count = 0;
	struct kvm_dirty_gfn *entry;
	bool first_round = true;

	/* This is only needed to make compilers happy */
	cur_slot = cur_offset = mask = 0;

	while (true) {
		entry = &ring->dirty_gfns[ring->reset_index & (ring->size - 1)];

		if (!kvm_dirty_gfn_harvested(entry))
			break;

		next_slot = READ_ONCE(entry->slot);
		next_offset = READ_ONCE(entry->offset);

		/* Update the flags to reflect that this GFN is reset */
		kvm_dirty_gfn_set_invalid(entry);

		ring->reset_index++;
		count++;
		/*
		 * Try to coalesce the reset operations when the guest is
		 * scanning pages in the same slot.
		 */
		if (!first_round && next_slot == cur_slot) {
			s64 delta = next_offset - cur_offset;

			if (delta >= 0 && delta < BITS_PER_LONG) {
				mask |= 1ull << delta;
				continue;
			}

			/* Backwards visit, careful about overflows!  */
			if (delta > -BITS_PER_LONG && delta < 0 &&
			    (mask << -delta >> -delta) == mask) {
				cur_offset = next_offset;
				mask = (mask << -delta) | 1;
				continue;
			}
		}
		kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask);
		cur_slot = next_slot;
		cur_offset = next_offset;
		mask = 1;
		first_round = false;
	}

	kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask);

	trace_kvm_dirty_ring_reset(ring);

	return count;
}

void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset)
{
	struct kvm_dirty_gfn *entry;

	/* It should never get full */
	WARN_ON_ONCE(kvm_dirty_ring_full(ring));

	entry = &ring->dirty_gfns[ring->dirty_index & (ring->size - 1)];

	entry->slot = slot;
	entry->offset = offset;
	/*
	 * Make sure the data is filled in before we publish this to
	 * the userspace program.  There's no paired kernel-side reader.
	 */
	smp_wmb();
	kvm_dirty_gfn_set_dirtied(entry);
	ring->dirty_index++;
	trace_kvm_dirty_ring_push(ring, slot, offset);
}

struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset)
{
	return vmalloc_to_page((void *)ring->dirty_gfns + offset * PAGE_SIZE);
}

void kvm_dirty_ring_free(struct kvm_dirty_ring *ring)
{
	vfree(ring->dirty_gfns);
	ring->dirty_gfns = NULL;
}