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
|
/*
* mmu_audit.c:
*
* Audit code for KVM MMU
*
* Copyright (C) 2006 Qumranet, Inc.
* Copyright 2010 Red Hat, Inc. and/or its affiliates.
*
* Authors:
* Yaniv Kamay <yaniv@qumranet.com>
* Avi Kivity <avi@qumranet.com>
* Marcelo Tosatti <mtosatti@redhat.com>
* Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
*/
#include <linux/ratelimit.h>
char const *audit_point_name[] = {
"pre page fault",
"post page fault",
"pre pte write",
"post pte write",
"pre sync",
"post sync"
};
#define audit_printk(kvm, fmt, args...) \
printk(KERN_ERR "audit: (%s) error: " \
fmt, audit_point_name[kvm->arch.audit_point], ##args)
typedef void (*inspect_spte_fn) (struct kvm_vcpu *vcpu, u64 *sptep, int level);
static void __mmu_spte_walk(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
inspect_spte_fn fn, int level)
{
int i;
for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
u64 *ent = sp->spt;
fn(vcpu, ent + i, level);
if (is_shadow_present_pte(ent[i]) &&
!is_last_spte(ent[i], level)) {
struct kvm_mmu_page *child;
child = page_header(ent[i] & PT64_BASE_ADDR_MASK);
__mmu_spte_walk(vcpu, child, fn, level - 1);
}
}
}
static void mmu_spte_walk(struct kvm_vcpu *vcpu, inspect_spte_fn fn)
{
int i;
struct kvm_mmu_page *sp;
if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
return;
if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) {
hpa_t root = vcpu->arch.mmu.root_hpa;
sp = page_header(root);
__mmu_spte_walk(vcpu, sp, fn, PT64_ROOT_LEVEL);
return;
}
for (i = 0; i < 4; ++i) {
hpa_t root = vcpu->arch.mmu.pae_root[i];
if (root && VALID_PAGE(root)) {
root &= PT64_BASE_ADDR_MASK;
sp = page_header(root);
__mmu_spte_walk(vcpu, sp, fn, 2);
}
}
return;
}
typedef void (*sp_handler) (struct kvm *kvm, struct kvm_mmu_page *sp);
static void walk_all_active_sps(struct kvm *kvm, sp_handler fn)
{
struct kvm_mmu_page *sp;
list_for_each_entry(sp, &kvm->arch.active_mmu_pages, link)
fn(kvm, sp);
}
static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level)
{
struct kvm_mmu_page *sp;
gfn_t gfn;
pfn_t pfn;
hpa_t hpa;
sp = page_header(__pa(sptep));
if (sp->unsync) {
if (level != PT_PAGE_TABLE_LEVEL) {
audit_printk(vcpu->kvm, "unsync sp: %p "
"level = %d\n", sp, level);
return;
}
}
if (!is_shadow_present_pte(*sptep) || !is_last_spte(*sptep, level))
return;
gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt);
pfn = gfn_to_pfn_atomic(vcpu->kvm, gfn);
if (is_error_pfn(pfn)) {
kvm_release_pfn_clean(pfn);
return;
}
hpa = pfn << PAGE_SHIFT;
if ((*sptep & PT64_BASE_ADDR_MASK) != hpa)
audit_printk(vcpu->kvm, "levels %d pfn %llx hpa %llx "
"ent %llxn", vcpu->arch.mmu.root_level, pfn,
hpa, *sptep);
}
static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep)
{
static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10);
unsigned long *rmapp;
struct kvm_mmu_page *rev_sp;
gfn_t gfn;
rev_sp = page_header(__pa(sptep));
gfn = kvm_mmu_page_get_gfn(rev_sp, sptep - rev_sp->spt);
if (!gfn_to_memslot(kvm, gfn)) {
if (!__ratelimit(&ratelimit_state))
return;
audit_printk(kvm, "no memslot for gfn %llx\n", gfn);
audit_printk(kvm, "index %ld of sp (gfn=%llx)\n",
(long int)(sptep - rev_sp->spt), rev_sp->gfn);
dump_stack();
return;
}
rmapp = gfn_to_rmap(kvm, gfn, rev_sp->role.level);
if (!*rmapp) {
if (!__ratelimit(&ratelimit_state))
return;
audit_printk(kvm, "no rmap for writable spte %llx\n",
*sptep);
dump_stack();
}
}
static void audit_sptes_have_rmaps(struct kvm_vcpu *vcpu, u64 *sptep, int level)
{
if (is_shadow_present_pte(*sptep) && is_last_spte(*sptep, level))
inspect_spte_has_rmap(vcpu->kvm, sptep);
}
static void audit_spte_after_sync(struct kvm_vcpu *vcpu, u64 *sptep, int level)
{
struct kvm_mmu_page *sp = page_header(__pa(sptep));
if (vcpu->kvm->arch.audit_point == AUDIT_POST_SYNC && sp->unsync)
audit_printk(vcpu->kvm, "meet unsync sp(%p) after sync "
"root.\n", sp);
}
static void check_mappings_rmap(struct kvm *kvm, struct kvm_mmu_page *sp)
{
int i;
if (sp->role.level != PT_PAGE_TABLE_LEVEL)
return;
for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
if (!is_rmap_spte(sp->spt[i]))
continue;
inspect_spte_has_rmap(kvm, sp->spt + i);
}
}
static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp)
{
struct kvm_memory_slot *slot;
unsigned long *rmapp;
u64 *sptep;
struct rmap_iterator iter;
if (sp->role.direct || sp->unsync || sp->role.invalid)
return;
slot = gfn_to_memslot(kvm, sp->gfn);
rmapp = &slot->rmap[sp->gfn - slot->base_gfn];
for (sptep = rmap_get_first(*rmapp, &iter); sptep;
sptep = rmap_get_next(&iter)) {
if (is_writable_pte(*sptep))
audit_printk(kvm, "shadow page has writable "
"mappings: gfn %llx role %x\n",
sp->gfn, sp->role.word);
}
}
static void audit_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
{
check_mappings_rmap(kvm, sp);
audit_write_protection(kvm, sp);
}
static void audit_all_active_sps(struct kvm *kvm)
{
walk_all_active_sps(kvm, audit_sp);
}
static void audit_spte(struct kvm_vcpu *vcpu, u64 *sptep, int level)
{
audit_sptes_have_rmaps(vcpu, sptep, level);
audit_mappings(vcpu, sptep, level);
audit_spte_after_sync(vcpu, sptep, level);
}
static void audit_vcpu_spte(struct kvm_vcpu *vcpu)
{
mmu_spte_walk(vcpu, audit_spte);
}
static bool mmu_audit;
static struct static_key mmu_audit_key;
static void __kvm_mmu_audit(struct kvm_vcpu *vcpu, int point)
{
static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10);
if (!__ratelimit(&ratelimit_state))
return;
vcpu->kvm->arch.audit_point = point;
audit_all_active_sps(vcpu->kvm);
audit_vcpu_spte(vcpu);
}
static inline void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point)
{
if (static_key_false((&mmu_audit_key)))
__kvm_mmu_audit(vcpu, point);
}
static void mmu_audit_enable(void)
{
if (mmu_audit)
return;
static_key_slow_inc(&mmu_audit_key);
mmu_audit = true;
}
static void mmu_audit_disable(void)
{
if (!mmu_audit)
return;
static_key_slow_dec(&mmu_audit_key);
|