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
|
From: Andrew Cooper <andrew.cooper3@citrix.com>
Subject: x86/pv: Fix ABAC cmpxchg() race in _get_page_type()
_get_page_type() suffers from a race condition where it incorrectly assumes
that because 'x' was read and a subsequent a cmpxchg() succeeds, the type
cannot have changed in-between. Consider:
CPU A:
1. Creates an L2e referencing pg
`-> _get_page_type(pg, PGT_l1_page_table), sees count 0, type PGT_writable_page
2. Issues flush_tlb_mask()
CPU B:
3. Creates a writeable mapping of pg
`-> _get_page_type(pg, PGT_writable_page), count increases to 1
4. Writes into new mapping, creating a TLB entry for pg
5. Removes the writeable mapping of pg
`-> _put_page_type(pg), count goes back down to 0
CPU A:
7. Issues cmpxchg(), setting count 1, type PGT_l1_page_table
CPU B now has a writeable mapping to pg, which Xen believes is a pagetable and
suitably protected (i.e. read-only). The TLB flush in step 2 must be deferred
until after the guest is prohibited from creating new writeable mappings,
which is after step 7.
Defer all safety actions until after the cmpxchg() has successfully taken the
intended typeref, because that is what prevents concurrent users from using
the old type.
Also remove the early validation for writeable and shared pages. This removes
race conditions where one half of a parallel mapping attempt can return
successfully before:
* The IOMMU pagetables are in sync with the new page type
* Writeable mappings to shared pages have been torn down
This is part of XSA-401 / CVE-2022-26362.
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: George Dunlap <george.dunlap@citrix.com>
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index ddd32f88c798..1693b580b152 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -2962,56 +2962,12 @@ static int _get_page_type(struct page_info *page, unsigned long type,
* Type changes are permitted when the typeref is 0. If the type
* actually changes, the page needs re-validating.
*/
- struct domain *d = page_get_owner(page);
-
- if ( d && shadow_mode_enabled(d) )
- shadow_prepare_page_type_change(d, page, type);
ASSERT(!(x & PGT_pae_xen_l2));
if ( (x & PGT_type_mask) != type )
{
- /*
- * On type change we check to flush stale TLB entries. It is
- * vital that no other CPUs are left with writeable mappings
- * to a frame which is intending to become pgtable/segdesc.
- */
- cpumask_t *mask = this_cpu(scratch_cpumask);
-
- BUG_ON(in_irq());
- cpumask_copy(mask, d->dirty_cpumask);
-
- /* Don't flush if the timestamp is old enough */
- tlbflush_filter(mask, page->tlbflush_timestamp);
-
- if ( unlikely(!cpumask_empty(mask)) &&
- /* Shadow mode: track only writable pages. */
- (!shadow_mode_enabled(d) ||
- ((nx & PGT_type_mask) == PGT_writable_page)) )
- {
- perfc_incr(need_flush_tlb_flush);
- /*
- * If page was a page table make sure the flush is
- * performed using an IPI in order to avoid changing the
- * type of a page table page under the feet of
- * spurious_page_fault().
- */
- flush_mask(mask,
- (x & PGT_type_mask) &&
- (x & PGT_type_mask) <= PGT_root_page_table
- ? FLUSH_TLB | FLUSH_FORCE_IPI
- : FLUSH_TLB);
- }
-
- /* We lose existing type and validity. */
nx &= ~(PGT_type_mask | PGT_validated);
nx |= type;
-
- /*
- * No special validation needed for writable pages.
- * Page tables and GDT/LDT need to be scanned for validity.
- */
- if ( type == PGT_writable_page || type == PGT_shared_page )
- nx |= PGT_validated;
}
}
else if ( unlikely((x & (PGT_type_mask|PGT_pae_xen_l2)) != type) )
@@ -3092,6 +3048,56 @@ static int _get_page_type(struct page_info *page, unsigned long type,
return -EINTR;
}
+ /*
+ * One typeref has been taken and is now globally visible.
+ *
+ * The page is either in the "validate locked" state (PGT_[type] | 1) or
+ * fully validated (PGT_[type] | PGT_validated | >0).
+ */
+
+ if ( unlikely((x & PGT_count_mask) == 0) )
+ {
+ struct domain *d = page_get_owner(page);
+
+ if ( d && shadow_mode_enabled(d) )
+ shadow_prepare_page_type_change(d, page, type);
+
+ if ( (x & PGT_type_mask) != type )
+ {
+ /*
+ * On type change we check to flush stale TLB entries. It is
+ * vital that no other CPUs are left with writeable mappings
+ * to a frame which is intending to become pgtable/segdesc.
+ */
+ cpumask_t *mask = this_cpu(scratch_cpumask);
+
+ BUG_ON(in_irq());
+ cpumask_copy(mask, d->dirty_cpumask);
+
+ /* Don't flush if the timestamp is old enough */
+ tlbflush_filter(mask, page->tlbflush_timestamp);
+
+ if ( unlikely(!cpumask_empty(mask)) &&
+ /* Shadow mode: track only writable pages. */
+ (!shadow_mode_enabled(d) ||
+ ((nx & PGT_type_mask) == PGT_writable_page)) )
+ {
+ perfc_incr(need_flush_tlb_flush);
+ /*
+ * If page was a page table make sure the flush is
+ * performed using an IPI in order to avoid changing the
+ * type of a page table page under the feet of
+ * spurious_page_fault().
+ */
+ flush_mask(mask,
+ (x & PGT_type_mask) &&
+ (x & PGT_type_mask) <= PGT_root_page_table
+ ? FLUSH_TLB | FLUSH_FORCE_IPI
+ : FLUSH_TLB);
+ }
+ }
+ }
+
if ( unlikely(((x & PGT_type_mask) == PGT_writable_page) !=
(type == PGT_writable_page)) )
{
@@ -3120,13 +3126,25 @@ static int _get_page_type(struct page_info *page, unsigned long type,
if ( unlikely(!(nx & PGT_validated)) )
{
- if ( !(x & PGT_partial) )
+ /*
+ * No special validation needed for writable or shared pages. Page
+ * tables and GDT/LDT need to have their contents audited.
+ *
+ * per validate_page(), non-atomic updates are fine here.
+ */
+ if ( type == PGT_writable_page || type == PGT_shared_page )
+ page->u.inuse.type_info |= PGT_validated;
+ else
{
- page->nr_validated_ptes = 0;
- page->partial_flags = 0;
- page->linear_pt_count = 0;
+ if ( !(x & PGT_partial) )
+ {
+ page->nr_validated_ptes = 0;
+ page->partial_flags = 0;
+ page->linear_pt_count = 0;
+ }
+
+ rc = validate_page(page, type, preemptible);
}
- rc = validate_page(page, type, preemptible);
}
out:
|
