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
|
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_X86_PGTABLE_3LEVEL_H
#define _ASM_X86_PGTABLE_3LEVEL_H
/*
* Intel Physical Address Extension (PAE) Mode - three-level page
* tables on PPro+ CPUs.
*
* Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
*/
#define pte_ERROR(e) \
pr_err("%s:%d: bad pte %p(%08lx%08lx)\n", \
__FILE__, __LINE__, &(e), (e).pte_high, (e).pte_low)
#define pmd_ERROR(e) \
pr_err("%s:%d: bad pmd %p(%016Lx)\n", \
__FILE__, __LINE__, &(e), pmd_val(e))
#define pgd_ERROR(e) \
pr_err("%s:%d: bad pgd %p(%016Lx)\n", \
__FILE__, __LINE__, &(e), pgd_val(e))
/* Rules for using set_pte: the pte being assigned *must* be
* either not present or in a state where the hardware will
* not attempt to update the pte. In places where this is
* not possible, use pte_get_and_clear to obtain the old pte
* value and then use set_pte to update it. -ben
*/
static inline void native_set_pte(pte_t *ptep, pte_t pte)
{
ptep->pte_high = pte.pte_high;
smp_wmb();
ptep->pte_low = pte.pte_low;
}
static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
{
set_64bit((unsigned long long *)(ptep), native_pte_val(pte));
}
static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
{
set_64bit((unsigned long long *)(pmdp), native_pmd_val(pmd));
}
static inline void native_set_pud(pud_t *pudp, pud_t pud)
{
#ifdef CONFIG_PAGE_TABLE_ISOLATION
pud.p4d.pgd = pti_set_user_pgtbl(&pudp->p4d.pgd, pud.p4d.pgd);
#endif
set_64bit((unsigned long long *)(pudp), native_pud_val(pud));
}
/*
* For PTEs and PDEs, we must clear the P-bit first when clearing a page table
* entry, so clear the bottom half first and enforce ordering with a compiler
* barrier.
*/
static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
ptep->pte_low = 0;
smp_wmb();
ptep->pte_high = 0;
}
static inline void native_pmd_clear(pmd_t *pmdp)
{
pmdp->pmd_low = 0;
smp_wmb();
pmdp->pmd_high = 0;
}
static inline void native_pud_clear(pud_t *pudp)
{
}
static inline void pud_clear(pud_t *pudp)
{
set_pud(pudp, __pud(0));
/*
* According to Intel App note "TLBs, Paging-Structure Caches,
* and Their Invalidation", April 2007, document 317080-001,
* section 8.1: in PAE mode we explicitly have to flush the
* TLB via cr3 if the top-level pgd is changed...
*
* Currently all places where pud_clear() is called either have
* flush_tlb_mm() followed or don't need TLB flush (x86_64 code or
* pud_clear_bad()), so we don't need TLB flush here.
*/
}
#ifdef CONFIG_SMP
static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
{
pte_t old = *ptep;
do {
} while (!try_cmpxchg64(&ptep->pte, &old.pte, 0ULL));
return old;
}
#else
#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
#endif
#ifdef CONFIG_SMP
static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
{
pmd_t res;
/* xchg acts as a barrier before setting of the high bits */
res.pmd_low = xchg(&pmdp->pmd_low, 0);
res.pmd_high = READ_ONCE(pmdp->pmd_high);
WRITE_ONCE(pmdp->pmd_high, 0);
return res;
}
#else
#define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp)
#endif
#ifndef pmdp_establish
#define pmdp_establish pmdp_establish
static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp, pmd_t pmd)
{
pmd_t old;
/*
* If pmd has present bit cleared we can get away without expensive
* cmpxchg64: we can update pmdp half-by-half without racing with
* anybody.
*/
if (!(pmd_val(pmd) & _PAGE_PRESENT)) {
/* xchg acts as a barrier before setting of the high bits */
old.pmd_low = xchg(&pmdp->pmd_low, pmd.pmd_low);
old.pmd_high = READ_ONCE(pmdp->pmd_high);
WRITE_ONCE(pmdp->pmd_high, pmd.pmd_high);
return old;
}
do {
old = *pmdp;
} while (cmpxchg64(&pmdp->pmd, old.pmd, pmd.pmd) != old.pmd);
return old;
}
#endif
#ifdef CONFIG_SMP
union split_pud {
struct {
u32 pud_low;
u32 pud_high;
};
pud_t pud;
};
static inline pud_t native_pudp_get_and_clear(pud_t *pudp)
{
union split_pud res, *orig = (union split_pud *)pudp;
#ifdef CONFIG_PAGE_TABLE_ISOLATION
pti_set_user_pgtbl(&pudp->p4d.pgd, __pgd(0));
#endif
/* xchg acts as a barrier before setting of the high bits */
res.pud_low = xchg(&orig->pud_low, 0);
res.pud_high = orig->pud_high;
orig->pud_high = 0;
return res.pud;
}
#else
#define native_pudp_get_and_clear(xp) native_local_pudp_get_and_clear(xp)
#endif
/* Encode and de-code a swap entry */
#define SWP_TYPE_BITS 5
#define SWP_OFFSET_FIRST_BIT (_PAGE_BIT_PROTNONE + 1)
/* We always extract/encode the offset by shifting it all the way up, and then down again */
#define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT + SWP_TYPE_BITS)
#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
#define __swp_type(x) (((x).val) & ((1UL << SWP_TYPE_BITS) - 1))
#define __swp_offset(x) ((x).val >> SWP_TYPE_BITS)
#define __swp_entry(type, offset) ((swp_entry_t){(type) | (offset) << SWP_TYPE_BITS})
/*
* Normally, __swp_entry() converts from arch-independent swp_entry_t to
* arch-dependent swp_entry_t, and __swp_entry_to_pte() just stores the result
* to pte. But here we have 32bit swp_entry_t and 64bit pte, and need to use the
* whole 64 bits. Thus, we shift the "real" arch-dependent conversion to
* __swp_entry_to_pte() through the following helper macro based on 64bit
* __swp_entry().
*/
#define __swp_pteval_entry(type, offset) ((pteval_t) { \
(~(pteval_t)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \
| ((pteval_t)(type) << (64 - SWP_TYPE_BITS)) })
#define __swp_entry_to_pte(x) ((pte_t){ .pte = \
__swp_pteval_entry(__swp_type(x), __swp_offset(x)) })
/*
* Analogically, __pte_to_swp_entry() doesn't just extract the arch-dependent
* swp_entry_t, but also has to convert it from 64bit to the 32bit
* intermediate representation, using the following macros based on 64bit
* __swp_type() and __swp_offset().
*/
#define __pteval_swp_type(x) ((unsigned long)((x).pte >> (64 - SWP_TYPE_BITS)))
#define __pteval_swp_offset(x) ((unsigned long)(~((x).pte) << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT))
#define __pte_to_swp_entry(pte) (__swp_entry(__pteval_swp_type(pte), \
__pteval_swp_offset(pte)))
#include <asm/pgtable-invert.h>
#endif /* _ASM_X86_PGTABLE_3LEVEL_H */
|
