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
|
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __KVM_X86_MMU_INTERNAL_H
#define __KVM_X86_MMU_INTERNAL_H
#include <linux/types.h>
#include <linux/kvm_host.h>
#include <asm/kvm_host.h>
#undef MMU_DEBUG
#ifdef MMU_DEBUG
extern bool dbg;
#define pgprintk(x...) do { if (dbg) printk(x); } while (0)
#define rmap_printk(fmt, args...) do { if (dbg) printk("%s: " fmt, __func__, ## args); } while (0)
#define MMU_WARN_ON(x) WARN_ON(x)
#else
#define pgprintk(x...) do { } while (0)
#define rmap_printk(x...) do { } while (0)
#define MMU_WARN_ON(x) do { } while (0)
#endif
struct kvm_mmu_page {
struct list_head link;
struct hlist_node hash_link;
struct list_head lpage_disallowed_link;
bool unsync;
u8 mmu_valid_gen;
bool mmio_cached;
bool lpage_disallowed; /* Can't be replaced by an equiv large page */
/*
* The following two entries are used to key the shadow page in the
* hash table.
*/
union kvm_mmu_page_role role;
gfn_t gfn;
u64 *spt;
/* hold the gfn of each spte inside spt */
gfn_t *gfns;
int root_count; /* Currently serving as active root */
unsigned int unsync_children;
struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */
DECLARE_BITMAP(unsync_child_bitmap, 512);
#ifdef CONFIG_X86_32
/*
* Used out of the mmu-lock to avoid reading spte values while an
* update is in progress; see the comments in __get_spte_lockless().
*/
int clear_spte_count;
#endif
/* Number of writes since the last time traversal visited this page. */
atomic_t write_flooding_count;
#ifdef CONFIG_X86_64
bool tdp_mmu_page;
/* Used for freeing the page asyncronously if it is a TDP MMU page. */
struct rcu_head rcu_head;
#endif
};
extern struct kmem_cache *mmu_page_header_cache;
static inline struct kvm_mmu_page *to_shadow_page(hpa_t shadow_page)
{
struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT);
return (struct kvm_mmu_page *)page_private(page);
}
static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep)
{
return to_shadow_page(__pa(sptep));
}
static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu)
{
/*
* When using the EPT page-modification log, the GPAs in the log
* would come from L2 rather than L1. Therefore, we need to rely
* on write protection to record dirty pages. This also bypasses
* PML, since writes now result in a vmexit. Note, this helper will
* tag SPTEs as needing write-protection even if PML is disabled or
* unsupported, but that's ok because the tag is consumed if and only
* if PML is enabled. Omit the PML check to save a few uops.
*/
return vcpu->arch.mmu == &vcpu->arch.guest_mmu;
}
bool is_nx_huge_page_enabled(void);
bool mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
bool can_unsync);
void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
struct kvm_memory_slot *slot, u64 gfn);
void kvm_flush_remote_tlbs_with_address(struct kvm *kvm,
u64 start_gfn, u64 pages);
static inline void kvm_mmu_get_root(struct kvm *kvm, struct kvm_mmu_page *sp)
{
BUG_ON(!sp->root_count);
lockdep_assert_held(&kvm->mmu_lock);
++sp->root_count;
}
static inline bool kvm_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *sp)
{
lockdep_assert_held(&kvm->mmu_lock);
--sp->root_count;
return !sp->root_count;
}
/*
* Return values of handle_mmio_page_fault, mmu.page_fault, and fast_page_fault().
*
* RET_PF_RETRY: let CPU fault again on the address.
* RET_PF_EMULATE: mmio page fault, emulate the instruction directly.
* RET_PF_INVALID: the spte is invalid, let the real page fault path update it.
* RET_PF_FIXED: The faulting entry has been fixed.
* RET_PF_SPURIOUS: The faulting entry was already fixed, e.g. by another vCPU.
*/
enum {
RET_PF_RETRY = 0,
RET_PF_EMULATE,
RET_PF_INVALID,
RET_PF_FIXED,
RET_PF_SPURIOUS,
};
/* Bits which may be returned by set_spte() */
#define SET_SPTE_WRITE_PROTECTED_PT BIT(0)
#define SET_SPTE_NEED_REMOTE_TLB_FLUSH BIT(1)
#define SET_SPTE_SPURIOUS BIT(2)
int kvm_mmu_max_mapping_level(struct kvm *kvm, struct kvm_memory_slot *slot,
gfn_t gfn, kvm_pfn_t pfn, int max_level);
int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn,
int max_level, kvm_pfn_t *pfnp,
bool huge_page_disallowed, int *req_level);
void disallowed_hugepage_adjust(u64 spte, gfn_t gfn, int cur_level,
kvm_pfn_t *pfnp, int *goal_levelp);
bool is_nx_huge_page_enabled(void);
void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
#endif /* __KVM_X86_MMU_INTERNAL_H */
|
