aboutsummaryrefslogtreecommitdiffstats
path: root/xen/include/asm-x86/domain.h
blob: 30c7601d1a41972a43b31d402bfdc7da8882a46d (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
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
304
305
306
307
308
309
310
311
312
313
314
#ifndef __ASM_DOMAIN_H__
#define __ASM_DOMAIN_H__

#include <xen/config.h>
#include <xen/mm.h>
#include <asm/hvm/vcpu.h>
#include <asm/hvm/domain.h>
#include <asm/e820.h>

#define has_32bit_shinfo(d)    ((d)->arch.has_32bit_shinfo)
#define is_pv_32bit_domain(d)  ((d)->arch.is_32bit_pv)
#define is_pv_32bit_vcpu(v)    (is_pv_32bit_domain((v)->domain))
#ifdef __x86_64__
#define is_pv_32on64_domain(d) (is_pv_32bit_domain(d))
#else
#define is_pv_32on64_domain(d) (0)
#endif
#define is_pv_32on64_vcpu(v)   (is_pv_32on64_domain((v)->domain))
#define IS_COMPAT(d)           (is_pv_32on64_domain(d))

struct trap_bounce {
    uint32_t      error_code;
    uint8_t       flags; /* TBF_ */
    uint16_t      cs;
    unsigned long eip;
};

#define MAPHASH_ENTRIES 8
#define MAPHASH_HASHFN(pfn) ((pfn) & (MAPHASH_ENTRIES-1))
#define MAPHASHENT_NOTINUSE ((u16)~0U)
struct vcpu_maphash {
    struct vcpu_maphash_entry {
        unsigned long mfn;
        uint16_t      idx;
        uint16_t      refcnt;
    } hash[MAPHASH_ENTRIES];
} __cacheline_aligned;

#define MAPCACHE_ORDER   10
#define MAPCACHE_ENTRIES (1 << MAPCACHE_ORDER)
struct mapcache {
    /* The PTEs that provide the mappings, and a cursor into the array. */
    l1_pgentry_t *l1tab;
    unsigned int cursor;

    /* Protects map_domain_page(). */
    spinlock_t lock;

    /* Garbage mappings are flushed from TLBs in batches called 'epochs'. */
    unsigned int epoch, shadow_epoch[MAX_VIRT_CPUS];
    u32 tlbflush_timestamp;

    /* Which mappings are in use, and which are garbage to reap next epoch? */
    unsigned long inuse[BITS_TO_LONGS(MAPCACHE_ENTRIES)];
    unsigned long garbage[BITS_TO_LONGS(MAPCACHE_ENTRIES)];

    /* Lock-free per-VCPU hash of recently-used mappings. */
    struct vcpu_maphash vcpu_maphash[MAX_VIRT_CPUS];
};

extern void mapcache_init(struct domain *);

/* x86/64: toggle guest between kernel and user modes. */
extern void toggle_guest_mode(struct vcpu *);

/*
 * Initialise a hypercall-transfer page. The given pointer must be mapped
 * in Xen virtual address space (accesses are not validated or checked).
 */
extern void hypercall_page_initialise(struct domain *d, void *);

/************************************************/
/*          shadow paging extension             */
/************************************************/
struct shadow_domain {
    spinlock_t        lock;  /* shadow domain lock */
    int               locker; /* processor which holds the lock */
    const char       *locker_function; /* Func that took it */
    unsigned int      opt_flags;    /* runtime tunable optimizations on/off */
    struct list_head  pinned_shadows; 

    /* Memory allocation */
    struct list_head  freelists[SHADOW_MAX_ORDER + 1]; 
    struct list_head  p2m_freelist;
    unsigned int      total_pages;  /* number of pages allocated */
    unsigned int      free_pages;   /* number of pages on freelists */
    unsigned int      p2m_pages;    /* number of pages allocates to p2m */

    /* Shadow hashtable */
    struct shadow_page_info **hash_table;
    int hash_walking;  /* Some function is walking the hash table */

    /* Fast MMIO path heuristic */
    int has_fast_mmio_entries;

    /* Shadow log-dirty bitmap */
    unsigned long *dirty_bitmap;
    unsigned int dirty_bitmap_size;  /* in pages, bit per page */

    /* Shadow log-dirty mode stats */
    unsigned int fault_count;
    unsigned int dirty_count;
};

struct shadow_vcpu {
#if CONFIG_PAGING_LEVELS >= 3
    /* PAE guests: per-vcpu shadow top-level table */
    l3_pgentry_t l3table[4] __attribute__((__aligned__(32)));
    /* PAE guests: per-vcpu cache of the top-level *guest* entries */
    l3_pgentry_t gl3e[4] __attribute__((__aligned__(32)));
#endif
    /* Non-PAE guests: pointer to guest top-level pagetable */
    void *guest_vtable;
    /* Last MFN that we emulated a write to. */
    unsigned long last_emulated_mfn;
    /* MFN of the last shadow that we shot a writeable mapping in */
    unsigned long last_writeable_pte_smfn;
};

/************************************************/
/*            hardware assisted paging          */
/************************************************/
struct hap_domain {
    spinlock_t        lock;
    int               locker;
    const char       *locker_function;
    
    struct list_head  freelists;
    unsigned int      total_pages;  /* number of pages allocated */
    unsigned int      free_pages;   /* number of pages on freelists */
    unsigned int      p2m_pages;    /* number of pages allocates to p2m */
};

/************************************************/
/*       p2m handling                           */
/************************************************/

struct p2m_domain {
    /* Lock that protects updates to the p2m */
    spinlock_t         lock;
    int                locker;   /* processor which holds the lock */
    const char        *locker_function; /* Func that took it */
    
    /* Pages used to construct the p2m */
    struct list_head   pages;

    /* Functions to call to get or free pages for the p2m */
    struct page_info * (*alloc_page  )(struct domain *d);
    void               (*free_page   )(struct domain *d, 
                                       struct page_info *pg);

    /* Highest guest frame that's ever been mapped in the p2m */
    unsigned long max_mapped_pfn;
};

/************************************************/
/*       common paging data structure           */
/************************************************/
struct paging_domain {
    u32               mode;  /* flags to control paging operation */

    /* extension for shadow paging support */
    struct shadow_domain shadow;

    /* Other paging assistance code will have structs here */
    struct hap_domain    hap;
};

struct paging_vcpu {
    /* Pointers to mode-specific entry points. */
    struct paging_mode *mode;
    /* HVM guest: paging enabled (CR0.PG)?  */
    unsigned int translate_enabled:1;
    /* HVM guest: last emulate was to a pagetable */
    unsigned int last_write_was_pt:1;

    /* paging support extension */
    struct shadow_vcpu shadow;
};

struct arch_domain
{
    l1_pgentry_t *mm_perdomain_pt;
#ifdef CONFIG_X86_64
    l2_pgentry_t *mm_perdomain_l2;
    l3_pgentry_t *mm_perdomain_l3;
#endif

#ifdef CONFIG_X86_32
    /* map_domain_page() mapping cache. */
    struct mapcache mapcache;
#endif

#ifdef CONFIG_COMPAT
    unsigned int hv_compat_vstart;
    l3_pgentry_t *mm_arg_xlat_l3;
#endif

    /* I/O-port admin-specified access capabilities. */
    struct rangeset *ioport_caps;

    struct hvm_domain hvm_domain;

    struct paging_domain paging;
    struct p2m_domain p2m ;

    /* Shadow translated domain: P2M mapping */
    pagetable_t phys_table;

    /* Pseudophysical e820 map (XENMEM_memory_map).  */
    struct e820entry e820[3];
    unsigned int nr_e820;

    /* Maximum physical-address bitwidth supported by this guest. */
    unsigned int physaddr_bitsize;

    /* Is a 32-bit PV (non-HVM) guest? */
    bool_t is_32bit_pv;
    /* Is shared-info page in 32-bit format? */
    bool_t has_32bit_shinfo;
} __cacheline_aligned;

#ifdef CONFIG_X86_PAE
struct pae_l3_cache {
    /*
     * Two low-memory (<4GB) PAE L3 tables, used as fallback when the guest
     * supplies a >=4GB PAE L3 table. We need two because we cannot set up
     * an L3 table while we are currently running on it (without using
     * expensive atomic 64-bit operations).
     */
    l3_pgentry_t  table[2][4] __attribute__((__aligned__(32)));
    unsigned long high_mfn;  /* The >=4GB MFN being shadowed. */
    unsigned int  inuse_idx; /* Which of the two cache slots is in use? */
    spinlock_t    lock;
};
#define pae_l3_cache_init(c) spin_lock_init(&(c)->lock)
#else /* !CONFIG_X86_PAE */
struct pae_l3_cache { };
#define pae_l3_cache_init(c) ((void)0)
#endif

struct arch_vcpu
{
    /* Needs 16-byte aligment for FXSAVE/FXRSTOR. */
    struct vcpu_guest_context guest_context
    __attribute__((__aligned__(16)));

    struct pae_l3_cache pae_l3_cache;

    unsigned long      flags; /* TF_ */

    void (*schedule_tail) (struct vcpu *);

    void (*ctxt_switch_from) (struct vcpu *);
    void (*ctxt_switch_to) (struct vcpu *);

    /* Bounce information for propagating an exception to guest OS. */
    struct trap_bounce trap_bounce;

    /* I/O-port access bitmap. */
    XEN_GUEST_HANDLE(uint8_t) iobmp; /* Guest kernel virtual address of the bitmap. */
    int iobmp_limit;  /* Number of ports represented in the bitmap.  */
    int iopl;         /* Current IOPL for this VCPU. */

#ifdef CONFIG_X86_32
    struct desc_struct int80_desc;
#endif
#ifdef CONFIG_X86_64
    struct trap_bounce int80_bounce;
#endif

    /* Virtual Machine Extensions */
    struct hvm_vcpu hvm_vcpu;

    /*
     * Every domain has a L1 pagetable of its own. Per-domain mappings
     * are put in this table (eg. the current GDT is mapped here).
     */
    l1_pgentry_t *perdomain_ptes;

#ifdef CONFIG_X86_64
    pagetable_t guest_table_user;       /* (MFN) x86/64 user-space pagetable */
#endif
    pagetable_t guest_table;            /* (MFN) guest notion of cr3 */
    /* guest_table holds a ref to the page, and also a type-count unless
     * shadow refcounts are in use */
    pagetable_t shadow_table[4];        /* (MFN) shadow(s) of guest */
    pagetable_t monitor_table;          /* (MFN) hypervisor PT (for HVM) */
    unsigned long cr3;           	    /* (MA) value to install in HW CR3 */

    /* Current LDT details. */
    unsigned long shadow_ldt_mapcnt;

    struct paging_vcpu paging;

    /* Guest-specified relocation of vcpu_info. */
    unsigned long vcpu_info_mfn;
} __cacheline_aligned;

/* shorthands to improve code legibility */
#define hvm_vmx         hvm_vcpu.u.vmx
#define hvm_svm         hvm_vcpu.u.svm

#endif /* __ASM_DOMAIN_H__ */

/*
 * Local variables:
 * mode: C
 * c-set-style: "BSD"
 * c-basic-offset: 4
 * tab-width: 4
 * indent-tabs-mode: nil
 * End:
 */