aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/kvm/kvm.h
blob: eda82cded88e6dca4b0310d2719f790c6c5223a1 (plain) (blame)
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
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
#ifndef __KVM_H
#define __KVM_H

/*
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 */

#include <linux/types.h>
#include <linux/hardirq.h>
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/preempt.h>
#include <asm/signal.h>

#include <linux/kvm.h>
#include <linux/kvm_para.h>

#define KVM_MAX_VCPUS 4
#define KVM_ALIAS_SLOTS 4
#define KVM_MEMORY_SLOTS 8
/* memory slots that does not exposed to userspace */
#define KVM_PRIVATE_MEM_SLOTS 4
#define KVM_PERMILLE_MMU_PAGES 20
#define KVM_MIN_ALLOC_MMU_PAGES 64
#define KVM_NUM_MMU_PAGES 1024
#define KVM_MIN_FREE_MMU_PAGES 5
#define KVM_REFILL_PAGES 25
#define KVM_MAX_CPUID_ENTRIES 40

#define KVM_PIO_PAGE_OFFSET 1

/*
 * vcpu->requests bit members
 */
#define KVM_REQ_TLB_FLUSH          0

/*
 * Address types:
 *
 *  gva - guest virtual address
 *  gpa - guest physical address
 *  gfn - guest frame number
 *  hva - host virtual address
 *  hpa - host physical address
 *  hfn - host frame number
 */

typedef unsigned long  gva_t;
typedef u64            gpa_t;
typedef unsigned long  gfn_t;

typedef unsigned long  hva_t;
typedef u64            hpa_t;
typedef unsigned long  hfn_t;

#define NR_PTE_CHAIN_ENTRIES 5

struct kvm_pte_chain {
	u64 *parent_ptes[NR_PTE_CHAIN_ENTRIES];
	struct hlist_node link;
};

/*
 * kvm_mmu_page_role, below, is defined as:
 *
 *   bits 0:3 - total guest paging levels (2-4, or zero for real mode)
 *   bits 4:7 - page table level for this shadow (1-4)
 *   bits 8:9 - page table quadrant for 2-level guests
 *   bit   16 - "metaphysical" - gfn is not a real page (huge page/real mode)
 *   bits 17:19 - "access" - the user, writable, and nx bits of a huge page pde
 */
union kvm_mmu_page_role {
	unsigned word;
	struct {
		unsigned glevels : 4;
		unsigned level : 4;
		unsigned quadrant : 2;
		unsigned pad_for_nice_hex_output : 6;
		unsigned metaphysical : 1;
		unsigned hugepage_access : 3;
	};
};

struct kvm_mmu_page {
	struct list_head link;
	struct hlist_node hash_link;

	/*
	 * The following two entries are used to key the shadow page in the
	 * hash table.
	 */
	gfn_t gfn;
	union kvm_mmu_page_role role;

	u64 *spt;
	/* hold the gfn of each spte inside spt */
	gfn_t *gfns;
	unsigned long slot_bitmap; /* One bit set per slot which has memory
				    * in this shadow page.
				    */
	int multimapped;         /* More than one parent_pte? */
	int root_count;          /* Currently serving as active root */
	union {
		u64 *parent_pte;               /* !multimapped */
		struct hlist_head parent_ptes; /* multimapped, kvm_pte_chain */
	};
};

struct kvm_vcpu;
extern struct kmem_cache *kvm_vcpu_cache;

/*
 * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level
 * 32-bit).  The kvm_mmu structure abstracts the details of the current mmu
 * mode.
 */
struct kvm_mmu {
	void (*new_cr3)(struct kvm_vcpu *vcpu);
	int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err);
	void (*free)(struct kvm_vcpu *vcpu);
	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva);
	void (*prefetch_page)(struct kvm_vcpu *vcpu,
			      struct kvm_mmu_page *page);
	hpa_t root_hpa;
	int root_level;
	int shadow_root_level;

	u64 *pae_root;
};

#define KVM_NR_MEM_OBJS 40

/*
 * We don't want allocation failures within the mmu code, so we preallocate
 * enough memory for a single page fault in a cache.
 */
struct kvm_mmu_memory_cache {
	int nobjs;
	void *objects[KVM_NR_MEM_OBJS];
};

struct kvm_guest_debug {
	int enabled;
	unsigned long bp[4];
	int singlestep;
};

struct kvm_pio_request {
	unsigned long count;
	int cur_count;
	struct page *guest_pages[2];
	unsigned guest_page_offset;
	int in;
	int port;
	int size;
	int string;
	int down;
	int rep;
};

struct kvm_vcpu_stat {
	u32 pf_fixed;
	u32 pf_guest;
	u32 tlb_flush;
	u32 invlpg;

	u32 exits;
	u32 io_exits;
	u32 mmio_exits;
	u32 signal_exits;
	u32 irq_window_exits;
	u32 halt_exits;
	u32 halt_wakeup;
	u32 request_irq_exits;
	u32 irq_exits;
	u32 host_state_reload;
	u32 efer_reload;
	u32 fpu_reload;
	u32 insn_emulation;
	u32 insn_emulation_fail;
};

struct kvm_io_device {
	void (*read)(struct kvm_io_device *this,
		     gpa_t addr,
		     int len,
		     void *val);
	void (*write)(struct kvm_io_device *this,
		      gpa_t addr,
		      int len,
		      const void *val);
	int (*in_range)(struct kvm_io_device *this, gpa_t addr);
	void (*destructor)(struct kvm_io_device *this);

	void             *private;
};

static inline void kvm_iodevice_read(struct kvm_io_device *dev,
				     gpa_t addr,
				     int len,
				     void *val)
{
	dev->read(dev, addr, len, val);
}

static inline void kvm_iodevice_write(struct kvm_io_device *dev,
				      gpa_t addr,
				      int len,
				      const void *val)
{
	dev->write(dev, addr, len, val);
}

static inline int kvm_iodevice_inrange(struct kvm_io_device *dev, gpa_t addr)
{
	return dev->in_range(dev, addr);
}

static inline void kvm_iodevice_destructor(struct kvm_io_device *dev)
{
	if (dev->destructor)
		dev->destructor(dev);
}

/*
 * It would be nice to use something smarter than a linear search, TBD...
 * Thankfully we dont expect many devices to register (famous last words :),
 * so until then it will suffice.  At least its abstracted so we can change
 * in one place.
 */
struct kvm_io_bus {
	int                   dev_count;
#define NR_IOBUS_DEVS 6
	struct kvm_io_device *devs[NR_IOBUS_DEVS];
};

void kvm_io_bus_init(struct kvm_io_bus *bus);
void kvm_io_bus_destroy(struct kvm_io_bus *bus);
struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus, gpa_t addr);
void kvm_io_bus_register_dev(struct kvm_io_bus *bus,
			     struct kvm_io_device *dev);

#ifdef CONFIG_HAS_IOMEM
#define KVM_VCPU_MMIO 			\
	int mmio_needed;		\
	int mmio_read_completed;	\
	int mmio_is_write;		\
	int mmio_size;			\
	unsigned char mmio_data[8];	\
	gpa_t mmio_phys_addr;

#else
#define KVM_VCPU_MMIO

#endif

#define KVM_VCPU_COMM 					\
	struct kvm *kvm; 				\
	struct preempt_notifier preempt_notifier;	\
	int vcpu_id;					\
	struct mutex mutex;				\
	int   cpu;					\
	struct kvm_run *run;				\
	int guest_mode;					\
	unsigned long requests;				\
	struct kvm_guest_debug guest_debug;		\
	int fpu_active; 				\
	int guest_fpu_loaded;				\
	wait_queue_head_t wq;				\
	int sigset_active;				\
	sigset_t sigset;				\
	struct kvm_vcpu_stat stat;			\
	KVM_VCPU_MMIO

struct kvm_mem_alias {
	gfn_t base_gfn;
	unsigned long npages;
	gfn_t target_gfn;
};

struct kvm_memory_slot {
	gfn_t base_gfn;
	unsigned long npages;
	unsigned long flags;
	unsigned long *rmap;
	unsigned long *dirty_bitmap;
	unsigned long userspace_addr;
	int user_alloc;
};

struct kvm_vm_stat {
	u32 mmu_shadow_zapped;
	u32 mmu_pte_write;
	u32 mmu_pte_updated;
	u32 mmu_pde_zapped;
	u32 mmu_flooded;
	u32 mmu_recycled;
	u32 remote_tlb_flush;
};

struct kvm {
	struct mutex lock; /* protects everything except vcpus */
	int naliases;
	struct kvm_mem_alias aliases[KVM_ALIAS_SLOTS];
	int nmemslots;
	struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS +
					KVM_PRIVATE_MEM_SLOTS];
	/*
	 * Hash table of struct kvm_mmu_page.
	 */
	struct list_head active_mmu_pages;
	unsigned int n_free_mmu_pages;
	unsigned int n_requested_mmu_pages;
	unsigned int n_alloc_mmu_pages;
	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
	struct list_head vm_list;
	struct file *filp;
	struct kvm_io_bus mmio_bus;
	struct kvm_io_bus pio_bus;
	struct kvm_pic *vpic;
	struct kvm_ioapic *vioapic;
	int round_robin_prev_vcpu;
	unsigned int tss_addr;
	struct page *apic_access_page;
	struct kvm_vm_stat stat;
};

static inline struct kvm_pic *pic_irqchip(struct kvm *kvm)
{
	return kvm->vpic;
}

static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm)
{
	return kvm->vioapic;
}

static inline int irqchip_in_kernel(struct kvm *kvm)
{
	return pic_irqchip(kvm) != NULL;
}

struct descriptor_table {
	u16 limit;
	unsigned long base;
} __attribute__((packed));

/* The guest did something we don't support. */
#define pr_unimpl(vcpu, fmt, ...)					\
 do {									\
	if (printk_ratelimit())						\
		printk(KERN_ERR "kvm: %i: cpu%i " fmt,			\
		       current->tgid, (vcpu)->vcpu_id , ## __VA_ARGS__); \
 } while (0)

#define kvm_printf(kvm, fmt ...) printk(KERN_DEBUG fmt)
#define vcpu_printf(vcpu, fmt...) kvm_printf(vcpu->kvm, fmt)

int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id);
void kvm_vcpu_uninit(struct kvm_vcpu *vcpu);

void vcpu_load(struct kvm_vcpu *vcpu);
void vcpu_put(struct kvm_vcpu *vcpu);

void decache_vcpus_on_cpu(int cpu);


int kvm_init(void *opaque, unsigned int vcpu_size,
		  struct module *module);
void kvm_exit(void);

hpa_t gpa_to_hpa(struct kvm *kvm, gpa_t gpa);
#define HPA_MSB ((sizeof(hpa_t) * 8) - 1)
#define HPA_ERR_MASK ((hpa_t)1 << HPA_MSB)
static inline int is_error_hpa(hpa_t hpa) { return hpa >> HPA_MSB; }
hpa_t gva_to_hpa(struct kvm_vcpu *vcpu, gva_t gva);
struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva);

extern struct page *bad_page;

int is_error_page(struct page *page);
int kvm_is_error_hva(unsigned long addr);
int kvm_set_memory_region(struct kvm *kvm,
			  struct kvm_userspace_memory_region *mem,
			  int user_alloc);
int __kvm_set_memory_region(struct kvm *kvm,
			    struct kvm_userspace_memory_region *mem,
			    int user_alloc);
int kvm_arch_set_memory_region(struct kvm *kvm,
				struct kvm_userspace_memory_region *mem,
				struct kvm_memory_slot old,
				int user_alloc);
gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn);
struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
void kvm_release_page_clean(struct page *page);
void kvm_release_page_dirty(struct page *page);
int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
			int len);
int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len);
int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data,
			 int offset, int len);
int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
		    unsigned long len);
int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
void mark_page_dirty(struct kvm *kvm, gfn_t gfn);

void kvm_vcpu_block(struct kvm_vcpu *vcpu);
void kvm_resched(struct kvm_vcpu *vcpu);
void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
void kvm_flush_remote_tlbs(struct kvm *kvm);

long kvm_arch_dev_ioctl(struct file *filp,
			unsigned int ioctl, unsigned long arg);
long kvm_arch_vcpu_ioctl(struct file *filp,
			 unsigned int ioctl, unsigned long arg);
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);

int kvm_dev_ioctl_check_extension(long ext);

int kvm_get_dirty_log(struct kvm *kvm,
			struct kvm_dirty_log *log, int *is_dirty);
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
				struct kvm_dirty_log *log);

int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
				   struct
				   kvm_userspace_memory_region *mem,
				   int user_alloc);
long kvm_arch_vm_ioctl(struct file *filp,
		       unsigned int ioctl, unsigned long arg);
void kvm_arch_destroy_vm(struct kvm *kvm);

int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu);
int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu);

int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
				    struct kvm_translation *tr);

int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs);
int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs);
int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs);
int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs);
int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
				    struct kvm_debug_guest *dbg);
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run);

int kvm_arch_init(void *opaque);
void kvm_arch_exit(void);

int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu);

void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id);
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu);

int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu);
void kvm_arch_hardware_enable(void *garbage);
void kvm_arch_hardware_disable(void *garbage);
int kvm_arch_hardware_setup(void);
void kvm_arch_hardware_unsetup(void);
void kvm_arch_check_processor_compat(void *rtn);

void kvm_free_physmem(struct kvm *kvm);

struct  kvm *kvm_arch_create_vm(void);
void kvm_arch_destroy_vm(struct kvm *kvm);

static inline void kvm_guest_enter(void)
{
	account_system_vtime(current);
	current->flags |= PF_VCPU;
}

static inline void kvm_guest_exit(void)
{
	account_system_vtime(current);
	current->flags &= ~PF_VCPU;
}

static inline int memslot_id(struct kvm *kvm, struct kvm_memory_slot *slot)
{
	return slot - kvm->memslots;
}

static inline gpa_t gfn_to_gpa(gfn_t gfn)
{
	return (gpa_t)gfn << PAGE_SHIFT;
}

enum kvm_stat_kind {
	KVM_STAT_VM,
	KVM_STAT_VCPU,
};

struct kvm_stats_debugfs_item {
	const char *name;
	int offset;
	enum kvm_stat_kind kind;
	struct dentry *dentry;
};
extern struct kvm_stats_debugfs_item debugfs_entries[];

#endif