[GitHub/mt8127/android_kernel_alcatel_ttab.git] / drivers / kvm / kvm.h

#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/list.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
#include <linux/mm.h>

#include "vmx.h"
#include <linux/kvm.h>

#define CR0_PE_MASK (1ULL << 0)
#define CR0_TS_MASK (1ULL << 3)
#define CR0_NE_MASK (1ULL << 5)
#define CR0_WP_MASK (1ULL << 16)
#define CR0_NW_MASK (1ULL << 29)
#define CR0_CD_MASK (1ULL << 30)
#define CR0_PG_MASK (1ULL << 31)

#define CR3_WPT_MASK (1ULL << 3)
#define CR3_PCD_MASK (1ULL << 4)

#define CR3_RESEVED_BITS 0x07ULL
#define CR3_L_MODE_RESEVED_BITS (~((1ULL << 40) - 1) | 0x0fe7ULL)
#define CR3_FLAGS_MASK ((1ULL << 5) - 1)

#define CR4_VME_MASK (1ULL << 0)
#define CR4_PSE_MASK (1ULL << 4)
#define CR4_PAE_MASK (1ULL << 5)
#define CR4_PGE_MASK (1ULL << 7)
#define CR4_VMXE_MASK (1ULL << 13)

#define KVM_GUEST_CR0_MASK \
	(CR0_PG_MASK | CR0_PE_MASK | CR0_WP_MASK | CR0_NE_MASK \
	 | CR0_NW_MASK | CR0_CD_MASK)
#define KVM_VM_CR0_ALWAYS_ON \
	(CR0_PG_MASK | CR0_PE_MASK | CR0_WP_MASK | CR0_NE_MASK)
#define KVM_GUEST_CR4_MASK \
	(CR4_PSE_MASK | CR4_PAE_MASK | CR4_PGE_MASK | CR4_VMXE_MASK | CR4_VME_MASK)
#define KVM_PMODE_VM_CR4_ALWAYS_ON (CR4_VMXE_MASK | CR4_PAE_MASK)
#define KVM_RMODE_VM_CR4_ALWAYS_ON (CR4_VMXE_MASK | CR4_PAE_MASK | CR4_VME_MASK)

#define INVALID_PAGE (~(hpa_t)0)
#define UNMAPPED_GVA (~(gpa_t)0)

#define KVM_MAX_VCPUS 1
#define KVM_MEMORY_SLOTS 4
#define KVM_NUM_MMU_PAGES 256

#define FX_IMAGE_SIZE 512
#define FX_IMAGE_ALIGN 16
#define FX_BUF_SIZE (2 * FX_IMAGE_SIZE + FX_IMAGE_ALIGN)

#define DE_VECTOR 0
#define DF_VECTOR 8
#define TS_VECTOR 10
#define NP_VECTOR 11
#define SS_VECTOR 12
#define GP_VECTOR 13
#define PF_VECTOR 14

#define SELECTOR_TI_MASK (1 << 2)
#define SELECTOR_RPL_MASK 0x03

#define IOPL_SHIFT 12

/*
 * 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)
 */
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;
	};
};

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;

	hpa_t page_hpa;
	unsigned long slot_bitmap; /* One bit set per slot which has memory
				    * in this shadow page.
				    */
	int global;              /* Set if all ptes in this page are global */
	int multimapped;         /* More than one parent_pte? */
	union {
		u64 *parent_pte;               /* !multimapped */
		struct hlist_head parent_ptes; /* multimapped, kvm_pte_chain */
	};
};

struct vmcs {
	u32 revision_id;
	u32 abort;
	char data[0];
};

#define vmx_msr_entry kvm_msr_entry

struct kvm_vcpu;

/*
 * 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 (*inval_page)(struct kvm_vcpu *vcpu, gva_t gva);
	void (*free)(struct kvm_vcpu *vcpu);
	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva);
	hpa_t root_hpa;
	int root_level;
	int shadow_root_level;

	u64 *pae_root;
};

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

enum {
	VCPU_REGS_RAX = 0,
	VCPU_REGS_RCX = 1,
	VCPU_REGS_RDX = 2,
	VCPU_REGS_RBX = 3,
	VCPU_REGS_RSP = 4,
	VCPU_REGS_RBP = 5,
	VCPU_REGS_RSI = 6,
	VCPU_REGS_RDI = 7,
#ifdef CONFIG_X86_64
	VCPU_REGS_R8 = 8,
	VCPU_REGS_R9 = 9,
	VCPU_REGS_R10 = 10,
	VCPU_REGS_R11 = 11,
	VCPU_REGS_R12 = 12,
	VCPU_REGS_R13 = 13,
	VCPU_REGS_R14 = 14,
	VCPU_REGS_R15 = 15,
#endif
	NR_VCPU_REGS
};

enum {
	VCPU_SREG_CS,
	VCPU_SREG_DS,
	VCPU_SREG_ES,
	VCPU_SREG_FS,
	VCPU_SREG_GS,
	VCPU_SREG_SS,
	VCPU_SREG_TR,
	VCPU_SREG_LDTR,
};

struct kvm_vcpu {
	struct kvm *kvm;
	union {
		struct vmcs *vmcs;
		struct vcpu_svm *svm;
	};
	struct mutex mutex;
	int   cpu;
	int   launched;
	int interrupt_window_open;
	unsigned long irq_summary; /* bit vector: 1 per word in irq_pending */
#define NR_IRQ_WORDS KVM_IRQ_BITMAP_SIZE(unsigned long)
	unsigned long irq_pending[NR_IRQ_WORDS];
	unsigned long regs[NR_VCPU_REGS]; /* for rsp: vcpu_load_rsp_rip() */
	unsigned long rip;      /* needs vcpu_load_rsp_rip() */

	unsigned long cr0;
	unsigned long cr2;
	unsigned long cr3;
	unsigned long cr4;
	unsigned long cr8;
	u64 pdptrs[4]; /* pae */
	u64 shadow_efer;
	u64 apic_base;
	int nmsrs;
	struct vmx_msr_entry *guest_msrs;
	struct vmx_msr_entry *host_msrs;

	struct list_head free_pages;
	struct kvm_mmu_page page_header_buf[KVM_NUM_MMU_PAGES];
	struct kvm_mmu mmu;

	struct kvm_guest_debug guest_debug;

	char fx_buf[FX_BUF_SIZE];
	char *host_fx_image;
	char *guest_fx_image;

	int mmio_needed;
	int mmio_read_completed;
	int mmio_is_write;
	int mmio_size;
	unsigned char mmio_data[8];
	gpa_t mmio_phys_addr;

	struct {
		int active;
		u8 save_iopl;
		struct kvm_save_segment {
			u16 selector;
			unsigned long base;
			u32 limit;
			u32 ar;
		} tr, es, ds, fs, gs;
	} rmode;
};

struct kvm_memory_slot {
	gfn_t base_gfn;
	unsigned long npages;
	unsigned long flags;
	struct page **phys_mem;
	unsigned long *dirty_bitmap;
};

struct kvm {
	spinlock_t lock; /* protects everything except vcpus */
	int nmemslots;
	struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS];
	/*
	 * Hash table of struct kvm_mmu_page.
	 */
	struct list_head active_mmu_pages;
	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
	struct kvm_vcpu vcpus[KVM_MAX_VCPUS];
	int memory_config_version;
	int busy;
	unsigned long rmap_overflow;
};

struct kvm_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 request_irq_exits;
	u32 irq_exits;
};

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

struct kvm_arch_ops {
	int (*cpu_has_kvm_support)(void);          /* __init */
	int (*disabled_by_bios)(void);             /* __init */
	void (*hardware_enable)(void *dummy);      /* __init */
	void (*hardware_disable)(void *dummy);
	int (*hardware_setup)(void);               /* __init */
	void (*hardware_unsetup)(void);            /* __exit */

	int (*vcpu_create)(struct kvm_vcpu *vcpu);
	void (*vcpu_free)(struct kvm_vcpu *vcpu);

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

	int (*set_guest_debug)(struct kvm_vcpu *vcpu,
			       struct kvm_debug_guest *dbg);
	int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
	int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
	u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
	void (*get_segment)(struct kvm_vcpu *vcpu,
			    struct kvm_segment *var, int seg);
	void (*set_segment)(struct kvm_vcpu *vcpu,
			    struct kvm_segment *var, int seg);
	void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
	void (*decache_cr0_cr4_guest_bits)(struct kvm_vcpu *vcpu);
	void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
	void (*set_cr0_no_modeswitch)(struct kvm_vcpu *vcpu,
				      unsigned long cr0);
	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
	void (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4);
	void (*set_efer)(struct kvm_vcpu *vcpu, u64 efer);
	void (*get_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
	void (*set_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
	void (*get_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
	void (*set_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
	unsigned long (*get_dr)(struct kvm_vcpu *vcpu, int dr);
	void (*set_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long value,
		       int *exception);
	void (*cache_regs)(struct kvm_vcpu *vcpu);
	void (*decache_regs)(struct kvm_vcpu *vcpu);
	unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);

	void (*invlpg)(struct kvm_vcpu *vcpu, gva_t addr);
	void (*tlb_flush)(struct kvm_vcpu *vcpu);
	void (*inject_page_fault)(struct kvm_vcpu *vcpu,
				  unsigned long addr, u32 err_code);

	void (*inject_gp)(struct kvm_vcpu *vcpu, unsigned err_code);

	int (*run)(struct kvm_vcpu *vcpu, struct kvm_run *run);
	int (*vcpu_setup)(struct kvm_vcpu *vcpu);
	void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
};

extern struct kvm_stat kvm_stat;
extern struct kvm_arch_ops *kvm_arch_ops;

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

int kvm_init_arch(struct kvm_arch_ops *ops, struct module *module);
void kvm_exit_arch(void);

void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
int kvm_mmu_setup(struct kvm_vcpu *vcpu);

int kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);

hpa_t gpa_to_hpa(struct kvm_vcpu *vcpu, 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);

void kvm_emulator_want_group7_invlpg(void);

extern hpa_t bad_page_address;

static inline struct page *gfn_to_page(struct kvm_memory_slot *slot, gfn_t gfn)
{
	return slot->phys_mem[gfn - slot->base_gfn];
}

struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
void mark_page_dirty(struct kvm *kvm, gfn_t gfn);

enum emulation_result {
	EMULATE_DONE,       /* no further processing */
	EMULATE_DO_MMIO,      /* kvm_run filled with mmio request */
	EMULATE_FAIL,         /* can't emulate this instruction */
};

int emulate_instruction(struct kvm_vcpu *vcpu, struct kvm_run *run,
			unsigned long cr2, u16 error_code);
void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
		   unsigned long *rflags);

unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr);
void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long value,
		     unsigned long *rflags);

struct x86_emulate_ctxt;

int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address);
int emulate_clts(struct kvm_vcpu *vcpu);
int emulator_get_dr(struct x86_emulate_ctxt* ctxt, int dr,
		    unsigned long *dest);
int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr,
		    unsigned long value);

void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr0);
void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr0);
void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr0);
void lmsw(struct kvm_vcpu *vcpu, unsigned long msw);

int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data);

void fx_init(struct kvm_vcpu *vcpu);

void load_msrs(struct vmx_msr_entry *e, int n);
void save_msrs(struct vmx_msr_entry *e, int n);
void kvm_resched(struct kvm_vcpu *vcpu);

int kvm_read_guest(struct kvm_vcpu *vcpu,
	       gva_t addr,
	       unsigned long size,
	       void *dest);

int kvm_write_guest(struct kvm_vcpu *vcpu,
		gva_t addr,
		unsigned long size,
		void *data);

unsigned long segment_base(u16 selector);

void kvm_mmu_pre_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes);
void kvm_mmu_post_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes);

static inline struct page *_gfn_to_page(struct kvm *kvm, gfn_t gfn)
{
	struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
	return (slot) ? slot->phys_mem[gfn - slot->base_gfn] : NULL;
}

static inline int is_long_mode(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_X86_64
	return vcpu->shadow_efer & EFER_LME;
#else
	return 0;
#endif
}

static inline int is_pae(struct kvm_vcpu *vcpu)
{
	return vcpu->cr4 & CR4_PAE_MASK;
}

static inline int is_pse(struct kvm_vcpu *vcpu)
{
	return vcpu->cr4 & CR4_PSE_MASK;
}

static inline int is_paging(struct kvm_vcpu *vcpu)
{
	return vcpu->cr0 & CR0_PG_MASK;
}

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

static inline struct kvm_mmu_page *page_header(hpa_t shadow_page)
{
	struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT);

	return (struct kvm_mmu_page *)page->private;
}

static inline u16 read_fs(void)
{
	u16 seg;
	asm ("mov %%fs, %0" : "=g"(seg));
	return seg;
}

static inline u16 read_gs(void)
{
	u16 seg;
	asm ("mov %%gs, %0" : "=g"(seg));
	return seg;
}

static inline u16 read_ldt(void)
{
	u16 ldt;
	asm ("sldt %0" : "=g"(ldt));
	return ldt;
}

static inline void load_fs(u16 sel)
{
	asm ("mov %0, %%fs" : : "rm"(sel));
}

static inline void load_gs(u16 sel)
{
	asm ("mov %0, %%gs" : : "rm"(sel));
}

#ifndef load_ldt
static inline void load_ldt(u16 sel)
{
	asm ("lldt %0" : : "g"(sel));
}
#endif

static inline void get_idt(struct descriptor_table *table)
{
	asm ("sidt %0" : "=m"(*table));
}

static inline void get_gdt(struct descriptor_table *table)
{
	asm ("sgdt %0" : "=m"(*table));
}

static inline unsigned long read_tr_base(void)
{
	u16 tr;
	asm ("str %0" : "=g"(tr));
	return segment_base(tr);
}

#ifdef CONFIG_X86_64
static inline unsigned long read_msr(unsigned long msr)
{
	u64 value;

	rdmsrl(msr, value);
	return value;
}
#endif

static inline void fx_save(void *image)
{
	asm ("fxsave (%0)":: "r" (image));
}

static inline void fx_restore(void *image)
{
	asm ("fxrstor (%0)":: "r" (image));
}

static inline void fpu_init(void)
{
	asm ("finit");
}

static inline u32 get_rdx_init_val(void)
{
	return 0x600; /* P6 family */
}

#define ASM_VMX_VMCLEAR_RAX       ".byte 0x66, 0x0f, 0xc7, 0x30"
#define ASM_VMX_VMLAUNCH          ".byte 0x0f, 0x01, 0xc2"
#define ASM_VMX_VMRESUME          ".byte 0x0f, 0x01, 0xc3"
#define ASM_VMX_VMPTRLD_RAX       ".byte 0x0f, 0xc7, 0x30"
#define ASM_VMX_VMREAD_RDX_RAX    ".byte 0x0f, 0x78, 0xd0"
#define ASM_VMX_VMWRITE_RAX_RDX   ".byte 0x0f, 0x79, 0xd0"
#define ASM_VMX_VMWRITE_RSP_RDX   ".byte 0x0f, 0x79, 0xd4"
#define ASM_VMX_VMXOFF            ".byte 0x0f, 0x01, 0xc4"
#define ASM_VMX_VMXON_RAX         ".byte 0xf3, 0x0f, 0xc7, 0x30"

#define MSR_IA32_TIME_STAMP_COUNTER		0x010

#define TSS_IOPB_BASE_OFFSET 0x66
#define TSS_BASE_SIZE 0x68
#define TSS_IOPB_SIZE (65536 / 8)
#define TSS_REDIRECTION_SIZE (256 / 8)
#define RMODE_TSS_SIZE (TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1)

#endif
Commit	Line	Data
6aa8b732 AK	1	#ifndef __KVM_H
	2	#define __KVM_H
	3
	4	/*
	5	* This work is licensed under the terms of the GNU GPL, version 2. See
	6	* the COPYING file in the top-level directory.
	7	*/
	8
	9	#include <linux/types.h>
	10	#include <linux/list.h>
	11	#include <linux/mutex.h>
	12	#include <linux/spinlock.h>
	13	#include <linux/mm.h>
	14
	15	#include "vmx.h"
	16	#include <linux/kvm.h>
	17
	18	#define CR0_PE_MASK (1ULL << 0)
	19	#define CR0_TS_MASK (1ULL << 3)
	20	#define CR0_NE_MASK (1ULL << 5)
	21	#define CR0_WP_MASK (1ULL << 16)
	22	#define CR0_NW_MASK (1ULL << 29)
	23	#define CR0_CD_MASK (1ULL << 30)
	24	#define CR0_PG_MASK (1ULL << 31)
	25
	26	#define CR3_WPT_MASK (1ULL << 3)
	27	#define CR3_PCD_MASK (1ULL << 4)
	28
	29	#define CR3_RESEVED_BITS 0x07ULL
	30	#define CR3_L_MODE_RESEVED_BITS (~((1ULL << 40) - 1) \| 0x0fe7ULL)
	31	#define CR3_FLAGS_MASK ((1ULL << 5) - 1)
	32
	33	#define CR4_VME_MASK (1ULL << 0)
	34	#define CR4_PSE_MASK (1ULL << 4)
	35	#define CR4_PAE_MASK (1ULL << 5)
	36	#define CR4_PGE_MASK (1ULL << 7)
	37	#define CR4_VMXE_MASK (1ULL << 13)
	38
	39	#define KVM_GUEST_CR0_MASK \
	40	(CR0_PG_MASK \| CR0_PE_MASK \| CR0_WP_MASK \| CR0_NE_MASK \
	41	\| CR0_NW_MASK \| CR0_CD_MASK)
	42	#define KVM_VM_CR0_ALWAYS_ON \
	43	(CR0_PG_MASK \| CR0_PE_MASK \| CR0_WP_MASK \| CR0_NE_MASK)
	44	#define KVM_GUEST_CR4_MASK \
	45	(CR4_PSE_MASK \| CR4_PAE_MASK \| CR4_PGE_MASK \| CR4_VMXE_MASK \| CR4_VME_MASK)
	46	#define KVM_PMODE_VM_CR4_ALWAYS_ON (CR4_VMXE_MASK \| CR4_PAE_MASK)
	47	#define KVM_RMODE_VM_CR4_ALWAYS_ON (CR4_VMXE_MASK \| CR4_PAE_MASK \| CR4_VME_MASK)
	48
	49	#define INVALID_PAGE (~(hpa_t)0)
	50	#define UNMAPPED_GVA (~(gpa_t)0)
	51
	52	#define KVM_MAX_VCPUS 1
	53	#define KVM_MEMORY_SLOTS 4
	54	#define KVM_NUM_MMU_PAGES 256
	55
	56	#define FX_IMAGE_SIZE 512
	57	#define FX_IMAGE_ALIGN 16
	58	#define FX_BUF_SIZE (2 * FX_IMAGE_SIZE + FX_IMAGE_ALIGN)
	59
	60	#define DE_VECTOR 0
	61	#define DF_VECTOR 8
	62	#define TS_VECTOR 10
	63	#define NP_VECTOR 11
	64	#define SS_VECTOR 12
65	#define GP_VECTOR 13
66	#define PF_VECTOR 14
67
68	#define SELECTOR_TI_MASK (1 << 2)
69	#define SELECTOR_RPL_MASK 0x03
70
71	#define IOPL_SHIFT 12
72
73	/*
74	* Address types:
75	*
76	* gva - guest virtual address
77	* gpa - guest physical address
78	* gfn - guest frame number
79	* hva - host virtual address
80	* hpa - host physical address
81	* hfn - host frame number
82	*/
83
84	typedef unsigned long gva_t;
85	typedef u64 gpa_t;
86	typedef unsigned long gfn_t;
87
88	typedef unsigned long hva_t;
89	typedef u64 hpa_t;
90	typedef unsigned long hfn_t;
91
cea0f0e7 AK	92	#define NR_PTE_CHAIN_ENTRIES 5
	93
	94	struct kvm_pte_chain {
	95	u64 *parent_ptes[NR_PTE_CHAIN_ENTRIES];
	96	struct hlist_node link;
	97	};
	98
	99	/*
	100	* kvm_mmu_page_role, below, is defined as:
	101	*
	102	* bits 0:3 - total guest paging levels (2-4, or zero for real mode)
	103	* bits 4:7 - page table level for this shadow (1-4)
	104	* bits 8:9 - page table quadrant for 2-level guests
	105	* bit 16 - "metaphysical" - gfn is not a real page (huge page/real mode)
	106	*/
	107	union kvm_mmu_page_role {
	108	unsigned word;
	109	struct {
	110	unsigned glevels : 4;
	111	unsigned level : 4;
	112	unsigned quadrant : 2;
	113	unsigned pad_for_nice_hex_output : 6;
	114	unsigned metaphysical : 1;
	115	};
	116	};
	117
6aa8b732 AK	118	struct kvm_mmu_page {
6aa8b732 AK	119	struct list_head link;
cea0f0e7 AK	120	struct hlist_node hash_link;
	121
	122	/*
	123	* The following two entries are used to key the shadow page in the
	124	* hash table.
	125	*/
	126	gfn_t gfn;
	127	union kvm_mmu_page_role role;
	128
6aa8b732 AK	129	hpa_t page_hpa;
	130	unsigned long slot_bitmap; /* One bit set per slot which has memory
	131	* in this shadow page.
	132	*/
	133	int global; /* Set if all ptes in this page are global */
cea0f0e7 AK	134	int multimapped; /* More than one parent_pte? */
	135	union {
	136	u64 parent_pte; / !multimapped */
	137	struct hlist_head parent_ptes; /* multimapped, kvm_pte_chain */
	138	};
6aa8b732 AK	139	};
	140
	141	struct vmcs {
	142	u32 revision_id;
	143	u32 abort;
	144	char data[0];
	145	};
	146
	147	#define vmx_msr_entry kvm_msr_entry
	148
	149	struct kvm_vcpu;
	150
	151	/*
	152	* x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level
	153	* 32-bit). The kvm_mmu structure abstracts the details of the current mmu
	154	* mode.
	155	*/
	156	struct kvm_mmu {
	157	void (new_cr3)(struct kvm_vcpu vcpu);
	158	int (page_fault)(struct kvm_vcpu vcpu, gva_t gva, u32 err);
	159	void (inval_page)(struct kvm_vcpu vcpu, gva_t gva);
	160	void (free)(struct kvm_vcpu vcpu);
	161	gpa_t (gva_to_gpa)(struct kvm_vcpu vcpu, gva_t gva);
	162	hpa_t root_hpa;
	163	int root_level;
	164	int shadow_root_level;
17ac10ad AK	165
17ac10ad AK	166	u64 *pae_root;
6aa8b732 AK	167	};
	168
	169	struct kvm_guest_debug {
	170	int enabled;
	171	unsigned long bp[4];
	172	int singlestep;
	173	};
	174
	175	enum {
	176	VCPU_REGS_RAX = 0,
	177	VCPU_REGS_RCX = 1,
	178	VCPU_REGS_RDX = 2,
	179	VCPU_REGS_RBX = 3,
	180	VCPU_REGS_RSP = 4,
	181	VCPU_REGS_RBP = 5,
	182	VCPU_REGS_RSI = 6,
	183	VCPU_REGS_RDI = 7,
05b3e0c2	184	#ifdef CONFIG_X86_64
6aa8b732 AK	185	VCPU_REGS_R8 = 8,
	186	VCPU_REGS_R9 = 9,
	187	VCPU_REGS_R10 = 10,
	188	VCPU_REGS_R11 = 11,
	189	VCPU_REGS_R12 = 12,
	190	VCPU_REGS_R13 = 13,
	191	VCPU_REGS_R14 = 14,
	192	VCPU_REGS_R15 = 15,
	193	#endif
	194	NR_VCPU_REGS
	195	};
	196
	197	enum {
	198	VCPU_SREG_CS,
	199	VCPU_SREG_DS,
	200	VCPU_SREG_ES,
	201	VCPU_SREG_FS,
	202	VCPU_SREG_GS,
	203	VCPU_SREG_SS,
	204	VCPU_SREG_TR,
	205	VCPU_SREG_LDTR,
	206	};
	207
	208	struct kvm_vcpu {
	209	struct kvm *kvm;
	210	union {
	211	struct vmcs *vmcs;
	212	struct vcpu_svm *svm;
	213	};
	214	struct mutex mutex;
	215	int cpu;
	216	int launched;
c1150d8c	217	int interrupt_window_open;
6aa8b732 AK	218	unsigned long irq_summary; /* bit vector: 1 per word in irq_pending */
	219	#define NR_IRQ_WORDS KVM_IRQ_BITMAP_SIZE(unsigned long)
	220	unsigned long irq_pending[NR_IRQ_WORDS];
	221	unsigned long regs[NR_VCPU_REGS]; /* for rsp: vcpu_load_rsp_rip() */
	222	unsigned long rip; /* needs vcpu_load_rsp_rip() */
	223
	224	unsigned long cr0;
	225	unsigned long cr2;
	226	unsigned long cr3;
	227	unsigned long cr4;
	228	unsigned long cr8;
1342d353	229	u64 pdptrs[4]; /* pae */
6aa8b732 AK	230	u64 shadow_efer;
	231	u64 apic_base;
	232	int nmsrs;
	233	struct vmx_msr_entry *guest_msrs;
	234	struct vmx_msr_entry *host_msrs;
	235
	236	struct list_head free_pages;
	237	struct kvm_mmu_page page_header_buf[KVM_NUM_MMU_PAGES];
	238	struct kvm_mmu mmu;
	239
	240	struct kvm_guest_debug guest_debug;
	241
	242	char fx_buf[FX_BUF_SIZE];
	243	char *host_fx_image;
	244	char *guest_fx_image;
	245
	246	int mmio_needed;
	247	int mmio_read_completed;
	248	int mmio_is_write;
	249	int mmio_size;
	250	unsigned char mmio_data[8];
	251	gpa_t mmio_phys_addr;
	252
	253	struct {
	254	int active;
	255	u8 save_iopl;
	256	struct kvm_save_segment {
	257	u16 selector;
	258	unsigned long base;
	259	u32 limit;
	260	u32 ar;
	261	} tr, es, ds, fs, gs;
	262	} rmode;
	263	};
	264
	265	struct kvm_memory_slot {
	266	gfn_t base_gfn;
	267	unsigned long npages;
	268	unsigned long flags;
	269	struct page **phys_mem;
	270	unsigned long *dirty_bitmap;
	271	};
	272
	273	struct kvm {
	274	spinlock_t lock; /* protects everything except vcpus */
	275	int nmemslots;
	276	struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS];
cea0f0e7 AK	277	/*
	278	* Hash table of struct kvm_mmu_page.
	279	*/
6aa8b732	280	struct list_head active_mmu_pages;
cea0f0e7	281	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
6aa8b732 AK	282	struct kvm_vcpu vcpus[KVM_MAX_VCPUS];
	283	int memory_config_version;
	284	int busy;
cd4a4e53	285	unsigned long rmap_overflow;
6aa8b732 AK	286	};
	287
	288	struct kvm_stat {
	289	u32 pf_fixed;
	290	u32 pf_guest;
	291	u32 tlb_flush;
	292	u32 invlpg;
	293
	294	u32 exits;
	295	u32 io_exits;
	296	u32 mmio_exits;
	297	u32 signal_exits;
c1150d8c DL	298	u32 irq_window_exits;
	299	u32 halt_exits;
	300	u32 request_irq_exits;
6aa8b732 AK	301	u32 irq_exits;
	302	};
	303
	304	struct descriptor_table {
	305	u16 limit;
	306	unsigned long base;
	307	} __attribute__((packed));
	308
	309	struct kvm_arch_ops {
	310	int (cpu_has_kvm_support)(void); / __init */
	311	int (disabled_by_bios)(void); / __init */
	312	void (hardware_enable)(void dummy); /* __init */
	313	void (hardware_disable)(void dummy);
	314	int (hardware_setup)(void); / __init */
	315	void (hardware_unsetup)(void); / __exit */
	316
	317	int (vcpu_create)(struct kvm_vcpu vcpu);
	318	void (vcpu_free)(struct kvm_vcpu vcpu);
	319
	320	struct kvm_vcpu (vcpu_load)(struct kvm_vcpu *vcpu);
	321	void (vcpu_put)(struct kvm_vcpu vcpu);
	322
	323	int (set_guest_debug)(struct kvm_vcpu vcpu,
	324	struct kvm_debug_guest *dbg);
	325	int (get_msr)(struct kvm_vcpu vcpu, u32 msr_index, u64 *pdata);
	326	int (set_msr)(struct kvm_vcpu vcpu, u32 msr_index, u64 data);
	327	u64 (get_segment_base)(struct kvm_vcpu vcpu, int seg);
	328	void (get_segment)(struct kvm_vcpu vcpu,
	329	struct kvm_segment *var, int seg);
	330	void (set_segment)(struct kvm_vcpu vcpu,
	331	struct kvm_segment *var, int seg);
6aa8b732	332	void (get_cs_db_l_bits)(struct kvm_vcpu vcpu, int db, int l);
399badf3	333	void (decache_cr0_cr4_guest_bits)(struct kvm_vcpu vcpu);
6aa8b732 AK	334	void (set_cr0)(struct kvm_vcpu vcpu, unsigned long cr0);
	335	void (set_cr0_no_modeswitch)(struct kvm_vcpu vcpu,
	336	unsigned long cr0);
	337	void (set_cr3)(struct kvm_vcpu vcpu, unsigned long cr3);
	338	void (set_cr4)(struct kvm_vcpu vcpu, unsigned long cr4);
	339	void (set_efer)(struct kvm_vcpu vcpu, u64 efer);
	340	void (get_idt)(struct kvm_vcpu vcpu, struct descriptor_table *dt);
	341	void (set_idt)(struct kvm_vcpu vcpu, struct descriptor_table *dt);
	342	void (get_gdt)(struct kvm_vcpu vcpu, struct descriptor_table *dt);
	343	void (set_gdt)(struct kvm_vcpu vcpu, struct descriptor_table *dt);
	344	unsigned long (get_dr)(struct kvm_vcpu vcpu, int dr);
	345	void (set_dr)(struct kvm_vcpu vcpu, int dr, unsigned long value,
	346	int *exception);
	347	void (cache_regs)(struct kvm_vcpu vcpu);
	348	void (decache_regs)(struct kvm_vcpu vcpu);
	349	unsigned long (get_rflags)(struct kvm_vcpu vcpu);
	350	void (set_rflags)(struct kvm_vcpu vcpu, unsigned long rflags);
	351
	352	void (invlpg)(struct kvm_vcpu vcpu, gva_t addr);
	353	void (tlb_flush)(struct kvm_vcpu vcpu);
	354	void (inject_page_fault)(struct kvm_vcpu vcpu,
	355	unsigned long addr, u32 err_code);
	356
	357	void (inject_gp)(struct kvm_vcpu vcpu, unsigned err_code);
	358
	359	int (run)(struct kvm_vcpu vcpu, struct kvm_run *run);
	360	int (vcpu_setup)(struct kvm_vcpu vcpu);
	361	void (skip_emulated_instruction)(struct kvm_vcpu vcpu);
	362	};
	363
	364	extern struct kvm_stat kvm_stat;
	365	extern struct kvm_arch_ops *kvm_arch_ops;
	366
	367	#define kvm_printf(kvm, fmt ...) printk(KERN_DEBUG fmt)
	368	#define vcpu_printf(vcpu, fmt...) kvm_printf(vcpu->kvm, fmt)
	369
	370	int kvm_init_arch(struct kvm_arch_ops ops, struct module module);
	371	void kvm_exit_arch(void);
	372
	373	void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
8018c27b IM	374	int kvm_mmu_create(struct kvm_vcpu *vcpu);
8018c27b IM	375	int kvm_mmu_setup(struct kvm_vcpu *vcpu);
6aa8b732 AK	376
	377	int kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
	378	void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);
	379
	380	hpa_t gpa_to_hpa(struct kvm_vcpu *vcpu, gpa_t gpa);
	381	#define HPA_MSB ((sizeof(hpa_t) * 8) - 1)
	382	#define HPA_ERR_MASK ((hpa_t)1 << HPA_MSB)
	383	static inline int is_error_hpa(hpa_t hpa) { return hpa >> HPA_MSB; }
	384	hpa_t gva_to_hpa(struct kvm_vcpu *vcpu, gva_t gva);
	385
	386	void kvm_emulator_want_group7_invlpg(void);
	387
	388	extern hpa_t bad_page_address;
	389
	390	static inline struct page gfn_to_page(struct kvm_memory_slot slot, gfn_t gfn)
	391	{
	392	return slot->phys_mem[gfn - slot->base_gfn];
	393	}
	394
	395	struct kvm_memory_slot gfn_to_memslot(struct kvm kvm, gfn_t gfn);
	396	void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
	397
	398	enum emulation_result {
	399	EMULATE_DONE, /* no further processing */
	400	EMULATE_DO_MMIO, /* kvm_run filled with mmio request */
	401	EMULATE_FAIL, /* can't emulate this instruction */
	402	};
	403
	404	int emulate_instruction(struct kvm_vcpu vcpu, struct kvm_run run,
	405	unsigned long cr2, u16 error_code);
	406	void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
	407	void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
	408	void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
	409	unsigned long *rflags);
	410
	411	unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr);
	412	void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long value,
	413	unsigned long *rflags);
	414
	415	struct x86_emulate_ctxt;
	416
	417	int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address);
	418	int emulate_clts(struct kvm_vcpu *vcpu);
	419	int emulator_get_dr(struct x86_emulate_ctxt* ctxt, int dr,
	420	unsigned long *dest);
	421	int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr,
	422	unsigned long value);
	423
	424	void set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
	425	void set_cr3(struct kvm_vcpu *vcpu, unsigned long cr0);
	426	void set_cr4(struct kvm_vcpu *vcpu, unsigned long cr0);
	427	void set_cr8(struct kvm_vcpu *vcpu, unsigned long cr0);
	428	void lmsw(struct kvm_vcpu *vcpu, unsigned long msw);
	429
3bab1f5d AK	430	int kvm_get_msr_common(struct kvm_vcpu vcpu, u32 msr, u64 pdata);
3bab1f5d AK	431	int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data);
6aa8b732 AK	432
	433	void fx_init(struct kvm_vcpu *vcpu);
	434
	435	void load_msrs(struct vmx_msr_entry *e, int n);
	436	void save_msrs(struct vmx_msr_entry *e, int n);
	437	void kvm_resched(struct kvm_vcpu *vcpu);
	438
	439	int kvm_read_guest(struct kvm_vcpu *vcpu,
	440	gva_t addr,
	441	unsigned long size,
	442	void *dest);
	443
	444	int kvm_write_guest(struct kvm_vcpu *vcpu,
	445	gva_t addr,
	446	unsigned long size,
	447	void *data);
	448
	449	unsigned long segment_base(u16 selector);
	450
da4a00f0 AK	451	void kvm_mmu_pre_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes);
	452	void kvm_mmu_post_write(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes);
	453
6aa8b732 AK	454	static inline struct page _gfn_to_page(struct kvm kvm, gfn_t gfn)
	455	{
	456	struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
	457	return (slot) ? slot->phys_mem[gfn - slot->base_gfn] : NULL;
	458	}
	459
a9058ecd AK	460	static inline int is_long_mode(struct kvm_vcpu *vcpu)
	461	{
	462	#ifdef CONFIG_X86_64
	463	return vcpu->shadow_efer & EFER_LME;
	464	#else
	465	return 0;
	466	#endif
	467	}
	468
6aa8b732 AK	469	static inline int is_pae(struct kvm_vcpu *vcpu)
	470	{
	471	return vcpu->cr4 & CR4_PAE_MASK;
	472	}
	473
	474	static inline int is_pse(struct kvm_vcpu *vcpu)
	475	{
	476	return vcpu->cr4 & CR4_PSE_MASK;
	477	}
	478
	479	static inline int is_paging(struct kvm_vcpu *vcpu)
	480	{
	481	return vcpu->cr0 & CR0_PG_MASK;
	482	}
	483
	484	static inline int memslot_id(struct kvm kvm, struct kvm_memory_slot slot)
	485	{
	486	return slot - kvm->memslots;
	487	}
	488
	489	static inline struct kvm_mmu_page *page_header(hpa_t shadow_page)
	490	{
	491	struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT);
	492
	493	return (struct kvm_mmu_page *)page->private;
	494	}
	495
	496	static inline u16 read_fs(void)
	497	{
	498	u16 seg;
	499	asm ("mov %%fs, %0" : "=g"(seg));
	500	return seg;
	501	}
	502
	503	static inline u16 read_gs(void)
	504	{
	505	u16 seg;
	506	asm ("mov %%gs, %0" : "=g"(seg));
	507	return seg;
	508	}
	509
	510	static inline u16 read_ldt(void)
	511	{
	512	u16 ldt;
	513	asm ("sldt %0" : "=g"(ldt));
	514	return ldt;
	515	}
	516
	517	static inline void load_fs(u16 sel)
	518	{
	519	asm ("mov %0, %%fs" : : "rm"(sel));
	520	}
	521
	522	static inline void load_gs(u16 sel)
	523	{
	524	asm ("mov %0, %%gs" : : "rm"(sel));
	525	}
	526
	527	#ifndef load_ldt
	528	static inline void load_ldt(u16 sel)
	529	{
	530	asm ("lldt %0" : : "g"(sel));
	531	}
	532	#endif
533
534	static inline void get_idt(struct descriptor_table *table)
535	{
536	asm ("sidt %0" : "=m"(*table));
537	}
538
539	static inline void get_gdt(struct descriptor_table *table)
540	{
541	asm ("sgdt %0" : "=m"(*table));
542	}
543
544	static inline unsigned long read_tr_base(void)
545	{
546	u16 tr;
547	asm ("str %0" : "=g"(tr));
548	return segment_base(tr);
549	}
550
05b3e0c2	551	#ifdef CONFIG_X86_64
6aa8b732 AK	552	static inline unsigned long read_msr(unsigned long msr)
	553	{
	554	u64 value;
	555
	556	rdmsrl(msr, value);
	557	return value;
	558	}
	559	#endif
	560
	561	static inline void fx_save(void *image)
	562	{
	563	asm ("fxsave (%0)":: "r" (image));
	564	}
	565
	566	static inline void fx_restore(void *image)
	567	{
	568	asm ("fxrstor (%0)":: "r" (image));
	569	}
	570
	571	static inline void fpu_init(void)
	572	{
	573	asm ("finit");
	574	}
	575
	576	static inline u32 get_rdx_init_val(void)
	577	{
	578	return 0x600; /* P6 family */
	579	}
	580
	581	#define ASM_VMX_VMCLEAR_RAX ".byte 0x66, 0x0f, 0xc7, 0x30"
	582	#define ASM_VMX_VMLAUNCH ".byte 0x0f, 0x01, 0xc2"
	583	#define ASM_VMX_VMRESUME ".byte 0x0f, 0x01, 0xc3"
	584	#define ASM_VMX_VMPTRLD_RAX ".byte 0x0f, 0xc7, 0x30"
	585	#define ASM_VMX_VMREAD_RDX_RAX ".byte 0x0f, 0x78, 0xd0"
	586	#define ASM_VMX_VMWRITE_RAX_RDX ".byte 0x0f, 0x79, 0xd0"
	587	#define ASM_VMX_VMWRITE_RSP_RDX ".byte 0x0f, 0x79, 0xd4"
	588	#define ASM_VMX_VMXOFF ".byte 0x0f, 0x01, 0xc4"
	589	#define ASM_VMX_VMXON_RAX ".byte 0xf3, 0x0f, 0xc7, 0x30"
	590
	591	#define MSR_IA32_TIME_STAMP_COUNTER 0x010
	592
	593	#define TSS_IOPB_BASE_OFFSET 0x66
	594	#define TSS_BASE_SIZE 0x68
	595	#define TSS_IOPB_SIZE (65536 / 8)
	596	#define TSS_REDIRECTION_SIZE (256 / 8)
	597	#define RMODE_TSS_SIZE (TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1)
	598
6aa8b732	599	#endif