kvm.h

来自「linux 内核源代码」· C头文件 代码 · 共 797 行 · 第 1/2 页

#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/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 CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1)
#define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD))
#define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS|0xFFFFFF0000000000ULL)

#define KVM_GUEST_CR0_MASK \
	(X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE \
	 | X86_CR0_NW | X86_CR0_CD)
#define KVM_VM_CR0_ALWAYS_ON \
	(X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE | X86_CR0_TS \
	 | X86_CR0_MP)
#define KVM_GUEST_CR4_MASK \
	(X86_CR4_VME | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_PGE | X86_CR4_VMXE)
#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)

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

#define KVM_MAX_VCPUS 4
#define KVM_ALIAS_SLOTS 4
#define KVM_MEMORY_SLOTS 8
#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 DE_VECTOR 0
#define NM_VECTOR 7
#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

#define KVM_PIO_PAGE_OFFSET 1

/*
 * vcpu->requests bit members
 */
#define KVM_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;
	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);
	hpa_t root_hpa;
	int root_level;
	int shadow_root_level;

	u64 *pae_root;
};

#define KVM_NR_MEM_OBJS 20

struct kvm_mmu_memory_cache {
	int nobjs;
	void *objects[KVM_NR_MEM_OBJS];
};

/*
 * 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_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_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_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 light_exits;
	u32 efer_reload;
};

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);

struct kvm_vcpu {
	struct kvm *kvm;
	struct preempt_notifier preempt_notifier;
	int vcpu_id;
	struct mutex mutex;
	int   cpu;
	u64 host_tsc;
	struct kvm_run *run;
	int interrupt_window_open;
	int guest_mode;
	unsigned long requests;
	unsigned long irq_summary; /* bit vector: 1 per word in irq_pending */
	DECLARE_BITMAP(irq_pending, KVM_NR_INTERRUPTS);
	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;
	gpa_t para_state_gpa;
	struct page *para_state_page;
	gpa_t hypercall_gpa;
	unsigned long cr4;
	unsigned long cr8;
	u64 pdptrs[4]; /* pae */
	u64 shadow_efer;
	u64 apic_base;
	struct kvm_lapic *apic;    /* kernel irqchip context */
#define VCPU_MP_STATE_RUNNABLE          0
#define VCPU_MP_STATE_UNINITIALIZED     1
#define VCPU_MP_STATE_INIT_RECEIVED     2
#define VCPU_MP_STATE_SIPI_RECEIVED     3
#define VCPU_MP_STATE_HALTED            4
	int mp_state;
	int sipi_vector;
	u64 ia32_misc_enable_msr;

	struct kvm_mmu mmu;

	struct kvm_mmu_memory_cache mmu_pte_chain_cache;
	struct kvm_mmu_memory_cache mmu_rmap_desc_cache;
	struct kvm_mmu_memory_cache mmu_page_cache;
	struct kvm_mmu_memory_cache mmu_page_header_cache;

	gfn_t last_pt_write_gfn;
	int   last_pt_write_count;

	struct kvm_guest_debug guest_debug;

	struct i387_fxsave_struct host_fx_image;
	struct i387_fxsave_struct guest_fx_image;
	int fpu_active;
	int guest_fpu_loaded;

	int mmio_needed;
	int mmio_read_completed;
	int mmio_is_write;
	int mmio_size;
	unsigned char mmio_data[8];
	gpa_t mmio_phys_addr;
	gva_t mmio_fault_cr2;
	struct kvm_pio_request pio;
	void *pio_data;
	wait_queue_head_t wq;

	int sigset_active;
	sigset_t sigset;

	struct kvm_stat stat;

	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;
	int halt_request; /* real mode on Intel only */

	int cpuid_nent;
	struct kvm_cpuid_entry cpuid_entries[KVM_MAX_CPUID_ENTRIES];
};

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;
	struct page **phys_mem;
	unsigned long *dirty_bitmap;
};