path: root/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>
#include <linux/kvm_para.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 KVM_MIN_FREE_MMU_PAGES 5
#define KVM_REFILL_PAGES 25

#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? */
	int root_count;          /* Currently serving as active root */
	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 (*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_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;
	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;
	u64 ia32_misc_enable_msr;
	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_mmu_memory_cache mmu_pte_chain_cache;
	struct kvm_mmu_memory_cache mmu_rmap_desc_cache;

	gfn_t last_pt_write_gfn;
	int   last_pt_write_count;

	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;
	int n_free_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 list_head vm_list;
	struct file *filp;
};

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;
	</