path: root/arch/x86/include/asm/kvm_host.h

/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * This header defines architecture specific interfaces, x86 version
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 */

#ifndef _ASM_X86_KVM_HOST_H
#define _ASM_X86_KVM_HOST_H

#include <linux/types.h>
#include <linux/mm.h>
#include <linux/mmu_notifier.h>

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

#include <asm/pvclock-abi.h>
#include <asm/desc.h>

#define KVM_MAX_VCPUS 16
#define KVM_MEMORY_SLOTS 32
/* memory slots that does not exposed to userspace */
#define KVM_PRIVATE_MEM_SLOTS 4

#define KVM_PIO_PAGE_OFFSET 1
#define KVM_COALESCED_MMIO_PAGE_OFFSET 2

#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)

/* shadow tables are PAE even on non-PAE hosts */
#define KVM_HPAGE_SHIFT 21
#define KVM_HPAGE_SIZE (1UL << KVM_HPAGE_SHIFT)
#define KVM_HPAGE_MASK (~(KVM_HPAGE_SIZE - 1))

#define KVM_PAGES_PER_HPAGE (KVM_HPAGE_SIZE / PAGE_SIZE)

#define DE_VECTOR 0
#define DB_VECTOR 1
#define BP_VECTOR 3
#define OF_VECTOR 4
#define BR_VECTOR 5
#define UD_VECTOR 6
#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 MF_VECTOR 16
#define MC_VECTOR 18

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

#define IOPL_SHIFT 12

#define KVM_ALIAS_SLOTS 4

#define KVM_PERMILLE_MMU_PAGES 20
#define KVM_MIN_ALLOC_MMU_PAGES 64
#define KVM_MMU_HASH_SHIFT 10
#define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
#define KVM_MIN_FREE_MMU_PAGES 5
#define KVM_REFILL_PAGES 25
#define KVM_MAX_CPUID_ENTRIES 40
#define KVM_NR_VAR_MTRR 8

extern spinlock_t kvm_lock;
extern struct list_head vm_list;

struct kvm_vcpu;
struct kvm;

enum kvm_reg {
	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
	VCPU_REGS_RIP,
	NR_VCPU_REGS
};

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

#include <asm/kvm_x86_emulate.h>

#define KVM_NR_MEM_OBJS 40

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

/*
 * 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];
};

#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 - common access permissions for all ptes in this shadow page
 */
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 access:3;
		unsigned invalid: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;

	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 */
	bool unsync;
	bool unsync_children;
	union {
		u64 *parent_pte;               /* !multimapped */
		struct hlist_head parent_ptes; /* multimapped, kvm_pte_chain */
	};
	DECLARE_BITMAP(unsync_child_bitmap, 512);
};

struct kvm_pv_mmu_op_buffer {
	void *ptr;
	unsigned len;
	unsigned processed;
	char buf[512] __aligned(sizeof(long));
};

/*
 * 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);
	int (*sync_page)(struct kvm_vcpu *vcpu,
			 struct kvm_mmu_page *sp);
	void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva);
	hpa_t root_hpa;
	int root_level;
	int shadow_root_level;

	u64 *pae_root;
};

struct kvm_vcpu_arch {
	u64 host_tsc;
	int interrupt_window_open;
	unsigned long irq_summary; /* bit vector: 1 per word in irq_pending */
	DECLARE_BITMAP(irq_pending, KVM_NR_INTERRUPTS);
	/*
	 * rip and regs accesses must go through
	 * kvm_{register,rip}_{read,write} functions.
	 */
	unsigned long regs[NR_VCPU_REGS];
	u32 regs_avail;
	u32 regs_dirty;

	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;
	struct kvm_lapic *apic;    /* kernel irqchip context */
	int mp_state;
	int sipi_vector;
	u64 ia32_misc_enable_msr;
	bool tpr_access_reporting;

	struct kvm_mmu mmu;
	/* only needed in kvm_pv_mmu_op() path, but it's hot so
	 * put it here to avoid allocation */
	struct kvm_pv_mmu_op_buffer mmu_op_buffer;

	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;
	u64  *last_pte_updated;
	gfn_t last_pte_gfn;

	struct {
		gfn_t gfn;	/* presumed gfn during guest pte update */
		pfn_t pfn;	/* pfn corresponding to that gfn */
		int largepage;
		unsigned long mmu_seq;
	} update_pte;

	struct i387_fxsave_struct host_fx_image;
	struct i387_fxsave_struct guest_fx_image;

	gva_t mmio_fault_cr2;
	struct kvm_pio_request pio;
	void *pio_data;

	struct kvm_queued_exception {
		bool pending;
		bool has_error_code;
		u8