#include <linux/types.h>
#include <linux/mm.h>
#include <linux/mmu_notifier.h>
+#include <linux/tracepoint.h>
#include <linux/kvm.h>
#include <linux/kvm_para.h>
#include <asm/pvclock-abi.h>
#include <asm/desc.h>
+#include <asm/mtrr.h>
+#include <asm/msr-index.h>
#define KVM_MAX_VCPUS 16
#define KVM_MEMORY_SLOTS 32
#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_GUEST_CR0_MASK_UNRESTRICTED_GUEST \
+ (X86_CR0_WP | X86_CR0_NE | X86_CR0_NW | X86_CR0_CD)
+#define KVM_GUEST_CR0_MASK \
+ (KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
+#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST \
+ (X86_CR0_WP | X86_CR0_NE | X86_CR0_TS | X86_CR0_MP)
#define KVM_VM_CR0_ALWAYS_ON \
- (X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE | X86_CR0_TS \
- | X86_CR0_MP)
+ (KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
#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 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)
+/* KVM Hugepage definitions for x86 */
+#define KVM_NR_PAGE_SIZES 3
+#define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + (((x) - 1) * 9))
+#define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x))
+#define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1))
+#define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE)
#define DE_VECTOR 0
#define DB_VECTOR 1
#define KVM_MIN_FREE_MMU_PAGES 5
#define KVM_REFILL_PAGES 25
#define KVM_MAX_CPUID_ENTRIES 40
+#define KVM_NR_FIXED_MTRR_REGION 88
#define KVM_NR_VAR_MTRR 8
extern spinlock_t kvm_lock;
NR_VCPU_REGS
};
+enum kvm_reg_ex {
+ VCPU_EXREG_PDPTR = NR_VCPU_REGS,
+};
+
enum {
VCPU_SREG_ES,
VCPU_SREG_CS,
VCPU_SREG_LDTR,
};
-#include <asm/kvm_x86_emulate.h>
+#include <asm/kvm_emulate.h>
#define KVM_NR_MEM_OBJS 40
-struct kvm_guest_debug {
- int enabled;
- unsigned long bp[4];
- int singlestep;
-};
+#define KVM_NR_DB_REGS 4
+
+#define DR6_BD (1 << 13)
+#define DR6_BS (1 << 14)
+#define DR6_FIXED_1 0xffff0ff0
+#define DR6_VOLATILE 0x0000e00f
+
+#define DR7_BP_EN_MASK 0x000000ff
+#define DR7_GE (1 << 9)
+#define DR7_GD (1 << 13)
+#define DR7_FIXED_1 0x00000400
+#define DR7_VOLATILE 0xffff23ff
/*
* We don't want allocation failures within the mmu code, so we preallocate
* 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)
+ * bit 16 - direct mapping of virtual to physical mapping at gfn
+ * used for real mode and two-dimensional paging
* bits 17:19 - common access permissions for all ptes in this shadow page
*/
union kvm_mmu_page_role {
unsigned level:4;
unsigned quadrant:2;
unsigned pad_for_nice_hex_output:6;
- unsigned metaphysical:1;
+ unsigned direct:1;
unsigned access:3;
unsigned invalid:1;
+ unsigned cr4_pge:1;
+ unsigned nxe:1;
};
};
struct list_head link;
struct hlist_node hash_link;
+ struct list_head oos_link;
+
/*
* The following two entries are used to key the shadow page in the
* hash table.
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.
- */
+ /*
+ * One bit set per slot which has memory
+ * in this shadow page.
+ */
+ DECLARE_BITMAP(slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS);
int multimapped; /* More than one parent_pte? */
int root_count; /* Currently serving as active root */
bool unsync;
- bool unsync_children;
+ unsigned int unsync_children;
union {
u64 *parent_pte; /* !multimapped */
struct hlist_head parent_ptes; /* multimapped, kvm_pte_chain */
char buf[512] __aligned(sizeof(long));
};
+struct kvm_pio_request {
+ unsigned long count;
+ int cur_count;
+ gva_t guest_gva;
+ int in;
+ int port;
+ int size;
+ int string;
+ int down;
+ int rep;
+};
+
/*
* 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
hpa_t root_hpa;
int root_level;
int shadow_root_level;
+ union kvm_mmu_page_role base_role;
u64 *pae_root;
+ u64 rsvd_bits_mask[2][4];
};
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 cr3;
unsigned long cr4;
unsigned long cr8;
+ u32 hflags;
u64 pdptrs[4]; /* pae */
u64 shadow_efer;
u64 apic_base;
struct kvm_lapic *apic; /* kernel irqchip context */
+ int32_t apic_arb_prio;
int mp_state;
int sipi_vector;
u64 ia32_misc_enable_msr;
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 kvm_pio_request pio;
void *pio_data;
+ u8 event_exit_inst_len;
+
struct kvm_queued_exception {
bool pending;
bool has_error_code;
struct kvm_queued_interrupt {
bool pending;
+ bool soft;
u8 nr;
} interrupt;
- 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;
unsigned int time_offset;
struct page *time_page;
+ bool singlestep; /* guest is single stepped by KVM */
bool nmi_pending;
bool nmi_injected;
- u64 mtrr[0x100];
+ struct mtrr_state_type mtrr_state;
+ u32 pat;
+
+ int switch_db_regs;
+ unsigned long db[KVM_NR_DB_REGS];
+ unsigned long dr6;
+ unsigned long dr7;
+ unsigned long eff_db[KVM_NR_DB_REGS];
+
+ u64 mcg_cap;
+ u64 mcg_status;
+ u64 mcg_ctl;
+ u64 *mce_banks;
};
struct kvm_mem_alias {
*/
struct list_head active_mmu_pages;
struct list_head assigned_dev_head;
- struct dmar_domain *intel_iommu_domain;
+ struct iommu_domain *iommu_domain;
+ int iommu_flags;
struct kvm_pic *vpic;
struct kvm_ioapic *vioapic;
struct kvm_pit *vpit;
struct hlist_head irq_ack_notifier_list;
+ int vapics_in_nmi_mode;
- int round_robin_prev_vcpu;
unsigned int tss_addr;
struct page *apic_access_page;
struct page *ept_identity_pagetable;
bool ept_identity_pagetable_done;
+ gpa_t ept_identity_map_addr;
unsigned long irq_sources_bitmap;
- unsigned long irq_states[KVM_IOAPIC_NUM_PINS];
+ u64 vm_init_tsc;
};
struct kvm_vm_stat {
u32 insn_emulation_fail;
u32 hypercalls;
u32 irq_injections;
+ u32 nmi_injections;
};
struct descriptor_table {
void (*vcpu_put)(struct kvm_vcpu *vcpu);
int (*set_guest_debug)(struct kvm_vcpu *vcpu,
- struct kvm_debug_guest *dbg);
- void (*guest_debug_pre)(struct kvm_vcpu *vcpu);
+ struct kvm_guest_debug *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 (*tlb_flush)(struct kvm_vcpu *vcpu);
- void (*run)(struct kvm_vcpu *vcpu, struct kvm_run *run);
- int (*handle_exit)(struct kvm_run *run, struct kvm_vcpu *vcpu);
+ void (*run)(struct kvm_vcpu *vcpu);
+ int (*handle_exit)(struct kvm_vcpu *vcpu);
void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
+ void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
+ u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask);
void (*patch_hypercall)(struct kvm_vcpu *vcpu,
unsigned char *hypercall_addr);
- int (*get_irq)(struct kvm_vcpu *vcpu);
- void (*set_irq)(struct kvm_vcpu *vcpu, int vec);
+ void (*set_irq)(struct kvm_vcpu *vcpu);
+ void (*set_nmi)(struct kvm_vcpu *vcpu);
void (*queue_exception)(struct kvm_vcpu *vcpu, unsigned nr,
bool has_error_code, u32 error_code);
- bool (*exception_injected)(struct kvm_vcpu *vcpu);
- void (*inject_pending_irq)(struct kvm_vcpu *vcpu);
- void (*inject_pending_vectors)(struct kvm_vcpu *vcpu,
- struct kvm_run *run);
-
+ int (*interrupt_allowed)(struct kvm_vcpu *vcpu);
+ int (*nmi_allowed)(struct kvm_vcpu *vcpu);
+ void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
+ void (*enable_irq_window)(struct kvm_vcpu *vcpu);
+ void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
int (*get_tdp_level)(void);
+ u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
+ bool (*gb_page_enable)(void);
+
+ const struct trace_print_flags *exit_reasons_str;
};
extern struct kvm_x86_ops *kvm_x86_ops;
const void *val, int bytes);
int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes,
gpa_t addr, unsigned long *ret);
+u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
extern bool tdp_enabled;
#define EMULTYPE_NO_DECODE (1 << 0)
#define EMULTYPE_TRAP_UD (1 << 1)
-int emulate_instruction(struct kvm_vcpu *vcpu, struct kvm_run *run,
+#define EMULTYPE_SKIP (1 << 2)
+int emulate_instruction(struct kvm_vcpu *vcpu,
unsigned long cr2, u16 error_code, int emulation_type);
void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context);
void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
struct x86_emulate_ctxt;
-int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
+int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in,
int size, unsigned port);
-int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
+int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in,
int size, unsigned long count, int down,
gva_t address, int rep, unsigned port);
void kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2,
u32 error_code);
+bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
-void kvm_pic_set_irq(void *opaque, int irq, int level);
+int kvm_pic_set_irq(void *opaque, int irq, int level);
void kvm_inject_nmi(struct kvm_vcpu *vcpu);
void fx_init(struct kvm_vcpu *vcpu);
-int emulator_read_std(unsigned long addr,
- void *val,
- unsigned int bytes,
- struct kvm_vcpu *vcpu);
int emulator_write_emulated(unsigned long addr,
const void *val,
unsigned int bytes,
void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu);
void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
- const u8 *new, int bytes);
+ const u8 *new, int bytes,
+ bool guest_initiated);
int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
int kvm_mmu_load(struct kvm_vcpu *vcpu);
int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
int complete_pio(struct kvm_vcpu *vcpu);
+struct kvm_memory_slot *gfn_to_memslot_unaliased(struct kvm *kvm, gfn_t gfn);
+
static inline struct kvm_mmu_page *page_header(hpa_t shadow_page)
{
struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT);
kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
}
-#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 ASM_VMX_INVEPT ".byte 0x66, 0x0f, 0x38, 0x80, 0x08"
-#define ASM_VMX_INVVPID ".byte 0x66, 0x0f, 0x38, 0x81, 0x08"
-
-#define MSR_IA32_TIME_STAMP_COUNTER 0x010
-
#define TSS_IOPB_BASE_OFFSET 0x66
#define TSS_BASE_SIZE 0x68
#define TSS_IOPB_SIZE (65536 / 8)
TASK_SWITCH_GATE = 3,
};
+#define HF_GIF_MASK (1 << 0)
+#define HF_HIF_MASK (1 << 1)
+#define HF_VINTR_MASK (1 << 2)
+#define HF_NMI_MASK (1 << 3)
+#define HF_IRET_MASK (1 << 4)
+
/*
* Hardware virtualization extension instructions may fault if a
* reboot turns off virtualization while processes are running.
#define KVM_ARCH_WANT_MMU_NOTIFIER
int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
int kvm_age_hva(struct kvm *kvm, unsigned long hva);
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
+int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
+int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
+int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
+int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
#endif /* _ASM_X86_KVM_HOST_H */