#include <linux/cpumask.h>
#include <linux/irq_work.h>
#include <linux/irq.h>
+#include <linux/workqueue.h>
#include <linux/kvm.h>
#include <linux/kvm_para.h>
#define KVM_REQ_MSR_FILTER_CHANGED KVM_ARCH_REQ(29)
#define KVM_REQ_UPDATE_CPU_DIRTY_LOGGING \
KVM_ARCH_REQ_FLAGS(30, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_MMU_FREE_OBSOLETE_ROOTS \
+ KVM_ARCH_REQ_FLAGS(31, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define CR0_RESERVED_BITS \
(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
#define PFERR_SGX_BIT 15
#define PFERR_GUEST_FINAL_BIT 32
#define PFERR_GUEST_PAGE_BIT 33
+#define PFERR_IMPLICIT_ACCESS_BIT 48
#define PFERR_PRESENT_MASK (1U << PFERR_PRESENT_BIT)
#define PFERR_WRITE_MASK (1U << PFERR_WRITE_BIT)
#define PFERR_SGX_MASK (1U << PFERR_SGX_BIT)
#define PFERR_GUEST_FINAL_MASK (1ULL << PFERR_GUEST_FINAL_BIT)
#define PFERR_GUEST_PAGE_MASK (1ULL << PFERR_GUEST_PAGE_BIT)
+#define PFERR_IMPLICIT_ACCESS (1ULL << PFERR_IMPLICIT_ACCESS_BIT)
#define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK | \
PFERR_WRITE_MASK | \
void (*inject_page_fault)(struct kvm_vcpu *vcpu,
struct x86_exception *fault);
gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
- gpa_t gva_or_gpa, u32 access,
+ gpa_t gva_or_gpa, u64 access,
struct x86_exception *exception);
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);
- hpa_t root_hpa;
- gpa_t root_pgd;
+ struct kvm_mmu_root_info root;
union kvm_mmu_role mmu_role;
u8 root_level;
u8 shadow_root_level;
bool intr;
};
+#define KVM_PMC_MAX_FIXED 3
struct kvm_pmu {
unsigned nr_arch_gp_counters;
unsigned nr_arch_fixed_counters;
u64 global_ctrl_mask;
u64 global_ovf_ctrl_mask;
u64 reserved_bits;
+ u64 raw_event_mask;
u8 version;
struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
- struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
+ struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED];
struct irq_work irq_work;
DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX);
DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX);
struct kvm_vcpu_xen {
u64 hypercall_rip;
u32 current_runstate;
- bool vcpu_info_set;
- bool vcpu_time_info_set;
- bool runstate_set;
- struct gfn_to_hva_cache vcpu_info_cache;
- struct gfn_to_hva_cache vcpu_time_info_cache;
- struct gfn_to_hva_cache runstate_cache;
+ u8 upcall_vector;
+ struct gfn_to_pfn_cache vcpu_info_cache;
+ struct gfn_to_pfn_cache vcpu_time_info_cache;
+ struct gfn_to_pfn_cache runstate_cache;
u64 last_steal;
u64 runstate_entry_time;
u64 runstate_times[4];
unsigned long evtchn_pending_sel;
+ u32 vcpu_id; /* The Xen / ACPI vCPU ID */
+ u32 timer_virq;
+ u64 timer_expires; /* In guest epoch */
+ atomic_t timer_pending;
+ struct hrtimer timer;
+ int poll_evtchn;
+ struct timer_list poll_timer;
};
struct kvm_vcpu_arch {
struct fpu_guest guest_fpu;
u64 xcr0;
- u64 guest_supported_xcr0;
struct kvm_pio_request pio;
void *pio_data;
gpa_t time;
struct pvclock_vcpu_time_info hv_clock;
unsigned int hw_tsc_khz;
- struct gfn_to_hva_cache pv_time;
- bool pv_time_enabled;
+ struct gfn_to_pfn_cache pv_time;
/* set guest stopped flag in pvclock flags field */
bool pvclock_set_guest_stopped_request;
HV_TSC_PAGE_UNSET = 0,
/* TSC page MSR was written by the guest, update pending */
HV_TSC_PAGE_GUEST_CHANGED,
- /* TSC page MSR was written by KVM userspace, update pending */
+ /* TSC page update was triggered from the host side */
HV_TSC_PAGE_HOST_CHANGED,
/* TSC page was properly set up and is currently active */
HV_TSC_PAGE_SET,
- /* TSC page is currently being updated and therefore is inactive */
- HV_TSC_PAGE_UPDATING,
/* TSC page was set up with an inaccessible GPA */
HV_TSC_PAGE_BROKEN,
};
/* Xen emulation context */
struct kvm_xen {
+ u32 xen_version;
bool long_mode;
u8 upcall_vector;
struct gfn_to_pfn_cache shinfo_cache;
+ struct idr evtchn_ports;
+ unsigned long poll_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)];
};
enum kvm_irqchip_mode {
struct msr_bitmap_range ranges[16];
};
-#define APICV_INHIBIT_REASON_DISABLE 0
-#define APICV_INHIBIT_REASON_HYPERV 1
-#define APICV_INHIBIT_REASON_NESTED 2
-#define APICV_INHIBIT_REASON_IRQWIN 3
-#define APICV_INHIBIT_REASON_PIT_REINJ 4
-#define APICV_INHIBIT_REASON_X2APIC 5
-#define APICV_INHIBIT_REASON_BLOCKIRQ 6
-#define APICV_INHIBIT_REASON_ABSENT 7
+enum kvm_apicv_inhibit {
+ APICV_INHIBIT_REASON_DISABLE,
+ APICV_INHIBIT_REASON_HYPERV,
+ APICV_INHIBIT_REASON_NESTED,
+ APICV_INHIBIT_REASON_IRQWIN,
+ APICV_INHIBIT_REASON_PIT_REINJ,
+ APICV_INHIBIT_REASON_X2APIC,
+ APICV_INHIBIT_REASON_BLOCKIRQ,
+ APICV_INHIBIT_REASON_ABSENT,
+ APICV_INHIBIT_REASON_SEV,
+};
struct kvm_arch {
unsigned long n_used_mmu_pages;
u64 cur_tsc_generation;
int nr_vcpus_matched_tsc;
+ u32 default_tsc_khz;
+
seqcount_raw_spinlock_t pvclock_sc;
bool use_master_clock;
u64 master_kernel_ns;
struct kvm_hv hyperv;
struct kvm_xen xen;
- #ifdef CONFIG_KVM_MMU_AUDIT
- int audit_point;
- #endif
-
bool backwards_tsc_observed;
bool boot_vcpu_runs_old_kvmclock;
u32 bsp_vcpu_id;
bool exception_payload_enabled;
bool bus_lock_detection_enabled;
+ bool enable_pmu;
/*
* If exit_on_emulation_error is set, and the in-kernel instruction
* emulator fails to emulate an instruction, allow userspace
* the thread holds the MMU lock in write mode.
*/
spinlock_t tdp_mmu_pages_lock;
+ struct workqueue_struct *tdp_mmu_zap_wq;
#endif /* CONFIG_X86_64 */
/*
int (*hardware_enable)(void);
void (*hardware_disable)(void);
void (*hardware_unsetup)(void);
- bool (*cpu_has_accelerated_tpr)(void);
bool (*has_emulated_msr)(struct kvm *kvm, u32 index);
void (*vcpu_after_set_cpuid)(struct kvm_vcpu *vcpu);
void (*vcpu_free)(struct kvm_vcpu *vcpu);
void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event);
- void (*prepare_guest_switch)(struct kvm_vcpu *vcpu);
+ void (*prepare_switch_to_guest)(struct kvm_vcpu *vcpu);
void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
void (*vcpu_put)(struct kvm_vcpu *vcpu);
void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
bool (*get_if_flag)(struct kvm_vcpu *vcpu);
- void (*tlb_flush_all)(struct kvm_vcpu *vcpu);
- void (*tlb_flush_current)(struct kvm_vcpu *vcpu);
+ void (*flush_tlb_all)(struct kvm_vcpu *vcpu);
+ void (*flush_tlb_current)(struct kvm_vcpu *vcpu);
int (*tlb_remote_flush)(struct kvm *kvm);
int (*tlb_remote_flush_with_range)(struct kvm *kvm,
struct kvm_tlb_range *range);
* Can potentially get non-canonical addresses through INVLPGs, which
* the implementation may choose to ignore if appropriate.
*/
- void (*tlb_flush_gva)(struct kvm_vcpu *vcpu, gva_t addr);
+ void (*flush_tlb_gva)(struct kvm_vcpu *vcpu, gva_t addr);
/*
* Flush any TLB entries created by the guest. Like tlb_flush_gva(),
* does not need to flush GPA->HPA mappings.
*/
- void (*tlb_flush_guest)(struct kvm_vcpu *vcpu);
+ void (*flush_tlb_guest)(struct kvm_vcpu *vcpu);
int (*vcpu_pre_run)(struct kvm_vcpu *vcpu);
- enum exit_fastpath_completion (*run)(struct kvm_vcpu *vcpu);
+ enum exit_fastpath_completion (*vcpu_run)(struct kvm_vcpu *vcpu);
int (*handle_exit)(struct kvm_vcpu *vcpu,
enum exit_fastpath_completion exit_fastpath);
int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu);
void (*patch_hypercall)(struct kvm_vcpu *vcpu,
unsigned char *hypercall_addr);
- void (*set_irq)(struct kvm_vcpu *vcpu);
- void (*set_nmi)(struct kvm_vcpu *vcpu);
+ void (*inject_irq)(struct kvm_vcpu *vcpu);
+ void (*inject_nmi)(struct kvm_vcpu *vcpu);
void (*queue_exception)(struct kvm_vcpu *vcpu);
void (*cancel_injection)(struct kvm_vcpu *vcpu);
int (*interrupt_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
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);
- bool (*check_apicv_inhibit_reasons)(ulong bit);
+ bool (*check_apicv_inhibit_reasons)(enum kvm_apicv_inhibit reason);
void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);
void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr);
void (*vcpu_blocking)(struct kvm_vcpu *vcpu);
void (*vcpu_unblocking)(struct kvm_vcpu *vcpu);
- int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq,
+ int (*pi_update_irte)(struct kvm *kvm, unsigned int host_irq,
uint32_t guest_irq, bool set);
- void (*start_assignment)(struct kvm *kvm);
+ void (*pi_start_assignment)(struct kvm *kvm);
void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu);
bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu);
int (*leave_smm)(struct kvm_vcpu *vcpu, const char *smstate);
void (*enable_smi_window)(struct kvm_vcpu *vcpu);
- int (*mem_enc_op)(struct kvm *kvm, void __user *argp);
- int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
- int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
+ int (*mem_enc_ioctl)(struct kvm *kvm, void __user *argp);
+ int (*mem_enc_register_region)(struct kvm *kvm, struct kvm_enc_region *argp);
+ int (*mem_enc_unregister_region)(struct kvm *kvm, struct kvm_enc_region *argp);
int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd);
int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd);
int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err);
void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector);
+
+ /*
+ * Returns vCPU specific APICv inhibit reasons
+ */
+ unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu);
};
struct kvm_x86_nested_ops {
#define KVM_X86_OP(func) \
DECLARE_STATIC_CALL(kvm_x86_##func, *(((struct kvm_x86_ops *)0)->func));
-#define KVM_X86_OP_NULL KVM_X86_OP
+#define KVM_X86_OP_OPTIONAL KVM_X86_OP
+#define KVM_X86_OP_OPTIONAL_RET0 KVM_X86_OP
#include <asm/kvm-x86-ops.h>
static inline void kvm_ops_static_call_update(void)
{
-#define KVM_X86_OP(func) \
+#define __KVM_X86_OP(func) \
static_call_update(kvm_x86_##func, kvm_x86_ops.func);
-#define KVM_X86_OP_NULL KVM_X86_OP
+#define KVM_X86_OP(func) \
+ WARN_ON(!kvm_x86_ops.func); __KVM_X86_OP(func)
+#define KVM_X86_OP_OPTIONAL __KVM_X86_OP
+#define KVM_X86_OP_OPTIONAL_RET0(func) \
+ static_call_update(kvm_x86_##func, (void *)kvm_x86_ops.func ? : \
+ (void *)__static_call_return0);
#include <asm/kvm-x86-ops.h>
+#undef __KVM_X86_OP
}
#define __KVM_HAVE_ARCH_VM_ALLOC
#define kvm_arch_pmi_in_guest(vcpu) \
((vcpu) && (vcpu)->arch.handling_intr_from_guest)
-int kvm_mmu_module_init(void);
-void kvm_mmu_module_exit(void);
+void kvm_mmu_x86_module_init(void);
+int kvm_mmu_vendor_module_init(void);
+void kvm_mmu_vendor_module_exit(void);
void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
-void kvm_mmu_init_vm(struct kvm *kvm);
+int kvm_mmu_init_vm(struct kvm *kvm);
void kvm_mmu_uninit_vm(struct kvm *kvm);
void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu);
void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
const struct kvm_memory_slot *memslot,
int start_level);
+void kvm_mmu_slot_try_split_huge_pages(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot,
+ int target_level);
+void kvm_mmu_try_split_huge_pages(struct kvm *kvm,
+ const struct kvm_memory_slot *memslot,
+ u64 start, u64 end,
+ int target_level);
void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
const struct kvm_memory_slot *memslot);
void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
void kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val);
unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu);
void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw);
-void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l);
int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu);
int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr);
void kvm_update_dr7(struct kvm_vcpu *vcpu);
int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
-void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu,
ulong roots_to_free);
-void kvm_mmu_free_guest_mode_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu);
+void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu);
gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
struct x86_exception *exception);
gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva,
struct x86_exception *exception);
bool kvm_apicv_activated(struct kvm *kvm);
+bool kvm_vcpu_apicv_activated(struct kvm_vcpu *vcpu);
void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu);
-void kvm_request_apicv_update(struct kvm *kvm, bool activate,
- unsigned long bit);
+void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
+ enum kvm_apicv_inhibit reason, bool set);
+void kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
+ enum kvm_apicv_inhibit reason, bool set);
+
+static inline void kvm_set_apicv_inhibit(struct kvm *kvm,
+ enum kvm_apicv_inhibit reason)
+{
+ kvm_set_or_clear_apicv_inhibit(kvm, reason, true);
+}
-void __kvm_request_apicv_update(struct kvm *kvm, bool activate,
- unsigned long bit);
+static inline void kvm_clear_apicv_inhibit(struct kvm *kvm,
+ enum kvm_apicv_inhibit reason)
+{
+ kvm_set_or_clear_apicv_inhibit(kvm, reason, false);
+}
int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
return kvm_find_user_return_msr(msr) >= 0;
}
-u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc, u64 ratio);
+u64 kvm_scale_tsc(u64 tsc, u64 ratio);
u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc);
u64 kvm_calc_nested_tsc_offset(u64 l1_offset, u64 l2_offset, u64 l2_multiplier);
u64 kvm_calc_nested_tsc_multiplier(u64 l1_multiplier, u64 l2_multiplier);
#define KVM_CLOCK_VALID_FLAGS \
(KVM_CLOCK_TSC_STABLE | KVM_CLOCK_REALTIME | KVM_CLOCK_HOST_TSC)
+#define KVM_X86_VALID_QUIRKS \
+ (KVM_X86_QUIRK_LINT0_REENABLED | \
+ KVM_X86_QUIRK_CD_NW_CLEARED | \
+ KVM_X86_QUIRK_LAPIC_MMIO_HOLE | \
+ KVM_X86_QUIRK_OUT_7E_INC_RIP | \
+ KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT | \
+ KVM_X86_QUIRK_FIX_HYPERCALL_INSN)
+
#endif /* _ASM_X86_KVM_HOST_H */