Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "ARM:
   - Move the arch-specific code into arch/arm64/kvm

   - Start the post-32bit cleanup

   - Cherry-pick a few non-invasive pre-NV patches

  x86:
   - Rework of TLB flushing

   - Rework of event injection, especially with respect to nested
     virtualization

   - Nested AMD event injection facelift, building on the rework of
     generic code and fixing a lot of corner cases

   - Nested AMD live migration support

   - Optimization for TSC deadline MSR writes and IPIs

   - Various cleanups

   - Asynchronous page fault cleanups (from tglx, common topic branch
     with tip tree)

   - Interrupt-based delivery of asynchronous "page ready" events (host
     side)

   - Hyper-V MSRs and hypercalls for guest debugging

   - VMX preemption timer fixes

  s390:
   - Cleanups

  Generic:
   - switch vCPU thread wakeup from swait to rcuwait

  The other architectures, and the guest side of the asynchronous page
  fault work, will come next week"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (256 commits)
  KVM: selftests: fix rdtsc() for vmx_tsc_adjust_test
  KVM: check userspace_addr for all memslots
  KVM: selftests: update hyperv_cpuid with SynDBG tests
  x86/kvm/hyper-v: Add support for synthetic debugger via hypercalls
  x86/kvm/hyper-v: enable hypercalls regardless of hypercall page
  x86/kvm/hyper-v: Add support for synthetic debugger interface
  x86/hyper-v: Add synthetic debugger definitions
  KVM: selftests: VMX preemption timer migration test
  KVM: nVMX: Fix VMX preemption timer migration
  x86/kvm/hyper-v: Explicitly align hcall param for kvm_hyperv_exit
  KVM: x86/pmu: Support full width counting
  KVM: x86/pmu: Tweak kvm_pmu_get_msr to pass 'struct msr_data' in
  KVM: x86: announce KVM_FEATURE_ASYNC_PF_INT
  KVM: x86: acknowledgment mechanism for async pf page ready notifications
  KVM: x86: interrupt based APF 'page ready' event delivery
  KVM: introduce kvm_read_guest_offset_cached()
  KVM: rename kvm_arch_can_inject_async_page_present() to kvm_arch_can_dequeue_async_page_present()
  KVM: x86: extend struct kvm_vcpu_pv_apf_data with token info
  Revert "KVM: async_pf: Fix #DF due to inject "Page not Present" and "Page Ready" exceptions simultaneously"
  KVM: VMX: Replace zero-length array with flexible-array
  ...

9 files changed, 160 insertions, 64 deletions

diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 4e91f6118d5d..7a4d2062385c 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -83,6 +83,8 @@
 #define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE		BIT(8)
 /* Crash MSR available */
 #define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE		BIT(10)
+/* Support for debug MSRs available */
+#define HV_FEATURE_DEBUG_MSRS_AVAILABLE			BIT(11)
 /* stimer Direct Mode is available */
 #define HV_STIMER_DIRECT_MODE_AVAILABLE			BIT(19)
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 1c0b62d26962..1da5858501ca 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -83,6 +83,10 @@
 #define KVM_REQ_GET_VMCS12_PAGES	KVM_ARCH_REQ(24)
 #define KVM_REQ_APICV_UPDATE \
 	KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_TLB_FLUSH_CURRENT	KVM_ARCH_REQ(26)
+#define KVM_REQ_HV_TLB_FLUSH \
+	KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_APF_READY		KVM_ARCH_REQ(28)
 
 #define CR0_RESERVED_BITS                                               \
 	(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
@@ -107,15 +111,8 @@
 #define UNMAPPED_GVA (~(gpa_t)0)
 
 /* KVM Hugepage definitions for x86 */
-enum {
-	PT_PAGE_TABLE_LEVEL   = 1,
-	PT_DIRECTORY_LEVEL    = 2,
-	PT_PDPE_LEVEL         = 3,
-	/* set max level to the biggest one */
-	PT_MAX_HUGEPAGE_LEVEL = PT_PDPE_LEVEL,
-};
-#define KVM_NR_PAGE_SIZES	(PT_MAX_HUGEPAGE_LEVEL - \
-				 PT_PAGE_TABLE_LEVEL + 1)
+#define KVM_MAX_HUGEPAGE_LEVEL	PG_LEVEL_1G
+#define KVM_NR_PAGE_SIZES	(KVM_MAX_HUGEPAGE_LEVEL - PG_LEVEL_4K + 1)
 #define KVM_HPAGE_GFN_SHIFT(x)	(((x) - 1) * 9)
 #define KVM_HPAGE_SHIFT(x)	(PAGE_SHIFT + KVM_HPAGE_GFN_SHIFT(x))
 #define KVM_HPAGE_SIZE(x)	(1UL << KVM_HPAGE_SHIFT(x))
@@ -124,7 +121,7 @@ enum {
 
 static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
 {
-	/* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */
+	/* KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K) must be 0. */
 	return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) -
 		(base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
 }
@@ -164,9 +161,13 @@ enum kvm_reg {
 	NR_VCPU_REGS,
 
 	VCPU_EXREG_PDPTR = NR_VCPU_REGS,
+	VCPU_EXREG_CR0,
 	VCPU_EXREG_CR3,
+	VCPU_EXREG_CR4,
 	VCPU_EXREG_RFLAGS,
 	VCPU_EXREG_SEGMENTS,
+	VCPU_EXREG_EXIT_INFO_1,
+	VCPU_EXREG_EXIT_INFO_2,
 };
 
 enum {
@@ -182,8 +183,10 @@ enum {
 
 enum exit_fastpath_completion {
 	EXIT_FASTPATH_NONE,
-	EXIT_FASTPATH_SKIP_EMUL_INS,
+	EXIT_FASTPATH_REENTER_GUEST,
+	EXIT_FASTPATH_EXIT_HANDLED,
 };
+typedef enum exit_fastpath_completion fastpath_t;
 
 struct x86_emulate_ctxt;
 struct x86_exception;
@@ -372,12 +375,12 @@ struct rsvd_bits_validate {
 };
 
 struct kvm_mmu_root_info {
-	gpa_t cr3;
+	gpa_t pgd;
 	hpa_t hpa;
 };
 
 #define KVM_MMU_ROOT_INFO_INVALID \
-	((struct kvm_mmu_root_info) { .cr3 = INVALID_PAGE, .hpa = INVALID_PAGE })
+	((struct kvm_mmu_root_info) { .pgd = INVALID_PAGE, .hpa = INVALID_PAGE })
 
 #define KVM_MMU_NUM_PREV_ROOTS 3
 
@@ -403,7 +406,7 @@ struct kvm_mmu {
 	void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 			   u64 *spte, const void *pte);
 	hpa_t root_hpa;
-	gpa_t root_cr3;
+	gpa_t root_pgd;
 	union kvm_mmu_role mmu_role;
 	u8 root_level;
 	u8 shadow_root_level;
@@ -598,6 +601,7 @@ struct kvm_vcpu_arch {
 	u64 ia32_xss;
 	u64 microcode_version;
 	u64 arch_capabilities;
+	u64 perf_capabilities;
 
 	/*
 	 * Paging state of the vcpu
@@ -650,7 +654,6 @@ struct kvm_vcpu_arch {
 
 	u64 xcr0;
 	u64 guest_supported_xcr0;
-	u32 guest_xstate_size;
 
 	struct kvm_pio_request pio;
 	void *pio_data;
@@ -680,6 +683,7 @@ struct kvm_vcpu_arch {
 	struct kvm_cpuid_entry2 cpuid_entries[KVM_MAX_CPUID_ENTRIES];
 
 	int maxphyaddr;
+	int tdp_level;
 
 	/* emulate context */
 
@@ -703,6 +707,7 @@ struct kvm_vcpu_arch {
 		struct gfn_to_pfn_cache cache;
 	} st;
 
+	u64 l1_tsc_offset;
 	u64 tsc_offset;
 	u64 last_guest_tsc;
 	u64 last_host_tsc;
@@ -762,14 +767,17 @@ struct kvm_vcpu_arch {
 
 	struct {
 		bool halted;
-		gfn_t gfns[roundup_pow_of_two(ASYNC_PF_PER_VCPU)];
+		gfn_t gfns[ASYNC_PF_PER_VCPU];
 		struct gfn_to_hva_cache data;
-		u64 msr_val;
+		u64 msr_en_val; /* MSR_KVM_ASYNC_PF_EN */
+		u64 msr_int_val; /* MSR_KVM_ASYNC_PF_INT */
+		u16 vec;
 		u32 id;
 		bool send_user_only;
-		u32 host_apf_reason;
+		u32 host_apf_flags;
 		unsigned long nested_apf_token;
 		bool delivery_as_pf_vmexit;
+		bool pageready_pending;
 	} apf;
 
 	/* OSVW MSRs (AMD only) */
@@ -855,6 +863,18 @@ struct kvm_apic_map {
 	struct kvm_lapic *phys_map[];
 };
 
+/* Hyper-V synthetic debugger (SynDbg)*/
+struct kvm_hv_syndbg {
+	struct {
+		u64 control;
+		u64 status;
+		u64 send_page;
+		u64 recv_page;
+		u64 pending_page;
+	} control;
+	u64 options;
+};
+
 /* Hyper-V emulation context */
 struct kvm_hv {
 	struct mutex hv_lock;
@@ -878,6 +898,7 @@ struct kvm_hv {
 	atomic_t num_mismatched_vp_indexes;
 
 	struct hv_partition_assist_pg *hv_pa_pg;
+	struct kvm_hv_syndbg hv_syndbg;
 };
 
 enum kvm_irqchip_mode {
@@ -1028,6 +1049,8 @@ struct kvm_vcpu_stat {
 	u64 irq_injections;
 	u64 nmi_injections;
 	u64 req_event;
+	u64 halt_poll_success_ns;
+	u64 halt_poll_fail_ns;
 };
 
 struct x86_instruction_info;
@@ -1059,7 +1082,7 @@ struct kvm_x86_ops {
 	void (*hardware_disable)(void);
 	void (*hardware_unsetup)(void);
 	bool (*cpu_has_accelerated_tpr)(void);
-	bool (*has_emulated_msr)(int index);
+	bool (*has_emulated_msr)(u32 index);
 	void (*cpuid_update)(struct kvm_vcpu *vcpu);
 
 	unsigned int vm_size;
@@ -1085,8 +1108,6 @@ struct kvm_x86_ops {
 	void (*set_segment)(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg);
 	void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
-	void (*decache_cr0_guest_bits)(struct kvm_vcpu *vcpu);
-	void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu);
 	void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
 	int (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4);
 	void (*set_efer)(struct kvm_vcpu *vcpu, u64 efer);
@@ -1100,7 +1121,8 @@ struct kvm_x86_ops {
 	unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
 	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
 
-	void (*tlb_flush)(struct kvm_vcpu *vcpu, bool invalidate_gpa);
+	void (*tlb_flush_all)(struct kvm_vcpu *vcpu);
+	void (*tlb_flush_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);
@@ -1113,7 +1135,13 @@ struct kvm_x86_ops {
 	 */
 	void (*tlb_flush_gva)(struct kvm_vcpu *vcpu, gva_t addr);
 
-	void (*run)(struct kvm_vcpu *vcpu);
+	/*
+	 * 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);
+
+	enum exit_fastpath_completion (*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);
@@ -1126,8 +1154,8 @@ struct kvm_x86_ops {
 	void (*set_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);
-	int (*nmi_allowed)(struct kvm_vcpu *vcpu);
+	int (*interrupt_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
+	int (*nmi_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
 	bool (*get_nmi_mask)(struct kvm_vcpu *vcpu);
 	void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked);
 	void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
@@ -1141,7 +1169,7 @@ struct kvm_x86_ops {
 	bool (*guest_apic_has_interrupt)(struct kvm_vcpu *vcpu);
 	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
 	void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu);
-	void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa);
+	void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu);
 	int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
 	int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
@@ -1153,7 +1181,6 @@ struct kvm_x86_ops {
 
 	bool (*has_wbinvd_exit)(void);
 
-	u64 (*read_l1_tsc_offset)(struct kvm_vcpu *vcpu);
 	/* Returns actual tsc_offset set in active VMCS */
 	u64 (*write_l1_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
 
@@ -1163,10 +1190,8 @@ struct kvm_x86_ops {
 			       struct x86_instruction_info *info,
 			       enum x86_intercept_stage stage,
 			       struct x86_exception *exception);
-	void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu,
-		enum exit_fastpath_completion *exit_fastpath);
+	void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu);
 
-	int (*check_nested_events)(struct kvm_vcpu *vcpu);
 	void (*request_immediate_exit)(struct kvm_vcpu *vcpu);
 
 	void (*sched_in)(struct kvm_vcpu *kvm, int cpu);
@@ -1199,6 +1224,7 @@ struct kvm_x86_ops {
 
 	/* pmu operations of sub-arch */
 	const struct kvm_pmu_ops *pmu_ops;
+	const struct kvm_x86_nested_ops *nested_ops;
 
 	/*
 	 * Architecture specific hooks for vCPU blocking due to
@@ -1226,18 +1252,10 @@ struct kvm_x86_ops {
 
 	void (*setup_mce)(struct kvm_vcpu *vcpu);
 
-	int (*get_nested_state)(struct kvm_vcpu *vcpu,
-				struct kvm_nested_state __user *user_kvm_nested_state,
-				unsigned user_data_size);
-	int (*set_nested_state)(struct kvm_vcpu *vcpu,
-				struct kvm_nested_state __user *user_kvm_nested_state,
-				struct kvm_nested_state *kvm_state);
-	bool (*get_vmcs12_pages)(struct kvm_vcpu *vcpu);
-
-	int (*smi_allowed)(struct kvm_vcpu *vcpu);
+	int (*smi_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
 	int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
 	int (*pre_leave_smm)(struct kvm_vcpu *vcpu, const char *smstate);
-	int (*enable_smi_window)(struct kvm_vcpu *vcpu);
+	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);
@@ -1245,14 +1263,28 @@ struct kvm_x86_ops {
 
 	int (*get_msr_feature)(struct kvm_msr_entry *entry);
 
-	int (*nested_enable_evmcs)(struct kvm_vcpu *vcpu,
-				   uint16_t *vmcs_version);
-	uint16_t (*nested_get_evmcs_version)(struct kvm_vcpu *vcpu);
-
 	bool (*need_emulation_on_page_fault)(struct kvm_vcpu *vcpu);
 
 	bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu);
 	int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu);
+
+	void (*migrate_timers)(struct kvm_vcpu *vcpu);
+};
+
+struct kvm_x86_nested_ops {
+	int (*check_events)(struct kvm_vcpu *vcpu);
+	bool (*hv_timer_pending)(struct kvm_vcpu *vcpu);
+	int (*get_state)(struct kvm_vcpu *vcpu,
+			 struct kvm_nested_state __user *user_kvm_nested_state,
+			 unsigned user_data_size);
+	int (*set_state)(struct kvm_vcpu *vcpu,
+			 struct kvm_nested_state __user *user_kvm_nested_state,
+			 struct kvm_nested_state *kvm_state);
+	bool (*get_vmcs12_pages)(struct kvm_vcpu *vcpu);
+
+	int (*enable_evmcs)(struct kvm_vcpu *vcpu,
+			    uint16_t *vmcs_version);
+	uint16_t (*get_evmcs_version)(struct kvm_vcpu *vcpu);
 };
 
 struct kvm_x86_init_ops {
@@ -1451,6 +1483,8 @@ void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long pay
 void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
 void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
+bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu,
+				    struct x86_exception *fault);
 int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 			    gfn_t gfn, void *data, int offset, int len,
 			    u32 access);
@@ -1478,6 +1512,8 @@ void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id);
 
 void kvm_inject_nmi(struct kvm_vcpu *vcpu);
 
+void kvm_update_dr7(struct kvm_vcpu *vcpu);
+
 int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
 int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
 void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
@@ -1508,8 +1544,11 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
 		       void *insn, int insn_len);
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
+void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+			    gva_t gva, hpa_t root_hpa);
 void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid);
-void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu, gpa_t new_cr3, bool skip_tlb_flush);
+void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd, bool skip_tlb_flush,
+		     bool skip_mmu_sync);
 
 void kvm_configure_mmu(bool enable_tdp, int tdp_page_level);
 
@@ -1573,8 +1612,6 @@ enum {
 };
 
 #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)
 #define HF_GUEST_MASK		(1 << 5) /* VCPU is in guest-mode */
@@ -1640,7 +1677,8 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 				 struct kvm_async_pf *work);
 void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
 			       struct kvm_async_pf *work);
-bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu);
+void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu);
+bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu);
 extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 
 int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 9b4df6eaa11a..57fd1966c4ea 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -88,11 +88,21 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
 bool kvm_para_available(void);
 unsigned int kvm_arch_para_features(void);
 unsigned int kvm_arch_para_hints(void);
-void kvm_async_pf_task_wait(u32 token, int interrupt_kernel);
+void kvm_async_pf_task_wait_schedule(u32 token);
 void kvm_async_pf_task_wake(u32 token);
-u32 kvm_read_and_reset_pf_reason(void);
-extern void kvm_disable_steal_time(void);
-void do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address);
+u32 kvm_read_and_reset_apf_flags(void);
+void kvm_disable_steal_time(void);
+bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token);
+
+DECLARE_STATIC_KEY_FALSE(kvm_async_pf_enabled);
+
+static __always_inline bool kvm_handle_async_pf(struct pt_regs *regs, u32 token)
+{
+	if (static_branch_unlikely(&kvm_async_pf_enabled))
+		return __kvm_handle_async_pf(regs, token);
+	else
+		return false;
+}
 
 #ifdef CONFIG_PARAVIRT_SPINLOCKS
 void __init kvm_spinlock_init(void);
@@ -103,7 +113,7 @@ static inline void kvm_spinlock_init(void)
 #endif /* CONFIG_PARAVIRT_SPINLOCKS */
 
 #else /* CONFIG_KVM_GUEST */
-#define kvm_async_pf_task_wait(T, I) do {} while(0)
+#define kvm_async_pf_task_wait_schedule(T) do {} while(0)
 #define kvm_async_pf_task_wake(T) do {} while(0)
 
 static inline bool kvm_para_available(void)
@@ -121,7 +131,7 @@ static inline unsigned int kvm_arch_para_hints(void)
 	return 0;
 }
 
-static inline u32 kvm_read_and_reset_pf_reason(void)
+static inline u32 kvm_read_and_reset_apf_flags(void)
 {
 	return 0;
 }
@@ -130,6 +140,11 @@ static inline void kvm_disable_steal_time(void)
 {
 	return;
 }
+
+static inline bool kvm_handle_async_pf(struct pt_regs *regs, u32 token)
+{
+	return false;
+}
 #endif
 
 #endif /* _ASM_X86_KVM_PARA_H */
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 6ece8561ba66..8a1f5382a4ea 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -96,7 +96,6 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 	u8 reserved_6[8];	/* Offset 0xe8 */
 	u64 avic_logical_id;	/* Offset 0xf0 */
 	u64 avic_physical_id;	/* Offset 0xf8 */
-	u8 reserved_7[768];
 };
 
 
@@ -203,8 +202,16 @@ struct __attribute__ ((__packed__)) vmcb_save_area {
 	u64 last_excp_to;
 };
 
+
+static inline void __unused_size_checks(void)
+{
+	BUILD_BUG_ON(sizeof(struct vmcb_save_area) != 0x298);
+	BUILD_BUG_ON(sizeof(struct vmcb_control_area) != 256);
+}
+
 struct __attribute__ ((__packed__)) vmcb {
 	struct vmcb_control_area control;
+	u8 reserved_control[1024 - sizeof(struct vmcb_control_area)];
 	struct vmcb_save_area save;
 };
 
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 5e090d1f03f8..cd7de4b401fe 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -527,10 +527,12 @@ struct vmx_msr_entry {
 /*
  * Exit Qualifications for entry failure during or after loading guest state
  */
-#define ENTRY_FAIL_DEFAULT		0
-#define ENTRY_FAIL_PDPTE		2
-#define ENTRY_FAIL_NMI			3
-#define ENTRY_FAIL_VMCS_LINK_PTR	4
+enum vm_entry_failure_code {
+	ENTRY_FAIL_DEFAULT		= 0,
+	ENTRY_FAIL_PDPTE		= 2,
+	ENTRY_FAIL_NMI			= 3,
+	ENTRY_FAIL_VMCS_LINK_PTR	= 4,
+};
 
 /*
  * Exit Qualifications for EPT Violations
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 96d9cd208610..6807153c0410 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -50,14 +50,12 @@ struct x86_init_resources {
  * @pre_vector_init:		init code to run before interrupt vectors
  *				are set up.
  * @intr_init:			interrupt init code
- * @trap_init:			platform specific trap setup
  * @intr_mode_select:		interrupt delivery mode selection
  * @intr_mode_init:		interrupt delivery mode setup
  */
 struct x86_init_irqs {
 	void (*pre_vector_init)(void);
 	void (*intr_init)(void);
-	void (*trap_init)(void);
 	void (*intr_mode_select)(void);
 	void (*intr_mode_init)(void);
 };
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 3f3f780c8c65..17c5a038f42d 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -385,32 +385,48 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4)
 
 #define KVM_STATE_NESTED_FORMAT_VMX	0
-#define KVM_STATE_NESTED_FORMAT_SVM	1	/* unused */
+#define KVM_STATE_NESTED_FORMAT_SVM	1
 
 #define KVM_STATE_NESTED_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING	0x00000002
 #define KVM_STATE_NESTED_EVMCS		0x00000004
 #define KVM_STATE_NESTED_MTF_PENDING	0x00000008
+#define KVM_STATE_NESTED_GIF_SET	0x00000100
 
 #define KVM_STATE_NESTED_SMM_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_SMM_VMXON	0x00000002
 
 #define KVM_STATE_NESTED_VMX_VMCS_SIZE	0x1000
 
+#define KVM_STATE_NESTED_SVM_VMCB_SIZE	0x1000
+
+#define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE	0x00000001
+
 struct kvm_vmx_nested_state_data {
 	__u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
 	__u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
 };
 
 struct kvm_vmx_nested_state_hdr {
+	__u32 flags;
 	__u64 vmxon_pa;
 	__u64 vmcs12_pa;
+	__u64 preemption_timer_deadline;
 
 	struct {
 		__u16 flags;
 	} smm;
 };
 
+struct kvm_svm_nested_state_data {
+	/* Save area only used if KVM_STATE_NESTED_RUN_PENDING.  */
+	__u8 vmcb12[KVM_STATE_NESTED_SVM_VMCB_SIZE];
+};
+
+struct kvm_svm_nested_state_hdr {
+	__u64 vmcb_pa;
+};
+
 /* for KVM_CAP_NESTED_STATE */
 struct kvm_nested_state {
 	__u16 flags;
@@ -419,6 +435,7 @@ struct kvm_nested_state {
 
 	union {
 		struct kvm_vmx_nested_state_hdr vmx;
+		struct kvm_svm_nested_state_hdr svm;
 
 		/* Pad the header to 128 bytes.  */
 		__u8 pad[120];
@@ -431,6 +448,7 @@ struct kvm_nested_state {
 	 */
 	union {
 		struct kvm_vmx_nested_state_data vmx[0];
+		struct kvm_svm_nested_state_data svm[0];
 	} data;
 };
 
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 2a8e0b6b9805..812e9b4c1114 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -31,6 +31,7 @@
 #define KVM_FEATURE_PV_SEND_IPI	11
 #define KVM_FEATURE_POLL_CONTROL	12
 #define KVM_FEATURE_PV_SCHED_YIELD	13
+#define KVM_FEATURE_ASYNC_PF_INT	14
 
 #define KVM_HINTS_REALTIME      0
 
@@ -50,6 +51,8 @@
 #define MSR_KVM_STEAL_TIME  0x4b564d03
 #define MSR_KVM_PV_EOI_EN      0x4b564d04
 #define MSR_KVM_POLL_CONTROL	0x4b564d05
+#define MSR_KVM_ASYNC_PF_INT	0x4b564d06
+#define MSR_KVM_ASYNC_PF_ACK	0x4b564d07
 
 struct kvm_steal_time {
 	__u64 steal;
@@ -81,6 +84,11 @@ struct kvm_clock_pairing {
 #define KVM_ASYNC_PF_ENABLED			(1 << 0)
 #define KVM_ASYNC_PF_SEND_ALWAYS		(1 << 1)
 #define KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT	(1 << 2)
+#define KVM_ASYNC_PF_DELIVERY_AS_INT		(1 << 3)
+
+/* MSR_KVM_ASYNC_PF_INT */
+#define KVM_ASYNC_PF_VEC_MASK			GENMASK(7, 0)
+
 
 /* Operations for KVM_HC_MMU_OP */
 #define KVM_MMU_OP_WRITE_PTE            1
@@ -112,8 +120,13 @@ struct kvm_mmu_op_release_pt {
 #define KVM_PV_REASON_PAGE_READY 2
 
 struct kvm_vcpu_pv_apf_data {
-	__u32 reason;
-	__u8 pad[60];
+	/* Used for 'page not present' events delivered via #PF */
+	__u32 flags;
+
+	/* Used for 'page ready' events delivered via interrupt notification */
+	__u32 token;
+
+	__u8 pad[56];
 	__u32 enabled;
 };
 
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index e95b72ec19bc..b8ff9e8ac0d5 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -150,6 +150,9 @@
 	{ EXIT_REASON_UMWAIT,                "UMWAIT" }, \
 	{ EXIT_REASON_TPAUSE,                "TPAUSE" }
 
+#define VMX_EXIT_REASON_FLAGS \
+	{ VMX_EXIT_REASONS_FAILED_VMENTRY,	"FAILED_VMENTRY" }
+
 #define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL       2
 #define VMX_ABORT_LOAD_HOST_MSR_FAIL         4