Merge tag 'kvm-4.13-2' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull more KVM updates from Radim Krčmář:
"Second batch of KVM updates for v4.13

Common:
- add uevents for VM creation/destruction
- annotate and properly access RCU-protected objects

s390:
- rename IOCTL added in the first v4.13 merge

x86:
- emulate VMLOAD VMSAVE feature in SVM
- support paravirtual asynchronous page fault while nested
- add Hyper-V userspace interfaces for better migration
- improve master clock corner cases
- extend internal error reporting after EPT misconfig
- correct single-stepping of emulated instructions in SVM
- handle MCE during VM entry
- fix nVMX VM entry checks and nVMX VMCS shadowing"

* tag 'kvm-4.13-2' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (28 commits)
kvm: x86: hyperv: make VP_INDEX managed by userspace
KVM: async_pf: Let guest support delivery of async_pf from guest mode
KVM: async_pf: Force a nested vmexit if the injected #PF is async_pf
KVM: async_pf: Add L1 guest async_pf #PF vmexit handler
KVM: x86: Simplify kvm_x86_ops->queue_exception parameter list
kvm: x86: hyperv: add KVM_CAP_HYPERV_SYNIC2
KVM: x86: make backwards_tsc_observed a per-VM variable
KVM: trigger uevents when creating or destroying a VM
KVM: SVM: Enable Virtual VMLOAD VMSAVE feature
KVM: SVM: Add Virtual VMLOAD VMSAVE feature definition
KVM: SVM: Rename lbr_ctl field in the vmcb control area
KVM: SVM: Prepare for new bit definition in lbr_ctl
KVM: SVM: handle singlestep exception when skipping emulated instructions
KVM: x86: take slots_lock in kvm_free_pit
KVM: s390: Fix KVM_S390_GET_CMMA_BITS ioctl definition
kvm: vmx: Properly handle machine check during VM-entry
KVM: x86: update master clock before computing kvmclock_offset
kvm: nVMX: Shadow "high" parts of shadowed 64-bit VMCS fields
kvm: nVMX: Fix nested_vmx_check_msr_bitmap_controls
kvm: nVMX: Validate the I/O bitmaps on nested VM-entry
...

Documentation/virtual/kvm/api.txt

···
 virtual SMT modes that can be set using KVM_CAP_PPC_SMT.  If bit N
 (counting from the right) is set, then a virtual SMT mode of 2^N is
 available.
+
+8.11 KVM_CAP_HYPERV_SYNIC2
+
+Architectures: x86
+
+This capability enables a newer version of Hyper-V Synthetic interrupt
+controller (SynIC).  The only difference with KVM_CAP_HYPERV_SYNIC is that KVM
+doesn't clear SynIC message and event flags pages when they are enabled by
+writing to the respective MSRs.
+
+8.12 KVM_CAP_HYPERV_VP_INDEX
+
+Architectures: x86
+
+This capability indicates that userspace can load HV_X64_MSR_VP_INDEX msr.  Its
+value is used to denote the target vcpu for a SynIC interrupt.  For
+compatibilty, KVM initializes this msr to KVM's internal vcpu index.  When this
+capability is absent, userspace can still query this msr's value.

Documentation/virtual/kvm/msr.txt

···
 MSR_KVM_ASYNC_PF_EN: 0x4b564d02
 	data: Bits 63-6 hold 64-byte aligned physical address of a
 	64 byte memory area which must be in guest RAM and must be
-	zeroed. Bits 5-2 are reserved and should be zero. Bit 0 is 1
+	zeroed. Bits 5-3 are reserved and should be zero. Bit 0 is 1
 	when asynchronous page faults are enabled on the vcpu 0 when
 	disabled. Bit 1 is 1 if asynchronous page faults can be injected
-	when vcpu is in cpl == 0.
+	when vcpu is in cpl == 0. Bit 2 is 1 if asynchronous page faults
+	are delivered to L1 as #PF vmexits.
 
 	First 4 byte of 64 byte memory location will be written to by
 	the hypervisor at the time of asynchronous page fault (APF)

arch/x86/include/asm/cpufeatures.h

···
 #define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
 #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
 #define X86_FEATURE_AVIC	(15*32+13) /* Virtual Interrupt Controller */
+#define X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE (15*32+15) /* Virtual VMLOAD VMSAVE */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
 #define X86_FEATURE_AVX512VBMI  (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/

arch/x86/include/asm/kvm_emulate.h

···
 	u16 error_code;
 	bool nested_page_fault;
 	u64 address; /* cr2 or nested page fault gpa */
+	u8 async_page_fault;
 };
 
 /*

arch/x86/include/asm/kvm_host.h

···
 	DECLARE_BITMAP(auto_eoi_bitmap, 256);
 	DECLARE_BITMAP(vec_bitmap, 256);
 	bool active;
+	bool dont_zero_synic_pages;
 };
 
 /* Hyper-V per vcpu emulation context */
 struct kvm_vcpu_hv {
+	u32 vp_index;
 	u64 hv_vapic;
 	s64 runtime_offset;
 	struct kvm_vcpu_hv_synic synic;
···
 		bool reinject;
 		u8 nr;
 		u32 error_code;
+		u8 nested_apf;
 	} exception;
 
 	struct kvm_queued_interrupt {
···
 		u64 msr_val;
 		u32 id;
 		bool send_user_only;
+		u32 host_apf_reason;
+		unsigned long nested_apf_token;
+		bool delivery_as_pf_vmexit;
 	} apf;
 
 	/* OSVW MSRs (AMD only) */
···
 	int audit_point;
 	#endif
 
+	bool backwards_tsc_observed;
 	bool boot_vcpu_runs_old_kvmclock;
 	u32 bsp_vcpu_id;
 
···
 				unsigned char *hypercall_addr);
 	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 reinject);
+	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);

arch/x86/include/asm/svm.h

···
 	u32 event_inj;
 	u32 event_inj_err;
 	u64 nested_cr3;
-	u64 lbr_ctl;
+	u64 virt_ext;
 	u32 clean;
 	u32 reserved_5;
 	u64 next_rip;
···
 
 #define AVIC_ENABLE_SHIFT 31
 #define AVIC_ENABLE_MASK (1 << AVIC_ENABLE_SHIFT)
+
+#define LBR_CTL_ENABLE_MASK BIT_ULL(0)
+#define VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK BIT_ULL(1)
 
 #define SVM_INTERRUPT_SHADOW_MASK 1
 

arch/x86/include/uapi/asm/kvm_para.h

···
 
 #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)
 
 /* Operations for KVM_HC_MMU_OP */
 #define KVM_MMU_OP_WRITE_PTE            1

arch/x86/kernel/kvm.c

···
 #ifdef CONFIG_PREEMPT
 		pa |= KVM_ASYNC_PF_SEND_ALWAYS;
 #endif
-		wrmsrl(MSR_KVM_ASYNC_PF_EN, pa | KVM_ASYNC_PF_ENABLED);
+		pa |= KVM_ASYNC_PF_ENABLED;
+
+		/* Async page fault support for L1 hypervisor is optional */
+		if (wrmsr_safe(MSR_KVM_ASYNC_PF_EN,
+			(pa | KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT) & 0xffffffff, pa >> 32) < 0)
+			wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
 		__this_cpu_write(apf_reason.enabled, 1);
 		printk(KERN_INFO"KVM setup async PF for cpu %d\n",
 		       smp_processor_id());

arch/x86/kvm/hyperv.c

···
 	return 0;
 }
 
-static struct kvm_vcpu_hv_synic *synic_get(struct kvm *kvm, u32 vcpu_id)
+static struct kvm_vcpu *get_vcpu_by_vpidx(struct kvm *kvm, u32 vpidx)
+{
+	struct kvm_vcpu *vcpu = NULL;
+	int i;
+
+	if (vpidx < KVM_MAX_VCPUS)
+		vcpu = kvm_get_vcpu(kvm, vpidx);
+	if (vcpu && vcpu_to_hv_vcpu(vcpu)->vp_index == vpidx)
+		return vcpu;
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		if (vcpu_to_hv_vcpu(vcpu)->vp_index == vpidx)
+			return vcpu;
+	return NULL;
+}
+
+static struct kvm_vcpu_hv_synic *synic_get(struct kvm *kvm, u32 vpidx)
 {
 	struct kvm_vcpu *vcpu;
 	struct kvm_vcpu_hv_synic *synic;
 
-	if (vcpu_id >= atomic_read(&kvm->online_vcpus))
-		return NULL;
-	vcpu = kvm_get_vcpu(kvm, vcpu_id);
+	vcpu = get_vcpu_by_vpidx(kvm, vpidx);
 	if (!vcpu)
 		return NULL;
 	synic = vcpu_to_synic(vcpu);
···
 		synic->version = data;
 		break;
 	case HV_X64_MSR_SIEFP:
-		if (data & HV_SYNIC_SIEFP_ENABLE)
+		if ((data & HV_SYNIC_SIEFP_ENABLE) && !host &&
+		    !synic->dont_zero_synic_pages)
 			if (kvm_clear_guest(vcpu->kvm,
 					    data & PAGE_MASK, PAGE_SIZE)) {
 				ret = 1;
···
 			synic_exit(synic, msr);
 		break;
 	case HV_X64_MSR_SIMP:
-		if (data & HV_SYNIC_SIMP_ENABLE)
+		if ((data & HV_SYNIC_SIMP_ENABLE) && !host &&
+		    !synic->dont_zero_synic_pages)
 			if (kvm_clear_guest(vcpu->kvm,
 					    data & PAGE_MASK, PAGE_SIZE)) {
 				ret = 1;
···
 	return ret;
 }
 
-int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint)
+int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vpidx, u32 sint)
 {
 	struct kvm_vcpu_hv_synic *synic;
 
-	synic = synic_get(kvm, vcpu_id);
+	synic = synic_get(kvm, vpidx);
 	if (!synic)
 		return -EINVAL;
 
···
 			kvm_hv_notify_acked_sint(vcpu, i);
 }
 
-static int kvm_hv_set_sint_gsi(struct kvm *kvm, u32 vcpu_id, u32 sint, int gsi)
+static int kvm_hv_set_sint_gsi(struct kvm *kvm, u32 vpidx, u32 sint, int gsi)
 {
 	struct kvm_vcpu_hv_synic *synic;
 
-	synic = synic_get(kvm, vcpu_id);
+	synic = synic_get(kvm, vpidx);
 	if (!synic)
 		return -EINVAL;
 
···
 		stimer_init(&hv_vcpu->stimer[i], i);
 }
 
-int kvm_hv_activate_synic(struct kvm_vcpu *vcpu)
+void kvm_hv_vcpu_postcreate(struct kvm_vcpu *vcpu)
 {
+	struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu);
+
+	hv_vcpu->vp_index = kvm_vcpu_get_idx(vcpu);
+}
+
+int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages)
+{
+	struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu);
+
 	/*
 	 * Hyper-V SynIC auto EOI SINT's are
 	 * not compatible with APICV, so deactivate APICV
 	 */
 	kvm_vcpu_deactivate_apicv(vcpu);
-	vcpu_to_synic(vcpu)->active = true;
+	synic->active = true;
+	synic->dont_zero_synic_pages = dont_zero_synic_pages;
 	return 0;
 }
 
···
 	struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
 
 	switch (msr) {
+	case HV_X64_MSR_VP_INDEX:
+		if (!host)
+			return 1;
+		hv->vp_index = (u32)data;
+		break;
 	case HV_X64_MSR_APIC_ASSIST_PAGE: {
 		u64 gfn;
 		unsigned long addr;
···
 	struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv;
 
 	switch (msr) {
-	case HV_X64_MSR_VP_INDEX: {
-		int r;
-		struct kvm_vcpu *v;
-
-		kvm_for_each_vcpu(r, v, vcpu->kvm) {
-			if (v == vcpu) {
-				data = r;
-				break;
-			}
-		}
+	case HV_X64_MSR_VP_INDEX:
+		data = hv->vp_index;
 		break;
-	}
 	case HV_X64_MSR_EOI:
 		return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata);
 	case HV_X64_MSR_ICR:

arch/x86/kvm/hyperv.h

···
 void kvm_hv_irq_routing_update(struct kvm *kvm);
 int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint);
 void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector);
-int kvm_hv_activate_synic(struct kvm_vcpu *vcpu);
+int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages);
 
 void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu);
+void kvm_hv_vcpu_postcreate(struct kvm_vcpu *vcpu);
 void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu);
 
 static inline struct kvm_vcpu_hv_stimer *vcpu_to_stimer(struct kvm_vcpu *vcpu,

arch/x86/kvm/i8254.c

···
 	struct kvm_pit *pit = kvm->arch.vpit;
 
 	if (pit) {
+		mutex_lock(&kvm->slots_lock);
 		kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->dev);
 		kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, &pit->speaker_dev);
+		mutex_unlock(&kvm->slots_lock);
 		kvm_pit_set_reinject(pit, false);
 		hrtimer_cancel(&pit->pit_state.timer);
 		kthread_destroy_worker(pit->worker);

arch/x86/kvm/mmu.c

···
 #include <asm/io.h>
 #include <asm/vmx.h>
 #include <asm/kvm_page_track.h>
+#include "trace.h"
 
 /*
  * When setting this variable to true it enables Two-Dimensional-Paging
···
 		     kvm_event_needs_reinjection(vcpu)))
 		return false;
 
-	if (is_guest_mode(vcpu))
+	if (!vcpu->arch.apf.delivery_as_pf_vmexit && is_guest_mode(vcpu))
 		return false;
 
 	return kvm_x86_ops->interrupt_allowed(vcpu);
···
 	*pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, write, writable);
 	return false;
 }
+
+int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
+				u64 fault_address, char *insn, int insn_len,
+				bool need_unprotect)
+{
+	int r = 1;
+
+	switch (vcpu->arch.apf.host_apf_reason) {
+	default:
+		trace_kvm_page_fault(fault_address, error_code);
+
+		if (need_unprotect && kvm_event_needs_reinjection(vcpu))
+			kvm_mmu_unprotect_page_virt(vcpu, fault_address);
+		r = kvm_mmu_page_fault(vcpu, fault_address, error_code, insn,
+				insn_len);
+		break;
+	case KVM_PV_REASON_PAGE_NOT_PRESENT:
+		vcpu->arch.apf.host_apf_reason = 0;
+		local_irq_disable();
+		kvm_async_pf_task_wait(fault_address);
+		local_irq_enable();
+		break;
+	case KVM_PV_REASON_PAGE_READY:
+		vcpu->arch.apf.host_apf_reason = 0;
+		local_irq_disable();
+		kvm_async_pf_task_wake(fault_address);
+		local_irq_enable();
+		break;
+	}
+	return r;
+}
+EXPORT_SYMBOL_GPL(kvm_handle_page_fault);
 
 static bool
 check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level)

arch/x86/kvm/mmu.h

···
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 			     bool accessed_dirty);
 bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);
+int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
+				u64 fault_address, char *insn, int insn_len,
+				bool need_unprotect);
 
 static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
 {

arch/x86/kvm/svm.c

···
 
 	unsigned int3_injected;
 	unsigned long int3_rip;
-	u32 apf_reason;
 
 	/* cached guest cpuid flags for faster access */
 	bool nrips_enabled	: 1;
···
 #ifdef CONFIG_X86_LOCAL_APIC
 module_param(avic, int, S_IRUGO);
 #endif
+
+/* enable/disable Virtual VMLOAD VMSAVE */
+static int vls = true;
+module_param(vls, int, 0444);
 
 /* AVIC VM ID bit masks and lock */
 static DECLARE_BITMAP(avic_vm_id_bitmap, AVIC_VM_ID_NR);
···
 	svm_set_interrupt_shadow(vcpu, 0);
 }
 
-static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
-				bool has_error_code, u32 error_code,
-				bool reinject)
+static void svm_queue_exception(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	unsigned nr = vcpu->arch.exception.nr;
+	bool has_error_code = vcpu->arch.exception.has_error_code;
+	bool reinject = vcpu->arch.exception.reinject;
+	u32 error_code = vcpu->arch.exception.error_code;
 
 	/*
 	 * If we are within a nested VM we'd better #VMEXIT and let the guest
···
 {
 	u32 *msrpm = svm->msrpm;
 
-	svm->vmcb->control.lbr_ctl = 1;
+	svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;
 	set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
 	set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
 	set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
···
 {
 	u32 *msrpm = svm->msrpm;
 
-	svm->vmcb->control.lbr_ctl = 0;
+	svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK;
 	set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0);
 	set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0);
 	set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 0, 0);
···
 			pr_info("AVIC enabled\n");
 
 			amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier);
+		}
+	}
+
+	if (vls) {
+		if (!npt_enabled ||
+		    !boot_cpu_has(X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE) ||
+		    !IS_ENABLED(CONFIG_X86_64)) {
+			vls = false;
+		} else {
+			pr_info("Virtual VMLOAD VMSAVE supported\n");
 		}
 	}
 
···
 
 	if (avic)
 		avic_init_vmcb(svm);
+
+	/*
+	 * If hardware supports Virtual VMLOAD VMSAVE then enable it
+	 * in VMCB and clear intercepts to avoid #VMEXIT.
+	 */
+	if (vls) {
+		clr_intercept(svm, INTERCEPT_VMLOAD);
+		clr_intercept(svm, INTERCEPT_VMSAVE);
+		svm->vmcb->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK;
+	}
 
 	mark_all_dirty(svm->vmcb);
 
···
 static int pf_interception(struct vcpu_svm *svm)
 {
 	u64 fault_address = svm->vmcb->control.exit_info_2;
-	u64 error_code;
-	int r = 1;
+	u64 error_code = svm->vmcb->control.exit_info_1;
 
-	switch (svm->apf_reason) {
-	default:
-		error_code = svm->vmcb->control.exit_info_1;
-
-		trace_kvm_page_fault(fault_address, error_code);
-		if (!npt_enabled && kvm_event_needs_reinjection(&svm->vcpu))
-			kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address);
-		r = kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code,
+	return kvm_handle_page_fault(&svm->vcpu, error_code, fault_address,
 			svm->vmcb->control.insn_bytes,
-			svm->vmcb->control.insn_len);
-		break;
-	case KVM_PV_REASON_PAGE_NOT_PRESENT:
-		svm->apf_reason = 0;
-		local_irq_disable();
-		kvm_async_pf_task_wait(fault_address);
-		local_irq_enable();
-		break;
-	case KVM_PV_REASON_PAGE_READY:
-		svm->apf_reason = 0;
-		local_irq_disable();
-		kvm_async_pf_task_wake(fault_address);
-		local_irq_enable();
-		break;
-	}
-	return r;
+			svm->vmcb->control.insn_len, !npt_enabled);
 }
 
 static int db_interception(struct vcpu_svm *svm)
···
 {
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 	u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */
-	int size, in, string;
+	int size, in, string, ret;
 	unsigned port;
 
 	++svm->vcpu.stat.io_exits;
···
 	port = io_info >> 16;
 	size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
 	svm->next_rip = svm->vmcb->control.exit_info_2;
-	skip_emulated_instruction(&svm->vcpu);
+	ret = kvm_skip_emulated_instruction(&svm->vcpu);
 
-	return in ? kvm_fast_pio_in(vcpu, size, port)
-		  : kvm_fast_pio_out(vcpu, size, port);
+	/*
+	 * TODO: we might be squashing a KVM_GUESTDBG_SINGLESTEP-triggered
+	 * KVM_EXIT_DEBUG here.
+	 */
+	if (in)
+		return kvm_fast_pio_in(vcpu, size, port) && ret;
+	else
+		return kvm_fast_pio_out(vcpu, size, port) && ret;
 }
 
 static int nmi_interception(struct vcpu_svm *svm)
···
 	if (!is_guest_mode(&svm->vcpu))
 		return 0;
 
+	vmexit = nested_svm_intercept(svm);
+	if (vmexit != NESTED_EXIT_DONE)
+		return 0;
+
 	svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr;
 	svm->vmcb->control.exit_code_hi = 0;
 	svm->vmcb->control.exit_info_1 = error_code;
-	svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
+	if (svm->vcpu.arch.exception.nested_apf)
+		svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token;
+	else
+		svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
 
-	vmexit = nested_svm_intercept(svm);
-	if (vmexit == NESTED_EXIT_DONE)
-		svm->nested.exit_required = true;
-
+	svm->nested.exit_required = true;
 	return vmexit;
 }
 
···
 		break;
 	case SVM_EXIT_EXCP_BASE + PF_VECTOR:
 		/* When we're shadowing, trap PFs, but not async PF */
-		if (!npt_enabled && svm->apf_reason == 0)
+		if (!npt_enabled && svm->vcpu.arch.apf.host_apf_reason == 0)
 			return NESTED_EXIT_HOST;
 		break;
 	default:
···
 		}
 		/* async page fault always cause vmexit */
 		else if ((exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) &&
-			 svm->apf_reason != 0)
+			 svm->vcpu.arch.exception.nested_apf != 0)
 			vmexit = NESTED_EXIT_DONE;
 		break;
 	}
···
 	dst->event_inj            = from->event_inj;
 	dst->event_inj_err        = from->event_inj_err;
 	dst->nested_cr3           = from->nested_cr3;
-	dst->lbr_ctl              = from->lbr_ctl;
+	dst->virt_ext              = from->virt_ext;
 }
 
 static int nested_svm_vmexit(struct vcpu_svm *svm)
···
 	/* We don't want to see VMMCALLs from a nested guest */
 	clr_intercept(svm, INTERCEPT_VMMCALL);
 
-	svm->vmcb->control.lbr_ctl = nested_vmcb->control.lbr_ctl;
+	svm->vmcb->control.virt_ext = nested_vmcb->control.virt_ext;
 	svm->vmcb->control.int_vector = nested_vmcb->control.int_vector;
 	svm->vmcb->control.int_state = nested_vmcb->control.int_state;
 	svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset;
···
 {
 	struct vmcb *nested_vmcb;
 	struct page *page;
+	int ret;
 
 	if (nested_svm_check_permissions(svm))
 		return 1;
···
 		return 1;
 
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
-	skip_emulated_instruction(&svm->vcpu);
+	ret = kvm_skip_emulated_instruction(&svm->vcpu);
 
 	nested_svm_vmloadsave(nested_vmcb, svm->vmcb);
 	nested_svm_unmap(page);
 
-	return 1;
+	return ret;
 }
 
 static int vmsave_interception(struct vcpu_svm *svm)
 {
 	struct vmcb *nested_vmcb;
 	struct page *page;
+	int ret;
 
 	if (nested_svm_check_permissions(svm))
 		return 1;
···
 		return 1;
 
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
-	skip_emulated_instruction(&svm->vcpu);
+	ret = kvm_skip_emulated_instruction(&svm->vcpu);
 
 	nested_svm_vmloadsave(svm->vmcb, nested_vmcb);
 	nested_svm_unmap(page);
 
-	return 1;
+	return ret;
 }
 
 static int vmrun_interception(struct vcpu_svm *svm)
···
 
 static int stgi_interception(struct vcpu_svm *svm)
 {
+	int ret;
+
 	if (nested_svm_check_permissions(svm))
 		return 1;
 
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
-	skip_emulated_instruction(&svm->vcpu);
+	ret = kvm_skip_emulated_instruction(&svm->vcpu);
 	kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
 
 	enable_gif(svm);
 
-	return 1;
+	return ret;
 }
 
 static int clgi_interception(struct vcpu_svm *svm)
 {
+	int ret;
+
 	if (nested_svm_check_permissions(svm))
 		return 1;
 
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
-	skip_emulated_instruction(&svm->vcpu);
+	ret = kvm_skip_emulated_instruction(&svm->vcpu);
 
 	disable_gif(svm);
 
···
 		mark_dirty(svm->vmcb, VMCB_INTR);
 	}
 
-	return 1;
+	return ret;
 }
 
 static int invlpga_interception(struct vcpu_svm *svm)
···
 	kvm_mmu_invlpg(vcpu, kvm_register_read(&svm->vcpu, VCPU_REGS_RAX));
 
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
-	skip_emulated_instruction(&svm->vcpu);
-	return 1;
+	return kvm_skip_emulated_instruction(&svm->vcpu);
 }
 
 static int skinit_interception(struct vcpu_svm *svm)
···
 
 	if (kvm_set_xcr(&svm->vcpu, index, new_bv) == 0) {
 		svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
-		skip_emulated_instruction(&svm->vcpu);
+		return kvm_skip_emulated_instruction(&svm->vcpu);
 	}
 
 	return 1;
···
 		return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE;
 
 	kvm_mmu_invlpg(&svm->vcpu, svm->vmcb->control.exit_info_1);
-	skip_emulated_instruction(&svm->vcpu);
-	return 1;
+	return kvm_skip_emulated_instruction(&svm->vcpu);
 }
 
 static int emulate_on_interception(struct vcpu_svm *svm)
···
 		kvm_register_write(&svm->vcpu, reg, val);
 	}
 
-	skip_emulated_instruction(&svm->vcpu);
-
-	return 1;
+	return kvm_skip_emulated_instruction(&svm->vcpu);
 }
 
 static int cr8_write_interception(struct vcpu_svm *svm)
···
 	if (svm_get_msr(&svm->vcpu, &msr_info)) {
 		trace_kvm_msr_read_ex(ecx);
 		kvm_inject_gp(&svm->vcpu, 0);
+		return 1;
 	} else {
 		trace_kvm_msr_read(ecx, msr_info.data);
 
···
 		kvm_register_write(&svm->vcpu, VCPU_REGS_RDX,
 				   msr_info.data >> 32);
 		svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
-		skip_emulated_instruction(&svm->vcpu);
+		return kvm_skip_emulated_instruction(&svm->vcpu);
 	}
-	return 1;
 }
 
 static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data)
···
 	if (kvm_set_msr(&svm->vcpu, &msr)) {
 		trace_kvm_msr_write_ex(ecx, data);
 		kvm_inject_gp(&svm->vcpu, 0);
+		return 1;
 	} else {
 		trace_kvm_msr_write(ecx, data);
-		skip_emulated_instruction(&svm->vcpu);
+		return kvm_skip_emulated_instruction(&svm->vcpu);
 	}
-	return 1;
 }
 
 static int msr_interception(struct vcpu_svm *svm)
···
 
 static int nop_interception(struct vcpu_svm *svm)
 {
-	skip_emulated_instruction(&(svm->vcpu));
-	return 1;
+	return kvm_skip_emulated_instruction(&(svm->vcpu));
 }
 
 static int monitor_interception(struct vcpu_svm *svm)
···
 	pr_err("%-20s%016llx\n", "avic_vapic_bar:", control->avic_vapic_bar);
 	pr_err("%-20s%08x\n", "event_inj:", control->event_inj);
 	pr_err("%-20s%08x\n", "event_inj_err:", control->event_inj_err);
-	pr_err("%-20s%lld\n", "lbr_ctl:", control->lbr_ctl);
+	pr_err("%-20s%lld\n", "virt_ext:", control->virt_ext);
 	pr_err("%-20s%016llx\n", "next_rip:", control->next_rip);
 	pr_err("%-20s%016llx\n", "avic_backing_page:", control->avic_backing_page);
 	pr_err("%-20s%016llx\n", "avic_logical_id:", control->avic_logical_id);
···
 
 	/* if exit due to PF check for async PF */
 	if (svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR)
-		svm->apf_reason = kvm_read_and_reset_pf_reason();
+		svm->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason();
 
 	if (npt_enabled) {
 		vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR);

arch/x86/kvm/vmx.c

···
  * KVM wants to inject page-faults which it got to the guest. This function
  * checks whether in a nested guest, we need to inject them to L1 or L2.
  */
-static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr)
+static int nested_vmx_check_exception(struct kvm_vcpu *vcpu)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	unsigned int nr = vcpu->arch.exception.nr;
 
-	if (!(vmcs12->exception_bitmap & (1u << nr)))
+	if (!((vmcs12->exception_bitmap & (1u << nr)) ||
+		(nr == PF_VECTOR && vcpu->arch.exception.nested_apf)))
 		return 0;
+
+	if (vcpu->arch.exception.nested_apf) {
+		vmcs_write32(VM_EXIT_INTR_ERROR_CODE, vcpu->arch.exception.error_code);
+		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
+			PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
+			INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK,
+			vcpu->arch.apf.nested_apf_token);
+		return 1;
+	}
 
 	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
 			  vmcs_read32(VM_EXIT_INTR_INFO),
···
 	return 1;
 }
 
-static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
-				bool has_error_code, u32 error_code,
-				bool reinject)
+static void vmx_queue_exception(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned nr = vcpu->arch.exception.nr;
+	bool has_error_code = vcpu->arch.exception.has_error_code;
+	bool reinject = vcpu->arch.exception.reinject;
+	u32 error_code = vcpu->arch.exception.error_code;
 	u32 intr_info = nr | INTR_INFO_VALID_MASK;
 
 	if (!reinject && is_guest_mode(vcpu) &&
-	    nested_vmx_check_exception(vcpu, nr))
+	    nested_vmx_check_exception(vcpu))
 		return;
 
 	if (has_error_code) {
···
 	}
 }
 
+enum vmcs_field_type {
+	VMCS_FIELD_TYPE_U16 = 0,
+	VMCS_FIELD_TYPE_U64 = 1,
+	VMCS_FIELD_TYPE_U32 = 2,
+	VMCS_FIELD_TYPE_NATURAL_WIDTH = 3
+};
+
+static inline int vmcs_field_type(unsigned long field)
+{
+	if (0x1 & field)	/* the *_HIGH fields are all 32 bit */
+		return VMCS_FIELD_TYPE_U32;
+	return (field >> 13) & 0x3 ;
+}
+
+static inline int vmcs_field_readonly(unsigned long field)
+{
+	return (((field >> 10) & 0x3) == 1);
+}
+
 static void init_vmcs_shadow_fields(void)
 {
 	int i, j;
···
 
 	/* shadowed fields guest access without vmexit */
 	for (i = 0; i < max_shadow_read_write_fields; i++) {
-		clear_bit(shadow_read_write_fields[i],
-			  vmx_vmwrite_bitmap);
-		clear_bit(shadow_read_write_fields[i],
-			  vmx_vmread_bitmap);
+		unsigned long field = shadow_read_write_fields[i];
+
+		clear_bit(field, vmx_vmwrite_bitmap);
+		clear_bit(field, vmx_vmread_bitmap);
+		if (vmcs_field_type(field) == VMCS_FIELD_TYPE_U64) {
+			clear_bit(field + 1, vmx_vmwrite_bitmap);
+			clear_bit(field + 1, vmx_vmread_bitmap);
+		}
 	}
-	for (i = 0; i < max_shadow_read_only_fields; i++)
-		clear_bit(shadow_read_only_fields[i],
-			  vmx_vmread_bitmap);
+	for (i = 0; i < max_shadow_read_only_fields; i++) {
+		unsigned long field = shadow_read_only_fields[i];
+
+		clear_bit(field, vmx_vmread_bitmap);
+		if (vmcs_field_type(field) == VMCS_FIELD_TYPE_U64)
+			clear_bit(field + 1, vmx_vmread_bitmap);
+	}
 }
 
 static __init int alloc_kvm_area(void)
···
 	 */
 
 	return true;
+}
+
+static bool page_address_valid(struct kvm_vcpu *vcpu, gpa_t gpa)
+{
+	return PAGE_ALIGNED(gpa) && !(gpa >> cpuid_maxphyaddr(vcpu));
 }
 
 static int init_rmode_tss(struct kvm *kvm)
···
 	}
 
 	if (is_page_fault(intr_info)) {
-		/* EPT won't cause page fault directly */
-		BUG_ON(enable_ept);
 		cr2 = vmcs_readl(EXIT_QUALIFICATION);
-		trace_kvm_page_fault(cr2, error_code);
-
-		if (kvm_event_needs_reinjection(vcpu))
-			kvm_mmu_unprotect_page_virt(vcpu, cr2);
-		return kvm_mmu_page_fault(vcpu, cr2, error_code, NULL, 0);
+		/* EPT won't cause page fault directly */
+		WARN_ON_ONCE(!vcpu->arch.apf.host_apf_reason && enable_ept);
+		return kvm_handle_page_fault(vcpu, error_code, cr2, NULL, 0,
+				true);
 	}
 
 	ex_no = intr_info & INTR_INFO_VECTOR_MASK;
···
 	return nested_vmx_run(vcpu, false);
 }
 
-enum vmcs_field_type {
-	VMCS_FIELD_TYPE_U16 = 0,
-	VMCS_FIELD_TYPE_U64 = 1,
-	VMCS_FIELD_TYPE_U32 = 2,
-	VMCS_FIELD_TYPE_NATURAL_WIDTH = 3
-};
-
-static inline int vmcs_field_type(unsigned long field)
-{
-	if (0x1 & field)	/* the *_HIGH fields are all 32 bit */
-		return VMCS_FIELD_TYPE_U32;
-	return (field >> 13) & 0x3 ;
-}
-
-static inline int vmcs_field_readonly(unsigned long field)
-{
-	return (((field >> 10) & 0x3) == 1);
-}
-
 /*
  * Read a vmcs12 field. Since these can have varying lengths and we return
  * one type, we chose the biggest type (u64) and zero-extend the return value
···
 		if (is_nmi(intr_info))
 			return false;
 		else if (is_page_fault(intr_info))
-			return enable_ept;
+			return !vmx->vcpu.arch.apf.host_apf_reason && enable_ept;
 		else if (is_no_device(intr_info) &&
 			 !(vmcs12->guest_cr0 & X86_CR0_TS))
 			return false;
···
 			exit_reason != EXIT_REASON_TASK_SWITCH)) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
-		vcpu->run->internal.ndata = 2;
+		vcpu->run->internal.ndata = 3;
 		vcpu->run->internal.data[0] = vectoring_info;
 		vcpu->run->internal.data[1] = exit_reason;
+		vcpu->run->internal.data[2] = vcpu->arch.exit_qualification;
+		if (exit_reason == EXIT_REASON_EPT_MISCONFIG) {
+			vcpu->run->internal.ndata++;
+			vcpu->run->internal.data[3] =
+				vmcs_read64(GUEST_PHYSICAL_ADDRESS);
+		}
 		return 0;
 	}
 
···
 
 static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
 {
-	u32 exit_intr_info;
+	u32 exit_intr_info = 0;
+	u16 basic_exit_reason = (u16)vmx->exit_reason;
 
-	if (!(vmx->exit_reason == EXIT_REASON_MCE_DURING_VMENTRY
-	      || vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI))
+	if (!(basic_exit_reason == EXIT_REASON_MCE_DURING_VMENTRY
+	      || basic_exit_reason == EXIT_REASON_EXCEPTION_NMI))
 		return;
 
-	vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
-	exit_intr_info = vmx->exit_intr_info;
+	if (!(vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY))
+		exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+	vmx->exit_intr_info = exit_intr_info;
+
+	/* if exit due to PF check for async PF */
+	if (is_page_fault(exit_intr_info))
+		vmx->vcpu.arch.apf.host_apf_reason = kvm_read_and_reset_pf_reason();
 
 	/* Handle machine checks before interrupts are enabled */
-	if (is_machine_check(exit_intr_info))
+	if (basic_exit_reason == EXIT_REASON_MCE_DURING_VMENTRY ||
+	    is_machine_check(exit_intr_info))
 		kvm_machine_check();
 
 	/* We need to handle NMIs before interrupts are enabled */
···
 		      ns_to_ktime(preemption_timeout), HRTIMER_MODE_REL);
 }
 
+static int nested_vmx_check_io_bitmap_controls(struct kvm_vcpu *vcpu,
+					       struct vmcs12 *vmcs12)
+{
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
+		return 0;
+
+	if (!page_address_valid(vcpu, vmcs12->io_bitmap_a) ||
+	    !page_address_valid(vcpu, vmcs12->io_bitmap_b))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int nested_vmx_check_msr_bitmap_controls(struct kvm_vcpu *vcpu,
 						struct vmcs12 *vmcs12)
 {
-	int maxphyaddr;
-	u64 addr;
-
 	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
 		return 0;
 
-	if (vmcs12_read_any(vcpu, MSR_BITMAP, &addr)) {
-		WARN_ON(1);
-		return -EINVAL;
-	}
-	maxphyaddr = cpuid_maxphyaddr(vcpu);
-
-	if (!PAGE_ALIGNED(vmcs12->msr_bitmap) ||
-	   ((addr + PAGE_SIZE) >> maxphyaddr))
+	if (!page_address_valid(vcpu, vmcs12->msr_bitmap))
 		return -EINVAL;
 
 	return 0;
···
 	    vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT)
 		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
 
+	if (nested_vmx_check_io_bitmap_controls(vcpu, vmcs12))
+		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
 	if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12))
 		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
 
···
 				EXIT_REASON_MSR_LOAD_FAIL, msr_entry_idx);
 		return 1;
 	}
-
-	vmcs12->launch_state = 1;
 
 	/*
 	 * Note no nested_vmx_succeed or nested_vmx_fail here. At this point
···
 	vmcs12->vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
 
 	if (!(vmcs12->vm_exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) {
+		vmcs12->launch_state = 1;
+
 		/* vm_entry_intr_info_field is cleared on exit. Emulate this
 		 * instead of reading the real value. */
 		vmcs12->vm_entry_intr_info_field &= ~INTR_INFO_VALID_MASK;

arch/x86/kvm/x86.c

···
 static bool __read_mostly vector_hashing = true;
 module_param(vector_hashing, bool, S_IRUGO);
 
-static bool __read_mostly backwards_tsc_observed = false;
-
 #define KVM_NR_SHARED_MSRS 16
 
 struct kvm_shared_msrs_global {
···
 void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
 {
 	++vcpu->stat.pf_guest;
-	vcpu->arch.cr2 = fault->address;
+	vcpu->arch.exception.nested_apf =
+		is_guest_mode(vcpu) && fault->async_page_fault;
+	if (vcpu->arch.exception.nested_apf)
+		vcpu->arch.apf.nested_apf_token = fault->address;
+	else
+		vcpu->arch.cr2 = fault->address;
 	kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code);
 }
 EXPORT_SYMBOL_GPL(kvm_inject_page_fault);
···
 					&ka->master_cycle_now);
 
 	ka->use_master_clock = host_tsc_clocksource && vcpus_matched
-				&& !backwards_tsc_observed
+				&& !ka->backwards_tsc_observed
 				&& !ka->boot_vcpu_runs_old_kvmclock;
 
 	if (ka->use_master_clock)
···
 {
 	gpa_t gpa = data & ~0x3f;
 
-	/* Bits 2:5 are reserved, Should be zero */
-	if (data & 0x3c)
+	/* Bits 3:5 are reserved, Should be zero */
+	if (data & 0x38)
 		return 1;
 
 	vcpu->arch.apf.msr_val = data;
···
 		return 1;
 
 	vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
+	vcpu->arch.apf.delivery_as_pf_vmexit = data & KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;
 	kvm_async_pf_wakeup_all(vcpu);
 	return 0;
 }
···
 	case KVM_CAP_HYPERV_VAPIC:
 	case KVM_CAP_HYPERV_SPIN:
 	case KVM_CAP_HYPERV_SYNIC:
+	case KVM_CAP_HYPERV_SYNIC2:
+	case KVM_CAP_HYPERV_VP_INDEX:
 	case KVM_CAP_PCI_SEGMENT:
 	case KVM_CAP_DEBUGREGS:
 	case KVM_CAP_X86_ROBUST_SINGLESTEP:
···
 		return -EINVAL;
 
 	switch (cap->cap) {
+	case KVM_CAP_HYPERV_SYNIC2:
+		if (cap->args[0])
+			return -EINVAL;
 	case KVM_CAP_HYPERV_SYNIC:
 		if (!irqchip_in_kernel(vcpu->kvm))
 			return -EINVAL;
-		return kvm_hv_activate_synic(vcpu);
+		return kvm_hv_activate_synic(vcpu, cap->cap ==
+					     KVM_CAP_HYPERV_SYNIC2);
 	default:
 		return -EINVAL;
 	}
···
 			goto out;
 
 		r = 0;
+		/*
+		 * TODO: userspace has to take care of races with VCPU_RUN, so
+		 * kvm_gen_update_masterclock() can be cut down to locked
+		 * pvclock_update_vm_gtod_copy().
+		 */
+		kvm_gen_update_masterclock(kvm);
 		now_ns = get_kvmclock_ns(kvm);
 		kvm->arch.kvmclock_offset += user_ns.clock - now_ns;
-		kvm_gen_update_masterclock(kvm);
+		kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE);
 		break;
 	}
 	case KVM_GET_CLOCK: {
···
 			kvm_update_dr7(vcpu);
 		}
 
-		kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr,
-					  vcpu->arch.exception.has_error_code,
-					  vcpu->arch.exception.error_code,
-					  vcpu->arch.exception.reinject);
+		kvm_x86_ops->queue_exception(vcpu);
 		return 0;
 	}
 
···
 	struct msr_data msr;
 	struct kvm *kvm = vcpu->kvm;
 
+	kvm_hv_vcpu_postcreate(vcpu);
+
 	if (vcpu_load(vcpu))
 		return;
 	msr.data = 0x0;
···
 	 */
 	if (backwards_tsc) {
 		u64 delta_cyc = max_tsc - local_tsc;
-		backwards_tsc_observed = true;
 		list_for_each_entry(kvm, &vm_list, vm_list) {
+			kvm->arch.backwards_tsc_observed = true;
 			kvm_for_each_vcpu(i, vcpu, kvm) {
 				vcpu->arch.tsc_offset_adjustment += delta_cyc;
 				vcpu->arch.last_host_tsc = local_tsc;
···
 		fault.error_code = 0;
 		fault.nested_page_fault = false;
 		fault.address = work->arch.token;
+		fault.async_page_fault = true;
 		kvm_inject_page_fault(vcpu, &fault);
 	}
 }
···
 		fault.error_code = 0;
 		fault.nested_page_fault = false;
 		fault.address = work->arch.token;
+		fault.async_page_fault = true;
 		kvm_inject_page_fault(vcpu, &fault);
 	}
 	vcpu->arch.apf.halted = false;

include/linux/kvm_host.h

···
 
 	int guest_fpu_loaded, guest_xcr0_loaded;
 	struct swait_queue_head wq;
-	struct pid *pid;
+	struct pid __rcu *pid;
 	int sigset_active;
 	sigset_t sigset;
 	struct kvm_vcpu_stat stat;
···
 	spinlock_t mmu_lock;
 	struct mutex slots_lock;
 	struct mm_struct *mm; /* userspace tied to this vm */
-	struct kvm_memslots *memslots[KVM_ADDRESS_SPACE_NUM];
+	struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM];
 	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
 
 	/*
···
 	int last_boosted_vcpu;
 	struct list_head vm_list;
 	struct mutex lock;
-	struct kvm_io_bus *buses[KVM_NR_BUSES];
+	struct kvm_io_bus __rcu *buses[KVM_NR_BUSES];
 #ifdef CONFIG_HAVE_KVM_EVENTFD
 	struct {
 		spinlock_t        lock;
···
 			      ## __VA_ARGS__)
 #define vcpu_err(vcpu, fmt, ...)					\
 	kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__)
+
+static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx)
+{
+	return srcu_dereference_check(kvm->buses[idx], &kvm->srcu,
+				      lockdep_is_held(&kvm->slots_lock));
+}
 
 static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
 {
···
 
 static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
 {
-	return rcu_dereference_check(kvm->memslots[as_id],
-			srcu_read_lock_held(&kvm->srcu)
-			|| lockdep_is_held(&kvm->slots_lock));
+	return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu,
+			lockdep_is_held(&kvm->slots_lock));
 }
 
 static inline struct kvm_memslots *kvm_memslots(struct kvm *kvm)

include/uapi/linux/kvm.h

···
 #define KVM_CAP_S390_CMMA_MIGRATION 145
 #define KVM_CAP_PPC_FWNMI 146
 #define KVM_CAP_PPC_SMT_POSSIBLE 147
+#define KVM_CAP_HYPERV_SYNIC2 148
+#define KVM_CAP_HYPERV_VP_INDEX 149
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
···
 /* Available with KVM_CAP_X86_SMM */
 #define KVM_SMI                   _IO(KVMIO,   0xb7)
 /* Available with KVM_CAP_S390_CMMA_MIGRATION */
-#define KVM_S390_GET_CMMA_BITS      _IOW(KVMIO, 0xb8, struct kvm_s390_cmma_log)
+#define KVM_S390_GET_CMMA_BITS      _IOWR(KVMIO, 0xb8, struct kvm_s390_cmma_log)
 #define KVM_S390_SET_CMMA_BITS      _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log)
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)

virt/kvm/eventfd.c

···
 	if (ret < 0)
 		goto unlock_fail;
 
-	kvm->buses[bus_idx]->ioeventfd_count++;
+	kvm_get_bus(kvm, bus_idx)->ioeventfd_count++;
 	list_add_tail(&p->list, &kvm->ioeventfds);
 
 	mutex_unlock(&kvm->slots_lock);
···
 {
 	struct _ioeventfd        *p, *tmp;
 	struct eventfd_ctx       *eventfd;
+	struct kvm_io_bus	 *bus;
 	int                       ret = -ENOENT;
 
 	eventfd = eventfd_ctx_fdget(args->fd);
···
 			continue;
 
 		kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
-		if (kvm->buses[bus_idx])
-			kvm->buses[bus_idx]->ioeventfd_count--;
+		bus = kvm_get_bus(kvm, bus_idx);
+		if (bus)
+			bus->ioeventfd_count--;
 		ioeventfd_release(p);
 		ret = 0;
 		break;

virt/kvm/irqchip.c

···
 	}
 
 	mutex_lock(&kvm->irq_lock);
-	old = kvm->irq_routing;
+	old = rcu_dereference_protected(kvm->irq_routing, 1);
 	rcu_assign_pointer(kvm->irq_routing, new);
 	kvm_irq_routing_update(kvm);
 	kvm_arch_irq_routing_update(kvm);

virt/kvm/kvm_main.c

···
 
 static bool largepages_enabled = true;
 
+#define KVM_EVENT_CREATE_VM 0
+#define KVM_EVENT_DESTROY_VM 1
+static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm);
+static unsigned long long kvm_createvm_count;
+static unsigned long long kvm_active_vms;
+
 bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
 {
 	if (pfn_valid(pfn))
···
 {
 }
 
+static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait)
+{
+	if (unlikely(!cpus))
+		cpus = cpu_online_mask;
+
+	if (cpumask_empty(cpus))
+		return false;
+
+	smp_call_function_many(cpus, ack_flush, NULL, wait);
+	return true;
+}
+
 bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
 {
 	int i, cpu, me;
 	cpumask_var_t cpus;
-	bool called = true;
-	bool wait = req & KVM_REQUEST_WAIT;
+	bool called;
 	struct kvm_vcpu *vcpu;
 
 	zalloc_cpumask_var(&cpus, GFP_ATOMIC);
···
 
 		if (cpus != NULL && cpu != -1 && cpu != me &&
 		    kvm_request_needs_ipi(vcpu, req))
-			cpumask_set_cpu(cpu, cpus);
+			__cpumask_set_cpu(cpu, cpus);
 	}
-	if (unlikely(cpus == NULL))
-		smp_call_function_many(cpu_online_mask, ack_flush, NULL, wait);
-	else if (!cpumask_empty(cpus))
-		smp_call_function_many(cpus, ack_flush, NULL, wait);
-	else
-		called = false;
+	called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT));
 	put_cpu();
 	free_cpumask_var(cpus);
 	return called;
···
 
 void kvm_vcpu_uninit(struct kvm_vcpu *vcpu)
 {
-	put_pid(vcpu->pid);
+	/*
+	 * no need for rcu_read_lock as VCPU_RUN is the only place that
+	 * will change the vcpu->pid pointer and on uninit all file
+	 * descriptors are already gone.
+	 */
+	put_pid(rcu_dereference_protected(vcpu->pid, 1));
 	kvm_arch_vcpu_uninit(vcpu);
 	free_page((unsigned long)vcpu->run);
 }
···
 	if (init_srcu_struct(&kvm->irq_srcu))
 		goto out_err_no_irq_srcu;
 	for (i = 0; i < KVM_NR_BUSES; i++) {
-		kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus),
-					GFP_KERNEL);
+		rcu_assign_pointer(kvm->buses[i],
+			kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL));
 		if (!kvm->buses[i])
 			goto out_err;
 	}
···
 	hardware_disable_all();
 out_err_no_disable:
 	for (i = 0; i < KVM_NR_BUSES; i++)
-		kfree(kvm->buses[i]);
+		kfree(rcu_access_pointer(kvm->buses[i]));
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
-		kvm_free_memslots(kvm, kvm->memslots[i]);
+		kvm_free_memslots(kvm,
+			rcu_dereference_protected(kvm->memslots[i], 1));
 	kvm_arch_free_vm(kvm);
 	mmdrop(current->mm);
 	return ERR_PTR(r);
···
 	int i;
 	struct mm_struct *mm = kvm->mm;
 
+	kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm);
 	kvm_destroy_vm_debugfs(kvm);
 	kvm_arch_sync_events(kvm);
 	spin_lock(&kvm_lock);
···
 	spin_unlock(&kvm_lock);
 	kvm_free_irq_routing(kvm);
 	for (i = 0; i < KVM_NR_BUSES; i++) {
-		if (kvm->buses[i])
-			kvm_io_bus_destroy(kvm->buses[i]);
+		struct kvm_io_bus *bus;
+
+		bus = rcu_dereference_protected(kvm->buses[i], 1);
+		if (bus)
+			kvm_io_bus_destroy(bus);
 		kvm->buses[i] = NULL;
 	}
 	kvm_coalesced_mmio_free(kvm);
···
 	kvm_arch_destroy_vm(kvm);
 	kvm_destroy_devices(kvm);
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
-		kvm_free_memslots(kvm, kvm->memslots[i]);
+		kvm_free_memslots(kvm,
+			rcu_dereference_protected(kvm->memslots[i], 1));
 	cleanup_srcu_struct(&kvm->irq_srcu);
 	cleanup_srcu_struct(&kvm->srcu);
 	kvm_arch_free_vm(kvm);
···
 	if (r)
 		return r;
 	switch (ioctl) {
-	case KVM_RUN:
+	case KVM_RUN: {
+		struct pid *oldpid;
 		r = -EINVAL;
 		if (arg)
 			goto out;
-		if (unlikely(vcpu->pid != current->pids[PIDTYPE_PID].pid)) {
+		oldpid = rcu_access_pointer(vcpu->pid);
+		if (unlikely(oldpid != current->pids[PIDTYPE_PID].pid)) {
 			/* The thread running this VCPU changed. */
-			struct pid *oldpid = vcpu->pid;
 			struct pid *newpid = get_task_pid(current, PIDTYPE_PID);
 
 			rcu_assign_pointer(vcpu->pid, newpid);
···
 		r = kvm_arch_vcpu_ioctl_run(vcpu, vcpu->run);
 		trace_kvm_userspace_exit(vcpu->run->exit_reason, r);
 		break;
+	}
 	case KVM_GET_REGS: {
 		struct kvm_regs *kvm_regs;
 
···
 		fput(file);
 		return -ENOMEM;
 	}
+	kvm_uevent_notify_change(KVM_EVENT_CREATE_VM, kvm);
 
 	fd_install(r, file);
 	return r;
···
 {
 	struct kvm_io_bus *new_bus, *bus;
 
-	bus = kvm->buses[bus_idx];
+	bus = kvm_get_bus(kvm, bus_idx);
 	if (!bus)
 		return -ENOMEM;
 
···
 	int i;
 	struct kvm_io_bus *new_bus, *bus;
 
-	bus = kvm->buses[bus_idx];
+	bus = kvm_get_bus(kvm, bus_idx);
 	if (!bus)
 		return;
 
···
 	[KVM_STAT_VCPU] = &vcpu_stat_fops,
 	[KVM_STAT_VM]   = &vm_stat_fops,
 };
+
+static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
+{
+	struct kobj_uevent_env *env;
+	char *tmp, *pathbuf = NULL;
+	unsigned long long created, active;
+
+	if (!kvm_dev.this_device || !kvm)
+		return;
+
+	spin_lock(&kvm_lock);
+	if (type == KVM_EVENT_CREATE_VM) {
+		kvm_createvm_count++;
+		kvm_active_vms++;
+	} else if (type == KVM_EVENT_DESTROY_VM) {
+		kvm_active_vms--;
+	}
+	created = kvm_createvm_count;
+	active = kvm_active_vms;
+	spin_unlock(&kvm_lock);
+
+	env = kzalloc(sizeof(*env), GFP_KERNEL);
+	if (!env)
+		return;
+
+	add_uevent_var(env, "CREATED=%llu", created);
+	add_uevent_var(env, "COUNT=%llu", active);
+
+	if (type == KVM_EVENT_CREATE_VM)
+		add_uevent_var(env, "EVENT=create");
+	else if (type == KVM_EVENT_DESTROY_VM)
+		add_uevent_var(env, "EVENT=destroy");
+
+	if (kvm->debugfs_dentry) {
+		char p[ITOA_MAX_LEN];
+
+		snprintf(p, sizeof(p), "%s", kvm->debugfs_dentry->d_name.name);
+		tmp = strchrnul(p + 1, '-');
+		*tmp = '\0';
+		add_uevent_var(env, "PID=%s", p);
+		pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
+		if (pathbuf) {
+			/* sizeof counts the final '\0' */
+			int len = sizeof("STATS_PATH=") - 1;
+			const char *pvar = "STATS_PATH=";
+
+			tmp = dentry_path_raw(kvm->debugfs_dentry,
+					      pathbuf + len,
+					      PATH_MAX - len);
+			if (!IS_ERR(tmp)) {
+				memcpy(tmp - len, pvar, len);
+				env->envp[env->envp_idx++] = tmp - len;
+			}
+		}
+	}
+	/* no need for checks, since we are adding at most only 5 keys */
+	env->envp[env->envp_idx++] = NULL;
+	kobject_uevent_env(&kvm_dev.this_device->kobj, KOBJ_CHANGE, env->envp);
+	kfree(env);
+	kfree(pathbuf);
+}
 
 static int kvm_init_debug(void)
 {