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

@@ -4329,3 +4329,21 @@ Querying this capability returns a bitmap indicating the possible
 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

@@ -166,10 +166,11 @@ MSR_KVM_SYSTEM_TIME: 0x12
 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

@@ -286,6 +286,7 @@
 #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

@@ -23,6 +23,7 @@ struct x86_exception {
 	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

@@ -462,10 +462,12 @@ struct kvm_vcpu_hv_synic {
 	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;
@@ -549,6 +551,7 @@ struct kvm_vcpu_arch {
 		bool reinject;
 		u8 nr;
 		u32 error_code;
+		u8 nested_apf;
 	} exception;
 
 	struct kvm_queued_interrupt {
@@ -649,6 +652,9 @@ struct kvm_vcpu_arch {
 		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) */
@@ -803,6 +809,7 @@ struct kvm_arch {
 	int audit_point;
 	#endif
 
+	bool backwards_tsc_observed;
 	bool boot_vcpu_runs_old_kvmclock;
 	u32 bsp_vcpu_id;
 
@@ -952,9 +959,7 @@ struct kvm_x86_ops {
 				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

@@ -83,7 +83,7 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 	u32 event_inj;
 	u32 event_inj_err;
 	u64 nested_cr3;
-	u64 lbr_ctl;
+	u64 virt_ext;
 	u32 clean;
 	u32 reserved_5;
 	u64 next_rip;
@@ -119,6 +119,9 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 #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
 
 #define SVM_IOIO_STR_SHIFT 2

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

@@ -67,6 +67,7 @@ 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)
 
 /* Operations for KVM_HC_MMU_OP */
 #define KVM_MMU_OP_WRITE_PTE            1

arch/x86/kernel/kvm.c

@@ -330,7 +330,12 @@ static void kvm_guest_cpu_init(void)
 #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

@@ -106,14 +106,27 @@ static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint,
 	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);
@@ -221,7 +234,8 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic,
 		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;
@@ -232,7 +246,8 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic,
 			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;
@@ -318,11 +333,11 @@ static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint)
 	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;
 
@@ -341,11 +356,11 @@ void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector)
 			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;
 
@@ -687,14 +702,24 @@ void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
 		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;
 }
 
@@ -978,6 +1003,11 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 	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;
@@ -1089,18 +1119,9 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	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

@@ -56,9 +56,10 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu);
 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

@@ -724,8 +724,10 @@ void kvm_free_pit(struct kvm *kvm)
 	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

@@ -46,6 +46,7 @@
 #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
@@ -3748,7 +3749,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
 		     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);
@@ -3780,6 +3781,38 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 	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

@@ -77,6 +77,9 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
 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)
 {