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

Pull KVM fixes from Paolo Bonzini:
 "All x86-specific, apart from some arch-independent syzkaller fixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: cleanup the page tracking SRCU instance
  KVM: nVMX: fix nested EPT detection
  KVM: pci-assign: do not map smm memory slot pages in vt-d page tables
  KVM: kvm_io_bus_unregister_dev() should never fail
  KVM: VMX: Fix enable VPID conditions
  KVM: nVMX: Fix nested VPID vmx exec control
  KVM: x86: correct async page present tracepoint
  kvm: vmx: Flush TLB when the APIC-access address changes
  KVM: x86: use pic/ioapic destructor when destroy vm
  KVM: x86: check existance before destroy
  KVM: x86: clear bus pointer when destroyed
  KVM: Documentation: document MCE ioctls
  KVM: nVMX: don't reset kvm mmu twice
  PTP: fix ptr_ret.cocci warnings
  kvm: fix usage of uninit spinlock in avic_vm_destroy()
  KVM: VMX: downgrade warning on unexpected exit code

7 files changed, 54 insertions, 15 deletions

diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h
index d74747b031ecd..c4eda791f877b 100644
--- a/arch/x86/include/asm/kvm_page_track.h
+++ b/arch/x86/include/asm/kvm_page_track.h
@@ -46,6 +46,7 @@ struct kvm_page_track_notifier_node {
 };
 
 void kvm_page_track_init(struct kvm *kvm);
+void kvm_page_track_cleanup(struct kvm *kvm);
 
 void kvm_page_track_free_memslot(struct kvm_memory_slot *free,
 				 struct kvm_memory_slot *dont);
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index 73ea24d4f119c..047b17a262696 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -657,6 +657,9 @@ void kvm_pic_destroy(struct kvm *kvm)
 {
 	struct kvm_pic *vpic = kvm->arch.vpic;
 
+	if (!vpic)
+		return;
+
 	kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_master);
 	kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_slave);
 	kvm_io_bus_unregister_dev(vpic->kvm, KVM_PIO_BUS, &vpic->dev_eclr);
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 6e219e5c07d27..289270a6aecbb 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -635,6 +635,9 @@ void kvm_ioapic_destroy(struct kvm *kvm)
 {
 	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
 
+	if (!ioapic)
+		return;
+
 	cancel_delayed_work_sync(&ioapic->eoi_inject);
 	kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
 	kvm->arch.vioapic = NULL;
diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c
index 37942e419c32e..60168cdd05463 100644
--- a/arch/x86/kvm/page_track.c
+++ b/arch/x86/kvm/page_track.c
@@ -160,6 +160,14 @@ bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn,
 	return !!ACCESS_ONCE(slot->arch.gfn_track[mode][index]);
 }
 
+void kvm_page_track_cleanup(struct kvm *kvm)
+{
+	struct kvm_page_track_notifier_head *head;
+
+	head = &kvm->arch.track_notifier_head;
+	cleanup_srcu_struct(&head->track_srcu);
+}
+
 void kvm_page_track_init(struct kvm *kvm)
 {
 	struct kvm_page_track_notifier_head *head;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index d1efe2c62b3f8..5fba70646c327 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1379,6 +1379,9 @@ static void avic_vm_destroy(struct kvm *kvm)
 	unsigned long flags;
 	struct kvm_arch *vm_data = &kvm->arch;
 
+	if (!avic)
+		return;
+
 	avic_free_vm_id(vm_data->avic_vm_id);
 
 	if (vm_data->avic_logical_id_table_page)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 98e82ee1e6996..2ee00dbbbd518 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1239,6 +1239,11 @@ static inline bool cpu_has_vmx_invvpid_global(void)
 	return vmx_capability.vpid & VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
 }
 
+static inline bool cpu_has_vmx_invvpid(void)
+{
+	return vmx_capability.vpid & VMX_VPID_INVVPID_BIT;
+}
+
 static inline bool cpu_has_vmx_ept(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
@@ -2753,7 +2758,6 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		SECONDARY_EXEC_RDTSCP |
 		SECONDARY_EXEC_DESC |
 		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
-		SECONDARY_EXEC_ENABLE_VPID |
 		SECONDARY_EXEC_APIC_REGISTER_VIRT |
 		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
 		SECONDARY_EXEC_WBINVD_EXITING |
@@ -2781,10 +2785,12 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	 * though it is treated as global context.  The alternative is
 	 * not failing the single-context invvpid, and it is worse.
 	 */
-	if (enable_vpid)
+	if (enable_vpid) {
+		vmx->nested.nested_vmx_secondary_ctls_high |=
+			SECONDARY_EXEC_ENABLE_VPID;
 		vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT |
 			VMX_VPID_EXTENT_SUPPORTED_MASK;
-	else
+	} else
 		vmx->nested.nested_vmx_vpid_caps = 0;
 
 	if (enable_unrestricted_guest)
@@ -4024,6 +4030,12 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
 	__vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid);
 }
 
+static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu)
+{
+	if (enable_ept)
+		vmx_flush_tlb(vcpu);
+}
+
 static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu)
 {
 	ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits;
@@ -6517,8 +6529,10 @@ static __init int hardware_setup(void)
 	if (boot_cpu_has(X86_FEATURE_NX))
 		kvm_enable_efer_bits(EFER_NX);
 
-	if (!cpu_has_vmx_vpid())
+	if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() ||
+		!(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global()))
 		enable_vpid = 0;
+
 	if (!cpu_has_vmx_shadow_vmcs())
 		enable_shadow_vmcs = 0;
 	if (enable_shadow_vmcs)
@@ -8501,7 +8515,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	    && kvm_vmx_exit_handlers[exit_reason])
 		return kvm_vmx_exit_handlers[exit_reason](vcpu);
 	else {
-		WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_reason);
+		vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n",
+				exit_reason);
 		kvm_queue_exception(vcpu, UD_VECTOR);
 		return 1;
 	}
@@ -8547,6 +8562,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 	} else {
 		sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE;
 		sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+		vmx_flush_tlb_ept_only(vcpu);
 	}
 	vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control);
 
@@ -8572,8 +8588,10 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
 	 */
 	if (!is_guest_mode(vcpu) ||
 	    !nested_cpu_has2(get_vmcs12(&vmx->vcpu),
-			     SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
+			     SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
 		vmcs_write64(APIC_ACCESS_ADDR, hpa);
+		vmx_flush_tlb_ept_only(vcpu);
+	}
 }
 
 static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
@@ -9974,7 +9992,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 exec_control;
-	bool nested_ept_enabled = false;
 
 	vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
 	vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
@@ -10121,8 +10138,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 				vmcs12->guest_intr_status);
 		}
 
-		nested_ept_enabled = (exec_control & SECONDARY_EXEC_ENABLE_EPT) != 0;
-
 		/*
 		 * Write an illegal value to APIC_ACCESS_ADDR. Later,
 		 * nested_get_vmcs12_pages will either fix it up or
@@ -10255,6 +10270,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	if (nested_cpu_has_ept(vmcs12)) {
 		kvm_mmu_unload(vcpu);
 		nested_ept_init_mmu_context(vcpu);
+	} else if (nested_cpu_has2(vmcs12,
+				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+		vmx_flush_tlb_ept_only(vcpu);
 	}
 
 	/*
@@ -10282,12 +10300,10 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	vmx_set_efer(vcpu, vcpu->arch.efer);
 
 	/* Shadow page tables on either EPT or shadow page tables. */
-	if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_ept_enabled,
+	if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12),
 				entry_failure_code))
 		return 1;
 
-	kvm_mmu_reset_context(vcpu);
-
 	if (!enable_ept)
 		vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;
 
@@ -11056,6 +11072,10 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 		vmx->nested.change_vmcs01_virtual_x2apic_mode = false;
 		vmx_set_virtual_x2apic_mode(vcpu,
 				vcpu->arch.apic_base & X2APIC_ENABLE);
+	} else if (!nested_cpu_has_ept(vmcs12) &&
+		   nested_cpu_has2(vmcs12,
+				   SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+		vmx_flush_tlb_ept_only(vcpu);
 	}
 
 	/* This is needed for same reason as it was needed in prepare_vmcs02 */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1faf620a6fdc2..ccbd45ecd41a3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8153,11 +8153,12 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	if (kvm_x86_ops->vm_destroy)
 		kvm_x86_ops->vm_destroy(kvm);
 	kvm_iommu_unmap_guest(kvm);
-	kfree(kvm->arch.vpic);
-	kfree(kvm->arch.vioapic);
+	kvm_pic_destroy(kvm);
+	kvm_ioapic_destroy(kvm);
 	kvm_free_vcpus(kvm);
 	kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 	kvm_mmu_uninit_vm(kvm);
+	kvm_page_track_cleanup(kvm);
 }
 
 void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
@@ -8566,11 +8567,11 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 {
 	struct x86_exception fault;
 
-	trace_kvm_async_pf_ready(work->arch.token, work->gva);
 	if (work->wakeup_all)
 		work->arch.token = ~0; /* broadcast wakeup */
 	else
 		kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
+	trace_kvm_async_pf_ready(work->arch.token, work->gva);
 
 	if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) &&
 	    !apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) {