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
  ...

1 files changed, 102 insertions, 60 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f76efad248ab..84e62acf2dd8 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2422,28 +2422,41 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
  * 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),
 			  vmcs_readl(EXIT_QUALIFICATION));
 	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) {
@@ -3764,6 +3777,25 @@ static void free_kvm_area(void)
 	}
 }
 
+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;
@@ -3789,14 +3821,22 @@ static void init_vmcs_shadow_fields(void)
 
 	/* 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++) {
+		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);
 	}
-	for (i = 0; i < max_shadow_read_only_fields; i++)
-		clear_bit(shadow_read_only_fields[i],
-			  vmx_vmread_bitmap);
 }
 
 static __init int alloc_kvm_area(void)
@@ -4634,6 +4674,11 @@ static bool guest_state_valid(struct kvm_vcpu *vcpu)
 	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)
 {
 	gfn_t fn;
@@ -5664,14 +5709,11 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 	}
 
 	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;
@@ -7214,25 +7256,6 @@ static int handle_vmresume(struct kvm_vcpu *vcpu)
 	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
@@ -8014,7 +8037,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 		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;
@@ -8418,9 +8441,15 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 			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;
 	}
 
@@ -8611,17 +8640,24 @@ static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu)
 
 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 */
@@ -9589,23 +9625,26 @@ static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu)
 		      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;
@@ -10293,6 +10332,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	    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;
 
@@ -10429,8 +10471,6 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 		return 1;
 	}
 
-	vmcs12->launch_state = 1;
-
 	/*
 	 * Note no nested_vmx_succeed or nested_vmx_fail here. At this point
 	 * we are no longer running L1, and VMLAUNCH/VMRESUME has not yet
@@ -10804,6 +10844,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	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;