KVM: async_pf: Force a nested vmexit if the injected #PF is async_pf

Add an nested_apf field to vcpu->arch.exception to identify an async page
fault, and constructs the expected vm-exit information fields. Force a
nested VM exit from nested_vmx_check_exception() if the injected #PF is
async page fault.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>

5 files changed, 35 insertions, 10 deletions

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 722d0e568863..fde36f189836 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/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;
 };
 
 /*
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 4f20ee6c79a1..5e9ac508f718 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -550,6 +550,7 @@ struct kvm_vcpu_arch {
 		bool reinject;
 		u8 nr;
 		u32 error_code;
+		u8 nested_apf;
 	} exception;
 
 	struct kvm_queued_interrupt {
@@ -651,6 +652,7 @@ struct kvm_vcpu_arch {
 		u32 id;
 		bool send_user_only;
 		u32 host_apf_reason;
+		unsigned long nested_apf_token;
 	} apf;
 
 	/* OSVW MSRs (AMD only) */
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index fb23497cf915..4d8141e533c3 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2423,15 +2423,19 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
 	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;
-
-	vmexit = nested_svm_intercept(svm);
-	if (vmexit == NESTED_EXIT_DONE)
-		svm->nested.exit_required = true;
+	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;
 
+	svm->nested.exit_required = true;
 	return vmexit;
 }
 
@@ -2653,7 +2657,7 @@ static int nested_svm_intercept(struct vcpu_svm *svm)
 		}
 		/* async page fault always cause vmexit */
 		else if ((exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) &&
-			 svm->vcpu.arch.apf.host_apf_reason != 0)
+			 svm->vcpu.arch.exception.nested_apf != 0)
 			vmexit = NESTED_EXIT_DONE;
 		break;
 	}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c9c46e63f744..5a3bb1a697a2 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2422,13 +2422,24 @@ 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));
@@ -2445,7 +2456,7 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu)
 	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) {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e149c92476f1..f3f10154c133 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -450,7 +450,12 @@ EXPORT_SYMBOL_GPL(kvm_complete_insn_gp);
 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);
@@ -8582,6 +8587,7 @@ void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
 		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);
 	}
 }
@@ -8604,6 +8610,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 		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;