KVM: x86: Clean up and document nested #PF workaround

Replace the per-vendor hack-a-fix for KVM's #PF => #PF => #DF workaround
with an explicit, common workaround in kvm_inject_emulated_page_fault().
Aside from being a hack, the current approach is brittle and incomplete,
e.g. nSVM's KVM_SET_NESTED_STATE fails to set ->inject_page_fault(),
and nVMX fails to apply the workaround when VMX is intercepting #PF due
to allow_smaller_maxphyaddr=1.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -1516,6 +1516,8 @@ struct kvm_x86_ops {
 struct kvm_x86_nested_ops {
 	void (*leave_nested)(struct kvm_vcpu *vcpu);
 	int (*check_events)(struct kvm_vcpu *vcpu);
+	bool (*handle_page_fault_workaround)(struct kvm_vcpu *vcpu,
+					     struct x86_exception *fault);
 	bool (*hv_timer_pending)(struct kvm_vcpu *vcpu);
 	void (*triple_fault)(struct kvm_vcpu *vcpu);
 	int (*get_state)(struct kvm_vcpu *vcpu,

arch/x86/kvm/svm/nested.c

@@ -55,7 +55,8 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu,
 	nested_svm_vmexit(svm);
 }
 
-static void svm_inject_page_fault_nested(struct kvm_vcpu *vcpu, struct x86_exception *fault)
+static bool nested_svm_handle_page_fault_workaround(struct kvm_vcpu *vcpu,
+						    struct x86_exception *fault)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct vmcb *vmcb = svm->vmcb;
@@ -64,15 +65,16 @@ static void svm_inject_page_fault_nested(struct kvm_vcpu *vcpu, struct x86_excep
 
 	if (vmcb12_is_intercept(&svm->nested.ctl,
 				INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) &&
-				!svm->nested.nested_run_pending) {
+	    !WARN_ON_ONCE(svm->nested.nested_run_pending)) {
 	     	vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + PF_VECTOR;
 		vmcb->control.exit_code_hi = 0;
 		vmcb->control.exit_info_1 = fault->error_code;
 		vmcb->control.exit_info_2 = fault->address;
 		nested_svm_vmexit(svm);
-	} else {
-		kvm_inject_page_fault(vcpu, fault);
+		return true;
 	}
+
+	return false;
 }
 
 static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index)
@@ -751,9 +753,6 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa,
 	if (ret)
 		return ret;
 
-	if (!npt_enabled)
-		vcpu->arch.mmu->inject_page_fault = svm_inject_page_fault_nested;
-
 	if (!from_vmrun)
 		kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
 
@@ -1659,6 +1658,7 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
 struct kvm_x86_nested_ops svm_nested_ops = {
 	.leave_nested = svm_leave_nested,
 	.check_events = svm_check_nested_events,
+	.handle_page_fault_workaround = nested_svm_handle_page_fault_workaround,
 	.triple_fault = nested_svm_triple_fault,
 	.get_nested_state_pages = svm_get_nested_state_pages,
 	.get_state = svm_get_nested_state,

arch/x86/kvm/vmx/nested.c

@@ -476,8 +476,7 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned long *exit
 	return 0;
 }
 
-
-static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu,
+static bool nested_vmx_handle_page_fault_workaround(struct kvm_vcpu *vcpu,
 						    struct x86_exception *fault)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
@@ -485,15 +484,15 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu,
 	WARN_ON(!is_guest_mode(vcpu));
 
 	if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) &&
-		!to_vmx(vcpu)->nested.nested_run_pending) {
+	    !WARN_ON_ONCE(to_vmx(vcpu)->nested.nested_run_pending)) {
 		vmcs12->vm_exit_intr_error_code = fault->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,
 				  fault->address);
-	} else {
-		kvm_inject_page_fault(vcpu, fault);
+		return true;
 	}
+	return false;
 }
 
 static int nested_vmx_check_io_bitmap_controls(struct kvm_vcpu *vcpu,
@@ -2614,9 +2613,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 		vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
 	}
 
-	if (!enable_ept)
-		vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;
-
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) &&
 	    WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
 				     vmcs12->guest_ia32_perf_global_ctrl))) {
@@ -6830,6 +6826,7 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *))
 struct kvm_x86_nested_ops vmx_nested_ops = {
 	.leave_nested = vmx_leave_nested,
 	.check_events = vmx_check_nested_events,
+	.handle_page_fault_workaround = nested_vmx_handle_page_fault_workaround,
 	.hv_timer_pending = nested_vmx_preemption_timer_pending,
 	.triple_fault = nested_vmx_triple_fault,
 	.get_state = vmx_get_nested_state,

arch/x86/kvm/x86.c

@@ -748,6 +748,7 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
 }
 EXPORT_SYMBOL_GPL(kvm_inject_page_fault);
 
+/* Returns true if the page fault was immediately morphed into a VM-Exit. */
 bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu,
 				    struct x86_exception *fault)
 {
@@ -766,8 +767,26 @@ bool kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu,
 		kvm_mmu_invalidate_gva(vcpu, fault_mmu, fault->address,
 				       fault_mmu->root.hpa);
 
+	/*
+	 * A workaround for KVM's bad exception handling.  If KVM injected an
+	 * exception into L2, and L2 encountered a #PF while vectoring the
+	 * injected exception, manually check to see if L1 wants to intercept
+	 * #PF, otherwise queuing the #PF will lead to #DF or a lost exception.
+	 * In all other cases, defer the check to nested_ops->check_events(),
+	 * which will correctly handle priority (this does not).  Note, other
+	 * exceptions, e.g. #GP, are theoretically affected, #PF is simply the
+	 * most problematic, e.g. when L0 and L1 are both intercepting #PF for
+	 * shadow paging.
+	 *
+	 * TODO: Rewrite exception handling to track injected and pending
+	 *       (VM-Exit) exceptions separately.
+	 */
+	if (unlikely(vcpu->arch.exception.injected && is_guest_mode(vcpu)) &&
+	    kvm_x86_ops.nested_ops->handle_page_fault_workaround(vcpu, fault))
+		return true;
+
 	fault_mmu->inject_page_fault(vcpu, fault);
-	return fault->nested_page_fault;
+	return false;
 }
 EXPORT_SYMBOL_GPL(kvm_inject_emulated_page_fault);