[PATCH v5 4/4] KVM: x86: Add VCPU substate for event states

[Jan Kiszka <jan.kiszka@siemens.com>]

This new substate exports all yet user-invisible states related to
exceptions, interrupts, and NMIs. Together with appropriate user space
changes, this fixes sporadic problems of vmsave/restore, live migration
and system reset.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---

Changes from v4:
 - updated doc as well (thanks, Gleb)

 Documentation/kvm/api.txt       |   29 +++++++++++++++++
 arch/x86/include/asm/kvm.h      |   24 ++++++++++++++
 arch/x86/include/asm/kvm_host.h |    2 +
 arch/x86/kvm/svm.c              |   22 +++++++++++++
 arch/x86/kvm/vmx.c              |   30 ++++++++++++++++++
 arch/x86/kvm/x86.c              |   65 +++++++++++++++++++++++++++++++++++++++
 6 files changed, 172 insertions(+), 0 deletions(-)

diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt
index 6421aee..374775e 100644
--- a/Documentation/kvm/api.txt
+++ b/Documentation/kvm/api.txt
@@ -929,3 +929,32 @@ Deprecates: KVM_GET/SET_CPUID2
 Architectures: x86
 Payload: struct kvm_lapic
 Deprecates: KVM_GET/SET_LAPIC
+
+6.8 KVM_X86_VCPU_STATE_EVENTS
+
+Architectures: x86
+Payload: struct kvm_x86_event_state
+Deprecates: interrupt_bitmap of struct kvm_sregs (pass it cleared)
+
+struct kvm_x86_event_state {
+	struct {
+		__u8 injected;
+		__u8 nr;
+		__u8 has_error_code;
+		__u8 pad;
+		__u32 error_code;
+	} exception;
+	struct {
+		__u8 injected;
+		__u8 nr;
+		__u8 soft;
+		__u8 pad;
+	} interrupt;
+	struct {
+		__u8 injected;
+		__u8 pending;
+		__u8 masked;
+		__u8 pad;
+	} nmi;
+	__u32 sipi_vector;
+};
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index 42286ef..ea2711f 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -257,5 +257,29 @@ struct kvm_reinject_control {
 #define KVM_X86_VCPU_STATE_MSRS		1000
 #define KVM_X86_VCPU_STATE_CPUID	1001
 #define KVM_X86_VCPU_STATE_LAPIC	1002
+#define KVM_X86_VCPU_STATE_EVENTS	1003
+
+struct kvm_x86_event_state {
+	struct {
+		__u8 injected;
+		__u8 nr;
+		__u8 has_error_code;
+		__u8 pad;
+		__u32 error_code;
+	} exception;
+	struct {
+		__u8 injected;
+		__u8 nr;
+		__u8 soft;
+		__u8 pad;
+	} interrupt;
+	struct {
+		__u8 injected;
+		__u8 pending;
+		__u8 masked;
+		__u8 pad;
+	} nmi;
+	__u32 sipi_vector;
+};
 
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 26a74b7..06e0856 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -523,6 +523,8 @@ struct kvm_x86_ops {
 				bool has_error_code, u32 error_code);
 	int (*interrupt_allowed)(struct kvm_vcpu *vcpu);
 	int (*nmi_allowed)(struct kvm_vcpu *vcpu);
+	bool (*get_nmi_mask)(struct kvm_vcpu *vcpu);
+	void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked);
 	void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
 	void (*enable_irq_window)(struct kvm_vcpu *vcpu);
 	void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 34b700f..3de0b37 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2499,6 +2499,26 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu)
 		!(svm->vcpu.arch.hflags & HF_NMI_MASK);
 }
 
+static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	return !!(svm->vcpu.arch.hflags & HF_NMI_MASK);
+}
+
+static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (masked) {
+		svm->vcpu.arch.hflags |= HF_NMI_MASK;
+		svm->vmcb->control.intercept |= (1UL << INTERCEPT_IRET);
+	} else {
+		svm->vcpu.arch.hflags &= ~HF_NMI_MASK;
+		svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET);
+	}
+}
+
 static int svm_interrupt_allowed(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -2946,6 +2966,8 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.queue_exception = svm_queue_exception,
 	.interrupt_allowed = svm_interrupt_allowed,
 	.nmi_allowed = svm_nmi_allowed,
+	.get_nmi_mask = svm_get_nmi_mask,
+	.set_nmi_mask = svm_set_nmi_mask,
 	.enable_nmi_window = enable_nmi_window,
 	.enable_irq_window = enable_irq_window,
 	.update_cr8_intercept = update_cr8_intercept,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index b923f2a..63e4a50 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2633,6 +2633,34 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu)
 				GUEST_INTR_STATE_NMI));
 }
 
+static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu)
+{
+	if (!cpu_has_virtual_nmis())
+		return to_vmx(vcpu)->soft_vnmi_blocked;
+	else
+		return !!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
+			  GUEST_INTR_STATE_NMI);
+}
+
+static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (!cpu_has_virtual_nmis()) {
+		if (vmx->soft_vnmi_blocked != masked) {
+			vmx->soft_vnmi_blocked = masked;
+			vmx->vnmi_blocked_time = 0;
+		}
+	} else {
+		if (masked)
+			vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
+				      GUEST_INTR_STATE_NMI);
+		else
+			vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
+					GUEST_INTR_STATE_NMI);
+	}
+}
+
 static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu)
 {
 	return (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
@@ -3973,6 +4001,8 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.queue_exception = vmx_queue_exception,
 	.interrupt_allowed = vmx_interrupt_allowed,
 	.nmi_allowed = vmx_nmi_allowed,
+	.get_nmi_mask = vmx_get_nmi_mask,
+	.set_nmi_mask = vmx_set_nmi_mask,
 	.enable_nmi_window = enable_nmi_window,
 	.enable_irq_window = enable_irq_window,
 	.update_cr8_intercept = update_cr8_intercept,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3484787..ade6c2d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4851,6 +4851,36 @@ out_free_lapic:
 		kfree(lapic);
 		break;
 	}
+	case KVM_X86_VCPU_STATE_EVENTS: {
+		struct kvm_x86_event_state events;
+
+		vcpu_load(vcpu);
+
+		events.exception.injected = vcpu->arch.exception.pending;
+		events.exception.nr = vcpu->arch.exception.nr;
+		events.exception.has_error_code =
+			vcpu->arch.exception.has_error_code;
+		events.exception.error_code = vcpu->arch.exception.error_code;
+
+		events.interrupt.injected = vcpu->arch.interrupt.pending;
+		events.interrupt.nr = vcpu->arch.interrupt.nr;
+		events.interrupt.soft = vcpu->arch.interrupt.soft;
+
+		events.nmi.injected = vcpu->arch.nmi_injected;
+		events.nmi.pending = vcpu->arch.nmi_pending;
+		events.nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu);
+
+		events.sipi_vector = vcpu->arch.sipi_vector;
+
+		vcpu_put(vcpu);
+
+		r = -EFAULT;
+		if (copy_to_user(argp, &events,
+				 sizeof(struct kvm_x86_event_state)))
+			break;
+		r = 0;
+		break;
+	}
 	default:
 		r = -EINVAL;
 	}
@@ -4901,6 +4931,40 @@ out_free_lapic:
 		kfree(lapic);
 		break;
 	}
+	case KVM_X86_VCPU_STATE_EVENTS: {
+		struct kvm_x86_event_state events;
+
+		r = -EFAULT;
+		if (copy_from_user(&events, argp,
+				   sizeof(struct kvm_x86_event_state)))
+			break;
+
+		vcpu_load(vcpu);
+
+		vcpu->arch.exception.pending = events.exception.injected;
+		vcpu->arch.exception.nr = events.exception.nr;
+		vcpu->arch.exception.has_error_code =
+			events.exception.has_error_code;
+		vcpu->arch.exception.error_code = events.exception.error_code;
+
+		vcpu->arch.interrupt.pending = events.interrupt.injected;
+		vcpu->arch.interrupt.nr = events.interrupt.nr;
+		vcpu->arch.interrupt.soft = events.interrupt.soft;
+		if (vcpu->arch.interrupt.pending &&
+		    irqchip_in_kernel(vcpu->kvm))
+			kvm_pic_clear_isr_ack(vcpu->kvm);
+
+		vcpu->arch.nmi_injected = events.nmi.injected;
+		vcpu->arch.nmi_pending = events.nmi.pending;
+		kvm_x86_ops->set_nmi_mask(vcpu, events.nmi.masked);
+
+		vcpu->arch.sipi_vector = events.sipi_vector;
+
+		vcpu_put(vcpu);
+
+		r = 0;
+		break;
+	}
 	default:
 		r = -EINVAL;
 	}
@@ -4913,6 +4977,7 @@ bool kvm_arch_check_substate(u32 type)
 	case KVM_X86_VCPU_STATE_MSRS:
 	case KVM_X86_VCPU_STATE_CPUID:
 	case KVM_X86_VCPU_STATE_LAPIC:
+	case KVM_X86_VCPU_STATE_EVENTS:
 		return true;
 	default:
 		return false;