KVM: x86: add KVM_CAP_X2APIC_API

KVM_CAP_X2APIC_API is a capability for features related to x2APIC
enablement.  KVM_X2APIC_API_32BIT_FORMAT feature can be enabled to
extend APIC ID in get/set ioctl and MSI addresses to 32 bits.
Both are needed to support x2APIC.

The feature has to be enableable and disabled by default, because
get/set ioctl shifted and truncated APIC ID to 8 bits by using a
non-standard protocol inspired by xAPIC and the change is not
backward-compatible.

Changes to MSI addresses follow the format used by interrupt remapping
unit.  The upper address word, that used to be 0, contains upper 24 bits
of the LAPIC address in its upper 24 bits.  Lower 8 bits are reserved as
0.  Using the upper address word is not backward-compatible either as we
didn't check that userspace zeroed the word.  Reserved bits are still
not explicitly checked, but non-zero data will affect LAPIC addresses,
which will cause a bug.

Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

4 files changed, 49 insertions, 10 deletions

diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 889563d50c55..25810b144b58 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -110,13 +110,17 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 	return r;
 }
 
-void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
+void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
 		     struct kvm_lapic_irq *irq)
 {
-	trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
+	trace_kvm_msi_set_irq(e->msi.address_lo | (kvm->arch.x2apic_format ?
+	                                     (u64)e->msi.address_hi << 32 : 0),
+	                      e->msi.data);
 
 	irq->dest_id = (e->msi.address_lo &
 			MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
+	if (kvm->arch.x2apic_format)
+		irq->dest_id |= MSI_ADDR_EXT_DEST_ID(e->msi.address_hi);
 	irq->vector = (e->msi.data &
 			MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT;
 	irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
@@ -129,15 +133,24 @@ void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
 }
 EXPORT_SYMBOL_GPL(kvm_set_msi_irq);
 
+static inline bool kvm_msi_route_invalid(struct kvm *kvm,
+		struct kvm_kernel_irq_routing_entry *e)
+{
+	return kvm->arch.x2apic_format && (e->msi.address_hi & 0xff);
+}
+
 int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 		struct kvm *kvm, int irq_source_id, int level, bool line_status)
 {
 	struct kvm_lapic_irq irq;
 
+	if (kvm_msi_route_invalid(kvm, e))
+		return -EINVAL;
+
 	if (!level)
 		return -1;
 
-	kvm_set_msi_irq(e, &irq);
+	kvm_set_msi_irq(kvm, e, &irq);
 
 	return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL);
 }
@@ -153,7 +166,10 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 	if (unlikely(e->type != KVM_IRQ_ROUTING_MSI))
 		return -EWOULDBLOCK;
 
-	kvm_set_msi_irq(e, &irq);
+	if (kvm_msi_route_invalid(kvm, e))
+		return -EINVAL;
+
+	kvm_set_msi_irq(kvm, e, &irq);
 
 	if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
 		return r;
@@ -286,6 +302,9 @@ int kvm_set_routing_entry(struct kvm *kvm,
 		e->msi.address_lo = ue->u.msi.address_lo;
 		e->msi.address_hi = ue->u.msi.address_hi;
 		e->msi.data = ue->u.msi.data;
+
+		if (kvm_msi_route_invalid(kvm, e))
+			goto out;
 		break;
 	case KVM_IRQ_ROUTING_HV_SINT:
 		e->set = kvm_hv_set_sint;
@@ -394,7 +413,7 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
 			if (entry->type != KVM_IRQ_ROUTING_MSI)
 				continue;
 
-			kvm_set_msi_irq(entry, &irq);
+			kvm_set_msi_irq(vcpu->kvm, entry, &irq);
 
 			if (irq.level && kvm_apic_match_dest(vcpu, NULL, 0,
 						irq.dest_id, irq.dest_mode))
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 3c2a8c113054..d27a7829a4ce 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1991,10 +1991,15 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
 	if (apic_x2apic_mode(vcpu->arch.apic)) {
 		u32 *id = (u32 *)(s->regs + APIC_ID);
 
-		if (set)
-			*id >>= 24;
-		else
-			*id <<= 24;
+		if (vcpu->kvm->arch.x2apic_format) {
+			if (*id != vcpu->vcpu_id)
+				return -EINVAL;
+		} else {
+			if (set)
+				*id >>= 24;
+			else
+				*id <<= 24;
+		}
 	}
 
 	return 0;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 7bdd6b1a2373..b61cdadf8623 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -11104,7 +11104,7 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 		 * We will support full lowest-priority interrupt later.
 		 */
 
-		kvm_set_msi_irq(e, &irq);
+		kvm_set_msi_irq(kvm, e, &irq);
 		if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) {
 			/*
 			 * Make sure the IRTE is in remapped mode if
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b6e402d16e0c..d86f563a6896 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -90,6 +90,8 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
 #define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
 #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
 
+#define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS)
+
 static void update_cr8_intercept(struct kvm_vcpu *vcpu);
 static void process_nmi(struct kvm_vcpu *vcpu);
 static void enter_smm(struct kvm_vcpu *vcpu);
@@ -2625,6 +2627,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_TSC_CONTROL:
 		r = kvm_has_tsc_control;
 		break;
+	case KVM_CAP_X2APIC_API:
+		r = KVM_X2APIC_API_VALID_FLAGS;
+		break;
 	default:
 		r = 0;
 		break;
@@ -3799,6 +3804,16 @@ split_irqchip_unlock:
 		mutex_unlock(&kvm->lock);
 		break;
 	}
+	case KVM_CAP_X2APIC_API:
+		r = -EINVAL;
+		if (cap->args[0] & ~KVM_X2APIC_API_VALID_FLAGS)
+			break;
+
+		if (cap->args[0] & KVM_X2APIC_API_USE_32BIT_IDS)
+			kvm->arch.x2apic_format = true;
+
+		r = 0;
+		break;
 	default:
 		r = -EINVAL;
 		break;