KVM: x86: Reset IRTE to host control if *new* route isn't postable

Restore an IRTE back to host control (remapped or posted MSI mode) if the
*new* GSI route prevents posting the IRQ directly to a vCPU, regardless of
the GSI routing type.  Updating the IRTE if and only if the new GSI is an
MSI results in KVM leaving an IRTE posting to a vCPU.

The dangling IRTE can result in interrupts being incorrectly delivered to
the guest, and in the worst case scenario can result in use-after-free,
e.g. if the VM is torn down, but the underlying host IRQ isn't freed.

Fixes: efc6440 ("KVM: x86: Update IRTE for posted-interrupts")
Fixes: 411b44b ("svm: Implements update_pi_irte hook to setup posted interrupt")
Cc: [email protected]
Signed-off-by: Sean Christopherson <[email protected]>
Message-ID: <[email protected]>
Signed-off-by: Paolo Bonzini <[email protected]>

Author: sean-jc

arch/x86/kvm/svm/avic.c

@@ -896,6 +896,7 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 {
 	struct kvm_kernel_irq_routing_entry *e;
 	struct kvm_irq_routing_table *irq_rt;
+	bool enable_remapped_mode = true;
 	int idx, ret = 0;
 
 	if (!kvm_arch_has_assigned_device(kvm) || !kvm_arch_has_irq_bypass())
@@ -932,6 +933,8 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 		    kvm_vcpu_apicv_active(&svm->vcpu)) {
 			struct amd_iommu_pi_data pi;
 
+			enable_remapped_mode = false;
+
 			/* Try to enable guest_mode in IRTE */
 			pi.base = __sme_set(page_to_phys(svm->avic_backing_page) &
 					    AVIC_HPA_MASK);
@@ -950,33 +953,6 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 			 */
 			if (!ret && pi.is_guest_mode)
 				svm_ir_list_add(svm, &pi);
-		} else {
-			/* Use legacy mode in IRTE */
-			struct amd_iommu_pi_data pi;
-
-			/**
-			 * Here, pi is used to:
-			 * - Tell IOMMU to use legacy mode for this interrupt.
-			 * - Retrieve ga_tag of prior interrupt remapping data.
-			 */
-			pi.prev_ga_tag = 0;
-			pi.is_guest_mode = false;
-			ret = irq_set_vcpu_affinity(host_irq, &pi);
-
-			/**
-			 * Check if the posted interrupt was previously
-			 * setup with the guest_mode by checking if the ga_tag
-			 * was cached. If so, we need to clean up the per-vcpu
-			 * ir_list.
-			 */
-			if (!ret && pi.prev_ga_tag) {
-				int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
-				struct kvm_vcpu *vcpu;
-
-				vcpu = kvm_get_vcpu_by_id(kvm, id);
-				if (vcpu)
-					svm_ir_list_del(to_svm(vcpu), &pi);
-			}
 		}
 
 		if (!ret && svm) {
@@ -992,6 +968,34 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 	}
 
 	ret = 0;
+	if (enable_remapped_mode) {
+		/* Use legacy mode in IRTE */
+		struct amd_iommu_pi_data pi;
+
+		/**
+		 * Here, pi is used to:
+		 * - Tell IOMMU to use legacy mode for this interrupt.
+		 * - Retrieve ga_tag of prior interrupt remapping data.
+		 */
+		pi.prev_ga_tag = 0;
+		pi.is_guest_mode = false;
+		ret = irq_set_vcpu_affinity(host_irq, &pi);
+
+		/**
+		 * Check if the posted interrupt was previously
+		 * setup with the guest_mode by checking if the ga_tag
+		 * was cached. If so, we need to clean up the per-vcpu
+		 * ir_list.
+		 */
+		if (!ret && pi.prev_ga_tag) {
+			int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
+			struct kvm_vcpu *vcpu;
+
+			vcpu = kvm_get_vcpu_by_id(kvm, id);
+			if (vcpu)
+				svm_ir_list_del(to_svm(vcpu), &pi);
+		}
+	}
 out:
 	srcu_read_unlock(&kvm->irq_srcu, idx);
 	return ret;

arch/x86/kvm/vmx/posted_intr.c

@@ -297,6 +297,7 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 {
 	struct kvm_kernel_irq_routing_entry *e;
 	struct kvm_irq_routing_table *irq_rt;
+	bool enable_remapped_mode = true;
 	struct kvm_lapic_irq irq;
 	struct kvm_vcpu *vcpu;
 	struct vcpu_data vcpu_info;
@@ -335,40 +336,31 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 
 		kvm_set_msi_irq(kvm, e, &irq);
 		if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
-		    !kvm_irq_is_postable(&irq)) {
-			/*
-			 * Make sure the IRTE is in remapped mode if
-			 * we don't handle it in posted mode.
-			 */
-			ret = irq_set_vcpu_affinity(host_irq, NULL);
-			if (ret < 0) {
-				printk(KERN_INFO
-				   "failed to back to remapped mode, irq: %u\n",
-				   host_irq);
-				goto out;
-			}
-
+		    !kvm_irq_is_postable(&irq))
 			continue;
-		}
 
 		vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
 		vcpu_info.vector = irq.vector;
 
 		trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
 				vcpu_info.vector, vcpu_info.pi_desc_addr, set);
 
-		if (set)
-			ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
-		else
-			ret = irq_set_vcpu_affinity(host_irq, NULL);
+		if (!set)
+			continue;
 
+		enable_remapped_mode = false;
+
+		ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
 		if (ret < 0) {
 			printk(KERN_INFO "%s: failed to update PI IRTE\n",
 					__func__);
 			goto out;
 		}
 	}
 
+	if (enable_remapped_mode)
+		ret = irq_set_vcpu_affinity(host_irq, NULL);
+
 	ret = 0;
 out:
 	srcu_read_unlock(&kvm->irq_srcu, idx);