From: Sean Christopherson <seanjc@google.com> stable inclusion from stable-v5.10.237 commit e5f2dee9f7fcd2ff4b97869f3c66a0d89c167769 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC6M58 CVE: CVE-2025-37885 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- commit 9bcac97dc42d2f4da8229d18feb0fe2b1ce523a2 upstream. 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: efc644048ecd ("KVM: x86: Update IRTE for posted-interrupts") Fixes: 411b44ba80ab ("svm: Implements update_pi_irte hook to setup posted interrupt") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson <seanjc@google.com> Message-ID: <20250404193923.1413163-3-seanjc@google.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Jinjiang Tu <tujinjiang@huawei.com> --- arch/x86/kvm/svm/avic.c | 58 ++++++++++++++++++---------------- arch/x86/kvm/vmx/posted_intr.c | 28 ++++++---------- 2 files changed, 41 insertions(+), 45 deletions(-) diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 680a628c0546..6a1506f21713 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -789,6 +789,7 @@ int svm_update_pi_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) || @@ -826,6 +827,8 @@ int svm_update_pi_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); @@ -844,33 +847,6 @@ int svm_update_pi_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) { @@ -886,6 +862,34 @@ int svm_update_pi_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; diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 9689541fa027..5878f439e1ac 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -255,6 +255,7 @@ int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_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; @@ -293,21 +294,8 @@ int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_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(&to_vmx(vcpu)->pi_desc); vcpu_info.vector = irq.vector; @@ -315,11 +303,12 @@ int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, 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__); @@ -327,6 +316,9 @@ int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, } } + if (enable_remapped_mode) + ret = irq_set_vcpu_affinity(host_irq, NULL); + ret = 0; out: srcu_read_unlock(&kvm->irq_srcu, idx); -- 2.43.0