From: Kai Huang <kai.huang@xxxxxxxxxxxxxxx> Introduce kvm_eoi_intercept_disallowed() to disallow the in-kernel I/O APIC, level triggered routes for a userspace I/O APIC, and anything else that relies on being able to intercept EOIs. It's currently for TDX, since TDX module does not allow intercepting EOI. Note, technically KVM could partially emulate the I/O APIC by allowing only edge triggered interrupts, but that adds a lot of complexity for basically zero benefit. Ideally KVM wouldn't even allow I/O APIC route reservation, but disabling that is a train wreck for Qemu. Co-developed-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx> Signed-off-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx> Signed-off-by: Kai Huang <kai.huang@xxxxxxxxxxxxxxx> Signed-off-by: Xiaoyao Li <xiaoyao.li@xxxxxxxxx> --- arch/x86/kvm/ioapic.c | 5 +++++ arch/x86/kvm/irq_comm.c | 9 +++++++-- arch/x86/kvm/lapic.c | 3 ++- arch/x86/kvm/x86.c | 6 ++++++ arch/x86/kvm/x86.h | 5 +++++ 5 files changed, 25 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 816a82515dcd..f9fb2c694c83 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -45,6 +45,7 @@ #include "ioapic.h" #include "lapic.h" #include "irq.h" +#include "x86.h" static int ioapic_service(struct kvm_ioapic *vioapic, int irq, bool line_status); @@ -311,6 +312,10 @@ void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm) { if (!ioapic_in_kernel(kvm)) return; + + if (WARN_ON_ONCE(kvm_eoi_intercept_disallowed(kvm))) + return; + kvm_make_scan_ioapic_request(kvm); } diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index d5b72a08e566..f9f643e31893 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -123,7 +123,12 @@ 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); + struct msi_msg msg = { .address_lo = e->msi.address_lo, + .address_hi = e->msi.address_hi, + .data = e->msi.data }; + return (kvm_eoi_intercept_disallowed(kvm) && + msg.arch_data.is_level) || + (kvm->arch.x2apic_format && (msg.address_hi & 0xff)); } int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, @@ -385,7 +390,7 @@ int kvm_setup_empty_irq_routing(struct kvm *kvm) void kvm_arch_post_irq_routing_update(struct kvm *kvm) { - if (!irqchip_split(kvm)) + if (!irqchip_split(kvm) || kvm_eoi_intercept_disallowed(kvm)) return; kvm_make_scan_ioapic_request(kvm); } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index d6ac32f3f650..235971c016d9 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -281,7 +281,8 @@ void kvm_recalculate_apic_map(struct kvm *kvm) if (old) call_rcu(&old->rcu, kvm_apic_map_free); - kvm_make_scan_ioapic_request(kvm); + if (!kvm_eoi_intercept_disallowed(kvm)) + kvm_make_scan_ioapic_request(kvm); } static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 34dd93b29932..113ed9aa5c82 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6023,6 +6023,9 @@ long kvm_arch_vm_ioctl(struct file *filp, goto create_irqchip_unlock; r = -EINVAL; + if (kvm_eoi_intercept_disallowed(kvm)) + goto create_irqchip_unlock; + if (kvm->created_vcpus) goto create_irqchip_unlock; @@ -6053,6 +6056,9 @@ long kvm_arch_vm_ioctl(struct file *filp, u.pit_config.flags = KVM_PIT_SPEAKER_DUMMY; goto create_pit; case KVM_CREATE_PIT2: + r = -EINVAL; + if (kvm_eoi_intercept_disallowed(kvm)) + goto out; r = -EFAULT; if (copy_from_user(&u.pit_config, argp, sizeof(struct kvm_pit_config))) diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 0d8435b32bf5..65c8c77e507b 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -451,6 +451,11 @@ static __always_inline bool kvm_tsc_immutable(struct kvm_vcpu *vcpu) return vcpu->kvm->arch.vm_type == KVM_X86_TDX_VM; } +static __always_inline bool kvm_eoi_intercept_disallowed(struct kvm *kvm) +{ + return kvm->arch.vm_type == KVM_X86_TDX_VM; +} + void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu); void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu); int kvm_spec_ctrl_test_value(u64 value); -- 2.27.0