From: Sean Christopherson <sean.j.christopher...@intel.com> commit 25bb2cf97139f81e3bb8910d26016a529019528e upstream.
On successful nested VM-Enter, check for pending interrupts and convert the highest priority interrupt to a pending posted interrupt if it matches L2's notification vector. If the vCPU receives a notification interrupt before nested VM-Enter (assuming L1 disables IRQs before doing VM-Enter), the pending interrupt (for L1) should be recognized and processed as a posted interrupt when interrupts become unblocked after VM-Enter to L2. This fixes a bug where L1/L2 will get stuck in an infinite loop if L1 is trying to inject an interrupt into L2 by setting the appropriate bit in L2's PIR and sending a self-IPI prior to VM-Enter (as opposed to KVM's method of manually moving the vector from PIR->vIRR/RVI). KVM will observe the IPI while the vCPU is in L1 context and so won't immediately morph it to a posted interrupt for L2. The pending interrupt will be seen by vmx_check_nested_events(), cause KVM to force an immediate exit after nested VM-Enter, and eventually be reflected to L1 as a VM-Exit. After handling the VM-Exit, L1 will see that L2 has a pending interrupt in PIR, send another IPI, and repeat until L2 is killed. Note, posted interrupts require virtual interrupt deliveriy, and virtual interrupt delivery requires exit-on-interrupt, ergo interrupts will be unconditionally unmasked on VM-Enter if posted interrupts are enabled. Fixes: 705699a13994 ("KVM: nVMX: Enable nested posted interrupt processing") Cc: sta...@vger.kernel.org Cc: Liran Alon <liran.a...@oracle.com> Signed-off-by: Sean Christopherson <sean.j.christopher...@intel.com> Message-Id: <20200812175129.12172-1-sean.j.christopher...@intel.com> Signed-off-by: Paolo Bonzini <pbonz...@redhat.com> Signed-off-by: Greg Kroah-Hartman <gre...@linuxfoundation.org> --- arch/x86/kvm/lapic.c | 7 +++++++ arch/x86/kvm/lapic.h | 1 + arch/x86/kvm/vmx/nested.c | 8 ++++++++ 3 files changed, 16 insertions(+) --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -490,6 +490,12 @@ static inline void apic_clear_irr(int ve } } +void kvm_apic_clear_irr(struct kvm_vcpu *vcpu, int vec) +{ + apic_clear_irr(vec, vcpu->arch.apic); +} +EXPORT_SYMBOL_GPL(kvm_apic_clear_irr); + static inline void apic_set_isr(int vec, struct kvm_lapic *apic) { struct kvm_vcpu *vcpu; @@ -2462,6 +2468,7 @@ int kvm_apic_has_interrupt(struct kvm_vc __apic_update_ppr(apic, &ppr); return apic_has_interrupt_for_ppr(apic, ppr); } +EXPORT_SYMBOL_GPL(kvm_apic_has_interrupt); int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu) { --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -89,6 +89,7 @@ int kvm_lapic_reg_read(struct kvm_lapic bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int shorthand, unsigned int dest, int dest_mode); int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2); +void kvm_apic_clear_irr(struct kvm_vcpu *vcpu, int vec); bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr); bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr); void kvm_apic_update_ppr(struct kvm_vcpu *vcpu); --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3480,6 +3480,14 @@ static int nested_vmx_run(struct kvm_vcp if (unlikely(status != NVMX_VMENTRY_SUCCESS)) goto vmentry_failed; + /* Emulate processing of posted interrupts on VM-Enter. */ + if (nested_cpu_has_posted_intr(vmcs12) && + kvm_apic_has_interrupt(vcpu) == vmx->nested.posted_intr_nv) { + vmx->nested.pi_pending = true; + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_apic_clear_irr(vcpu, vmx->nested.posted_intr_nv); + } + /* Hide L1D cache contents from the nested guest. */ vmx->vcpu.arch.l1tf_flush_l1d = true;