From 7bb86329da81a9d9f1523e7ce7392d39cb6f085a Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 7 Jun 2024 10:26:05 -0700 Subject: [PATCH] KVM: nVMX: Request immediate exit iff pending nested event needs injection BugLink: https://bugs.launchpad.net/bugs/2083196 commit 32f55e475ce2c4b8b124d335fcfaf1152ba977a1 upstream. When requesting an immediate exit from L2 in order to inject a pending event, do so only if the pending event actually requires manual injection, i.e. if and only if KVM actually needs to regain control in order to deliver the event. Avoiding the "immediate exit" isn't simply an optimization, it's necessary to make forward progress, as the "already expired" VMX preemption timer trick that KVM uses to force a VM-Exit has higher priority than events that aren't directly injected. At present time, this is a glorified nop as all events processed by vmx_has_nested_events() require injection, but that will not hold true in the future, e.g. if there's a pending virtual interrupt in vmcs02.RVI. I.e. if KVM is trying to deliver a virtual interrupt to L2, the expired VMX preemption timer will trigger VM-Exit before the virtual interrupt is delivered, and KVM will effectively hang the vCPU in an endless loop of forced immediate VM-Exits (because the pending virtual interrupt never goes away). Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240607172609.3205077-3-seanjc@google.com Signed-off-by: Sean Christopherson Signed-off-by: Greg Kroah-Hartman Signed-off-by: Portia Stephens Signed-off-by: Roxana Nicolescu --- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/vmx/nested.c | 2 +- arch/x86/kvm/x86.c | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index b7a539ea2986..84ada72b0bd2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1804,7 +1804,7 @@ struct kvm_x86_nested_ops { bool (*is_exception_vmexit)(struct kvm_vcpu *vcpu, u8 vector, u32 error_code); int (*check_events)(struct kvm_vcpu *vcpu); - bool (*has_events)(struct kvm_vcpu *vcpu); + bool (*has_events)(struct kvm_vcpu *vcpu, bool for_injection); void (*triple_fault)(struct kvm_vcpu *vcpu); int (*get_state)(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 6329a306856b..b926fb6b852d 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4006,7 +4006,7 @@ static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu) to_vmx(vcpu)->nested.preemption_timer_expired; } -static bool vmx_has_nested_events(struct kvm_vcpu *vcpu) +static bool vmx_has_nested_events(struct kvm_vcpu *vcpu, bool for_injection) { return nested_vmx_preemption_timer_pending(vcpu) || to_vmx(vcpu)->nested.mtf_pending; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3750a0c688b7..6103c45dddbe 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10440,7 +10440,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, if (is_guest_mode(vcpu) && kvm_x86_ops.nested_ops->has_events && - kvm_x86_ops.nested_ops->has_events(vcpu)) + kvm_x86_ops.nested_ops->has_events(vcpu, true)) *req_immediate_exit = true; /* @@ -13083,7 +13083,7 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) if (is_guest_mode(vcpu) && kvm_x86_ops.nested_ops->has_events && - kvm_x86_ops.nested_ops->has_events(vcpu)) + kvm_x86_ops.nested_ops->has_events(vcpu, false)) return true; if (kvm_xen_has_pending_events(vcpu))