From a06230b62b898e51cfb1de256b2042a09a691f58 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 7 Feb 2020 02:36:06 -0800 Subject: KVM: x86: Deliver exception payload on KVM_GET_VCPU_EVENTS KVM allows the deferral of exception payloads when a vCPU is in guest mode to allow the L1 hypervisor to intercept certain events (#PF, #DB) before register state has been modified. However, this behavior is incompatible with the KVM_{GET,SET}_VCPU_EVENTS ABI, as userspace expects register state to have been immediately modified. Userspace may opt-in for the payload deferral behavior with the KVM_CAP_EXCEPTION_PAYLOAD per-VM capability. As such, kvm_multiple_exception() will immediately manipulate guest registers if the capability hasn't been requested. Since the deferral is only necessary if a userspace ioctl were to be serviced at the same as a payload bearing exception is recognized, this behavior can be relaxed. Instead, opportunistically defer the payload from kvm_multiple_exception() and deliver the payload before completing a KVM_GET_VCPU_EVENTS ioctl. Signed-off-by: Oliver Upton Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 29 ++++++++++++++++------------- 1 file changed, 16 insertions(+), 13 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 95b753dab207..4d3310df1758 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -498,19 +498,7 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu, vcpu->arch.exception.error_code = error_code; vcpu->arch.exception.has_payload = has_payload; vcpu->arch.exception.payload = payload; - /* - * In guest mode, payload delivery should be deferred, - * so that the L1 hypervisor can intercept #PF before - * CR2 is modified (or intercept #DB before DR6 is - * modified under nVMX). However, for ABI - * compatibility with KVM_GET_VCPU_EVENTS and - * KVM_SET_VCPU_EVENTS, we can't delay payload - * delivery unless userspace has enabled this - * functionality via the per-VM capability, - * KVM_CAP_EXCEPTION_PAYLOAD. - */ - if (!vcpu->kvm->arch.exception_payload_enabled || - !is_guest_mode(vcpu)) + if (!is_guest_mode(vcpu)) kvm_deliver_exception_payload(vcpu); return; } @@ -3803,6 +3791,21 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, { process_nmi(vcpu); + /* + * In guest mode, payload delivery should be deferred, + * so that the L1 hypervisor can intercept #PF before + * CR2 is modified (or intercept #DB before DR6 is + * modified under nVMX). Unless the per-VM capability, + * KVM_CAP_EXCEPTION_PAYLOAD, is set, we may not defer the delivery of + * an exception payload and handle after a KVM_GET_VCPU_EVENTS. Since we + * opportunistically defer the exception payload, deliver it if the + * capability hasn't been requested before processing a + * KVM_GET_VCPU_EVENTS. + */ + if (!vcpu->kvm->arch.exception_payload_enabled && + vcpu->arch.exception.pending && vcpu->arch.exception.has_payload) + kvm_deliver_exception_payload(vcpu); + /* * The API doesn't provide the instruction length for software * exceptions, so don't report them. As long as the guest RIP -- cgit