Commit 0f65a9d3 authored by Sean Christopherson's avatar Sean Christopherson Committed by Paolo Bonzini
Browse files

KVM: VMX: Don't do full kick when triggering posted interrupt "fails" 



Replace the full "kick" with just the "wake" in the fallback path when
triggering a virtual interrupt via a posted interrupt fails because the
guest is not IN_GUEST_MODE.  If the guest transitions into guest mode
between the check and the kick, then it's guaranteed to see the pending
interrupt as KVM syncs the PIR to IRR (and onto GUEST_RVI) after setting
IN_GUEST_MODE.  Kicking the guest in this case is nothing more than an
unnecessary VM-Exit (and host IRQ).

Opportunistically update comments to explain the various ordering rules
and barriers at play.

Signed-off-by: default avatarSean Christopherson <seanjc@google.com>
Message-Id: <20211208015236.1616697-17-seanjc@google.com>
Signed-off-by: default avatarPaolo Bonzini <pbonzini@redhat.com>
parent 782f6455

arch/x86/kvm/vmx/vmx.c

+2 −2
Original line number Diff line number Diff line
@@ -3998,7 +3998,7 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, 


		/* the PIR and ON have been set by L1. */

		if (!kvm_vcpu_trigger_posted_interrupt(vcpu, true))

			kvm_vcpu_kick(vcpu);

			kvm_vcpu_wake_up(vcpu);

		return 0;

	}

	return -1;
@@ -4036,7 +4036,7 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) 
	 * posted interrupt "fails" because vcpu->mode != IN_GUEST_MODE.

	 */

	if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))

		kvm_vcpu_kick(vcpu);

		kvm_vcpu_wake_up(vcpu);



	return 0;

}

arch/x86/kvm/x86.c

+5 −4
Original line number Diff line number Diff line
@@ -9978,10 +9978,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) 
	smp_mb__after_srcu_read_unlock();



	/*

	 * This handles the case where a posted interrupt was

	 * notified with kvm_vcpu_kick.  Assigned devices can

	 * use the POSTED_INTR_VECTOR even if APICv is disabled,

	 * so do it even if APICv is disabled on this vCPU.

	 * Process pending posted interrupts to handle the case where the

	 * notification IRQ arrived in the host, or was never sent (because the

	 * target vCPU wasn't running).  Do this regardless of the vCPU's APICv

	 * status, KVM doesn't update assigned devices when APICv is inhibited,

	 * i.e. they can post interrupts even if APICv is temporarily disabled.

	 */

	if (kvm_lapic_enabled(vcpu))

		static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);