Re: [PATCH v2] KVM: x86: check PIR even for vCPUs with disabled APICv

[Maxim Levitsky <mlevitsk@redhat.com>]

On Thu, 2021-11-18 at 02:25 -0500, Paolo Bonzini wrote:
> The IRTE for an assigned device can trigger a POSTED_INTR_VECTOR even
> if APICv is disabled on the vCPU that receives it.  In that case, the
> interrupt will just cause a vmexit and leave the ON bit set together
> with the PIR bit corresponding to the interrupt.
100% true.
> 
> Right now, the interrupt would not be delivered until APICv is re-enabled.
> However, fixing this is just a matter of always doing the PIR->IRR
> synchronization, even if the vCPU has temporarily disabled APICv.
> 
> This is not a problem for performance, or if anything it is an
> improvement.  First, in the common case where vcpu->arch.apicv_active is
> true, one fewer check has to be performed.  Second, static_call_cond will
> elide the function call if APICv is not present or disabled.  Finally,
> in the case for AMD hardware we can remove the sync_pir_to_irr callback:
> it is only needed for apic_has_interrupt_for_ppr, and that function
> already has a fallback for !APICv.
> 
> Cc: stable@vger.kernel.org
> Co-developed-by: Sean Christopherson <seanjc@google.com>
> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
> ---
>  arch/x86/kvm/lapic.c   |  2 +-
>  arch/x86/kvm/svm/svm.c |  1 -
>  arch/x86/kvm/x86.c     | 18 +++++++++---------
>  3 files changed, 10 insertions(+), 11 deletions(-)
> 
> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
> index 759952dd1222..f206fc35deff 100644
> --- a/arch/x86/kvm/lapic.c
> +++ b/arch/x86/kvm/lapic.c
> @@ -707,7 +707,7 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu)
>  static int apic_has_interrupt_for_ppr(struct kvm_lapic *apic, u32 ppr)
>  {
>  	int highest_irr;
> -	if (apic->vcpu->arch.apicv_active)
> +	if (kvm_x86_ops.sync_pir_to_irr)
>  		highest_irr = static_call(kvm_x86_sync_pir_to_irr)(apic->vcpu);

>  	else
>  		highest_irr = apic_find_highest_irr(apic);
> diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
> index 5630c241d5f6..d0f68d11ec70 100644
> --- a/arch/x86/kvm/svm/svm.c
> +++ b/arch/x86/kvm/svm/svm.c
> @@ -4651,7 +4651,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
>  	.load_eoi_exitmap = svm_load_eoi_exitmap,
>  	.hwapic_irr_update = svm_hwapic_irr_update,
>  	.hwapic_isr_update = svm_hwapic_isr_update,
> -	.sync_pir_to_irr = kvm_lapic_find_highest_irr,
>  	.apicv_post_state_restore = avic_post_state_restore,
>  
>  	.set_tss_addr = svm_set_tss_addr,
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 627c955101a0..a8f12c83db4b 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -4448,8 +4448,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
>  static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
>  				    struct kvm_lapic_state *s)
>  {
> -	if (vcpu->arch.apicv_active)
> -		static_call(kvm_x86_sync_pir_to_irr)(vcpu);
> +	static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
>  
>  	return kvm_apic_get_state(vcpu, s);
>  }
> @@ -9528,8 +9527,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
>  	if (irqchip_split(vcpu->kvm))
>  		kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors);
>  	else {
> -		if (vcpu->arch.apicv_active)
> -			static_call(kvm_x86_sync_pir_to_irr)(vcpu);
> +		static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
>  		if (ioapic_in_kernel(vcpu->kvm))
>  			kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
>  	}
> @@ -9802,10 +9800,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
>  
>  	/*
>  	 * This handles the case where a posted interrupt was
> -	 * notified with kvm_vcpu_kick.
> +	 * notified with kvm_vcpu_kick.  Assigned devices can
> +	 * use the POSTED_INTR_VECTOR even if APICv is disabled,
> +	 * so do it even if !kvm_vcpu_apicv_active(vcpu).
>  	 */
> -	if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active)
> -		static_call(kvm_x86_sync_pir_to_irr)(vcpu);
> +	if (kvm_lapic_enabled(vcpu))
> +		static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
>  
>  	if (kvm_vcpu_exit_request(vcpu)) {
>  		vcpu->mode = OUTSIDE_GUEST_MODE;
> @@ -9849,8 +9849,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
>  		if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST))
>  			break;
>  
> -		if (kvm_lapic_enabled(vcpu) && kvm->arch.apicv_active)
> -			static_call(kvm_x86_sync_pir_to_irr)(vcpu);
> +		if (kvm_lapic_enabled(vcpu))
> +			static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu);
>  
>  		if (unlikely(kvm_vcpu_exit_request(vcpu))) {
>  			exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED;


vmx_sync_pir_to_irr has 'if (KVM_BUG_ON(!vcpu->arch.apicv_active, vcpu->kvm))'
That has to be removed I think for this to work.

Plus the above calls now can happen when APICv is fully disabled (and not just inhibited),
which is also something that I think that vmx_sync_pir_to_irr should be fixed to be aware of.

Also note that VMX has code that sets vmx_x86_ops.sync_pir_to_irr to NULL in its 'hardware_setup'
if APICv is disabled. 
I wonder if that done befor or after the static_call_cond sites are updated.

I think that this code should be removed as well, and vmx_sync_pir_to_irr should just
do nothing when APICv is fully disabled.

I haven't run tested this code so I might be wrong of course.


Best regards,
	Maxim Levitsky