linux-kernel - Re: [PATCH 1/1] KVM: nVMX: update VPPR on vmlaunch/vmresume

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20240920124414.26988-1-mankku@gmail.com>
Date: Fri, 20 Sep 2024 15:40:29 +0300
From: Markku Ahvenjärvi <mankku@...il.com>
To: seanjc@...gle.com
Cc: bp@...en8.de,
	dave.hansen@...ux.intel.com,
	hpa@...or.com,
	janne.karhunen@...il.com,
	kvm@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	mankku@...il.com,
	mingo@...hat.com,
	pbonzini@...hat.com,
	tglx@...utronix.de,
	x86@...nel.org
Subject: Re: [PATCH 1/1] KVM: nVMX: update VPPR on vmlaunch/vmresume

> This is architecturally incorrect, PPR isn't refreshed at VM-Enter.

Ah, I see. Thanks for pointing out.

> Aha!  I wonder if the missing PPR update is due to the nested VM-Enter path
> directly clearing IRR when processing a posted interrupt.
> 
> On top of https://github.com/kvm-x86/linux/tree/next, does this fix things?
> 
> diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
> index a8e7bc04d9bf..a8255c6f0d51 100644
> --- a/arch/x86/kvm/vmx/nested.c
> +++ b/arch/x86/kvm/vmx/nested.c
> @@ -3731,7 +3731,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
>             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);
> +               kvm_apic_ack_interrupt(vcpu, vmx->nested.posted_intr_nv);
>         }
> 
>         /* Hide L1D cache contents from the nested guest.  */

No, unfortunately.

The vmexits L1 is not receiving originate from deprivileged host (like timer
ticks), running in vmx non-root mode.

Thanks,
Markku