linux-kernel - Re: [PATCH] KVM: nVMX: Properly handle userspace interrupt window request

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] [day] [month] [year] [list]

Date:   Tue, 3 Mar 2020 09:50:36 +0100
From:   Paolo Bonzini <pbonzini@...hat.com>
To:     Sean Christopherson <sean.j.christopherson@...el.com>
Cc:     Vitaly Kuznetsov <vkuznets@...hat.com>,
        Wanpeng Li <wanpengli@...cent.com>,
        Jim Mattson <jmattson@...gle.com>,
        Joerg Roedel <joro@...tes.org>, kvm@...r.kernel.org,
        linux-kernel@...r.kernel.org, Liran Alon <liran.alon@...cle.com>
Subject: Re: [PATCH] KVM: nVMX: Properly handle userspace interrupt window
 request

On 03/03/20 07:27, Sean Christopherson wrote:
> Odds are good that this doesn't solve all the problems with running nested
> VMX and a userspace LAPIC, but I'm at least able to boot a kernel and run
> unit tests, i.e. it's less broken than before.  Not that it matters, I'm
> guessing no one actually uses this configuration, e.g. running a SMP
> guest with the current KVM+kernel hangs during boot because Qemu
> advertises PV IPIs to the guest, which require an in-kernel LAPIC.  I
> stumbled on this disaster when disabling the in-kernel LAPIC for a
> completely unrelated test.  I'm happy even if it does nothing more than
> get rid of the awful logic vmx_check_nested_events().

Yes, userspace LAPIC is more or less constantly broken.  I think it
should be deprecated in QEMU.

Paolo