Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable
From:   Andy Lutomirski <luto@amacapital.net>
Mime-Version: 1.0 (1.0)
Subject: Re: [patch 1/2] x86,module: Detect VMX modules and disable Split-Lock-Detect
Date:   Fri, 3 Apr 2020 13:58:17 -0700
Message-Id: <737F6739-9B8B-4C73-91D3-B873D5780F5E@amacapital.net>
References: <87o8s8l7t3.fsf@nanos.tec.linutronix.de>
Cc:     Peter Zijlstra <peterz@infradead.org>,
        Jessica Yu <jeyu@kernel.org>,
        Rasmus Villemoes <rasmus.villemoes@prevas.dk>,
        LKML <linux-kernel@vger.kernel.org>, x86@kernel.org,
        "Kenneth R. Crudup" <kenny@panix.com>,
        Paolo Bonzini <pbonzini@redhat.com>,
        Fenghua Yu <fenghua.yu@intel.com>,
        Xiaoyao Li <xiaoyao.li@intel.com>,
        Nadav Amit <namit@vmware.com>,
        Thomas Hellstrom <thellstrom@vmware.com>,
        Sean Christopherson <sean.j.christopherson@intel.com>,
        Tony Luck <tony.luck@intel.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        jannh@google.com, keescook@chromium.org, vbox-dev@virtualbox.org
In-Reply-To: <87o8s8l7t3.fsf@nanos.tec.linutronix.de>
To:     Thomas Gleixner <tglx@linutronix.de>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk


> On Apr 3, 2020, at 11:54 AM, Thomas Gleixner <tglx@linutronix.de> wrote:
>=20
> =EF=BB=BFPeter Zijlstra <peterz@infradead.org> writes:
>>> On Fri, Apr 03, 2020 at 04:35:00PM +0200, Jessica Yu wrote:
>>> +++ Rasmus Villemoes [03/04/20 01:42 +0200]:
>>>> On 02/04/2020 14.32, Thomas Gleixner wrote:
>>>>> From: Peter Zijlstra <peterz@infradead.org>
>>>>>=20
>>>>> It turns out that with Split-Lock-Detect enabled (default) any VMX
>>>>> hypervisor needs at least a little modification in order to not blindl=
y
>>>>> inject the #AC into the guest without the guest being ready for it.
>>>>>=20
>>>>> Since there is no telling which module implements a hypervisor, scan t=
he
>>>>> module text and look for the VMLAUNCH instruction. If found, the modul=
e is
>>>>> assumed to be a hypervisor of some sort and SLD is disabled.
>>>>=20
>>>> How long does that scan take/add to module load time? Would it make
>>>> sense to exempt in-tree modules?
>>>>=20
>>>> Rasmus
>>>=20
>>> I second Rasmus's question. It seems rather unfortunate that we have
>>> to do this text scan for every module load on x86, when it doesn't
>>> apply to the majority of them, and only to a handful of out-of-tree
>>> hypervisor modules (assuming kvm is taken care of already).
>>>=20
>>> I wonder if it would make sense then to limit the text scans to just
>>> out-of-tree modules (i.e., missing the intree modinfo flag)?
>>=20
>> It would; didn't know there was one.
>=20
> But that still would not make it complete.
>=20
> I was staring at virtualbox today after Jann pointed out that this
> sucker does complete backwards things.
>=20
>  The kernel driver does not contain any VM* instructions at all.
>=20
> The actual hypervisor code is built as a separate binary and somehow
> loaded into the kernel with their own magic fixup of relocations and
> function linking. This "design" probably comes from the original
> virtualbox implementation which circumvented GPL that way.
>=20
> TBH, I don't care if we wreckage virtualbox simply because that thing is
> already a complete and utter trainwreck violating taste and common sense
> in any possible way. Just for illustration:
>=20
>  - It installs preempt notifiers and the first thing in the callback
>    function is to issue 'stac()'!
>=20
>  - There is quite some other horrible code in there which fiddles in
>    the guts of the kernel just because it can.
>=20
>  - Conditionals in release code which check stuff like
>    VBOX_WITH_TEXT_MODMEM_HACK, VBOX_WITH_EFLAGS_AC_SET_IN_VBOXDRV,
>    VBOX_WITH_NON_PROD_HACK_FOR_PERF_STACKS along with the most absurd
>    hacks ever.
>=20
> If you feel the need to look yourself, please use your eyecancer
> protection gear.
>=20
> Can someone at Oracle please make sure, that this monstrosity gets shred
> in pieces?
>=20
> Enough vented, but that still does not solve the SLD problem in any
> sensible way.

Could we unexport set_memory_x perhaps?  And maybe try to make virtualbox br=
eak in as many ways as possible?

>=20
> Thanks,
>=20
>        tglx