From: Paolo Bonzini <pbonzini@redhat.com>
To: "Woodhouse, David" <dwmw@amazon.co.uk>,
"jmattson@google.com" <jmattson@google.com>,
"kernellwp@gmail.com" <kernellwp@gmail.com>
Cc: "kvm@vger.kernel.org" <kvm@vger.kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"tim.c.chen@linux.intel.com" <tim.c.chen@linux.intel.com>,
"Liguori, Anthony" <aliguori@amazon.com>,
"x86@kernel.org" <x86@kernel.org>,
"liran.alon@oracle.com" <liran.alon@oracle.com>,
"bp@alien8.de" <bp@alien8.de>,
"thomas.lendacky@amd.com" <thomas.lendacky@amd.com>,
"rkrcmar@redhat.com" <rkrcmar@redhat.com>
Subject: Re: [PATCH 4/8] kvm: vmx: Set IBPB when running a different VCPU
Date: Mon, 15 Jan 2018 10:21:08 +0100 [thread overview]
Message-ID: <dd274539-8943-d8b8-9938-53162e3e85e8@redhat.com> (raw)
In-Reply-To: <1515835795.22302.517.camel@amazon.co.uk>
On 13/01/2018 10:29, Woodhouse, David wrote:
> On Fri, 2018-01-12 at 09:03 -0800, Jim Mattson wrote:
>> The point behind the IPBP in vmx_vcpu_load is to prevent one VCPU from
>> steering the speculative execution of the next. If the VMCS address is
>> recycled, vmx_vcpu_load doesn't realize that the VCPUs are different,
>> and so it won't issue the IPBP.
>
> I don't understand the sequence of events that could lead to this.
>
> If the VMCS is freed, surely per_cpu(current_vmcs, cpu) has to be
> cleared? If the VMCS is freed while it's still *active* on a CPU,
> that's a bug, surely? And if that CPU is later offlined and clears the
> VMCS, it's going to scribble on freed (and potentially re-used) memory.
You're right, svm.c needs it but vmx.c does not (because AMD has no
vmclear equivalent).
>>> + if (have_spec_ctrl)
>>> + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
>
> Also, I think the same condition applies to the conditional branches
> over the IBPB-frobbing, as it does to setting IBRS. You can eschew the
> 'else lfence' only if you put in a comment showing that you've proved
> it's safe. Many of the other bits like this are being done with
> alternatives, which avoids that concern completely.
>
> But really, I don't like this series much. Don't say "let's do this
> until upstream supports...". Just fix it up properly, and add the
> generic X86_FEATURE_IBPB bit and use it. We have *too* many separate
> tiny patch sets, and we need to be getting our act together and putting
> it all in one.
I agree, this series is not meant to be committed. I only posted to get
early reviews (and it was very effective for that purpose).
Paolo
next prev parent reply other threads:[~2018-01-15 9:21 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-09 12:03 [PATCH v2 0/8] KVM: x86: expose CVE-2017-5715 ("Spectre variant 2") mitigations to guest Paolo Bonzini
2018-01-09 12:03 ` [PATCH 1/8] KVM: x86: add SPEC_CTRL and IBPB_SUPPORT accessors Paolo Bonzini
2018-01-15 9:42 ` David Hildenbrand
2018-01-09 12:03 ` [PATCH 2/8] x86/msr: add definitions for indirect branch predictor MSRs Paolo Bonzini
2018-01-09 12:03 ` [PATCH 3/8] kvm: vmx: pass MSR_IA32_SPEC_CTRL and MSR_IA32_PRED_CMD down to the guest Paolo Bonzini
2018-01-13 10:16 ` Longpeng (Mike)
2018-01-15 9:23 ` Paolo Bonzini
2018-01-15 9:34 ` Thomas Gleixner
2018-01-09 12:03 ` [PATCH 4/8] kvm: vmx: Set IBPB when running a different VCPU Paolo Bonzini
2018-01-12 1:49 ` Wanpeng Li
2018-01-12 17:03 ` Jim Mattson
2018-01-13 9:29 ` Woodhouse, David
2018-01-15 9:21 ` Paolo Bonzini [this message]
2018-01-09 12:03 ` [PATCH 5/8] KVM: SVM: fix comment Paolo Bonzini
2018-01-15 9:53 ` David Hildenbrand
2018-01-09 12:03 ` [PATCH 6/8] kvm: svm: pass MSR_IA32_SPEC_CTRL and MSR_IA32_PRED_CMD down to guest Paolo Bonzini
2018-01-09 14:22 ` Konrad Rzeszutek Wilk
2018-01-09 16:05 ` Paolo Bonzini
2018-01-09 16:08 ` Paolo Bonzini
2018-01-11 10:45 ` Wanpeng Li
2018-01-10 20:13 ` Tom Lendacky
2018-01-11 10:33 ` Paolo Bonzini
2018-01-09 12:03 ` [PATCH 7/8] x86/svm: Set IBPB when running a different VCPU Paolo Bonzini
2018-01-09 14:23 ` Konrad Rzeszutek Wilk
2018-01-09 12:03 ` [PATCH 8/8] KVM: x86: add SPEC_CTRL and IBPB_SUPPORT to MSR and CPUID lists Paolo Bonzini
2018-01-13 1:25 ` Eric Wheeler
2018-01-13 8:00 ` Paolo Bonzini
2018-01-16 0:40 ` Eric Wheeler
2018-01-16 7:39 ` R: " Paolo Bonzini
2018-01-09 12:03 ` [PATCH 9/8] KVM: x86: limit MSR_IA32_SPEC_CTRL access based on CPUID availability Paolo Bonzini
2018-01-16 0:55 ` Eric Wheeler
2018-01-16 12:59 ` Paolo Bonzini
2018-01-30 13:21 ` [9/8] " Mihai Carabas
2018-01-30 16:33 ` Jim Mattson
2018-01-30 16:43 ` Mihai Carabas
2018-01-30 16:57 ` Jim Mattson
2018-01-30 17:14 ` David Woodhouse
2018-01-30 17:38 ` Jim Mattson
2018-01-30 17:45 ` Thomas Gleixner
2018-01-30 23:11 ` Paolo Bonzini
2018-01-30 23:47 ` David Woodhouse
2018-01-31 1:06 ` Paolo Bonzini
2018-02-05 11:10 ` Ingo Molnar
2018-02-05 11:15 ` David Woodhouse
2018-02-05 12:10 ` Ingo Molnar
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=dd274539-8943-d8b8-9938-53162e3e85e8@redhat.com \
--to=pbonzini@redhat.com \
--cc=aliguori@amazon.com \
--cc=bp@alien8.de \
--cc=dwmw@amazon.co.uk \
--cc=jmattson@google.com \
--cc=kernellwp@gmail.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=liran.alon@oracle.com \
--cc=rkrcmar@redhat.com \
--cc=thomas.lendacky@amd.com \
--cc=tim.c.chen@linux.intel.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®