From: Thomas Gleixner <tglx@linutronix.de>
To: Andy Lutomirski <luto@kernel.org>, Andy Lutomirski <luto@kernel.org>
Cc: LKML <linux-kernel@vger.kernel.org>, X86 ML <x86@kernel.org>,
kvm list <kvm@vger.kernel.org>,
Paolo Bonzini <pbonzini@redhat.com>,
stable <stable@vger.kernel.org>
Subject: Re: [PATCH v2] x86/kvm: Disable KVM_ASYNC_PF_SEND_ALWAYS
Date: Sat, 07 Mar 2020 16:47:01 +0100 [thread overview]
Message-ID: <87ftek9ngq.fsf@nanos.tec.linutronix.de> (raw)
In-Reply-To: <CALCETrVmsF9JSMLSd44-3GGWEz6siJQxudeaYiVnvv__YDT1BQ@mail.gmail.com>
Andy Lutomirski <luto@kernel.org> writes:
> On Fri, Mar 6, 2020 at 6:26 PM Andy Lutomirski <luto@kernel.org> wrote:
>> + /*
>> + * We do not set KVM_ASYNC_PF_SEND_ALWAYS. With the current
>> + * KVM paravirt ABI, the following scenario is possible:
>> + *
>> + * #PF: async page fault (KVM_PV_REASON_PAGE_NOT_PRESENT)
>> + * NMI before CR2 or KVM_PF_REASON_PAGE_NOT_PRESENT
>> + * NMI accesses user memory, e.g. due to perf
>> + * #PF: normal page fault
>> + * #PF reads CR2 and apf_reason -- apf_reason should be 0
>> + *
>> + * outer #PF reads CR2 and apf_reason -- apf_reason should be
>> + * KVM_PV_REASON_PAGE_NOT_PRESENT
>> + *
>> + * There is no possible way that both reads of CR2 and
>> + * apf_reason get the correct values. Fixing this would
>> + * require paravirt ABI changes.
>> + */
>> +
>
> Upon re-reading my own comment, I think the problem is real, but I
> don't think my patch fixes it. The outer #PF could just as easily
> have come from user mode. We may actually need the NMI code (and
> perhaps MCE and maybe #DB too) to save, clear, and restore apf_reason.
> If we do this, then maybe CPL0 async PFs are actually okay, but the
> semantics are so poorly defined that I'm not very confident about
> that.
I think even with the current mode this is fixable on the host side when
it keeps track of the state.
The host knows exactly when it injects a async PF and it can store CR2
and reason of that async PF in flight.
On the next VMEXIT it checks whether apf_reason is 0. If apf_reason is 0
then it knows that the guest has read CR2 and apf_reason. All good
nothing to worry about.
If not it needs to be careful.
As long as the apf_reason of the last async #PF is not cleared by the
guest no new async #PF can be injected. That's already correct because
in that case IF==0 which prevents a nested async #PF.
If MCE, NMI trigger a real pagefault then the #PF injection needs to
clear apf_reason and set the correct CR2. When that #PF returns then the
old CR2 and apf_reason need to be restored.
I tried to figure out whether any of this logic exists in the KVM code,
but I got completely lost in that code. Maybe I try later today again.
Thanks,
tglx
next prev parent reply other threads:[~2020-03-07 15:47 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-07 2:26 [PATCH v2] x86/kvm: Disable KVM_ASYNC_PF_SEND_ALWAYS Andy Lutomirski
2020-03-07 15:03 ` Andy Lutomirski
2020-03-07 15:47 ` Thomas Gleixner [this message]
2020-03-07 15:59 ` Andy Lutomirski
2020-03-07 19:01 ` Thomas Gleixner
2020-03-07 19:34 ` Andy Lutomirski
2020-03-08 7:23 ` Thomas Gleixner
2020-03-09 6:57 ` Thomas Gleixner
2020-03-09 8:40 ` Paolo Bonzini
2020-03-09 9:09 ` Thomas Gleixner
2020-03-09 18:14 ` Andy Lutomirski
2020-03-09 19:05 ` Thomas Gleixner
2020-03-09 20:22 ` Peter Zijlstra
2020-04-06 19:09 ` Vivek Goyal
2020-04-06 20:25 ` Peter Zijlstra
2020-04-06 20:32 ` Andy Lutomirski
2020-04-06 20:42 ` Andy Lutomirski
2020-04-07 17:21 ` Vivek Goyal
2020-04-07 17:38 ` Andy Lutomirski
2020-04-07 20:20 ` Thomas Gleixner
2020-04-07 21:41 ` Andy Lutomirski
2020-04-07 22:07 ` Paolo Bonzini
2020-04-07 22:29 ` Andy Lutomirski
2020-04-08 0:30 ` Paolo Bonzini
2020-05-21 15:55 ` Vivek Goyal
2020-04-07 22:48 ` Thomas Gleixner
2020-04-08 4:48 ` Andy Lutomirski
2020-04-08 9:32 ` Borislav Petkov
2020-04-08 10:12 ` Thomas Gleixner
2020-04-08 18:23 ` Vivek Goyal
2020-04-07 22:49 ` Vivek Goyal
2020-04-08 10:01 ` Borislav Petkov
2020-04-07 22:04 ` Paolo Bonzini
2020-04-07 23:21 ` Thomas Gleixner
2020-04-08 8:23 ` Paolo Bonzini
2020-04-08 13:01 ` Thomas Gleixner
2020-04-08 15:38 ` Peter Zijlstra
2020-04-08 16:41 ` Thomas Gleixner
2020-04-09 9:03 ` Paolo Bonzini
2020-04-08 15:34 ` Sean Christopherson
2020-04-08 16:50 ` Paolo Bonzini
2020-04-08 18:01 ` Thomas Gleixner
2020-04-08 20:34 ` Vivek Goyal
2020-04-08 23:06 ` Thomas Gleixner
2020-04-08 23:14 ` Thomas Gleixner
2020-04-09 4:50 ` Andy Lutomirski
2020-04-09 9:43 ` Paolo Bonzini
2020-04-09 11:36 ` Andrew Cooper
2020-04-09 12:47 ` Paolo Bonzini
2020-04-09 14:13 ` Andrew Cooper
2020-04-09 14:32 ` Paolo Bonzini
2020-04-09 15:03 ` Andy Lutomirski
2020-04-09 15:17 ` Paolo Bonzini
2020-04-09 17:32 ` Andy Lutomirski
2020-04-06 21:32 ` Thomas Gleixner
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=87ftek9ngq.fsf@nanos.tec.linutronix.de \
--to=tglx@linutronix.de \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=pbonzini@redhat.com \
--cc=stable@vger.kernel.org \
--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;
as well as URLs for NNTP newsgroup(s).