From: Paolo Bonzini <pbonzini@redhat.com>
To: Thomas Gleixner <tglx@linutronix.de>,
Andy Lutomirski <luto@amacapital.net>,
Vivek Goyal <vgoyal@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
Andy Lutomirski <luto@kernel.org>,
LKML <linux-kernel@vger.kernel.org>, X86 ML <x86@kernel.org>,
kvm list <kvm@vger.kernel.org>, stable <stable@vger.kernel.org>
Subject: Re: [PATCH v2] x86/kvm: Disable KVM_ASYNC_PF_SEND_ALWAYS
Date: Thu, 9 Apr 2020 11:03:50 +0200 [thread overview]
Message-ID: <92ea7036-0b77-20da-34ac-f425e6f233c2@redhat.com> (raw)
In-Reply-To: <87pncib06x.fsf@nanos.tec.linutronix.de>
On 08/04/20 15:01, Thomas Gleixner wrote:
>
> And it comes with restrictions:
>
> The Do Other Stuff event can only be delivered when guest IF=1.
>
> If guest IF=0 then the host has to suspend the guest until the
> situation is resolved.
>
> The 'Situation resolved' event must also wait for a guest IF=1 slot.
Additionally:
- the do other stuff event must be delivered to the same CPU that is
causing the host-side page fault
- the do other stuff event provides a token that identifies the cause
and the situation resolved event provides a matching token
This stuff is why I think the do other stuff event looks very much like
a #VE. But I think we're in violent agreement after all.
> If you just want to solve Viveks problem, then its good enough. I.e. the
> file truncation turns the EPT entries into #VE convertible entries and
> the guest #VE handler can figure it out. This one can be injected
> directly by the hardware, i.e. you don't need a VMEXIT.
>
> If you want the opportunistic do other stuff mechanism, then #VE has
> exactly the same problems as the existing async "PF". It's not magicaly
> making that go away.
You can inject #VE from the hypervisor too, with PV magic to distinguish
the two. However that's not necessarily a good idea because it makes it
harder to switch to hardware delivery in the future.
> One possible solution might be to make all recoverable EPT entries
> convertible and let the HW inject #VE for those.
>
> So the #VE handler in the guest would have to do:
>
> if (!recoverable()) {
> if (user_mode)
> send_signal();
> else if (!fixup_exception())
> die_hard();
> goto done;
> }
>
> store_ve_info_in_pv_page();
>
> if (!user_mode(regs) || !preemptible()) {
> hypercall_resolve_ept(can_continue = false);
> } else {
> init_completion();
> hypercall_resolve_ept(can_continue = true);
> wait_for_completion();
> }
>
> or something like that.
Yes, pretty much. The VE info can also be passed down to the hypercall
as arguments.
Paolo
> The hypercall to resolve the EPT fail on the host acts on the
> can_continue argument.
>
> If false, it suspends the guest vCPU and only returns when done.
>
> If true it kicks the resolve process and returns to the guest which
> suspends the task and tries to do something else.
>
> The wakeup side needs to be a regular interrupt and cannot go through
> #VE.
next prev parent reply other threads:[~2020-04-09 9:03 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
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 [this message]
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=92ea7036-0b77-20da-34ac-f425e6f233c2@redhat.com \
--to=pbonzini@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@amacapital.net \
--cc=luto@kernel.org \
--cc=peterz@infradead.org \
--cc=stable@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=vgoyal@redhat.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;
as well as URLs for NNTP newsgroup(s).