From: Paolo Bonzini <pbonzini@redhat.com>
To: Marcelo Tosatti <mtosatti@redhat.com>,
Andy Lutomirski <luto@amacapital.net>
Cc: Gleb Natapov <gleb@kernel.org>,
"xen-devel@lists.xenproject.org" <xen-devel@lists.xenproject.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
kvm list <kvm@vger.kernel.org>
Subject: Re: [RFC 2/2] x86, vdso, pvclock: Simplify and speed up the vdso pvclock reader
Date: Tue, 06 Jan 2015 09:42:37 +0100 [thread overview]
Message-ID: <54AB9FFD.6070309@redhat.com> (raw)
In-Reply-To: <20150105224858.GA6846@amt.cnet>
On 05/01/2015 23:48, Marcelo Tosatti wrote:
>>> > > But there is no guarantee that vCPU-N has updated its pvti when
>>> > > vCPU-M resumes guest instruction execution.
>> >
>> > Still confused. So we can freeze all vCPUs in the host, then update
>> > pvti 1, then resume vCPU 1, then update pvti 0? In that case, we have
>> > a problem, because vCPU 1 can observe pvti 0 mid-update, and KVM
>> > doesn't increment the version pre-update, and we can return completely
>> > bogus results.
> Yes.
But then the getcpu test would fail (1->0). Even if you have an ABA
situation (1->0->1), it's okay because the pvti that is fetched is the
one returned by the first getcpu.
Paolo
WARNING: multiple messages have this Message-ID (diff)
From: Paolo Bonzini <pbonzini@redhat.com>
To: Marcelo Tosatti <mtosatti@redhat.com>,
Andy Lutomirski <luto@amacapital.net>
Cc: Gleb Natapov <gleb@kernel.org>, kvm list <kvm@vger.kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"xen-devel@lists.xenproject.org" <xen-devel@lists.xenproject.org>
Subject: Re: [RFC 2/2] x86, vdso, pvclock: Simplify and speed up the vdso pvclock reader
Date: Tue, 06 Jan 2015 09:42:37 +0100 [thread overview]
Message-ID: <54AB9FFD.6070309@redhat.com> (raw)
In-Reply-To: <20150105224858.GA6846@amt.cnet>
On 05/01/2015 23:48, Marcelo Tosatti wrote:
>>> > > But there is no guarantee that vCPU-N has updated its pvti when
>>> > > vCPU-M resumes guest instruction execution.
>> >
>> > Still confused. So we can freeze all vCPUs in the host, then update
>> > pvti 1, then resume vCPU 1, then update pvti 0? In that case, we have
>> > a problem, because vCPU 1 can observe pvti 0 mid-update, and KVM
>> > doesn't increment the version pre-update, and we can return completely
>> > bogus results.
> Yes.
But then the getcpu test would fail (1->0). Even if you have an ABA
situation (1->0->1), it's okay because the pvti that is fetched is the
one returned by the first getcpu.
Paolo
next prev parent reply other threads:[~2015-01-06 8:42 UTC|newest]
Thread overview: 76+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-12-23 0:39 [RFC 0/2] x86, vdso, pvclock: Cleanups and speedups Andy Lutomirski
2014-12-23 0:39 ` [RFC 1/2] x86, vdso: Use asm volatile in __getcpu Andy Lutomirski
2014-12-23 0:39 ` Andy Lutomirski
2014-12-23 0:39 ` [RFC 2/2] x86, vdso, pvclock: Simplify and speed up the vdso pvclock reader Andy Lutomirski
2014-12-23 0:39 ` Andy Lutomirski
2014-12-23 10:28 ` [Xen-devel] " David Vrabel
2014-12-23 10:28 ` David Vrabel
2014-12-23 15:14 ` Boris Ostrovsky
2014-12-23 15:14 ` [Xen-devel] " Boris Ostrovsky
2014-12-23 15:14 ` Paolo Bonzini
2014-12-23 15:25 ` Boris Ostrovsky
2014-12-23 15:25 ` [Xen-devel] " Boris Ostrovsky
2014-12-23 15:14 ` Paolo Bonzini
2014-12-24 21:30 ` David Matlack
2014-12-24 21:30 ` David Matlack
2014-12-24 21:43 ` Andy Lutomirski
2014-12-24 21:43 ` Andy Lutomirski
2015-01-05 15:25 ` Marcelo Tosatti
2015-01-05 15:25 ` Marcelo Tosatti
2015-01-05 18:56 ` Andy Lutomirski
2015-01-05 19:17 ` Marcelo Tosatti
2015-01-05 22:38 ` Andy Lutomirski
2015-01-05 22:48 ` Marcelo Tosatti
2015-01-05 22:48 ` Marcelo Tosatti
2015-01-05 22:53 ` Andy Lutomirski
2015-01-05 22:53 ` Andy Lutomirski
2015-01-06 8:42 ` Paolo Bonzini [this message]
2015-01-06 8:42 ` Paolo Bonzini
2015-01-06 12:01 ` Paolo Bonzini
2015-01-06 16:56 ` Andy Lutomirski
2015-01-06 16:56 ` Andy Lutomirski
2015-01-06 18:13 ` Marcelo Tosatti
2015-01-06 18:26 ` Andy Lutomirski
2015-01-06 18:45 ` Marcelo Tosatti
2015-01-06 18:45 ` Marcelo Tosatti
2015-01-06 19:49 ` Andy Lutomirski
2015-01-06 19:49 ` Andy Lutomirski
2015-01-06 20:20 ` Marcelo Tosatti
2015-01-06 20:20 ` Marcelo Tosatti
2015-01-06 21:54 ` Andy Lutomirski
2015-01-06 21:54 ` Andy Lutomirski
2015-01-08 22:31 ` Marcelo Tosatti
2015-01-08 22:31 ` Marcelo Tosatti
2015-01-08 22:43 ` Andy Lutomirski
2015-02-26 22:46 ` Andy Lutomirski
2015-02-26 22:46 ` Andy Lutomirski
2015-01-08 22:43 ` Andy Lutomirski
2015-01-07 5:41 ` Paolo Bonzini
2015-01-07 5:41 ` Paolo Bonzini
2015-01-06 18:26 ` Andy Lutomirski
2015-01-06 18:13 ` Marcelo Tosatti
2015-01-07 5:38 ` Paolo Bonzini
2015-01-07 7:18 ` Andy Lutomirski
2015-01-07 9:00 ` Paolo Bonzini
2015-01-07 9:00 ` Paolo Bonzini
2015-01-07 14:45 ` Marcelo Tosatti
2015-01-07 14:45 ` Marcelo Tosatti
2015-01-07 7:18 ` Andy Lutomirski
2015-01-07 5:38 ` Paolo Bonzini
2015-01-05 22:38 ` Andy Lutomirski
2015-01-06 8:39 ` Paolo Bonzini
2015-01-06 8:39 ` Paolo Bonzini
2015-01-05 19:17 ` Marcelo Tosatti
2015-01-05 22:23 ` Paolo Bonzini
2015-01-05 22:23 ` Paolo Bonzini
2015-01-06 14:35 ` Konrad Rzeszutek Wilk
2015-01-06 14:35 ` [Xen-devel] " Konrad Rzeszutek Wilk
2015-01-05 18:56 ` Andy Lutomirski
2015-01-08 12:51 ` David Vrabel
2015-01-08 12:51 ` [Xen-devel] " David Vrabel
2014-12-23 7:21 ` [RFC 0/2] x86, vdso, pvclock: Cleanups and speedups Paolo Bonzini
2014-12-23 7:21 ` Paolo Bonzini
2014-12-23 8:16 ` Andy Lutomirski
2014-12-23 8:16 ` Andy Lutomirski
2014-12-23 8:30 ` Paolo Bonzini
2014-12-23 8:30 ` Paolo Bonzini
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=54AB9FFD.6070309@redhat.com \
--to=pbonzini@redhat.com \
--cc=gleb@kernel.org \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@amacapital.net \
--cc=mtosatti@redhat.com \
--cc=xen-devel@lists.xenproject.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.