public inbox for kvm@vger.kernel.org
 help / color / mirror / Atom feed
From: "Radim Krčmář" <rkrcmar@redhat.com>
To: Andy Lutomirski <luto@amacapital.net>
Cc: Marcelo Tosatti <mtosatti@redhat.com>,
	kvm-devel <kvm@vger.kernel.org>, stable <stable@vger.kernel.org>,
	Paolo Bonzini <pbonzini@redhat.com>
Subject: Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
Date: Wed, 25 Mar 2015 13:52:15 +0100	[thread overview]
Message-ID: <20150325125212.GC21710@potion.brq.redhat.com> (raw)
In-Reply-To: <20150325110814.GE21522@potion.brq.redhat.com>

2015-03-25 12:08+0100, Radim Krčmář:
> Reverting the patch protects us from any migration, but I don't think we
> need to care about changing VCPUs as long as we read a consistent data
> from kvmclock.  (VCPU can change outside of this loop too, so it doesn't
> matter if we return a value not fit for this VCPU.)
> 
> I think we could drop the second __getcpu if our kvmclock was being
> handled better;  maybe with a patch like the one below:

The second __getcpu is not neccessary, but I forgot about rdtsc.
We need to either use rtdscp, know the host has synchronized tsc, or
monitor VCPU migrations.  Only the last one works everywhere.

  reply	other threads:[~2015-03-25 12:52 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-03-23 23:21 x86: kvm: Revert "remove sched notifier for cross-cpu migrations" Marcelo Tosatti
2015-03-23 23:30 ` Andy Lutomirski
2015-03-24 15:34 ` Radim Krčmář
2015-03-24 22:33   ` Andy Lutomirski
2015-03-25 11:08     ` Radim Krčmář
2015-03-25 12:52       ` Radim Krčmář [this message]
2015-03-25 21:28         ` Marcelo Tosatti
2015-03-25 22:33           ` Andy Lutomirski
2015-03-25 22:41             ` Marcelo Tosatti
2015-03-25 22:48               ` Andy Lutomirski
2015-03-25 23:13                 ` Marcelo Tosatti
2015-03-25 23:22                   ` Andy Lutomirski
2015-03-26 11:29                     ` Marcelo Tosatti
2015-03-26 18:51                       ` Andy Lutomirski
2015-03-26 20:31                         ` Radim Krcmar
2015-03-26 20:58                           ` Andy Lutomirski
2015-03-26 22:22                             ` Andy Lutomirski
2015-03-26 22:56                             ` Marcelo Tosatti
2015-03-26 23:09                               ` Andy Lutomirski
2015-03-26 23:22                                 ` Marcelo Tosatti
2015-03-26 23:28                                   ` Andy Lutomirski
2015-03-26 23:38                                     ` Marcelo Tosatti
2015-03-26 18:47       ` Andy Lutomirski
2015-03-26 20:10         ` Radim Krčmář
2015-03-26 20:52           ` Paolo Bonzini
2015-03-24 22:59   ` Marcelo Tosatti
2015-03-25 11:09     ` Radim Krčmář
2015-03-25 13:06 ` Radim Krčmář
2015-03-26 20:59 ` Radim Krčmář
2015-03-26 22:22   ` Marcelo Tosatti
2015-03-26 22:24     ` Andy Lutomirski
2015-03-26 22:40       ` Marcelo Tosatti

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=20150325125212.GC21710@potion.brq.redhat.com \
    --to=rkrcmar@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=luto@amacapital.net \
    --cc=mtosatti@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=stable@vger.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