From: Andi Kleen <andi@firstfloor.org>
To: Zachary Amsden <zamsden@redhat.com>
Cc: kvm@vger.kernel.org, Avi Kivity <avi@redhat.com>,
Marcelo Tosatti <mtosatti@redhat.com>,
Joerg Roedel <joerg.roedel@amd.com>,
linux-kernel@vger.kernel.org, Dor Laor <dlaor@redhat.com>
Subject: Re: [PATCH RFC: kvm tsc virtualization 15/20] Fix longstanding races
Date: Tue, 15 Dec 2009 14:58:13 +0100 [thread overview]
Message-ID: <87ws0owd8q.fsf@basil.nowhere.org> (raw)
In-Reply-To: <1260850127-9766-16-git-send-email-zamsden@redhat.com> (Zachary Amsden's message of "Mon, 14 Dec 2009 18:08:42 -1000")
Zachary Amsden <zamsden@redhat.com> writes:
>
> Damn, this is complicated crap. The analagous task in real life would
> be keeping a band of howler monkeys, each in their own tree, singing in
> unison while the lead vocalist jumps from tree to tree, and meanwhile,
> an unseen conductor keeps changing the tempo the piece is played at.
> Thankfully, there are no key changes, however, occasionally new trees
> sprout up at random and live ones fall over.
On CPUs where the TSC frequency is not constant typically you can't tell
exactly when the frequency changes. So you would always have a race window
where the frequency is unknown and wrong results occur. This can be worked
around, but it's quite complicated.
The safe way is to not use the TSC on such CPUs.
-Andi
--
ak@linux.intel.com -- Speaking for myself only.
next prev parent reply other threads:[~2009-12-15 13:58 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <1260850127-9766-1-git-send-email-zamsden@redhat.com>
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 01/20] Move TSC read to vmx_vcpu_put Zachary Amsden
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 02/20] Add a hotplug notifier to KVM x86 backend Zachary Amsden
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 03/20] TSC offset framework Zachary Amsden
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 04/20] Synchronize TSC when a new CPU comes up Zachary Amsden
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 05/20] Fix AMD C1 TSC desynchronization Zachary Amsden
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 06/20] Make TSC reference stable across frequency changes Zachary Amsden
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 07/20] Basic SVM implementation of RDTSC trapping Zachary Amsden
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 08/20] Export the reference TSC from KVM module Zachary Amsden
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 09/20] Use TSC reference for SVM Zachary Amsden
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 10/20] Add a stat counter for RDTSC exits Zachary Amsden
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 11/20] Use highest TSC frequency as reference clock Zachary Amsden
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 12/20] Higher accuracy TSC offset computation Zachary Amsden
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 13/20] Combine observed TSC deviation into moving average Zachary Amsden
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 14/20] Move TSC cpu vars to a struct Zachary Amsden
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 15/20] Fix longstanding races Zachary Amsden
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 16/20] Fix 32-bit mult_precise Zachary Amsden
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 17/20] Periodically measure TSC skew Zachary Amsden
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 18/20] Implement variable speed TSC Zachary Amsden
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 19/20] IOCTL for different TSC modes Zachary Amsden
2009-12-15 4:08 ` [PATCH RFC: kvm tsc virtualization 20/20] Get passthrough TSC working in SVM again Zachary Amsden
2009-12-15 13:58 ` Andi Kleen [this message]
2009-12-15 18:21 ` [PATCH RFC: kvm tsc virtualization 15/20] Fix longstanding races Marcelo Tosatti
2009-12-15 21:26 ` Zachary Amsden
2009-12-16 14:41 ` 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=87ws0owd8q.fsf@basil.nowhere.org \
--to=andi@firstfloor.org \
--cc=avi@redhat.com \
--cc=dlaor@redhat.com \
--cc=joerg.roedel@amd.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mtosatti@redhat.com \
--cc=zamsden@redhat.com \
/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