From: "H. Peter Anvin" <hpa@zytor.com>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: caglar@pardus.org.tr, Avi Kivity <avi@qumranet.com>,
linux-kernel@vger.kernel.org, kvm-devel@lists.sourceforge.net,
Andi Kleen <andi@firstfloor.org>
Subject: Re: [GIT PULL][RESEND #2] KVM Updates for 2.6.23-rc1
Date: Tue, 17 Jul 2007 12:26:01 -0700 [thread overview]
Message-ID: <469D17C9.9010509@zytor.com> (raw)
In-Reply-To: <alpine.LFD.0.999.0707171212070.27353@woody.linux-foundation.org>
Linus Torvalds wrote:
>
> Actually, I think the *real* solution would be:
>
> - add a X86_HAS_CMPXCHG8B config option, and set it for the appropriate
> CPU selection (P6 and up, or whatever the rule is)
>
> - make KVM depend on it
>
> - make KVM and HIGHMEM64 _select_ another config option, namely the
> NEEDS_CMPXCHG8B
>
> and then we make the cpufeatures code check the CMPXCHG bit only if the
> NEEDS_CMPXCHG8B thing is set. That gives us the best of all worlds.
>
> Because there is no point in checking whether the CPU supports it if the
> kernel doesn't _need_ it. Especially since we know that some CPU's lie
> about it due to old NT bugs.
>
Yes. This is probably also true for other CPU feature options, at least
in the abstract (i.e. it may not apply to any of the current options).
-hpa
WARNING: multiple messages have this Message-ID (diff)
From: "H. Peter Anvin" <hpa-YMNOUZJC4hwAvxtiuMwx3w@public.gmane.org>
To: Linus Torvalds
<torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
Cc: kvm-devel-5NWGOfrQmneRv+LV9MX5uipxlwaOVQ5f@public.gmane.org,
Andi Kleen <andi-Vw/NltI1exuRpAAqCnN02g@public.gmane.org>,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: Re: [GIT PULL][RESEND #2] KVM Updates for 2.6.23-rc1
Date: Tue, 17 Jul 2007 12:26:01 -0700 [thread overview]
Message-ID: <469D17C9.9010509@zytor.com> (raw)
In-Reply-To: <alpine.LFD.0.999.0707171212070.27353-5CScLwifNT1QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org>
Linus Torvalds wrote:
>
> Actually, I think the *real* solution would be:
>
> - add a X86_HAS_CMPXCHG8B config option, and set it for the appropriate
> CPU selection (P6 and up, or whatever the rule is)
>
> - make KVM depend on it
>
> - make KVM and HIGHMEM64 _select_ another config option, namely the
> NEEDS_CMPXCHG8B
>
> and then we make the cpufeatures code check the CMPXCHG bit only if the
> NEEDS_CMPXCHG8B thing is set. That gives us the best of all worlds.
>
> Because there is no point in checking whether the CPU supports it if the
> kernel doesn't _need_ it. Especially since we know that some CPU's lie
> about it due to old NT bugs.
>
Yes. This is probably also true for other CPU feature options, at least
in the abstract (i.e. it may not apply to any of the current options).
-hpa
-------------------------------------------------------------------------
This SF.net email is sponsored by DB2 Express
Download DB2 Express C - the FREE version of DB2 express and take
control of your XML. No limits. Just data. Click to get it now.
http://sourceforge.net/powerbar/db2/
next prev parent reply other threads:[~2007-07-17 19:27 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-07-17 16:51 [GIT PULL][RESEND #2] KVM Updates for 2.6.23-rc1 Avi Kivity
2007-07-17 16:51 ` Avi Kivity
2007-07-17 18:39 ` S.Çağlar Onur
2007-07-17 19:05 ` H. Peter Anvin
2007-07-17 19:05 ` H. Peter Anvin
2007-07-17 19:15 ` Linus Torvalds
2007-07-17 19:15 ` Linus Torvalds
2007-07-17 19:26 ` H. Peter Anvin [this message]
2007-07-17 19:26 ` H. Peter Anvin
2007-07-17 23:25 ` S.Çağlar Onur
2007-07-17 23:25 ` S.Çağlar Onur
2007-07-17 23:38 ` [kvm-devel] " Anthony Liguori
2007-07-17 23:38 ` Anthony Liguori
2007-07-17 23:40 ` [kvm-devel] " S.Çağlar Onur
2007-07-18 9:31 ` S.Çağlar Onur
2007-07-18 9:31 ` S.Çağlar Onur
2007-07-18 9:35 ` [kvm-devel] " Avi Kivity
2007-07-18 9:35 ` Avi Kivity
2007-07-18 10:09 ` [kvm-devel] " S.Çağlar Onur
2007-07-18 10:09 ` S.Çağlar Onur
2007-07-18 10:17 ` [kvm-devel] " S.Çağlar Onur
2007-07-18 10:17 ` S.Çağlar Onur
2007-07-18 10:31 ` [kvm-devel] " Avi Kivity
2007-07-18 10:50 ` S.Çağlar Onur
2007-07-18 10:50 ` S.Çağlar Onur
2007-07-20 5:31 ` [kvm-devel] " Avi Kivity
2007-07-20 5:31 ` Avi Kivity
2007-07-20 11:37 ` [kvm-devel] " S.Çağlar Onur
2007-07-20 11:37 ` S.Çağlar Onur
2007-07-18 17:46 ` [kvm-devel] " S.Çağlar Onur
2007-07-18 17:46 ` S.Çağlar Onur
2007-07-18 18:04 ` [kvm-devel] " Avi Kivity
2007-07-18 18:04 ` Avi Kivity
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=469D17C9.9010509@zytor.com \
--to=hpa@zytor.com \
--cc=andi@firstfloor.org \
--cc=avi@qumranet.com \
--cc=caglar@pardus.org.tr \
--cc=kvm-devel@lists.sourceforge.net \
--cc=linux-kernel@vger.kernel.org \
--cc=torvalds@linux-foundation.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.