From: Gleb Natapov <gleb@redhat.com>
To: Andre Przywara <andre@andrep.de>
Cc: "Borislav Petkov" <bp@alien8.de>,
kvm@vger.kernel.org, "Jörg Rödel" <joro@8bytes.org>,
"H. Peter Anvin" <hpa@zytor.com>, x86-ml <x86@kernel.org>,
kvm@vger-kernel.org
Subject: Re: [RFC PATCH] Emulate MOVBE
Date: Wed, 10 Apr 2013 13:08:46 +0300 [thread overview]
Message-ID: <20130410100845.GB17919@redhat.com> (raw)
In-Reply-To: <20130410112942.07dfc167@slackpad>
On Wed, Apr 10, 2013 at 11:29:42AM +0200, Andre Przywara wrote:
> In a real world VendorSpecific should be replaced with something more
> meaningful. Depends on KVMs intention to emulate instructions, actually
> out of scope for a pure virtualizer.
>
Something like EmulateOnUD.
> What is the opinion from the KVM folks on this? Shall we start to
> emulate instructions the host does not provide? In this particular case
> a relatively simple patch fixes a problem (starting Atom optimized
> kernels on non-Atom machines).
We can add the emulation, but we should not start announcing the instruction
availability to a guest if host cpu does not have it by default. This
may trick a guest into thinking that movbe is the fastest way to do
something when it is not.
>
> (And if one can believe the AMD Fam16h SWOG [1], PS4^Wfuture AMD
> processors have MOVBE, so it's not even actually one CPU anymore).
If a host CPU has the instruction emulation is not needed unless the
instruction is used for MMIO access.
--
Gleb.
next prev parent reply other threads:[~2013-04-10 10:09 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-04-09 23:46 [RFC PATCH] Emulate MOVBE Borislav Petkov
2013-04-10 0:03 ` Borislav Petkov
2013-04-10 0:04 ` H. Peter Anvin
2013-04-10 9:53 ` Borislav Petkov
2013-04-10 9:29 ` Andre Przywara
2013-04-10 10:08 ` Gleb Natapov [this message]
2013-04-10 10:17 ` Borislav Petkov
2013-04-10 10:21 ` Gleb Natapov
2013-04-10 10:39 ` Andre Przywara
2013-04-10 12:16 ` Gleb Natapov
2013-04-11 0:18 ` [PATCH -v2] kvm: " Borislav Petkov
2013-04-11 14:28 ` Gleb Natapov
2013-04-11 15:37 ` Borislav Petkov
2013-04-14 7:41 ` Gleb Natapov
2013-04-14 17:32 ` Borislav Petkov
2013-04-14 18:36 ` H. Peter Anvin
2013-04-14 19:09 ` Borislav Petkov
2013-04-14 19:40 ` H. Peter Anvin
2013-04-16 17:42 ` Gleb Natapov
2013-04-17 11:04 ` Borislav Petkov
2013-04-17 13:38 ` Gleb Natapov
2013-04-17 14:02 ` Borislav Petkov
2013-04-18 22:48 ` Borislav Petkov
2013-04-21 9:46 ` Gleb Natapov
2013-04-21 11:30 ` Borislav Petkov
2013-04-21 12:51 ` Gleb Natapov
2013-04-23 23:41 ` Borislav Petkov
2013-04-23 23:50 ` H. Peter Anvin
2013-04-24 8:42 ` Gleb Natapov
2013-04-24 8:47 ` Borislav Petkov
2013-04-14 8:43 ` Gleb Natapov
2013-04-14 21:02 ` Borislav Petkov
2013-04-16 11:36 ` Paolo Bonzini
2013-04-21 11:46 ` Borislav Petkov
2013-04-21 12:23 ` Borislav Petkov
2013-04-22 8:53 ` Paolo Bonzini
2013-04-22 9:38 ` Borislav Petkov
2013-04-22 9:42 ` Gleb Natapov
2013-04-22 9:52 ` Borislav Petkov
2013-04-22 9:58 ` Gleb Natapov
2013-04-22 13:49 ` Borislav Petkov
2013-04-26 16:08 ` Borislav Petkov
2013-04-16 11:47 ` [RFC PATCH] " Paolo Bonzini
2013-04-16 12:08 ` Borislav Petkov
2013-04-16 12:13 ` H. Peter Anvin
2013-04-16 17:28 ` Gleb Natapov
2013-04-17 10:42 ` Paolo Bonzini
2013-04-17 13:33 ` Gleb Natapov
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=20130410100845.GB17919@redhat.com \
--to=gleb@redhat.com \
--cc=andre@andrep.de \
--cc=bp@alien8.de \
--cc=hpa@zytor.com \
--cc=joro@8bytes.org \
--cc=kvm@vger-kernel.org \
--cc=kvm@vger.kernel.org \
--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