From: Avi Kivity <avi@redhat.com>
To: Alexander Graf <agraf@suse.de>
Cc: kvm@vger.kernel.org, joro@8bytes.org, anthony@codemonkey.ws
Subject: Re: [PATCH 12/12] Accelerate nested SVM by emulating parts of GIF=0 v6
Date: Fri, 21 Nov 2008 19:18:46 +0200 [thread overview]
Message-ID: <4926ED76.9060606@redhat.com> (raw)
In-Reply-To: <8E9A93AB-6EEF-4582-A23A-BCB491A9307A@suse.de>
Alexander Graf wrote:
>>
>> Yeah. We could move some of these out, and emulate the rest (ltr I
>> think is needed).
>
> Then older versions of kvm would still break
If emulation fails, go back to virtualization. Or am I missing something?
>>
>> That's what kvm_x86_ops is for. We already emulate vendor specific
>> instructions (vmcall and vmmcall).
>
> From what I can tell kvm_x86_ops tries to multiplex calls that happen
> to be different on svm/vmx, but existent on both. SVM instructions
> usually don't appear on VMX ;-).
Right. But so what? I don't want to lose any future improvements the
emulator may have (like traps on debug register, etc).
--
I have a truly marvellous patch that fixes the bug which this
signature is too narrow to contain.
next prev parent reply other threads:[~2008-11-21 17:18 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-11-21 15:14 [PATCH 00/12] Add support for nested SVM (kernel) v6 Alexander Graf
2008-11-21 15:14 ` [PATCH 01/12] Clean up VINTR setting v6 Alexander Graf
2008-11-21 15:14 ` [PATCH 02/12] Move EFER and MSR constants to generic x86 code v6 Alexander Graf
2008-11-21 15:14 ` [PATCH 03/12] Add helper functions for nested SVM v6 Alexander Graf
2008-11-21 15:14 ` [PATCH 04/12] Implement GIF, clgi and stgi v6 Alexander Graf
2008-11-21 15:14 ` [PATCH 05/12] Implement hsave v6 Alexander Graf
2008-11-21 15:14 ` [PATCH 06/12] Add VMLOAD and VMSAVE handlers v6 Alexander Graf
2008-11-21 15:14 ` [PATCH 07/12] Add VMRUN handler v6 Alexander Graf
2008-11-21 15:14 ` [PATCH 08/12] Add VMEXIT handler and intercepts v6 Alexander Graf
2008-11-21 15:14 ` [PATCH 09/12] Allow read access to MSR_VM_VR v6 Alexander Graf
2008-11-21 15:14 ` [PATCH 10/12] Allow setting the SVME bit v6 Alexander Graf
2008-11-21 15:14 ` [PATCH 11/12] Only allow setting of EFER_SVME when CPUID SVM is set v6 Alexander Graf
2008-11-21 15:14 ` [PATCH 12/12] Accelerate nested SVM by emulating parts of GIF=0 v6 Alexander Graf
2008-11-21 16:53 ` Avi Kivity
2008-11-21 16:58 ` Alexander Graf
2008-11-21 17:07 ` Avi Kivity
2008-11-21 17:14 ` Alexander Graf
2008-11-21 17:18 ` Avi Kivity [this message]
2008-11-21 17:35 ` Alexander Graf
2008-11-21 15:23 ` [PATCH 07/12] Add VMRUN handler v6 Muli Ben-Yehuda
2008-11-21 15:26 ` Alexander Graf
2008-11-21 15:35 ` Alexander Graf
2008-11-23 8:06 ` Muli Ben-Yehuda
2008-11-23 13:48 ` Alexander Graf
2008-11-23 15:09 ` Muli Ben-Yehuda
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=4926ED76.9060606@redhat.com \
--to=avi@redhat.com \
--cc=agraf@suse.de \
--cc=anthony@codemonkey.ws \
--cc=joro@8bytes.org \
--cc=kvm@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