From: Haozhong Zhang <haozhong.zhang@intel.com>
To: "Tian, Kevin" <kevin.tian@intel.com>
Cc: Keir Fraser <keir@xen.org>,
Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>,
"Nakajima, Jun" <jun.nakajima@intel.com>,
Andrew Cooper <andrew.cooper3@citrix.com>,
"Egger, Christoph" <chegger@amazon.de>,
"xen-devel@lists.xen.org" <xen-devel@lists.xen.org>,
Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>,
Jan Beulich <jbeulich@suse.com>,
Boris Ostrovsky <boris.ostrovsky@oracle.com>
Subject: Re: [PATCH v2 00/14] Add VMX TSC scaling support
Date: Thu, 10 Dec 2015 19:13:24 +0800 [thread overview]
Message-ID: <20151210111324.GP3547@hz-desktop.sh.intel.com> (raw)
In-Reply-To: <AADFC41AFE54684AB9EE6CBC0274A5D15F7405E9@SHSMSX101.ccr.corp.intel.com>
On 12/10/15 10:43, Tian, Kevin wrote:
> > From: Andrew Cooper [mailto:andrew.cooper3@citrix.com]
> > Sent: Tuesday, December 08, 2015 1:04 AM
> >
> > On 07/12/15 10:16, Haozhong Zhang wrote:
> > > On 12/07/15 10:03, Egger, Christoph wrote:
> > >> Did you consider nested virtualization?
> > >> L1 hypervisor may have a different tsc scaling
> > >> and L2 guest again may have a different tsc scale ratio.
> > >>
> > > Oh, I forgot this. I'll check the nested TSC scaling code (mostly
> > > about nested SVM TSC ratio, because this patch series does not expose
> > > VMX TSC scaling to L1 guest).
> > >
> > > BTW, are there any practical usage scenarios of nested TSC scaling? If
> > > any, I may also need to consider adding nested virtualization support
> > > to VMX TSC scaling.
> >
> > I would say that there are genuine uses for nested TSC scaling. An L1
> > hypervisor is going to want to scale for the same reasons as the L0
> > hypervisor.
> >
> > Having said that, if TSC scaling is correctly hidden from the L1 guests,
> > I would advise against conflating the two issues together. i.e. getting
> > nested TSC scaling working is not a prerequisite for accepting this series.
> >
>
> Why is nested TSC scaling even an issue? If L0 hypervisors cross hosts
> can always guarantee constant TSC frequency through TSC scaling, L1
> hypervisor will never see inconstant TSC frequency so why bother to
> expose TSC scaling at all?
>
If exposing TSC scaling to L1, then L0 hypervisor will need to adapt
the TSC scaling ratio set by L1 hypervisor, which has not been done by
this patch series.
Consider an example that the host TSC frequency is freq_0 and
1. L0 Xen sets TSC scaling ratio to a non-identical one ratio_0.
2. Then L1 hypervisor will observe a "host" TSC frequency (freq_0 * ratio_0).
3. If L1 hypervisor sets a TSC scaling ratio ratio_1, it intends to
provide a guest TSC frequency (freq_0 * ratio_0 * ratio_1).
However, if ratio_1 is directly written into nested VMCS that is
later applied to the host CPU, then the L2 guest will get an
incorrect guest TSC frequency (freq_0 * ratio_1).
Haozhong
next prev parent reply other threads:[~2015-12-10 11:13 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-12-06 20:58 [PATCH v2 00/14] Add VMX TSC scaling support Haozhong Zhang
2015-12-06 20:58 ` [PATCH v2 01/14] svm: Fix incorrect TSC scaling Haozhong Zhang
2015-12-07 16:49 ` Boris Ostrovsky
2015-12-06 20:58 ` [PATCH v2 02/14] x86/time.c: Fix domain type check in tsc_set_info() Haozhong Zhang
2015-12-07 16:49 ` Boris Ostrovsky
2015-12-06 20:58 ` [PATCH v2 03/14] x86/time.c: Use correct guest TSC frequency " Haozhong Zhang
2015-12-07 16:57 ` Boris Ostrovsky
2015-12-08 0:30 ` Haozhong Zhang
2015-12-06 20:58 ` [PATCH v2 04/14] x86/time.c: Use correct guest TSC frequency in tsc_get_info() Haozhong Zhang
2015-12-07 17:53 ` Boris Ostrovsky
2015-12-08 1:08 ` Haozhong Zhang
2015-12-08 18:26 ` Boris Ostrovsky
2015-12-10 0:14 ` Haozhong Zhang
2015-12-06 20:58 ` [PATCH v2 05/14] x86/hvm: Scale host TSC when setting/getting guest TSC Haozhong Zhang
2015-12-07 17:54 ` Boris Ostrovsky
2015-12-06 20:58 ` [PATCH v2 06/14] x86/time.c: Scale host TSC in pvclock properly Haozhong Zhang
2015-12-07 18:14 ` Boris Ostrovsky
2015-12-08 1:52 ` Haozhong Zhang
2015-12-08 19:21 ` Boris Ostrovsky
2015-12-10 0:23 ` Haozhong Zhang
2015-12-10 11:56 ` Joao Martins
2015-12-29 18:22 ` Joao Martins
2015-12-30 1:07 ` Haozhong Zhang
2015-12-06 20:58 ` [PATCH v2 07/14] svm: Remove redundant TSC scaling in svm_set_tsc_offset() Haozhong Zhang
2015-12-07 18:25 ` Boris Ostrovsky
2015-12-08 1:54 ` Haozhong Zhang
2015-12-06 20:58 ` [PATCH v2 08/14] x86/hvm: Collect information of TSC scaling ratio Haozhong Zhang
2015-12-07 18:31 ` Boris Ostrovsky
2015-12-10 10:19 ` Tian, Kevin
2015-12-10 10:27 ` Zhang, Haozhong
2015-12-06 20:58 ` [PATCH v2 09/14] x86/hvm: Setup " Haozhong Zhang
2015-12-07 18:42 ` Boris Ostrovsky
2015-12-08 1:58 ` Haozhong Zhang
2015-12-10 10:27 ` Tian, Kevin
2015-12-10 10:37 ` Zhang, Haozhong
2015-12-06 20:58 ` [PATCH v2 10/14] x86/hvm: Replace architecture TSC scaling by a common function Haozhong Zhang
2015-12-07 18:55 ` Boris Ostrovsky
2015-12-08 2:06 ` Haozhong Zhang
2015-12-10 10:29 ` Tian, Kevin
2015-12-06 20:58 ` [PATCH v2 11/14] x86/hvm: Move saving/loading vcpu's TSC to common code Haozhong Zhang
2015-12-07 18:56 ` Boris Ostrovsky
2015-12-10 10:30 ` Tian, Kevin
2015-12-06 20:58 ` [PATCH v2 12/14] x86/hvm: Detect TSC scaling through hvm_funcs Haozhong Zhang
2015-12-07 18:58 ` Boris Ostrovsky
2015-12-10 10:31 ` Tian, Kevin
2015-12-06 20:58 ` [PATCH v2 13/14] vmx: Add VMX RDTSC(P) scaling support Haozhong Zhang
2015-12-10 10:33 ` Tian, Kevin
2015-12-06 20:58 ` [PATCH v2 14/14] docs: Add descriptions of TSC scaling in xl.cfg and tscmode.txt Haozhong Zhang
2015-12-10 10:40 ` Tian, Kevin
2015-12-10 10:56 ` Zhang, Haozhong
2015-12-06 21:14 ` [PATCH v2 00/14] Add VMX TSC scaling support Haozhong Zhang
2015-12-07 9:03 ` Egger, Christoph
2015-12-07 10:16 ` Haozhong Zhang
2015-12-07 17:04 ` Andrew Cooper
2015-12-08 2:13 ` Haozhong Zhang
2015-12-10 10:43 ` Tian, Kevin
2015-12-10 11:13 ` Haozhong Zhang [this message]
2015-12-11 7:35 ` Tian, Kevin
2015-12-11 10:09 ` Andrew Cooper
2015-12-07 10:37 ` Jan Beulich
2015-12-07 10:56 ` Haozhong Zhang
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=20151210111324.GP3547@hz-desktop.sh.intel.com \
--to=haozhong.zhang@intel.com \
--cc=Aravind.Gopalakrishnan@amd.com \
--cc=andrew.cooper3@citrix.com \
--cc=boris.ostrovsky@oracle.com \
--cc=chegger@amazon.de \
--cc=jbeulich@suse.com \
--cc=jun.nakajima@intel.com \
--cc=keir@xen.org \
--cc=kevin.tian@intel.com \
--cc=suravee.suthikulpanit@amd.com \
--cc=xen-devel@lists.xen.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.