From: "Wu, Feng" <feng.wu@intel.com>
To: Dario Faggioli <dario.faggioli@citrix.com>,
"xen-devel@lists.xen.org" <xen-devel@lists.xen.org>
Cc: "george.dunlap@eu.citrix.com" <george.dunlap@eu.citrix.com>,
"andrew.cooper3@citrix.com" <andrew.cooper3@citrix.com>,
"Tian, Kevin" <kevin.tian@intel.com>,
"Wu, Feng" <feng.wu@intel.com>,
"jbeulich@suse.com" <jbeulich@suse.com>
Subject: Re: [PATCH v3 1/6] VMX: Statically assign two PI hooks
Date: Tue, 6 Sep 2016 09:53:30 +0000 [thread overview]
Message-ID: <E959C4978C3B6342920538CF579893F0197C65D9@SHSMSX103.ccr.corp.intel.com> (raw)
In-Reply-To: <1473151351.19612.84.camel@citrix.com>
> -----Original Message-----
> From: Dario Faggioli [mailto:dario.faggioli@citrix.com]
> Sent: Tuesday, September 6, 2016 4:43 PM
> To: Wu, Feng <feng.wu@intel.com>; xen-devel@lists.xen.org
> Cc: Tian, Kevin <kevin.tian@intel.com>; george.dunlap@eu.citrix.com;
> andrew.cooper3@citrix.com; jbeulich@suse.com
> Subject: Re: [Xen-devel] [PATCH v3 1/6] VMX: Statically assign two PI hooks
>
> On Wed, 2016-08-31 at 11:56 +0800, Feng Wu wrote:
> > PI hooks: vmx_pi_switch_from() and vmx_pi_switch_to() are
> > needed even all the assigned devices were dettached from
> > the domain.
> >
> maybe "are needed even when any previously passed through device is
> detached from the domain" (or something like that)?
Looks good, thanks for improve the wording.
>
> > We change the state of SN bit in these two
> > functions, and evaluate this bit in vmx_deliver_posted_intr()
> > when trying to deliver the interrupt in posted way via software.
> > The problem is if we deassign the hooks while the vCPU is runnable
> > in the runqueue with 'SN' set, all the furture notificaton event
> > will be suppressed. This patch makes these two hooks statically
> > assigned.
> >
> Which, if SN is used only for controlling VT-d PI from passed thru
> devices does not sound like an issue to me.
>
> What I sort of get from the discussion you had with Jan, however, is
> that this is an issue, because SN is also used for other things, i.e.,
> it is indeed useful even when there are no passed thru device, is that
> the case?
>
> If yes, I think this deserves at least a quick mention in the sentence
> above.
Yes, SN controls all the PI including CPU side PI activity, sure, I will
explicitly add those information.
Thanks,
Feng
>
> Regards,
> Dario
> --
> <<This happens because I choose it to happen!>> (Raistlin Majere)
> -----------------------------------------------------------------
> Dario Faggioli, Ph.D, http://about.me/dario.faggioli
> Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK)
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
next prev parent reply other threads:[~2016-09-06 9:53 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-08-31 3:56 [PATCH v3 0/6] VMX: Properly handle pi descriptor and per-cpu blocking list Feng Wu
2016-08-31 3:56 ` [PATCH v3 1/6] VMX: Statically assign two PI hooks Feng Wu
2016-09-01 8:16 ` Jan Beulich
2016-09-01 9:13 ` Wu, Feng
2016-09-01 9:23 ` Jan Beulich
2016-09-01 9:38 ` Wu, Feng
2016-09-06 8:42 ` Dario Faggioli
2016-09-06 9:53 ` Wu, Feng [this message]
2016-08-31 3:56 ` [PATCH v3 2/6] VMX: Properly handle pi when all the assigned devices are removed Feng Wu
2016-09-01 8:21 ` Jan Beulich
2016-09-01 9:22 ` Wu, Feng
2016-09-01 10:23 ` Jan Beulich
2016-09-01 13:12 ` Wu, Feng
2016-09-06 8:58 ` Dario Faggioli
2016-08-31 3:56 ` [PATCH v3 3/6] VMX: Cleanup PI per-cpu blocking list when vcpu is destroyed Feng Wu
2016-09-06 9:21 ` Dario Faggioli
2016-09-06 23:27 ` Wu, Feng
2016-08-31 3:56 ` [PATCH v3 4/6] Pause/Unpause the domain before/after assigning PI hooks Feng Wu
2016-09-01 8:29 ` Jan Beulich
2016-09-02 1:46 ` Wu, Feng
2016-09-02 7:04 ` Jan Beulich
2016-09-02 7:31 ` Wu, Feng
2016-09-02 8:16 ` Jan Beulich
2016-09-02 8:40 ` Wu, Feng
2016-09-02 9:25 ` Jan Beulich
2016-09-02 10:30 ` Wu, Feng
2016-09-02 10:45 ` Jan Beulich
2016-09-02 13:15 ` Wu, Feng
2016-09-02 13:54 ` Jan Beulich
2016-09-05 3:11 ` Wu, Feng
2016-09-05 9:27 ` Jan Beulich
2016-09-14 2:23 ` Wu, Feng
2016-09-14 8:46 ` Jan Beulich
2016-09-14 14:51 ` Dario Faggioli
2016-09-18 8:37 ` Wu, Feng
2016-09-19 23:12 ` Dario Faggioli
2016-09-20 0:48 ` Wu, Feng
2016-09-20 7:31 ` Jan Beulich
2016-09-20 7:53 ` Wu, Feng
2016-09-20 8:13 ` Dario Faggioli
2016-09-20 8:18 ` Wu, Feng
2016-09-23 14:19 ` Jan Beulich
2016-09-26 2:53 ` Wu, Feng
2016-08-31 3:56 ` [PATCH v3 5/6] VT-d: No need to set irq affinity for posted format IRTE Feng Wu
2016-09-01 8:38 ` Jan Beulich
2016-09-02 1:58 ` Wu, Feng
2016-08-31 3:56 ` [PATCH v3 6/6] VMX: Fixup PI descritpor when cpu is offline Feng Wu
2016-09-01 8:48 ` Jan Beulich
2016-09-02 3:25 ` Wu, Feng
2016-09-02 7:08 ` Jan Beulich
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=E959C4978C3B6342920538CF579893F0197C65D9@SHSMSX103.ccr.corp.intel.com \
--to=feng.wu@intel.com \
--cc=andrew.cooper3@citrix.com \
--cc=dario.faggioli@citrix.com \
--cc=george.dunlap@eu.citrix.com \
--cc=jbeulich@suse.com \
--cc=kevin.tian@intel.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.