From: Keir Fraser <keir.xen@gmail.com>
To: Jan Beulich <JBeulich@suse.com>, Tim Deegan <tim@xen.org>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>,
Malcolm Crossley <malcolm.crossley@citrix.com>,
"xen-devel@lists.xen.org" <xen-devel@lists.xen.org>
Subject: Re: [PATCH V3] vmx/nmi: Do not use self_nmi() in VMEXIT handler
Date: Thu, 28 Feb 2013 19:02:04 +0000 [thread overview]
Message-ID: <CD555A2C.4CE31%keir.xen@gmail.com> (raw)
In-Reply-To: <512F913902000078000C222A@nat28.tlf.novell.com>
On 28/02/2013 16:17, "Jan Beulich" <JBeulich@suse.com> wrote:
>> Is this alternative that we might not process events for an unbounded time?
>> No, I guess not -- either we would interrupt the notifying IPI and we will
>> be IRETing into that IPI's handler, or the notifying IPI is delayed until
>> the NMI handler's IRET.
>>
>> What about if the NMI handler itself raises an event (eg softirq)? Perhaps
>> there are no very essential ones of those?
>
> We do raise PCI_SERR_SOFTIRQ, and the possibly injected NMI
> (to Dom0) might get slightly deferred too. The latter seems of
> little concern (Dom0 will get the event eventually). For the
> former, we might want to explicitly send a self-IPI with
> EVENT_CHECK_VECTOR following the raise_softirq()?
Or perhaps self-IPI on the NMI exit path if softirq_pending is non-zero?
Conservative but more generic.
-- Keir
next prev parent reply other threads:[~2013-02-28 19:02 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-11-22 15:00 [PATCH V3] vmx/nmi: Do not use self_nmi() in VMEXIT handler Andrew Cooper
2012-11-22 15:15 ` Jan Beulich
2012-11-22 15:16 ` Andrew Cooper
2012-11-22 15:21 ` Jan Beulich
2012-11-22 15:37 ` Andrew Cooper
2012-11-22 15:55 ` Jan Beulich
2012-11-22 16:05 ` Andrew Cooper
2012-11-22 16:12 ` Jan Beulich
2012-11-22 16:31 ` Andrew Cooper
2013-02-28 9:58 ` Jan Beulich
2013-02-28 12:32 ` Andrew Cooper
2013-02-28 13:00 ` Tim Deegan
2013-02-28 13:12 ` Andrew Cooper
2013-02-28 13:39 ` Jan Beulich
2013-02-28 14:25 ` Tim Deegan
2013-02-28 14:42 ` Jan Beulich
2013-02-28 14:45 ` Andrew Cooper
2013-02-28 14:49 ` Tim Deegan
2013-02-28 15:01 ` Jan Beulich
2013-02-28 15:41 ` Jan Beulich
2013-02-28 15:52 ` Andrew Cooper
2013-02-28 15:55 ` Tim Deegan
2013-02-28 16:12 ` Jan Beulich
2013-02-28 16:01 ` Keir Fraser
2013-02-28 16:17 ` Jan Beulich
2013-02-28 19:02 ` Keir Fraser [this message]
2013-03-01 10:49 ` [PATCH v2 0/2] x86: defer processing events on the NMI exit path Jan Beulich
2013-03-01 10:56 ` [PATCH v2 1/2] " Jan Beulich
2013-03-01 11:37 ` Andrew Cooper
2013-03-01 11:53 ` Jan Beulich
2013-03-01 15:56 ` Keir Fraser
2013-03-01 16:01 ` Andrew Cooper
2013-03-01 16:08 ` Jan Beulich
2013-03-01 10:57 ` [PATCH v2 2/2] x86: don't rely on __softirq_pending to be the first field in irq_cpustat_t Jan Beulich
2013-03-01 15:55 ` [PATCH v2 0/2] x86: defer processing events on the NMI exit path Keir Fraser
2013-02-28 13:42 ` [PATCH V3] vmx/nmi: Do not use self_nmi() in VMEXIT handler Jan Beulich
2013-02-28 14:04 ` Tim Deegan
2013-02-28 14:51 ` Konrad Rzeszutek Wilk
2012-11-22 15:22 ` Mats Petersson
2012-11-22 16:00 ` Jan Beulich
2012-11-22 17:34 ` Tim Deegan
2012-11-26 11:50 ` George Dunlap
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=CD555A2C.4CE31%keir.xen@gmail.com \
--to=keir.xen@gmail.com \
--cc=JBeulich@suse.com \
--cc=andrew.cooper3@citrix.com \
--cc=malcolm.crossley@citrix.com \
--cc=tim@xen.org \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).