From: Keir Fraser <keir.xen@gmail.com>
To: Jan Beulich <JBeulich@suse.com>, Yang Z Zhang <yang.z.zhang@intel.com>
Cc: Xiantao Zhang <xiantao.zhang@intel.com>,
"xen-devel@lists.xen.org" <xen-devel@lists.xen.org>
Subject: Re: [PATCH 3/4] VMX: Add posted interrupt supporting
Date: Tue, 09 Apr 2013 10:18:55 +0100 [thread overview]
Message-ID: <CD899B8F.205A4%keir.xen@gmail.com> (raw)
In-Reply-To: <5163F4C502000078000CBA9D@nat28.tlf.novell.com>
On 09/04/2013 10:00, "Jan Beulich" <JBeulich@suse.com> wrote:
>>>> Can't you use vlapic_set_vector() here (even if that means
>>>> looping over vectors individually rather than groups), to add the
>>>> necessary atomicity (I don't see how you avoid races with other
>>>> updates) and to avoid the ugly cast?
>> Which races?
>
> vlapic.c also updates the APIC_IRR bit array, and hence (unless
> you can guarantee that now and forever such updates only
> happen when the subject vCPU is current, which I don't think is
> the case)
It's not the case. Which is one reason the IRR updates (and I think all
bitmap updates) in vlapic.c are atomic.
-- Keir
> your non-atomic read-modify-write operation here can
> discard an update done in vlapic.c. And am I wrong in recalling
> that the CPU may actually also on its own update that bit array?
next prev parent reply other threads:[~2013-04-09 9:18 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-04-09 6:01 [PATCH 0/4] Add posted interrupt supporting Yang Zhang
2013-04-09 6:01 ` [PATCH 1/4] VMX: Detect posted interrupt capability Yang Zhang
2013-04-09 6:01 ` [PATCH 2/4] VMX: Turn on posted interrupt bit in vmcs Yang Zhang
2013-04-09 8:04 ` Jan Beulich
2013-04-09 8:30 ` Zhang, Yang Z
2013-04-09 8:55 ` Jan Beulich
2013-04-09 9:53 ` Zhang, Yang Z
2013-04-09 8:23 ` Jan Beulich
2013-04-09 8:38 ` Keir Fraser
2013-04-09 8:48 ` Zhang, Yang Z
2013-04-09 6:01 ` [PATCH 3/4] VMX: Add posted interrupt supporting Yang Zhang
2013-04-09 7:39 ` Keir Fraser
2013-04-09 7:58 ` Zhang, Yang Z
2013-04-09 8:14 ` Keir Fraser
2013-04-09 8:23 ` Zhang, Yang Z
2013-04-09 8:40 ` Keir Fraser
2013-04-09 8:17 ` Jan Beulich
2013-04-09 8:40 ` Zhang, Yang Z
2013-04-09 8:59 ` Keir Fraser
2013-04-09 8:53 ` Zhang, Yang Z
2013-04-09 9:00 ` Jan Beulich
2013-04-09 9:18 ` Keir Fraser [this message]
2013-04-09 6:01 ` [PATCH 4/4] VMX: Use posted interrupt to deliver virutal interrupt Yang Zhang
2013-04-09 7:40 ` Keir Fraser
2013-04-09 8:25 ` Zhang, Yang Z
2013-04-09 20:26 ` [PATCH 0/4] Add posted interrupt supporting Konrad Rzeszutek Wilk
2013-04-10 2:51 ` Zhang, Yang Z
2013-04-10 13:22 ` Konrad Rzeszutek Wilk
2013-04-10 13:32 ` Zhang, Yang Z
2013-04-10 13:42 ` Konrad Rzeszutek Wilk
2013-04-19 11:49 ` Stefano Stabellini
2013-04-19 13:10 ` Jan Beulich
2013-04-19 14:16 ` Stefano Stabellini
2013-04-19 14:23 ` Jan Beulich
2013-04-20 7:26 ` Zhang, Yang Z
2013-04-20 13:33 ` Stefano Stabellini
2013-04-10 13:58 ` Zhang, Yang Z
2013-04-10 14:34 ` Jan Beulich
2013-04-10 16:18 ` Keir Fraser
2013-04-11 1:04 ` Zhang, Yang Z
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=CD899B8F.205A4%keir.xen@gmail.com \
--to=keir.xen@gmail.com \
--cc=JBeulich@suse.com \
--cc=xen-devel@lists.xen.org \
--cc=xiantao.zhang@intel.com \
--cc=yang.z.zhang@intel.com \
/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.