| |
|
 |
|
 |
|
|
|
| |
|
|
xen-devel
Re: [Xen-devel] Re: [PATCH] EPT: Flush running cpus, add mask to flush
|
To: |
Jan Beulich <JBeulich@xxxxxxxxxx> |
|
Subject: |
Re: [Xen-devel] Re: [PATCH] EPT: Flush running cpus, add mask to flush when scheduled in |
|
From: |
Keir Fraser <keir.fraser@xxxxxxxxxxxxx> |
|
Date: |
Tue, 22 Sep 2009 10:17:43 +0100 |
|
Cc: |
Xiaohui Xin <Xiaohui.xin@xxxxxxxxx>, Xin Li <xin.b.li@xxxxxxxxx>, George Dunlap <George.Dunlap@xxxxxxxxxxxxx>, Tim Deegan <Tim.Deegan@xxxxxxxxxxxxx>, Paul Durrant <Paul.Durrant@xxxxxxxxxx>, Jun Nakajima <jun.nakajima@xxxxxxxxx>, "xen-devel@xxxxxxxxxxxxxxxxxxx" <xen-devel@xxxxxxxxxxxxxxxxxxx> |
|
Delivery-date: |
Tue, 22 Sep 2009 02:18:07 -0700 |
|
Envelope-to: |
www-data@xxxxxxxxxxxxxxxxxxx |
|
In-reply-to: |
<4AB8AEA90200007800016325@xxxxxxxxxxxxxxxxxx> |
|
List-help: |
<mailto:xen-devel-request@lists.xensource.com?subject=help> |
|
List-id: |
Xen developer discussion <xen-devel.lists.xensource.com> |
|
List-post: |
<mailto:xen-devel@lists.xensource.com> |
|
List-subscribe: |
<http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=subscribe> |
|
List-unsubscribe: |
<http://lists.xensource.com/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe> |
|
Sender: |
xen-devel-bounces@xxxxxxxxxxxxxxxxxxx |
|
Thread-index: |
Aco7Y1s//VSe5PVWSTOzeyhLILHeegAAi72H |
|
Thread-topic: |
[Xen-devel] Re: [PATCH] EPT: Flush running cpus, add mask to flush when scheduled in |
|
User-agent: |
Microsoft-Entourage/12.20.0.090605 |
On 22/09/2009 10:02, "Jan Beulich" <JBeulich@xxxxxxxxxx> wrote:
>> Please see what you think of xen-unstable:20244.
>
> With no assertion in ept_sync_domain() on any locks held, is it guaranteed
> that the function cannot be entered twice at the same time for a given
> guest? If not, passing a pointer to the new ept_synced member isn't any
> better than passing the one to domain_dirty_cpumask.
I assume George is knowledgeable on that area. If calls to ept_sync_domain()
are not serialised then I think synchronisation around the
ept_needs_flush/ept_synced cpumask is indeed pretty suspect. If there isn't
such a serialising lock, we could add one to ept_sync_domain() quite safely.
-- Keir
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel
|
|
|
| |
|
Home