From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Vrabel Subject: Re: [PATCH 02/13] xen/events: remove unnecessary init_evtchn_cpu_bindings() Date: Tue, 24 Sep 2013 17:06:06 +0100 Message-ID: <5241B86E.8070602@cantab.net> References: <1379091601-30358-1-git-send-email-david.vrabel@citrix.com> <1379091601-30358-3-git-send-email-david.vrabel@citrix.com> <20130924144004.GC4712@phenom.dumpdata.com> Reply-To: David Vrabel Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20130924144004.GC4712@phenom.dumpdata.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Konrad Rzeszutek Wilk Cc: Boris Ostrovsky , David Vrabel , Jan Beulich , xen-devel@lists.xen.org List-Id: xen-devel@lists.xenproject.org On 24/09/2013 15:40, Konrad Rzeszutek Wilk wrote: > On Fri, Sep 13, 2013 at 05:59:50PM +0100, David Vrabel wrote: >> From: David Vrabel >> >> Event channels are always explicitly bound to a specific VCPU before >> they are first enabled. There is no need to initialize all possible >> events as bound to VCPU 0 at start of day or after a resume. > > How long has this presumption about explicit bounding been in the > hypervisor? This is about the Linux-side binding -- i.e., the adjustment of the per-cpu masks. There's always an explicit call to update this masks after an event channel is bound. David