> -----Original Message----- > From: Dario Faggioli [mailto:dario.faggi...@citrix.com] > Sent: Thursday, October 29, 2015 12:37 AM > To: Jan Beulich <jbeul...@suse.com>; Wu, Feng <feng...@intel.com> > Cc: Tian, Kevin <kevin.t...@intel.com>; Keir Fraser <k...@xen.org>; > GeorgeDunlap <george.dun...@eu.citrix.com>; Andrew Cooper > <andrew.coop...@citrix.com>; xen-devel@lists.xen.org > Subject: Re: [Xen-devel] [PATCH v8 15/17] vmx: VT-d posted-interrupt core > logic > handling > > On Wed, 2015-10-28 at 03:03 -0600, Jan Beulich wrote: > > > > > On 28.10.15 at 03:58, <feng...@intel.com> wrote: > > > > We still call arch_vcpu_block() in vcpu_block(), but we don't need > > > to > > > call arch_vcpu_block_cancel(v) when local_events_need_delivery() > > > returns true. Then before VM-Entry, we can check if 'NV' field is > > > ' pi_wakeup_vector', if it is, we change the PI status and remove > > > it from the blocking list. > > > > > > Jan, if #2 is what you mean, I think it worth a try. If I don't > > > understand > > > your comments correctly, could you please elaborate it more? Thanks > > > a lot! > > > > Ideally we'd avoid both arch_vcpu_*() calls by doing what is needed > > in arch code (e.g. the VM entry path). > > > +1 > > > If only avoiding the cancel > > hook is reasonably possible this way, then so be it - still better to > > have just one hook here than having two. > > > +1 again > > As an aside, I've spoked with some ARM people, the context being that > they will get to implement a similar feature in the nearish future. > > They said that, although they can't be sure, they don't think they'll > be interested in arch hooks in the scheduling code and that, actually, > having them risk being more harmful than helpful. > > Of course, that does not mean that we shouldn't add them for the sake > of this patch, if we can't avoid doing that. But if we can avoid them, > that is perhaps one more reason for doing things that way.
Jan & Dario, thanks a lot for you guys' input. If you agree, I will remove the arch_vcpu_block_cancel() and maybe arch_vcpu_wake_prepare() as well, and implement the logic before VM-entry in V9, the patch will be coming soon. Thanks again! 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 http://lists.xen.org/xen-devel
