Re: [Xen-devel] [PATCH] xen-evtchn: Bind dyn evtchn:qemu-dm interrupt to next online VCPU

From	Anoob Soman <anoob.soman@citrix.com>
Newsgroups	linux.kernel
Subject	Re: [Xen-devel] [PATCH] xen-evtchn: Bind dyn evtchn:qemu-dm interrupt to next online VCPU
Date	2017-06-05 18:20 +0200
Message-ID	<tP2Tw-59z-29@gated-at.bofh.it> (permalink)
References	(1 earlier) <tNXCy-3wP-11@gated-at.bofh.it> <tOXh7-1Ba-3@gated-at.bofh.it> <tP11o-3Xu-17@gated-at.bofh.it> <tP1uq-499-5@gated-at.bofh.it> <tP2gO-4G7-19@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On 05/06/17 16:32, Boris Ostrovsky wrote:
> I believe we do need to take affinity into consideration even if the
> chance that it is non-default is small.

Agreed.

> I am not opposed to having bind_last_selected_cpu percpu, I just wanted
> to understand the reason better. Additional locking would be a downside
> with a global so if you feel that percpu is worth it then I won't object.

If affinity == cpu_online_mask, then percpu will give a better spread. 
atomic set/get can be used, if we want to use a global variable, but I 
think it will be more random than percpu.

>
>> Yes, you are correct. .irq_set_affinity pretty much does the same thing.
>>
>> The code will now looks like this.
>> raw_spin_lock_irqsave(lock, flags);
>> percpu read
>> select_cpu
>> percpu write
>> xen_rebind_evtchn_to_cpu(evtchn, selected_cpu)
>> raw_spin_unlock_irqsave(lock, flags);
> (BTW, I just noticed --- you don't need to initialize desc)

Sorry, I didn't get it. Which desc doesn't need init ?

-Anoob

Thread

[PATCH] xen-evtchn: Bind dyn evtchn:qemu-dm interrupt to next online VCPU Anoob Soman <anoob.soman@citrix.com> - 2017-06-02 17:00 +0200
  Re: [PATCH] xen-evtchn: Bind dyn evtchn:qemu-dm interrupt to next  online VCPU Juergen Gross <jgross@suse.com> - 2017-06-02 17:20 +0200
    Re: [PATCH] xen-evtchn: Bind dyn evtchn:qemu-dm interrupt to next  online VCPU Anoob Soman <anoob.soman@citrix.com> - 2017-06-05 12:00 +0200
  Re: [PATCH] xen-evtchn: Bind dyn evtchn:qemu-dm interrupt to next  online VCPU Boris Ostrovsky <boris.ostrovsky@oracle.com> - 2017-06-02 18:30 +0200
    Re: [PATCH] xen-evtchn: Bind dyn evtchn:qemu-dm interrupt to next  online VCPU Anoob Soman <anoob.soman@citrix.com> - 2017-06-05 12:20 +0200
      Re: [PATCH] xen-evtchn: Bind dyn evtchn:qemu-dm interrupt to next  online VCPU Boris Ostrovsky <boris.ostrovsky@oracle.com> - 2017-06-05 16:20 +0200
        Re: [Xen-devel] [PATCH] xen-evtchn: Bind dyn evtchn:qemu-dm interrupt  to next online VCPU Anoob Soman <anoob.soman@citrix.com> - 2017-06-05 16:50 +0200
          Re: [Xen-devel] [PATCH] xen-evtchn: Bind dyn evtchn:qemu-dm interrupt  to next online VCPU Boris Ostrovsky <boris.ostrovsky@oracle.com> - 2017-06-05 17:40 +0200
            Re: [Xen-devel] [PATCH] xen-evtchn: Bind dyn evtchn:qemu-dm interrupt  to next online VCPU Anoob Soman <anoob.soman@citrix.com> - 2017-06-05 18:20 +0200
              Re: [Xen-devel] [PATCH] xen-evtchn: Bind dyn evtchn:qemu-dm interrupt  to next online VCPU Boris Ostrovsky <boris.ostrovsky@oracle.com> - 2017-06-05 18:50 +0200
                Re: [Xen-devel] [PATCH] xen-evtchn: Bind dyn evtchn:qemu-dm interrupt  to next online VCPU Anoob Soman <anoob.soman@citrix.com> - 2017-06-05 19:20 +0200

csiph-web