[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] irq_guest_eoi_timer interaction with MSI


  • To: Jan Beulich <jbeulich@xxxxxxxxxx>
  • From: Keir Fraser <keir.fraser@xxxxxxxxxxxxx>
  • Date: Thu, 13 Nov 2008 16:21:30 +0000
  • Cc: xen-devel@xxxxxxxxxxxxxxxxxxx
  • Delivery-date: Thu, 13 Nov 2008 08:21:55 -0800
  • List-id: Xen developer discussion <xen-devel.lists.xensource.com>
  • Thread-index: AclFq+KWINmAHrGfEd2N7wAX8io7RQ==
  • Thread-topic: [Xen-devel] irq_guest_eoi_timer interaction with MSI

On 13/11/08 15:28, "Jan Beulich" <jbeulich@xxxxxxxxxx> wrote:

>> PHYSDEVOP_eoi and unmask happen at the same time for pirqs. The fact that we
>> only need this new mechanism for pirqs, and that we already have a gated
>> hypercall for pirq eoi (and can gate it further if need be) is an argument
>> for hanging this off PHYSDEVOP_eoi imo.
> 
> But then there'd be a hypercall for each MSI instance, most of the time
> without any real need. With a high interrupt rate I'm afraid this does
> matter.

I don't understand what you mean. There is a one-to-one-one relationship
between MSIs, PIRQs, and event channels.

 -- Keir



_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.