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

Re: [Xen-devel] [PATCH, RFC] x86: make the GDT per-CPU


  • To: Jan Beulich <jbeulich@xxxxxxxxxx>
  • From: Keir Fraser <keir.fraser@xxxxxxxxxxxxx>
  • Date: Thu, 11 Sep 2008 14:15:51 +0100
  • Cc: xen-devel@xxxxxxxxxxxxxxxxxxx
  • Delivery-date: Thu, 11 Sep 2008 06:16:23 -0700
  • List-id: Xen developer discussion <xen-devel.lists.xensource.com>
  • Thread-index: AckUEIMzwciO1IADEd2NXQAX8io7RQ==
  • Thread-topic: [Xen-devel] [PATCH, RFC] x86: make the GDT per-CPU

On 11/9/08 13:42, "Jan Beulich" <jbeulich@xxxxxxxxxx> wrote:

>> No, this would break 32-bits at least: The GDT entry for the selector
>> loaded into TR must remain a valid, busy TSS descriptor for the whole
>> lifetime of the system. So it can't be shared with the LDT. But even for
>> 64-bits I would fear using the same GDT slot for both LDT and GDT
>> loading.
> 
> Actually, there's a second aspect here, too (again for 32-bits): As a
> follow-up patch I'm planning to make the double fault TSS per-CPU, too.
> This wasn't as simple with the global GDT as it would be with the per-CPU
> one.

Well, the extra LGDT looks like it will take about 130 cycles on Core-2
hardware. I suppose that is tolerable.

 -- 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®.