Okay, seems a cleanup patch for that is needed, otherwise the related logic 
maybe misleading... 
Xiantao
Keir Fraser wrote:
> At some point we will introduce hotplug notifiers and have per-cpu
> areas set up only for present CPUs. The possible_map is basically
> deprecated/obsolete. 
>
> -- keir
>
> On 14/01/2010 12:19, "Zhang, Xiantao" <xiantao.zhang@xxxxxxxxx> wrote:
>
>> I am curious that all bits of cpu_possible_map are all set to 1, so
>> the related checks in percpu_free_unused_areas are unnecessary ?
>> Xiantao
>> 
>> 
>> Keir Fraser wrote:
>>> On 14/01/2010 11:21, "Jan Beulich" <JBeulich@xxxxxxxxxx> wrote:
>>> 
>>>>>> However, in iommu_set_dom0_mapping(), xen_in_range() is still
>>>>>> True for the freed pages above, so devices in Dom0 can meet with
>>>>>> DMA fault.
>>>>> 
>>>>> Should be fixed by c/s 20803.
>>>> 
>>>> Do you really think so? Masking "start" with PERCPU_SIZE-1 doesn't
>>>> make sense, as it may be arbitrarily before __percpu_start and
>>>> not aligned. Below my take on it.
>>> 
>>> How about c/s 20806?
>>> 
>>> 
>>> _______________________________________________
>>> Xen-devel mailing list
>>> Xen-devel@xxxxxxxxxxxxxxxxxxx
>>> http://lists.xensource.com/xen-devel 
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel