Keir Fraser wrote:
> On 21/08/2009 13:03, "Stephen Smalley" <sds@xxxxxxxxxxxxx> wrote:
>
>> On Thu, 2009年08月20日 at 17:02 +0100, Keir Fraser wrote:
>>> Looks like a lock normally taken with irqs disabled may be being
>>> taken with irqs enabled. Which wouldn't be allowed but could be
>>> easy to fix. 
>> 
>> This appears to have been introduced by CS 20073, x86: Implement
>> per-cpu vector for xen hypervisor. It introduces mixed usage of
>> spin_lock() and spin_lock_irqsave() on the vector_lock, whereas
>> previously it was always spin_lock_irqsave().
>
> Xiantao, Can you make a patch for this? Any acquisition of the lock
> where irqs may not already be disabled must do spin_lock_irq or
> spin_lock_irqsave. 
Yes, I will work out a fix for that. :)
Xiantao
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel