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

RE: [Xen-devel] [patch] make hypercall_preempt_check() a little moresensitive

>From: Jimi Xenidis [mailto:jimix@xxxxxxxxxxxxxx]
>Sent: 2006年3月31日 10:20
>Yes, some bits can be controlled by xenlinux

OK, it's always good thing to learn a different model.

>> to
>> disable real external interrupts on that physical processor,
>Yes, even this bit, tho' it this is on the 970 class of processor,
>newer processors can be configured to not disable externals, but they
>can still set the bit.

So, is there any brief info about the model that ppc is currently using, like 
whether dom0/domU is para-virtualized or unmodifield, if para-virtualized, 
to which extent? Maybe I asked too many questions in one mail, but such 
info may help other people to understand your specific requirement more 
easily. I think I'm still lacking of a whole picture about current xen/ppc 
model. :-)

>This is an interesting example,  but why deliver an upcall thru the
>HV in the first place, why not just call the evtchn handler directly?

Then you may fall into dead loop, since evtchn_device_upcall tries to get 
spinlock while unmask_evtchn path may already holds the lock.


Xen-devel mailing list



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