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

Re: [Xen-devel] Strange PVM spinlock case revisited (nailed down)



>>> On 14.02.13 at 15:21, Stefan Bader <stefan.bader@xxxxxxxxxxxxx> wrote:
> Having more understanding now, I had a different idea. Not sure this is
> foolproof and surely is causing some more active spinning. But it looks like I
> also can keep the system from locking up (v3.2 kernel and the testcase) if I
> change xen_spin_unlock_slow to send the wakeup IPI to _all_ spinners instead 
> of only the first one found.

That, afaict, is an absolute requirement with the open coded
lock that you pointed at, as otherwise the code makes a
pseudo ticket assumption in believing to know who's going to
be the next owner of the lock.

Jan


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel


 


Rackspace

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