On 12/16/2014 04:31 AM, Jan Beulich wrote:
On 15.12.14 at 23:24, <boris.ostrov...@oracle.com> wrote:
We need to make sure that last_vcpu is not pointing to VCPU whose
VPMU is being destroyed. Otherwise we may try to dereference it in
the future, when VCPU is gone.
We have to do this via IPI since otherwise there is a (somewheat
theoretical) chance that between test and subsequent clearing
of last_vcpu the remote processor (i.e. vpmu->last_pcpu) might do
both load_vpmu() and then save_vpmu() for another VCPU. The former
will clear last_vcpu and the latter will set it to something else.
Apart from the question of using cmpxchg instead of the IPI (I can
see with the current model that using an IPI is the only clean way,
i.e. the alternative - if usable - would mean altering existing logic
too),
You mean something like
struct vcpu **last = &per_cpu(last_vcpu, vpmu->last_pcpu);
cmpxchg(last, v, NULL);
Yes, that could work.
-boris
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel
