Messages in this thread | | | Date | Mon, 28 Jan 2013 12:27:45 -0800 | Subject | Re: [PATCH] generic dynamic per cpu refcounting | From | Tejun Heo <> |
| |
Hey, Kent.
On Mon, Jan 28, 2013 at 12:22 PM, Kent Overstreet <koverstreet@google.com> wrote: > Could do that too, but then teardown gets really messy for the user - we > need two synchronize_rcu()s: > > state := dying > > synchronize_rcu() > > /* Now nothing's changing the per cpu counters */ > > Add per cpu counters to atomic counter counter > > /* Atomic counter is now consistent */ > > state := dead > > synchronize_rcu()
I don't understand why we need two stages. What prevents the killing thread from fetching percpu counters after dying passes one synchronize_sched()?
> /* Now percpu_ref_put will check for ref == 0 */ > > /* Drop initial ref */ > > percpu_ref_put() > > And note that the first synchronize_rcu() is only needed when we had > allocated per cpu counters, my current code skips it otherwise.
And regardless, at the interface level, can't it just provide percpu_ref_put_base_ref(release_fn)?
Thanks.
-- tejun
| |