On Wed, Jan 15, 2020 at 09:24:28AM -0400, Jason Gunthorpe wrote: > > Your requirement seems a little different, and in fact in many ways > > similar to the percpu_ref primitive. > > I was interested because you are talking about allowing the read/write side > of a rw sem to be held across a return to user space/etc, which is the > same basic problem. > > precpu refcount looks more like a typical refcount with a release that > is called by whatever context does the final put. The point above is > to basically move the release of a refcount into a synchrnous path by > introducing some barrier to wait for the refcount to go to zero. In > the above the barrier is the down_write() as it is really closer to a > rwsem than a refcount.
No, percpu_ref is a little different than the name suggests, as it has a magic initial reference, and then the other short term reference. To actually tear it down now just a normal put of the reference is needed, but an explicit percpu_ref_kill or percpu_ref_kill_and_confirm. Various callers (including all I added) would like that operation to be synchronous and currently hack that up, so a version of the percpu_ref that actually waits for the other references to away like we hacked up various places seems to exactly suit your requirements.