Messages in this thread | | | Date | Mon, 8 Nov 2010 11:52:48 -0800 | From | "Paul E. McKenney" <> | Subject | Re: [PATCH] a local-timer-free version of RCU |
| |
On Mon, Nov 08, 2010 at 04:15:38PM +0000, houston.jim@comcast.net wrote: > Hi Everyone, > > I'm sorry started this thread and have not been able to keep up > with the discussion. I agree that the problems described are real.
Not a problem -- your patch is helpful in any case.
> > > UAS> PEM> o CPU 1 continues in rcu_grace_period_complete(), > > > UAS> PEM> incorrectly ending the new grace period. > > > UAS> PEM> > > > UAS> PEM> Or am I missing something here? > > > UAS> > > > UAS> The scenario you describe seems possible. However, it should be easily > > > UAS> fixed by passing the perceived batch number as another parameter to > > > UAS> rcu_set_state() and making it part of the cmpxchg. So if the caller > > > UAS> tries to set state bits on a stale batch number (e.g., batch != > > > UAS> rcu_batch), it can be detected. > > My thought on how to fix this case is to only hand off the DO_RCU_COMPLETION > to a single cpu. The rcu_unlock which receives this hand off would clear its > own bit and then call rcu_poll_other_cpus to complete the process.
Or we could map to TREE_RCU's data structures, with one thread per leaf rcu_node structure.
> > What is scary with this is that it also changes rcu sched semantics, and users > > of call_rcu_sched() and synchronize_sched(), who rely on that to do more > > tricky things than just waiting for rcu_derefence_sched() pointer grace periods, > > like really wanting for preempt_disable and local_irq_save/disable, those > > users will be screwed... :-( ...unless we also add relevant rcu_read_lock_sched() > > for them... > > I need to stare at the code and get back up to speed. I expect that the synchronize_sched > path in my patch is just plain broken.
Again, not a problem -- we have a couple approaches that might work. That said, additional ideas are always welcome!
Thanx, Paul
| |