Re: rcu-bh design

[Steven Rostedt]

On Fri, 4 May 2018 10:32:06 -0700
"Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx> wrote:

> > > But preemptible RCU *does not* use context-switch as a quiescent state.  
> > 
> > It doesn't?  
> 
> It does, but only sort of.

Ah, my confusion. I was thinking of rcu_read_lock_sched() as
"preemptible RCU", not the "we can preempt in rcu_read_lock() context".

-- Steve


> 
> A context switch really is always an RCU-preempt quiescent state from
> the perspective of the CPU.  However, from the perspective of the task,
> context switch is a quiescent state only if the task is not in an
> RCU-preempt read-side critical section at the time.