Re: [RFC PATCH 10/12] rcu: Process batch locally as long as offloading isn't complete

[Paul E. McKenney]

On Mon, Sep 21, 2020 at 02:43:49PM +0200, Frederic Weisbecker wrote:
> During the offloading or de-offloading process, make sure to process
> the callbacks batch locally whenever the segcblist isn't entirely
> offloaded. This enforces callback service processing while we are still
> in intermediate (de-)offloading state.
> 
> FIXME: Note that __call_rcu_core() isn't called during these intermediate
> states. Some pieces there may still be necessary.

Joel's per-segment callback-count work might help there, though I believe
that to be a separate issue.

The key point is that if there are a lot of callbacks, but all of them
are ready to be invoked, then there isn't much point in making the
grace periods complete faster.  Right now, lacking per-segment counts,
RCU just assumes that none of the callbacks are ready to be invoked.

						Thanx, Paul

> Inspired-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
> Signed-off-by: Frederic Weisbecker <frederic@xxxxxxxxxx>
> Cc: Paul E. McKenney <paulmck@xxxxxxxxxx>
> Cc: Josh Triplett <josh@xxxxxxxxxxxxxxxx>
> Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
> Cc: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
> Cc: Lai Jiangshan <jiangshanlai@xxxxxxxxx>
> Cc: Joel Fernandes <joel@xxxxxxxxxxxxxxxxx>
> ---
>  kernel/rcu/rcu_segcblist.h | 12 ++++++++++++
>  kernel/rcu/tree.c          |  3 ++-
>  2 files changed, 14 insertions(+), 1 deletion(-)
> 
> diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h
> index 00ebeb8d39b7..f7da3d535888 100644
> --- a/kernel/rcu/rcu_segcblist.h
> +++ b/kernel/rcu/rcu_segcblist.h
> @@ -92,6 +92,18 @@ static inline bool rcu_segcblist_is_offloaded(struct rcu_segcblist *rsclp)
>  	return false;
>  }
>  
> +static inline bool rcu_segcblist_completely_offloaded(struct rcu_segcblist *rsclp)
> +{
> +	int flags = SEGCBLIST_KTHREAD_CB | SEGCBLIST_KTHREAD_GP | SEGCBLIST_OFFLOADED;
> +
> +	if (IS_ENABLED(CONFIG_RCU_NOCB_CPU)) {
> +		if ((rsclp->flags & flags) == flags)
> +			return true;
> +	}
> +
> +	return false;
> +}
> +
>  /*
>   * Are all segments following the specified segment of the specified
>   * rcu_segcblist structure empty of callbacks?  (The specified
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index b4292489db0c..928907e9ba94 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -2620,6 +2620,7 @@ static __latent_entropy void rcu_core(void)
>  	struct rcu_data *rdp = raw_cpu_ptr(&rcu_data);
>  	struct rcu_node *rnp = rdp->mynode;
>  	const bool offloaded = rcu_segcblist_is_offloaded(&rdp->cblist);
> +	const bool do_batch = !rcu_segcblist_completely_offloaded(&rdp->cblist);
>  
>  	if (cpu_is_offline(smp_processor_id()))
>  		return;
> @@ -2649,7 +2650,7 @@ static __latent_entropy void rcu_core(void)
>  	rcu_check_gp_start_stall(rnp, rdp, rcu_jiffies_till_stall_check());
>  
>  	/* If there are callbacks ready, invoke them. */
> -	if (!offloaded && rcu_segcblist_ready_cbs(&rdp->cblist) &&
> +	if (do_batch && rcu_segcblist_ready_cbs(&rdp->cblist) &&
>  	    likely(READ_ONCE(rcu_scheduler_fully_active)))
>  		rcu_do_batch(rdp);
>  
> -- 
> 2.28.0
>