Re: [PATCH 4/4] rcu: Identify grace period is in progress as we advance up the tree

[Paul E. McKenney]

On Tue, May 22, 2018 at 11:38:15PM -0700, Joel Fernandes wrote:
> From: "Joel Fernandes (Google)" <joel@xxxxxxxxxxxxxxxxx>
> 
> There's no need to keep checking the same starting node for whether a
> grace period is in progress as we advance up the funnel lock loop. Its
> sufficient if we just checked it in the start, and then subsequently
> checked the internal nodes as we advanced up the combining tree. This
> also makes sense because the grace-period updates propogate from the
> root to the leaf, so there's a chance we may find a grace period has
> started as we advance up, lets check for the same.
> 
> Reported-by: Paul McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
> Signed-off-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>

Looks good, queued for further review and testing, thank you!

							Thanx, Paul

> ---
>  kernel/rcu/tree.c | 9 +++++----
>  1 file changed, 5 insertions(+), 4 deletions(-)
> 
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index 31f4b4b7d824..65e49282429c 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -1570,11 +1570,12 @@ static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp,
>  			goto unlock_out;
>  		}
>  		rnp->gp_seq_needed = gp_seq_req;
> -		if (rcu_seq_state(rcu_seq_current(&rnp_start->gp_seq))) {
> +		if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) {
>  			/*
> -			 * We just marked the leaf, and a grace period
> -			 * is in progress, which means that rcu_gp_cleanup()
> -			 * will see the marking.  Bail to reduce contention.
> +			 * We just marked the leaf or internal node, and a
> +			 * grace period is in progress, which means that
> +			 * rcu_gp_cleanup() will see the marking.  Bail to
> +			 * reduce contention.
>  			 */
>  			trace_rcu_this_gp(rnp_start, rdp, gp_seq_req,
>  					  TPS("Startedleaf"));
> -- 
> 2.17.0.441.gb46fe60e1d-goog
>