Re: [PATCH RFC 6/8] rcu: Add back the Startedleaf tracepoint

[Paul E. McKenney]

On Sun, May 13, 2018 at 08:15:39PM -0700, Joel Fernandes (Google) wrote:
> In recent discussion [1], the check for whether a leaf believes RCU is
> not idle, is being added back to funnel locking code, to avoid more
> locking. In this we are marking the leaf node for a future grace-period
> and bailing out since a GP is currently in progress. However the
> tracepoint is missing. Lets add it back.
> 
> Also add a small comment about why we do this check (basically the point
> is to avoid locking intermediate nodes unnecessarily) and clarify the
> comments in the trace event header now that we are doing traversal of
> one or more intermediate nodes.
> 
> [1] http://lkml.kernel.org/r/20180513190906.GL26088@xxxxxxxxxxxxxxxxxx
> 
> Signed-off-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>

Looks like a good idea, but it does not apply -- which is not a surprise,
given the change rate in this code.  I hand-applied as a modification
to c1b3f9fce26f ("rcu: Don't funnel-lock above leaf node if GP in progress")
with attribution, but with the changes below.  Please let me know if I
am missing something.

Ah, I see -- this commit depends on your earlier name-change commit.
I therefore made this patch use the old names.

> ---
>  include/trace/events/rcu.h |  4 ++--
>  kernel/rcu/tree.c          | 11 ++++++++++-
>  2 files changed, 12 insertions(+), 3 deletions(-)
> 
> diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
> index 539900a9f8c7..dc0bd11739c7 100644
> --- a/include/trace/events/rcu.h
> +++ b/include/trace/events/rcu.h
> @@ -91,8 +91,8 @@ TRACE_EVENT(rcu_grace_period,
>   *
>   * "Startleaf": Request a grace period based on leaf-node data.
>   * "Prestarted": Someone beat us to the request
> - * "Startedleaf": Leaf-node start proved sufficient.
> - * "Startedleafroot": Leaf-node start proved sufficient after checking root.
> + * "Startedleaf": Leaf and one or more non-root nodes marked for future start.

Actually, we only get to that trace if all we did was mark the leaf
node, right?

> + * "Startedleafroot": all non-root nodes from leaf to root marked for future start.

I got rid of the "non-root" part, given that we had to have marked
the root to break out of the loop.

							Thanx, Paul

>   * "Startedroot": Requested a nocb grace period based on root-node data.
>   * "NoGPkthread": The RCU grace-period kthread has not yet started.
>   * "StartWait": Start waiting for the requested grace period.
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index 40670047d22c..8401a253e7de 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -1593,8 +1593,17 @@ static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
>  			goto unlock_out;
>  		}
>  		rnp_node->gp_seq_needed = gp_seq_start;
> -		if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))
> +
> +		/*
> +		 * Check if leaf believes a GP is in progress, if yes we can
> +		 * bail and avoid more locking. We have already marked the leaf.
> +		 */
> +		if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) {
> +			trace_rcu_this_gp(rnp_node, rdp, gp_seq_start,
> +					  TPS("Startedleaf"));
>  			goto unlock_out;
> +		}
> +
>  		if (rnp_node != rnp && rnp_node->parent != NULL)
>  			raw_spin_unlock_rcu_node(rnp_node);
>  		if (!rnp_node->parent) {
> -- 
> 2.17.0.441.gb46fe60e1d-goog
>