Re: [PATCH -next 4/8] rcu/nocb: Add warning if no rcuog wake up attempt happened during overload

[Frederic Weisbecker <frederic@kernel.org>]

Le Thu, Jan 01, 2026 at 11:34:13AM -0500, Joel Fernandes a écrit :
> To be sure we have no rcog wake ups that were lost, add a warning
> to cover the case where the rdp is overloaded with callbacks but
> no wake up was attempted.
> 
> Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
> ---
>  kernel/rcu/tree.c      | 4 ++++
>  kernel/rcu/tree.h      | 1 +
>  kernel/rcu/tree_nocb.h | 6 +++++-
>  3 files changed, 10 insertions(+), 1 deletion(-)
> 
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index 293bbd9ac3f4..78c045a5ef03 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -3767,6 +3767,10 @@ static void rcu_barrier_entrain(struct rcu_data *rdp)
>  		debug_rcu_head_unqueue(&rdp->barrier_head);
>  		rcu_barrier_trace(TPS("IRQNQ"), -1, rcu_state.barrier_sequence);
>  	}
> +#ifdef CONFIG_RCU_NOCB_CPU
> +	if (wake_nocb)
> +		rdp->nocb_gp_wake_attempt = true;
> +#endif

entrain only queues a callback if the list is non-empty. And if it's
non-empty, rdp->nocb_gp_wake_attempt should be true already.

>  	rcu_nocb_unlock(rdp);
>  	if (wake_nocb)
>  		wake_nocb_gp(rdp, false);
> diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
> index 653fb4ba5852..74bd6a2a2f84 100644
> --- a/kernel/rcu/tree.h
> +++ b/kernel/rcu/tree.h
> @@ -257,6 +257,7 @@ struct rcu_data {
>  	unsigned long nocb_gp_loops;	/* # passes through wait code. */
>  	struct swait_queue_head nocb_gp_wq; /* For nocb kthreads to sleep on. */
>  	bool nocb_cb_sleep;		/* Is the nocb CB thread asleep? */
> +	bool nocb_gp_wake_attempt;	/* Was a rcuog wakeup attempted? */

How about nocb_gp_handling ?

>  	struct task_struct *nocb_cb_kthread;
>  	struct list_head nocb_head_rdp; /*
>  					 * Head of rcu_data list in wakeup chain,
> diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
> index daff2756cd90..7e9d465c8ab1 100644
> --- a/kernel/rcu/tree_nocb.h
> +++ b/kernel/rcu/tree_nocb.h
> @@ -546,6 +546,7 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
>  	lazy_len = READ_ONCE(rdp->lazy_len);
>  	if (was_alldone) {
>  		rdp->qlen_last_fqs_check = len;
> +		rdp->nocb_gp_wake_attempt = true;
>  		rcu_nocb_unlock(rdp);
>  		// Only lazy CBs in bypass list
>  		if (lazy_len && bypass_len == lazy_len) {
> @@ -563,7 +564,8 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
>  
>  		return;
>  	} else if (len > rdp->qlen_last_fqs_check + qhimark) {
> -		/* ... or if many callbacks queued. */
> +		/* Callback overload condition. */
> +		WARN_ON_ONCE(!rdp->nocb_gp_wake_attempt);
>  		rdp->qlen_last_fqs_check = len;
>  		j = jiffies;
>  		if (j != rdp->nocb_gp_adv_time &&
> @@ -688,6 +690,7 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
>  		     bypass_ncbs > 2 * qhimark)) {
>  			flush_bypass = true;
>  		} else if (!bypass_ncbs && rcu_segcblist_empty(&rdp->cblist)) {
> +			rdp->nocb_gp_wake_attempt = false;

This is when nocb_cb_wait() is done with callbacks but nocb_gp_wait() is done
with them sooner, when the grace period is done for all pending callbacks.

Something like this would perhaps be more accurate:

diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index e6cd56603cad..52010cbeaa76 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -746,6 +746,8 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 			needwait_gp = true;
 			trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
 					    TPS("NeedWaitGP"));
+		} else if (!rcu_cblist_n_cbs(&rdp->nocb_bypass)) {
+			rdp->nocb_gp_wake_attempt = false;
 		}
 		if (rcu_segcblist_ready_cbs(&rdp->cblist)) {
 			needwake = rdp->nocb_cb_sleep;


>  			rcu_nocb_unlock_irqrestore(rdp, flags);
>  			continue; /* No callbacks here, try next. */
>  		}
> @@ -1254,6 +1257,7 @@ lazy_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
>  			continue;
>  		}
>  		rcu_nocb_try_flush_bypass(rdp, jiffies);
> +		rdp->nocb_gp_wake_attempt = true;

Same here, we should expect rdp->nocb_gp_wake_attempt to be already on since
there are lazy callbacks. That's a good opportunity to test the related assertion
though.

Thanks.

>  		rcu_nocb_unlock_irqrestore(rdp, flags);
>  		wake_nocb_gp(rdp, false);
>  		sc->nr_to_scan -= _count;
> -- 
> 2.34.1
> 

-- 
Frederic Weisbecker
SUSE Labs