1. Patchew
  2. linux
  3. [PATCH 0/5 v2] rcu/exp updates
  4. View patch

[PATCH 2/5] rcu/exp: Remove confusing needless full barrier on task unblock

Frederic Weisbecker posted 5 patches 9 months, 1 week ago
There is a newer version of this series
[PATCH 2/5] rcu/exp: Remove confusing needless full barrier on task unblock
Posted by Frederic Weisbecker 9 months, 1 week ago 
A full memory barrier in the RCU-PREEMPT task unblock path advertizes
to order the context switch (or rather the accesses prior to
rcu_read_unlock()) with the expedited grace period fastpath.

However the grace period can not complete without the rnp calling into
rcu_report_exp_rnp() with the node locked. This reports the quiescent
state in a fully ordered fashion against updater's accesses thanks to:

1) The READ-SIDE smp_mb__after_unlock_lock() barrier accross nodes
   locking while propagating QS up to the root.

2) The UPDATE-SIDE smp_mb__after_unlock_lock() barrier while holding the
   the root rnp to wait/check for the GP completion.

3) The (perhaps redundant given step 1) and 2)) smp_mb() in rcu_seq_end()
   before the grace period completes.

This makes the explicit barrier in this place superflous. Therefore
remove it as it is confusing.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
---
 kernel/rcu/tree_plugin.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 3c0bbbbb686f..d51cc7a5dfc7 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -534,7 +534,6 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
 		WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq &&
 			     (!empty_norm || rnp->qsmask));
 		empty_exp = sync_rcu_exp_done(rnp);
-		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
 		np = rcu_next_node_entry(t, rnp);
 		list_del_init(&t->rcu_node_entry);
 		t->rcu_blocked_node = NULL;
-- 
2.48.1
Re: [PATCH 2/5] rcu/exp: Remove confusing needless full barrier on task unblock
Posted by Paul E. McKenney 9 months ago 
On Fri, Mar 14, 2025 at 03:36:39PM +0100, Frederic Weisbecker wrote:
> A full memory barrier in the RCU-PREEMPT task unblock path advertizes
> to order the context switch (or rather the accesses prior to
> rcu_read_unlock()) with the expedited grace period fastpath.
> 
> However the grace period can not complete without the rnp calling into
> rcu_report_exp_rnp() with the node locked. This reports the quiescent
> state in a fully ordered fashion against updater's accesses thanks to:
> 
> 1) The READ-SIDE smp_mb__after_unlock_lock() barrier accross nodes
>    locking while propagating QS up to the root.
> 
> 2) The UPDATE-SIDE smp_mb__after_unlock_lock() barrier while holding the
>    the root rnp to wait/check for the GP completion.
> 
> 3) The (perhaps redundant given step 1) and 2)) smp_mb() in rcu_seq_end()
>    before the grace period completes.
> 
> This makes the explicit barrier in this place superflous. Therefore
> remove it as it is confusing.
> 
> Signed-off-by: Frederic Weisbecker <frederic@kernel.org>

Still cannot see a problem with this, but still a bit nervous.

Acked-by: Paul E. McKenney <paulmck@kernel.org>

> ---
>  kernel/rcu/tree_plugin.h | 1 -
>  1 file changed, 1 deletion(-)
> 
> diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
> index 3c0bbbbb686f..d51cc7a5dfc7 100644
> --- a/kernel/rcu/tree_plugin.h
> +++ b/kernel/rcu/tree_plugin.h
> @@ -534,7 +534,6 @@ rcu_preempt_deferred_qs_irqrestore(struct task_struct *t, unsigned long flags)
>  		WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq &&
>  			     (!empty_norm || rnp->qsmask));
>  		empty_exp = sync_rcu_exp_done(rnp);
> -		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
>  		np = rcu_next_node_entry(t, rnp);
>  		list_del_init(&t->rcu_node_entry);
>  		t->rcu_blocked_node = NULL;
> -- 
> 2.48.1
>
Re: [PATCH 2/5] rcu/exp: Remove confusing needless full barrier on task unblock
Posted by Frederic Weisbecker 9 months ago 
Le Tue, Mar 18, 2025 at 10:18:12AM -0700, Paul E. McKenney a écrit :
> On Fri, Mar 14, 2025 at 03:36:39PM +0100, Frederic Weisbecker wrote:
> > A full memory barrier in the RCU-PREEMPT task unblock path advertizes
> > to order the context switch (or rather the accesses prior to
> > rcu_read_unlock()) with the expedited grace period fastpath.
> > 
> > However the grace period can not complete without the rnp calling into
> > rcu_report_exp_rnp() with the node locked. This reports the quiescent
> > state in a fully ordered fashion against updater's accesses thanks to:
> > 
> > 1) The READ-SIDE smp_mb__after_unlock_lock() barrier accross nodes
> >    locking while propagating QS up to the root.
> > 
> > 2) The UPDATE-SIDE smp_mb__after_unlock_lock() barrier while holding the
> >    the root rnp to wait/check for the GP completion.
> > 
> > 3) The (perhaps redundant given step 1) and 2)) smp_mb() in rcu_seq_end()
> >    before the grace period completes.
> > 
> > This makes the explicit barrier in this place superflous. Therefore
> > remove it as it is confusing.
> > 
> > Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
> 
> Still cannot see a problem with this, but still a bit nervous.

Where is the challenge in life if we manage to fall alseep within a minute
at bedtime?

> 
> Acked-by: Paul E. McKenney <paulmck@kernel.org>

Thanks!
Re: [PATCH 2/5] rcu/exp: Remove confusing needless full barrier on task unblock
Posted by Paul E. McKenney 9 months ago 
On Wed, Mar 19, 2025 at 10:01:36AM +0100, Frederic Weisbecker wrote:
> Le Tue, Mar 18, 2025 at 10:18:12AM -0700, Paul E. McKenney a écrit :
> > On Fri, Mar 14, 2025 at 03:36:39PM +0100, Frederic Weisbecker wrote:
> > > A full memory barrier in the RCU-PREEMPT task unblock path advertizes
> > > to order the context switch (or rather the accesses prior to
> > > rcu_read_unlock()) with the expedited grace period fastpath.
> > > 
> > > However the grace period can not complete without the rnp calling into
> > > rcu_report_exp_rnp() with the node locked. This reports the quiescent
> > > state in a fully ordered fashion against updater's accesses thanks to:
> > > 
> > > 1) The READ-SIDE smp_mb__after_unlock_lock() barrier accross nodes
> > >    locking while propagating QS up to the root.
> > > 
> > > 2) The UPDATE-SIDE smp_mb__after_unlock_lock() barrier while holding the
> > >    the root rnp to wait/check for the GP completion.
> > > 
> > > 3) The (perhaps redundant given step 1) and 2)) smp_mb() in rcu_seq_end()
> > >    before the grace period completes.
> > > 
> > > This makes the explicit barrier in this place superflous. Therefore
> > > remove it as it is confusing.
> > > 
> > > Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
> > 
> > Still cannot see a problem with this, but still a bit nervous.
> 
> Where is the challenge in life if we manage to fall alseep within a minute
> at bedtime?

;-) ;-) ;-)

Suppose that there was an issue with this that we are somehow not spotting.
How would you go about debugging it?

							Thanx, Paul

> > Acked-by: Paul E. McKenney <paulmck@kernel.org>
> 
> Thanks!

Patchew 2.1-devel-b67e4c2

© 2016 - 2025 Red Hat, Inc.