Re: [PATCH 00/10] rcu: Make rcu_core() safe in PREEMPT_RT with NOCB + a few other fixes v3

[Paul E. McKenney]

On Tue, Oct 19, 2021 at 02:08:06AM +0200, Frederic Weisbecker wrote:
> Changes since v2:
> 
> _ Drop first patch (got applied by Paul)
> 
> _ Fix unwanted rcu_core() hanging around after setting a CPU as nocb
>   on boot. This resulted in terrible rcu_barrier() misordering.
>   I simply forgot to clear SEGCBLIST_RCU_CORE on nocb CPUs on boot.
> 
> git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git
> 	rcu/rt-v3
> 
> HEAD: 7610a2ba5eaca8caf977ed45bad251ac693feefa

Queued for further review and testing!

							Thanx, Paul

> Thanks,
> 	Frederic
> ---
> 
> Frederic Weisbecker (9):
>       rcu/nocb: Prepare state machine for a new step
>       rcu/nocb: Invoke rcu_core() at the start of deoffloading
>       rcu/nocb: Make rcu_core() callbacks acceleration (de-)offloading safe
>       rcu/nocb: Check a stable offloaded state to manipulate qlen_last_fqs_check
>       rcu/nocb: Use appropriate rcu_nocb_lock_irqsave()
>       rcu/nocb: Limit number of softirq callbacks only on softirq
>       rcu: Fix callbacks processing time limit retaining cond_resched()
>       rcu: Apply callbacks processing time limit only on softirq
>       rcu/nocb: Don't invoke local rcu core on callback overload from nocb kthread
> 
> Thomas Gleixner (1):
>       rcu/nocb: Make rcu_core() callbacks acceleration preempt-safe
> 
> 
>  include/linux/rcu_segcblist.h | 51 ++++++++++++++++++-------
>  kernel/rcu/rcu_segcblist.c    | 10 ++---
>  kernel/rcu/rcu_segcblist.h    | 12 +++---
>  kernel/rcu/tree.c             | 87 +++++++++++++++++++++++++++++--------------
>  kernel/rcu/tree_nocb.h        | 33 ++++++++++++----
>  5 files changed, 133 insertions(+), 60 deletions(-)