Received-SPF: pass (google.com: domain of linux-kernel+bounces-132091-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
Date: Thu, 4 Apr 2024 22:19:11 +0200
From: Frederic Weisbecker <frederic@kernel.org>
To: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Cc: linux-kernel@vger.kernel.org, "Paul E. McKenney" <paulmck@kernel.org>,
	Neeraj Upadhyay <neeraj.upadhyay@kernel.org>,
	Josh Triplett <josh@joshtriplett.org>,
	Boqun Feng <boqun.feng@gmail.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
	Lai Jiangshan <jiangshanlai@gmail.com>,
	Zqiang <qiang.zhang1211@gmail.com>, urezki@gmail.com,
	neeraj.iitr10@gmail.com, rcu@vger.kernel.org
Subject: Re: [PATCH v4] rcu/tree: Reduce wake up for synchronize_rcu() common
 case
Message-ID: <Zg8LP9fEHlDPeq5L@pavilion.home>
References: <20240319185458.3968308-1-joel@joelfernandes.org>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <20240319185458.3968308-1-joel@joelfernandes.org>

Le Tue, Mar 19, 2024 at 02:54:57PM -0400, Joel Fernandes (Google) a ?crit :
> In the synchronize_rcu() common case, we will have less than
> SR_MAX_USERS_WAKE_FROM_GP number of users per GP. Waking up the kworker
> is pointless just to free the last injected wait head since at that point,
> all the users have already been awakened.
> 
> Introduce a new counter to track this and prevent the wakeup in the
> common case.
> 
> Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
> ---
> v1->v2: Rebase on paul/dev
> v2->v3: Additional optimization for wait_tail->next == NULL case.
> v3->v4: Apply clean ups from Vlad. Tested rcutorture all scenarios.
> ---
>  kernel/rcu/tree.c | 35 ++++++++++++++++++++++++++++++-----
>  kernel/rcu/tree.h |  1 +
>  2 files changed, 31 insertions(+), 5 deletions(-)
> 
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index 9fbb5ab57c84..f3193670fe42 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -96,6 +96,7 @@ static struct rcu_state rcu_state = {
>  	.ofl_lock = __ARCH_SPIN_LOCK_UNLOCKED,
>  	.srs_cleanup_work = __WORK_INITIALIZER(rcu_state.srs_cleanup_work,
>  		rcu_sr_normal_gp_cleanup_work),
> +	.srs_cleanups_pending = ATOMIC_INIT(0),
>  };
>  
>  /* Dump rcu_node combining tree at boot to verify correct setup. */
> @@ -1642,8 +1643,11 @@ static void rcu_sr_normal_gp_cleanup_work(struct work_struct *work)
>  	 * the done tail list manipulations are protected here.
>  	 */
>  	done = smp_load_acquire(&rcu_state.srs_done_tail);
> -	if (!done)
> +	if (!done) {

Can this really happen? And if not should we warn?

> +		/* See comments below. */
> +		atomic_dec_return_release(&rcu_state.srs_cleanups_pending);

And if not should we really do that?

>  		return;
> +	}
>  
>  	WARN_ON_ONCE(!rcu_sr_is_wait_head(done));
>  	head = done->next;
> @@ -1666,6 +1670,9 @@ static void rcu_sr_normal_gp_cleanup_work(struct work_struct *work)
>  
>  		rcu_sr_put_wait_head(rcu);
>  	}
> +
> +	/* Order list manipulations with atomic access. */
> +	atomic_dec_return_release(&rcu_state.srs_cleanups_pending);

Can we have a sanity check here ensuring this never goes negative?

Thanks.