Received-SPF: pass (google.com: domain of linux-kernel+bounces-96370-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
From: "Joel Fernandes (Google)" <joel@joelfernandes.org>
To: linux-kernel@vger.kernel.org,
	frederic@kernel.org,
	boqun.feng@gmail.com,
	urezki@gmail.com,
	neeraj.iitr10@gmail.com,
	joel@joelfernandes.org,
	rcu@vger.kernel.org,
	rostedt@goodmis.org,
	"Paul E. McKenney" <paulmck@kernel.org>,
	Neeraj Upadhyay <neeraj.upadhyay@kernel.org>,
	Josh Triplett <josh@joshtriplett.org>,
	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
	Lai Jiangshan <jiangshanlai@gmail.com>,
	Zqiang <qiang.zhang1211@gmail.com>
Subject: [PATCH] [RFC] rcu/tree: Reduce wake up for synchronize_rcu() common case
Date: Thu,  7 Mar 2024 18:48:51 -0500
Message-Id: <20240307234852.2132637-1-joel@joelfernandes.org>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

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>
---
 kernel/rcu/tree.c | 36 +++++++++++++++++++++++++++++++-----
 kernel/rcu/tree.h |  1 +
 2 files changed, 32 insertions(+), 5 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 12978049cb99..cba3a82e9ed9 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. */
@@ -1641,8 +1642,11 @@ 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) {
+		/* See comments below. */
+		atomic_dec_return_release(&rcu_state.srs_cleanups_pending);
 		return;
+	}
 
 	WARN_ON_ONCE(!rcu_sr_is_wait_head(done));
 	head = done->next;
@@ -1665,6 +1669,9 @@ 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);
 }
 
 /*
@@ -1672,7 +1679,7 @@ static void rcu_sr_normal_gp_cleanup_work(struct work_struct *work)
  */
 static void rcu_sr_normal_gp_cleanup(void)
 {
-	struct llist_node *wait_tail, *next, *rcu;
+	struct llist_node *wait_tail, *next = NULL, *rcu = NULL;
 	int done = 0;
 
 	wait_tail = rcu_state.srs_wait_tail;
@@ -1698,16 +1705,35 @@ static void rcu_sr_normal_gp_cleanup(void)
 			break;
 	}
 
-	// concurrent sr_normal_gp_cleanup work might observe this update.
-	smp_store_release(&rcu_state.srs_done_tail, wait_tail);
+	/*
+	 * Fast path, no more users to process. Remove the last wait head
+	 * if no inflight-workers. If there are in-flight workers, let them
+	 * remove the last wait head.
+	 */
+	WARN_ON_ONCE(!rcu);
 	ASSERT_EXCLUSIVE_WRITER(rcu_state.srs_done_tail);
 
+	if (rcu && rcu_sr_is_wait_head(rcu) && rcu->next == NULL &&
+		/* Order atomic access with list manipulation. */
+		!atomic_read_acquire(&rcu_state.srs_cleanups_pending)) {
+		wait_tail->next = NULL;
+		rcu_sr_put_wait_head(rcu);
+		smp_store_release(&rcu_state.srs_done_tail, wait_tail);
+		return;
+	}
+
+	/* Concurrent sr_normal_gp_cleanup work might observe this update. */
+	smp_store_release(&rcu_state.srs_done_tail, wait_tail);
+
 	/*
 	 * We schedule a work in order to perform a final processing
 	 * of outstanding users(if still left) and releasing wait-heads
 	 * added by rcu_sr_normal_gp_init() call.
 	 */
-	queue_work(system_highpri_wq, &rcu_state.srs_cleanup_work);
+	atomic_inc(&rcu_state.srs_cleanups_pending);
+	if (!queue_work(system_highpri_wq, &rcu_state.srs_cleanup_work)) {
+		atomic_dec(&rcu_state.srs_cleanups_pending);
+	}
 }
 
 /*
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 2832787cee1d..f162b947c5b6 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -420,6 +420,7 @@ struct rcu_state {
 	struct llist_node *srs_done_tail; /* ready for GP users. */
 	struct sr_wait_node srs_wait_nodes[SR_NORMAL_GP_WAIT_HEAD_MAX];
 	struct work_struct srs_cleanup_work;
+	atomic_t srs_cleanups_pending; /* srs inflight worker cleanups. */
 };
 
 /* Values for rcu_state structure's gp_flags field. */
-- 
2.34.1