rcu/exp: Make parallel exp gp kworker per rcu node

When CONFIG_RCU_EXP_KTHREAD=n, the expedited grace period per node
initialization is performed in parallel via workqueues (one work per
node).

However in CONFIG_RCU_EXP_KTHREAD=y, this per node initialization is
performed by a single kworker serializing each node initialization (one
work for all nodes).

The second part is certainly less scalable and efficient beyond a single
leaf node.

To improve this, expand this single kworker into per-node kworkers. This
new layout is eventually intended to remove the workqueues based
implementation since it will essentially now become duplicate code.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>

Author: Frederic Weisbecker

kernel/rcu/rcu.h

@@ -625,7 +625,6 @@ void rcu_force_quiescent_state(void);
 extern struct workqueue_struct *rcu_gp_wq;
 #ifdef CONFIG_RCU_EXP_KTHREAD
 extern struct kthread_worker *rcu_exp_gp_kworker;
-extern struct kthread_worker *rcu_exp_par_gp_kworker;
 #else /* !CONFIG_RCU_EXP_KTHREAD */
 extern struct workqueue_struct *rcu_par_gp_wq;
 #endif /* CONFIG_RCU_EXP_KTHREAD */

kernel/rcu/tree.c

@@ -4396,33 +4396,39 @@ rcu_boot_init_percpu_data(int cpu)
 
 #ifdef CONFIG_RCU_EXP_KTHREAD
 struct kthread_worker *rcu_exp_gp_kworker;
-struct kthread_worker *rcu_exp_par_gp_kworker;
 
-static void __init rcu_start_exp_gp_kworkers(void)
+static void rcu_spawn_exp_par_gp_kworker(struct rcu_node *rnp)
 {
-	const char *par_gp_kworker_name = "rcu_exp_par_gp_kthread_worker";
-	const char *gp_kworker_name = "rcu_exp_gp_kthread_worker";
+	struct kthread_worker *kworker;
+	const char *name = "rcu_exp_par_gp_kthread_worker/%d";
 	struct sched_param param = { .sched_priority = kthread_prio };
+	int rnp_index = rnp - rcu_get_root();
 
-	rcu_exp_gp_kworker = kthread_create_worker(0, gp_kworker_name);
-	if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) {
-		pr_err("Failed to create %s!\n", gp_kworker_name);
-		rcu_exp_gp_kworker = NULL;
+	if (rnp->exp_kworker)
+		return;
+
+	kworker = kthread_create_worker(0, name, rnp_index);
+	if (IS_ERR_OR_NULL(kworker)) {
+		pr_err("Failed to create par gp kworker on %d/%d\n",
+		       rnp->grplo, rnp->grphi);
 		return;
 	}
+	WRITE_ONCE(rnp->exp_kworker, kworker);
+	sched_setscheduler_nocheck(kworker->task, SCHED_FIFO, &param);
+}
 
-	rcu_exp_par_gp_kworker = kthread_create_worker(0, par_gp_kworker_name);
-	if (IS_ERR_OR_NULL(rcu_exp_par_gp_kworker)) {
-		pr_err("Failed to create %s!\n", par_gp_kworker_name);
-		rcu_exp_par_gp_kworker = NULL;
-		kthread_destroy_worker(rcu_exp_gp_kworker);
+static void __init rcu_start_exp_gp_kworker(void)
+{
+	const char *name = "rcu_exp_gp_kthread_worker";
+	struct sched_param param = { .sched_priority = kthread_prio };
+
+	rcu_exp_gp_kworker = kthread_create_worker(0, name);
+	if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) {
+		pr_err("Failed to create %s!\n", name);
 		rcu_exp_gp_kworker = NULL;
 		return;
 	}
-
 	sched_setscheduler_nocheck(rcu_exp_gp_kworker->task, SCHED_FIFO, &param);
-	sched_setscheduler_nocheck(rcu_exp_par_gp_kworker->task, SCHED_FIFO,
-				   &param);
 }
 
 static inline void rcu_alloc_par_gp_wq(void)
@@ -4431,7 +4437,11 @@ static inline void rcu_alloc_par_gp_wq(void)
 #else /* !CONFIG_RCU_EXP_KTHREAD */
 struct workqueue_struct *rcu_par_gp_wq;
 
-static void __init rcu_start_exp_gp_kworkers(void)
+static void rcu_spawn_exp_par_gp_kworker(struct rcu_node *rnp)
+{
+}
+
+static void __init rcu_start_exp_gp_kworker(void)
 {
 }
 
@@ -4442,6 +4452,17 @@ static inline void rcu_alloc_par_gp_wq(void)
 }
 #endif /* CONFIG_RCU_EXP_KTHREAD */
 
+static void rcu_spawn_rnp_kthreads(struct rcu_node *rnp)
+{
+	if ((IS_ENABLED(CONFIG_RCU_EXP_KTHREAD) ||
+	     IS_ENABLED(CONFIG_RCU_BOOST)) && rcu_scheduler_fully_active) {
+		mutex_lock(&rnp->kthread_mutex);
+		rcu_spawn_one_boost_kthread(rnp);
+		rcu_spawn_exp_par_gp_kworker(rnp);
+		mutex_unlock(&rnp->kthread_mutex);
+	}
+}
+
 /*
  * Invoked early in the CPU-online process, when pretty much all services
  * are available.  The incoming CPU is not present.
@@ -4490,7 +4511,7 @@ int rcutree_prepare_cpu(unsigned int cpu)
 	rdp->rcu_iw_gp_seq = rdp->gp_seq - 1;
 	trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl"));
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-	rcu_spawn_one_boost_kthread(rnp);
+	rcu_spawn_rnp_kthreads(rnp);
 	rcu_spawn_cpu_nocb_kthread(cpu);
 	WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus + 1);
 
@@ -4812,10 +4833,10 @@ static int __init rcu_spawn_gp_kthread(void)
 	 * due to rcu_scheduler_fully_active.
 	 */
 	rcu_spawn_cpu_nocb_kthread(smp_processor_id());
-	rcu_spawn_one_boost_kthread(rdp->mynode);
+	rcu_spawn_rnp_kthreads(rdp->mynode);
 	rcu_spawn_core_kthreads();
 	/* Create kthread worker for expedited GPs */
-	rcu_start_exp_gp_kworkers();
+	rcu_start_exp_gp_kworker();
 	return 0;
 }
 early_initcall(rcu_spawn_gp_kthread);

kernel/rcu/tree.h

@@ -72,6 +72,9 @@ struct rcu_node {
 				/* Online CPUs for next expedited GP. */
 				/*  Any CPU that has ever been online will */
 				/*  have its bit set. */
+	struct kthread_worker *exp_kworker;
+				/* Workers performing per node expedited GP */
+				/* initialization. */
 	unsigned long cbovldmask;
 				/* CPUs experiencing callback overload. */
 	unsigned long ffmask;	/* Fully functional CPUs. */

kernel/rcu/tree_exp.h

@@ -432,9 +432,9 @@ static inline bool rcu_exp_worker_started(void)
 	return !!READ_ONCE(rcu_exp_gp_kworker);
 }
 
-static inline bool rcu_exp_par_worker_started(void)
+static inline bool rcu_exp_par_worker_started(struct rcu_node *rnp)
 {
-	return !!READ_ONCE(rcu_exp_par_gp_kworker);
+	return !!READ_ONCE(rnp->exp_kworker);
 }
 
 static inline void sync_rcu_exp_select_cpus_queue_work(struct rcu_node *rnp)
@@ -445,7 +445,7 @@ static inline void sync_rcu_exp_select_cpus_queue_work(struct rcu_node *rnp)
 	 * another work item on the same kthread worker can result in
 	 * deadlock.
 	 */
-	kthread_queue_work(rcu_exp_par_gp_kworker, &rnp->rew.rew_work);
+	kthread_queue_work(READ_ONCE(rnp->exp_kworker), &rnp->rew.rew_work);
 }
 
 static inline void sync_rcu_exp_select_cpus_flush_work(struct rcu_node *rnp)
@@ -487,7 +487,7 @@ static inline bool rcu_exp_worker_started(void)
 	return !!READ_ONCE(rcu_gp_wq);
 }
 
-static inline bool rcu_exp_par_worker_started(void)
+static inline bool rcu_exp_par_worker_started(struct rcu_node *rnp)
 {
 	return !!READ_ONCE(rcu_par_gp_wq);
 }
@@ -550,7 +550,7 @@ static void sync_rcu_exp_select_cpus(void)
 		rnp->exp_need_flush = false;
 		if (!READ_ONCE(rnp->expmask))
 			continue; /* Avoid early boot non-existent wq. */
-		if (!rcu_exp_par_worker_started() ||
+		if (!rcu_exp_par_worker_started(rnp) ||
 		    rcu_scheduler_active != RCU_SCHEDULER_RUNNING ||
 		    rcu_is_last_leaf_node(rnp)) {
 			/* No worker started yet or last leaf, do direct call. */

kernel/rcu/tree_plugin.h

@@ -1195,24 +1195,20 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp)
 	struct sched_param sp;
 	struct task_struct *t;
 
-	mutex_lock(&rnp->kthread_mutex);
-	if (rnp->boost_kthread_task || !rcu_scheduler_fully_active)
-		goto out;
+	if (rnp->boost_kthread_task)
+		return;
 
 	t = kthread_create(rcu_boost_kthread, (void *)rnp,
 			   "rcub/%d", rnp_index);
 	if (WARN_ON_ONCE(IS_ERR(t)))
-		goto out;
+		return;
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	rnp->boost_kthread_task = t;
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	sp.sched_priority = kthread_prio;
 	sched_setscheduler_nocheck(t, SCHED_FIFO, &sp);
 	wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */
-
- out:
-	mutex_unlock(&rnp->kthread_mutex);
 }
 
 /*