rcu: Move expedited grace period (GP) work to RT kthread_worker

Enabling CONFIG_RCU_BOOST did not reduce RCU expedited grace-period
latency because its workqueues run at SCHED_OTHER, and thus can be
delayed by normal processes.  This commit avoids these delays by moving
the expedited GP work items to a real-time-priority kthread_worker.

This option is controlled by CONFIG_RCU_EXP_KTHREAD and disabled by
default on PREEMPT_RT=y kernels which disable expedited grace periods
after boot by unconditionally setting rcupdate.rcu_normal_after_boot=1.

The results were evaluated on arm64 Android devices (6GB ram) running
5.10 kernel, and capturing trace data in critical user-level code.

The table below shows the resulting order-of-magnitude improvements
in synchronize_rcu_expedited() latency:

------------------------------------------------------------------------
|                          |   workqueues  |  kthread_worker |  Diff   |
------------------------------------------------------------------------
| Count                    |          725  |            688  |         |
------------------------------------------------------------------------
| Min Duration       (ns)  |          326  |            447  |  37.12% |
------------------------------------------------------------------------
| Q1                 (ns)  |       39,428  |         38,971  |  -1.16% |
------------------------------------------------------------------------
| Q2 - Median        (ns)  |       98,225  |         69,743  | -29.00% |
------------------------------------------------------------------------
| Q3                 (ns)  |      342,122  |        126,638  | -62.98% |
------------------------------------------------------------------------
| Max Duration       (ns)  |  372,766,967  |      2,329,671  | -99.38% |
------------------------------------------------------------------------
| Avg Duration       (ns)  |    2,746,353  |        151,242  | -94.49% |
------------------------------------------------------------------------
| Standard Deviation (ns)  |   19,327,765  |        294,408  |         |
------------------------------------------------------------------------

The below table show the range of maximums/minimums for
synchronize_rcu_expedited() latency from all experiments:

------------------------------------------------------------------------
|                          |   workqueues  |  kthread_worker |  Diff   |
------------------------------------------------------------------------
| Total No. of Experiments |           25  |             23  |         |
------------------------------------------------------------------------
| Largest  Maximum   (ns)  |  372,766,967  |      2,329,671  | -99.38% |
------------------------------------------------------------------------
| Smallest Maximum   (ns)  |       38,819  |         86,954  | 124.00% |
------------------------------------------------------------------------
| Range of Maximums  (ns)  |  372,728,148  |      2,242,717  |         |
------------------------------------------------------------------------
| Largest  Minimum   (ns)  |       88,623  |         27,588  | -68.87% |
------------------------------------------------------------------------
| Smallest Minimum   (ns)  |          326  |            447  |  37.12% |
------------------------------------------------------------------------
| Range of Minimums  (ns)  |       88,297  |         27,141  |         |
------------------------------------------------------------------------

Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Reported-by: Tim Murray <timmurray@google.com>
Reported-by: Wei Wang <wvw@google.com>
Tested-by: Kyle Lin <kylelin@google.com>
Tested-by: Chunwei Lu <chunweilu@google.com>
Tested-by: Lulu Wang <luluw@google.com>
Signed-off-by: Kalesh Singh <kaleshsingh@google.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

1 files changed, 48 insertions, 3 deletions

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index a4b8189455d5..763e45fdf49b 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -4471,6 +4471,51 @@ static int rcu_pm_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
+#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)
+{
+	const char *par_gp_kworker_name = "rcu_exp_par_gp_kthread_worker";
+	const char *gp_kworker_name = "rcu_exp_gp_kthread_worker";
+	struct sched_param param = { .sched_priority = kthread_prio };
+
+	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);
+		return;
+	}
+
+	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);
+		kthread_destroy_worker(rcu_exp_gp_kworker);
+		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)
+{
+}
+#else /* !CONFIG_RCU_EXP_KTHREAD */
+struct workqueue_struct *rcu_par_gp_wq;
+
+static void __init rcu_start_exp_gp_kworkers(void)
+{
+}
+
+static inline void rcu_alloc_par_gp_wq(void)
+{
+	rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0);
+	WARN_ON(!rcu_par_gp_wq);
+}
+#endif /* CONFIG_RCU_EXP_KTHREAD */
+
 /*
  * Spawn the kthreads that handle RCU's grace periods.
  */
@@ -4500,6 +4545,8 @@ static int __init rcu_spawn_gp_kthread(void)
 	rcu_spawn_nocb_kthreads();
 	rcu_spawn_boost_kthreads();
 	rcu_spawn_core_kthreads();
+	/* Create kthread worker for expedited GPs */
+	rcu_start_exp_gp_kworkers();
 	return 0;
 }
 early_initcall(rcu_spawn_gp_kthread);
@@ -4745,7 +4792,6 @@ static void __init rcu_dump_rcu_node_tree(void)
 }
 
 struct workqueue_struct *rcu_gp_wq;
-struct workqueue_struct *rcu_par_gp_wq;
 
 static void __init kfree_rcu_batch_init(void)
 {
@@ -4811,8 +4857,7 @@ void __init rcu_init(void)
 	/* Create workqueue for Tree SRCU and for expedited GPs. */
 	rcu_gp_wq = alloc_workqueue("rcu_gp", WQ_MEM_RECLAIM, 0);
 	WARN_ON(!rcu_gp_wq);
-	rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0);
-	WARN_ON(!rcu_par_gp_wq);
+	rcu_alloc_par_gp_wq();
 
 	/* Fill in default value for rcutree.qovld boot parameter. */
 	/* -After- the rcu_node ->lock fields are initialized! */