diff mbox series

[4/8] rcu/exp: Handle RCU expedited grace period kworker allocation failure

Message ID 20231219140843.939329-5-frederic@kernel.org (mailing list archive)
State New, archived
Headers show
Series rcu: Fix expedited GP deadlock (and cleanup some nocb stuff) | expand

Commit Message

Frederic Weisbecker Dec. 19, 2023, 2:08 p.m. UTC
Just like is done for the kworker performing nodes initialization,
gracefully handle the possible allocation failure of the RCU expedited
grace period main kworker.

While at it perform a rename of the related checking functions to better
reflect the expedited specifics.

Reviewed-by: Kalesh Singh <kaleshsingh@google.com>
Fixes: 9621fbee44df ("rcu: Move expedited grace period (GP) work to RT kthread_worker")
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
---
 kernel/rcu/tree.c     |  2 ++
 kernel/rcu/tree_exp.h | 25 +++++++++++++++++++------
 2 files changed, 21 insertions(+), 6 deletions(-)
diff mbox series

Patch

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 65d730a2b492..3777fd305f2e 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -4753,6 +4753,7 @@  static void __init rcu_start_exp_gp_kworkers(void)
 	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;
 		return;
 	}
 
@@ -4761,6 +4762,7 @@  static void __init rcu_start_exp_gp_kworkers(void)
 		pr_err("Failed to create %s!\n", par_gp_kworker_name);
 		rcu_exp_par_gp_kworker = NULL;
 		kthread_destroy_worker(rcu_exp_gp_kworker);
+		rcu_exp_gp_kworker = NULL;
 		return;
 	}
 
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 014ddf672165..c078e214b12e 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -427,7 +427,12 @@  static void sync_rcu_exp_select_node_cpus(struct kthread_work *wp)
 	__sync_rcu_exp_select_node_cpus(rewp);
 }
 
-static inline bool rcu_gp_par_worker_started(void)
+static inline bool rcu_exp_worker_started(void)
+{
+	return !!READ_ONCE(rcu_exp_gp_kworker);
+}
+
+static inline bool rcu_exp_par_worker_started(void)
 {
 	return !!READ_ONCE(rcu_exp_par_gp_kworker);
 }
@@ -477,7 +482,12 @@  static void sync_rcu_exp_select_node_cpus(struct work_struct *wp)
 	__sync_rcu_exp_select_node_cpus(rewp);
 }
 
-static inline bool rcu_gp_par_worker_started(void)
+static inline bool rcu_exp_worker_started(void)
+{
+	return !!READ_ONCE(rcu_gp_wq);
+}
+
+static inline bool rcu_exp_par_worker_started(void)
 {
 	return !!READ_ONCE(rcu_par_gp_wq);
 }
@@ -540,7 +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_gp_par_worker_started() ||
+		if (!rcu_exp_par_worker_started() ||
 		    rcu_scheduler_active != RCU_SCHEDULER_RUNNING ||
 		    rcu_is_last_leaf_node(rnp)) {
 			/* No worker started yet or last leaf, do direct call. */
@@ -955,7 +965,7 @@  static void rcu_exp_print_detail_task_stall_rnp(struct rcu_node *rnp)
  */
 void synchronize_rcu_expedited(void)
 {
-	bool boottime = (rcu_scheduler_active == RCU_SCHEDULER_INIT);
+	bool can_queue;
 	unsigned long flags;
 	struct rcu_exp_work rew;
 	struct rcu_node *rnp;
@@ -966,6 +976,9 @@  void synchronize_rcu_expedited(void)
 			 lock_is_held(&rcu_sched_lock_map),
 			 "Illegal synchronize_rcu_expedited() in RCU read-side critical section");
 
+	can_queue = (rcu_scheduler_active != RCU_SCHEDULER_INIT) &&
+		    rcu_exp_worker_started();
+
 	/* Is the state is such that the call is a grace period? */
 	if (rcu_blocking_is_gp()) {
 		// Note well that this code runs with !PREEMPT && !SMP.
@@ -995,7 +1008,7 @@  void synchronize_rcu_expedited(void)
 		return;  /* Someone else did our work for us. */
 
 	/* Ensure that load happens before action based on it. */
-	if (unlikely(boottime)) {
+	if (unlikely(!can_queue)) {
 		/* Direct call during scheduler init and early_initcalls(). */
 		rcu_exp_sel_wait_wake(s);
 	} else {
@@ -1013,7 +1026,7 @@  void synchronize_rcu_expedited(void)
 	/* Let the next expedited grace period start. */
 	mutex_unlock(&rcu_state.exp_mutex);
 
-	if (likely(!boottime))
+	if (likely(can_queue))
 		synchronize_rcu_expedited_destroy_work(&rew);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_expedited);