PM: cpu: Make notifier chain use a raw_spinlock_t

Invoking atomic_notifier_chain_notify() requires acquiring a spinlock_t,
which can block under CONFIG_PREEMPT_RT. Notifications for members of the
cpu_pm notification chain will be issued by the idle task, which can never
block.

Making *all* atomic_notifiers use a raw_spinlock is too big of a hammer, as
only notifications issued by the idle task are problematic.

Special-case cpu_pm_notifier_chain by kludging a raw_notifier and
raw_spinlock_t together, matching the atomic_notifier behavior with a
raw_spinlock_t.

Fixes: 70d9329 ("notifier: Fix broken error handling pattern")
Signed-off-by: Valentin Schneider <[email protected]>
Acked-by: Sebastian Andrzej Siewior <[email protected]>
Signed-off-by: Rafael J. Wysocki <[email protected]>

Author: Valentin Schneider

kernel/cpu_pm.c

@@ -13,30 +13,46 @@
 #include <linux/spinlock.h>
 #include <linux/syscore_ops.h>
 
-static ATOMIC_NOTIFIER_HEAD(cpu_pm_notifier_chain);
+/*
+ * atomic_notifiers use a spinlock_t, which can block under PREEMPT_RT.
+ * Notifications for cpu_pm will be issued by the idle task itself, which can
+ * never block, IOW it requires using a raw_spinlock_t.
+ */
+static struct {
+	struct raw_notifier_head chain;
+	raw_spinlock_t lock;
+} cpu_pm_notifier = {
+	.chain = RAW_NOTIFIER_INIT(cpu_pm_notifier.chain),
+	.lock  = __RAW_SPIN_LOCK_UNLOCKED(cpu_pm_notifier.lock),
+};
 
 static int cpu_pm_notify(enum cpu_pm_event event)
 {
 	int ret;
 
 	/*
-	 * atomic_notifier_call_chain has a RCU read critical section, which
-	 * could be disfunctional in cpu idle. Copy RCU_NONIDLE code to let
-	 * RCU know this.
+	 * This introduces a RCU read critical section, which could be
+	 * disfunctional in cpu idle. Copy RCU_NONIDLE code to let RCU know
+	 * this.
 	 */
 	rcu_irq_enter_irqson();
-	ret = atomic_notifier_call_chain(&cpu_pm_notifier_chain, event, NULL);
+	rcu_read_lock();
+	ret = raw_notifier_call_chain(&cpu_pm_notifier.chain, event, NULL);
+	rcu_read_unlock();
 	rcu_irq_exit_irqson();
 
 	return notifier_to_errno(ret);
 }
 
 static int cpu_pm_notify_robust(enum cpu_pm_event event_up, enum cpu_pm_event event_down)
 {
+	unsigned long flags;
 	int ret;
 
 	rcu_irq_enter_irqson();
-	ret = atomic_notifier_call_chain_robust(&cpu_pm_notifier_chain, event_up, event_down, NULL);
+	raw_spin_lock_irqsave(&cpu_pm_notifier.lock, flags);
+	ret = raw_notifier_call_chain_robust(&cpu_pm_notifier.chain, event_up, event_down, NULL);
+	raw_spin_unlock_irqrestore(&cpu_pm_notifier.lock, flags);
 	rcu_irq_exit_irqson();
 
 	return notifier_to_errno(ret);
@@ -49,12 +65,17 @@ static int cpu_pm_notify_robust(enum cpu_pm_event event_up, enum cpu_pm_event ev
  * Add a driver to a list of drivers that are notified about
  * CPU and CPU cluster low power entry and exit.
  *
- * This function may sleep, and has the same return conditions as
- * raw_notifier_chain_register.
+ * This function has the same return conditions as raw_notifier_chain_register.
  */
 int cpu_pm_register_notifier(struct notifier_block *nb)
 {
-	return atomic_notifier_chain_register(&cpu_pm_notifier_chain, nb);
+	unsigned long flags;
+	int ret;
+
+	raw_spin_lock_irqsave(&cpu_pm_notifier.lock, flags);
+	ret = raw_notifier_chain_register(&cpu_pm_notifier.chain, nb);
+	raw_spin_unlock_irqrestore(&cpu_pm_notifier.lock, flags);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(cpu_pm_register_notifier);
 
@@ -64,12 +85,17 @@ EXPORT_SYMBOL_GPL(cpu_pm_register_notifier);
  *
  * Remove a driver from the CPU PM notifier list.
  *
- * This function may sleep, and has the same return conditions as
- * raw_notifier_chain_unregister.
+ * This function has the same return conditions as raw_notifier_chain_unregister.
  */
 int cpu_pm_unregister_notifier(struct notifier_block *nb)
 {
-	return atomic_notifier_chain_unregister(&cpu_pm_notifier_chain, nb);
+	unsigned long flags;
+	int ret;
+
+	raw_spin_lock_irqsave(&cpu_pm_notifier.lock, flags);
+	ret = raw_notifier_chain_unregister(&cpu_pm_notifier.chain, nb);
+	raw_spin_unlock_irqrestore(&cpu_pm_notifier.lock, flags);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(cpu_pm_unregister_notifier);