notifier: Fix broken error handling pattern

The current notifiers have the following error handling pattern all
over the place:

	int err, nr;

	err = __foo_notifier_call_chain(&chain, val_up, v, -1, &nr);
	if (err & NOTIFIER_STOP_MASK)
		__foo_notifier_call_chain(&chain, val_down, v, nr-1, NULL)

And aside from the endless repetition thereof, it is broken. Consider
blocking notifiers; both calls take and drop the rwsem, this means
that the notifier list can change in between the two calls, making @nr
meaningless.

Fix this by replacing all the __foo_notifier_call_chain() functions
with foo_notifier_call_chain_robust() that embeds the above pattern,
but ensures it is inside a single lock region.

Note: I switched atomic_notifier_call_chain_robust() to use
      the spinlock, since RCU cannot provide the guarantee
      required for the recovery.

Note: software_resume() error handling was broken afaict.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/20200818135804.325626653@infradead.org

1 files changed, 18 insertions, 30 deletions

diff --git a/kernel/cpu_pm.c b/kernel/cpu_pm.c
index 44a259338e33..f7e1d0eccdbc 100644
--- a/kernel/cpu_pm.c
+++ b/kernel/cpu_pm.c
@@ -15,18 +15,28 @@
 
 static ATOMIC_NOTIFIER_HEAD(cpu_pm_notifier_chain);
 
-static int cpu_pm_notify(enum cpu_pm_event event, int nr_to_call, int *nr_calls)
+static int cpu_pm_notify(enum cpu_pm_event event)
 {
 	int ret;
 
 	/*
-	 * __atomic_notifier_call_chain has a RCU read critical section, which
+	 * 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.
 	 */
 	rcu_irq_enter_irqson();
-	ret = __atomic_notifier_call_chain(&cpu_pm_notifier_chain, event, NULL,
-		nr_to_call, nr_calls);
+	ret = atomic_notifier_call_chain(&cpu_pm_notifier_chain, event, NULL);
+	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)
+{
+	int ret;
+
+	rcu_irq_enter_irqson();
+	ret = atomic_notifier_call_chain_robust(&cpu_pm_notifier_chain, event_up, event_down, NULL);
 	rcu_irq_exit_irqson();
 
 	return notifier_to_errno(ret);
@@ -80,18 +90,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_unregister_notifier);
  */
 int cpu_pm_enter(void)
 {
-	int nr_calls = 0;
-	int ret = 0;
-
-	ret = cpu_pm_notify(CPU_PM_ENTER, -1, &nr_calls);
-	if (ret)
-		/*
-		 * Inform listeners (nr_calls - 1) about failure of CPU PM
-		 * PM entry who are notified earlier to prepare for it.
-		 */
-		cpu_pm_notify(CPU_PM_ENTER_FAILED, nr_calls - 1, NULL);
-
-	return ret;
+	return cpu_pm_notify_robust(CPU_PM_ENTER, CPU_PM_ENTER_FAILED);
 }
 EXPORT_SYMBOL_GPL(cpu_pm_enter);
 
@@ -109,7 +108,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_enter);
  */
 int cpu_pm_exit(void)
 {
-	return cpu_pm_notify(CPU_PM_EXIT, -1, NULL);
+	return cpu_pm_notify(CPU_PM_EXIT);
 }
 EXPORT_SYMBOL_GPL(cpu_pm_exit);
 
@@ -131,18 +130,7 @@ EXPORT_SYMBOL_GPL(cpu_pm_exit);
  */
 int cpu_cluster_pm_enter(void)
 {
-	int nr_calls = 0;
-	int ret = 0;
-
-	ret = cpu_pm_notify(CPU_CLUSTER_PM_ENTER, -1, &nr_calls);
-	if (ret)
-		/*
-		 * Inform listeners (nr_calls - 1) about failure of CPU cluster
-		 * PM entry who are notified earlier to prepare for it.
-		 */
-		cpu_pm_notify(CPU_CLUSTER_PM_ENTER_FAILED, nr_calls - 1, NULL);
-
-	return ret;
+	return cpu_pm_notify_robust(CPU_CLUSTER_PM_ENTER, CPU_CLUSTER_PM_ENTER_FAILED);
 }
 EXPORT_SYMBOL_GPL(cpu_cluster_pm_enter);
 
@@ -163,7 +151,7 @@ EXPORT_SYMBOL_GPL(cpu_cluster_pm_enter);
  */
 int cpu_cluster_pm_exit(void)
 {
-	return cpu_pm_notify(CPU_CLUSTER_PM_EXIT, -1, NULL);
+	return cpu_pm_notify(CPU_CLUSTER_PM_EXIT);
 }
 EXPORT_SYMBOL_GPL(cpu_cluster_pm_exit);