Merge tag 'thermal-7.0-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull thermal control fixes from Rafael Wysocki:
 "Address potential races between thermal zone removal and system
  resume that may lead to a use-after-free (in two different ways)
  and a potential use-after-free in the thermal zone unregistration
  path (Rafael Wysocki)"

* tag 'thermal-7.0-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  thermal: core: Fix thermal zone device registration error path
  thermal: core: Address thermal zone removal races with resume

Author: torvalds

drivers/thermal/thermal_core.c

@@ -41,6 +41,8 @@ static struct thermal_governor *def_governor;
 
 static bool thermal_pm_suspended;
 
+static struct workqueue_struct *thermal_wq __ro_after_init;
+
 /*
  * Governor section: set of functions to handle thermal governors
  *
@@ -313,7 +315,7 @@ static void thermal_zone_device_set_polling(struct thermal_zone_device *tz,
 	if (delay > HZ)
 		delay = round_jiffies_relative(delay);
 
-	mod_delayed_work(system_freezable_power_efficient_wq, &tz->poll_queue, delay);
+	mod_delayed_work(thermal_wq, &tz->poll_queue, delay);
 }
 
 static void thermal_zone_recheck(struct thermal_zone_device *tz, int error)
@@ -1640,6 +1642,7 @@ thermal_zone_device_register_with_trips(const char *type,
 	device_del(&tz->device);
 release_device:
 	put_device(&tz->device);
+	wait_for_completion(&tz->removal);
 remove_id:
 	ida_free(&thermal_tz_ida, id);
 free_tzp:
@@ -1785,6 +1788,10 @@ static void thermal_zone_device_resume(struct work_struct *work)
 
 	guard(thermal_zone)(tz);
 
+	/* If the thermal zone is going away, there's nothing to do. */
+	if (tz->state & TZ_STATE_FLAG_EXIT)
+		return;
+
 	tz->state &= ~(TZ_STATE_FLAG_SUSPENDED | TZ_STATE_FLAG_RESUMING);
 
 	thermal_debug_tz_resume(tz);
@@ -1811,6 +1818,9 @@ static void thermal_zone_pm_prepare(struct thermal_zone_device *tz)
 	}
 
 	tz->state |= TZ_STATE_FLAG_SUSPENDED;
+
+	/* Prevent new work from getting to the workqueue subsequently. */
+	cancel_delayed_work(&tz->poll_queue);
 }
 
 static void thermal_pm_notify_prepare(void)
@@ -1829,8 +1839,6 @@ static void thermal_zone_pm_complete(struct thermal_zone_device *tz)
 {
 	guard(thermal_zone)(tz);
 
-	cancel_delayed_work(&tz->poll_queue);
-
 	reinit_completion(&tz->resume);
 	tz->state |= TZ_STATE_FLAG_RESUMING;
 
@@ -1840,7 +1848,7 @@ static void thermal_zone_pm_complete(struct thermal_zone_device *tz)
 	 */
 	INIT_DELAYED_WORK(&tz->poll_queue, thermal_zone_device_resume);
 	/* Queue up the work without a delay. */
-	mod_delayed_work(system_freezable_power_efficient_wq, &tz->poll_queue, 0);
+	mod_delayed_work(thermal_wq, &tz->poll_queue, 0);
 }
 
 static void thermal_pm_notify_complete(void)
@@ -1863,6 +1871,11 @@ static int thermal_pm_notify(struct notifier_block *nb,
 	case PM_RESTORE_PREPARE:
 	case PM_SUSPEND_PREPARE:
 		thermal_pm_notify_prepare();
+		/*
+		 * Allow any leftover thermal work items already on the
+		 * worqueue to complete so they don't get in the way later.
+		 */
+		flush_workqueue(thermal_wq);
 		break;
 	case PM_POST_HIBERNATION:
 	case PM_POST_RESTORE:
@@ -1895,9 +1908,16 @@ static int __init thermal_init(void)
 	if (result)
 		goto error;
 
+	thermal_wq = alloc_workqueue("thermal_events",
+				      WQ_FREEZABLE | WQ_POWER_EFFICIENT | WQ_PERCPU, 0);
+	if (!thermal_wq) {
+		result = -ENOMEM;
+		goto unregister_netlink;
+	}
+
 	result = thermal_register_governors();
 	if (result)
-		goto unregister_netlink;
+		goto destroy_workqueue;
 
 	thermal_class = kzalloc_obj(*thermal_class);
 	if (!thermal_class) {
@@ -1924,6 +1944,8 @@ static int __init thermal_init(void)
 
 unregister_governors:
 	thermal_unregister_governors();
+destroy_workqueue:
+	destroy_workqueue(thermal_wq);
 unregister_netlink:
 	thermal_netlink_exit();
 error: