thermal: core: Add a back up thermal shutdown mechanism

orderly_poweroff is triggered when a graceful shutdown
of system is desired. This may be used in many critical states of the
kernel such as when subsystems detects conditions such as critical
temperature conditions. However, in certain conditions in system
boot up sequences like those in the middle of driver probes being
initiated, userspace will be unable to power off the system in a clean
manner and leaves the system in a critical state. In cases like these,
the /sbin/poweroff will return success (having forked off to attempt
powering off the system. However, the system overall will fail to
completely poweroff (since other modules will be probed) and the system
is still functional with no userspace (since that would have shut itself
off).

However, there is no clean way of detecting such failure of userspace
powering off the system. In such scenarios, it is necessary for a backup
workqueue to be able to force a shutdown of the system when orderly
shutdown is not successful after a configurable time period.

Reported-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Keerthy <j-keerthy@ti.com>
Acked-by: Eduardo Valentin <edubezval@gmail.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>

1 files changed, 53 insertions, 0 deletions

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 8337c272d3ec..b21b9cc2c8d6 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -324,6 +324,54 @@ static void handle_non_critical_trips(struct thermal_zone_device *tz,
 		       def_governor->throttle(tz, trip);
 }
 
+/**
+ * thermal_emergency_poweroff_func - emergency poweroff work after a known delay
+ * @work: work_struct associated with the emergency poweroff function
+ *
+ * This function is called in very critical situations to force
+ * a kernel poweroff after a configurable timeout value.
+ */
+static void thermal_emergency_poweroff_func(struct work_struct *work)
+{
+	/*
+	 * We have reached here after the emergency thermal shutdown
+	 * Waiting period has expired. This means orderly_poweroff has
+	 * not been able to shut off the system for some reason.
+	 * Try to shut down the system immediately using kernel_power_off
+	 * if populated
+	 */
+	WARN(1, "Attempting kernel_power_off: Temperature too high\n");
+	kernel_power_off();
+
+	/*
+	 * Worst of the worst case trigger emergency restart
+	 */
+	WARN(1, "Attempting emergency_restart: Temperature too high\n");
+	emergency_restart();
+}
+
+static DECLARE_DELAYED_WORK(thermal_emergency_poweroff_work,
+			    thermal_emergency_poweroff_func);
+
+/**
+ * thermal_emergency_poweroff - Trigger an emergency system poweroff
+ *
+ * This may be called from any critical situation to trigger a system shutdown
+ * after a known period of time. By default this is not scheduled.
+ */
+void thermal_emergency_poweroff(void)
+{
+	int poweroff_delay_ms = CONFIG_THERMAL_EMERGENCY_POWEROFF_DELAY_MS;
+	/*
+	 * poweroff_delay_ms must be a carefully profiled positive value.
+	 * Its a must for thermal_emergency_poweroff_work to be scheduled
+	 */
+	if (poweroff_delay_ms <= 0)
+		return;
+	schedule_delayed_work(&thermal_emergency_poweroff_work,
+			      msecs_to_jiffies(poweroff_delay_ms));
+}
+
 static void handle_critical_trips(struct thermal_zone_device *tz,
 				  int trip, enum thermal_trip_type trip_type)
 {
@@ -346,6 +394,11 @@ static void handle_critical_trips(struct thermal_zone_device *tz,
 			  tz->temperature / 1000);
 		mutex_lock(&poweroff_lock);
 		if (!power_off_triggered) {
+			/*
+			 * Queue a backup emergency shutdown in the event of
+			 * orderly_poweroff failure
+			 */
+			thermal_emergency_poweroff();
 			orderly_poweroff(true);
 			power_off_triggered = true;
 		}