1 files changed, 54 insertions, 4 deletions

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 48bf267d090d..95c399f94744 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -288,6 +288,28 @@ static int __thermal_zone_device_set_mode(struct thermal_zone_device *tz,
 	return 0;
 }
 
+static void thermal_zone_broken_disable(struct thermal_zone_device *tz)
+{
+	struct thermal_trip_desc *td;
+
+	dev_err(&tz->device, "Unable to get temperature, disabling!\n");
+	/*
+	 * This function only runs for enabled thermal zones, so no need to
+	 * check for the current mode.
+	 */
+	__thermal_zone_device_set_mode(tz, THERMAL_DEVICE_DISABLED);
+	thermal_notify_tz_disable(tz);
+
+	for_each_trip_desc(tz, td) {
+		if (td->trip.type == THERMAL_TRIP_CRITICAL &&
+		    td->trip.temperature > THERMAL_TEMP_INVALID) {
+			dev_crit(&tz->device,
+				 "Disabled thermal zone with critical trip point\n");
+			return;
+		}
+	}
+}
+
 /*
  * Zone update section: main control loop applied to each zone while monitoring
  * in polling mode. The monitoring is done using a workqueue.
@@ -308,6 +330,34 @@ static void thermal_zone_device_set_polling(struct thermal_zone_device *tz,
 		cancel_delayed_work(&tz->poll_queue);
 }
 
+static void thermal_zone_recheck(struct thermal_zone_device *tz, int error)
+{
+	if (error == -EAGAIN) {
+		thermal_zone_device_set_polling(tz, THERMAL_RECHECK_DELAY);
+		return;
+	}
+
+	/*
+	 * Print the message once to reduce log noise.  It will be followed by
+	 * another one if the temperature cannot be determined after multiple
+	 * attempts.
+	 */
+	if (tz->recheck_delay_jiffies == THERMAL_RECHECK_DELAY)
+		dev_info(&tz->device, "Temperature check failed (%d)\n", error);
+
+	thermal_zone_device_set_polling(tz, tz->recheck_delay_jiffies);
+
+	tz->recheck_delay_jiffies += max(tz->recheck_delay_jiffies >> 1, 1ULL);
+	if (tz->recheck_delay_jiffies > THERMAL_MAX_RECHECK_DELAY) {
+		thermal_zone_broken_disable(tz);
+		/*
+		 * Restore the original recheck delay value to allow the thermal
+		 * zone to try to recover when it is reenabled by user space.
+		 */
+		tz->recheck_delay_jiffies = THERMAL_RECHECK_DELAY;
+	}
+}
+
 static void monitor_thermal_zone(struct thermal_zone_device *tz)
 {
 	if (tz->mode != THERMAL_DEVICE_ENABLED)
@@ -507,10 +557,7 @@ void __thermal_zone_device_update(struct thermal_zone_device *tz,
 
 	ret = __thermal_zone_get_temp(tz, &temp);
 	if (ret) {
-		if (ret != -EAGAIN)
-			dev_info(&tz->device, "Temperature check failed (%d)\n", ret);
-
-		thermal_zone_device_set_polling(tz, msecs_to_jiffies(THERMAL_RECHECK_DELAY_MS));
+		thermal_zone_recheck(tz, ret);
 		return;
 	} else if (temp <= THERMAL_TEMP_INVALID) {
 		/*
@@ -522,6 +569,8 @@ void __thermal_zone_device_update(struct thermal_zone_device *tz,
 		goto monitor;
 	}
 
+	tz->recheck_delay_jiffies = THERMAL_RECHECK_DELAY;
+
 	tz->last_temperature = tz->temperature;
 	tz->temperature = temp;
 
@@ -1462,6 +1511,7 @@ thermal_zone_device_register_with_trips(const char *type,
 
 	thermal_set_delay_jiffies(&tz->passive_delay_jiffies, passive_delay);
 	thermal_set_delay_jiffies(&tz->polling_delay_jiffies, polling_delay);
+	tz->recheck_delay_jiffies = THERMAL_RECHECK_DELAY;
 
 	/* sys I/F */
 	/* Add nodes that are always present via .groups */