1 files changed, 99 insertions, 35 deletions

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 8795187fbc52..95c399f94744 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -272,6 +272,44 @@ static int __init thermal_register_governors(void)
 	return ret;
 }
 
+static int __thermal_zone_device_set_mode(struct thermal_zone_device *tz,
+					  enum thermal_device_mode mode)
+{
+	if (tz->ops.change_mode) {
+		int ret;
+
+		ret = tz->ops.change_mode(tz, mode);
+		if (ret)
+			return ret;
+	}
+
+	tz->mode = mode;
+
+	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.
@@ -292,6 +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)
@@ -300,8 +366,6 @@ static void monitor_thermal_zone(struct thermal_zone_device *tz)
 		thermal_zone_device_set_polling(tz, tz->passive_delay_jiffies);
 	else if (tz->polling_delay_jiffies)
 		thermal_zone_device_set_polling(tz, tz->polling_delay_jiffies);
-	else if (tz->temperature == THERMAL_TEMP_INVALID)
-		thermal_zone_device_set_polling(tz, msecs_to_jiffies(THERMAL_RECHECK_DELAY_MS));
 }
 
 static struct thermal_governor *thermal_get_tz_governor(struct thermal_zone_device *tz)
@@ -382,7 +446,7 @@ static void handle_thermal_trip(struct thermal_zone_device *tz,
 	td->threshold = trip->temperature;
 
 	if (tz->last_temperature >= old_threshold &&
-	    tz->last_temperature != THERMAL_TEMP_INVALID) {
+	    tz->last_temperature != THERMAL_TEMP_INIT) {
 		/*
 		 * Mitigation is under way, so it needs to stop if the zone
 		 * temperature falls below the low temperature of the trip.
@@ -417,27 +481,6 @@ static void handle_thermal_trip(struct thermal_zone_device *tz,
 	}
 }
 
-static void update_temperature(struct thermal_zone_device *tz)
-{
-	int temp, ret;
-
-	ret = __thermal_zone_get_temp(tz, &temp);
-	if (ret) {
-		if (ret != -EAGAIN)
-			dev_warn(&tz->device,
-				 "failed to read out thermal zone (%d)\n",
-				 ret);
-		return;
-	}
-
-	tz->last_temperature = tz->temperature;
-	tz->temperature = temp;
-
-	trace_thermal_temperature(tz);
-
-	thermal_genl_sampling_temp(tz->id, temp);
-}
-
 static void thermal_zone_device_check(struct work_struct *work)
 {
 	struct thermal_zone_device *tz = container_of(work, struct
@@ -452,7 +495,7 @@ static void thermal_zone_device_init(struct thermal_zone_device *tz)
 
 	INIT_DELAYED_WORK(&tz->poll_queue, thermal_zone_device_check);
 
-	tz->temperature = THERMAL_TEMP_INVALID;
+	tz->temperature = THERMAL_TEMP_INIT;
 	tz->passive = 0;
 	tz->prev_low_trip = -INT_MAX;
 	tz->prev_high_trip = INT_MAX;
@@ -504,6 +547,7 @@ void __thermal_zone_device_update(struct thermal_zone_device *tz,
 	struct thermal_trip_desc *td;
 	LIST_HEAD(way_down_list);
 	LIST_HEAD(way_up_list);
+	int temp, ret;
 
 	if (tz->suspended)
 		return;
@@ -511,10 +555,28 @@ void __thermal_zone_device_update(struct thermal_zone_device *tz,
 	if (!thermal_zone_device_is_enabled(tz))
 		return;
 
-	update_temperature(tz);
-
-	if (tz->temperature == THERMAL_TEMP_INVALID)
+	ret = __thermal_zone_get_temp(tz, &temp);
+	if (ret) {
+		thermal_zone_recheck(tz, ret);
+		return;
+	} else if (temp <= THERMAL_TEMP_INVALID) {
+		/*
+		 * Special case: No valid temperature value is available, but
+		 * the zone owner does not want the core to do anything about
+		 * it.  Continue regular zone polling if needed, so that this
+		 * function can be called again, but skip everything else.
+		 */
 		goto monitor;
+	}
+
+	tz->recheck_delay_jiffies = THERMAL_RECHECK_DELAY;
+
+	tz->last_temperature = tz->temperature;
+	tz->temperature = temp;
+
+	trace_thermal_temperature(tz);
+
+	thermal_genl_sampling_temp(tz->id, temp);
 
 	tz->notify_event = event;
 
@@ -543,7 +605,7 @@ monitor:
 static int thermal_zone_device_set_mode(struct thermal_zone_device *tz,
 					enum thermal_device_mode mode)
 {
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&tz->lock);
 
@@ -551,14 +613,15 @@ static int thermal_zone_device_set_mode(struct thermal_zone_device *tz,
 	if (mode == tz->mode) {
 		mutex_unlock(&tz->lock);
 
-		return ret;
+		return 0;
 	}
 
-	if (tz->ops.change_mode)
-		ret = tz->ops.change_mode(tz, mode);
+	ret = __thermal_zone_device_set_mode(tz, mode);
+	if (ret) {
+		mutex_unlock(&tz->lock);
 
-	if (!ret)
-		tz->mode = mode;
+		return ret;
+	}
 
 	__thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
 
@@ -569,7 +632,7 @@ static int thermal_zone_device_set_mode(struct thermal_zone_device *tz,
 	else
 		thermal_notify_tz_disable(tz);
 
-	return ret;
+	return 0;
 }
 
 int thermal_zone_device_enable(struct thermal_zone_device *tz)
@@ -1448,6 +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 */