Message-ID: <3391226.KRKnzuvfpg@kreacher>
Date:   Thu, 14 Jan 2021 19:34:22 +0100
From:   "Rafael J. Wysocki" <rjw@...ysocki.net>
To:     Linux ACPI <linux-acpi@...r.kernel.org>
Cc:     LKML <linux-kernel@...r.kernel.org>,
        Zhang Rui <rui.zhang@...el.com>,
        Linux PM <linux-pm@...r.kernel.org>,
        Stephen Berman <stephen.berman@....net>,
        Sebastian Andrzej Siewior <bigeasy@...utronix.de>
Subject: [PATCH] ACPI: thermal: Do not call acpi_thermal_check() directly

From: Rafael J. Wysocki <rafael.j.wysocki@...el.com>

Calling acpi_thermal_check() from acpi_thermal_notify() directly
is problematic if _TMP triggers Notify () on the thermal zone for
which it has been evaluated (which happens on some systems), because
it causes a new acpi_thermal_notify() invocation to be queued up
every time and if that takes place too often, an indefinite number of
pending work items may accumulate in kacpi_notify_wq over time.

Besides, it is not really useful to queue up a new invocation of
acpi_thermal_check() if one of them is pending already.

For these reasons, rework acpi_thermal_notify() to queue up a thermal
check instead of calling acpi_thermal_check() directly and only allow
one thermal check to be pending at a time.  Moreover, only allow one
acpi_thermal_check_fn() instance at a time to run
thermal_zone_device_update() for one thermal zone and make it return
early if it sees other instances running for the same thermal zone.

While at it, fold acpi_thermal_check() into acpi_thermal_check_fn(),
as it is only called from there after the other changes made here.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=208877
Reported-by: Stephen Berman <stephen.berman@....net> 
Diagnosed-by: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@...el.com>
---
 drivers/acpi/thermal.c |   46 +++++++++++++++++++++++++++++++++-------------
 1 file changed, 33 insertions(+), 13 deletions(-)

Index: linux-pm/drivers/acpi/thermal.c
===================================================================
--- linux-pm.orig/drivers/acpi/thermal.c
+++ linux-pm/drivers/acpi/thermal.c
@@ -174,6 +174,8 @@ struct acpi_thermal {
 	struct thermal_zone_device *thermal_zone;
 	int kelvin_offset;	/* in millidegrees */
 	struct work_struct thermal_check_work;
+	struct mutex thermal_check_lock;
+	refcount_t thermal_check_count;
 };
 
 /* --------------------------------------------------------------------------
@@ -495,14 +497,6 @@ static int acpi_thermal_get_trip_points(
 	return 0;
 }
 
-static void acpi_thermal_check(void *data)
-{
-	struct acpi_thermal *tz = data;
-
-	thermal_zone_device_update(tz->thermal_zone,
-				   THERMAL_EVENT_UNSPECIFIED);
-}
-
 /* sys I/F for generic thermal sysfs support */
 
 static int thermal_get_temp(struct thermal_zone_device *thermal, int *temp)
@@ -900,6 +894,12 @@ static void acpi_thermal_unregister_ther
                                  Driver Interface
    -------------------------------------------------------------------------- */
 
+static void acpi_queue_thermal_check(struct acpi_thermal *tz)
+{
+	if (!work_pending(&tz->thermal_check_work))
+		queue_work(acpi_thermal_pm_queue, &tz->thermal_check_work);
+}
+
 static void acpi_thermal_notify(struct acpi_device *device, u32 event)
 {
 	struct acpi_thermal *tz = acpi_driver_data(device);
@@ -910,17 +910,17 @@ static void acpi_thermal_notify(struct a
 
 	switch (event) {
 	case ACPI_THERMAL_NOTIFY_TEMPERATURE:
-		acpi_thermal_check(tz);
+		acpi_queue_thermal_check(tz);
 		break;
 	case ACPI_THERMAL_NOTIFY_THRESHOLDS:
 		acpi_thermal_trips_update(tz, ACPI_TRIPS_REFRESH_THRESHOLDS);
-		acpi_thermal_check(tz);
+		acpi_queue_thermal_check(tz);
 		acpi_bus_generate_netlink_event(device->pnp.device_class,
 						  dev_name(&device->dev), event, 0);
 		break;
 	case ACPI_THERMAL_NOTIFY_DEVICES:
 		acpi_thermal_trips_update(tz, ACPI_TRIPS_REFRESH_DEVICES);
-		acpi_thermal_check(tz);
+		acpi_queue_thermal_check(tz);
 		acpi_bus_generate_netlink_event(device->pnp.device_class,
 						  dev_name(&device->dev), event, 0);
 		break;
@@ -1020,7 +1020,25 @@ static void acpi_thermal_check_fn(struct
 {
 	struct acpi_thermal *tz = container_of(work, struct acpi_thermal,
 					       thermal_check_work);
-	acpi_thermal_check(tz);
+
+	/*
+	 * In general, it is not sufficient to check the pending bit, because
+	 * subsequent instances of this function may be queued after one of them
+	 * has started running (e.g. if _TMP sleeps).  Avoid bailing out if just
+	 * one of them is running, though, because it may have done the actual
+	 * check some time ago, so allow at least one of them to block on the
+	 * mutex while another one is running the update.
+	 */
+	if (!refcount_dec_not_one(&tz->thermal_check_count))
+		return;
+
+	mutex_lock(&tz->thermal_check_lock);
+
+	thermal_zone_device_update(tz->thermal_zone, THERMAL_EVENT_UNSPECIFIED);
+
+	refcount_inc(&tz->thermal_check_count);
+
+	mutex_unlock(&tz->thermal_check_lock);
 }
 
 static int acpi_thermal_add(struct acpi_device *device)
@@ -1052,6 +1070,8 @@ static int acpi_thermal_add(struct acpi_
 	if (result)
 		goto free_memory;
 
+	refcount_set(&tz->thermal_check_count, 3);
+	mutex_init(&tz->thermal_check_lock);
 	INIT_WORK(&tz->thermal_check_work, acpi_thermal_check_fn);
 
 	pr_info(PREFIX "%s [%s] (%ld C)\n", acpi_device_name(device),
@@ -1117,7 +1137,7 @@ static int acpi_thermal_resume(struct de
 		tz->state.active |= tz->trips.active[i].flags.enabled;
 	}
 
-	queue_work(acpi_thermal_pm_queue, &tz->thermal_check_work);
+	acpi_queue_thermal_check(tz);
 
 	return AE_OK;
 }

Powered by blists - more mailing lists