linux-kernel - [PATCH v3 11/12] thermal: core: allow user configuration of hardware protection action

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20250217-hw_protection-reboot-v3-11-e1c09b090c0c@pengutronix.de>
Date: Mon, 17 Feb 2025 21:39:51 +0100
From: Ahmad Fatoum <a.fatoum@...gutronix.de>
To: Andrew Morton <akpm@...ux-foundation.org>, 
 Daniel Lezcano <daniel.lezcano@...aro.org>, 
 Fabio Estevam <festevam@...x.de>, "Rafael J. Wysocki" <rafael@...nel.org>, 
 Zhang Rui <rui.zhang@...el.com>, Lukasz Luba <lukasz.luba@....com>, 
 Jonathan Corbet <corbet@....net>, Serge Hallyn <serge@...lyn.com>, 
 Liam Girdwood <lgirdwood@...il.com>, Mark Brown <broonie@...nel.org>, 
 Matti Vaittinen <mazziesaccount@...il.com>, 
 Benson Leung <bleung@...omium.org>, Tzung-Bi Shih <tzungbi@...nel.org>, 
 Guenter Roeck <groeck@...omium.org>, Rob Herring <robh@...nel.org>, 
 Krzysztof Kozlowski <krzk+dt@...nel.org>, 
 Conor Dooley <conor+dt@...nel.org>
Cc: linux-kernel@...r.kernel.org, linux-pm@...r.kernel.org, 
 linux-doc@...r.kernel.org, linux-security-module@...r.kernel.org, 
 chrome-platform@...ts.linux.dev, devicetree@...r.kernel.org, 
 kernel@...gutronix.de, Ahmad Fatoum <a.fatoum@...gutronix.de>
Subject: [PATCH v3 11/12] thermal: core: allow user configuration of
 hardware protection action

In the general case, we don't know which of system shutdown or
reboot is the better action to take to protect hardware in an emergency
situation. We thus allow the policy to come from the device-tree in the
form of an optional critical-action OF property, but so far there was no
way for the end user to configure this.

With recent addition of the hw_protection parameter, the user can now
choose a default action for the case, where the driver isn't fully sure
what's the better course of action.

Let's make use of this by passing HWPROT_ACT_DEFAULT in absence of the
critical-action OF property.

As HWPROT_ACT_DEFAULT is shutdown by default, this introduces no
functional change for users, unless they start using the new parameter.

Reviewed-by: Tzung-Bi Shih <tzungbi@...nel.org>
Signed-off-by: Ahmad Fatoum <a.fatoum@...gutronix.de>
---
 drivers/thermal/thermal_core.c | 17 ++++++++++-------
 drivers/thermal/thermal_core.h |  1 +
 drivers/thermal/thermal_of.c   |  7 +++++--
 3 files changed, 16 insertions(+), 9 deletions(-)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 2328ac0d8561b1d051a0dea6d7565c145d584cbb..5847729419f2e02e3367ad39553440defe702d59 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -369,7 +369,8 @@ void thermal_governor_update_tz(struct thermal_zone_device *tz,
 	tz->governor->update_tz(tz, reason);
 }

-static void thermal_zone_device_halt(struct thermal_zone_device *tz, bool shutdown)
+static void thermal_zone_device_halt(struct thermal_zone_device *tz,
+				     enum hw_protection_action action)
 {
 	/*
 	 * poweroff_delay_ms must be a carefully profiled positive value.
@@ -380,21 +381,23 @@ static void thermal_zone_device_halt(struct thermal_zone_device *tz, bool shutdo

 	dev_emerg(&tz->device, "%s: critical temperature reached\n", tz->type);

-	if (shutdown)
-		hw_protection_shutdown(msg, poweroff_delay_ms);
-	else
-		hw_protection_reboot(msg, poweroff_delay_ms);
+	__hw_protection_trigger(msg, poweroff_delay_ms, action);
 }

 void thermal_zone_device_critical(struct thermal_zone_device *tz)
 {
-	thermal_zone_device_halt(tz, true);
+	thermal_zone_device_halt(tz, HWPROT_ACT_DEFAULT);
 }
 EXPORT_SYMBOL(thermal_zone_device_critical);

+void thermal_zone_device_critical_shutdown(struct thermal_zone_device *tz)
+{
+	thermal_zone_device_halt(tz, HWPROT_ACT_SHUTDOWN);
+}
+
 void thermal_zone_device_critical_reboot(struct thermal_zone_device *tz)
 {
-	thermal_zone_device_halt(tz, false);
+	thermal_zone_device_halt(tz, HWPROT_ACT_REBOOT);
 }

 static void handle_critical_trips(struct thermal_zone_device *tz,
diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
index 09866f0ce76585d4c7f2322ee62030fc1af9afc2..bdadd141aa24cf3c0afaf8d4c274e62bd796a4e9 100644
--- a/drivers/thermal/thermal_core.h
+++ b/drivers/thermal/thermal_core.h
@@ -262,6 +262,7 @@ int thermal_build_list_of_policies(char *buf);
 void __thermal_zone_device_update(struct thermal_zone_device *tz,
 				  enum thermal_notify_event event);
 void thermal_zone_device_critical_reboot(struct thermal_zone_device *tz);
+void thermal_zone_device_critical_shutdown(struct thermal_zone_device *tz);
 void thermal_governor_update_tz(struct thermal_zone_device *tz,
 				enum thermal_notify_event reason);

diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c
index 5ab4ce4daaebdf0210d9b318ae17b3eb8a4bccaf..0eb92d57a1e2d5170754ee04c86e85634f10acc1 100644
--- a/drivers/thermal/thermal_of.c
+++ b/drivers/thermal/thermal_of.c
@@ -397,9 +397,12 @@ static struct thermal_zone_device *thermal_of_zone_register(struct device_node *
 	of_ops.should_bind = thermal_of_should_bind;

 	ret = of_property_read_string(np, "critical-action", &action);
-	if (!ret)
-		if (!of_ops.critical && !strcasecmp(action, "reboot"))
+	if (!ret && !of_ops.critical) {
+		if (!strcasecmp(action, "reboot"))
 			of_ops.critical = thermal_zone_device_critical_reboot;
+		else if (!strcasecmp(action, "shutdown"))
+			of_ops.critical = thermal_zone_device_critical_shutdown;
+	}

 	tz = thermal_zone_device_register_with_trips(np->name, trips, ntrips,
 						     data, &of_ops, &tzp,

-- 
2.39.5