diff mbox series

[RESEND,v10,02/11] reboot: Add hardware protection power-off

Message ID e83ec1ca9408f90c857ea9dcdc57b14d9037b03f.1622628333.git.matti.vaittinen@fi.rohmeurope.com
State Accepted
Commit dfa19b11385d4cf8f0242fd93e2073e25183c331
Headers show
Series Extend regulator notification support | expand

Commit Message

Vaittinen, Matti June 3, 2021, 5:40 a.m. UTC
There can be few cases when we need to shut-down the system in order to
protect the hardware. Currently this is done at least by the thermal core
when temperature raises over certain limit.

Some PMICs can also generate interrupts for example for over-current or
over-voltage, voltage drops, short-circuit, ... etc. On some systems
these are a sign of hardware failure and only thing to do is try to
protect the rest of the hardware by shutting down the system.

Add shut-down logic which can be used by all subsystems instead of
implementing the shutdown in each subsystem. The logic is stolen from
thermal_core with difference of using atomic_t instead of a mutex in
order to allow calls directly from IRQ context and changing the WARN()
to pr_emerg() as discussed here:
https://lore.kernel.org/lkml/YJuPwAZroVZ%2Fw633@alley/
and here:
https://lore.kernel.org/linux-iommu/20210331093104.383705-4-geert+renesas@glider.be/

Signed-off-by: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>

---

Changelog:
v10: (changes suggested by Petr Mladek and Geert)
 - replace WARN() by pr_emerg()
v8: (changes suggested by Daniel Lezcano)
 - replace a protection implemented by a flag + spin_lock_irqsave() with
   simple atomic_dec_and_test().
 - Split thermal-core changes and adding the new API to separate patches
v7:
 - New patch
---
 include/linux/reboot.h |  1 +
 kernel/reboot.c        | 79 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 80 insertions(+)

Comments

Daniel Lezcano June 18, 2021, 8:25 a.m. UTC | #1
On 03/06/2021 07:40, Matti Vaittinen wrote:
> There can be few cases when we need to shut-down the system in order to
> protect the hardware. Currently this is done at least by the thermal core
> when temperature raises over certain limit.
> 
> Some PMICs can also generate interrupts for example for over-current or
> over-voltage, voltage drops, short-circuit, ... etc. On some systems
> these are a sign of hardware failure and only thing to do is try to
> protect the rest of the hardware by shutting down the system.
> 
> Add shut-down logic which can be used by all subsystems instead of
> implementing the shutdown in each subsystem. The logic is stolen from
> thermal_core with difference of using atomic_t instead of a mutex in
> order to allow calls directly from IRQ context and changing the WARN()
> to pr_emerg() as discussed here:
> https://lore.kernel.org/lkml/YJuPwAZroVZ%2Fw633@alley/
> and here:
> https://lore.kernel.org/linux-iommu/20210331093104.383705-4-geert+renesas@glider.be/
> 
> Signed-off-by: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>

Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
diff mbox series

Patch

diff --git a/include/linux/reboot.h b/include/linux/reboot.h
index 3734cd8f38a8..af907a3d68d1 100644
--- a/include/linux/reboot.h
+++ b/include/linux/reboot.h
@@ -79,6 +79,7 @@  extern char poweroff_cmd[POWEROFF_CMD_PATH_LEN];
 
 extern void orderly_poweroff(bool force);
 extern void orderly_reboot(void);
+void hw_protection_shutdown(const char *reason, int ms_until_forced);
 
 /*
  * Emergency restart, callable from an interrupt handler.
diff --git a/kernel/reboot.c b/kernel/reboot.c
index a6ad5eb2fa73..f7440c0c7e43 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -7,6 +7,7 @@ 
 
 #define pr_fmt(fmt)	"reboot: " fmt
 
+#include <linux/atomic.h>
 #include <linux/ctype.h>
 #include <linux/export.h>
 #include <linux/kexec.h>
@@ -518,6 +519,84 @@  void orderly_reboot(void)
 }
 EXPORT_SYMBOL_GPL(orderly_reboot);
 
+/**
+ * hw_failure_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 hw_failure_emergency_poweroff_func(struct work_struct *work)
+{
+	/*
+	 * We have reached here after the emergency 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
+	 */
+	pr_emerg("Hardware protection timed-out. Trying forced poweroff\n");
+	kernel_power_off();
+
+	/*
+	 * Worst of the worst case trigger emergency restart
+	 */
+	pr_emerg("Hardware protection shutdown failed. Trying emergency restart\n");
+	emergency_restart();
+}
+
+static DECLARE_DELAYED_WORK(hw_failure_emergency_poweroff_work,
+			    hw_failure_emergency_poweroff_func);
+
+/**
+ * hw_failure_emergency_poweroff - Trigger an emergency system poweroff
+ *
+ * This may be called from any critical situation to trigger a system shutdown
+ * after a given period of time. If time is negative this is not scheduled.
+ */
+static void hw_failure_emergency_poweroff(int poweroff_delay_ms)
+{
+	if (poweroff_delay_ms <= 0)
+		return;
+	schedule_delayed_work(&hw_failure_emergency_poweroff_work,
+			      msecs_to_jiffies(poweroff_delay_ms));
+}
+
+/**
+ * hw_protection_shutdown - Trigger an emergency system poweroff
+ *
+ * @reason:		Reason of emergency shutdown to be printed.
+ * @ms_until_forced:	Time to wait for orderly shutdown before tiggering a
+ *			forced shudown. Negative value disables the forced
+ *			shutdown.
+ *
+ * Initiate an emergency system shutdown in order to protect hardware from
+ * further damage. Usage examples include a thermal protection or a voltage or
+ * current regulator failures.
+ * NOTE: The request is ignored if protection shutdown is already pending even
+ * if the previous request has given a large timeout for forced shutdown.
+ * Can be called from any context.
+ */
+void hw_protection_shutdown(const char *reason, int ms_until_forced)
+{
+	static atomic_t allow_proceed = ATOMIC_INIT(1);
+
+	pr_emerg("HARDWARE PROTECTION shutdown (%s)\n", reason);
+
+	/* Shutdown should be initiated only once. */
+	if (!atomic_dec_and_test(&allow_proceed))
+		return;
+
+	/*
+	 * Queue a backup emergency shutdown in the event of
+	 * orderly_poweroff failure
+	 */
+	hw_failure_emergency_poweroff(ms_until_forced);
+	orderly_poweroff(true);
+}
+EXPORT_SYMBOL_GPL(hw_protection_shutdown);
+
 static int __init reboot_setup(char *str)
 {
 	for (;;) {