[PATCH v4] driver core: Add timeout for device shutdown

[Soumya Khasnis]

The device shutdown callbacks invoked during shutdown/reboot
are prone to errors depending on the device state or mishandling
by one or more driver. In order to prevent a device hang in such
scenarios, we bail out after a timeout while dumping a meaningful
call trace of the shutdown callback to kernel logs, which blocks
the shutdown or reboot process.

Signed-off-by: Soumya Khasnis <soumya.khasnis@xxxxxxxx>
Signed-off-by: Srinavasa Nagaraju <Srinavasa.Nagaraju@xxxxxxxx>
---
Changes v3:
  - fix review comments
 1. added help text  
 2. set configuration by default "y"
 3. added range for timeout value(DEVICE_SHUTDOWN_TIMEOUT_SEC)
 4. moved #define's to base.h file
 5. moved timeout functionality to device_shutdown() driver/base/core.c from reboot.c
  - updated commit message 
 1. added information of where call trace is logged.
 2. changed patch subject from "reboot:" to "driver core:"

Changes v4:
 1. set configuration by default "n"
 2. removed range for timeout value(DEVICE_SHUTDOWN_TIMEOUT_SEC)

 drivers/base/Kconfig | 17 +++++++++++++++++
 drivers/base/base.h  |  8 ++++++++
 drivers/base/core.c  | 40 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 65 insertions(+)

diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index 2b8fd6bb7da0..4e1d1efb4937 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -243,3 +243,20 @@ config FW_DEVLINK_SYNC_STATE_TIMEOUT
 	  work on.
 
 endmenu
+
+config DEVICE_SHUTDOWN_TIMEOUT
+	bool "device shutdown timeout"
+	default n
+	help
+	   Enable timeout for device shutdown. In case of device shutdown is
+	   broken or device is not responding, system shutdown or restart may hang.
+	   This timeout handles such situation and triggers emergency_restart or
+	   machine_power_off. Also dumps call trace of shutdown process.
+
+
+config DEVICE_SHUTDOWN_TIMEOUT_SEC
+	int "device shutdown timeout in seconds"
+	default 10
+	depends on DEVICE_SHUTDOWN_TIMEOUT
+	help
+	  sets time for device shutdown timeout in seconds
diff --git a/drivers/base/base.h b/drivers/base/base.h
index 0738ccad08b2..97eea57a8868 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -243,3 +243,11 @@ static inline int devtmpfs_delete_node(struct device *dev) { return 0; }
 
 void software_node_notify(struct device *dev);
 void software_node_notify_remove(struct device *dev);
+
+#ifdef CONFIG_DEVICE_SHUTDOWN_TIMEOUT
+struct device_shutdown_timeout {
+	struct timer_list timer;
+	struct task_struct *task;
+};
+#define SHUTDOWN_TIMEOUT CONFIG_DEVICE_SHUTDOWN_TIMEOUT_SEC
+#endif
diff --git a/drivers/base/core.c b/drivers/base/core.c
index b93f3c5716ae..dab455054a80 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -35,6 +35,12 @@
 #include "base.h"
 #include "physical_location.h"
 #include "power/power.h"
+#include <linux/sched/debug.h>
+#include <linux/reboot.h>
+
+#ifdef CONFIG_DEVICE_SHUTDOWN_TIMEOUT
+struct device_shutdown_timeout devs_shutdown;
+#endif
 
 /* Device links support. */
 static LIST_HEAD(deferred_sync);
@@ -4799,6 +4805,38 @@ int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid)
 }
 EXPORT_SYMBOL_GPL(device_change_owner);
 
+#ifdef CONFIG_DEVICE_SHUTDOWN_TIMEOUT
+static void device_shutdown_timeout_handler(struct timer_list *t)
+{
+	pr_emerg("**** device shutdown timeout ****\n");
+	show_stack(devs_shutdown.task, NULL, KERN_EMERG);
+	if (system_state == SYSTEM_RESTART)
+		emergency_restart();
+	else
+		machine_power_off();
+}
+
+static void device_shutdown_timer_set(void)
+{
+	devs_shutdown.task = current;
+	timer_setup(&devs_shutdown.timer, device_shutdown_timeout_handler, 0);
+	devs_shutdown.timer.expires = jiffies + SHUTDOWN_TIMEOUT * HZ;
+	add_timer(&devs_shutdown.timer);
+}
+
+static void device_shutdown_timer_clr(void)
+{
+	del_timer(&devs_shutdown.timer);
+}
+#else
+static inline void device_shutdown_timer_set(void)
+{
+}
+static inline void device_shutdown_timer_clr(void)
+{
+}
+#endif
+
 /**
  * device_shutdown - call ->shutdown() on each device to shutdown.
  */
@@ -4810,6 +4848,7 @@ void device_shutdown(void)
 	device_block_probing();
 
 	cpufreq_suspend();
+	device_shutdown_timer_set();
 
 	spin_lock(&devices_kset->list_lock);
 	/*
@@ -4869,6 +4908,7 @@ void device_shutdown(void)
 		spin_lock(&devices_kset->list_lock);
 	}
 	spin_unlock(&devices_kset->list_lock);
+	device_shutdown_timer_clr();
 }
 
 /*
-- 
2.40.0