From 70fea60d888d472ac044910fd0dc46b304419705 Mon Sep 17 00:00:00 2001 From: Benoit Goby Date: Thu, 17 Oct 2013 10:48:46 -0700 Subject: PM / Sleep: Detect device suspend/resume lockup and log event Rather than hard-lock the kernel, dump the suspend/resume thread stack and panic() to capture a message in pstore when a driver takes too long to suspend/resume. Default suspend/resume watchdog timeout is set to 12 seconds to be longer than the usbhid 10 second timeout, but could be changed at compile time. Exclude from the watchdog the time spent waiting for children that are resumed asynchronously and time every device, whether or not they resumed synchronously. This patch is targeted for mobile devices where a suspend/resume lockup could cause a system reboot. Information about failing device can be retrieved in subsequent boot session by mounting pstore and inspecting the log. Laptops with EFI-enabled pstore could also benefit from this feature. The hardware watchdog timer is likely suspended during this time and couldn't be relied upon. The soft-lockup detector would eventually tell that tasks are not scheduled, but would provide little context as to why. The patch hence uses system timer and assumes it is still active while the devices are suspended/resumed. This feature can be enabled/disabled during kernel configuration. This change is based on earlier work by San Mehat. Signed-off-by: Benoit Goby Signed-off-by: Zoran Markovic Acked-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- drivers/base/power/main.c | 73 +++++++++++++++++++++++++++++++++++++++++++++++ kernel/power/Kconfig | 16 +++++++++++ 2 files changed, 89 insertions(+) diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 9f098a8..ee039af 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -30,6 +30,8 @@ #include #include #include +#include + #include "../base.h" #include "power.h" @@ -390,6 +392,71 @@ static int dpm_run_callback(pm_callback_t cb, struct device *dev, return error; } +#ifdef CONFIG_DPM_WATCHDOG +struct dpm_watchdog { + struct device *dev; + struct task_struct *tsk; + struct timer_list timer; +}; + +#define DECLARE_DPM_WATCHDOG_ON_STACK(wd) \ + struct dpm_watchdog wd + +/** + * dpm_watchdog_handler - Driver suspend / resume watchdog handler. + * @data: Watchdog object address. + * + * Called when a driver has timed out suspending or resuming. + * There's not much we can do here to recover so panic() to + * capture a crash-dump in pstore. + */ +static void dpm_watchdog_handler(unsigned long data) +{ + struct dpm_watchdog *wd = (void *)data; + + dev_emerg(wd->dev, "**** DPM device timeout ****\n"); + show_stack(wd->tsk, NULL); + panic("%s %s: unrecoverable failure\n", + dev_driver_string(wd->dev), dev_name(wd->dev)); +} + +/** + * dpm_watchdog_set - Enable pm watchdog for given device. + * @wd: Watchdog. Must be allocated on the stack. + * @dev: Device to handle. + */ +static void dpm_watchdog_set(struct dpm_watchdog *wd, struct device *dev) +{ + struct timer_list *timer = &wd->timer; + + wd->dev = dev; + wd->tsk = current; + + init_timer_on_stack(timer); + /* use same timeout value for both suspend and resume */ + timer->expires = jiffies + HZ * CONFIG_DPM_WATCHDOG_TIMEOUT; + timer->function = dpm_watchdog_handler; + timer->data = (unsigned long)wd; + add_timer(timer); +} + +/** + * dpm_watchdog_clear - Disable suspend/resume watchdog. + * @wd: Watchdog to disable. + */ +static void dpm_watchdog_clear(struct dpm_watchdog *wd) +{ + struct timer_list *timer = &wd->timer; + + del_timer_sync(timer); + destroy_timer_on_stack(timer); +} +#else +#define DECLARE_DPM_WATCHDOG_ON_STACK(wd) +#define dpm_watchdog_set(x, y) +#define dpm_watchdog_clear(x) +#endif + /*------------------------- Resume routines -------------------------*/ /** @@ -576,6 +643,7 @@ static int device_resume(struct device *dev, pm_message_t state, bool async) pm_callback_t callback = NULL; char *info = NULL; int error = 0; + DECLARE_DPM_WATCHDOG_ON_STACK(wd); TRACE_DEVICE(dev); TRACE_RESUME(0); @@ -584,6 +652,7 @@ static int device_resume(struct device *dev, pm_message_t state, bool async) goto Complete; dpm_wait(dev->parent, async); + dpm_watchdog_set(&wd, dev); device_lock(dev); /* @@ -642,6 +711,7 @@ static int device_resume(struct device *dev, pm_message_t state, bool async) Unlock: device_unlock(dev); + dpm_watchdog_clear(&wd); Complete: complete_all(&dev->power.completion); @@ -1060,6 +1130,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) pm_callback_t callback = NULL; char *info = NULL; int error = 0; + DECLARE_DPM_WATCHDOG_ON_STACK(wd); dpm_wait_for_children(dev, async); @@ -1083,6 +1154,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) if (dev->power.syscore) goto Complete; + dpm_watchdog_set(&wd, dev); device_lock(dev); if (dev->pm_domain) { @@ -1139,6 +1211,7 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async) } device_unlock(dev); + dpm_watchdog_clear(&wd); Complete: complete_all(&dev->power.completion); diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index d444c4e..2fac9cc 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -178,6 +178,22 @@ config PM_SLEEP_DEBUG def_bool y depends on PM_DEBUG && PM_SLEEP +config DPM_WATCHDOG + bool "Device suspend/resume watchdog" + depends on PM_DEBUG && PSTORE + ---help--- + Sets up a watchdog timer to capture drivers that are + locked up attempting to suspend/resume a device. + A detected lockup causes system panic with message + captured in pstore device for inspection in subsequent + boot session. + +config DPM_WATCHDOG_TIMEOUT + int "Watchdog timeout in seconds" + range 1 120 + default 12 + depends on DPM_WATCHDOG + config PM_TRACE bool help -- cgit v1.1 From 7bc9b1cffc95675a957e870d258e95d43dcbba0b Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 18 Oct 2013 22:20:40 +0200 Subject: PM / Hibernate: Use bool for boolean fields of struct snapshot_data The snapshot_data structure used internally by the hibernate user space interface code in user.c has three char fields that are used to store boolean values. Change their data type to bool and use true and false instead of 1 and 0, respectively, in assignments involving those fields. Signed-off-by: Rafael J. Wysocki --- kernel/power/user.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/kernel/power/user.c b/kernel/power/user.c index 957f061..2485027 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -36,9 +36,9 @@ static struct snapshot_data { struct snapshot_handle handle; int swap; int mode; - char frozen; - char ready; - char platform_support; + bool frozen; + bool ready; + bool platform_support; bool free_bitmaps; } snapshot_state; @@ -93,9 +93,9 @@ static int snapshot_open(struct inode *inode, struct file *filp) if (error) atomic_inc(&snapshot_device_available); - data->frozen = 0; - data->ready = 0; - data->platform_support = 0; + data->frozen = false; + data->ready = false; + data->platform_support = false; Unlock: unlock_system_sleep(); @@ -229,7 +229,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, if (error) thaw_processes(); else - data->frozen = 1; + data->frozen = true; break; @@ -240,7 +240,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, free_basic_memory_bitmaps(); data->free_bitmaps = false; thaw_processes(); - data->frozen = 0; + data->frozen = false; break; case SNAPSHOT_CREATE_IMAGE: @@ -270,7 +270,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, case SNAPSHOT_FREE: swsusp_free(); memset(&data->handle, 0, sizeof(struct snapshot_handle)); - data->ready = 0; + data->ready = false; /* * It is necessary to thaw kernel threads here, because * SNAPSHOT_CREATE_IMAGE may be invoked directly after @@ -334,7 +334,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, * PM_HIBERNATION_PREPARE */ error = suspend_devices_and_enter(PM_SUSPEND_MEM); - data->ready = 0; + data->ready = false; break; case SNAPSHOT_PLATFORM_SUPPORT: -- cgit v1.1