drivers: power: Add watchdog timer to catch drivers which lockup during suspend.

Rather than hard-lock the kernel, dump the suspend thread stack and
BUG() when a driver takes too long to suspend.  The timeout is set
to 12 seconds to be longer than the usbhid 10 second timeout.

Exclude from the watchdog the time spent waiting for children that
are resumed asynchronously and time every device, whether or not they
resumed synchronously.

Change-Id: Ifd211c06b104860c2fee6eecfe0d61774aa4508a
Original-author: San Mehat <san@google.com>
Signed-off-by: Benoit Goby <benoit@android.com>

diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 1710c26ba097d363873dfd8318ff1d949aeb4a86..df539322d9f5a2197a0371847f802f62af4ce3a0 100644 (file)
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -59,6 +59,12 @@ struct suspend_stats suspend_stats;
 static DEFINE_MUTEX(dpm_list_mtx);
 static pm_message_t pm_transition;
 
+static void dpm_drv_timeout(unsigned long data);
+struct dpm_drv_wd_data {
+       struct device *dev;
+       struct task_struct *tsk;
+};
+
 static int async_error;
 
 static char *pm_verb(int event)
@@ -829,6 +835,30 @@ static void async_resume(void *data, async_cookie_t cookie)
        put_device(dev);
 }
 
+/**
+ *     dpm_drv_timeout - Driver suspend / resume watchdog handler
+ *     @data: struct device which timed out
+ *
+ *     Called when a driver has timed out suspending or resuming.
+ *     There's not much we can do here to recover so
+ *     BUG() out for a crash-dump
+ *
+ */
+static void dpm_drv_timeout(unsigned long data)
+{
+       struct dpm_drv_wd_data *wd_data = (void *)data;
+       struct device *dev = wd_data->dev;
+       struct task_struct *tsk = wd_data->tsk;
+
+       printk(KERN_EMERG "**** DPM device timeout: %s (%s)\n", dev_name(dev),
+              (dev->driver ? dev->driver->name : "no driver"));
+
+       printk(KERN_EMERG "dpm suspend stack:\n");
+       show_stack(tsk, NULL);
+
+       BUG();
+}
+
 /**
  * dpm_resume - Execute "resume" callbacks for non-sysdev devices.
  * @state: PM transition of the system being carried out.
@@ -1347,6 +1377,8 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
        pm_callback_t callback = NULL;
        char *info = NULL;
        int error = 0;
+       struct timer_list timer;
+       struct dpm_drv_wd_data data;
        DECLARE_DPM_WATCHDOG_ON_STACK(wd);
 
        TRACE_DEVICE(dev);
@@ -1373,6 +1405,14 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 
        if (dev->power.syscore)
                goto Complete;
+       
+       data.dev = dev;
+       data.tsk = get_current();
+       init_timer_on_stack(&timer);
+       timer.expires = jiffies + HZ * 12;
+       timer.function = dpm_drv_timeout;
+       timer.data = (unsigned long)&data;
+       add_timer(&timer);
 
        if (dev->power.direct_complete) {
                if (pm_runtime_status_suspended(dev)) {
@@ -1453,6 +1493,9 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
        device_unlock(dev);
        dpm_watchdog_clear(&wd);
 
+       del_timer_sync(&timer);
+       destroy_timer_on_stack(&timer);
+
  Complete:
        complete_all(&dev->power.completion);
        if (error)