hung_task: add method to reset detector

In certain occasions it is possible for a hung task detector
positive to be false: continuation from a paused VM, for example.

Add a method to reset detection, similar as is done
with other kernel watchdogs.

Acked-by: Don Zickus <dzickus@redhat.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>

diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 6279928..2f355d2 100644 (file)
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -48,6 +48,7 @@ void pvclock_touch_watchdogs(void)
        touch_softlockup_watchdog_sync();
        clocksource_touch_watchdog();
        rcu_cpu_stall_reset();
+       reset_hung_task_detector();
 }
 
 static atomic64_t last_value = ATOMIC64_INIT(0);

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6682da3..7bb4b4a 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -285,6 +285,14 @@ static inline void lockup_detector_init(void)
 }
 #endif
 
+#ifdef CONFIG_DETECT_HUNG_TASK
+void reset_hung_task_detector(void);
+#else
+static inline void reset_hung_task_detector(void)
+{
+}
+#endif
+
 /* Attach to any functions which should be ignored in wchan output. */
 #define __sched                __attribute__((__section__(".sched.text")))
 

diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 3e97fb1..dfdf515 100644 (file)
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -203,6 +203,14 @@ int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
        return ret;
 }
 
+static atomic_t reset_hung_task = ATOMIC_INIT(0);
+
+void reset_hung_task_detector(void)
+{
+       atomic_set(&reset_hung_task, 1);
+}
+EXPORT_SYMBOL_GPL(reset_hung_task_detector);
+
 /*
  * kthread which checks for tasks stuck in D state
  */
@@ -216,6 +224,9 @@ static int watchdog(void *dummy)
                while (schedule_timeout_interruptible(timeout_jiffies(timeout)))
                        timeout = sysctl_hung_task_timeout_secs;
 
+               if (atomic_xchg(&reset_hung_task, 0))
+                       continue;
+
                check_hung_uninterruptible_tasks(timeout);
        }