Linux Virtualization - Apr 2007 - [patch 0/2] softlockup watchdog improvements

Here's couple of patches to improve the softlockup watchdog.

The first changes the softlockup timer from using jiffies to sched_clock()
as a timebase.  Xen and VMI implement sched_clock() as counting unstolen
time, so time stolen by the hypervisor won't cause the watchdog to bite.

The second adds per-cpu enable flags for the watchdog timer.  This allows
the timer to be disabled when the CPU goes into a (potentially unbounded)
tickless sleep.

I know this conflicts with
fix-bogus-softlockup-warning-with-sysrq-t.patch in -mm2.  I think that
patch incorrectly changes the behaviour of the softlockup watchdog,
and a better solution is to temporarily disable the watchdog while
doing something known to be cpu-consuming, like a long sysreq output.

	J
--

On a NO_HZ system, there may be an arbitrarily long delay between
ticks on a CPU.  When we're disabling ticks for a CPU, also disable
the softlockup watchdog timer.

Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: john stultz <johnstul@us.ibm.com>
Cc: Zachary Amsden <zach@vmware.com>
Cc: James Morris <jmorris@namei.org>
Cc: Dan Hecht <dhecht@vmware.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>

---
 include/linux/sched.h    |    8 ++++++++
 kernel/softlockup.c      |   23 +++++++++++++++++++----
 kernel/time/tick-sched.c |   34 +++++++++++++++-------------------
 3 files changed, 42 insertions(+), 23 deletions(-)

==================================================================---
a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -232,10 +232,18 @@ extern void scheduler_tick(void);
 
 #ifdef CONFIG_DETECT_SOFTLOCKUP
 extern void softlockup_tick(void);
+extern void softlockup_enable(void);
+extern void softlockup_disable(void);
 extern void spawn_softlockup_task(void);
 extern void touch_softlockup_watchdog(void);
 #else
 static inline void softlockup_tick(void)
+{
+}
+static inline void softlockup_enable(void)
+{
+}
+static inline void softlockup_disable(void)
 {
 }
 static inline void spawn_softlockup_task(void)
==================================================================---
a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -20,6 +20,7 @@ static DEFINE_PER_CPU(unsigned long long
 static DEFINE_PER_CPU(unsigned long long, touch_timestamp);
 static DEFINE_PER_CPU(unsigned long long, print_timestamp);
 static DEFINE_PER_CPU(struct task_struct *, watchdog_task);
+static DEFINE_PER_CPU(int, enabled);
 
 static int did_panic = 0;
 
@@ -41,6 +42,18 @@ void touch_softlockup_watchdog(void)
 }
 EXPORT_SYMBOL(touch_softlockup_watchdog);
 
+void softlockup_enable(void)
+{
+	touch_softlockup_watchdog();
+	wmb();			/* update timestamp before enable */
+	__get_cpu_var(enabled) = 1;
+}
+
+void softlockup_disable(void)
+{
+	__get_cpu_var(enabled) = 0;
+}
+
 /*
  * This callback runs from the timer interrupt, and checks
  * whether the watchdog thread has hung or not:
@@ -51,8 +64,8 @@ void softlockup_tick(void)
 	unsigned long long touch_timestamp = per_cpu(touch_timestamp, this_cpu);
 	unsigned long long now;
 
-	/* watchdog task hasn't updated timestamp yet */
-	if (touch_timestamp == 0)
+	/* return if not enabled */
+	if (!__get_cpu_var(enabled))
 		return;
 
 	/* report at most once a second */
@@ -95,8 +108,8 @@ static int watchdog(void * __bind_cpu)
 	sched_setscheduler(current, SCHED_FIFO, &param);
 	current->flags |= PF_NOFREEZE;
 
-	/* initialize timestamp */
-	touch_softlockup_watchdog();
+	/* enable on this cpu */
+	softlockup_enable();
 
 	/*
 	 * Run briefly once per second to reset the softlockup timestamp.
@@ -109,6 +122,8 @@ static int watchdog(void * __bind_cpu)
 		touch_softlockup_watchdog();
 		schedule();
 	}
+
+	softlockup_disable();
 
 	return 0;
 }
==================================================================---
a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -228,6 +228,8 @@ void tick_nohz_stop_sched_tick(void)
 			ts->idle_tick = ts->sched_timer.expires;
 			ts->tick_stopped = 1;
 			ts->idle_jiffies = last_jiffies;
+
+			softlockup_disable();
 		}
 		/*
 		 * calculate the expiry time for the next timer wheel
@@ -255,6 +257,7 @@ void tick_nohz_stop_sched_tick(void)
 		cpu_clear(cpu, nohz_cpu_mask);
 	}
 	raise_softirq_irqoff(TIMER_SOFTIRQ);
+
 out:
 	ts->next_jiffies = next_jiffies;
 	ts->last_jiffies = last_jiffies;
@@ -311,6 +314,8 @@ void tick_nohz_restart_sched_tick(void)
 	ts->tick_stopped  = 0;
 	hrtimer_cancel(&ts->sched_timer);
 	ts->sched_timer.expires = ts->idle_tick;
+
+	softlockup_enable();
 
 	while (1) {
 		/* Forward the time to expire in the future */
@@ -355,17 +360,12 @@ static void tick_nohz_handler(struct clo
 	tick_do_update_jiffies64(now);
 
 	/*
-	 * When we are idle and the tick is stopped, we have to touch
-	 * the watchdog as we might not schedule for a really long
-	 * time. This happens on complete idle SMP systems while
-	 * waiting on the login prompt. We also increment the "start
-	 * of idle" jiffy stamp so the idle accounting adjustment we
-	 * do when we go busy again does not account too much ticks.
-	 */
-	if (ts->tick_stopped) {
-		touch_softlockup_watchdog();
+	 * Increment the "start of idle" jiffy stamp so the idle
+	 * accounting adjustment we do when we go busy again does not
+	 * account too much ticks.
+	 */
+	if (ts->tick_stopped)
 		ts->idle_jiffies++;
-	}
 
 	update_process_times(user_mode(regs));
 	profile_tick(CPU_PROFILING);
@@ -450,17 +450,12 @@ static enum hrtimer_restart tick_sched_t
 	 */
 	if (regs) {
 		/*
-		 * When we are idle and the tick is stopped, we have to touch
-		 * the watchdog as we might not schedule for a really long
-		 * time. This happens on complete idle SMP systems while
-		 * waiting on the login prompt. We also increment the "start of
-		 * idle" jiffy stamp so the idle accounting adjustment we do
-		 * when we go busy again does not account too much ticks.
+		 * Increment the "start of idle" jiffy stamp so the
+		 * idle accounting adjustment we do when we go busy
+		 * again does not account too much ticks.
 		 */
-		if (ts->tick_stopped) {
-			touch_softlockup_watchdog();
+		if (ts->tick_stopped)
 			ts->idle_jiffies++;
-		}
 		/*
 		 * update_process_times() might take tasklist_lock, hence
 		 * drop the base lock. sched-tick hrtimers are per-CPU and
@@ -522,6 +517,7 @@ void tick_cancel_sched_timer(int cpu)
 	if (ts->sched_timer.base)
 		hrtimer_cancel(&ts->sched_timer);
 	ts->tick_stopped = 0;
+	softlockup_enable();
 	ts->nohz_mode = NOHZ_MODE_INACTIVE;
 }
 #endif /* HIGH_RES_TIMERS */

--

The softlockup watchdog is currently a nuisance in a virtual machine,
since the whole system could have the CPU stolen from it for a long
period of time.  While it would be unlikely for a guest domain to be
denied timer interrupts for over 10s, it could happen and any softlockup
message would be completely spurious.

Earlier I proposed that sched_clock() return time in unstolen
nanoseconds, which is how Xen and VMI currently implement it.  If the
softlockup watchdog uses sched_clock() to measure time, it would
automatically ignore stolen time, and therefore only report when the
guest itself locked up.  When running native, sched_clock() returns
real-time nanoseconds, so the behaviour would be unchanged.

Note that sched_clock() used this way is inherently per-cpu, so this
patch makes sure that the per-processor watchdog thread initialized
its own timestamp.

Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: john stultz <johnstul@us.ibm.com>
Cc: Zachary Amsden <zach@vmware.com>
Cc: James Morris <jmorris@namei.org>
Cc: Dan Hecht <dhecht@vmware.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Chris Lalancette <clalance@redhat.com>
Cc: Rick Lindsley <ricklind@us.ibm.com>

---
 kernel/softlockup.c |   28 +++++++++++++++++++---------
 1 file changed, 19 insertions(+), 9 deletions(-)

==================================================================---
a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -17,8 +17,8 @@
 
 static DEFINE_SPINLOCK(print_lock);
 
-static DEFINE_PER_CPU(unsigned long, touch_timestamp);
-static DEFINE_PER_CPU(unsigned long, print_timestamp);
+static DEFINE_PER_CPU(unsigned long long, touch_timestamp);
+static DEFINE_PER_CPU(unsigned long long, print_timestamp);
 static DEFINE_PER_CPU(struct task_struct *, watchdog_task);
 
 static int did_panic = 0;
@@ -37,7 +37,7 @@ static struct notifier_block panic_block
 
 void touch_softlockup_watchdog(void)
 {
-	__raw_get_cpu_var(touch_timestamp) = jiffies;
+	__raw_get_cpu_var(touch_timestamp) = sched_clock();
 }
 EXPORT_SYMBOL(touch_softlockup_watchdog);
 
@@ -48,10 +48,15 @@ void softlockup_tick(void)
 void softlockup_tick(void)
 {
 	int this_cpu = smp_processor_id();
-	unsigned long touch_timestamp = per_cpu(touch_timestamp, this_cpu);
+	unsigned long long touch_timestamp = per_cpu(touch_timestamp, this_cpu);
+	unsigned long long now;
 
-	/* prevent double reports: */
-	if (per_cpu(print_timestamp, this_cpu) == touch_timestamp ||
+	/* watchdog task hasn't updated timestamp yet */
+	if (touch_timestamp == 0)
+		return;
+
+	/* report at most once a second */
+	if (per_cpu(print_timestamp, this_cpu) < (touch_timestamp + NSEC_PER_SEC)
||
 		did_panic ||
 			!per_cpu(watchdog_task, this_cpu))
 		return;
@@ -62,12 +67,14 @@ void softlockup_tick(void)
 		return;
 	}
 
+	now = sched_clock();
+
 	/* Wake up the high-prio watchdog task every second: */
-	if (time_after(jiffies, touch_timestamp + HZ))
+	if (now > (touch_timestamp + NSEC_PER_SEC))
 		wake_up_process(per_cpu(watchdog_task, this_cpu));
 
 	/* Warn about unreasonable 10+ seconds delays: */
-	if (time_after(jiffies, touch_timestamp + 10*HZ)) {
+	if (now > (touch_timestamp + 10ull*NSEC_PER_SEC)) {
 		per_cpu(print_timestamp, this_cpu) = touch_timestamp;
 
 		spin_lock(&print_lock);
@@ -87,6 +94,9 @@ static int watchdog(void * __bind_cpu)
 
 	sched_setscheduler(current, SCHED_FIFO, &param);
 	current->flags |= PF_NOFREEZE;
+
+	/* initialize timestamp */
+	touch_softlockup_watchdog();
 
 	/*
 	 * Run briefly once per second to reset the softlockup timestamp.
@@ -120,7 +130,7 @@ cpu_callback(struct notifier_block *nfb,
 			printk("watchdog for %i failed\n", hotcpu);
 			return NOTIFY_BAD;
 		}
-  		per_cpu(touch_timestamp, hotcpu) = jiffies;
+  		per_cpu(touch_timestamp, hotcpu) = 0;
   		per_cpu(watchdog_task, hotcpu) = p;
 		kthread_bind(p, hotcpu);
  		break;

--