hrtimers: increase clock min delta threshold while interrupt hanging

Impact: avoid timer IRQ hanging slow systems

While using the function graph tracer on a virtualized system, the
hrtimer_interrupt can hang the system on an infinite loop.

This can be caused in several situations:

 - the hardware is very slow and HZ is set too high

 - something intrusive is slowing the system down (tracing under emulation)

... and the next clock events to program are always before the current time.

This patch implements a reasonable compromise: if such a situation is
detected, we share the CPUs time in 1/4 to process the hrtimer interrupts.
This is enough to let the system running without serious starvation.

It has been successfully tested under VirtualBox with 1000 HZ and 100 HZ
with function graph tracer launched. On both cases, the clock events were
increased until about 25 ms periodic ticks, which means 40 HZ.

So we change a hard to debug hang into a warning message and a system that
still manages to limp along.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index bda9cb92427673a4c2e47676596e854d57d7dca3..c2a69b89ac6190c8be46e8677b42ad055c9fa748 100644 (file)
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1171,6 +1171,29 @@ static void __run_hrtimer(struct hrtimer *timer)
 
 #ifdef CONFIG_HIGH_RES_TIMERS
 
+static int force_clock_reprogram;
+
+/*
+ * After 5 iteration's attempts, we consider that hrtimer_interrupt()
+ * is hanging, which could happen with something that slows the interrupt
+ * such as the tracing. Then we force the clock reprogramming for each future
+ * hrtimer interrupts to avoid infinite loops and use the min_delta_ns
+ * threshold that we will overwrite.
+ * The next tick event will be scheduled to 3 times we currently spend on
+ * hrtimer_interrupt(). This gives a good compromise, the cpus will spend
+ * 1/4 of their time to process the hrtimer interrupts. This is enough to
+ * let it running without serious starvation.
+ */
+
+static inline void
+hrtimer_interrupt_hanging(struct clock_event_device *dev,
+                       ktime_t try_time)
+{
+       force_clock_reprogram = 1;
+       dev->min_delta_ns = (unsigned long)try_time.tv64 * 3;
+       printk(KERN_WARNING "hrtimer: interrupt too slow, "
+               "forcing clock min delta to %lu ns\n", dev->min_delta_ns);
+}
 /*
  * High resolution timer interrupt
  * Called with interrupts disabled
@@ -1180,6 +1203,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
        struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
        struct hrtimer_clock_base *base;
        ktime_t expires_next, now;
+       int nr_retries = 0;
        int i;
 
        BUG_ON(!cpu_base->hres_active);
@@ -1187,6 +1211,10 @@ void hrtimer_interrupt(struct clock_event_device *dev)
        dev->next_event.tv64 = KTIME_MAX;
 
  retry:
+       /* 5 retries is enough to notice a hang */
+       if (!(++nr_retries % 5))
+               hrtimer_interrupt_hanging(dev, ktime_sub(ktime_get(), now));
+
        now = ktime_get();
 
        expires_next.tv64 = KTIME_MAX;
@@ -1239,7 +1267,7 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 
        /* Reprogramming necessary ? */
        if (expires_next.tv64 != KTIME_MAX) {
-               if (tick_program_event(expires_next, 0))
+               if (tick_program_event(expires_next, force_clock_reprogram))
                        goto retry;
        }
 }