hrtimer: Tune hrtimer_interrupt hang logic

The hrtimer_interrupt hang logic adjusts min_delta_ns based on the
execution time of the hrtimer callbacks.

This is error-prone for virtual machines, where a guest vcpu can be
scheduled out during the execution of the callbacks (and the callbacks
themselves can do operations that translate to blocking operations in
the hypervisor), which in can lead to large min_delta_ns rendering the
system unusable.

Replace the current heuristics with something more reliable. Allow the
interrupt code to try 3 times to catch up with the lost time. If that
fails use the total time spent in the interrupt handler to defer the
next timer interrupt so the system can catch up with other things
which got delayed. Limit that deferment to 100ms.

The retry events and the maximum time spent in the interrupt handler
are recorded and exposed via /proc/timer_list

Inspired by a patch from Marcelo.

Reported-by: Michael Tokarev <mjt@tls.msk.ru>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Marcelo Tosatti <mtosatti@redhat.com>
Cc: kvm@vger.kernel.org

1 files changed, 9 insertions, 4 deletions

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 9bace4b9f4fe9..040b6796ab4d4 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -162,10 +162,11 @@ struct hrtimer_clock_base {
  * @expires_next:	absolute time of the next event which was scheduled
  *			via clock_set_next_event()
  * @hres_active:	State of high resolution mode
- * @check_clocks:	Indictator, when set evaluate time source and clock
- *			event devices whether high resolution mode can be
- *			activated.
- * @nr_events:		Total number of timer interrupt events
+ * @hang_detected:	The last hrtimer interrupt detected a hang
+ * @nr_events:		Total number of hrtimer interrupt events
+ * @nr_retries:		Total number of hrtimer interrupt retries
+ * @nr_hangs:		Total number of hrtimer interrupt hangs
+ * @max_hang_time:	Maximum time spent in hrtimer_interrupt
  */
 struct hrtimer_cpu_base {
 	spinlock_t			lock;
@@ -173,7 +174,11 @@ struct hrtimer_cpu_base {
 #ifdef CONFIG_HIGH_RES_TIMERS
 	ktime_t				expires_next;
 	int				hres_active;
+	int				hang_detected;
 	unsigned long			nr_events;
+	unsigned long			nr_retries;
+	unsigned long			nr_hangs;
+	ktime_t				max_hang_time;
 #endif
 };