ntp: Fix leap-second hrtimer livelock

Since commit 7dffa3c673fbcf835cd7be80bb4aec8ad3f51168 the ntp
subsystem has used an hrtimer for triggering the leapsecond
adjustment. However, this can cause a potential livelock.

Thomas diagnosed this as the following pattern:
CPU 0                                                    CPU 1
do_adjtimex()
  spin_lock_irq(&ntp_lock);
    process_adjtimex_modes();				 timer_interrupt()
      process_adj_status();                                do_timer()
        ntp_start_leap_timer();                             write_lock(&xtime_lock);
          hrtimer_start();                                  update_wall_time();
             hrtimer_reprogram();                            ntp_tick_length()
               tick_program_event()                            spin_lock(&ntp_lock);
                 clockevents_program_event()
		   ktime_get()
                     seq = req_seqbegin(xtime_lock);

This patch tries to avoid the problem by reverting back to not using
an hrtimer to inject leapseconds, and instead we handle the leapsecond
processing in the second_overflow() function.

The downside to this change is that on systems that support highres
timers, the leap second processing will occur on a HZ tick boundary,
(ie: ~1-10ms, depending on HZ)  after the leap second instead of
possibly sooner (~34us in my tests w/ x86_64 lapic).

This patch applies on top of tip/timers/core.

CC: Sasha Levin <levinsasha928@gmail.com>
CC: Thomas Gleixner <tglx@linutronix.de>
Reported-by: Sasha Levin <levinsasha928@gmail.com>
Diagnoised-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Sasha Levin <levinsasha928@gmail.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>

1 files changed, 6 insertions, 14 deletions

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index b53da5ecbea2..5d76e09ddd3d 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -184,18 +184,6 @@ static void timekeeping_update(bool clearntp)
 }
 
 
-void timekeeping_leap_insert(int leapsecond)
-{
-	unsigned long flags;
-
-	write_seqlock_irqsave(&timekeeper.lock, flags);
-	timekeeper.xtime.tv_sec += leapsecond;
-	timekeeper.wall_to_monotonic.tv_sec -= leapsecond;
-	timekeeping_update(false);
-	write_sequnlock_irqrestore(&timekeeper.lock, flags);
-
-}
-
 /**
  * timekeeping_forward_now - update clock to the current time
  *
@@ -969,9 +957,11 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
 
 	timekeeper.xtime_nsec += timekeeper.xtime_interval << shift;
 	while (timekeeper.xtime_nsec >= nsecps) {
+		int leap;
 		timekeeper.xtime_nsec -= nsecps;
 		timekeeper.xtime.tv_sec++;
-		second_overflow();
+		leap = second_overflow(timekeeper.xtime.tv_sec);
+		timekeeper.xtime.tv_sec += leap;
 	}
 
 	/* Accumulate raw time */
@@ -1082,9 +1072,11 @@ static void update_wall_time(void)
 	 * xtime.tv_nsec isn't larger then NSEC_PER_SEC
 	 */
 	if (unlikely(timekeeper.xtime.tv_nsec >= NSEC_PER_SEC)) {
+		int leap;
 		timekeeper.xtime.tv_nsec -= NSEC_PER_SEC;
 		timekeeper.xtime.tv_sec++;
-		second_overflow();
+		leap = second_overflow(timekeeper.xtime.tv_sec);
+		timekeeper.xtime.tv_sec += leap;
 	}
 
 	timekeeping_update(false);