3 files changed, 28 insertions, 14 deletions

diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 64522ecdfe0e..162b03ab0ad2 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -33,6 +33,21 @@ DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
  */
 ktime_t tick_next_period;
 ktime_t tick_period;
+
+/*
+ * tick_do_timer_cpu is a timer core internal variable which holds the CPU NR
+ * which is responsible for calling do_timer(), i.e. the timekeeping stuff. This
+ * variable has two functions:
+ *
+ * 1) Prevent a thundering herd issue of a gazillion of CPUs trying to grab the
+ *    timekeeping lock all at once. Only the CPU which is assigned to do the
+ *    update is handling it.
+ *
+ * 2) Hand off the duty in the NOHZ idle case by setting the value to
+ *    TICK_DO_TIMER_NONE, i.e. a non existing CPU. So the next cpu which looks
+ *    at it will take over and keep the time keeping alive.  The handover
+ *    procedure also covers cpu hotplug.
+ */
 int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
 
 /*
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 2afd43fca93b..52cee12b3302 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -361,8 +361,8 @@ void __init tick_nohz_init(void)
 /*
  * NO HZ enabled ?
  */
-int tick_nohz_enabled __read_mostly  = 1;
-
+static int tick_nohz_enabled __read_mostly  = 1;
+int tick_nohz_active  __read_mostly;
 /*
  * Enable / Disable tickless mode
  */
@@ -461,7 +461,7 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
         struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
         ktime_t now, idle;
 
-        if (!tick_nohz_enabled)
+        if (!tick_nohz_active)
                 return -1;
 
         now = ktime_get();
@@ -502,7 +502,7 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
         struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
         ktime_t now, iowait;
 
-        if (!tick_nohz_enabled)
+        if (!tick_nohz_active)
                 return -1;
 
         now = ktime_get();
@@ -707,8 +707,10 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
                 return false;
         }
 
-        if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
+        if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) {
+                ts->sleep_length = (ktime_t) { .tv64 = NSEC_PER_SEC/HZ };
                 return false;
+        }
 
         if (need_resched())
                 return false;
@@ -795,11 +797,6 @@ void tick_nohz_idle_enter(void)
         local_irq_disable();
 
         ts = &__get_cpu_var(tick_cpu_sched);
-        /*
-         * set ts->inidle unconditionally. even if the system did not
-         * switch to nohz mode the cpu frequency governers rely on the
-         * update of the idle time accounting in tick_nohz_start_idle().
-         */
         ts->inidle = 1;
         __tick_nohz_idle_enter(ts);
 
@@ -968,7 +965,7 @@ static void tick_nohz_switch_to_nohz(void)
         struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
         ktime_t next;
 
-        if (!tick_nohz_enabled)
+        if (!tick_nohz_active)
                 return;
 
         local_irq_disable();
@@ -976,7 +973,7 @@ static void tick_nohz_switch_to_nohz(void)
                 local_irq_enable();
                 return;
         }
-
+        tick_nohz_active = 1;
         ts->nohz_mode = NOHZ_MODE_LOWRES;
 
         /*
@@ -1132,8 +1129,10 @@ void tick_setup_sched_timer(void)
         }
 
 #ifdef CONFIG_NO_HZ_COMMON
-        if (tick_nohz_enabled)
+        if (tick_nohz_enabled) {
                 ts->nohz_mode = NOHZ_MODE_HIGHRES;
+                tick_nohz_active = 1;
+        }
 #endif
 }
 #endif /* HIGH_RES_TIMERS */
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 3abf53418b67..87b4f00284c9 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1347,7 +1347,7 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk)
         tk->xtime_nsec -= remainder;
         tk->xtime_nsec += 1ULL << tk->shift;
         tk->ntp_error += remainder << tk->ntp_error_shift;
-
+        tk->ntp_error -= (1ULL << tk->shift) << tk->ntp_error_shift;
 }
 #else
 #define old_vsyscall_fixup(tk)