3 files changed, 123 insertions, 20 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 835b6c6fcc56..f6cd60f2de63 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1558,13 +1558,28 @@ static inline void sched_clock_idle_sleep_event(void)
 static inline void sched_clock_idle_wakeup_event(u64 delta_ns)
 {
 }
-#else
+
+#ifdef CONFIG_NO_HZ
+static inline void sched_clock_tick_stop(int cpu)
+{
+}
+
+static inline void sched_clock_tick_start(int cpu)
+{
+}
+#endif
+
+#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 extern void sched_clock_init(void);
 extern u64 sched_clock_cpu(int cpu);
 extern void sched_clock_tick(void);
 extern void sched_clock_idle_sleep_event(void);
 extern void sched_clock_idle_wakeup_event(u64 delta_ns);
+#ifdef CONFIG_NO_HZ
+extern void sched_clock_tick_stop(int cpu);
+extern void sched_clock_tick_start(int cpu);
 #endif
+#endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
 /*
  * For kernel-internal use: high-speed (but slightly incorrect) per-cpu
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index 60094e257a9a..22ed55d1167f 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -3,6 +3,9 @@
  *
  *  Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
  *
+ *  Updates and enhancements:
+ *    Copyright (C) 2008 Red Hat, Inc. Steven Rostedt <srostedt@redhat.com>
+ *
  * Based on code by:
  *   Ingo Molnar <mingo@redhat.com>
  *   Guillaume Chazarain <guichaz@gmail.com>
@@ -32,6 +35,11 @@
 
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
 
+#define MULTI_SHIFT 15
+/* Max is double, Min is 1/2 */
+#define MAX_MULTI (2LL << MULTI_SHIFT)
+#define MIN_MULTI (1LL << (MULTI_SHIFT-1))
+
 struct sched_clock_data {
         /*
          * Raw spinlock - this is a special case: this might be called
@@ -40,11 +48,15 @@ struct sched_clock_data {
          */
         raw_spinlock_t          lock;
 
-        unsigned long           prev_jiffies;
+        unsigned long           tick_jiffies;
         u64                     prev_raw;
         u64                     tick_raw;
         u64                     tick_gtod;
         u64                     clock;
+        s64                     multi;
+#ifdef CONFIG_NO_HZ
+        int                     check_max;
+#endif
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
@@ -71,41 +83,91 @@ void sched_clock_init(void)
                 struct sched_clock_data *scd = cpu_sdc(cpu);
 
                 scd->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
-                scd->prev_jiffies = now_jiffies;
+                scd->tick_jiffies = now_jiffies;
                 scd->prev_raw = 0;
                 scd->tick_raw = 0;
                 scd->tick_gtod = ktime_now;
                 scd->clock = ktime_now;
+                scd->multi = 1 << MULTI_SHIFT;
+#ifdef CONFIG_NO_HZ
+                scd->check_max = 1;
+#endif
         }
 
         sched_clock_running = 1;
 }
 
+#ifdef CONFIG_NO_HZ
+/*
+ * The dynamic ticks makes the delta jiffies inaccurate. This
+ * prevents us from checking the maximum time update.
+ * Disable the maximum check during stopped ticks.
+ */
+void sched_clock_tick_stop(int cpu)
+{
+        struct sched_clock_data *scd = cpu_sdc(cpu);
+
+        scd->check_max = 0;
+}
+
+void sched_clock_tick_start(int cpu)
+{
+        struct sched_clock_data *scd = cpu_sdc(cpu);
+
+        scd->check_max = 1;
+}
+
+static int check_max(struct sched_clock_data *scd)
+{
+        return scd->check_max;
+}
+#else
+static int check_max(struct sched_clock_data *scd)
+{
+        return 1;
+}
+#endif /* CONFIG_NO_HZ */
+
 /*
  * update the percpu scd from the raw @now value
  *
  *  - filter out backward motion
  *  - use jiffies to generate a min,max window to clip the raw values
  */
-static void __update_sched_clock(struct sched_clock_data *scd, u64 now)
+static void __update_sched_clock(struct sched_clock_data *scd, u64 now, u64 *time)
 {
         unsigned long now_jiffies = jiffies;
-        long delta_jiffies = now_jiffies - scd->prev_jiffies;
+        long delta_jiffies = now_jiffies - scd->tick_jiffies;
         u64 clock = scd->clock;
         u64 min_clock, max_clock;
         s64 delta = now - scd->prev_raw;
 
         WARN_ON_ONCE(!irqs_disabled());
-        min_clock = scd->tick_gtod + delta_jiffies * TICK_NSEC;
+
+        /*
+         * At schedule tick the clock can be just under the gtod. We don't
+         * want to push it too prematurely.
+         */
+        min_clock = scd->tick_gtod + (delta_jiffies * TICK_NSEC);
+        if (min_clock > TICK_NSEC)
+                min_clock -= TICK_NSEC / 2;
 
         if (unlikely(delta < 0)) {
                 clock++;
                 goto out;
         }
 
-        max_clock = min_clock + TICK_NSEC;
+        /*
+         * The clock must stay within a jiffie of the gtod.
+         * But since we may be at the start of a jiffy or the end of one
+         * we add another jiffy buffer.
+         */
+        max_clock = scd->tick_gtod + (2 + delta_jiffies) * TICK_NSEC;
+
+        delta *= scd->multi;
+        delta >>= MULTI_SHIFT;
 
-        if (unlikely(clock + delta > max_clock)) {
+        if (unlikely(clock + delta > max_clock) && check_max(scd)) {
                 if (clock < max_clock)
                         clock = max_clock;
                 else
@@ -118,9 +180,12 @@ static void __update_sched_clock(struct sched_clock_data *scd, u64 now)
         if (unlikely(clock < min_clock))
                 clock = min_clock;
 
-        scd->prev_raw = now;
-        scd->prev_jiffies = now_jiffies;
-        scd->clock = clock;
+        if (time)
+                *time = clock;
+        else {
+                scd->prev_raw = now;
+                scd->clock = clock;
+        }
 }
 
 static void lock_double_clock(struct sched_clock_data *data1,
@@ -160,25 +225,30 @@ u64 sched_clock_cpu(int cpu)
                 now -= my_scd->tick_raw;
                 now += scd->tick_raw;
 
-                now -= my_scd->tick_gtod;
-                now += scd->tick_gtod;
+                now += my_scd->tick_gtod;
+                now -= scd->tick_gtod;
 
                 __raw_spin_unlock(&my_scd->lock);
+
+                __update_sched_clock(scd, now, &clock);
+
+                __raw_spin_unlock(&scd->lock);
+
         } else {
                 __raw_spin_lock(&scd->lock);
+                __update_sched_clock(scd, now, NULL);
+                clock = scd->clock;
+                __raw_spin_unlock(&scd->lock);
         }
 
-        __update_sched_clock(scd, now);
-        clock = scd->clock;
-
-        __raw_spin_unlock(&scd->lock);
-
         return clock;
 }
 
 void sched_clock_tick(void)
 {
         struct sched_clock_data *scd = this_scd();
+        unsigned long now_jiffies = jiffies;
+        s64 mult, delta_gtod, delta_raw;
         u64 now, now_gtod;
 
         if (unlikely(!sched_clock_running))
@@ -186,18 +256,33 @@ void sched_clock_tick(void)
 
         WARN_ON_ONCE(!irqs_disabled());
 
-        now = sched_clock();
         now_gtod = ktime_to_ns(ktime_get());
+        now = sched_clock();
 
         __raw_spin_lock(&scd->lock);
-        __update_sched_clock(scd, now);
+        __update_sched_clock(scd, now, NULL);
         /*
          * update tick_gtod after __update_sched_clock() because that will
          * already observe 1 new jiffy; adding a new tick_gtod to that would
          * increase the clock 2 jiffies.
          */
+        delta_gtod = now_gtod - scd->tick_gtod;
+        delta_raw = now - scd->tick_raw;
+
+        if ((long)delta_raw > 0) {
+                mult = delta_gtod << MULTI_SHIFT;
+                do_div(mult, delta_raw);
+                scd->multi = mult;
+                if (scd->multi > MAX_MULTI)
+                        scd->multi = MAX_MULTI;
+                else if (scd->multi < MIN_MULTI)
+                        scd->multi = MIN_MULTI;
+        } else
+                scd->multi = 1 << MULTI_SHIFT;
+
         scd->tick_raw = now;
         scd->tick_gtod = now_gtod;
+        scd->tick_jiffies = now_jiffies;
         __raw_spin_unlock(&scd->lock);
 }
 
@@ -227,6 +312,7 @@ void sched_clock_idle_wakeup_event(u64 delta_ns)
         __raw_spin_lock(&scd->lock);
         scd->prev_raw = now;
         scd->clock += delta_ns;
+        scd->multi = 1 << MULTI_SHIFT;
         __raw_spin_unlock(&scd->lock);
 
         touch_softlockup_watchdog();
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index b854a895591e..d63008b09a4c 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -276,6 +276,7 @@ void tick_nohz_stop_sched_tick(void)
                         ts->tick_stopped = 1;
                         ts->idle_jiffies = last_jiffies;
                         rcu_enter_nohz();
+                        sched_clock_tick_stop(cpu);
                 }
 
                 /*
@@ -375,6 +376,7 @@ void tick_nohz_restart_sched_tick(void)
         select_nohz_load_balancer(0);
         now = ktime_get();
         tick_do_update_jiffies64(now);
+        sched_clock_tick_start(cpu);
         cpu_clear(cpu, nohz_cpu_mask);
 
         /*