1 files changed, 71 insertions, 153 deletions

diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index 22ed55d1167..e8ab096ddfe 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -12,19 +12,17 @@
  *
  * Create a semi stable clock from a mixture of other events, including:
  *  - gtod
- *  - jiffies
  *  - sched_clock()
  *  - explicit idle events
  *
  * We use gtod as base and the unstable clock deltas. The deltas are filtered,
- * making it monotonic and keeping it within an expected window.  This window
- * is set up using jiffies.
+ * making it monotonic and keeping it within an expected window.
  *
  * Furthermore, explicit sleep and wakeup hooks allow us to account for time
  * that is otherwise invisible (TSC gets stopped).
  *
  * The clock: sched_clock_cpu() is monotonic per cpu, and should be somewhat
- * consistent between cpus (never more than 1 jiffies difference).
+ * consistent between cpus (never more than 2 jiffies difference).
  */
 #include <linux/sched.h>
 #include <linux/percpu.h>
@@ -32,13 +30,19 @@
 #include <linux/ktime.h>
 #include <linux/module.h>
 
+/*
+ * Scheduler clock - returns current time in nanosec units.
+ * This is default implementation.
+ * Architectures and sub-architectures can override this.
+ */
+unsigned long long __attribute__((weak)) sched_clock(void)
+{
+	return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
+}
 
-#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+static __read_mostly int sched_clock_running;
 
-#define MULTI_SHIFT 15
-/* Max is double, Min is 1/2 */
-#define MAX_MULTI (2LL << MULTI_SHIFT)
-#define MIN_MULTI (1LL << (MULTI_SHIFT-1))
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
 
 struct sched_clock_data {
 	/*
@@ -48,15 +52,9 @@ struct sched_clock_data {
 	 */
 	raw_spinlock_t		lock;
 
-	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);
@@ -71,121 +69,69 @@ static inline struct sched_clock_data *cpu_sdc(int cpu)
 	return &per_cpu(sched_clock_data, cpu);
 }
 
-static __read_mostly int sched_clock_running;
-
 void sched_clock_init(void)
 {
 	u64 ktime_now = ktime_to_ns(ktime_get());
-	unsigned long now_jiffies = jiffies;
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
 		struct sched_clock_data *scd = cpu_sdc(cpu);
 
 		scd->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
-		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.
+ * min,max except they take wrapping into account
  */
-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)
+static inline u64 wrap_min(u64 x, u64 y)
 {
-	struct sched_clock_data *scd = cpu_sdc(cpu);
-
-	scd->check_max = 1;
+	return (s64)(x - y) < 0 ? x : y;
 }
 
-static int check_max(struct sched_clock_data *scd)
+static inline u64 wrap_max(u64 x, u64 y)
 {
-	return scd->check_max;
+	return (s64)(x - y) > 0 ? x : y;
 }
-#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
+ *  - use the GTOD tick value to create a window to filter crazy TSC values
  */
-static void __update_sched_clock(struct sched_clock_data *scd, u64 now, u64 *time)
+static u64 __update_sched_clock(struct sched_clock_data *scd, u64 now)
 {
-	unsigned long now_jiffies = jiffies;
-	long delta_jiffies = now_jiffies - scd->tick_jiffies;
-	u64 clock = scd->clock;
-	u64 min_clock, max_clock;
-	s64 delta = now - scd->prev_raw;
+	s64 delta = now - scd->tick_raw;
+	u64 clock, min_clock, max_clock;
 
 	WARN_ON_ONCE(!irqs_disabled());
 
-	/*
-	 * 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;
-	}
+	if (unlikely(delta < 0))
+		delta = 0;
 
 	/*
-	 * 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.
+	 * scd->clock = clamp(scd->tick_gtod + delta,
+	 * 		      max(scd->tick_gtod, scd->clock),
+	 * 		      scd->tick_gtod + TICK_NSEC);
 	 */
-	max_clock = scd->tick_gtod + (2 + delta_jiffies) * TICK_NSEC;
 
-	delta *= scd->multi;
-	delta >>= MULTI_SHIFT;
+	clock = scd->tick_gtod + delta;
+	min_clock = wrap_max(scd->tick_gtod, scd->clock);
+	max_clock = scd->tick_gtod + TICK_NSEC;
 
-	if (unlikely(clock + delta > max_clock) && check_max(scd)) {
-		if (clock < max_clock)
-			clock = max_clock;
-		else
-			clock++;
-	} else {
-		clock += delta;
-	}
+	clock = wrap_max(clock, min_clock);
+	clock = wrap_min(clock, max_clock);
 
- out:
-	if (unlikely(clock < min_clock))
-		clock = min_clock;
+	scd->clock = clock;
 
-	if (time)
-		*time = clock;
-	else {
-		scd->prev_raw = now;
-		scd->clock = clock;
-	}
+	return scd->clock;
 }
 
 static void lock_double_clock(struct sched_clock_data *data1,
@@ -203,7 +149,7 @@ static void lock_double_clock(struct sched_clock_data *data1,
 u64 sched_clock_cpu(int cpu)
 {
 	struct sched_clock_data *scd = cpu_sdc(cpu);
-	u64 now, clock;
+	u64 now, clock, this_clock, remote_clock;
 
 	if (unlikely(!sched_clock_running))
 		return 0ull;
@@ -212,43 +158,44 @@ u64 sched_clock_cpu(int cpu)
 	now = sched_clock();
 
 	if (cpu != raw_smp_processor_id()) {
-		/*
-		 * in order to update a remote cpu's clock based on our
-		 * unstable raw time rebase it against:
-		 *   tick_raw		(offset between raw counters)
-		 *   tick_gotd          (tick offset between cpus)
-		 */
 		struct sched_clock_data *my_scd = this_scd();
 
 		lock_double_clock(scd, my_scd);
 
-		now -= my_scd->tick_raw;
-		now += scd->tick_raw;
+		this_clock = __update_sched_clock(my_scd, now);
+		remote_clock = scd->clock;
 
-		now += my_scd->tick_gtod;
-		now -= scd->tick_gtod;
+		/*
+		 * Use the opportunity that we have both locks
+		 * taken to couple the two clocks: we take the
+		 * larger time as the latest time for both
+		 * runqueues. (this creates monotonic movement)
+		 */
+		if (likely((s64)(remote_clock - this_clock) < 0)) {
+			clock = this_clock;
+			scd->clock = clock;
+		} else {
+			/*
+			 * Should be rare, but possible:
+			 */
+			clock = remote_clock;
+			my_scd->clock = remote_clock;
+		}
 
 		__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);
+		clock = __update_sched_clock(scd, now);
 	}
 
+	__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))
@@ -260,29 +207,9 @@ void sched_clock_tick(void)
 	now = sched_clock();
 
 	__raw_spin_lock(&scd->lock);
-	__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;
+	__update_sched_clock(scd, now);
 	__raw_spin_unlock(&scd->lock);
 }
 
@@ -300,37 +227,28 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);
  */
 void sched_clock_idle_wakeup_event(u64 delta_ns)
 {
-	struct sched_clock_data *scd = this_scd();
-	u64 now = sched_clock();
-
-	/*
-	 * Override the previous timestamp and ignore all
-	 * sched_clock() deltas that occured while we idled,
-	 * and use the PM-provided delta_ns to advance the
-	 * rq clock:
-	 */
-	__raw_spin_lock(&scd->lock);
-	scd->prev_raw = now;
-	scd->clock += delta_ns;
-	scd->multi = 1 << MULTI_SHIFT;
-	__raw_spin_unlock(&scd->lock);
-
+	sched_clock_tick();
 	touch_softlockup_watchdog();
 }
 EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 
-#endif
+#else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
-/*
- * Scheduler clock - returns current time in nanosec units.
- * This is default implementation.
- * Architectures and sub-architectures can override this.
- */
-unsigned long long __attribute__((weak)) sched_clock(void)
+void sched_clock_init(void)
 {
-	return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
+	sched_clock_running = 1;
 }
 
+u64 sched_clock_cpu(int cpu)
+{
+	if (unlikely(!sched_clock_running))
+		return 0;
+
+	return sched_clock();
+}
+
+#endif
+
 unsigned long long cpu_clock(int cpu)
 {
 	unsigned long long clock;