sched clock: revert various sched_clock() changes

Found an interactivity problem on a quad core test-system - simple
CPU loops would occasionally delay the system un an unacceptable way.

After much debugging with Peter Zijlstra it turned out that the problem
is caused by the string of sched_clock() changes - they caused the CPU
clock to jump backwards a bit - which confuses the scheduler arithmetics.

(which is unsigned for performance reasons)

So revert:

 # c300ba2: sched_clock: and multiplier for TSC to gtod drift
 # c0c8773: sched_clock: only update deltas with local reads.
 # af52a90: sched_clock: stop maximum check on NO HZ
 # f7cce27: sched_clock: widen the max and min time

This solves the interactivity problems.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Mike Galbraith <efault@gmx.de>

1 files changed, 13 insertions, 96 deletions

diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index 5a2dc7d8fd98..9a7844158ae8 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -44,11 +44,6 @@ unsigned long long __attribute__((weak)) sched_clock(void)
 
 #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
@@ -62,10 +57,6 @@ struct sched_clock_data {
 	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);
@@ -97,53 +88,18 @@ void sched_clock_init(void)
 		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, u64 *time)
+static void __update_sched_clock(struct sched_clock_data *scd, u64 now)
 {
 	unsigned long now_jiffies = jiffies;
 	long delta_jiffies = now_jiffies - scd->tick_jiffies;
@@ -152,31 +108,16 @@ static void __update_sched_clock(struct sched_clock_data *scd, u64 now, u64 *tim
 	s64 delta = now - scd->prev_raw;
 
 	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;
+	min_clock = scd->tick_gtod + delta_jiffies * TICK_NSEC;
 
 	if (unlikely(delta < 0)) {
 		clock++;
 		goto out;
 	}
 
-	/*
-	 * 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;
+	max_clock = min_clock + TICK_NSEC;
 
-	if (unlikely(clock + delta > max_clock) && check_max(scd)) {
+	if (unlikely(clock + delta > max_clock)) {
 		if (clock < max_clock)
 			clock = max_clock;
 		else
@@ -189,12 +130,9 @@ static void __update_sched_clock(struct sched_clock_data *scd, u64 now, u64 *tim
 	if (unlikely(clock < min_clock))
 		clock = min_clock;
 
-	if (time)
-		*time = clock;
-	else {
-		scd->prev_raw = now;
-		scd->clock = clock;
-	}
+	scd->prev_raw = now;
+	scd->tick_jiffies = now_jiffies;
+	scd->clock = clock;
 }
 
 static void lock_double_clock(struct sched_clock_data *data1,
@@ -238,26 +176,21 @@ u64 sched_clock_cpu(int cpu)
 		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))
@@ -269,29 +202,14 @@ void sched_clock_tick(void)
 	now = sched_clock();
 
 	__raw_spin_lock(&scd->lock);
-	__update_sched_clock(scd, now, NULL);
+	__update_sched_clock(scd, now);
 	/*
 	 * 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);
 }
 
@@ -321,7 +239,6 @@ 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();