Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "The main changes in this (fairly busy) cycle were:

   - There was a class of scheduler bugs related to forgetting to update
     the rq-clock timestamp which can cause weird and hard to debug
     problems, so there's a new debug facility for this: which uncovered
     a whole lot of bugs which convinced us that we want to keep the
     debug facility.

     (Peter Zijlstra, Matt Fleming)

   - Various cputime related updates: eliminate cputime and use u64
     nanoseconds directly, simplify and improve the arch interfaces,
     implement delayed accounting more widely, etc. - (Frederic
     Weisbecker)

   - Move code around for better structure plus cleanups (Ingo Molnar)

   - Move IO schedule accounting deeper into the scheduler plus related
     changes to improve the situation (Tejun Heo)

   - ... plus a round of sched/rt and sched/deadline fixes, plus other
     fixes, updats and cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (85 commits)
  sched/core: Remove unlikely() annotation from sched_move_task()
  sched/autogroup: Rename auto_group.[ch] to autogroup.[ch]
  sched/topology: Split out scheduler topology code from core.c into topology.c
  sched/core: Remove unnecessary #include headers
  sched/rq_clock: Consolidate the ordering of the rq_clock methods
  delayacct: Include <uapi/linux/taskstats.h>
  sched/core: Clean up comments
  sched/rt: Show the 'sched_rr_timeslice' SCHED_RR timeslice tuning knob in milliseconds
  sched/clock: Add dummy clear_sched_clock_stable() stub function
  sched/cputime: Remove generic asm headers
  sched/cputime: Remove unused nsec_to_cputime()
  s390, sched/cputime: Remove unused cputime definitions
  powerpc, sched/cputime: Remove unused cputime definitions
  s390, sched/cputime: Make arch_cpu_idle_time() to return nsecs
  ia64, sched/cputime: Remove unused cputime definitions
  ia64: Convert vtime to use nsec units directly
  ia64, sched/cputime: Move the nsecs based cputime headers to the last arch using it
  sched/cputime: Remove jiffies based cputime
  sched/cputime, vtime: Return nsecs instead of cputime_t to account
  sched/cputime: Complete nsec conversion of tick based accounting
  ...

1 files changed, 83 insertions, 75 deletions

diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index e85a725e5c34..ad64efe41722 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -77,41 +77,88 @@ EXPORT_SYMBOL_GPL(sched_clock);
 
 __read_mostly int sched_clock_running;
 
+void sched_clock_init(void)
+{
+	sched_clock_running = 1;
+}
+
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-static struct static_key __sched_clock_stable = STATIC_KEY_INIT;
-static int __sched_clock_stable_early;
+/*
+ * We must start with !__sched_clock_stable because the unstable -> stable
+ * transition is accurate, while the stable -> unstable transition is not.
+ *
+ * Similarly we start with __sched_clock_stable_early, thereby assuming we
+ * will become stable, such that there's only a single 1 -> 0 transition.
+ */
+static DEFINE_STATIC_KEY_FALSE(__sched_clock_stable);
+static int __sched_clock_stable_early = 1;
 
-int sched_clock_stable(void)
+/*
+ * We want: ktime_get_ns() + gtod_offset == sched_clock() + raw_offset
+ */
+static __read_mostly u64 raw_offset;
+static __read_mostly u64 gtod_offset;
+
+struct sched_clock_data {
+	u64			tick_raw;
+	u64			tick_gtod;
+	u64			clock;
+};
+
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
+
+static inline struct sched_clock_data *this_scd(void)
 {
-	return static_key_false(&__sched_clock_stable);
+	return this_cpu_ptr(&sched_clock_data);
 }
 
-static void __set_sched_clock_stable(void)
+static inline struct sched_clock_data *cpu_sdc(int cpu)
 {
-	if (!sched_clock_stable())
-		static_key_slow_inc(&__sched_clock_stable);
+	return &per_cpu(sched_clock_data, cpu);
+}
 
-	tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
+int sched_clock_stable(void)
+{
+	return static_branch_likely(&__sched_clock_stable);
 }
 
-void set_sched_clock_stable(void)
+static void __set_sched_clock_stable(void)
 {
-	__sched_clock_stable_early = 1;
+	struct sched_clock_data *scd = this_scd();
 
-	smp_mb(); /* matches sched_clock_init() */
+	/*
+	 * Attempt to make the (initial) unstable->stable transition continuous.
+	 */
+	raw_offset = (scd->tick_gtod + gtod_offset) - (scd->tick_raw);
 
-	if (!sched_clock_running)
-		return;
+	printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n",
+			scd->tick_gtod, gtod_offset,
+			scd->tick_raw,  raw_offset);
 
-	__set_sched_clock_stable();
+	static_branch_enable(&__sched_clock_stable);
+	tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
 }
 
 static void __clear_sched_clock_stable(struct work_struct *work)
 {
-	/* XXX worry about clock continuity */
-	if (sched_clock_stable())
-		static_key_slow_dec(&__sched_clock_stable);
+	struct sched_clock_data *scd = this_scd();
+
+	/*
+	 * Attempt to make the stable->unstable transition continuous.
+	 *
+	 * Trouble is, this is typically called from the TSC watchdog
+	 * timer, which is late per definition. This means the tick
+	 * values can already be screwy.
+	 *
+	 * Still do what we can.
+	 */
+	gtod_offset = (scd->tick_raw + raw_offset) - (scd->tick_gtod);
+
+	printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n",
+			scd->tick_gtod, gtod_offset,
+			scd->tick_raw,  raw_offset);
 
+	static_branch_disable(&__sched_clock_stable);
 	tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE);
 }
 
@@ -121,47 +168,15 @@ void clear_sched_clock_stable(void)
 {
 	__sched_clock_stable_early = 0;
 
-	smp_mb(); /* matches sched_clock_init() */
-
-	if (!sched_clock_running)
-		return;
+	smp_mb(); /* matches sched_clock_init_late() */
 
-	schedule_work(&sched_clock_work);
+	if (sched_clock_running == 2)
+		schedule_work(&sched_clock_work);
 }
 
-struct sched_clock_data {
-	u64			tick_raw;
-	u64			tick_gtod;
-	u64			clock;
-};
-
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
-
-static inline struct sched_clock_data *this_scd(void)
+void sched_clock_init_late(void)
 {
-	return this_cpu_ptr(&sched_clock_data);
-}
-
-static inline struct sched_clock_data *cpu_sdc(int cpu)
-{
-	return &per_cpu(sched_clock_data, cpu);
-}
-
-void sched_clock_init(void)
-{
-	u64 ktime_now = ktime_to_ns(ktime_get());
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		struct sched_clock_data *scd = cpu_sdc(cpu);
-
-		scd->tick_raw = 0;
-		scd->tick_gtod = ktime_now;
-		scd->clock = ktime_now;
-	}
-
-	sched_clock_running = 1;
-
+	sched_clock_running = 2;
 	/*
 	 * Ensure that it is impossible to not do a static_key update.
 	 *
@@ -173,8 +188,6 @@ void sched_clock_init(void)
 
 	if (__sched_clock_stable_early)
 		__set_sched_clock_stable();
-	else
-		__clear_sched_clock_stable(NULL);
 }
 
 /*
@@ -216,7 +229,7 @@ again:
 	 *		      scd->tick_gtod + TICK_NSEC);
 	 */
 
-	clock = scd->tick_gtod + delta;
+	clock = scd->tick_gtod + gtod_offset + delta;
 	min_clock = wrap_max(scd->tick_gtod, old_clock);
 	max_clock = wrap_max(old_clock, scd->tick_gtod + TICK_NSEC);
 
@@ -302,7 +315,7 @@ u64 sched_clock_cpu(int cpu)
 	u64 clock;
 
 	if (sched_clock_stable())
-		return sched_clock();
+		return sched_clock() + raw_offset;
 
 	if (unlikely(!sched_clock_running))
 		return 0ull;
@@ -323,23 +336,22 @@ EXPORT_SYMBOL_GPL(sched_clock_cpu);
 void sched_clock_tick(void)
 {
 	struct sched_clock_data *scd;
-	u64 now, now_gtod;
-
-	if (sched_clock_stable())
-		return;
-
-	if (unlikely(!sched_clock_running))
-		return;
 
 	WARN_ON_ONCE(!irqs_disabled());
 
+	/*
+	 * Update these values even if sched_clock_stable(), because it can
+	 * become unstable at any point in time at which point we need some
+	 * values to fall back on.
+	 *
+	 * XXX arguably we can skip this if we expose tsc_clocksource_reliable
+	 */
 	scd = this_scd();
-	now_gtod = ktime_to_ns(ktime_get());
-	now = sched_clock();
+	scd->tick_raw  = sched_clock();
+	scd->tick_gtod = ktime_get_ns();
 
-	scd->tick_raw = now;
-	scd->tick_gtod = now_gtod;
-	sched_clock_local(scd);
+	if (!sched_clock_stable() && likely(sched_clock_running))
+		sched_clock_local(scd);
 }
 
 /*
@@ -366,11 +378,6 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 
 #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
-void sched_clock_init(void)
-{
-	sched_clock_running = 1;
-}
-
 u64 sched_clock_cpu(int cpu)
 {
 	if (unlikely(!sched_clock_running))
@@ -378,6 +385,7 @@ u64 sched_clock_cpu(int cpu)
 
 	return sched_clock();
 }
+
 #endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
 /*