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

Pull scheduler changes from Ingo Molnar:

 - Add the initial implementation of SCHED_DEADLINE support: a real-time
   scheduling policy where tasks that meet their deadlines and
   periodically execute their instances in less than their runtime quota
   see real-time scheduling and won't miss any of their deadlines.
   Tasks that go over their quota get delayed (Available to privileged
   users for now)

 - Clean up and fix preempt_enable_no_resched() abuse all around the
   tree

 - Do sched_clock() performance optimizations on x86 and elsewhere

 - Fix and improve auto-NUMA balancing

 - Fix and clean up the idle loop

 - Apply various cleanups and fixes

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (60 commits)
  sched: Fix __sched_setscheduler() nice test
  sched: Move SCHED_RESET_ON_FORK into attr::sched_flags
  sched: Fix up attr::sched_priority warning
  sched: Fix up scheduler syscall LTP fails
  sched: Preserve the nice level over sched_setscheduler() and sched_setparam() calls
  sched/core: Fix htmldocs warnings
  sched/deadline: No need to check p if dl_se is valid
  sched/deadline: Remove unused variables
  sched/deadline: Fix sparse static warnings
  m68k: Fix build warning in mac_via.h
  sched, thermal: Clean up preempt_enable_no_resched() abuse
  sched, net: Fixup busy_loop_us_clock()
  sched, net: Clean up preempt_enable_no_resched() abuse
  sched/preempt: Fix up missed PREEMPT_NEED_RESCHED folding
  sched/preempt, locking: Rework local_bh_{dis,en}able()
  sched/clock, x86: Avoid a runtime condition in native_sched_clock()
  sched/clock: Fix up clear_sched_clock_stable()
  sched/clock, x86: Use a static_key for sched_clock_stable
  sched/clock: Remove local_irq_disable() from the clocks
  sched/clock, x86: Rewrite cyc2ns() to avoid the need to disable IRQs
  ...

1 files changed, 47 insertions, 31 deletions

diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c3ae144..6bd6a67 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -26,9 +26,10 @@
  * at 0 on boot (but people really shouldn't rely on that).
  *
  * cpu_clock(i)       -- can be used from any context, including NMI.
- * sched_clock_cpu(i) -- must be used with local IRQs disabled (implied by NMI)
  * local_clock()      -- is cpu_clock() on the current cpu.
  *
+ * sched_clock_cpu(i)
+ *
  * How:
  *
  * The implementation either uses sched_clock() when
@@ -50,15 +51,6 @@
  * Furthermore, explicit sleep and wakeup hooks allow us to account for time
  * that is otherwise invisible (TSC gets stopped).
  *
- *
- * Notes:
- *
- * The !IRQ-safetly of sched_clock() and sched_clock_cpu() comes from things
- * like cpufreq interrupts that can change the base clock (TSC) multiplier
- * and cause funny jumps in time -- although the filtering provided by
- * sched_clock_cpu() should mitigate serious artifacts we cannot rely on it
- * in general since for !CONFIG_HAVE_UNSTABLE_SCHED_CLOCK we fully rely on
- * sched_clock().
  */
 #include <linux/spinlock.h>
 #include <linux/hardirq.h>
@@ -66,6 +58,8 @@
 #include <linux/percpu.h>
 #include <linux/ktime.h>
 #include <linux/sched.h>
+#include <linux/static_key.h>
+#include <linux/workqueue.h>
 
 /*
  * Scheduler clock - returns current time in nanosec units.
@@ -82,7 +76,37 @@ EXPORT_SYMBOL_GPL(sched_clock);
 __read_mostly int sched_clock_running;
 
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-__read_mostly int sched_clock_stable;
+static struct static_key __sched_clock_stable = STATIC_KEY_INIT;
+
+int sched_clock_stable(void)
+{
+	if (static_key_false(&__sched_clock_stable))
+		return false;
+	return true;
+}
+
+void set_sched_clock_stable(void)
+{
+	if (!sched_clock_stable())
+		static_key_slow_dec(&__sched_clock_stable);
+}
+
+static void __clear_sched_clock_stable(struct work_struct *work)
+{
+	/* XXX worry about clock continuity */
+	if (sched_clock_stable())
+		static_key_slow_inc(&__sched_clock_stable);
+}
+
+static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable);
+
+void clear_sched_clock_stable(void)
+{
+	if (keventd_up())
+		schedule_work(&sched_clock_work);
+	else
+		__clear_sched_clock_stable(&sched_clock_work);
+}
 
 struct sched_clock_data {
 	u64			tick_raw;
@@ -242,20 +266,20 @@ u64 sched_clock_cpu(int cpu)
 	struct sched_clock_data *scd;
 	u64 clock;
 
-	WARN_ON_ONCE(!irqs_disabled());
-
-	if (sched_clock_stable)
+	if (sched_clock_stable())
 		return sched_clock();
 
 	if (unlikely(!sched_clock_running))
 		return 0ull;
 
+	preempt_disable();
 	scd = cpu_sdc(cpu);
 
 	if (cpu != smp_processor_id())
 		clock = sched_clock_remote(scd);
 	else
 		clock = sched_clock_local(scd);
+	preempt_enable();
 
 	return clock;
 }
@@ -265,7 +289,7 @@ void sched_clock_tick(void)
 	struct sched_clock_data *scd;
 	u64 now, now_gtod;
 
-	if (sched_clock_stable)
+	if (sched_clock_stable())
 		return;
 
 	if (unlikely(!sched_clock_running))
@@ -316,14 +340,10 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
  */
 u64 cpu_clock(int cpu)
 {
-	u64 clock;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	clock = sched_clock_cpu(cpu);
-	local_irq_restore(flags);
+	if (static_key_false(&__sched_clock_stable))
+		return sched_clock_cpu(cpu);
 
-	return clock;
+	return sched_clock();
 }
 
 /*
@@ -335,14 +355,10 @@ u64 cpu_clock(int cpu)
  */
 u64 local_clock(void)
 {
-	u64 clock;
-	unsigned long flags;
+	if (static_key_false(&__sched_clock_stable))
+		return sched_clock_cpu(raw_smp_processor_id());
 
-	local_irq_save(flags);
-	clock = sched_clock_cpu(smp_processor_id());
-	local_irq_restore(flags);
-
-	return clock;
+	return sched_clock();
 }
 
 #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
@@ -362,12 +378,12 @@ u64 sched_clock_cpu(int cpu)
 
 u64 cpu_clock(int cpu)
 {
-	return sched_clock_cpu(cpu);
+	return sched_clock();
 }
 
 u64 local_clock(void)
 {
-	return sched_clock_cpu(0);
+	return sched_clock();
 }
 
 #endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */