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

Pull scheduler changes from Ingo Molnar:
 "The main changes in this cycle were:

   - sched/fair load tracking fixes and cleanups (Byungchul Park)

   - Make load tracking frequency scale invariant (Dietmar Eggemann)

   - sched/deadline updates (Juri Lelli)

   - stop machine fixes, cleanups and enhancements for bugs triggered by
     CPU hotplug stress testing (Oleg Nesterov)

   - scheduler preemption code rework: remove PREEMPT_ACTIVE and related
     cleanups (Peter Zijlstra)

   - Rework the sched_info::run_delay code to fix races (Peter Zijlstra)

   - Optimize per entity utilization tracking (Peter Zijlstra)

   - ... misc other fixes, cleanups and smaller updates"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (57 commits)
  sched: Don't scan all-offline ->cpus_allowed twice if !CONFIG_CPUSETS
  sched: Move cpu_active() tests from stop_two_cpus() into migrate_swap_stop()
  sched: Start stopper early
  stop_machine: Kill cpu_stop_threads->setup() and cpu_stop_unpark()
  stop_machine: Kill smp_hotplug_thread->pre_unpark, introduce stop_machine_unpark()
  stop_machine: Change cpu_stop_queue_two_works() to rely on stopper->enabled
  stop_machine: Introduce __cpu_stop_queue_work() and cpu_stop_queue_two_works()
  stop_machine: Ensure that a queued callback will be called before cpu_stop_park()
  sched/x86: Fix typo in __switch_to() comments
  sched/core: Remove a parameter in the migrate_task_rq() function
  sched/core: Drop unlikely behind BUG_ON()
  sched/core: Fix task and run queue sched_info::run_delay inconsistencies
  sched/numa: Fix task_tick_fair() from disabling numa_balancing
  sched/core: Add preempt_count invariant check
  sched/core: More notrace annotations
  sched/core: Kill PREEMPT_ACTIVE
  sched/core, sched/x86: Kill thread_info::saved_preempt_count
  sched/core: Simplify preempt_count tests
  sched/core: Robustify preemption leak checks
  sched/core: Stop setting PREEMPT_ACTIVE
  ...

7 files changed, 38 insertions, 53 deletions

diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index 0bec580a4885..5d8ffa3e6f8c 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -24,7 +24,7 @@ static __always_inline void preempt_count_set(int pc)
  * must be macros to avoid header recursion hell
  */
 #define init_task_preempt_count(p) do { \
-	task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
+	task_thread_info(p)->preempt_count = FORK_PREEMPT_COUNT; \
 } while (0)
 
 #define init_idle_preempt_count(p, cpu) do { \
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index bea8dd8ff5e0..75e4e30677f1 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -26,7 +26,6 @@
  *         SOFTIRQ_MASK:	0x0000ff00
  *         HARDIRQ_MASK:	0x000f0000
  *             NMI_MASK:	0x00100000
- *       PREEMPT_ACTIVE:	0x00200000
  * PREEMPT_NEED_RESCHED:	0x80000000
  */
 #define PREEMPT_BITS	8
@@ -53,10 +52,6 @@
 
 #define SOFTIRQ_DISABLE_OFFSET	(2 * SOFTIRQ_OFFSET)
 
-#define PREEMPT_ACTIVE_BITS	1
-#define PREEMPT_ACTIVE_SHIFT	(NMI_SHIFT + NMI_BITS)
-#define PREEMPT_ACTIVE	(__IRQ_MASK(PREEMPT_ACTIVE_BITS) << PREEMPT_ACTIVE_SHIFT)
-
 /* We use the MSB mostly because its available */
 #define PREEMPT_NEED_RESCHED	0x80000000
 
@@ -126,8 +121,7 @@
  * Check whether we were atomic before we did preempt_disable():
  * (used by the scheduler)
  */
-#define in_atomic_preempt_off() \
-		((preempt_count() & ~PREEMPT_ACTIVE) != PREEMPT_DISABLE_OFFSET)
+#define in_atomic_preempt_off() (preempt_count() != PREEMPT_DISABLE_OFFSET)
 
 #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER)
 extern void preempt_count_add(int val);
@@ -146,18 +140,6 @@ extern void preempt_count_sub(int val);
 #define preempt_count_inc() preempt_count_add(1)
 #define preempt_count_dec() preempt_count_sub(1)
 
-#define preempt_active_enter() \
-do { \
-	preempt_count_add(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET); \
-	barrier(); \
-} while (0)
-
-#define preempt_active_exit() \
-do { \
-	barrier(); \
-	preempt_count_sub(PREEMPT_ACTIVE + PREEMPT_DISABLE_OFFSET); \
-} while (0)
-
 #ifdef CONFIG_PREEMPT_COUNT
 
 #define preempt_disable() \
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 56667292d1e4..9e1e06c3ce05 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -599,20 +599,26 @@ struct task_cputime_atomic {
 		.sum_exec_runtime = ATOMIC64_INIT(0),		\
 	}
 
-#ifdef CONFIG_PREEMPT_COUNT
-#define PREEMPT_DISABLED	(1 + PREEMPT_ENABLED)
-#else
-#define PREEMPT_DISABLED	PREEMPT_ENABLED
-#endif
+#define PREEMPT_DISABLED	(PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)
+
+/*
+ * Disable preemption until the scheduler is running -- use an unconditional
+ * value so that it also works on !PREEMPT_COUNT kernels.
+ *
+ * Reset by start_kernel()->sched_init()->init_idle()->init_idle_preempt_count().
+ */
+#define INIT_PREEMPT_COUNT	PREEMPT_OFFSET
 
 /*
- * Disable preemption until the scheduler is running.
- * Reset by start_kernel()->sched_init()->init_idle().
+ * Initial preempt_count value; reflects the preempt_count schedule invariant
+ * which states that during context switches:
  *
- * We include PREEMPT_ACTIVE to avoid cond_resched() from working
- * before the scheduler is active -- see should_resched().
+ *    preempt_count() == 2*PREEMPT_DISABLE_OFFSET
+ *
+ * Note: PREEMPT_DISABLE_OFFSET is 0 for !PREEMPT_COUNT kernels.
+ * Note: See finish_task_switch().
  */
-#define INIT_PREEMPT_COUNT	(PREEMPT_DISABLED + PREEMPT_ACTIVE)
+#define FORK_PREEMPT_COUNT	(2*PREEMPT_DISABLE_OFFSET + PREEMPT_ENABLED)
 
 /**
  * struct thread_group_cputimer - thread group interval timer counts
@@ -1142,8 +1148,6 @@ struct sched_domain_topology_level {
 #endif
 };
 
-extern struct sched_domain_topology_level *sched_domain_topology;
-
 extern void set_sched_topology(struct sched_domain_topology_level *tl);
 extern void wake_up_if_idle(int cpu);
 
@@ -1192,10 +1196,10 @@ struct load_weight {
 
 /*
  * The load_avg/util_avg accumulates an infinite geometric series.
- * 1) load_avg factors the amount of time that a sched_entity is
- * runnable on a rq into its weight. For cfs_rq, it is the aggregated
- * such weights of all runnable and blocked sched_entities.
- * 2) util_avg factors frequency scaling into the amount of time
+ * 1) load_avg factors frequency scaling into the amount of time that a
+ * sched_entity is runnable on a rq into its weight. For cfs_rq, it is the
+ * aggregated such weights of all runnable and blocked sched_entities.
+ * 2) util_avg factors frequency and cpu scaling into the amount of time
  * that a sched_entity is running on a CPU, in the range [0..SCHED_LOAD_SCALE].
  * For cfs_rq, it is the aggregated such times of all runnable and
  * blocked sched_entities.
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index 9d303b8847df..9089a2ae913d 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -21,4 +21,9 @@ static inline int dl_task(struct task_struct *p)
 	return dl_prio(p->prio);
 }
 
+static inline bool dl_time_before(u64 a, u64 b)
+{
+	return (s64)(a - b) < 0;
+}
+
 #endif /* _SCHED_DEADLINE_H */
diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h
index e6109a6cd8f6..12910cf19869 100644
--- a/include/linux/smpboot.h
+++ b/include/linux/smpboot.h
@@ -24,9 +24,6 @@ struct smpboot_thread_data;
  *			parked (cpu offline)
  * @unpark:		Optional unpark function, called when the thread is
  *			unparked (cpu online)
- * @pre_unpark:		Optional unpark function, called before the thread is
- *			unparked (cpu online). This is not guaranteed to be
- *			called on the target cpu of the thread. Careful!
  * @cpumask:		Internal state.  To update which threads are unparked,
  *			call smpboot_update_cpumask_percpu_thread().
  * @selfparking:	Thread is not parked by the park function.
@@ -42,7 +39,6 @@ struct smp_hotplug_thread {
 	void				(*cleanup)(unsigned int cpu, bool online);
 	void				(*park)(unsigned int cpu);
 	void				(*unpark)(unsigned int cpu);
-	void				(*pre_unpark)(unsigned int cpu);
 	cpumask_var_t			cpumask;
 	bool				selfparking;
 	const char			*thread_comm;
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 414d924318ce..0adedca24c5b 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -33,6 +33,8 @@ void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
 			 struct cpu_stop_work *work_buf);
 int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg);
 int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg);
+void stop_machine_park(int cpu);
+void stop_machine_unpark(int cpu);
 
 #else	/* CONFIG_SMP */
 
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 539d6bc3216a..9b90c57517a9 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -104,22 +104,17 @@ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
 	     TP_ARGS(p));
 
 #ifdef CREATE_TRACE_POINTS
-static inline long __trace_sched_switch_state(struct task_struct *p)
+static inline long __trace_sched_switch_state(bool preempt, struct task_struct *p)
 {
-	long state = p->state;
-
-#ifdef CONFIG_PREEMPT
 #ifdef CONFIG_SCHED_DEBUG
 	BUG_ON(p != current);
 #endif /* CONFIG_SCHED_DEBUG */
+
 	/*
-	 * For all intents and purposes a preempted task is a running task.
+	 * Preemption ignores task state, therefore preempted tasks are always
+	 * RUNNING (we will not have dequeued if state != RUNNING).
 	 */
-	if (preempt_count() & PREEMPT_ACTIVE)
-		state = TASK_RUNNING | TASK_STATE_MAX;
-#endif /* CONFIG_PREEMPT */
-
-	return state;
+	return preempt ? TASK_RUNNING | TASK_STATE_MAX : p->state;
 }
 #endif /* CREATE_TRACE_POINTS */
 
@@ -128,10 +123,11 @@ static inline long __trace_sched_switch_state(struct task_struct *p)
  */
 TRACE_EVENT(sched_switch,
 
-	TP_PROTO(struct task_struct *prev,
+	TP_PROTO(bool preempt,
+		 struct task_struct *prev,
 		 struct task_struct *next),
 
-	TP_ARGS(prev, next),
+	TP_ARGS(preempt, prev, next),
 
 	TP_STRUCT__entry(
 		__array(	char,	prev_comm,	TASK_COMM_LEN	)
@@ -147,7 +143,7 @@ TRACE_EVENT(sched_switch,
 		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
 		__entry->prev_pid	= prev->pid;
 		__entry->prev_prio	= prev->prio;
-		__entry->prev_state	= __trace_sched_switch_state(prev);
+		__entry->prev_state	= __trace_sched_switch_state(preempt, prev);
 		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
 		__entry->next_pid	= next->pid;
 		__entry->next_prio	= next->prio;