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 are:

   - irqtime accounting cleanups and enhancements. (Frederic Weisbecker)

   - schedstat debugging enhancements, make it more broadly runtime
     available. (Josh Poimboeuf)

   - More work on asymmetric topology/capacity scheduling. (Morten
     Rasmussen)

   - sched/wait fixes and cleanups. (Oleg Nesterov)

   - PELT (per entity load tracking) improvements. (Peter Zijlstra)

   - Rewrite and enhance select_idle_siblings(). (Peter Zijlstra)

   - sched/numa enhancements/fixes (Rik van Riel)

   - sched/cputime scalability improvements (Stanislaw Gruszka)

   - Load calculation arithmetics fixes. (Dietmar Eggemann)

   - sched/deadline enhancements (Tommaso Cucinotta)

   - Fix utilization accounting when switching to the SCHED_NORMAL
     policy. (Vincent Guittot)

   - ... plus misc cleanups and enhancements"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (64 commits)
  sched/irqtime: Consolidate irqtime flushing code
  sched/irqtime: Consolidate accounting synchronization with u64_stats API
  u64_stats: Introduce IRQs disabled helpers
  sched/irqtime: Remove needless IRQs disablement on kcpustat update
  sched/irqtime: No need for preempt-safe accessors
  sched/fair: Fix min_vruntime tracking
  sched/debug: Add SCHED_WARN_ON()
  sched/core: Fix set_user_nice()
  sched/fair: Introduce set_curr_task() helper
  sched/core, ia64: Rename set_curr_task()
  sched/core: Fix incorrect utilization accounting when switching to fair class
  sched/core: Optimize SCHED_SMT
  sched/core: Rewrite and improve select_idle_siblings()
  sched/core: Replace sd_busy/nr_busy_cpus with sched_domain_shared
  sched/core: Introduce 'struct sched_domain_shared'
  sched/core: Restructure destroy_sched_domain()
  sched/core: Remove unused @cpu argument from destroy_sched_domain*()
  sched/wait: Introduce init_wait_entry()
  sched/wait: Avoid abort_exclusive_wait() in __wait_on_bit_lock()
  sched/wait: Avoid abort_exclusive_wait() in ___wait_event()
  ...

1 files changed, 47 insertions, 45 deletions

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b7fc1ce..58df559 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2,6 +2,7 @@
 #include <linux/sched.h>
 #include <linux/sched/sysctl.h>
 #include <linux/sched/rt.h>
+#include <linux/u64_stats_sync.h>
 #include <linux/sched/deadline.h>
 #include <linux/binfmts.h>
 #include <linux/mutex.h>
@@ -15,6 +16,12 @@
 #include "cpudeadline.h"
 #include "cpuacct.h"
 
+#ifdef CONFIG_SCHED_DEBUG
+#define SCHED_WARN_ON(x)	WARN_ONCE(x, #x)
+#else
+#define SCHED_WARN_ON(x)	((void)(x))
+#endif
+
 struct rq;
 struct cpuidle_state;
 
@@ -565,6 +572,8 @@ struct root_domain {
 	 */
 	cpumask_var_t rto_mask;
 	struct cpupri cpupri;
+
+	unsigned long max_cpu_capacity;
 };
 
 extern struct root_domain def_root_domain;
@@ -597,7 +606,6 @@ struct rq {
 #ifdef CONFIG_SMP
 	unsigned long last_load_update_tick;
 #endif /* CONFIG_SMP */
-	u64 nohz_stamp;
 	unsigned long nohz_flags;
 #endif /* CONFIG_NO_HZ_COMMON */
 #ifdef CONFIG_NO_HZ_FULL
@@ -723,6 +731,23 @@ static inline int cpu_of(struct rq *rq)
 #endif
 }
 
+
+#ifdef CONFIG_SCHED_SMT
+
+extern struct static_key_false sched_smt_present;
+
+extern void __update_idle_core(struct rq *rq);
+
+static inline void update_idle_core(struct rq *rq)
+{
+	if (static_branch_unlikely(&sched_smt_present))
+		__update_idle_core(rq);
+}
+
+#else
+static inline void update_idle_core(struct rq *rq) { }
+#endif
+
 DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
 #define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
@@ -857,8 +882,8 @@ static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
 DECLARE_PER_CPU(struct sched_domain *, sd_llc);
 DECLARE_PER_CPU(int, sd_llc_size);
 DECLARE_PER_CPU(int, sd_llc_id);
+DECLARE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
 DECLARE_PER_CPU(struct sched_domain *, sd_numa);
-DECLARE_PER_CPU(struct sched_domain *, sd_busy);
 DECLARE_PER_CPU(struct sched_domain *, sd_asym);
 
 struct sched_group_capacity {
@@ -870,10 +895,6 @@ struct sched_group_capacity {
 	unsigned int capacity;
 	unsigned long next_update;
 	int imbalance; /* XXX unrelated to capacity but shared group state */
-	/*
-	 * Number of busy cpus in this group.
-	 */
-	atomic_t nr_busy_cpus;
 
 	unsigned long cpumask[0]; /* iteration mask */
 };
@@ -1260,6 +1281,11 @@ static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
 	prev->sched_class->put_prev_task(rq, prev);
 }
 
+static inline void set_curr_task(struct rq *rq, struct task_struct *curr)
+{
+	curr->sched_class->set_curr_task(rq);
+}
+
 #define sched_class_highest (&stop_sched_class)
 #define for_each_class(class) \
    for (class = sched_class_highest; class; class = class->next)
@@ -1290,7 +1316,7 @@ static inline void idle_set_state(struct rq *rq,
 
 static inline struct cpuidle_state *idle_get_state(struct rq *rq)
 {
-	WARN_ON(!rcu_read_lock_held());
+	SCHED_WARN_ON(!rcu_read_lock_held());
 	return rq->idle_state;
 }
 #else
@@ -1710,52 +1736,28 @@ static inline void nohz_balance_exit_idle(unsigned int cpu) { }
 #endif
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
+struct irqtime {
+	u64			hardirq_time;
+	u64			softirq_time;
+	u64			irq_start_time;
+	struct u64_stats_sync	sync;
+};
 
-DECLARE_PER_CPU(u64, cpu_hardirq_time);
-DECLARE_PER_CPU(u64, cpu_softirq_time);
-
-#ifndef CONFIG_64BIT
-DECLARE_PER_CPU(seqcount_t, irq_time_seq);
-
-static inline void irq_time_write_begin(void)
-{
-	__this_cpu_inc(irq_time_seq.sequence);
-	smp_wmb();
-}
-
-static inline void irq_time_write_end(void)
-{
-	smp_wmb();
-	__this_cpu_inc(irq_time_seq.sequence);
-}
+DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
 
 static inline u64 irq_time_read(int cpu)
 {
-	u64 irq_time;
-	unsigned seq;
+	struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu);
+	unsigned int seq;
+	u64 total;
 
 	do {
-		seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu));
-		irq_time = per_cpu(cpu_softirq_time, cpu) +
-			   per_cpu(cpu_hardirq_time, cpu);
-	} while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq));
-
-	return irq_time;
-}
-#else /* CONFIG_64BIT */
-static inline void irq_time_write_begin(void)
-{
-}
+		seq = __u64_stats_fetch_begin(&irqtime->sync);
+		total = irqtime->softirq_time + irqtime->hardirq_time;
+	} while (__u64_stats_fetch_retry(&irqtime->sync, seq));
 
-static inline void irq_time_write_end(void)
-{
-}
-
-static inline u64 irq_time_read(int cpu)
-{
-	return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
+	return total;
 }
-#endif /* CONFIG_64BIT */
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
 #ifdef CONFIG_CPU_FREQ