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, 55 insertions, 48 deletions

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 2a0a9995256d..13935886a471 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -369,8 +369,12 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 
 #define P(F) \
 	SEQ_printf(m, "  .%-30s: %lld\n", #F, (long long)F)
+#define P_SCHEDSTAT(F) \
+	SEQ_printf(m, "  .%-30s: %lld\n", #F, (long long)schedstat_val(F))
 #define PN(F) \
 	SEQ_printf(m, "  .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F))
+#define PN_SCHEDSTAT(F) \
+	SEQ_printf(m, "  .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)schedstat_val(F)))
 
 	if (!se)
 		return;
@@ -378,26 +382,27 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
 	PN(se->exec_start);
 	PN(se->vruntime);
 	PN(se->sum_exec_runtime);
-#ifdef CONFIG_SCHEDSTATS
 	if (schedstat_enabled()) {
-		PN(se->statistics.wait_start);
-		PN(se->statistics.sleep_start);
-		PN(se->statistics.block_start);
-		PN(se->statistics.sleep_max);
-		PN(se->statistics.block_max);
-		PN(se->statistics.exec_max);
-		PN(se->statistics.slice_max);
-		PN(se->statistics.wait_max);
-		PN(se->statistics.wait_sum);
-		P(se->statistics.wait_count);
+		PN_SCHEDSTAT(se->statistics.wait_start);
+		PN_SCHEDSTAT(se->statistics.sleep_start);
+		PN_SCHEDSTAT(se->statistics.block_start);
+		PN_SCHEDSTAT(se->statistics.sleep_max);
+		PN_SCHEDSTAT(se->statistics.block_max);
+		PN_SCHEDSTAT(se->statistics.exec_max);
+		PN_SCHEDSTAT(se->statistics.slice_max);
+		PN_SCHEDSTAT(se->statistics.wait_max);
+		PN_SCHEDSTAT(se->statistics.wait_sum);
+		P_SCHEDSTAT(se->statistics.wait_count);
 	}
-#endif
 	P(se->load.weight);
 #ifdef CONFIG_SMP
 	P(se->avg.load_avg);
 	P(se->avg.util_avg);
 #endif
+
+#undef PN_SCHEDSTAT
 #undef PN
+#undef P_SCHEDSTAT
 #undef P
 }
 #endif
@@ -429,9 +434,9 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 		p->prio);
 
 	SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld",
-		SPLIT_NS(schedstat_val(p, se.statistics.wait_sum)),
+		SPLIT_NS(schedstat_val_or_zero(p->se.statistics.wait_sum)),
 		SPLIT_NS(p->se.sum_exec_runtime),
-		SPLIT_NS(schedstat_val(p, se.statistics.sum_sleep_runtime)));
+		SPLIT_NS(schedstat_val_or_zero(p->se.statistics.sum_sleep_runtime)));
 
 #ifdef CONFIG_NUMA_BALANCING
 	SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p));
@@ -626,9 +631,7 @@ do {									\
 #undef P64
 #endif
 
-#ifdef CONFIG_SCHEDSTATS
-#define P(n) SEQ_printf(m, "  .%-30s: %d\n", #n, rq->n);
-
+#define P(n) SEQ_printf(m, "  .%-30s: %d\n", #n, schedstat_val(rq->n));
 	if (schedstat_enabled()) {
 		P(yld_count);
 		P(sched_count);
@@ -636,9 +639,8 @@ do {									\
 		P(ttwu_count);
 		P(ttwu_local);
 	}
-
 #undef P
-#endif
+
 	spin_lock_irqsave(&sched_debug_lock, flags);
 	print_cfs_stats(m, cpu);
 	print_rt_stats(m, cpu);
@@ -868,10 +870,14 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F)
 #define P(F) \
 	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F)
+#define P_SCHEDSTAT(F) \
+	SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)schedstat_val(p->F))
 #define __PN(F) \
 	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F))
 #define PN(F) \
 	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F))
+#define PN_SCHEDSTAT(F) \
+	SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)schedstat_val(p->F)))
 
 	PN(se.exec_start);
 	PN(se.vruntime);
@@ -881,37 +887,36 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 
 	P(se.nr_migrations);
 
-#ifdef CONFIG_SCHEDSTATS
 	if (schedstat_enabled()) {
 		u64 avg_atom, avg_per_cpu;
 
-		PN(se.statistics.sum_sleep_runtime);
-		PN(se.statistics.wait_start);
-		PN(se.statistics.sleep_start);
-		PN(se.statistics.block_start);
-		PN(se.statistics.sleep_max);
-		PN(se.statistics.block_max);
-		PN(se.statistics.exec_max);
-		PN(se.statistics.slice_max);
-		PN(se.statistics.wait_max);
-		PN(se.statistics.wait_sum);
-		P(se.statistics.wait_count);
-		PN(se.statistics.iowait_sum);
-		P(se.statistics.iowait_count);
-		P(se.statistics.nr_migrations_cold);
-		P(se.statistics.nr_failed_migrations_affine);
-		P(se.statistics.nr_failed_migrations_running);
-		P(se.statistics.nr_failed_migrations_hot);
-		P(se.statistics.nr_forced_migrations);
-		P(se.statistics.nr_wakeups);
-		P(se.statistics.nr_wakeups_sync);
-		P(se.statistics.nr_wakeups_migrate);
-		P(se.statistics.nr_wakeups_local);
-		P(se.statistics.nr_wakeups_remote);
-		P(se.statistics.nr_wakeups_affine);
-		P(se.statistics.nr_wakeups_affine_attempts);
-		P(se.statistics.nr_wakeups_passive);
-		P(se.statistics.nr_wakeups_idle);
+		PN_SCHEDSTAT(se.statistics.sum_sleep_runtime);
+		PN_SCHEDSTAT(se.statistics.wait_start);
+		PN_SCHEDSTAT(se.statistics.sleep_start);
+		PN_SCHEDSTAT(se.statistics.block_start);
+		PN_SCHEDSTAT(se.statistics.sleep_max);
+		PN_SCHEDSTAT(se.statistics.block_max);
+		PN_SCHEDSTAT(se.statistics.exec_max);
+		PN_SCHEDSTAT(se.statistics.slice_max);
+		PN_SCHEDSTAT(se.statistics.wait_max);
+		PN_SCHEDSTAT(se.statistics.wait_sum);
+		P_SCHEDSTAT(se.statistics.wait_count);
+		PN_SCHEDSTAT(se.statistics.iowait_sum);
+		P_SCHEDSTAT(se.statistics.iowait_count);
+		P_SCHEDSTAT(se.statistics.nr_migrations_cold);
+		P_SCHEDSTAT(se.statistics.nr_failed_migrations_affine);
+		P_SCHEDSTAT(se.statistics.nr_failed_migrations_running);
+		P_SCHEDSTAT(se.statistics.nr_failed_migrations_hot);
+		P_SCHEDSTAT(se.statistics.nr_forced_migrations);
+		P_SCHEDSTAT(se.statistics.nr_wakeups);
+		P_SCHEDSTAT(se.statistics.nr_wakeups_sync);
+		P_SCHEDSTAT(se.statistics.nr_wakeups_migrate);
+		P_SCHEDSTAT(se.statistics.nr_wakeups_local);
+		P_SCHEDSTAT(se.statistics.nr_wakeups_remote);
+		P_SCHEDSTAT(se.statistics.nr_wakeups_affine);
+		P_SCHEDSTAT(se.statistics.nr_wakeups_affine_attempts);
+		P_SCHEDSTAT(se.statistics.nr_wakeups_passive);
+		P_SCHEDSTAT(se.statistics.nr_wakeups_idle);
 
 		avg_atom = p->se.sum_exec_runtime;
 		if (nr_switches)
@@ -930,7 +935,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 		__PN(avg_atom);
 		__PN(avg_per_cpu);
 	}
-#endif
+
 	__P(nr_switches);
 	SEQ_printf(m, "%-45s:%21Ld\n",
 		   "nr_voluntary_switches", (long long)p->nvcsw);
@@ -947,8 +952,10 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 #endif
 	P(policy);
 	P(prio);
+#undef PN_SCHEDSTAT
 #undef PN
 #undef __PN
+#undef P_SCHEDSTAT
 #undef P
 #undef __P