1 files changed, 55 insertions, 56 deletions

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c2119fd20f8..31cc02ebc54 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -24,24 +24,6 @@ extern long calc_load_fold_active(struct rq *this_rq);
 extern void update_cpu_load_active(struct rq *this_rq);
 
 /*
- * Convert user-nice values [ -20 ... 0 ... 19 ]
- * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
- * and back.
- */
-#define NICE_TO_PRIO(nice)	(MAX_RT_PRIO + (nice) + 20)
-#define PRIO_TO_NICE(prio)	((prio) - MAX_RT_PRIO - 20)
-#define TASK_NICE(p)		PRIO_TO_NICE((p)->static_prio)
-
-/*
- * 'User priority' is the nice value converted to something we
- * can work with better when scaling various scheduler parameters,
- * it's a [ 0 ... 39 ] range.
- */
-#define USER_PRIO(p)		((p)-MAX_RT_PRIO)
-#define TASK_USER_PRIO(p)	USER_PRIO((p)->static_prio)
-#define MAX_USER_PRIO		(USER_PRIO(MAX_PRIO))
-
-/*
  * Helpers for converting nanosecond timing to jiffy resolution
  */
 #define NS_TO_JIFFIES(TIME)	((unsigned long)(TIME) / (NSEC_PER_SEC / HZ))
@@ -296,7 +278,7 @@ extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
 extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
 
 extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
-extern void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
+extern void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force);
 extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);
 
 extern void free_rt_sched_group(struct task_group *tg);
@@ -427,6 +409,8 @@ struct rt_rq {
 	int overloaded;
 	struct plist_head pushable_tasks;
 #endif
+	int rt_queued;
+
 	int rt_throttled;
 	u64 rt_time;
 	u64 rt_runtime;
@@ -462,7 +446,6 @@ struct dl_rq {
 	} earliest_dl;
 
 	unsigned long dl_nr_migratory;
-	unsigned long dl_nr_total;
 	int overloaded;
 
 	/*
@@ -559,11 +542,9 @@ struct rq {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* list of leaf cfs_rq on this cpu: */
 	struct list_head leaf_cfs_rq_list;
-#endif /* CONFIG_FAIR_GROUP_SCHED */
 
-#ifdef CONFIG_RT_GROUP_SCHED
-	struct list_head leaf_rt_rq_list;
-#endif
+	struct sched_avg avg;
+#endif /* CONFIG_FAIR_GROUP_SCHED */
 
 	/*
 	 * This is part of a global counter where only the total sum
@@ -586,7 +567,7 @@ struct rq {
 	struct root_domain *rd;
 	struct sched_domain *sd;
 
-	unsigned long cpu_power;
+	unsigned long cpu_capacity;
 
 	unsigned char idle_balance;
 	/* For active balancing */
@@ -652,8 +633,6 @@ struct rq {
 #ifdef CONFIG_SMP
 	struct llist_head wake_list;
 #endif
-
-	struct sched_avg avg;
 };
 
 static inline int cpu_of(struct rq *rq)
@@ -691,6 +670,8 @@ extern int migrate_swap(struct task_struct *, struct task_struct *);
 
 #ifdef CONFIG_SMP
 
+extern void sched_ttwu_pending(void);
+
 #define rcu_dereference_check_sched_domain(p) \
 	rcu_dereference_check((p), \
 			      lockdep_is_held(&sched_domains_mutex))
@@ -749,15 +730,15 @@ 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_power {
+struct sched_group_capacity {
 	atomic_t ref;
 	/*
-	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
-	 * single CPU.
+	 * CPU capacity of this group, SCHED_LOAD_SCALE being max capacity
+	 * for a single CPU.
 	 */
-	unsigned int power, power_orig;
+	unsigned int capacity, capacity_orig;
 	unsigned long next_update;
-	int imbalance; /* XXX unrelated to power but shared group state */
+	int imbalance; /* XXX unrelated to capacity but shared group state */
 	/*
 	 * Number of busy cpus in this group.
 	 */
@@ -771,7 +752,7 @@ struct sched_group {
 	atomic_t ref;
 
 	unsigned int group_weight;
-	struct sched_group_power *sgp;
+	struct sched_group_capacity *sgc;
 
 	/*
 	 * The CPUs this group covers.
@@ -794,7 +775,7 @@ static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
  */
 static inline struct cpumask *sched_group_mask(struct sched_group *sg)
 {
-	return to_cpumask(sg->sgp->cpumask);
+	return to_cpumask(sg->sgc->cpumask);
 }
 
 /**
@@ -808,6 +789,10 @@ static inline unsigned int group_first_cpu(struct sched_group *group)
 
 extern int group_balance_cpu(struct sched_group *sg);
 
+#else
+
+static inline void sched_ttwu_pending(void) { }
+
 #endif /* CONFIG_SMP */
 
 #include "stats.h"
@@ -1113,6 +1098,8 @@ static const u32 prio_to_wmult[40] = {
 
 #define DEQUEUE_SLEEP		1
 
+#define RETRY_TASK		((void *)-1UL)
+
 struct sched_class {
 	const struct sched_class *next;
 
@@ -1123,14 +1110,22 @@ struct sched_class {
 
 	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
 
-	struct task_struct * (*pick_next_task) (struct rq *rq);
+	/*
+	 * It is the responsibility of the pick_next_task() method that will
+	 * return the next task to call put_prev_task() on the @prev task or
+	 * something equivalent.
+	 *
+	 * May return RETRY_TASK when it finds a higher prio class has runnable
+	 * tasks.
+	 */
+	struct task_struct * (*pick_next_task) (struct rq *rq,
+						struct task_struct *prev);
 	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
 	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
 	void (*migrate_task_rq)(struct task_struct *p, int next_cpu);
 
-	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
 	void (*post_schedule) (struct rq *this_rq);
 	void (*task_waking) (struct task_struct *task);
 	void (*task_woken) (struct rq *this_rq, struct task_struct *task);
@@ -1160,6 +1155,11 @@ struct sched_class {
 #endif
 };
 
+static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
+{
+	prev->sched_class->put_prev_task(rq, prev);
+}
+
 #define sched_class_highest (&stop_sched_class)
 #define for_each_class(class) \
    for (class = sched_class_highest; class; class = class->next)
@@ -1173,19 +1173,17 @@ extern const struct sched_class idle_sched_class;
 
 #ifdef CONFIG_SMP
 
-extern void update_group_power(struct sched_domain *sd, int cpu);
+extern void update_group_capacity(struct sched_domain *sd, int cpu);
 
 extern void trigger_load_balance(struct rq *rq);
-extern void idle_balance(int this_cpu, struct rq *this_rq);
 
 extern void idle_enter_fair(struct rq *this_rq);
 extern void idle_exit_fair(struct rq *this_rq);
 
-#else	/* CONFIG_SMP */
+#else
 
-static inline void idle_balance(int cpu, struct rq *rq)
-{
-}
+static inline void idle_enter_fair(struct rq *rq) { }
+static inline void idle_exit_fair(struct rq *rq) { }
 
 #endif
 
@@ -1214,22 +1212,14 @@ extern void update_idle_cpu_load(struct rq *this_rq);
 
 extern void init_task_runnable_average(struct task_struct *p);
 
-#ifdef CONFIG_PARAVIRT
-static inline u64 steal_ticks(u64 steal)
+static inline void add_nr_running(struct rq *rq, unsigned count)
 {
-	if (unlikely(steal > NSEC_PER_SEC))
-		return div_u64(steal, TICK_NSEC);
-
-	return __iter_div_u64_rem(steal, TICK_NSEC, &steal);
-}
-#endif
+	unsigned prev_nr = rq->nr_running;
 
-static inline void inc_nr_running(struct rq *rq)
-{
-	rq->nr_running++;
+	rq->nr_running = prev_nr + count;
 
 #ifdef CONFIG_NO_HZ_FULL
-	if (rq->nr_running == 2) {
+	if (prev_nr < 2 && rq->nr_running >= 2) {
 		if (tick_nohz_full_cpu(rq->cpu)) {
 			/* Order rq->nr_running write against the IPI */
 			smp_wmb();
@@ -1239,9 +1229,9 @@ static inline void inc_nr_running(struct rq *rq)
 #endif
 }
 
-static inline void dec_nr_running(struct rq *rq)
+static inline void sub_nr_running(struct rq *rq, unsigned count)
 {
-	rq->nr_running--;
+	rq->nr_running -= count;
 }
 
 static inline void rq_last_tick_reset(struct rq *rq)
@@ -1393,6 +1383,15 @@ static inline void double_lock(spinlock_t *l1, spinlock_t *l2)
 	spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
 }
 
+static inline void double_lock_irq(spinlock_t *l1, spinlock_t *l2)
+{
+	if (l1 > l2)
+		swap(l1, l2);
+
+	spin_lock_irq(l1);
+	spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
+}
+
 static inline void double_raw_lock(raw_spinlock_t *l1, raw_spinlock_t *l2)
 {
 	if (l1 > l2)