Merge branch 'sched/rt' into sched/core, to pick up -rt changes

[linux-2.6-block.git] / kernel / sched / sched.h

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index f2ce6ba1c5d5681d99ded1f51c2fe3a7940bc2b5..b3cb895d14a2088eef7a8853f00e7fc9b5823dd6 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -335,8 +335,6 @@ struct cfs_bandwidth {
        u64                     quota;
        u64                     runtime;
        s64                     hierarchical_quota;
-       u64                     runtime_expires;
-       int                     expires_seq;
 
        u8                      idle;
        u8                      period_active;
@@ -393,6 +391,16 @@ struct task_group {
 #endif
 
        struct cfs_bandwidth    cfs_bandwidth;
+
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+       /* The two decimal precision [%] value requested from user-space */
+       unsigned int            uclamp_pct[UCLAMP_CNT];
+       /* Clamp values requested for a task group */
+       struct uclamp_se        uclamp_req[UCLAMP_CNT];
+       /* Effective clamp values used for a task group */
+       struct uclamp_se        uclamp[UCLAMP_CNT];
+#endif
+
 };
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -483,7 +491,8 @@ struct cfs_rq {
        struct load_weight      load;
        unsigned long           runnable_weight;
        unsigned int            nr_running;
-       unsigned int            h_nr_running;
+       unsigned int            h_nr_running;      /* SCHED_{NORMAL,BATCH,IDLE} */
+       unsigned int            idle_h_nr_running; /* SCHED_IDLE */
 
        u64                     exec_clock;
        u64                     min_vruntime;
@@ -556,8 +565,6 @@ struct cfs_rq {
 
 #ifdef CONFIG_CFS_BANDWIDTH
        int                     runtime_enabled;
-       int                     expires_seq;
-       u64                     runtime_expires;
        s64                     runtime_remaining;
 
        u64                     throttled_clock;
@@ -777,9 +784,6 @@ struct root_domain {
        struct perf_domain __rcu *pd;
 };
 
-extern struct root_domain def_root_domain;
-extern struct mutex sched_domains_mutex;
-
 extern void init_defrootdomain(void);
 extern int sched_init_domains(const struct cpumask *cpu_map);
 extern void rq_attach_root(struct rq *rq, struct root_domain *rd);
@@ -1261,16 +1265,18 @@ enum numa_topology_type {
 extern enum numa_topology_type sched_numa_topology_type;
 extern int sched_max_numa_distance;
 extern bool find_numa_distance(int distance);
-#endif
-
-#ifdef CONFIG_NUMA
 extern void sched_init_numa(void);
 extern void sched_domains_numa_masks_set(unsigned int cpu);
 extern void sched_domains_numa_masks_clear(unsigned int cpu);
+extern int sched_numa_find_closest(const struct cpumask *cpus, int cpu);
 #else
 static inline void sched_init_numa(void) { }
 static inline void sched_domains_numa_masks_set(unsigned int cpu) { }
 static inline void sched_domains_numa_masks_clear(unsigned int cpu) { }
+static inline int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
+{
+       return nr_cpu_ids;
+}
 #endif
 
 #ifdef CONFIG_NUMA_BALANCING
@@ -1449,10 +1455,14 @@ static inline void unregister_sched_domain_sysctl(void)
 }
 #endif
 
+extern int newidle_balance(struct rq *this_rq, struct rq_flags *rf);
+
 #else
 
 static inline void sched_ttwu_pending(void) { }
 
+static inline int newidle_balance(struct rq *this_rq, struct rq_flags *rf) { return 0; }
+
 #endif /* CONFIG_SMP */
 
 #include "stats.h"
@@ -1700,17 +1710,21 @@ struct sched_class {
        void (*check_preempt_curr)(struct rq *rq, struct task_struct *p, int flags);
 
        /*
-        * 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.
+        * Both @prev and @rf are optional and may be NULL, in which case the
+        * caller must already have invoked put_prev_task(rq, prev, rf).
+        *
+        * Otherwise it is the responsibility of the pick_next_task() to call
+        * put_prev_task() on the @prev task or something equivalent, IFF it
+        * returns a next task.
         *
-        * May return RETRY_TASK when it finds a higher prio class has runnable
-        * tasks.
+        * In that case (@rf != NULL) it 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,
                                               struct rq_flags *rf);
-       void (*put_prev_task)(struct rq *rq, struct task_struct *p);
+       void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct rq_flags *rf);
+       void (*set_next_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);
@@ -1725,7 +1739,6 @@ struct sched_class {
        void (*rq_offline)(struct rq *rq);
 #endif
 
-       void (*set_curr_task)(struct rq *rq);
        void (*task_tick)(struct rq *rq, struct task_struct *p, int queued);
        void (*task_fork)(struct task_struct *p);
        void (*task_dead)(struct task_struct *p);
@@ -1755,12 +1768,14 @@ struct sched_class {
 
 static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
-       prev->sched_class->put_prev_task(rq, prev);
+       WARN_ON_ONCE(rq->curr != prev);
+       prev->sched_class->put_prev_task(rq, prev, NULL);
 }
 
-static inline void set_curr_task(struct rq *rq, struct task_struct *curr)
+static inline void set_next_task(struct rq *rq, struct task_struct *next)
 {
-       curr->sched_class->set_curr_task(rq);
+       WARN_ON_ONCE(rq->curr != next);
+       next->sched_class->set_next_task(rq, next);
 }
 
 #ifdef CONFIG_SMP
@@ -2266,7 +2281,7 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #endif /* CONFIG_CPU_FREQ */
 
 #ifdef CONFIG_UCLAMP_TASK
-unsigned int uclamp_eff_value(struct task_struct *p, unsigned int clamp_id);
+enum uclamp_id uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
 
 static __always_inline
 unsigned int uclamp_util_with(struct rq *rq, unsigned int util,