Merge remote-tracking branch 'rcu/rcu/next'

[karo-tx-linux.git] / include / linux / sched.h

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 530c52ef873ecb40272eb5062d2cdc1233fcdc4d..ada55c965fabe7efb79eedadaf5b2e745b88f797 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -825,6 +825,7 @@ enum cpu_idle_type {
 #define SD_ASYM_PACKING                0x0800  /* Place busy groups earlier in the domain */
 #define SD_PREFER_SIBLING      0x1000  /* Prefer to place tasks in a sibling domain */
 #define SD_OVERLAP             0x2000  /* sched_domains of this level overlap */
+#define SD_NUMA                        0x4000  /* cross-node balancing */
 
 extern int __weak arch_sd_sibiling_asym_packing(void);
 
@@ -1063,6 +1064,7 @@ struct sched_class {
 
 #ifdef CONFIG_SMP
        int  (*select_task_rq)(struct task_struct *p, 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);
@@ -1097,6 +1099,18 @@ struct load_weight {
        unsigned long weight, inv_weight;
 };
 
+struct sched_avg {
+       /*
+        * These sums represent an infinite geometric series and so are bound
+        * above by 1024/(1-y).  Thus we only need a u32 to store them for for all
+        * choices of y < 1-2^(-32)*1024.
+        */
+       u32 runnable_avg_sum, runnable_avg_period;
+       u64 last_runnable_update;
+       s64 decay_count;
+       unsigned long load_avg_contrib;
+};
+
 #ifdef CONFIG_SCHEDSTATS
 struct sched_statistics {
        u64                     wait_start;
@@ -1157,6 +1171,15 @@ struct sched_entity {
        /* rq "owned" by this entity/group: */
        struct cfs_rq           *my_q;
 #endif
+/*
+ * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
+ * removed when useful for applications beyond shares distribution (e.g.
+ * load-balance).
+ */
+#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
+       /* Per-entity load-tracking */
+       struct sched_avg        avg;
+#endif
 };
 
 struct sched_rt_entity {
@@ -1481,6 +1504,17 @@ struct task_struct {
        short il_next;
        short pref_node_fork;
 #endif
+#ifdef CONFIG_SCHED_NUMA
+       int node;                       /* task home node   */
+       int numa_scan_seq;
+       int numa_migrate_seq;
+       unsigned int numa_scan_period;
+       u64 node_stamp;                 /* migration stamp  */
+       unsigned long numa_contrib;
+       unsigned long *numa_faults;
+       struct callback_head numa_work;
+#endif /* CONFIG_SCHED_NUMA */
+
        struct rcu_head rcu;
 
        /*
@@ -1555,6 +1589,24 @@ struct task_struct {
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
 #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
 
+#ifdef CONFIG_SCHED_NUMA
+static inline int tsk_home_node(struct task_struct *p)
+{
+       return p->node;
+}
+
+extern void task_numa_fault(int node, int pages);
+#else
+static inline int tsk_home_node(struct task_struct *p)
+{
+       return -1;
+}
+
+static inline void task_numa_fault(int node, int pages)
+{
+}
+#endif /* CONFIG_SCHED_NUMA */
+
 /*
  * Priority of a process goes from 0..MAX_PRIO-1, valid RT
  * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
@@ -1984,6 +2036,12 @@ enum sched_tunable_scaling {
 };
 extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
 
+extern unsigned int sysctl_sched_numa_scan_delay;
+extern unsigned int sysctl_sched_numa_scan_period_min;
+extern unsigned int sysctl_sched_numa_scan_period_max;
+extern unsigned int sysctl_sched_numa_scan_size;
+extern unsigned int sysctl_sched_numa_settle_count;
+
 #ifdef CONFIG_SCHED_DEBUG
 extern unsigned int sysctl_sched_migration_cost;
 extern unsigned int sysctl_sched_nr_migrate;
@@ -1994,18 +2052,17 @@ extern unsigned int sysctl_sched_shares_window;
 int sched_proc_update_handler(struct ctl_table *table, int write,
                void __user *buffer, size_t *length,
                loff_t *ppos);
-#endif
-#ifdef CONFIG_SCHED_DEBUG
+
 static inline unsigned int get_sysctl_timer_migration(void)
 {
        return sysctl_timer_migration;
 }
-#else
+#else /* CONFIG_SCHED_DEBUG */
 static inline unsigned int get_sysctl_timer_migration(void)
 {
        return 1;
 }
-#endif
+#endif /* CONFIG_SCHED_DEBUG */
 extern unsigned int sysctl_sched_rt_period;
 extern int sysctl_sched_rt_runtime;
 
@@ -2066,6 +2123,7 @@ extern int sched_setscheduler(struct task_struct *, int,
                              const struct sched_param *);
 extern int sched_setscheduler_nocheck(struct task_struct *, int,
                                      const struct sched_param *);
+extern void sched_setnode(struct task_struct *p, int node);
 extern struct task_struct *idle_task(int cpu);
 /**
  * is_idle_task - is the specified task an idle task?