1 files changed, 69 insertions, 50 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 62671f53202a..f9123a82cbb6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -306,6 +306,9 @@ __read_mostly int scheduler_running;
  */
 int sysctl_sched_rt_runtime = 950000;
 
+/* cpus with isolated domains */
+cpumask_var_t cpu_isolated_map;
+
 /*
  * this_rq_lock - lock this runqueue and disable interrupts.
  */
@@ -690,6 +693,23 @@ static inline bool got_nohz_idle_kick(void)
 bool sched_can_stop_tick(void)
 {
         /*
+         * FIFO realtime policy runs the highest priority task. Other runnable
+         * tasks are of a lower priority. The scheduler tick does nothing.
+         */
+        if (current->policy == SCHED_FIFO)
+                return true;
+
+        /*
+         * Round-robin realtime tasks time slice with other tasks at the same
+         * realtime priority. Is this task the only one at this priority?
+         */
+        if (current->policy == SCHED_RR) {
+                struct sched_rt_entity *rt_se = &current->rt;
+
+                return rt_se->run_list.prev == rt_se->run_list.next;
+        }
+
+        /*
          * More than one running task need preemption.
          * nr_running update is assumed to be visible
          * after IPI is sent from wakers.
@@ -996,6 +1016,13 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
                 rq_clock_skip_update(rq, true);
 }
 
+static ATOMIC_NOTIFIER_HEAD(task_migration_notifier);
+
+void register_task_migration_notifier(struct notifier_block *n)
+{
+        atomic_notifier_chain_register(&task_migration_notifier, n);
+}
+
 #ifdef CONFIG_SMP
 void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 {
@@ -1026,10 +1053,18 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
         trace_sched_migrate_task(p, new_cpu);
 
         if (task_cpu(p) != new_cpu) {
+                struct task_migration_notifier tmn;
+
                 if (p->sched_class->migrate_task_rq)
                         p->sched_class->migrate_task_rq(p, new_cpu);
                 p->se.nr_migrations++;
                 perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0);
+
+                tmn.task = p;
+                tmn.from_cpu = task_cpu(p);
+                tmn.to_cpu = new_cpu;
+
+                atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn);
         }
 
         __set_task_cpu(p, new_cpu);
@@ -2818,7 +2853,7 @@ asmlinkage __visible void __sched schedule_user(void)
          * we find a better solution.
          *
          * NB: There are buggy callers of this function.  Ideally we
-         * should warn if prev_state != IN_USER, but that will trigger
+         * should warn if prev_state != CONTEXT_USER, but that will trigger
          * too frequently to make sense yet.
          */
         enum ctx_state prev_state = exception_enter();
@@ -5320,36 +5355,13 @@ static int sched_cpu_active(struct notifier_block *nfb,
 static int sched_cpu_inactive(struct notifier_block *nfb,
                                         unsigned long action, void *hcpu)
 {
-        unsigned long flags;
-        long cpu = (long)hcpu;
-        struct dl_bw *dl_b;
-
         switch (action & ~CPU_TASKS_FROZEN) {
         case CPU_DOWN_PREPARE:
-                set_cpu_active(cpu, false);
-
-                /* explicitly allow suspend */
-                if (!(action & CPU_TASKS_FROZEN)) {
-                        bool overflow;
-                        int cpus;
-
-                        rcu_read_lock_sched();
-                        dl_b = dl_bw_of(cpu);
-
-                        raw_spin_lock_irqsave(&dl_b->lock, flags);
-                        cpus = dl_bw_cpus(cpu);
-                        overflow = __dl_overflow(dl_b, cpus, 0, 0);
-                        raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-
-                        rcu_read_unlock_sched();
-
-                        if (overflow)
-                                return notifier_from_errno(-EBUSY);
-                }
+                set_cpu_active((long)hcpu, false);
                 return NOTIFY_OK;
+        default:
+                return NOTIFY_DONE;
         }
-
-        return NOTIFY_DONE;
 }
 
 static int __init migration_init(void)
@@ -5430,17 +5442,6 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
                         break;
                 }
 
-                /*
-                 * Even though we initialize ->capacity to something semi-sane,
-                 * we leave capacity_orig unset. This allows us to detect if
-                 * domain iteration is still funny without causing /0 traps.
-                 */
-                if (!group->sgc->capacity_orig) {
-                        printk(KERN_CONT "\n");
-                        printk(KERN_ERR "ERROR: domain->cpu_capacity not set\n");
-                        break;
-                }
-
                 if (!cpumask_weight(sched_group_cpus(group))) {
                         printk(KERN_CONT "\n");
                         printk(KERN_ERR "ERROR: empty group\n");
@@ -5813,9 +5814,6 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
         update_top_cache_domain(cpu);
 }
 
-/* cpus with isolated domains */
-static cpumask_var_t cpu_isolated_map;
-
 /* Setup the mask of cpus configured for isolated domains */
 static int __init isolated_cpu_setup(char *str)
 {
@@ -5924,7 +5922,6 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
                  * die on a /0 trap.
                  */
                 sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
-                sg->sgc->capacity_orig = sg->sgc->capacity;
 
                 /*
                  * Make sure the first group of this domain contains the
@@ -6235,6 +6232,7 @@ sd_init(struct sched_domain_topology_level *tl, int cpu)
          */
 
         if (sd->flags & SD_SHARE_CPUCAPACITY) {
+                sd->flags |= SD_PREFER_SIBLING;
                 sd->imbalance_pct = 110;
                 sd->smt_gain = 1178; /* ~15% */
 
@@ -7000,7 +6998,6 @@ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action,
                  */
 
         case CPU_ONLINE:
-        case CPU_DOWN_FAILED:
                 cpuset_update_active_cpus(true);
                 break;
         default:
@@ -7012,8 +7009,30 @@ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action,
 static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action,
                                void *hcpu)
 {
-        switch (action) {
+        unsigned long flags;
+        long cpu = (long)hcpu;
+        struct dl_bw *dl_b;
+
+        switch (action & ~CPU_TASKS_FROZEN) {
         case CPU_DOWN_PREPARE:
+                /* explicitly allow suspend */
+                if (!(action & CPU_TASKS_FROZEN)) {
+                        bool overflow;
+                        int cpus;
+
+                        rcu_read_lock_sched();
+                        dl_b = dl_bw_of(cpu);
+
+                        raw_spin_lock_irqsave(&dl_b->lock, flags);
+                        cpus = dl_bw_cpus(cpu);
+                        overflow = __dl_overflow(dl_b, cpus, 0, 0);
+                        raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+
+                        rcu_read_unlock_sched();
+
+                        if (overflow)
+                                return notifier_from_errno(-EBUSY);
+                }
                 cpuset_update_active_cpus(false);
                 break;
         case CPU_DOWN_PREPARE_FROZEN:
@@ -7158,8 +7177,8 @@ void __init sched_init(void)
                 rq->calc_load_active = 0;
                 rq->calc_load_update = jiffies + LOAD_FREQ;
                 init_cfs_rq(&rq->cfs);
-                init_rt_rq(&rq->rt, rq);
-                init_dl_rq(&rq->dl, rq);
+                init_rt_rq(&rq->rt);
+                init_dl_rq(&rq->dl);
 #ifdef CONFIG_FAIR_GROUP_SCHED
                 root_task_group.shares = ROOT_TASK_GROUP_LOAD;
                 INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
@@ -7199,7 +7218,7 @@ void __init sched_init(void)
 #ifdef CONFIG_SMP
                 rq->sd = NULL;
                 rq->rd = NULL;
-                rq->cpu_capacity = SCHED_CAPACITY_SCALE;
+                rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE;
                 rq->post_schedule = 0;
                 rq->active_balance = 0;
                 rq->next_balance = jiffies;
@@ -7798,7 +7817,7 @@ static int sched_rt_global_constraints(void)
 }
 #endif /* CONFIG_RT_GROUP_SCHED */
 
-static int sched_dl_global_constraints(void)
+static int sched_dl_global_validate(void)
 {
         u64 runtime = global_rt_runtime();
         u64 period = global_rt_period();
@@ -7899,11 +7918,11 @@ int sched_rt_handler(struct ctl_table *table, int write,
                 if (ret)
                         goto undo;
 
-                ret = sched_rt_global_constraints();
+                ret = sched_dl_global_validate();
                 if (ret)
                         goto undo;
 
-                ret = sched_dl_global_constraints();
+                ret = sched_rt_global_constraints();
                 if (ret)
                         goto undo;