sched: Do not consider SCHED_IDLE tasks to be cache hot

[firefly-linux-kernel-4.4.55.git] / kernel / sched.c

diff --git a/kernel/sched.c b/kernel/sched.c
index 2111491f642473e5b2a3662462f03266678473ac..771b518e5f1f9f522fe0403f34f884f9aa045f83 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -486,7 +486,7 @@ struct rq {
         */
        unsigned long nr_uninterruptible;
 
-       struct task_struct *curr, *idle;
+       struct task_struct *curr, *idle, *stop;
        unsigned long next_balance;
        struct mm_struct *prev_mm;
 
@@ -1837,7 +1837,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 
 static const struct sched_class rt_sched_class;
 
-#define sched_class_highest (&rt_sched_class)
+#define sched_class_highest (&stop_sched_class)
 #define for_each_class(class) \
    for (class = sched_class_highest; class; class = class->next)
 
@@ -1855,12 +1855,6 @@ static void dec_nr_running(struct rq *rq)
 
 static void set_load_weight(struct task_struct *p)
 {
-       if (task_has_rt_policy(p)) {
-               p->se.load.weight = 0;
-               p->se.load.inv_weight = WMULT_CONST;
-               return;
-       }
-
        /*
         * SCHED_IDLE tasks get minimal weight:
         */
@@ -1917,10 +1911,41 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 #include "sched_idletask.c"
 #include "sched_fair.c"
 #include "sched_rt.c"
+#include "sched_stoptask.c"
 #ifdef CONFIG_SCHED_DEBUG
 # include "sched_debug.c"
 #endif
 
+void sched_set_stop_task(int cpu, struct task_struct *stop)
+{
+       struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
+       struct task_struct *old_stop = cpu_rq(cpu)->stop;
+
+       if (stop) {
+               /*
+                * Make it appear like a SCHED_FIFO task, its something
+                * userspace knows about and won't get confused about.
+                *
+                * Also, it will make PI more or less work without too
+                * much confusion -- but then, stop work should not
+                * rely on PI working anyway.
+                */
+               sched_setscheduler_nocheck(stop, SCHED_FIFO, &param);
+
+               stop->sched_class = &stop_sched_class;
+       }
+
+       cpu_rq(cpu)->stop = stop;
+
+       if (old_stop) {
+               /*
+                * Reset it back to a normal scheduling class so that
+                * it can die in pieces.
+                */
+               old_stop->sched_class = &rt_sched_class;
+       }
+}
+
 /*
  * __normal_prio - return the priority that is based on the static prio
  */
@@ -2000,6 +2025,9 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
        if (p->sched_class != &fair_sched_class)
                return 0;
 
+       if (unlikely(p->policy == SCHED_IDLE))
+               return 0;
+
        /*
         * Buddy candidates are cache hot:
         */
@@ -3720,17 +3748,13 @@ pick_next_task(struct rq *rq)
                        return p;
        }
 
-       class = sched_class_highest;
-       for ( ; ; ) {
+       for_each_class(class) {
                p = class->pick_next_task(rq);
                if (p)
                        return p;
-               /*
-                * Will never be NULL as the idle class always
-                * returns a non-NULL p:
-                */
-               class = class->next;
        }
+
+       BUG(); /* the idle class will always have a runnable task */
 }
 
 /*
@@ -4659,6 +4683,15 @@ recheck:
         */
        rq = __task_rq_lock(p);
 
+       /*
+        * Changing the policy of the stop threads its a very bad idea
+        */
+       if (p == rq->stop) {
+               __task_rq_unlock(rq);
+               raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+               return -EINVAL;
+       }
+
 #ifdef CONFIG_RT_GROUP_SCHED
        if (user) {
                /*
@@ -4891,7 +4924,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 
        cpuset_cpus_allowed(p, cpus_allowed);
        cpumask_and(new_mask, in_mask, cpus_allowed);
- again:
+again:
        retval = set_cpus_allowed_ptr(p, new_mask);
 
        if (!retval) {
@@ -8141,9 +8174,9 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 
        return 1;
 
- err_free_rq:
+err_free_rq:
        kfree(cfs_rq);
- err:
+err:
        return 0;
 }
 
@@ -8231,9 +8264,9 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 
        return 1;
 
- err_free_rq:
+err_free_rq:
        kfree(rt_rq);
- err:
+err:
        return 0;
 }
 
@@ -8591,7 +8624,7 @@ static int tg_set_bandwidth(struct task_group *tg,
                raw_spin_unlock(&rt_rq->rt_runtime_lock);
        }
        raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
- unlock:
+unlock:
        read_unlock(&tasklist_lock);
        mutex_unlock(&rt_constraints_mutex);