sched: Update yield() docs

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

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d7c43227311d37c4182c0ed196c3fb84fa38a491..47614a5cdd475c5b17baeffb8cac6be0438eb1c0 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1284,7 +1284,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
         * leave kernel.
         */
        if (p->mm && printk_ratelimit()) {
-               printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n",
+               printk_sched("process %d (%s) no longer affine to cpu%d\n",
                                task_pid_nr(p), p->comm, cpu);
        }
 
@@ -1932,7 +1932,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
        local_irq_enable();
 #endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
        finish_lock_switch(rq, prev);
-       trace_sched_stat_sleeptime(current, rq->clock);
 
        fire_sched_in_preempt_notifiers(current);
        if (mm)
@@ -3221,14 +3220,14 @@ need_resched:
 
        post_schedule(rq);
 
-       preempt_enable_no_resched();
+       sched_preempt_enable_no_resched();
        if (need_resched())
                goto need_resched;
 }
 
 static inline void sched_submit_work(struct task_struct *tsk)
 {
-       if (!tsk->state)
+       if (!tsk->state || tsk_is_pi_blocked(tsk))
                return;
        /*
         * If we are going to sleep and we have plugged IO queued,
@@ -3247,6 +3246,18 @@ asmlinkage void __sched schedule(void)
 }
 EXPORT_SYMBOL(schedule);
 
+/**
+ * schedule_preempt_disabled - called with preemption disabled
+ *
+ * Returns with preemption disabled. Note: preempt_count must be 1
+ */
+void __sched schedule_preempt_disabled(void)
+{
+       sched_preempt_enable_no_resched();
+       schedule();
+       preempt_disable();
+}
+
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
 
 static inline bool owner_running(struct mutex *lock, struct task_struct *owner)
@@ -3407,9 +3418,9 @@ EXPORT_SYMBOL(__wake_up);
 /*
  * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
  */
-void __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
+void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr)
 {
-       __wake_up_common(q, mode, 1, 0, NULL);
+       __wake_up_common(q, mode, nr, 0, NULL);
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked);
 
@@ -3768,6 +3779,24 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
 
        rq = __task_rq_lock(p);
 
+       /*
+        * Idle task boosting is a nono in general. There is one
+        * exception, when PREEMPT_RT and NOHZ is active:
+        *
+        * The idle task calls get_next_timer_interrupt() and holds
+        * the timer wheel base->lock on the CPU and another CPU wants
+        * to access the timer (probably to cancel it). We can safely
+        * ignore the boosting request, as the idle CPU runs this code
+        * with interrupts disabled and will complete the lock
+        * protected section without being interrupted. So there is no
+        * real need to boost.
+        */
+       if (unlikely(p == rq->idle)) {
+               WARN_ON(p != rq->curr);
+               WARN_ON(p->pi_blocked_on);
+               goto out_unlock;
+       }
+
        trace_sched_pi_setprio(p, prio);
        oldprio = p->prio;
        prev_class = p->sched_class;
@@ -3791,11 +3820,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
                enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
 
        check_class_changed(rq, p, prev_class, oldprio);
+out_unlock:
        __task_rq_unlock(rq);
 }
-
 #endif
-
 void set_user_nice(struct task_struct *p, long nice)
 {
        int old_prio, delta, on_rq;
@@ -4475,7 +4503,7 @@ SYSCALL_DEFINE0(sched_yield)
        __release(rq->lock);
        spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
        do_raw_spin_unlock(&rq->lock);
-       preempt_enable_no_resched();
+       sched_preempt_enable_no_resched();
 
        schedule();
 
@@ -4549,8 +4577,24 @@ EXPORT_SYMBOL(__cond_resched_softirq);
 /**
  * yield - yield the current processor to other threads.
  *
- * This is a shortcut for kernel-space yielding - it marks the
- * thread runnable and calls sys_sched_yield().
+ * Do not ever use this function, there's a 99% chance you're doing it wrong.
+ *
+ * The scheduler is at all times free to pick the calling task as the most
+ * eligible task to run, if removing the yield() call from your code breaks
+ * it, its already broken.
+ *
+ * Typical broken usage is:
+ *
+ * while (!event)
+ *     yield();
+ *
+ * where one assumes that yield() will let 'the other' process run that will
+ * make event true. If the current task is a SCHED_FIFO task that will never
+ * happen. Never use yield() as a progress guarantee!!
+ *
+ * If you want to use yield() to wait for something, use wait_event().
+ * If you want to use yield() to be 'nice' for others, use cond_resched().
+ * If you still want to use yield(), do not!
  */
 void __sched yield(void)
 {
@@ -5382,7 +5426,7 @@ static int __cpuinit sched_cpu_active(struct notifier_block *nfb,
                                      unsigned long action, void *hcpu)
 {
        switch (action & ~CPU_TASKS_FROZEN) {
-       case CPU_ONLINE:
+       case CPU_STARTING:
        case CPU_DOWN_FAILED:
                set_cpu_active((long)hcpu, true);
                return NOTIFY_OK;
@@ -6931,6 +6975,9 @@ void __init sched_init(void)
                rq->online = 0;
                rq->idle_stamp = 0;
                rq->avg_idle = 2*sysctl_sched_migration_cost;
+
+               INIT_LIST_HEAD(&rq->cfs_tasks);
+
                rq_attach_root(rq, &def_root_domain);
 #ifdef CONFIG_NO_HZ
                rq->nohz_flags = 0;