Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

[safe/jmp/linux-2.6] / kernel / sched.c

diff --git a/kernel/sched.c b/kernel/sched.c
index 526d237..3c11ae0 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -309,6 +309,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq);
  */
 static DEFINE_SPINLOCK(task_group_lock);
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+
 #ifdef CONFIG_SMP
 static int root_task_group_empty(void)
 {
@@ -316,7 +318,6 @@ static int root_task_group_empty(void)
 }
 #endif
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
 #ifdef CONFIG_USER_SCHED
 # define INIT_TASK_GROUP_LOAD  (2*NICE_0_LOAD)
 #else /* !CONFIG_USER_SCHED */
@@ -676,6 +677,7 @@ inline void update_rq_clock(struct rq *rq)
 
 /**
  * runqueue_is_locked
+ * @cpu: the processor in question.
  *
  * Returns true if the current cpu runqueue is locked.
  * This interface allows printk to be called with the runqueue lock
@@ -780,7 +782,7 @@ static int sched_feat_open(struct inode *inode, struct file *filp)
        return single_open(filp, sched_feat_show, NULL);
 }
 
-static struct file_operations sched_feat_fops = {
+static const struct file_operations sched_feat_fops = {
        .open           = sched_feat_open,
        .write          = sched_feat_write,
        .read           = seq_read,
@@ -1991,6 +1993,38 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
                p->sched_class->prio_changed(rq, p, oldprio, running);
 }
 
+/**
+ * kthread_bind - bind a just-created kthread to a cpu.
+ * @p: thread created by kthread_create().
+ * @cpu: cpu (might not be online, must be possible) for @k to run on.
+ *
+ * Description: This function is equivalent to set_cpus_allowed(),
+ * except that @cpu doesn't need to be online, and the thread must be
+ * stopped (i.e., just returned from kthread_create()).
+ *
+ * Function lives here instead of kthread.c because it messes with
+ * scheduler internals which require locking.
+ */
+void kthread_bind(struct task_struct *p, unsigned int cpu)
+{
+       struct rq *rq = cpu_rq(cpu);
+       unsigned long flags;
+
+       /* Must have done schedule() in kthread() before we set_task_cpu */
+       if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
+               WARN_ON(1);
+               return;
+       }
+
+       spin_lock_irqsave(&rq->lock, flags);
+       set_task_cpu(p, cpu);
+       p->cpus_allowed = cpumask_of_cpu(cpu);
+       p->rt.nr_cpus_allowed = 1;
+       p->flags |= PF_THREAD_BOUND;
+       spin_unlock_irqrestore(&rq->lock, flags);
+}
+EXPORT_SYMBOL(kthread_bind);
+
 #ifdef CONFIG_SMP
 /*
  * Is this task likely cache-hot:
@@ -2003,7 +2037,7 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
        /*
         * Buddy candidates are cache hot:
         */
-       if (sched_feat(CACHE_HOT_BUDDY) &&
+       if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running &&
                        (&p->se == cfs_rq_of(&p->se)->next ||
                         &p->se == cfs_rq_of(&p->se)->last))
                return 1;
@@ -2307,7 +2341,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
 {
        int cpu, orig_cpu, this_cpu, success = 0;
        unsigned long flags;
-       struct rq *rq;
+       struct rq *rq, *orig_rq;
 
        if (!sched_feat(SYNC_WAKEUPS))
                wake_flags &= ~WF_SYNC;
@@ -2315,7 +2349,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
        this_cpu = get_cpu();
 
        smp_wmb();
-       rq = task_rq_lock(p, &flags);
+       rq = orig_rq = task_rq_lock(p, &flags);
        update_rq_clock(rq);
        if (!(p->state & state))
                goto out;
@@ -2346,6 +2380,10 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state,
                set_task_cpu(p, cpu);
 
        rq = task_rq_lock(p, &flags);
+
+       if (rq != orig_rq)
+               update_rq_clock(rq);
+
        WARN_ON(p->state != TASK_WAKING);
        cpu = task_cpu(p);
 
@@ -2511,22 +2549,17 @@ void sched_fork(struct task_struct *p, int clone_flags)
        __sched_fork(p);
 
        /*
-        * Make sure we do not leak PI boosting priority to the child.
-        */
-       p->prio = current->normal_prio;
-
-       /*
         * Revert to default priority/policy on fork if requested.
         */
        if (unlikely(p->sched_reset_on_fork)) {
-               if (p->policy == SCHED_FIFO || p->policy == SCHED_RR)
+               if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) {
                        p->policy = SCHED_NORMAL;
-
-               if (p->normal_prio < DEFAULT_PRIO)
-                       p->prio = DEFAULT_PRIO;
+                       p->normal_prio = p->static_prio;
+               }
 
                if (PRIO_TO_NICE(p->static_prio) < 0) {
                        p->static_prio = NICE_TO_PRIO(0);
+                       p->normal_prio = p->static_prio;
                        set_load_weight(p);
                }
 
@@ -2537,6 +2570,11 @@ void sched_fork(struct task_struct *p, int clone_flags)
                p->sched_reset_on_fork = 0;
        }
 
+       /*
+        * Make sure we do not leak PI boosting priority to the child.
+        */
+       p->prio = current->normal_prio;
+
        if (!rt_prio(p->prio))
                p->sched_class = &fair_sched_class;
 
@@ -2577,8 +2615,6 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
        BUG_ON(p->state != TASK_RUNNING);
        update_rq_clock(rq);
 
-       p->prio = effective_prio(p);
-
        if (!p->sched_class->task_new || !current->se.on_rq) {
                activate_task(rq, p, 0);
        } else {
@@ -3654,6 +3690,7 @@ static void update_group_power(struct sched_domain *sd, int cpu)
 
 /**
  * update_sg_lb_stats - Update sched_group's statistics for load balancing.
+ * @sd: The sched_domain whose statistics are to be updated.
  * @group: sched_group whose statistics are to be updated.
  * @this_cpu: Cpu for which load balance is currently performed.
  * @idle: Idle status of this_cpu
@@ -6716,9 +6753,6 @@ EXPORT_SYMBOL(yield);
 /*
  * This task is about to go to sleep on IO. Increment rq->nr_iowait so
  * that process accounting knows that this is a task in IO wait state.
- *
- * But don't do that if it is a deliberate, throttling IO wait (this task
- * has set its backing_dev_info: the queue against which it should throttle)
  */
 void __sched io_schedule(void)
 {
@@ -9531,13 +9565,13 @@ void __init sched_init(void)
        current->sched_class = &fair_sched_class;
 
        /* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
-       alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
+       zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
 #ifdef CONFIG_SMP
 #ifdef CONFIG_NO_HZ
-       alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
+       zalloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
        alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT);
 #endif
-       alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
+       zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
 #endif /* SMP */
 
        perf_event_init();