Merge git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus

[linux-2.6] / kernel / sched.c

diff --git a/kernel/sched.c b/kernel/sched.c
index 5ea2c533b43244c509db38adf29c4b5847729b1c..ba4c88088f62c53ab8ec414e3d77da65b1cd9f67 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -442,6 +442,7 @@ struct rq {
        struct cfs_rq cfs;
        struct rt_rq rt;
        u64 rt_period_expire;
+       int rt_throttled;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
        /* list of leaf cfs_rq on this cpu: */
@@ -464,7 +465,7 @@ struct rq {
        u64 clock, prev_clock_raw;
        s64 clock_max_delta;
 
-       unsigned int clock_warps, clock_overflows;
+       unsigned int clock_warps, clock_overflows, clock_underflows;
        u64 idle_clock;
        unsigned int clock_deep_idle_events;
        u64 tick_timestamp;
@@ -594,6 +595,23 @@ static void update_rq_clock(struct rq *rq)
 #define task_rq(p)             cpu_rq(task_cpu(p))
 #define cpu_curr(cpu)          (cpu_rq(cpu)->curr)
 
+unsigned long rt_needs_cpu(int cpu)
+{
+       struct rq *rq = cpu_rq(cpu);
+       u64 delta;
+
+       if (!rq->rt_throttled)
+               return 0;
+
+       if (rq->clock > rq->rt_period_expire)
+               return 1;
+
+       delta = rq->rt_period_expire - rq->clock;
+       do_div(delta, NSEC_PER_SEC / HZ);
+
+       return (unsigned long)delta;
+}
+
 /*
  * Tunables that become constants when CONFIG_SCHED_DEBUG is off:
  */
@@ -840,7 +858,6 @@ void sched_clock_idle_wakeup_event(u64 delta_ns)
        struct rq *rq = cpu_rq(smp_processor_id());
        u64 now = sched_clock();
 
-       touch_softlockup_watchdog();
        rq->idle_clock += delta_ns;
        /*
         * Override the previous timestamp and ignore all
@@ -852,6 +869,7 @@ void sched_clock_idle_wakeup_event(u64 delta_ns)
        rq->prev_clock_raw = now;
        rq->clock += delta_ns;
        spin_unlock(&rq->lock);
+       touch_softlockup_watchdog();
 }
 EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 
@@ -3718,8 +3736,10 @@ void scheduler_tick(void)
        /*
         * Let rq->clock advance by at least TICK_NSEC:
         */
-       if (unlikely(rq->clock < next_tick))
+       if (unlikely(rq->clock < next_tick)) {
                rq->clock = next_tick;
+               rq->clock_underflows++;
+       }
        rq->tick_timestamp = rq->clock;
        update_cpu_load(rq);
        curr->sched_class->task_tick(rq, curr, 0);
@@ -3937,10 +3957,9 @@ EXPORT_SYMBOL(schedule);
 asmlinkage void __sched preempt_schedule(void)
 {
        struct thread_info *ti = current_thread_info();
-#ifdef CONFIG_PREEMPT_BKL
        struct task_struct *task = current;
        int saved_lock_depth;
-#endif
+
        /*
         * If there is a non-zero preempt_count or interrupts are disabled,
         * we do not want to preempt the current task. Just return..
@@ -3956,14 +3975,10 @@ asmlinkage void __sched preempt_schedule(void)
                 * clear ->lock_depth so that schedule() doesnt
                 * auto-release the semaphore:
                 */
-#ifdef CONFIG_PREEMPT_BKL
                saved_lock_depth = task->lock_depth;
                task->lock_depth = -1;
-#endif
                schedule();
-#ifdef CONFIG_PREEMPT_BKL
                task->lock_depth = saved_lock_depth;
-#endif
                sub_preempt_count(PREEMPT_ACTIVE);
 
                /*
@@ -3984,10 +3999,9 @@ EXPORT_SYMBOL(preempt_schedule);
 asmlinkage void __sched preempt_schedule_irq(void)
 {
        struct thread_info *ti = current_thread_info();
-#ifdef CONFIG_PREEMPT_BKL
        struct task_struct *task = current;
        int saved_lock_depth;
-#endif
+
        /* Catch callers which need to be fixed */
        BUG_ON(ti->preempt_count || !irqs_disabled());
 
@@ -3999,16 +4013,12 @@ asmlinkage void __sched preempt_schedule_irq(void)
                 * clear ->lock_depth so that schedule() doesnt
                 * auto-release the semaphore:
                 */
-#ifdef CONFIG_PREEMPT_BKL
                saved_lock_depth = task->lock_depth;
                task->lock_depth = -1;
-#endif
                local_irq_enable();
                schedule();
                local_irq_disable();
-#ifdef CONFIG_PREEMPT_BKL
                task->lock_depth = saved_lock_depth;
-#endif
                sub_preempt_count(PREEMPT_ACTIVE);
 
                /*
@@ -4935,19 +4945,15 @@ EXPORT_SYMBOL(_cond_resched);
  */
 int cond_resched_lock(spinlock_t *lock)
 {
+       int resched = need_resched() && system_state == SYSTEM_RUNNING;
        int ret = 0;
 
-       if (need_lockbreak(lock)) {
+       if (spin_needbreak(lock) || resched) {
                spin_unlock(lock);
-               cpu_relax();
-               ret = 1;
-               spin_lock(lock);
-       }
-       if (need_resched() && system_state == SYSTEM_RUNNING) {
-               spin_release(&lock->dep_map, 1, _THIS_IP_);
-               _raw_spin_unlock(lock);
-               preempt_enable_no_resched();
-               __cond_resched();
+               if (resched && need_resched())
+                       __cond_resched();
+               else
+                       cpu_relax();
                ret = 1;
                spin_lock(lock);
        }
@@ -5151,8 +5157,7 @@ void sched_show_task(struct task_struct *p)
        printk(KERN_CONT "%5lu %5d %6d\n", free,
                task_pid_nr(p), task_pid_nr(p->real_parent));
 
-       if (state != TASK_RUNNING)
-               show_stack(p, NULL);
+       show_stack(p, NULL);
 }
 
 void show_state_filter(unsigned long state_filter)
@@ -5223,11 +5228,8 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
        spin_unlock_irqrestore(&rq->lock, flags);
 
        /* Set the preempt count _outside_ the spinlocks! */
-#if defined(CONFIG_PREEMPT) && !defined(CONFIG_PREEMPT_BKL)
-       task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0);
-#else
        task_thread_info(idle)->preempt_count = 0;
-#endif
+
        /*
         * The idle tasks have their own, simple scheduling class:
         */
@@ -7102,9 +7104,11 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
        /* delimiter for bitsearch: */
        __set_bit(MAX_RT_PRIO, array->bitmap);
 
+#if defined CONFIG_SMP || defined CONFIG_FAIR_GROUP_SCHED
+       rt_rq->highest_prio = MAX_RT_PRIO;
+#endif
 #ifdef CONFIG_SMP
        rt_rq->rt_nr_migratory = 0;
-       rt_rq->highest_prio = MAX_RT_PRIO;
        rt_rq->overloaded = 0;
 #endif
 
@@ -7191,6 +7195,7 @@ void __init sched_init(void)
                                &per_cpu(init_sched_rt_entity, i), i, 1);
 #endif
                rq->rt_period_expire = 0;
+               rq->rt_throttled = 0;
 
                for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
                        rq->cpu_load[j] = 0;