4 files changed, 14 insertions, 166 deletions

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 476cb0c0b4a4..de93a8176ca6 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1355,17 +1355,16 @@ static void migrate_hrtimers(int cpu)
         tick_cancel_sched_timer(cpu);
 
         local_irq_disable();
-
-        spin_lock(&new_base->lock);
-        spin_lock(&old_base->lock);
+        double_spin_lock(&new_base->lock, &old_base->lock,
+                         smp_processor_id() < cpu);
 
         for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
                 migrate_hrtimer_list(&old_base->clock_base[i],
                                      &new_base->clock_base[i]);
         }
-        spin_unlock(&old_base->lock);
-        spin_unlock(&new_base->lock);
 
+        double_spin_unlock(&new_base->lock, &old_base->lock,
+                           smp_processor_id() < cpu);
         local_irq_enable();
         put_cpu_var(hrtimer_bases);
 }
diff --git a/kernel/sched.c b/kernel/sched.c
index 5f102e6c7a4c..a4ca632c477c 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3006,23 +3006,6 @@ static inline void idle_balance(int cpu, struct rq *rq)
 }
 #endif
 
-static inline void wake_priority_sleeper(struct rq *rq)
-{
-#ifdef CONFIG_SCHED_SMT
-        if (!rq->nr_running)
-                return;
-
-        spin_lock(&rq->lock);
-        /*
-         * If an SMT sibling task has been put to sleep for priority
-         * reasons reschedule the idle task to see if it can now run.
-         */
-        if (rq->nr_running)
-                resched_task(rq->idle);
-        spin_unlock(&rq->lock);
-#endif
-}
-
 DEFINE_PER_CPU(struct kernel_stat, kstat);
 
 EXPORT_PER_CPU_SYMBOL(kstat);
@@ -3239,10 +3222,7 @@ void scheduler_tick(void)
 
         update_cpu_clock(p, rq, now);
 
-        if (p == rq->idle)
-                /* Task on the idle queue */
-                wake_priority_sleeper(rq);
-        else
+        if (p != rq->idle)
                 task_running_tick(rq, p);
 #ifdef CONFIG_SMP
         update_load(rq);
@@ -3251,136 +3231,6 @@ void scheduler_tick(void)
 #endif
 }
 
-#ifdef CONFIG_SCHED_SMT
-static inline void wakeup_busy_runqueue(struct rq *rq)
-{
-        /* If an SMT runqueue is sleeping due to priority reasons wake it up */
-        if (rq->curr == rq->idle && rq->nr_running)
-                resched_task(rq->idle);
-}
-
-/*
- * Called with interrupt disabled and this_rq's runqueue locked.
- */
-static void wake_sleeping_dependent(int this_cpu)
-{
-        struct sched_domain *tmp, *sd = NULL;
-        int i;
-
-        for_each_domain(this_cpu, tmp) {
-                if (tmp->flags & SD_SHARE_CPUPOWER) {
-                        sd = tmp;
-                        break;
-                }
-        }
-
-        if (!sd)
-                return;
-
-        for_each_cpu_mask(i, sd->span) {
-                struct rq *smt_rq = cpu_rq(i);
-
-                if (i == this_cpu)
-                        continue;
-                if (unlikely(!spin_trylock(&smt_rq->lock)))
-                        continue;
-
-                wakeup_busy_runqueue(smt_rq);
-                spin_unlock(&smt_rq->lock);
-        }
-}
-
-/*
- * number of 'lost' timeslices this task wont be able to fully
- * utilize, if another task runs on a sibling. This models the
- * slowdown effect of other tasks running on siblings:
- */
-static inline unsigned long
-smt_slice(struct task_struct *p, struct sched_domain *sd)
-{
-        return p->time_slice * (100 - sd->per_cpu_gain) / 100;
-}
-
-/*
- * To minimise lock contention and not have to drop this_rq's runlock we only
- * trylock the sibling runqueues and bypass those runqueues if we fail to
- * acquire their lock. As we only trylock the normal locking order does not
- * need to be obeyed.
- */
-static int
-dependent_sleeper(int this_cpu, struct rq *this_rq, struct task_struct *p)
-{
-        struct sched_domain *tmp, *sd = NULL;
-        int ret = 0, i;
-
-        /* kernel/rt threads do not participate in dependent sleeping */
-        if (!p->mm || rt_task(p))
-                return 0;
-
-        for_each_domain(this_cpu, tmp) {
-                if (tmp->flags & SD_SHARE_CPUPOWER) {
-                        sd = tmp;
-                        break;
-                }
-        }
-
-        if (!sd)
-                return 0;
-
-        for_each_cpu_mask(i, sd->span) {
-                struct task_struct *smt_curr;
-                struct rq *smt_rq;
-
-                if (i == this_cpu)
-                        continue;
-
-                smt_rq = cpu_rq(i);
-                if (unlikely(!spin_trylock(&smt_rq->lock)))
-                        continue;
-
-                smt_curr = smt_rq->curr;
-
-                if (!smt_curr->mm)
-                        goto unlock;
-
-                /*
-                 * If a user task with lower static priority than the
-                 * running task on the SMT sibling is trying to schedule,
-                 * delay it till there is proportionately less timeslice
-                 * left of the sibling task to prevent a lower priority
-                 * task from using an unfair proportion of the
-                 * physical cpu's resources. -ck
-                 */
-                if (rt_task(smt_curr)) {
-                        /*
-                         * With real time tasks we run non-rt tasks only
-                         * per_cpu_gain% of the time.
-                         */
-                        if ((jiffies % DEF_TIMESLICE) >
-                                (sd->per_cpu_gain * DEF_TIMESLICE / 100))
-                                        ret = 1;
-                } else {
-                        if (smt_curr->static_prio < p->static_prio &&
-                                !TASK_PREEMPTS_CURR(p, smt_rq) &&
-                                smt_slice(smt_curr, sd) > task_timeslice(p))
-                                        ret = 1;
-                }
-unlock:
-                spin_unlock(&smt_rq->lock);
-        }
-        return ret;
-}
-#else
-static inline void wake_sleeping_dependent(int this_cpu)
-{
-}
-static inline int
-dependent_sleeper(int this_cpu, struct rq *this_rq, struct task_struct *p)
-{
-        return 0;
-}
-#endif
-
 #if defined(CONFIG_PREEMPT) && defined(CONFIG_DEBUG_PREEMPT)
 
 void fastcall add_preempt_count(int val)
@@ -3507,7 +3357,6 @@ need_resched_nonpreemptible:
                 if (!rq->nr_running) {
                         next = rq->idle;
                         rq->expired_timestamp = 0;
-                        wake_sleeping_dependent(cpu);
                         goto switch_tasks;
                 }
         }
@@ -3547,8 +3396,6 @@ need_resched_nonpreemptible:
                 }
         }
         next->sleep_type = SLEEP_NORMAL;
-        if (rq->nr_running == 1 && dependent_sleeper(cpu, rq, next))
-                next = rq->idle;
 switch_tasks:
         if (next == rq->idle)
                 schedstat_inc(rq, sched_goidle);
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 193a0793af95..5b0e46b56fd0 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -55,16 +55,18 @@ static DEFINE_SPINLOCK(clocksource_lock);
 static char override_name[32];
 static int finished_booting;
 
-/* clocksource_done_booting - Called near the end of bootup
+/* clocksource_done_booting - Called near the end of core bootup
  *
- * Hack to avoid lots of clocksource churn at boot time
+ * Hack to avoid lots of clocksource churn at boot time.
+ * We use fs_initcall because we want this to start before
+ * device_initcall but after subsys_initcall.
  */
 static int __init clocksource_done_booting(void)
 {
         finished_booting = 1;
         return 0;
 }
-late_initcall(clocksource_done_booting);
+fs_initcall(clocksource_done_booting);
 
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 static LIST_HEAD(watchdog_list);
diff --git a/kernel/timer.c b/kernel/timer.c
index 6663a87f7304..8ad384253ef2 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1651,8 +1651,8 @@ static void __devinit migrate_timers(int cpu)
         new_base = get_cpu_var(tvec_bases);
 
         local_irq_disable();
-        spin_lock(&new_base->lock);
-        spin_lock(&old_base->lock);
+        double_spin_lock(&new_base->lock, &old_base->lock,
+                         smp_processor_id() < cpu);
 
         BUG_ON(old_base->running_timer);
 
@@ -1665,8 +1665,8 @@ static void __devinit migrate_timers(int cpu)
                 migrate_timer_list(new_base, old_base->tv5.vec + i);
         }
 
-        spin_unlock(&old_base->lock);
-        spin_unlock(&new_base->lock);
+        double_spin_unlock(&new_base->lock, &old_base->lock,
+                           smp_processor_id() < cpu);
         local_irq_enable();
         put_cpu_var(tvec_bases);
 }