Merge branch 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  sched: Fix kthread_bind() by moving the body of kthread_bind() to sched.c
  sched: Disable SD_PREFER_LOCAL at node level
  sched: Fix boot crash by zalloc()ing most of the cpu masks
  sched: Strengthen buddies and mitigate buddy induced latencies

4 files changed, 84 insertions, 54 deletions

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index d823c245f63b..40e37b10c6c0 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -143,7 +143,7 @@ extern unsigned long node_remap_size[];
                                 | 1*SD_BALANCE_FORK                     \
                                 | 0*SD_BALANCE_WAKE                     \
                                 | 1*SD_WAKE_AFFINE                      \
-                                | 1*SD_PREFER_LOCAL                     \
+                                | 0*SD_PREFER_LOCAL                     \
                                 | 0*SD_SHARE_CPUPOWER                   \
                                 | 0*SD_POWERSAVINGS_BALANCE             \
                                 | 0*SD_SHARE_PKG_RESOURCES              \
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 5fe709982caa..ab7ae57773e1 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -150,29 +150,6 @@ struct task_struct *kthread_create(int (*threadfn)(void *data),
 EXPORT_SYMBOL(kthread_create);
 
 /**
- * kthread_bind - bind a just-created kthread to a cpu.
- * @k: 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()).
- */
-void kthread_bind(struct task_struct *k, unsigned int cpu)
-{
-        /* Must have done schedule() in kthread() before we set_task_cpu */
-        if (!wait_task_inactive(k, TASK_UNINTERRUPTIBLE)) {
-                WARN_ON(1);
-                return;
-        }
-        set_task_cpu(k, cpu);
-        k->cpus_allowed = cpumask_of_cpu(cpu);
-        k->rt.nr_cpus_allowed = 1;
-        k->flags |= PF_THREAD_BOUND;
-}
-EXPORT_SYMBOL(kthread_bind);
-
-/**
  * kthread_stop - stop a thread created by kthread_create().
  * @k: thread created by kthread_create().
  *
diff --git a/kernel/sched.c b/kernel/sched.c
index a455dca884a6..28dd4f490bfc 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1992,6 +1992,38 @@ 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.
+ * @k: 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:
@@ -2004,7 +2036,7 @@ 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;
@@ -9532,13 +9564,13 @@ 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();
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index c32c3e643daa..37087a7fac22 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -822,6 +822,26 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
                  * re-elected due to buddy favours.
                  */
                 clear_buddies(cfs_rq, curr);
+                return;
+        }
+
+        /*
+         * Ensure that a task that missed wakeup preemption by a
+         * narrow margin doesn't have to wait for a full slice.
+         * This also mitigates buddy induced latencies under load.
+         */
+        if (!sched_feat(WAKEUP_PREEMPT))
+                return;
+
+        if (delta_exec < sysctl_sched_min_granularity)
+                return;
+
+        if (cfs_rq->nr_running > 1) {
+                struct sched_entity *se = __pick_next_entity(cfs_rq);
+                s64 delta = curr->vruntime - se->vruntime;
+
+                if (delta > ideal_runtime)
+                        resched_task(rq_of(cfs_rq)->curr);
         }
 }
 
@@ -861,21 +881,18 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
 static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 {
         struct sched_entity *se = __pick_next_entity(cfs_rq);
-        struct sched_entity *buddy;
+        struct sched_entity *left = se;
 
-        if (cfs_rq->next) {
-                buddy = cfs_rq->next;
-                cfs_rq->next = NULL;
-                if (wakeup_preempt_entity(buddy, se) < 1)
-                        return buddy;
-        }
+        if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
+                se = cfs_rq->next;
 
-        if (cfs_rq->last) {
-                buddy = cfs_rq->last;
-                cfs_rq->last = NULL;
-                if (wakeup_preempt_entity(buddy, se) < 1)
-                        return buddy;
-        }
+        /*
+         * Prefer last buddy, try to return the CPU to a preempted task.
+         */
+        if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
+                se = cfs_rq->last;
+
+        clear_buddies(cfs_rq, se);
 
         return se;
 }
@@ -1577,6 +1594,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
         struct sched_entity *se = &curr->se, *pse = &p->se;
         struct cfs_rq *cfs_rq = task_cfs_rq(curr);
         int sync = wake_flags & WF_SYNC;
+        int scale = cfs_rq->nr_running >= sched_nr_latency;
 
         update_curr(cfs_rq);
 
@@ -1591,18 +1609,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
         if (unlikely(se == pse))
                 return;
 
-        /*
-         * Only set the backward buddy when the current task is still on the
-         * rq. This can happen when a wakeup gets interleaved with schedule on
-         * the ->pre_schedule() or idle_balance() point, either of which can
-         * drop the rq lock.
-         *
-         * Also, during early boot the idle thread is in the fair class, for
-         * obvious reasons its a bad idea to schedule back to the idle thread.
-         */
-        if (sched_feat(LAST_BUDDY) && likely(se->on_rq && curr != rq->idle))
-                set_last_buddy(se);
-        if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK))
+        if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK))
                 set_next_buddy(pse);
 
         /*
@@ -1648,8 +1655,22 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 
         BUG_ON(!pse);
 
-        if (wakeup_preempt_entity(se, pse) == 1)
+        if (wakeup_preempt_entity(se, pse) == 1) {
                 resched_task(curr);
+                /*
+                 * Only set the backward buddy when the current task is still
+                 * on the rq. This can happen when a wakeup gets interleaved
+                 * with schedule on the ->pre_schedule() or idle_balance()
+                 * point, either of which can * drop the rq lock.
+                 *
+                 * Also, during early boot the idle thread is in the fair class,
+                 * for obvious reasons its a bad idea to schedule back to it.
+                 */
+                if (unlikely(!se->on_rq || curr == rq->idle))
+                        return;
+                if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se))
+                        set_last_buddy(se);
+        }
 }
 
 static struct task_struct *pick_next_task_fair(struct rq *rq)