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 nr_uninterruptible accounting of frozen tasks really
  sched: fix load average accounting vs. cpu hotplug
  sched: Account for vruntime wrapping

4 files changed, 19 insertions, 5 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 16a982e389fb..3ab08e4bb6b8 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -209,7 +209,7 @@ extern unsigned long long time_sync_thresh;
                         ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
 #define task_contributes_to_load(task)  \
                                 ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
-                                 (task->flags & PF_FROZEN) == 0)
+                                 (task->flags & PF_FREEZING) == 0)
 
 #define __set_task_state(tsk, state_value)              \
         do { (tsk)->state = (state_value); } while (0)
@@ -1680,6 +1680,7 @@ extern cputime_t task_gtime(struct task_struct *p);
 #define PF_MEMALLOC     0x00000800      /* Allocating memory */
 #define PF_FLUSHER      0x00001000      /* responsible for disk writeback */
 #define PF_USED_MATH    0x00002000      /* if unset the fpu must be initialized before use */
+#define PF_FREEZING     0x00004000      /* freeze in progress. do not account to load */
 #define PF_NOFREEZE     0x00008000      /* this thread should not be frozen */
 #define PF_FROZEN       0x00010000      /* frozen for system suspend */
 #define PF_FSTRANS      0x00020000      /* inside a filesystem transaction */
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 2f4936cf7083..bd1d42b17cb2 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -44,12 +44,19 @@ void refrigerator(void)
         recalc_sigpending(); /* We sent fake signal, clean it up */
         spin_unlock_irq(&current->sighand->siglock);
 
+        /* prevent accounting of that task to load */
+        current->flags |= PF_FREEZING;
+
         for (;;) {
                 set_current_state(TASK_UNINTERRUPTIBLE);
                 if (!frozen(current))
                         break;
                 schedule();
         }
+
+        /* Remove the accounting blocker */
+        current->flags &= ~PF_FREEZING;
+
         pr_debug("%s left refrigerator\n", current->comm);
         __set_current_state(save);
 }
diff --git a/kernel/sched.c b/kernel/sched.c
index 98972d366fdc..1b59e265273b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -7289,6 +7289,7 @@ static void migrate_dead_tasks(unsigned int dead_cpu)
 static void calc_global_load_remove(struct rq *rq)
 {
         atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
+        rq->calc_load_active = 0;
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
@@ -7515,6 +7516,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
                 task_rq_unlock(rq, &flags);
                 get_task_struct(p);
                 cpu_rq(cpu)->migration_thread = p;
+                rq->calc_load_update = calc_load_update;
                 break;
 
         case CPU_ONLINE:
@@ -7525,8 +7527,6 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
                 /* Update our root-domain */
                 rq = cpu_rq(cpu);
                 spin_lock_irqsave(&rq->lock, flags);
-                rq->calc_load_update = calc_load_update;
-                rq->calc_load_active = 0;
                 if (rq->rd) {
                         BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
 
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 7c248dc30f41..9ffb2b2ceba4 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -266,6 +266,12 @@ static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)
         return min_vruntime;
 }
 
+static inline int entity_before(struct sched_entity *a,
+                                struct sched_entity *b)
+{
+        return (s64)(a->vruntime - b->vruntime) < 0;
+}
+
 static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
         return se->vruntime - cfs_rq->min_vruntime;
@@ -1017,7 +1023,7 @@ static void yield_task_fair(struct rq *rq)
         /*
          * Already in the rightmost position?
          */
-        if (unlikely(!rightmost || rightmost->vruntime < se->vruntime))
+        if (unlikely(!rightmost || entity_before(rightmost, se)))
                 return;
 
         /*
@@ -1713,7 +1719,7 @@ static void task_new_fair(struct rq *rq, struct task_struct *p)
 
         /* 'curr' will be NULL if the child belongs to a different group */
         if (sysctl_sched_child_runs_first && this_cpu == task_cpu(p) &&
-                        curr && curr->vruntime < se->vruntime) {
+                        curr && entity_before(curr, se)) {
                 /*
                  * Upon rescheduling, sched_class::put_prev_task() will place
                  * 'current' within the tree based on its new key value.