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

Pull scheduler fixes from Ingo Molnar:
 "Misc fixes"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched: Fix comment for sched_info_depart
  sched/Documentation: Update sched-design-CFS.txt documentation
  sched/debug: Take PID namespace into account
  sched/fair: Fix small race where child->se.parent,cfs_rq might point to invalid ones

4 files changed, 16 insertions, 13 deletions

diff --git a/Documentation/scheduler/sched-design-CFS.txt b/Documentation/scheduler/sched-design-CFS.txt
index d529e02d928d..f14f49304222 100644
--- a/Documentation/scheduler/sched-design-CFS.txt
+++ b/Documentation/scheduler/sched-design-CFS.txt
@@ -66,9 +66,7 @@ rq->cfs.load value, which is the sum of the weights of the tasks queued on the
 runqueue.
 
 CFS maintains a time-ordered rbtree, where all runnable tasks are sorted by the
-p->se.vruntime key (there is a subtraction using rq->cfs.min_vruntime to
-account for possible wraparounds).  CFS picks the "leftmost" task from this
-tree and sticks to it.
+p->se.vruntime key. CFS picks the "leftmost" task from this tree and sticks to it.
 As the system progresses forwards, the executed tasks are put into the tree
 more and more to the right --- slowly but surely giving a chance for every task
 to become the "leftmost task" and thus get on the CPU within a deterministic
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index e076bddd4c66..196559994f7c 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -124,7 +124,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
                 SEQ_printf(m, " ");
 
         SEQ_printf(m, "%15s %5d %9Ld.%06ld %9Ld %5d ",
-                p->comm, p->pid,
+                p->comm, task_pid_nr(p),
                 SPLIT_NS(p->se.vruntime),
                 (long long)(p->nvcsw + p->nivcsw),
                 p->prio);
@@ -289,7 +289,7 @@ do {									\
         P(nr_load_updates);
         P(nr_uninterruptible);
         PN(next_balance);
-        P(curr->pid);
+        SEQ_printf(m, "  .%-30s: %ld\n", "curr->pid", (long)(task_pid_nr(rq->curr)));
         PN(clock);
         P(cpu_load[0]);
         P(cpu_load[1]);
@@ -492,7 +492,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 {
         unsigned long nr_switches;
 
-        SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, p->pid,
+        SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, task_pid_nr(p),
                                                 get_nr_threads(p));
         SEQ_printf(m,
                 "---------------------------------------------------------"
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9b3fe1cd8f40..11cd13667359 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5928,11 +5928,15 @@ static void task_fork_fair(struct task_struct *p)
         cfs_rq = task_cfs_rq(current);
         curr = cfs_rq->curr;
 
-        if (unlikely(task_cpu(p) != this_cpu)) {
-                rcu_read_lock();
-                __set_task_cpu(p, this_cpu);
-                rcu_read_unlock();
-        }
+        /*
+         * Not only the cpu but also the task_group of the parent might have
+         * been changed after parent->se.parent,cfs_rq were copied to
+         * child->se.parent,cfs_rq. So call __set_task_cpu() to make those
+         * of child point to valid ones.
+         */
+        rcu_read_lock();
+        __set_task_cpu(p, this_cpu);
+        rcu_read_unlock();
 
         update_curr(cfs_rq);
 
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 5aef494fc8b4..c7edee71bce8 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -104,8 +104,9 @@ static inline void sched_info_queued(struct task_struct *t)
 }
 
 /*
- * Called when a process ceases being the active-running process, either
- * voluntarily or involuntarily.  Now we can calculate how long we ran.
+ * Called when a process ceases being the active-running process involuntarily
+ * due, typically, to expiring its time slice (this may also be called when
+ * switching to the idle task).  Now we can calculate how long we ran.
  * Also, if the process is still in the TASK_RUNNING state, call
  * sched_info_queued() to mark that it has now again started waiting on
  * the runqueue.