Merge master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6 into next

1 files changed, 40 insertions, 9 deletions

diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index 5bae2e0c3ff2..8385d43987e2 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -67,6 +67,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
                 preempt_enable();
 #endif
         }
+        kfree(mask_str);
         return 0;
 }
 
@@ -117,6 +118,13 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta)
         if (rq)
                 rq->rq_sched_info.cpu_time += delta;
 }
+
+static inline void
+rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
+{
+        if (rq)
+                rq->rq_sched_info.run_delay += delta;
+}
 # define schedstat_inc(rq, field)       do { (rq)->field++; } while (0)
 # define schedstat_add(rq, field, amt)  do { (rq)->field += (amt); } while (0)
 # define schedstat_set(var, val)        do { var = (val); } while (0)
@@ -125,6 +133,9 @@ static inline void
 rq_sched_info_arrive(struct rq *rq, unsigned long long delta)
 {}
 static inline void
+rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
+{}
+static inline void
 rq_sched_info_depart(struct rq *rq, unsigned long long delta)
 {}
 # define schedstat_inc(rq, field)       do { } while (0)
@@ -133,6 +144,11 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta)
 #endif
 
 #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
+static inline void sched_info_reset_dequeued(struct task_struct *t)
+{
+        t->sched_info.last_queued = 0;
+}
+
 /*
  * Called when a process is dequeued from the active array and given
  * the cpu.  We should note that with the exception of interactive
@@ -142,15 +158,22 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta)
  * active queue, thus delaying tasks in the expired queue from running;
  * see scheduler_tick()).
  *
- * This function is only called from sched_info_arrive(), rather than
- * dequeue_task(). Even though a task may be queued and dequeued multiple
- * times as it is shuffled about, we're really interested in knowing how
- * long it was from the *first* time it was queued to the time that it
- * finally hit a cpu.
+ * Though we are interested in knowing how long it was from the *first* time a
+ * task was queued to the time that it finally hit a cpu, we call this routine
+ * from dequeue_task() to account for possible rq->clock skew across cpus. The
+ * delta taken on each cpu would annul the skew.
  */
 static inline void sched_info_dequeued(struct task_struct *t)
 {
-        t->sched_info.last_queued = 0;
+        unsigned long long now = task_rq(t)->clock, delta = 0;
+
+        if (unlikely(sched_info_on()))
+                if (t->sched_info.last_queued)
+                        delta = now - t->sched_info.last_queued;
+        sched_info_reset_dequeued(t);
+        t->sched_info.run_delay += delta;
+
+        rq_sched_info_dequeued(task_rq(t), delta);
 }
 
 /*
@@ -164,7 +187,7 @@ static void sched_info_arrive(struct task_struct *t)
 
         if (t->sched_info.last_queued)
                 delta = now - t->sched_info.last_queued;
-        sched_info_dequeued(t);
+        sched_info_reset_dequeued(t);
         t->sched_info.run_delay += delta;
         t->sched_info.last_arrival = now;
         t->sched_info.pcount++;
@@ -197,6 +220,9 @@ 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.
+ * 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.
  */
 static inline void sched_info_depart(struct task_struct *t)
 {
@@ -205,6 +231,9 @@ static inline void sched_info_depart(struct task_struct *t)
 
         t->sched_info.cpu_time += delta;
         rq_sched_info_depart(task_rq(t), delta);
+
+        if (t->state == TASK_RUNNING)
+                sched_info_queued(t);
 }
 
 /*
@@ -235,7 +264,9 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next)
                 __sched_info_switch(prev, next);
 }
 #else
-#define sched_info_queued(t)            do { } while (0)
-#define sched_info_switch(t, next)      do { } while (0)
+#define sched_info_queued(t)                    do { } while (0)
+#define sched_info_reset_dequeued(t)    do { } while (0)
+#define sched_info_dequeued(t)                  do { } while (0)
+#define sched_info_switch(t, next)              do { } while (0)
 #endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */