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

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  sched: Fix/clarify set_task_cpu() locking rules
  lockdep: Fix lock_is_held() on recursion
  sched: Fix schedstat.nr_wakeups_migrate
  sched: Fix cross-cpu clock sync on remote wakeups

3 files changed, 26 insertions, 10 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2a8621c4be1e..a837b20ba190 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1063,6 +1063,7 @@ struct sched_domain;
  */
 #define WF_SYNC		0x01		/* waker goes to sleep after wakup */
 #define WF_FORK		0x02		/* child wakeup after fork */
+#define WF_MIGRATED	0x04		/* internal use, task got migrated */
 
 #define ENQUEUE_WAKEUP		1
 #define ENQUEUE_HEAD		2
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 63437d065ac8..298c9276dfdb 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -3426,7 +3426,7 @@ int lock_is_held(struct lockdep_map *lock)
 	int ret = 0;
 
 	if (unlikely(current->lockdep_recursion))
-		return ret;
+		return 1; /* avoid false negative lockdep_assert_held() */
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
diff --git a/kernel/sched.c b/kernel/sched.c
index cbb3a0eee58e..3f2e502d609b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -605,10 +605,10 @@ static inline int cpu_of(struct rq *rq)
 /*
  * Return the group to which this tasks belongs.
  *
- * We use task_subsys_state_check() and extend the RCU verification
- * with lockdep_is_held(&p->pi_lock) because cpu_cgroup_attach()
- * holds that lock for each task it moves into the cgroup. Therefore
- * by holding that lock, we pin the task to the current cgroup.
+ * We use task_subsys_state_check() and extend the RCU verification with
+ * pi->lock and rq->lock because cpu_cgroup_attach() holds those locks for each
+ * task it moves into the cgroup. Therefore by holding either of those locks,
+ * we pin the task to the current cgroup.
  */
 static inline struct task_group *task_group(struct task_struct *p)
 {
@@ -616,7 +616,8 @@ static inline struct task_group *task_group(struct task_struct *p)
 	struct cgroup_subsys_state *css;
 
 	css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
-			lockdep_is_held(&p->pi_lock));
+			lockdep_is_held(&p->pi_lock) ||
+			lockdep_is_held(&task_rq(p)->lock));
 	tg = container_of(css, struct task_group, css);
 
 	return autogroup_task_group(p, tg);
@@ -2200,6 +2201,16 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 			!(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE));
 
 #ifdef CONFIG_LOCKDEP
+	/*
+	 * The caller should hold either p->pi_lock or rq->lock, when changing
+	 * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
+	 *
+	 * sched_move_task() holds both and thus holding either pins the cgroup,
+	 * see set_task_rq().
+	 *
+	 * Furthermore, all task_rq users should acquire both locks, see
+	 * task_rq_lock().
+	 */
 	WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
 				      lockdep_is_held(&task_rq(p)->lock)));
 #endif
@@ -2447,6 +2458,10 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 		}
 		rcu_read_unlock();
 	}
+
+	if (wake_flags & WF_MIGRATED)
+		schedstat_inc(p, se.statistics.nr_wakeups_migrate);
+
 #endif /* CONFIG_SMP */
 
 	schedstat_inc(rq, ttwu_count);
@@ -2455,9 +2470,6 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 	if (wake_flags & WF_SYNC)
 		schedstat_inc(p, se.statistics.nr_wakeups_sync);
 
-	if (cpu != task_cpu(p))
-		schedstat_inc(p, se.statistics.nr_wakeups_migrate);
-
 #endif /* CONFIG_SCHEDSTATS */
 }
 
@@ -2600,6 +2612,7 @@ static void ttwu_queue(struct task_struct *p, int cpu)
 
 #if defined(CONFIG_SMP)
 	if (sched_feat(TTWU_QUEUE) && cpu != smp_processor_id()) {
+		sched_clock_cpu(cpu); /* sync clocks x-cpu */
 		ttwu_queue_remote(p, cpu);
 		return;
 	}
@@ -2674,8 +2687,10 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		p->sched_class->task_waking(p);
 
 	cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
-	if (task_cpu(p) != cpu)
+	if (task_cpu(p) != cpu) {
+		wake_flags |= WF_MIGRATED;
 		set_task_cpu(p, cpu);
+	}
 #endif /* CONFIG_SMP */
 
 	ttwu_queue(p, cpu);