[PATCH V3 04/10] sched/core: Prevent race condition between cpuset and __sched_setscheduler()

[Mathieu Poirier]

No synchronisation mechanism exist between the cpuset subsystem and calls
to function __sched_setscheduler().  As such it is possible that new root
domains are created on the cpuset side while a deadline acceptance test
is carried out in __sched_setscheduler(), leading to a potential oversell
of CPU bandwidth.

By making available the cpuset_mutex to the core scheduler it is possible
to prevent situations such as the one described above from happening.

Signed-off-by: Mathieu Poirier <mathieu.poirier@xxxxxxxxxx>
---
 include/linux/cpuset.h |  6 ++++++
 kernel/cgroup/cpuset.c | 16 ++++++++++++++++
 kernel/sched/core.c    |  9 +++++++++
 3 files changed, 31 insertions(+)

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 934633a05d20..4bbb3f5a3020 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -55,6 +55,8 @@ extern void cpuset_init_smp(void);
 extern void cpuset_force_rebuild(void);
 extern void cpuset_update_active_cpus(void);
 extern void cpuset_wait_for_hotplug(void);
+extern void cpuset_lock(void);
+extern void cpuset_unlock(void);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
 extern void cpuset_cpus_allowed_fallback(struct task_struct *p);
 extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
@@ -176,6 +178,10 @@ static inline void cpuset_update_active_cpus(void)
 
 static inline void cpuset_wait_for_hotplug(void) { }
 
+static inline void cpuset_lock(void) { }
+
+static inline void cpuset_unlock(void) { }
+
 static inline void cpuset_cpus_allowed(struct task_struct *p,
 				       struct cpumask *mask)
 {
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index d18c72e83de4..41f8391640e6 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2410,6 +2410,22 @@ void __init cpuset_init_smp(void)
 }
 
 /**
+ * cpuset_lock - Grab the cpuset_mutex from another subsysytem
+ */
+void cpuset_lock(void)
+{
+	mutex_lock(&cpuset_mutex);
+}
+
+/**
+ * cpuset_unlock - Release the cpuset_mutex from another subsysytem
+ */
+void cpuset_unlock(void)
+{
+	mutex_unlock(&cpuset_mutex);
+}
+
+/**
  * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset.
  * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed.
  * @pmask: pointer to struct cpumask variable to receive cpus_allowed set.
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f727c3d0064c..0d8badcf1f0f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4176,6 +4176,13 @@ static int __sched_setscheduler(struct task_struct *p,
 	}
 
 	/*
+	 * Make sure we don't race with the cpuset subsystem where root
+	 * domains can be rebuilt or modified while operations like DL
+	 * admission checks are carried out.
+	 */
+	cpuset_lock();
+
+	/*
 	 * Make sure no PI-waiters arrive (or leave) while we are
 	 * changing the priority of the task:
 	 *
@@ -4247,6 +4254,7 @@ static int __sched_setscheduler(struct task_struct *p,
 	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
 		policy = oldpolicy = -1;
 		task_rq_unlock(rq, p, &rf);
+		cpuset_unlock();
 		goto recheck;
 	}
 
@@ -4316,6 +4324,7 @@ static int __sched_setscheduler(struct task_struct *p,
 
 unlock:
 	task_rq_unlock(rq, p, &rf);
+	cpuset_unlock();
 	return retval;
 }
 
-- 
2.7.4