sched/core: Prevent race condition between cpuset and __sched_setscheduler()

No synchronisation mechanism exists 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.

Grab cpuset_rwsem read lock from core scheduler, so to prevent
situations such as the one described above from happening.

The only exception is normalize_rt_tasks() which needs to work under
tasklist_lock and can't therefore grab cpuset_rwsem. We are fine with
this, as this function is only called by sysrq and, if that gets
triggered, DEADLINE guarantees are already gone out of the window
anyway.

Tested-by: Dietmar Eggemann <[email protected]>
Signed-off-by: Juri Lelli <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

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_read_lock(void);
+extern void cpuset_read_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 +178,9 @@ static inline void cpuset_update_active_cpus(void)
 
 static inline void cpuset_wait_for_hotplug(void) { }
 
+static inline void cpuset_read_lock(void) { }
+static inline void cpuset_read_unlock(void) { }
+
 static inline void cpuset_cpus_allowed(struct task_struct *p,
 				       struct cpumask *mask)
 {

kernel/cgroup/cpuset.c

@@ -334,6 +334,17 @@ static struct cpuset top_cpuset = {
  */
 
 DEFINE_STATIC_PERCPU_RWSEM(cpuset_rwsem);
+
+void cpuset_read_lock(void)
+{
+	percpu_down_read(&cpuset_rwsem);
+}
+
+void cpuset_read_unlock(void)
+{
+	percpu_up_read(&cpuset_rwsem);
+}
+
 static DEFINE_SPINLOCK(callback_lock);
 
 static struct workqueue_struct *cpuset_migrate_mm_wq;

kernel/sched/core.c

@@ -4698,6 +4698,9 @@ recheck:
 			return retval;
 	}
 
+	if (pi)
+		cpuset_read_lock();
+
 	/*
 	 * Make sure no PI-waiters arrive (or leave) while we are
 	 * changing the priority of the task:
@@ -4772,6 +4775,8 @@ change:
 	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
 		policy = oldpolicy = -1;
 		task_rq_unlock(rq, p, &rf);
+		if (pi)
+			cpuset_read_unlock();
 		goto recheck;
 	}
 
@@ -4832,8 +4837,10 @@ change:
 	preempt_disable();
 	task_rq_unlock(rq, p, &rf);
 
-	if (pi)
+	if (pi) {
+		cpuset_read_unlock();
 		rt_mutex_adjust_pi(p);
+	}
 
 	/* Run balance callbacks after we've adjusted the PI chain: */
 	balance_callback(rq);
@@ -4843,6 +4850,8 @@ change:
 
 unlock:
 	task_rq_unlock(rq, p, &rf);
+	if (pi)
+		cpuset_read_unlock();
 	return retval;
 }
 
@@ -4927,10 +4936,15 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
 	rcu_read_lock();
 	retval = -ESRCH;
 	p = find_process_by_pid(pid);
-	if (p != NULL)
-		retval = sched_setscheduler(p, policy, &lparam);
+	if (likely(p))
+		get_task_struct(p);
 	rcu_read_unlock();
 
+	if (likely(p)) {
+		retval = sched_setscheduler(p, policy, &lparam);
+		put_task_struct(p);
+	}
+
 	return retval;
 }