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 <dietmar.eggemann@arm.com>
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: bristot@redhat.com
Cc: claudio@evidence.eu.com
Cc: lizefan@huawei.com
Cc: longman@redhat.com
Cc: luca.abeni@santannapisa.it
Cc: mathieu.poirier@linaro.org
Cc: rostedt@goodmis.org
Cc: tj@kernel.org
Cc: tommaso.cucinotta@santannapisa.it
Link: https://lkml.kernel.org/r/20190719140000.31694-9-juri.lelli@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 17 insertions, 3 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1af3d2dc6b29..1bceb22dac18 100644
--- a/kernel/sched/core.c
+++ b/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;
 }