sched/rt: Up the root domain ref count when passing it around via IPIs

commit 364f56653708ba8bcdefd4f0da2a42904baa8eeb upstream.

When issuing an IPI RT push, where an IPI is sent to each CPU that has more
than one RT task scheduled on it, it references the root domain's rto_mask,
that contains all the CPUs within the root domain that has more than one RT
task in the runable state. The problem is, after the IPIs are initiated, the
rq->lock is released. This means that the root domain that is associated to
the run queue could be freed while the IPIs are going around.

Add a sched_get_rd() and a sched_put_rd() that will increment and decrement
the root domain's ref count respectively. This way when initiating the IPIs,
the scheduler will up the root domain's ref count before releasing the
rq->lock, ensuring that the root domain does not go away until the IPI round
is complete.

Reported-by: Pavan Kondeti <pkondeti@codeaurora.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 4bdced5c9a292 ("sched/rt: Simplify the IPI based RT balancing logic")
Link: http://lkml.kernel.org/r/CAEU1=PkiHO35Dzna8EQqNSKW1fr1y1zRQ5y66X117MG06sQtNA@mail.gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 22 insertions, 2 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e6d1173a2046..c5b1c62623cf 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5896,6 +5896,19 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd)
 		call_rcu_sched(&old_rd->rcu, free_rootdomain);
 }
 
+void sched_get_rd(struct root_domain *rd)
+{
+	atomic_inc(&rd->refcount);
+}
+
+void sched_put_rd(struct root_domain *rd)
+{
+	if (!atomic_dec_and_test(&rd->refcount))
+		return;
+
+	call_rcu_sched(&rd->rcu, free_rootdomain);
+}
+
 static int init_rootdomain(struct root_domain *rd)
 {
 	memset(rd, 0, sizeof(*rd));
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index bc9724344434..e0b5169aeac4 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1916,8 +1916,11 @@ static void tell_cpu_to_push(struct rq *rq)
 
 	rto_start_unlock(&rq->rd->rto_loop_start);
 
-	if (cpu >= 0)
+	if (cpu >= 0) {
+		/* Make sure the rd does not get freed while pushing */
+		sched_get_rd(rq->rd);
 		irq_work_queue_on(&rq->rd->rto_push_work, cpu);
+	}
 }
 
 /* Called from hardirq context */
@@ -1947,8 +1950,10 @@ void rto_push_irq_work_func(struct irq_work *work)
 
 	raw_spin_unlock(&rd->rto_lock);
 
-	if (cpu < 0)
+	if (cpu < 0) {
+		sched_put_rd(rd);
 		return;
+	}
 
 	/* Try the next RT overloaded CPU */
 	irq_work_queue_on(&rd->rto_push_work, cpu);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 448a8266ceea..0c9ebd82a684 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -553,6 +553,8 @@ struct root_domain {
 };
 
 extern struct root_domain def_root_domain;
+extern void sched_get_rd(struct root_domain *rd);
+extern void sched_put_rd(struct root_domain *rd);
 
 #ifdef HAVE_RT_PUSH_IPI
 extern void rto_push_irq_work_func(struct irq_work *work);