[PATCH v2] sched: Use READ_ONCE()/WRITE_ONCE() in move_queued_task()/task_rq_lock()

[Andrea Parri]

move_queued_task() synchronizes with task_rq_lock() as follows:

	move_queued_task()		task_rq_lock()

	[S] ->on_rq = MIGRATING		[L] rq = task_rq()
	WMB (__set_task_cpu())		ACQUIRE (rq->lock);
	[S] ->cpu = new_cpu		[L] ->on_rq

where "[L] rq = task_rq()" is ordered before "ACQUIRE (rq->lock)" by an
address dependency and, in turn, "ACQUIRE (rq->lock)" is ordered before
"[L] ->on_rq" by the ACQUIRE itself.

Use READ_ONCE() to load ->cpu in task_rq() (c.f., task_cpu()) to honor
this address dependency.  Also, mark the accesses to ->cpu and ->on_rq
with READ_ONCE()/WRITE_ONCE() to comply with the LKMM.

Signed-off-by: Andrea Parri <andrea.parri@xxxxxxxxxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxx>
Cc: Alan Stern <stern@xxxxxxxxxxxxxxxxxxx>
Cc: Will Deacon <will.deacon@xxxxxxx>
---
 Changes in v2:
 - mark accesses to ->on_rq as well
 - update inline comment for task_rq_lock()
 - minor editing in the subject/changelog
 
 include/linux/sched.h | 4 ++--
 kernel/sched/core.c   | 9 +++++----
 kernel/sched/sched.h  | 6 +++---
 3 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index d2f90fa924683..41212d725a0eb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1754,9 +1754,9 @@ static __always_inline bool need_resched(void)
 static inline unsigned int task_cpu(const struct task_struct *p)
 {
 #ifdef CONFIG_THREAD_INFO_IN_TASK
-	return p->cpu;
+	return READ_ONCE(p->cpu);
 #else
-	return task_thread_info(p)->cpu;
+	return READ_ONCE(task_thread_info(p)->cpu);
 #endif
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a674c7db2f29d..d6e08faaa2843 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -107,11 +107,12 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 		 *					[L] ->on_rq
 		 *	RELEASE (rq->lock)
 		 *
-		 * If we observe the old CPU in task_rq_lock, the acquire of
+		 * If we observe the old CPU in task_rq_lock(), the acquire of
 		 * the old rq->lock will fully serialize against the stores.
 		 *
-		 * If we observe the new CPU in task_rq_lock, the acquire will
-		 * pair with the WMB to ensure we must then also see migrating.
+		 * If we observe the new CPU in task_rq_lock(), the address
+		 * dependency headed by '[L] rq = task_rq()' and the acquire
+		 * will pair with the WMB to ensure we then also see migrating.
 		 */
 		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
 			rq_pin_lock(rq, rf);
@@ -915,7 +916,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
 {
 	lockdep_assert_held(&rq->lock);
 
-	p->on_rq = TASK_ON_RQ_MIGRATING;
+	WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING);
 	dequeue_task(rq, p, DEQUEUE_NOCLOCK);
 	set_task_cpu(p, new_cpu);
 	rq_unlock(rq, rf);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index d04530bf251fe..425a5589e5f60 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1460,9 +1460,9 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 	 */
 	smp_wmb();
 #ifdef CONFIG_THREAD_INFO_IN_TASK
-	p->cpu = cpu;
+	WRITE_ONCE(p->cpu, cpu);
 #else
-	task_thread_info(p)->cpu = cpu;
+	WRITE_ONCE(task_thread_info(p)->cpu, cpu);
 #endif
 	p->wake_cpu = cpu;
 #endif
@@ -1563,7 +1563,7 @@ static inline int task_on_rq_queued(struct task_struct *p)
 
 static inline int task_on_rq_migrating(struct task_struct *p)
 {
-	return p->on_rq == TASK_ON_RQ_MIGRATING;
+	return READ_ONCE(p->on_rq) == TASK_ON_RQ_MIGRATING;
 }
 
 /*
-- 
2.17.1