[PATCH v27 01/10] sched: Rework pick_next_task() and prev_balance() to avoid stale prev references

[John Stultz]

Historically, the prev value from __schedule() was the rq->curr.
This prev value is passed down through numerous functions, and
used in the class scheduler implementations. The fact that
prev was on_cpu until the end of __schedule(), meant it was
stable across the rq lock drops that the class->pick_next_task()
and ->balance() implementations often do.

However, with proxy-exec, the prev passed to functions called
by __schedule() is rq->donor, which may not be the same as
rq->curr and may not be on_cpu, this makes the prev value
potentially unstable across rq lock drops.

A recently found issue with proxy-exec, is when we begin doing
return migration from try_to_wake_up(), its possible we may be
waking up the rq->donor.  When we do this, we proxy_resched_idle()
to put_prev_set_next() setting the rq->donor to rq->idle, allowing
the rq->donor to be return migrated and allowed to run.

This however runs into trouble, as on another cpu we might be in
the middle of calling __schedule(). Conceptually the rq lock is
held for the majority of the time, but in calling pick_next_task()
its possible the class->pick_next_task() handler or the
->balance() call may briefly drop the rq lock. This opens a
window for try_to_wake_up() to wake and return migrate the
rq->donor before the class logic reacquires the rq lock.

Unfortunately pick_next_task() and prev_balance() pass in a prev
argument, to which we pass rq->donor. However this prev value can
now become stale and incorrect across a rq lock drop.

So, to correct this, rework the pick_next_task() and
prev_balance() calls so that they do not take a "prev" argument.

Also rework the class ->pick_next_task() and ->balance()
implementations to drop the prev argument, and in the cases
where it was used, and have the class functions reference
rq->donor directly, and not save the value across rq lock drops
so that we don't end up with a stale references.

Signed-off-by: John Stultz <jstultz@xxxxxxxxxx>
---
Cc: Joel Fernandes <joelagnelf@xxxxxxxxxx>
Cc: Qais Yousef <qyousef@xxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Juri Lelli <juri.lelli@xxxxxxxxxx>
Cc: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Cc: Valentin Schneider <vschneid@xxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Ben Segall <bsegall@xxxxxxxxxx>
Cc: Zimuzo Ezeozue <zezeozue@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Waiman Long <longman@xxxxxxxxxx>
Cc: Boqun Feng <boqun.feng@xxxxxxxxx>
Cc: "Paul E. McKenney" <paulmck@xxxxxxxxxx>
Cc: Metin Kaya <Metin.Kaya@xxxxxxx>
Cc: Xuewen Yan <xuewen.yan94@xxxxxxxxx>
Cc: K Prateek Nayak <kprateek.nayak@xxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
Cc: Suleiman Souhlal <suleiman@xxxxxxxxxx>
Cc: kuyo chang <kuyo.chang@xxxxxxxxxxxx>
Cc: hupu <hupu.gm@xxxxxxxxx>
Cc: kernel-team@xxxxxxxxxxx
---
 kernel/sched/core.c      | 37 ++++++++++++++++++-------------------
 kernel/sched/deadline.c  |  8 +++++++-
 kernel/sched/fair.c      |  9 +++++++--
 kernel/sched/idle.c      |  2 +-
 kernel/sched/rt.c        |  8 +++++++-
 kernel/sched/sched.h     | 10 ++++------
 kernel/sched/stop_task.c |  2 +-
 7 files changed, 45 insertions(+), 31 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c15c9865299e7..9c8a769a6d109 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5907,10 +5907,9 @@ static inline void schedule_debug(struct task_struct *prev, bool preempt)
 	schedstat_inc(this_rq()->sched_count);
 }
 
-static void prev_balance(struct rq *rq, struct task_struct *prev,
-			 struct rq_flags *rf)
+static void prev_balance(struct rq *rq, struct rq_flags *rf)
 {
-	const struct sched_class *start_class = prev->sched_class;
+	const struct sched_class *start_class = rq->donor->sched_class;
 	const struct sched_class *class;
 
 	/*
@@ -5922,7 +5921,7 @@ static void prev_balance(struct rq *rq, struct task_struct *prev,
 	 * a runnable task of @class priority or higher.
 	 */
 	for_active_class_range(class, start_class, &idle_sched_class) {
-		if (class->balance && class->balance(rq, prev, rf))
+		if (class->balance && class->balance(rq, rf))
 			break;
 	}
 }
@@ -5931,7 +5930,7 @@ static void prev_balance(struct rq *rq, struct task_struct *prev,
  * Pick up the highest-prio task:
  */
 static inline struct task_struct *
-__pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+__pick_next_task(struct rq *rq, struct rq_flags *rf)
 	__must_hold(__rq_lockp(rq))
 {
 	const struct sched_class *class;
@@ -5948,28 +5947,28 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	 * higher scheduling class, because otherwise those lose the
 	 * opportunity to pull in more work from other CPUs.
 	 */
-	if (likely(!sched_class_above(prev->sched_class, &fair_sched_class) &&
+	if (likely(!sched_class_above(rq->donor->sched_class, &fair_sched_class) &&
 		   rq->nr_running == rq->cfs.h_nr_queued)) {
 
-		p = pick_next_task_fair(rq, prev, rf);
+		p = pick_next_task_fair(rq, rf);
 		if (unlikely(p == RETRY_TASK))
 			goto restart;
 
 		/* Assume the next prioritized class is idle_sched_class */
 		if (!p) {
 			p = pick_task_idle(rq, rf);
-			put_prev_set_next_task(rq, prev, p);
+			put_prev_set_next_task(rq, rq->donor, p);
 		}
 
 		return p;
 	}
 
 restart:
-	prev_balance(rq, prev, rf);
+	prev_balance(rq, rf);
 
 	for_each_active_class(class) {
 		if (class->pick_next_task) {
-			p = class->pick_next_task(rq, prev, rf);
+			p = class->pick_next_task(rq, rf);
 			if (unlikely(p == RETRY_TASK))
 				goto restart;
 			if (p)
@@ -5979,7 +5978,7 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 			if (unlikely(p == RETRY_TASK))
 				goto restart;
 			if (p) {
-				put_prev_set_next_task(rq, prev, p);
+				put_prev_set_next_task(rq, rq->donor, p);
 				return p;
 			}
 		}
@@ -6032,7 +6031,7 @@ extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_f
 static void queue_core_balance(struct rq *rq);
 
 static struct task_struct *
-pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+pick_next_task(struct rq *rq, struct rq_flags *rf)
 	__must_hold(__rq_lockp(rq))
 {
 	struct task_struct *next, *p, *max;
@@ -6045,7 +6044,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	bool need_sync;
 
 	if (!sched_core_enabled(rq))
-		return __pick_next_task(rq, prev, rf);
+		return __pick_next_task(rq, rf);
 
 	cpu = cpu_of(rq);
 
@@ -6058,7 +6057,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		 */
 		rq->core_pick = NULL;
 		rq->core_dl_server = NULL;
-		return __pick_next_task(rq, prev, rf);
+		return __pick_next_task(rq, rf);
 	}
 
 	/*
@@ -6082,7 +6081,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		goto out_set_next;
 	}
 
-	prev_balance(rq, prev, rf);
+	prev_balance(rq, rf);
 
 	smt_mask = cpu_smt_mask(cpu);
 	need_sync = !!rq->core->core_cookie;
@@ -6264,7 +6263,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	}
 
 out_set_next:
-	put_prev_set_next_task(rq, prev, next);
+	put_prev_set_next_task(rq, rq->donor, next);
 	if (rq->core->core_forceidle_count && next == rq->idle)
 		queue_core_balance(rq);
 
@@ -6487,10 +6486,10 @@ static inline void sched_core_cpu_deactivate(unsigned int cpu) {}
 static inline void sched_core_cpu_dying(unsigned int cpu) {}
 
 static struct task_struct *
-pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+pick_next_task(struct rq *rq, struct rq_flags *rf)
 	__must_hold(__rq_lockp(rq))
 {
-	return __pick_next_task(rq, prev, rf);
+	return __pick_next_task(rq, rf);
 }
 
 #endif /* !CONFIG_SCHED_CORE */
@@ -7038,7 +7037,7 @@ static void __sched notrace __schedule(int sched_mode)
 
 pick_again:
 	assert_balance_callbacks_empty(rq);
-	next = pick_next_task(rq, rq->donor, &rf);
+	next = pick_next_task(rq, &rf);
 	rq->next_class = next->sched_class;
 	if (sched_proxy_exec()) {
 		struct task_struct *prev_donor = rq->donor;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 27359a1e995f9..7352506208287 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2509,8 +2509,14 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
 	resched_curr(rq);
 }
 
-static int balance_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
+static int balance_dl(struct rq *rq, struct rq_flags *rf)
 {
+	/*
+	 * Note, rq->donor may change during rq lock drops,
+	 * so don't re-use prev across lock drops
+	 */
+	struct task_struct *p = rq->donor;
+
 	if (!on_dl_rq(&p->dl) && need_pull_dl_task(rq, p)) {
 		/*
 		 * This is OK, because current is on_cpu, which avoids it being
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 597ce5b718d26..4a6669c517dae 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9153,14 +9153,19 @@ static void __set_next_task_fair(struct rq *rq, struct task_struct *p, bool firs
 static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first);
 
 struct task_struct *
-pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+pick_next_task_fair(struct rq *rq, struct rq_flags *rf)
 	__must_hold(__rq_lockp(rq))
 {
 	struct sched_entity *se;
-	struct task_struct *p;
+	struct task_struct *p, *prev;
 	int new_tasks;
 
 again:
+	/*
+	 * Re-read rq->donor at the top as it may have
+	 * changed across a rq lock drop
+	 */
+	prev = rq->donor;
 	p = pick_task_fair(rq, rf);
 	if (!p)
 		goto idle;
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index a83be0c834ddb..ff39120d723a9 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -462,7 +462,7 @@ select_task_rq_idle(struct task_struct *p, int cpu, int flags)
 }
 
 static int
-balance_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+balance_idle(struct rq *rq, struct rq_flags *rf)
 {
 	return WARN_ON_ONCE(1);
 }
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 4e5f1957b91b1..3fd03a836731e 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1596,8 +1596,14 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 	resched_curr(rq);
 }
 
-static int balance_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
+static int balance_rt(struct rq *rq, struct rq_flags *rf)
 {
+	/*
+	 * Note, rq->donor may change during rq lock drops,
+	 * so don't re-use p across lock drops
+	 */
+	struct task_struct *p = rq->donor;
+
 	if (!on_rt_rq(&p->rt) && need_pull_rt_task(rq, p)) {
 		/*
 		 * This is OK, because current is on_cpu, which avoids it being
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 9594355a36811..8ee82b03a8a10 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2550,7 +2550,7 @@ struct sched_class {
 	/*
 	 * schedule/pick_next_task/prev_balance: rq->lock
 	 */
-	int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
+	int (*balance)(struct rq *rq, struct rq_flags *rf);
 
 	/*
 	 * schedule/pick_next_task: rq->lock
@@ -2561,12 +2561,11 @@ struct sched_class {
 	 *
 	 *   next = pick_task();
 	 *   if (next) {
-	 *       put_prev_task(prev);
+	 *       put_prev_task(rq->donor);
 	 *       set_next_task_first(next);
 	 *   }
 	 */
-	struct task_struct *(*pick_next_task)(struct rq *rq, struct task_struct *prev,
-					      struct rq_flags *rf);
+	struct task_struct *(*pick_next_task)(struct rq *rq, struct rq_flags *rf);
 
 	/*
 	 * sched_change:
@@ -2790,8 +2789,7 @@ static inline bool sched_fair_runnable(struct rq *rq)
 	return rq->cfs.nr_queued > 0;
 }
 
-extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev,
-					       struct rq_flags *rf);
+extern struct task_struct *pick_next_task_fair(struct rq *rq, struct rq_flags *rf);
 extern struct task_struct *pick_task_idle(struct rq *rq, struct rq_flags *rf);
 
 #define SCA_CHECK		0x01
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index f95798baddebb..c909ca0d8c87c 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -16,7 +16,7 @@ select_task_rq_stop(struct task_struct *p, int cpu, int flags)
 }
 
 static int
-balance_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+balance_stop(struct rq *rq, struct rq_flags *rf)
 {
 	return sched_stop_runnable(rq);
 }
-- 
2.53.0.1213.gd9a14994de-goog