[PATCH 6.18.y 2/3] sched: Rework prev_balance() to avoid stale prev references

From: Sasha Levin <sashal@kernel.org>
Date: 2026-09-09 09:26:34
Subsystem: scheduler, the rest · Maintainers: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot, Linus Torvalds

From: John Stultz <jstultz@google.com>

[ Upstream commit 7a3a6bfbd62a2ba3e0ef1e92d6b71abb66890825 ]

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->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 prev_balance()
its possible the class->balance() handler 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 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 prev_balance() call so that it does not take a
"prev" argument.

Signed-off-by: John Stultz <jstultz@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20260512025635.2840817-2-jstultz@google.com

Backport adaptation for 6.18:
Keep the existing sched_class::pick_next_task callbacks, pick_task
interfaces, SCX balancing setup and proxy-execution flow. The later
upstream scheduler refactors and lock annotations are not prerequisites
for this dependency.

Convert all six balance callbacks, including the fair and SCX callbacks
still present here, to the new signature. Read rq->donor at the existing
selection and balance call sites, and refresh prev after new-idle
balancing in pick_next_task_fair() because that path still drops the rq
lock inside the stable pick_next_task implementation.

This preserves the existing functions and supplies the selection context
needed for f3629c63a4af (sched/core: Make core-sched flips wait for
in-flight selections) to apply without changes.

Stable-dep-of: f3629c63a4af ("sched/core: Make core-sched flips wait for in-flight selections")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/sched/core.c      | 37 ++++++++++++++++++-------------------
 kernel/sched/deadline.c  |  8 +++++++-
 kernel/sched/ext.c       |  5 ++---
 kernel/sched/fair.c      |  4 +++-
 kernel/sched/idle.c      |  2 +-
 kernel/sched/rt.c        |  8 +++++++-
 kernel/sched/sched.h     |  2 +-
 kernel/sched/stop_task.c |  2 +-
 8 files changed, 40 insertions(+), 28 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 09310f762cd51..940c4d8a9d223 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c

@@ -5923,10 +5923,9 @@ 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;
 
 #ifdef CONFIG_SCHED_CLASS_EXT

@@ -5951,7 +5950,7 @@ 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;
 	}
 }

@@ -5960,7 +5959,7 @@ 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)
 {
 	const struct sched_class *class;
 	struct task_struct *p;

@@ -5976,34 +5975,34 @@ __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, rq->donor, rf);
 		if (unlikely(p == RETRY_TASK))
 			goto restart;
 
 		/* Assume the next prioritized class is idle_sched_class */
 		if (!p) {
 			p = pick_task_idle(rq);
-			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);
+			p = class->pick_next_task(rq, rq->donor);
 			if (p)
 				return p;
 		} else {
 			p = class->pick_task(rq);
 			if (p) {
-				put_prev_set_next_task(rq, prev, p);
+				put_prev_set_next_task(rq, rq->donor, p);
 				return p;
 			}
 		}

@@ -6052,7 +6051,7 @@ 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)
 {
 	struct task_struct *next, *p, *max = NULL;
 	const struct cpumask *smt_mask;

@@ -6064,7 +6063,7 @@ 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);

@@ -6077,7 +6076,7 @@ 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);
 	}
 
 	/*

@@ -6101,7 +6100,7 @@ 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;

@@ -6274,7 +6273,7 @@ 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);

@@ -6496,9 +6495,9 @@ 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)
 {
-	return __pick_next_task(rq, prev, rf);
+	return __pick_next_task(rq, rf);
 }
 
 #endif /* !CONFIG_SCHED_CORE */

@@ -6881,7 +6880,7 @@ 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_set_donor(rq, next);
 	if (unlikely(task_is_blocked(next))) {
 		next = find_proxy_task(rq, next, &rf);

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index e8b9cf0767b27..9c90d9f101a87 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c

@@ -2474,8 +2474,14 @@ 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 p 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/ext.c b/kernel/sched/ext.c
index b5f95b379ea6c..995650c330421 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c

@@ -2200,14 +2200,13 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 	return true;
 }
 
-static int balance_scx(struct rq *rq, struct task_struct *prev,
-		       struct rq_flags *rf)
+static int balance_scx(struct rq *rq, struct rq_flags *rf)
 {
 	int ret;
 
 	rq_unpin_lock(rq, rf);
 
-	ret = balance_one(rq, prev);
+	ret = balance_one(rq, rq->donor);
 
 #ifdef CONFIG_SCHED_SMT
 	/*

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index aed035aaece1d..eb4d5e558b6e1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c

@@ -8879,7 +8879,7 @@ static void set_cpus_allowed_fair(struct task_struct *p, struct affinity_context
 }
 
 static int
-balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+balance_fair(struct rq *rq, struct rq_flags *rf)
 {
 	if (sched_fair_runnable(rq))
 		return 1;

@@ -9200,6 +9200,8 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
 idle:
 	if (rf) {
 		new_tasks = sched_balance_newidle(rq, rf);
+		/* The donor may have changed while the rq lock was dropped. */
+		prev = rq->donor;
 
 		/*
 		 * Because sched_balance_newidle() releases (and re-acquires)

diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index bf92ae29361ed..220fc9e7c22db 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c

@@ -460,7 +460,7 @@ 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 3e81b9d83d14d..717deb5d02156 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c

@@ -1591,8 +1591,14 @@ 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 02df2334e06d0..15c5b11d2a665 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h

@@ -2422,7 +2422,7 @@ struct sched_class {
 
 	void (*wakeup_preempt)(struct rq *rq, struct task_struct *p, int flags);
 
-	int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
+	int (*balance)(struct rq *rq, struct rq_flags *rf);
 	struct task_struct *(*pick_task)(struct rq *rq);
 	/*
 	 * Optional! When implemented pick_next_task() should be equivalent to:

diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 2d4e279f05ee9..73aeb0743aa2e 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

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help