[PATCH 6.12.y 1/2] sched: Rework prev_balance() to avoid stale prev references

[Sasha Levin <sashal@kernel.org>]

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 Linux 6.12, as a dependency of f3629c63a4af
("sched/core: Make core-sched flips wait for in-flight selections"):

This tree has no proxy execution. Alias rq->donor and rq->curr in a union,
as upstream does without CONFIG_SCHED_PROXY_EXEC, so the existing curr
updates also provide the scheduling context without separate state.
Remove the prev parameter from prev_balance(), __pick_next_task(), and
both pick_next_task() variants, and read rq->donor at their call sites.

Keep the stable sched_class balance and pick_next_task interfaces and the
fair and sched_ext selection paths. Pass rq->donor to these existing
callbacks; it aliases the on-CPU current task and remains stable across
lock drops here. Drop the upstream deadline, RT, idle, and stop callback
signature changes, along with assumptions about newer selection APIs,
proxy execution, and lock annotations. No functions are added.

Label the CONFIG_SCHED_CORE closing directive in struct rq to match the
target's patch context. The unmodified target patch applies cleanly after
this adaptation. The core-selection counter fix remains in the target.

[ sashal: Reduced backport -- upstream 7a3a6bfbd62a2 touches 6 file(s), this
  backport carries 2. Not backported here:
  kernel/sched/deadline.c
  kernel/sched/idle.c
  kernel/sched/rt.c
  kernel/sched/stop_task.c
  This note is generated from the file lists only; see the resolution record
  for the reasoning. ]

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  | 39 +++++++++++++++++++--------------------
 kernel/sched/sched.h |  8 ++++++--
 2 files changed, 25 insertions(+), 22 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ea106403abd86..10206603f6ae8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5936,10 +5936,9 @@ 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
@@ -5964,7 +5963,7 @@ 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, rq->donor, rf))
 			break;
 	}
 }
@@ -5973,7 +5972,7 @@ 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;
@@ -5985,38 +5984,38 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 	/*
 	 * Optimization: we know that if all tasks are in the fair class we can
-	 * call that function directly, but only if the @prev task wasn't of a
+	 * call that function directly, but only if the current task wasn't of a
 	 * 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;
 			}
 		}
@@ -6065,7 +6064,7 @@ 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;
@@ -6077,7 +6076,7 @@ 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);
 
@@ -6090,7 +6089,7 @@ 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);
 	}
 
 	/*
@@ -6114,7 +6113,7 @@ 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;
@@ -6287,7 +6286,7 @@ 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);
 
@@ -6512,9 +6511,9 @@ 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 */
@@ -6682,7 +6681,7 @@ static void __sched notrace __schedule(int sched_mode)
 		switch_count = &prev->nvcsw;
 	}
 
-	next = pick_next_task(rq, prev, &rf);
+	next = pick_next_task(rq, &rf);
 picked:
 	clear_tsk_need_resched(prev);
 	clear_preempt_need_resched();
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7956abeb9154e..620d0e347ed88 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1184,7 +1184,11 @@ struct rq {
 	 */
 	unsigned long 		nr_uninterruptible;
 
-	struct task_struct __rcu	*curr;
+	/* Scheduling and execution contexts coincide without proxy execution. */
+	union {
+		struct task_struct __rcu *donor;
+		struct task_struct __rcu *curr;
+	};
 	struct sched_dl_entity	*dl_server;
 	struct task_struct	*idle;
 	struct task_struct	*stop;
@@ -1326,7 +1330,7 @@ struct rq {
 	unsigned int		core_forceidle_seq;
 	unsigned int		core_forceidle_occupation;
 	u64			core_forceidle_start;
-#endif
+#endif /* CONFIG_SCHED_CORE */
 
 	/* Scratch cpumask to be temporarily used under rq_lock */
 	cpumask_var_t		scratch_mask;
-- 
2.53.0