[PATCH 09/15] sched_ext: Generalize the reject DSQ reenqueue path

[PATCH 09/15] sched_ext: Generalize the reject DSQ reenqueue path

[Andrea Righi]

The reject DSQ is currently specific to sub-scheduler cap failures. Its
storage and initialization depend on CONFIG_EXT_SUB_SCHED, and the drain
path assumes every rejected task was rejected for SCX_TASK_REENQ_CAP.

Other transient placement failures need the same ability to park a task
on its source rq and return it to the owning BPF scheduler. Make the
reject DSQ unconditional, move its drain path into the core sched_ext
implementation, and record the reenqueue reason on each parked task.

This is a preparatory change to support proxy execution with sched_ext.

Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 include/linux/sched/ext.h |  1 +
 kernel/sched/ext/ext.c    | 59 ++++++++++++++++++++++++++++++++++++---
 kernel/sched/ext/sub.c    | 47 ++-----------------------------
 kernel/sched/ext/sub.h    |  2 --
 kernel/sched/sched.h      |  4 +--
 5 files changed, 59 insertions(+), 54 deletions(-)

diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index 4785a02905ecc..0f25d99f5fdd0 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -197,6 +197,7 @@ struct sched_ext_entity {
 	struct rb_node		dsq_priq;	/* p->scx.dsq_vtime order */
 	u32			dsq_seq;
 	u32			dsq_flags;	/* protected by DSQ lock */
+	u32			reject_reason;	/* protected by rq lock */
 	u32			flags;		/* protected by rq lock */
 	u32			weight;
 	u32			reenq_cnt;	/* reenqueues since last run */
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 240d84a0aaa37..fd4860b7fce4e 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -1521,11 +1521,10 @@ static void scx_dispatch_enqueue(struct scx_sched *sch, struct rq *rq,
 				 struct scx_dispatch_q *dsq, struct task_struct *p,
 				 u64 enq_flags)
 {
-	bool is_rq_owned = false;
+	bool is_rq_owned = dsq_is_rq_owned(dsq);
 
 	if (dsq->id == SCX_DSQ_LOCAL) {
 		dsq = scx_local_or_reject_dsq(sch, rq, p, &enq_flags);
-		is_rq_owned = true;
 	}
 
 	WARN_ON_ONCE(p->scx.dsq || !list_empty(&p->scx.dsq_list.node));
@@ -1725,6 +1724,9 @@ void scx_dispatch_dequeue(struct rq *rq, struct task_struct *p)
 	}
 	p->scx.dsq = NULL;
 
+	if (dsq->id == SCX_DSQ_REJECT)
+		p->scx.reject_reason = SCX_TASK_REENQ_NONE;
+
 	if (!is_rq_owned)
 		raw_spin_unlock(&dsq->lock);
 }
@@ -4396,6 +4398,57 @@ static void process_deferred_reenq_users(struct rq *rq)
 	}
 }
 
+/*
+ * Drain @rq->scx.reject_dsq and reenqueue each task so that its owning BPF
+ * scheduler chooses placement again.
+ *
+ * A task can be re-rejected repeatedly. Reenqueues are bounded per task by
+ * SCX_REENQ_MAX_REPEAT in scx_do_enqueue_task(), which ejects the owning
+ * scheduler. The private list below prevents a task from being revisited in
+ * the same round.
+ */
+static void scx_reenq_reject(struct rq *rq)
+{
+	LIST_HEAD(tasks);
+	struct task_struct *p, *n;
+
+	lockdep_assert_rq_held(rq);
+
+	if (list_empty(&rq->scx.reject_dsq.list))
+		return;
+
+	/*
+	 * Move tasks to a private list so a task re-rejected by
+	 * scx_do_enqueue_task() below isn't revisited this round.
+	 */
+	list_for_each_entry_safe(p, n, &rq->scx.reject_dsq.list, scx.dsq_list.node) {
+		u32 reason = p->scx.reject_reason;
+
+		/* migration_pending tasks should have bypassed to local DSQ */
+		if (WARN_ON_ONCE(p->migration_pending))
+			continue;
+		if (WARN_ON_ONCE(!reason))
+			continue;
+
+		scx_dispatch_dequeue(rq, p);
+		p->scx.reject_reason = SCX_TASK_REENQ_NONE;
+
+		if (WARN_ON_ONCE(p->scx.flags & SCX_TASK_REENQ_REASON_MASK))
+			p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;
+		p->scx.flags |= reason;
+
+		list_add_tail(&p->scx.dsq_list.node, &tasks);
+	}
+
+	list_for_each_entry_safe(p, n, &tasks, scx.dsq_list.node) {
+		list_del_init(&p->scx.dsq_list.node);
+
+		scx_do_enqueue_task(rq, p, SCX_ENQ_REENQ, -1);
+
+		p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;
+	}
+}
+
 static void run_deferred(struct rq *rq)
 {
 	process_ddsp_deferred_locals(rq);
@@ -8421,9 +8474,7 @@ void __init init_sched_ext_class(void)
 
 		/* local_dsq's sch will be set during scx_root_enable() */
 		BUG_ON(init_dsq(&rq->scx.local_dsq, SCX_DSQ_LOCAL, NULL));
-#ifdef CONFIG_EXT_SUB_SCHED
 		BUG_ON(init_dsq(&rq->scx.reject_dsq, SCX_DSQ_REJECT, NULL));
-#endif
 
 		INIT_LIST_HEAD(&rq->scx.runnable_list);
 		INIT_LIST_HEAD(&rq->scx.ddsp_deferred_locals);
diff --git a/kernel/sched/ext/sub.c b/kernel/sched/ext/sub.c
index 8758317035754..640e4a4f3c07f 100644
--- a/kernel/sched/ext/sub.c
+++ b/kernel/sched/ext/sub.c
@@ -284,6 +284,8 @@ struct scx_dispatch_q *scx_local_or_reject_dsq(struct scx_sched *sch, struct rq
 
 	p->scx.reenq_reason_caps = missing;
 	p->scx.reenq_reason_cid = cid;
+	WARN_ON_ONCE(p->scx.reject_reason);
+	p->scx.reject_reason = SCX_TASK_REENQ_CAP;
 
 	/*
 	 * Only local DSQ can honor IMMED and dsq_inc_nr() WARNs on IMMED into
@@ -315,51 +317,6 @@ bool scx_task_reenq_on_cap_revoke(struct rq *rq, struct task_struct *p)
 	return true;
 }
 
-/*
- * Drain @rq->scx.reject_dsq, reenqueueing each task so the BPF re-decides
- * from p->scx.reenq_reason_*.
- *
- * A task can be re-rejected repeatedly. The reenqueue is bounded per task in
- * scx_do_enqueue_task(), which ejects the owning sub past SCX_REENQ_MAX_REPEAT.
- * Rejection can't happen for root.
- */
-void scx_reenq_reject(struct rq *rq)
-{
-	LIST_HEAD(tasks);
-	struct task_struct *p, *n;
-
-	lockdep_assert_rq_held(rq);
-
-	if (!scx_has_subs() || list_empty(&rq->scx.reject_dsq.list))
-		return;
-
-	/*
-	 * Move to a private list so a task re-rejected by the
-	 * scx_do_enqueue_task() below isn't revisited this round.
-	 */
-	list_for_each_entry_safe(p, n, &rq->scx.reject_dsq.list, scx.dsq_list.node) {
-		/* migration_pending tasks should have bypassed to local DSQ */
-		if (WARN_ON_ONCE(p->migration_pending))
-			continue;
-
-		scx_dispatch_dequeue(rq, p);
-
-		if (WARN_ON_ONCE(p->scx.flags & SCX_TASK_REENQ_REASON_MASK))
-			p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;
-		p->scx.flags |= SCX_TASK_REENQ_CAP;
-
-		list_add_tail(&p->scx.dsq_list.node, &tasks);
-	}
-
-	list_for_each_entry_safe(p, n, &tasks, scx.dsq_list.node) {
-		list_del_init(&p->scx.dsq_list.node);
-
-		scx_do_enqueue_task(rq, p, SCX_ENQ_REENQ, -1);
-
-		p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;
-	}
-}
-
 /* record a caps change, see struct scx_caps_updated */
 static void caps_updated_record(struct scx_pshard *ps, const struct scx_cmask *cids, u64 caps,
 				struct list_head *to_deliver)
diff --git a/kernel/sched/ext/sub.h b/kernel/sched/ext/sub.h
index 0019b75a2560e..b5870aeb9c625 100644
--- a/kernel/sched/ext/sub.h
+++ b/kernel/sched/ext/sub.h
@@ -37,7 +37,6 @@ void scx_discard_stale_ecaps_syncs(void);
 struct scx_dispatch_q *scx_local_or_reject_dsq(struct scx_sched *sch, struct rq *rq,
 					       struct task_struct *p, u64 *enq_flags);
 bool scx_task_reenq_on_cap_revoke(struct rq *rq, struct task_struct *p);
-void scx_reenq_reject(struct rq *rq);
 
 /*
  * cgrp->scx_sched is written by root/sub enable/disable under all of
@@ -86,7 +85,6 @@ static inline void scx_discard_ecaps_to_sync(s32 cpu, struct scx_sched_pcpu *pcp
 static inline void scx_discard_stale_ecaps_syncs(void) {}
 static inline struct scx_dispatch_q *scx_local_or_reject_dsq(struct scx_sched *sch, struct rq *rq, struct task_struct *p, u64 *enq_flags) { return &rq->scx.local_dsq; }
 static inline bool scx_task_reenq_on_cap_revoke(struct rq *rq, struct task_struct *p) { return false; }
-static inline void scx_reenq_reject(struct rq *rq) {}
 static inline void scx_dec_has_subs(struct scx_sched *sch) {}
 
 #endif	/* CONFIG_EXT_SUB_SCHED */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 79daacc2389e1..ade8bb393786a 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -796,9 +796,7 @@ enum scx_rq_flags {
 
 struct scx_rq {
 	struct scx_dispatch_q	local_dsq;
-#ifdef CONFIG_EXT_SUB_SCHED
-	struct scx_dispatch_q	reject_dsq;		/* staging for cap-rejected tasks */
-#endif
+	struct scx_dispatch_q	reject_dsq;		/* staging for rejected tasks */
 	struct list_head	runnable_list;		/* runnable tasks on this rq */
 	struct list_head	ddsp_deferred_locals;	/* deferred ddsps from enq */
 	unsigned long		ops_qseq;
-- 
2.55.0

Re: [PATCH 09/15] sched_ext: Generalize the reject DSQ reenqueue path

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Transient failure to set a reject reason leaves the task permanently stranded on the reject DSQ.
--

--- Patch [9]: [PATCH 09/15] sched_ext: Generalize the reject DSQ reenqueue path ---
commit b71cb24d29b22c40aa0f3482e228cd8cd043d267
Author: Andrea Righi <arighi@nvidia.com>

sched_ext: Generalize the reject DSQ reenqueue path

This commit makes the reject DSQ unconditional and moves its drain path into
the core sched_ext implementation. It also records the reenqueue reason on
each parked task to support future proxy execution features.

> diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
> --- a/kernel/sched/ext/ext.c
> +++ b/kernel/sched/ext/ext.c

[ ... ]

> @@ -4399,6 +4401,57 @@ static void process_deferred_reenq_users(struct rq *rq)
[ ... ]
> +static void scx_reenq_reject(struct rq *rq)
> +{
[ ... ]
> +	/*
> +	 * Move tasks to a private list so a task re-rejected by
> +	 * scx_do_enqueue_task() below isn't revisited this round.
> +	 */
> +	list_for_each_entry_safe(p, n, &rq->scx.reject_dsq.list, scx.dsq_list.node) {
> +		u32 reason = p->scx.reject_reason;
> +
> +		/* migration_pending tasks should have bypassed to local DSQ */
> +		if (WARN_ON_ONCE(p->migration_pending))
> +			continue;
> +		if (WARN_ON_ONCE(!reason))
> +			continue;

[Severity: High]
If !reason is true and this WARN_ON_ONCE triggers, will this continue
statement leave the task permanently stranded on the reject DSQ list?

Because the continue bypasses scx_dispatch_dequeue() and the subsequent
list_add_tail(), the task is never unlinked from rq->scx.reject_dsq.list.

Since the reject DSQ is just a staging list, the task won't be scheduled,
and every subsequent run of scx_reenq_reject() will hit this continue again.

Should this error path safely recover the task (perhaps by falling back to
the local DSQ) or at least unlink it instead of leaving it in an unrecoverable
hung state?

> +
> +		scx_dispatch_dequeue(rq, p);
> +		p->scx.reject_reason = SCX_TASK_REENQ_NONE;

[ ... ]

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260728154425.1549660-1-arighi@nvidia.com?part=9

Re: [PATCH 09/15] sched_ext: Generalize the reject DSQ reenqueue path

[Tejun Heo]

On Tue, Jul 28, 2026 at 05:43:27PM +0200, Andrea Righi wrote:
...
> +static void scx_reenq_reject(struct rq *rq)
> +{
> +	LIST_HEAD(tasks);
> +	struct task_struct *p, *n;
> +
> +	lockdep_assert_rq_held(rq);
> +
> +	if (list_empty(&rq->scx.reject_dsq.list))
> +		return;
> +
> +	/*
> +	 * Move tasks to a private list so a task re-rejected by
> +	 * scx_do_enqueue_task() below isn't revisited this round.
> +	 */
> +	list_for_each_entry_safe(p, n, &rq->scx.reject_dsq.list, scx.dsq_list.node) {
> +		u32 reason = p->scx.reject_reason;
> +
> +		/* migration_pending tasks should have bypassed to local DSQ */
> +		if (WARN_ON_ONCE(p->migration_pending))
> +			continue;
> +		if (WARN_ON_ONCE(!reason))
> +			continue;
> +
> +		scx_dispatch_dequeue(rq, p);
> +		p->scx.reject_reason = SCX_TASK_REENQ_NONE;
> +
> +		if (WARN_ON_ONCE(p->scx.flags & SCX_TASK_REENQ_REASON_MASK))
> +			p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;
> +		p->scx.flags |= reason;

Can you separate out code movement and actual changes into separate patches?
Even for relatively simple changes, combining move and changes adds
significant unnecessary review friction.

Thanks.

-- 
tejun

Re: [PATCH 09/15] sched_ext: Generalize the reject DSQ reenqueue path

[Tejun Heo]

On Mon, Aug 03, 2026 at 10:35:16AM -1000, Tejun Heo wrote:
> On Tue, Jul 28, 2026 at 05:43:27PM +0200, Andrea Righi wrote:
> ...
> > +static void scx_reenq_reject(struct rq *rq)
> > +{
> > +	LIST_HEAD(tasks);
> > +	struct task_struct *p, *n;
> > +
> > +	lockdep_assert_rq_held(rq);
> > +
> > +	if (list_empty(&rq->scx.reject_dsq.list))
> > +		return;
> > +
> > +	/*
> > +	 * Move tasks to a private list so a task re-rejected by
> > +	 * scx_do_enqueue_task() below isn't revisited this round.
> > +	 */
> > +	list_for_each_entry_safe(p, n, &rq->scx.reject_dsq.list, scx.dsq_list.node) {
> > +		u32 reason = p->scx.reject_reason;
> > +
> > +		/* migration_pending tasks should have bypassed to local DSQ */
> > +		if (WARN_ON_ONCE(p->migration_pending))
> > +			continue;
> > +		if (WARN_ON_ONCE(!reason))
> > +			continue;
> > +
> > +		scx_dispatch_dequeue(rq, p);
> > +		p->scx.reject_reason = SCX_TASK_REENQ_NONE;
> > +
> > +		if (WARN_ON_ONCE(p->scx.flags & SCX_TASK_REENQ_REASON_MASK))
> > +			p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;
> > +		p->scx.flags |= reason;
> 
> Can you separate out code movement and actual changes into separate patches?
> Even for relatively simple changes, combining move and changes adds
> significant unnecessary review friction.

I wonder whether the reason can be carried in p->scx.flags from the
rejection site instead of bouncing through p->scx.reject_reason.

Thanks.

-- 
tejun

Re: [PATCH 09/15] sched_ext: Generalize the reject DSQ reenqueue path

[Andrea Righi]

On Mon, Aug 03, 2026 at 10:38:11AM -1000, Tejun Heo wrote:
> On Mon, Aug 03, 2026 at 10:35:16AM -1000, Tejun Heo wrote:
> > On Tue, Jul 28, 2026 at 05:43:27PM +0200, Andrea Righi wrote:
> > ...
> > > +static void scx_reenq_reject(struct rq *rq)
> > > +{
> > > +	LIST_HEAD(tasks);
> > > +	struct task_struct *p, *n;
> > > +
> > > +	lockdep_assert_rq_held(rq);
> > > +
> > > +	if (list_empty(&rq->scx.reject_dsq.list))
> > > +		return;
> > > +
> > > +	/*
> > > +	 * Move tasks to a private list so a task re-rejected by
> > > +	 * scx_do_enqueue_task() below isn't revisited this round.
> > > +	 */
> > > +	list_for_each_entry_safe(p, n, &rq->scx.reject_dsq.list, scx.dsq_list.node) {
> > > +		u32 reason = p->scx.reject_reason;
> > > +
> > > +		/* migration_pending tasks should have bypassed to local DSQ */
> > > +		if (WARN_ON_ONCE(p->migration_pending))
> > > +			continue;
> > > +		if (WARN_ON_ONCE(!reason))
> > > +			continue;
> > > +
> > > +		scx_dispatch_dequeue(rq, p);
> > > +		p->scx.reject_reason = SCX_TASK_REENQ_NONE;
> > > +
> > > +		if (WARN_ON_ONCE(p->scx.flags & SCX_TASK_REENQ_REASON_MASK))
> > > +			p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;
> > > +		p->scx.flags |= reason;
> > 
> > Can you separate out code movement and actual changes into separate patches?
> > Even for relatively simple changes, combining move and changes adds
> > significant unnecessary review friction.
> 
> I wonder whether the reason can be carried in p->scx.flags from the
> rejection site instead of bouncing through p->scx.reject_reason.

Ack, I think it's possible. I'll split the patches and set the rejection reason
directly in p->scx.flags.

Thanks,
-Andrea

[PATCHSET v11 sched_ext/for-7.3] sched: Make proxy execution compatible with sched_ext

[Andrea Righi]

This series enables using proxy execution with sched_ext and is based on early
work by John Stultz [1].

Background
==========

Proxy execution (proxy-exec) lets a waiting task ("donor") donate its scheduling
context to a mutex owner, so the owner can run while the donor stays eligible on
the runqueue.

Currently, proxy-exec and sched_ext are mutually exclusive at build time: we
can't enable CONFIG_SCHED_PROXY_EXEC=y and CONFIG_SCHED_CLASS_EXT=y in the same
kernel.

This restriction can be problematic for Linux distributions and for anyone who
wants to ship one kernel and choose features at runtime.

Why are they mutually exclusive?
================================

sched_ext schedulers drive dispatch through their own interfaces. A proxy-exec
handoff can run a task that the BPF scheduler never dispatched through that
path. sched_ext callbacks then observe a "current" task that does not match what
the BPF side considers running, so kfuncs and helper state can see an
inconsistent view of the executing task.

sched_ext also tracks runnable work through Dispatch Queues (DSQs) and BPF
chosen dispatch rules, while the core scheduler still maintains classic per-CPU
runqueues and pick paths. A proxy handoff can therefore switch the CPU to a task
that the BPF scheduler never inserted or ordered through its DSQ interface.

DSQ state, vtime, and "who is running" bookkeeping inside the BPF program can
then disagree with what the core actually executes, so helpers and kfuncs that
assume their dispatched task is current may observe stale or inconsistent state.

Design: supporting proxy-exec with sched_ext
============================================

Provide proxy-exec in sched_ext as optional per-scheduler capability: a BPF
scheduler can set the ops flag SCX_OPS_ENQ_BLOCKED to keep mutex-blocked donors
runnable and receive them through ops.enqueue() with SCX_ENQ_BLOCKED set.

This flag requires an ops.enqueue() callback and gives BPF control over whether,
where, and in what order to dispatch each donor. The core then walks the
mutex-owner chain and, when needed, migrates the donor's scheduling context to
the owner's rq before executing the owner.

Without the SCX_OPS_ENQ_BLOCKED flag, mutex waiters block normally and do not
participate in proxy-exec while owned by that scheduler.

Once BPF dispatches a donor, proxy execution may move its scheduling context
to the mutex owner's rq. This move is distinct from BPF placement: wake_cpu
continues to identify the donor's callback CPU, while task_cpu() identifies the
proxy CPU. When the donor wakes, the normal wakeup path uses wake_cpu as
prev_cpu when returning the task to the BPF scheduler, which can then choose
its next placement normally.

The donor-to-owner handoff is modeled like a "function call" from the
scheduler's perspective. The donor remains the running scheduling entity
selected by BPF: its scheduling context, runtime and slice are consumed while
the core temporarily invokes the mutex owner's code to make the critical section
progress. It is not a scheduler-visible switch to the owner.

Accordingly, the donor remains the scheduling context presented to sched_ext,
while the mutex owner is treated solely as the execution context selected
internally by the core scheduler. Scheduling state is accounted against
rq->donor where appropriate, while rq->curr identifies the execution context.
The internal owner substitution does not generate synthetic sched_ext callbacks
for a task that BPF did not dispatch.

Scheduler-facing current-task kfuncs follow the same rule:
scx_bpf_task_running(), scx_bpf_cpu_curr() and scx_bpf_cid_curr() report the
donor selected by the scheduler rather than the mutex owner whose code happens
to execute on its behalf.

The sched_ext callback bookkeeping is adjusted accordingly. A blocked donor
enters a tracked ops.running()/ops.stopping() session only after proxy
resolution succeeds, and ops.stopping() is only called for tasks that entered
such a session. This state is independent of physical rq->curr execution,
which may refer to the mutex owner instead of the donor.

NOHZ CFS bandwidth checks also follow rq->donor rather than rq->curr and use
the number of queued FAIR tasks when deciding whether the tick can stop. This
keeps bandwidth enforcement active for a constrained FAIR donor even when its
proxy owner remains runnable in another scheduling class.

Scheduler ownership changes need special handling because a donor may already be
blocked when a root scheduler is enabled, when a task moves between root and
sub-schedulers, or when a class transition moves it into or out of EXT. Start
every scheduling-class or BPF-scheduler ownership change from clean task state:
fully deactivate a retained donor before the transition and let the incoming
scheduler apply its own admission policy the next time the task blocks. This
conservative rule leaves retaining proxy state across compatible RT/DL PI
transitions as a future improvement.

Remote DSQ transfers recheck proxy-sensitive state after locking the source
runqueue. If a transfer races with proxy execution, the task is parked on the
source runqueue's reject DSQ and returned to its owning BPF scheduler after
proxy resolution settles. If an affinity migration is pending, the task remains
parked until the affinity machinery completes the operation. This preserves
scheduler placement and sub-scheduler capability rules without migrating an
active execution context.

scx_qmap has been modified with a -X option to enable queueing mutex-blocked
tasks for proxy-exec. Blocked donors receive a fresh slice, are inserted at the
head of their current cid's local DSQ and request immediate preemption. This is
an intentionally aggressive policy for making proxy-exec easy to observe.
With SCX_OPS_ALWAYS_ENQ_IMMED, a blocked donor which is returned through
ops.enqueue() with SCX_ENQ_REENQ falls back to the shared DSQ, avoiding a loop
which would repeatedly return it from the same local DSQ. A new statistic
reports blocked-donor dispatches.

A new kselftest (enq_blocked) is also introduced to validate proxy-exec with
sched_ext. The test creates a priority inversion with a low-priority owner
(nice +19), a high-priority donor (nice -20) and one nice 0 contender per
available CPU. It exercises a same-CPU topology and a cross-CPU topology, where
the donor and owner run on different CPUs. Each configuration runs with
SCX_OPS_ENQ_BLOCKED first disabled and then enabled, counts blocked-donor
enqueues by CPU and reports mutex hold/wait-time deltas. Access to the mutex is
provided by a loadable kernel module built via TEST_GEN_MODS_DIR, with the test
responsible for its lifecycle.

Example kselftest run:

===== START =====
TEST: enq_blocked
DESCRIPTION: Verify proxy donor admission under CPU-wide contention
OUTPUT:

[topology=same-cpu SCX_OPS_ENQ_BLOCKED=disabled]
  proxy_exec=enabled
  donor_cpu=0
  owner_cpu=0
  nr_contenders=16
  measured_trials=10
  owner_nice=19
  donor_nice=-20
  contender_nice=0
  mutex_hold_avg_ns=263587544 (263.587 ms, samples=10)
  mutex_wait_avg_ns=263597934 (263.597 ms, samples=10)
  nr_blocked_enqueues=0
  nr_blocked_enqueues_donor_cpu=0
  nr_blocked_enqueues_owner_cpu=0
  nr_blocked_enqueues_other_cpu=0
  nr_blocked_wakeups=0

[topology=same-cpu SCX_OPS_ENQ_BLOCKED=enabled]
  proxy_exec=enabled
  donor_cpu=0
  owner_cpu=0
  nr_contenders=16
  measured_trials=10
  owner_nice=19
  donor_nice=-20
  contender_nice=0
  mutex_hold_avg_ns=251789178 (251.789 ms, samples=10)
  mutex_wait_avg_ns=209808599 (209.808 ms, samples=10)
  nr_blocked_enqueues=50
  nr_blocked_enqueues_donor_cpu=50
  nr_blocked_enqueues_owner_cpu=0
  nr_blocked_enqueues_other_cpu=0
  nr_blocked_wakeups=0

[topology=same-cpu delta: enabled - disabled]
  mutex_hold_delta_ns=-11798366 (-4.48%)
  mutex_wait_delta_ns=-53789335 (-20.41%)

[topology=cross-cpu SCX_OPS_ENQ_BLOCKED=disabled]
  proxy_exec=enabled
  donor_cpu=0
  owner_cpu=1
  nr_contenders=16
  measured_trials=10
  owner_nice=19
  donor_nice=-20
  contender_nice=0
  mutex_hold_avg_ns=246794454 (246.794 ms, samples=10)
  mutex_wait_avg_ns=247298497 (247.298 ms, samples=10)
  nr_blocked_enqueues=0
  nr_blocked_enqueues_donor_cpu=0
  nr_blocked_enqueues_owner_cpu=0
  nr_blocked_enqueues_other_cpu=0
  nr_blocked_wakeups=0

[topology=cross-cpu SCX_OPS_ENQ_BLOCKED=enabled]
  proxy_exec=enabled
  donor_cpu=0
  owner_cpu=1
  nr_contenders=16
  measured_trials=10
  owner_nice=19
  donor_nice=-20
  contender_nice=0
  mutex_hold_avg_ns=215486809 (215.486 ms, samples=10)
  mutex_wait_avg_ns=215498090 (215.498 ms, samples=10)
  nr_blocked_enqueues=80
  nr_blocked_enqueues_donor_cpu=20
  nr_blocked_enqueues_owner_cpu=60
  nr_blocked_enqueues_other_cpu=0
  nr_blocked_wakeups=0

[topology=cross-cpu delta: enabled - disabled]
  mutex_hold_delta_ns=-31307645 (-12.69%)
  mutex_wait_delta_ns=-31800407 (-12.86%)
ok 1 enq_blocked #
=====  END  =====


=============================

RESULTS:

PASSED:  1
SKIPPED: 0
FAILED:  0

References
==========

[1] https://lore.kernel.org/all/20251206001451.1418225-1-jstultz@google.com

Git tree: git://git.kernel.org/pub/scm/linux/kernel/git/arighi/linux.git scx-proxy-exec

Changes in v11:
 - End retained proxy execution before every scheduling-class or BPF-scheduler
   ownership change, passing the incoming class to sched_change_begin() and
   removing the prepare_switch() class callback (Tejun Heo)
 - Document the conservative class-transition rule and leave retaining proxy
   state across compatible RT/DL PI transitions for future work (Tejun Heo)
 - Split reject-DSQ code movement from its generalization and carry the
   re-enqueue reason directly in p->scx.flags (Tejun Heo)
 - Use one SCX_TASK_REENQ_PROXY reason for all proxy-raced remote transfers,
   clarify why proxy migration differs from BPF-directed migration and keep
   tasks parked while affinity migration is pending (Tejun Heo)
 - Factor local-DSQ diversion cleanup into a shared helper, clear HEAD, IMMED,
   PREEMPT and carried-slice state for proxy rejection (Tejun Heo)
 - Explain the scx_qmap SCX_OPS_ALWAYS_ENQ_IMMED re-enqueue fallback (Tejun Heo)
 - Rename the blocked-donor command-line option to -X, since -B is now taken for
   the rescue bandwidth setting
 - Drop the SCHED_FLAG_KEEP_PARAMS preparatory fix (this is addressed separately
   by https://lore.kernel.org/all/20260730135858.2460751-1-arighi@nvidia.com)
 - Link to v10: https://lore.kernel.org/all/20260728154425.1549660-1-arighi@nvidia.com/

Changes in v10:
 - Check constrained FAIR proxy donors before the RT fast paths in
   sched_can_stop_tick(), so a throttled RT owner cannot bypass bandwidth
   enforcement (sashiko)
 - Add a preparatory fix that sets DEQUEUE_CLASS only when
   SCHED_FLAG_KEEP_PARAMS permits the scheduling class to change, preventing
   class-transition callbacks from running without an actual transition
   (sashiko)
 - Update try_to_block_task() comment to describe the sched_ext blocked-donor
   admission check (sashiko)
 - Link to v9: https://lore.kernel.org/all/20260725160513.57477-1-arighi@nvidia.com/

Changes in v9:
 - Add an incoming-class prepare_switch() callback and use it to block retained
   donors before transitions into sched_ext (Tejun Heo)
 - Generalize the per-rq reject DSQ and use it for proxy-raced remote transfers
   instead of bouncing tasks to a global DSQ (Tejun Heo)
 - Restrict migration-disabled warning exception to blocked donors whose
   scheduling context was actually proxy-migrated (sashiko)
 - Keep ops.tick() and other donor accounting inside a tracked
   ops.running()/ops.stopping() session (sashiko)
 - Prevent BPF-directed migration of an active proxy donor and use the donor as
   the current scheduling context during restore (sashiko)
 - Update sched_fair_update_stop_tick() to use the number of queued FAIR tasks
   (sashiko)
 - Fold the temporary local-DSQ donor placement into the final BPF-controlled
   admission change
 - Link to v8: https://lore.kernel.org/all/20260721063242.552774-1-arighi@nvidia.com/

Changes in v8:
 - Rework remote-DSQ migration check so the locked re-check handles only
   proxy-exec state changes (Tejun Heo)
 - Use the current-donor helper when preventing migration of an active donor
   (sashiko)
 - Handle blocked-donor reactivation into scx schedulers without
   SCX_OPS_ENQ_BLOCKED (John Stultz)
 - Document sched_ext callback behavior under proxy execution (sashiko)
 - Avoid redispatching a rejected blocked donor to the same local DSQ in
   scx_qmap (sashiko)
 - Add a preparatory fix to avoid false migration warnings when proxy-exec moves
   a migration-disabled donor
 - Skip the enq_blocked kselftest when proxy execution is unavailable
 - Link to v7: https://lore.kernel.org/all/20260716132229.61603-1-arighi@nvidia.com/

Changes in v7:
 - Move the remote CPU check out of the lockless remote-DSQ scan and perform it
   only after locking the source rq, retain the locked migration recheck
   immediately before moving the task (sashiko)
 - Complete the scheduler-context conversion from rq->curr to rq->donor for
   capability revocation and preemption checks, make scx_bpf_task_running(),
   scx_bpf_cpu_curr() and scx_bpf_cid_curr() expose the donor selected by the
   scheduler (sashiko)
 - Handle SCX_ENQ_REENQ before scx_qmap's blocked-donor fast path to avoid an
   infinite reject/re-enqueue loop (sashiko)
 - Add scx_qmap stat for SCX_ENQ_BLOCKED dispatches
 - Link to v6: https://lore.kernel.org/all/20260715205622.276220-1-arighi@nvidia.com/

Changes in v6:
 - Add a scheduler-core fix to make NOHZ CFS bandwidth checks follow the proxy
   donor instead of the physical execution context (sashiko)
 - Block retained donors when entering sched_ext through PI de-boosting or
   global scheduler activation (sashiko)
 - Distinguish ordinary wakeup activations from retained-donor admissions so
   SCX_ENQ_BLOCKED is not reported for normal wakeups; extend the selftest to
   detect this regression (sashiko)
 - Validate unexpected-CPU blocked-donor enqueues in both same-CPU and
   cross-CPU test topologies (sashiko)
 - Link to v5: https://lore.kernel.org/all/20260713162112.26785-1-arighi@nvidia.com/

Changes in v5:
 - Split retained-donor deactivation and sched_ext's default rejection into
   preparatory patches so the scheduler-core changes can be routed separately
 - Drop the proxy destination query kfuncs and the preparatory mutex lock-scope
   change (John Stultz)
 - Use p->is_blocked instead of task_is_blocked() to fix a WARN triggered during
   scx_pair testing (John Stultz)
 - Rename SCX_TASK_IS_RUNNING to SCX_TASK_RUN_TRACKED and document that it
   tracks an ops.running()/stopping() session rather than physical rq->curr
   execution
 - Keep a proxy-migrated blocked donor on the owner's rq until wakeup instead of
   allowing BPF-directed migration to pull it back to wake_cpu and cause
   repeated donor migration
 - Extend kselftest to cover same-CPU and cross-CPU proxy-exec switches
 - Make scx_qmap insert blocked donors at the head of their current cid's local
   DSQ and request immediate preemption
 - Link to v4: https://lore.kernel.org/all/20260710083913.30573-1-arighi@nvidia.com/

Changes in v4:
 - Harden scx_bpf_task_proxy_cpu() locking and blocked-state validation, return
   -ENOENT for unrunnable owners and drop unnecessary donor-affinity checks
   (K Prateek Nayak, sashiko)
 - Reschedule remote CPUs after donor deactivation, handle sched_setscheduler()
   admission and assert scheduler-change locking (sashiko)
 - Avoid a potential KCSAN data-race report in the lockless blocked-donor
   migration check by using rcu_access_pointer() for rq->donor (sashiko)
 - Fix tick dependency updates for incoming EXT contexts and keep the tick
   enabled for blocked donors (sashiko)
 - Dump EXT donors in scx_dump_state() (sashiko)
 - Reordered the preparatory sched_ext changes so real running-state tracking
   is established before donor-based accounting, and split the proxy
   destination query kfuncs into a separate patch
 - Add compatibility wrappers for the proxy CPU/cid kfuncs and document their
   results as scheduling hints
 - Link to v3: https://lore.kernel.org/all/20260706070410.282826-1-arighi@nvidia.com/

Changes in v3:
 - Dropped the core restrictions on proxy-migrating migration-disabled and
   single-CPU donors: proxy execution moves the scheduling context, not the
   task's execution context. (Peter Zijlstra, K Prateek Nayak)
 - Dropped the sched_ext-specific put_prev_task()/set_next_task() exception and
   fixed ops.running()/ops.stopping() pairing inside sched_ext instead; track a
   real running transition even when either callback is absent. (Peter Zijlstra)
 - Dropped the kf_tasks[] nesting and nested ops.runnable() patches from v2;
   extensive proxy-exec testing did not reproduce task-op re-entry, so retain
   the existing non-nesting invariant.
 - Replaced scx_bpf_task_is_blocked() with SCX_ENQ_BLOCKED in ops.enqueue()
   flags, identifying blocked-donor admission directly at enqueue time.
 - Expanded the curr/donor description to cover mixed scheduling classes and
   fixed local preemption to expire rq->donor's slice. (Aiqun Maria Yu)
 - Allow inactive blocked donors to be placed on a remote local DSQ while
   preventing normal migration of an active rq donor. (Aiqun Maria Yu)
 - Deactivate retained donors when ownership changes to a root or sub-scheduler
   without SCX_OPS_ENQ_BLOCKED, and extend the selftest to cover attaching a
   scheduler after the donor blocks. (K Prateek Nayak)
 - Harden remote DSQ consumption by rejecting active tasks and rechecking
   migration eligibility after locking the source rq. Fall back to the global
   DSQ without treating an eligibility change during the lock handoff as a BPF
   scheduler error.
 - scx_qmap has a command line option (-B) to enable blocked-donor queueing
 - Link to v2: https://lore.kernel.org/all/20260702171909.1994478-1-arighi@nvidia.com/

Changes in v2:
 - Rebased onto sched_ext/for-7.3 and adapted the series to the split
   sched_ext implementation and cid-form scheduler interfaces.
 - Replaced the global sched_proxy_exec_scx boot-time opt-in with the
   per-scheduler SCX_OPS_ENQ_BLOCKED capability, allowing BPF to control donor
   admission and ordering through ops.enqueue().
 - Added scx_bpf_task_is_blocked(), scx_bpf_task_proxy_cpu(), and
   scx_bpf_task_proxy_cid(); enforce CPU/cid API separation for cid-form
   schedulers.
 - Added proxy exec support to scx_qmap, including optional owner-cid steering,
   affinity validation, and fallback to the donor's current cid.
 - Added a kselftest with a kernel mutex test and a three-task priority
   inversion workload, test is executed with blocked task admission disabled and
   enabled, validates the behavior, and reports hold/wait-time deltas.
 - Link to v1: https://lore.kernel.org/all/20260506174639.535232-1-arighi@nvidia.com/

Andrea Righi (15):
      sched: Make NOHZ CFS bandwidth checks follow proxy donor
      sched/core: Avoid false migration warning for proxy donors
      sched: Pass next class to sched_change_begin()
      sched: Add helper to block retained proxy donors
      sched: Add sched_ext hooks for proxy execution
      sched_ext: Block proxy donors across scheduler transitions
      sched_ext: Fix ops.running/stopping() pairing for proxy-exec donors
      sched_ext: Move reject DSQ draining into core
      sched_ext: Generalize the reject DSQ reenqueue path
      sched_ext: Handle proxy-exec races in remote DSQ transfers
      sched_ext: Split curr|donor references properly
      sched_ext: Delegate proxy donor admission to BPF schedulers
      sched_ext: Add selftest for blocked donor admission
      sched_ext: scx_qmap: Add proxy execution support
      sched: Allow enabling proxy exec with sched_ext

 Documentation/scheduler/sched-ext.rst              |   6 +
 include/linux/sched/ext.h                          |   4 +
 init/Kconfig                                       |   2 -
 kernel/sched/core.c                                |  95 ++-
 kernel/sched/ext/ext.c                             | 536 ++++++++++--
 kernel/sched/ext/ext.h                             |   6 +
 kernel/sched/ext/internal.h                        |  37 +-
 kernel/sched/ext/sub.c                             |  64 +-
 kernel/sched/ext/sub.h                             |  13 +-
 kernel/sched/fair.c                                |  12 +-
 kernel/sched/sched.h                               |  18 +-
 kernel/sched/syscalls.c                            |   4 +-
 tools/sched_ext/include/scx/compat.h               |   1 +
 tools/sched_ext/include/scx/enum_defs.autogen.h    |   2 +
 tools/sched_ext/include/scx/enums.autogen.bpf.h    |   3 +
 tools/sched_ext/include/scx/enums.autogen.h        |   1 +
 tools/sched_ext/scx_qmap.bpf.c                     |  37 +
 tools/sched_ext/scx_qmap.c                         |  13 +-
 tools/sched_ext/scx_qmap.h                         |   1 +
 tools/testing/selftests/sched_ext/.gitignore       |   4 +
 tools/testing/selftests/sched_ext/Makefile         |   2 +
 tools/testing/selftests/sched_ext/config           |   2 +
 .../testing/selftests/sched_ext/enq_blocked.bpf.c  | 116 +++
 tools/testing/selftests/sched_ext/enq_blocked.c    | 917 +++++++++++++++++++++
 tools/testing/selftests/sched_ext/enq_blocked.h    |  28 +
 .../selftests/sched_ext/test_modules/Makefile      |  13 +
 .../sched_ext/test_modules/scx_enq_blocked_test.c  | 195 +++++
 27 files changed, 1940 insertions(+), 192 deletions(-)
 create mode 100644 tools/testing/selftests/sched_ext/enq_blocked.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/enq_blocked.c
 create mode 100644 tools/testing/selftests/sched_ext/enq_blocked.h
 create mode 100644 tools/testing/selftests/sched_ext/test_modules/Makefile
 create mode 100644 tools/testing/selftests/sched_ext/test_modules/scx_enq_blocked_test.c

[PATCH 01/15] sched: Make NOHZ CFS bandwidth checks follow proxy donor

[Andrea Righi]

Proxy execution separates the scheduling context in rq->donor from the
physical execution context in rq->curr. sched_can_stop_tick() checks the
latter for CFS bandwidth constraints and only does so when nr_running is
one.

A retained proxy donor keeps both the donor and mutex owner queued. The
check therefore misses a constrained FAIR donor and may stop the tick
while its runtime still needs to be enforced.

Check the selected donor instead and remove the nr_running restriction.
The donor being a queued FAIR task is sufficient to require bandwidth
accounting regardless of other runnable tasks.

Fixes: af0c8b2bf67b ("sched: Split scheduler and execution contexts")
Reported-by: Sashiko <sashiko-bot@kernel.org>
Link: https://lore.kernel.org/r/20260713164807.E5ED21F00A3A@smtp.kernel.org
Acked-by: John Stultz <jstultz@google.com>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 kernel/sched/core.c | 25 +++++++++----------------
 kernel/sched/fair.c | 12 +++++++-----
 2 files changed, 16 insertions(+), 21 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3cc6fb1d20547..fbdbe2762ba96 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1409,11 +1409,8 @@ static void nohz_csd_func(void *info)
 #endif /* CONFIG_NO_HZ_COMMON */
 
 #ifdef CONFIG_NO_HZ_FULL
-static inline bool __need_bw_check(struct rq *rq, struct task_struct *p)
+static inline bool __need_bw_check(struct task_struct *p)
 {
-	if (rq->nr_running != 1)
-		return false;
-
 	if (p->sched_class != &fair_sched_class)
 		return false;
 
@@ -1431,6 +1428,14 @@ bool sched_can_stop_tick(struct rq *rq)
 	if (rq->dl.dl_nr_running)
 		return false;
 
+	/*
+	 * The selected scheduling context can be a constrained FAIR donor even
+	 * when rq->curr is an RT task. Check it before the RT fast paths below,
+	 * which may report that the tick can stop for a throttled RT context.
+	 */
+	if (__need_bw_check(rq->donor) && cfs_task_bw_constrained(rq->donor))
+		return false;
+
 	/*
 	 * If there are more than one RR tasks, we need the tick to affect the
 	 * actual RR behaviour.
@@ -1461,18 +1466,6 @@ bool sched_can_stop_tick(struct rq *rq)
 	if (rq->cfs.h_nr_queued > 1)
 		return false;
 
-	/*
-	 * If there is one task and it has CFS runtime bandwidth constraints
-	 * and it's on the cpu now we don't want to stop the tick.
-	 * This check prevents clearing the bit if a newly enqueued task here is
-	 * dequeued by migrating while the constrained task continues to run.
-	 * E.g. going from 2->1 without going through pick_next_task().
-	 */
-	if (__need_bw_check(rq, rq->curr)) {
-		if (cfs_task_bw_constrained(rq->curr))
-			return false;
-	}
-
 	return true;
 }
 #endif /* CONFIG_NO_HZ_FULL */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d78467ec6ee13..14c5b2aa01777 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7570,14 +7570,16 @@ static void sched_fair_update_stop_tick(struct rq *rq, struct task_struct *p)
 	if (!tick_nohz_full_cpu(cpu))
 		return;
 
-	if (rq->nr_running != 1)
+	if (rq->cfs.h_nr_queued != 1)
 		return;
 
 	/*
-	 *  We know there is only one task runnable and we've just picked it. The
-	 *  normal enqueue path will have cleared TICK_DEP_BIT_SCHED if we will
-	 *  be otherwise able to stop the tick. Just need to check if we are using
-	 *  bandwidth control.
+	 * We know there is only one FAIR task queued and we've just picked it.
+	 * The normal enqueue path will have cleared TICK_DEP_BIT_SCHED if we
+	 * will be otherwise able to stop the tick. With proxy execution, its
+	 * lock owner may remain runnable in another scheduling class, so
+	 * rq->nr_running can be greater than one. Just need to check if we are
+	 * using bandwidth control.
 	 */
 	if (cfs_task_bw_constrained(p))
 		tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED);
-- 
2.55.0

[PATCH 02/15] sched/core: Avoid false migration warning for proxy donors

[Andrea Righi]

Proxy execution can move a blocked donor's scheduling context to the
lock owner's CPU even when the donor is migration-disabled. The donor
does not execute there, and its original execution CPU remains recorded
in wake_cpu.

set_task_cpu() warns unconditionally for migration-disabled tasks, so a
subsequent proxy migration or the wakeup path returning the donor home
triggers a false positive. Moving a blocked scheduling context does not
violate the migration-disabled execution context.

Exclude blocked proxy donors from the warning. The proxy wakeup path
restores an executable placement before clearing the blocked state.

This is a preparatory fix for enabling proxy execution together with
sched_ext.

Acked-by: John Stultz <jstultz@google.com>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 kernel/sched/core.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fbdbe2762ba96..96b8b01d43101 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3334,6 +3334,8 @@ void relax_compatible_cpus_allowed_ptr(struct task_struct *p)
 void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 {
 	unsigned int state = READ_ONCE(p->__state);
+	bool proxy_migrated = sched_proxy_exec() && p->is_blocked &&
+			      task_cpu(p) != p->wake_cpu;
 
 	/*
 	 * We should never call set_task_cpu() on a blocked task,
@@ -3369,7 +3371,12 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	 */
 	WARN_ON_ONCE(!cpu_online(new_cpu));
 
-	WARN_ON_ONCE(is_migration_disabled(p));
+	/*
+	 * Proxy execution can move a blocked task's scheduling context to any
+	 * CPU without moving its migration-disabled execution context. The
+	 * wakeup path will return the task to a CPU where it can execute.
+	 */
+	WARN_ON_ONCE(is_migration_disabled(p) && !proxy_migrated);
 
 	trace_sched_migrate_task(p, new_cpu);
 
-- 
2.55.0

[PATCH 03/15] sched: Pass next class to sched_change_begin()

[Andrea Righi]

sched_change_begin() currently only receives the task whose scheduling
state is being changed. It cannot distinguish a class transition from a
same-class update before recording the task queueing state.

Pass the incoming scheduling class to sched_change_begin() and update all
callers. This allows transition handling to run before the normal dequeue
and class change.

This is a preparatory change to support proxy execution with sched_ext.

Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 kernel/sched/core.c     | 12 +++++++-----
 kernel/sched/ext/ext.c  |  7 ++++---
 kernel/sched/ext/sub.c  |  9 ++++++---
 kernel/sched/sched.h    |  9 ++++++---
 kernel/sched/syscalls.c |  4 ++--
 5 files changed, 25 insertions(+), 16 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 96b8b01d43101..e71fd07254d6e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2785,7 +2785,7 @@ void set_cpus_allowed_common(struct task_struct *p, struct affinity_context *ctx
 static void
 do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx)
 {
-	scoped_guard (sched_change, p, DEQUEUE_SAVE)
+	scoped_guard (sched_change, p, p->sched_class, DEQUEUE_SAVE)
 		p->sched_class->set_cpus_allowed(p, ctx);
 }
 
@@ -7687,7 +7687,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 	if (prev_class != next_class)
 		queue_flag |= DEQUEUE_CLASS;
 
-	scoped_guard (sched_change, p, queue_flag) {
+	scoped_guard (sched_change, p, next_class, queue_flag) {
 		/*
 		 * Boosting condition are:
 		 * 1. -rt task is running and holds mutex A
@@ -8364,7 +8364,7 @@ int migrate_task_to(struct task_struct *p, int target_cpu)
 void sched_setnuma(struct task_struct *p, int nid)
 {
 	guard(task_rq_lock)(p);
-	scoped_guard (sched_change, p, DEQUEUE_SAVE)
+	scoped_guard (sched_change, p, p->sched_class, DEQUEUE_SAVE)
 		p->numa_preferred_nid = nid;
 }
 #endif /* CONFIG_NUMA_BALANCING */
@@ -9481,7 +9481,7 @@ void sched_move_task(struct task_struct *tsk, bool for_autogroup)
 	CLASS(task_rq_lock, rq_guard)(tsk);
 	rq = rq_guard.rq;
 
-	scoped_guard (sched_change, tsk, queue_flags) {
+	scoped_guard (sched_change, tsk, tsk->sched_class, queue_flags) {
 		sched_change_group(tsk);
 		if (!for_autogroup)
 			scx_cgroup_move_task(tsk);
@@ -11185,7 +11185,9 @@ static inline void sched_mm_cid_fork(struct task_struct *t) { }
 
 static DEFINE_PER_CPU(struct sched_change_ctx, sched_change_ctx);
 
-struct sched_change_ctx *sched_change_begin(struct task_struct *p, unsigned int flags)
+struct sched_change_ctx *
+sched_change_begin(struct task_struct *p, const struct sched_class *next_class,
+		   unsigned int flags)
 {
 	struct sched_change_ctx *ctx = this_cpu_ptr(&sched_change_ctx);
 	struct rq *rq = task_rq(p);
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 0bbe144c98111..17dab1543f012 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -6069,7 +6069,8 @@ void scx_bypass(struct scx_sched *sch, bool bypass)
 				scx_task_slice_ended(rq, p);
 
 			/* cycling deq/enq is enough, see the function comment */
-			scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_MOVE) {
+			scoped_guard (sched_change, p, p->sched_class,
+				      DEQUEUE_SAVE | DEQUEUE_MOVE) {
 				/* nothing */ ;
 			}
 		}
@@ -6350,7 +6351,7 @@ static void scx_root_disable(struct scx_sched *sch)
 		if (old_class != new_class)
 			queue_flags |= DEQUEUE_CLASS;
 
-		scoped_guard (sched_change, p, queue_flags) {
+		scoped_guard (sched_change, p, new_class, queue_flags) {
 			p->sched_class = new_class;
 		}
 
@@ -7716,7 +7717,7 @@ static void scx_root_enable_workfn(struct kthread_work *work)
 		if (old_class != new_class)
 			queue_flags |= DEQUEUE_CLASS;
 
-		scoped_guard (sched_change, p, queue_flags) {
+		scoped_guard (sched_change, p, new_class, queue_flags) {
 			scx_set_task_slice(p, READ_ONCE(sch->slice_dfl));
 			p->sched_class = new_class;
 		}
diff --git a/kernel/sched/ext/sub.c b/kernel/sched/ext/sub.c
index b81254be1b04c..9e1f1afd389f1 100644
--- a/kernel/sched/ext/sub.c
+++ b/kernel/sched/ext/sub.c
@@ -1253,7 +1253,8 @@ static void scx_rehome_task(struct scx_sched *to, struct task_struct *p)
 	lockdep_assert_held(&p->pi_lock);
 	lockdep_assert_rq_held(task_rq(p));
 
-	scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_MOVE) {
+	scoped_guard (sched_change, p, p->sched_class,
+		      DEQUEUE_SAVE | DEQUEUE_MOVE) {
 		scx_disable_and_exit_task(scx_task_sched(p), p);
 		scx_set_task_state(p, SCX_TASK_INIT_BEGIN);
 		scx_set_task_state(p, SCX_TASK_INIT);
@@ -1283,7 +1284,8 @@ static void scx_punt_task(struct scx_sched *to, struct task_struct *p)
 	lockdep_assert_rq_held(task_rq(p));
 	WARN_ON_ONCE(!READ_ONCE(to->bypass_depth));
 
-	scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_MOVE) {
+	scoped_guard (sched_change, p, p->sched_class,
+		      DEQUEUE_SAVE | DEQUEUE_MOVE) {
 		scx_disable_and_exit_task(scx_task_sched(p), p);
 		scx_set_task_sched(p, to);
 	}
@@ -1937,7 +1939,8 @@ void scx_sub_enable_workfn(struct kthread_work *work)
 		if (!(p->scx.flags & SCX_TASK_SUB_INIT))
 			continue;
 
-		scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_MOVE) {
+		scoped_guard (sched_change, p, p->sched_class,
+			      DEQUEUE_SAVE | DEQUEUE_MOVE) {
 			/*
 			 * $p must be either READY or ENABLED. If ENABLED,
 			 * __scx_disabled_and_exit_task() first disables and
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 63786712a1156..7779bcf7c6a12 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -4220,13 +4220,16 @@ struct sched_change_ctx {
 	bool			running;
 };
 
-struct sched_change_ctx *sched_change_begin(struct task_struct *p, unsigned int flags);
+struct sched_change_ctx *
+sched_change_begin(struct task_struct *p, const struct sched_class *next_class,
+		   unsigned int flags);
 void sched_change_end(struct sched_change_ctx *ctx);
 
 DEFINE_CLASS(sched_change, struct sched_change_ctx *,
 	     sched_change_end(_T),
-	     sched_change_begin(p, flags),
-	     struct task_struct *p, unsigned int flags)
+	     sched_change_begin(p, next_class, flags),
+	     struct task_struct *p, const struct sched_class *next_class,
+	     unsigned int flags)
 
 DEFINE_CLASS_IS_UNCONDITIONAL(sched_change)
 
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index b215b0ead9a60..bc32ce76ff4fe 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -85,7 +85,7 @@ void set_user_nice(struct task_struct *p, long nice)
 		return;
 	}
 
-	scoped_guard (sched_change, p, DEQUEUE_SAVE) {
+	scoped_guard (sched_change, p, p->sched_class, DEQUEUE_SAVE) {
 		p->static_prio = NICE_TO_PRIO(nice);
 		set_load_weight(p, true);
 		old_prio = p->prio;
@@ -678,7 +678,7 @@ int __sched_setscheduler(struct task_struct *p,
 	if (prev_class != next_class)
 		queue_flags |= DEQUEUE_CLASS;
 
-	scoped_guard (sched_change, p, queue_flags) {
+	scoped_guard (sched_change, p, next_class, queue_flags) {
 
 		if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) {
 			__setscheduler_params(p, attr);
-- 
2.55.0

[PATCH 04/15] sched: Add helper to block retained proxy donors

[Andrea Righi]

Scheduler ownership changes may need to turn a mutex-blocked task
retained on the runqueue for proxy execution back into a normally
blocked task.

Add sched_proxy_block_task() to perform that transition while holding
p->pi_lock and the task's runqueue lock. Reset an active donor to the
physical current task before blocking it. If DELAY_DEQUEUE keeps a FAIR
donor queued, the immediately following sched_change_begin() completes
the dequeue through switching_from_fair() before recording its queued
state.

This is a preparatory change to support proxy execution with sched_ext.

Acked-by: John Stultz <jstultz@google.com>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 kernel/sched/core.c  | 28 ++++++++++++++++++++++++++++
 kernel/sched/sched.h |  6 ++++++
 2 files changed, 34 insertions(+)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e71fd07254d6e..fe142e3bb78c8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6764,6 +6764,34 @@ static void proxy_deactivate(struct rq *rq, struct task_struct *donor)
 	block_task(rq, donor, state);
 }
 
+/*
+ * Remove a retained proxy donor before changing its scheduler ownership.
+ * The caller holds p->pi_lock, so p cannot wake and migrate if block_task()
+ * drops it from the runqueue. If DELAY_DEQUEUE keeps a blocked fair task
+ * queued, switching_from_fair() completes the dequeue in the immediately
+ * following sched_change_begin().
+ */
+void sched_proxy_block_task(struct rq *rq, struct task_struct *p)
+{
+	unsigned long state = READ_ONCE(p->__state);
+
+	lockdep_assert_held(&p->pi_lock);
+	lockdep_assert_rq_held(rq);
+
+	if (!p->is_blocked || !task_on_rq_queued(p))
+		return;
+	if (WARN_ON_ONCE(state == TASK_RUNNING))
+		return;
+
+	if (task_current_donor(rq, p))
+		proxy_reset_donor(rq);
+
+	if (!p->se.sched_delayed)
+		block_task(rq, p, state);
+
+	WARN_ON_ONCE(task_on_rq_queued(p) && !p->se.sched_delayed);
+}
+
 static inline void proxy_release_rq_lock(struct rq *rq, struct rq_flags *rf)
 	__releases(__rq_lockp(rq))
 {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7779bcf7c6a12..ee3ba7b5b11f5 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2489,6 +2489,12 @@ static inline bool task_is_blocked(struct task_struct *p)
 	return !!p->blocked_on;
 }
 
+#ifdef CONFIG_SCHED_PROXY_EXEC
+void sched_proxy_block_task(struct rq *rq, struct task_struct *p);
+#else
+static inline void sched_proxy_block_task(struct rq *rq, struct task_struct *p) {}
+#endif
+
 static inline int task_on_cpu(struct rq *rq, struct task_struct *p)
 {
 	return p->on_cpu;
-- 
2.55.0

[PATCH 05/15] sched: Add sched_ext hooks for proxy execution

[Andrea Righi]

Proxy execution splits the scheduling context (the donor) from the
execution context (the lock owner). sched_ext needs to observe that
split at three points in __schedule():

 - whether a blocked EXT task can be retained on the runqueue as a
   donor,
 - when a donor's scheduling context starts driving a lock owner,
 - once proxy resolution has settled for the current pick.

Introduce scx_allow_proxy_exec(), scx_proxy_donor_start() and
scx_proxy_resolved(), and add their call sites in __schedule(). The
implementations are empty here and are filled in by the sched_ext
changes that follow, so that all the sched core changes needed by proxy
execution stay together in the preparatory patches.

SCHED_PROXY_EXEC still depends on !SCHED_CLASS_EXT, so the new hooks are
inert: they are compiled out with CONFIG_SCHED_CLASS_EXT=n and
unreachable otherwise.

This is a preparatory change to support proxy execution with sched_ext.
No functional change.

Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 kernel/sched/core.c    | 12 +++++++-----
 kernel/sched/ext/ext.c | 13 +++++++++++++
 kernel/sched/ext/ext.h |  6 ++++++
 3 files changed, 26 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fe142e3bb78c8..08b4245a8f6b0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7156,13 +7156,12 @@ static void __sched notrace __schedule(int sched_mode)
 		}
 	} else if (!preempt && prev_state) {
 		/*
-		 * We pass task_is_blocked() as the should_block arg
-		 * in order to keep mutex-blocked tasks on the runqueue
-		 * for slection with proxy-exec (without proxy-exec
-		 * task_is_blocked() will always be false).
+		 * Keep mutex-blocked tasks on the runqueue for proxy execution
+		 * only when their scheduling class allows it. Without proxy
+		 * execution, task_is_blocked() always returns false.
 		 */
 		try_to_block_task(rq, prev, &prev_state,
-				  !task_is_blocked(prev));
+				  !task_is_blocked(prev) || !scx_allow_proxy_exec(prev));
 		switch_count = &prev->nvcsw;
 	}
 
@@ -7183,6 +7182,7 @@ static void __sched notrace __schedule(int sched_mode)
 			}
 			if (next == rq->idle) {
 				zap_balance_callbacks(rq);
+				scx_proxy_resolved(rq);
 				goto keep_resched;
 			}
 		}
@@ -7203,6 +7203,8 @@ static void __sched notrace __schedule(int sched_mode)
 			donor->sched_class->put_prev_task(rq, donor, donor);
 			donor->sched_class->set_next_task(rq, donor, true);
 		}
+		scx_proxy_donor_start(rq);
+		scx_proxy_resolved(rq);
 	} else {
 		rq_set_donor(rq, next);
 	}
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 17dab1543f012..4f2b0f1583989 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -24,6 +24,11 @@
 
 DEFINE_RAW_SPINLOCK(scx_sched_lock);
 
+bool scx_allow_proxy_exec(const struct task_struct *p)
+{
+	return true;
+}
+
 /*
  * NOTE: sched_ext is in the process of growing multiple scheduler support and
  * scx_root usage is in a transitional state. Naked dereferences are safe if the
@@ -1062,6 +1067,10 @@ static void schedule_deferred_locked(struct rq *rq)
 	schedule_deferred(rq);
 }
 
+void scx_proxy_resolved(struct rq *rq)
+{
+}
+
 void schedule_dsq_reenq(struct scx_sched *sch, struct scx_dispatch_q *dsq,
 			u64 reenq_flags, struct rq *locked_rq)
 {
@@ -3104,6 +3113,10 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
 	}
 }
 
+void scx_proxy_donor_start(struct rq *rq)
+{
+}
+
 static enum scx_cpu_preempt_reason
 preempt_reason_from_class(const struct sched_class *class)
 {
diff --git a/kernel/sched/ext/ext.h b/kernel/sched/ext/ext.h
index 0b7fc46aee08c..859b9261a8a6b 100644
--- a/kernel/sched/ext/ext.h
+++ b/kernel/sched/ext/ext.h
@@ -20,6 +20,9 @@ void scx_rq_deactivate(struct rq *rq);
 int scx_check_setscheduler(struct task_struct *p, int policy);
 bool task_should_scx(int policy);
 bool scx_allow_ttwu_queue(const struct task_struct *p);
+bool scx_allow_proxy_exec(const struct task_struct *p);
+void scx_proxy_donor_start(struct rq *rq);
+void scx_proxy_resolved(struct rq *rq);
 void init_sched_ext_class(void);
 
 static inline u32 scx_cpuperf_target(s32 cpu)
@@ -54,6 +57,9 @@ static inline void scx_rq_deactivate(struct rq *rq) {}
 static inline int scx_check_setscheduler(struct task_struct *p, int policy) { return 0; }
 static inline bool task_on_scx(const struct task_struct *p) { return false; }
 static inline bool scx_allow_ttwu_queue(const struct task_struct *p) { return true; }
+static inline bool scx_allow_proxy_exec(const struct task_struct *p) { return true; }
+static inline void scx_proxy_donor_start(struct rq *rq) {}
+static inline void scx_proxy_resolved(struct rq *rq) {}
 static inline void init_sched_ext_class(void) {}
 
 #endif	/* CONFIG_SCHED_CLASS_EXT */
-- 
2.55.0

[PATCH 06/15] sched_ext: Block proxy donors across scheduler transitions

[Andrea Righi]

Proxy execution retains mutex-blocked donors on the runqueue so their
scheduling context can execute a lock owner. sched_ext cannot safely retain
such donors unless the BPF scheduler explicitly participates in their
admission and ordering.

Make sched_ext reject retained donors by default. Implement
scx_allow_proxy_exec() to force blocked EXT tasks through the regular block
path in schedule().

Also fully deactivate any retained proxy donor in sched_change_begin()
before changing its scheduling class. This prevents sched_setscheduler(),
PI transitions and sched_ext activation from carrying an existing proxy
session into the new class.

Some RT/DL PI transitions could usefully preserve the proxy session. For
example, an RT waiter can boost a FAIR donor which is itself blocked on a
non-PI mutex; retaining the donor would allow the boosted context to keep
proxy-executing that mutex owner. Doing so safely requires defining which
scheduling classes can carry retained proxy state across a transition. Keep
the conservative reset for now and leave compatible RT/DL PI chains for
future work.

This is a preparatory change to support proxy execution with sched_ext.

Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 kernel/sched/core.c    | 9 +++++++++
 kernel/sched/ext/ext.c | 2 +-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 08b4245a8f6b0..26d351ac27a80 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -11235,6 +11235,15 @@ sched_change_begin(struct task_struct *p, const struct sched_class *next_class,
 		flags |= DEQUEUE_NOCLOCK;
 	}
 
+	/*
+	 * Don't carry retained proxy state across scheduling class changes.
+	 * Compatible RT/DL PI transitions could preserve the session so that a
+	 * boosted donor continues proxy-executing its lock owner. Defining which
+	 * class transitions can safely retain that state is left for future work.
+	 */
+	if ((flags & DEQUEUE_CLASS) && next_class != p->sched_class)
+		sched_proxy_block_task(rq, p);
+
 	if ((flags & DEQUEUE_CLASS) && p->sched_class->switching_from)
 		p->sched_class->switching_from(rq, p);
 
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 4f2b0f1583989..5efbd80304dae 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -26,7 +26,7 @@ DEFINE_RAW_SPINLOCK(scx_sched_lock);
 
 bool scx_allow_proxy_exec(const struct task_struct *p)
 {
-	return true;
+	return p->sched_class != &ext_sched_class;
 }
 
 /*
-- 
2.55.0

[PATCH 07/15] sched_ext: Fix ops.running/stopping() pairing for proxy-exec donors

[Andrea Righi]

With proxy execution, pick_next_task() can select a blocked task as the
scheduling context before find_proxy_task() resolves the execution
context.

From the BPF scheduler perspective, that donor is running while its
scheduling context drives the lock owner; ops.tick() and other
accounting must therefore remain enclosed by a matching
ops.running()/ops.stopping() session.

In this scenario, the session boundaries do not always match physical
task switches. Keep the "running" session open when the same donor
continues on the same CPU. When proxy execution migrates a donor's
scheduling context to another CPU, end its running session on the source
CPU and start a new session on the destination CPU only after proxy
resolution succeeds. This prevents a failed resolution from exposing a
provisional ops.running() event.

Track these sessions with a new SCX_TASK_RUN_TRACKED flag.

This is a preparatory change for enabling proxy execution together with
sched_ext. The explicit running-state tracking is also required by later
donor-based accounting: it prevents an EXT owner executing for a non-EXT
donor from being treated as the active EXT scheduling context when it is
dequeued.

Acked-by: John Stultz <jstultz@google.com>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 include/linux/sched/ext.h   |  1 +
 kernel/sched/ext/ext.c      | 65 ++++++++++++++++++++++++++++---------
 kernel/sched/ext/internal.h |  6 ++++
 3 files changed, 56 insertions(+), 16 deletions(-)

diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index a3ec980e29259..c34744c493885 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -104,6 +104,7 @@ enum scx_ent_flags {
 	SCX_TASK_SUB_INIT	= 1 << 4, /* task being initialized for a sub sched */
 	SCX_TASK_IMMED		= 1 << 5, /* task is on local DSQ with %SCX_ENQ_IMMED */
 	SCX_TASK_PROTECTED	= 1 << 6, /* slice and DSQ head position protected */
+	SCX_TASK_RUN_TRACKED	= 1 << 7, /* task is in an ops.running()/stopping() session */
 
 	/*
 	 * Bits 8 to 10 are used to carry task state:
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 5efbd80304dae..0958622d4382d 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -2334,10 +2334,10 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int core_deq_
 	ops_dequeue(rq, p, deq_flags);
 
 	/*
-	 * A currently running task which is going off @rq first gets dequeued
-	 * and then stops running. As we want running <-> stopping transitions
-	 * to be contained within runnable <-> quiescent transitions, trigger
-	 * ->stopping() early here instead of in put_prev_task_scx().
+	 * A current scheduling context which is going off @rq first gets
+	 * dequeued and then stops running. As we want running <-> stopping
+	 * transitions to be contained within runnable <-> quiescent transitions,
+	 * trigger ->stopping() early here instead of in put_prev_task_scx().
 	 *
 	 * @p may go through multiple stopping <-> running transitions between
 	 * here and put_prev_task_scx() if task attribute changes occur while
@@ -2345,11 +2345,13 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int core_deq_
 	 * information meaningful to the BPF scheduler and can be suppressed by
 	 * skipping the callbacks if the task is !QUEUED.
 	 */
-	if (task_current(rq, p) &&
-	    (SCX_HAS_OP(sch, stopping) || unlikely(p == scx_rescuee(rq)))) {
-		update_curr_scx(rq);
-		if (SCX_HAS_OP(sch, stopping))
-			SCX_CALL_OP_TASK(sch, stopping, rq, p, false);
+	if (task_current_donor(rq, p) && (p->scx.flags & SCX_TASK_RUN_TRACKED)) {
+		if (SCX_HAS_OP(sch, stopping) || unlikely(p == scx_rescuee(rq))) {
+			update_curr_scx(rq);
+			if (SCX_HAS_OP(sch, stopping))
+				SCX_CALL_OP_TASK(sch, stopping, rq, p, false);
+		}
+		p->scx.flags &= ~SCX_TASK_RUN_TRACKED;
 	}
 
 	if (SCX_HAS_OP(sch, quiescent) && !task_on_rq_migrating(p))
@@ -3052,10 +3054,21 @@ static int balance_one(struct rq *rq, struct task_struct *prev)
 	return true;
 }
 
-static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
+static void scx_start_task_running(struct rq *rq, struct task_struct *p)
 {
 	struct scx_sched *sch = scx_task_sched(p);
 
+	if (p->scx.flags & SCX_TASK_RUN_TRACKED)
+		return;
+
+	if (SCX_HAS_OP(sch, running))
+		SCX_CALL_OP_TASK(sch, running, rq, p);
+
+	p->scx.flags |= SCX_TASK_RUN_TRACKED;
+}
+
+static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
+{
 	if (p->scx.flags & SCX_TASK_QUEUED) {
 		/*
 		 * Core-sched might decide to execute @p before it is
@@ -3067,9 +3080,14 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
 
 	p->se.exec_start = rq_clock_task(rq);
 
-	/* see dequeue_task_scx() on why we skip when !QUEUED */
-	if (SCX_HAS_OP(sch, running) && (p->scx.flags & SCX_TASK_QUEUED))
-		SCX_CALL_OP_TASK(sch, running, rq, p);
+	/*
+	 * See dequeue_task_scx() for why we skip when !QUEUED. On a normal
+	 * scheduling transition, defer starting a blocked donor's session until
+	 * proxy resolution succeeds. A restore follows an already resolved
+	 * scheduling context and can start the session immediately.
+	 */
+	if ((p->scx.flags & SCX_TASK_QUEUED) && (!p->is_blocked || !first))
+		scx_start_task_running(rq, p);
 
 	clr_task_runnable(p, true);
 
@@ -3115,6 +3133,13 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
 
 void scx_proxy_donor_start(struct rq *rq)
 {
+	struct task_struct *donor = rq->donor;
+
+	lockdep_assert_rq_held(rq);
+
+	if (donor->sched_class == &ext_sched_class &&
+	    (donor->scx.flags & SCX_TASK_QUEUED))
+		scx_start_task_running(rq, donor);
 }
 
 static enum scx_cpu_preempt_reason
@@ -3190,9 +3215,17 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p,
 			scx_task_slice_ended(rq, p);
 	}
 
-	/* see dequeue_task_scx() on why we skip when !QUEUED */
-	if (SCX_HAS_OP(sch, stopping) && (p->scx.flags & SCX_TASK_QUEUED))
-		SCX_CALL_OP_TASK(sch, stopping, rq, p, true);
+	/*
+	 * Preserve the running session when proxy execution refreshes the same
+	 * donor around an execution-context switch on this rq.
+	 */
+	if (next != p && (p->scx.flags & SCX_TASK_QUEUED) &&
+	    (p->scx.flags & SCX_TASK_RUN_TRACKED)) {
+		if (SCX_HAS_OP(sch, stopping))
+			SCX_CALL_OP_TASK(sch, stopping, rq, p, true);
+
+		p->scx.flags &= ~SCX_TASK_RUN_TRACKED;
+	}
 
 	if (p->scx.flags & SCX_TASK_QUEUED) {
 		set_task_runnable(rq, p);
diff --git a/kernel/sched/ext/internal.h b/kernel/sched/ext/internal.h
index b699e7c1103fc..c458a12c64574 100644
--- a/kernel/sched/ext/internal.h
+++ b/kernel/sched/ext/internal.h
@@ -449,6 +449,12 @@ struct sched_ext_ops {
 	 * Therefore, always use scx_bpf_task_cpu(@p) to determine the
 	 * target CPU the task is going to use.
 	 *
+	 * Under proxy execution, the BPF scheduler continues to observe the
+	 * donor as the current scheduling context. A blocked donor enters a
+	 * ->running()/->stopping() session while its scheduling context drives
+	 * the lock owner. The lock owner executing on its behalf is intentionally
+	 * not reported through these callbacks.
+	 *
 	 * See ->runnable() for explanation on the task state notifiers.
 	 */
 	void (*running)(struct task_struct *p);
-- 
2.55.0

[PATCH 08/15] sched_ext: Move reject DSQ draining into core

[Andrea Righi]

The reject DSQ drain will be generalized for placement failures outside
sub-scheduler capability rejection. Move the drain into the core
sched_ext implementation first so the subsequent behavioral changes can
be reviewed separately.

Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 kernel/sched/ext/ext.c | 49 ++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/ext/sub.c | 45 --------------------------------------
 kernel/sched/ext/sub.h |  2 --
 3 files changed, 49 insertions(+), 47 deletions(-)

diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 0958622d4382d..1ad65b8051008 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -4582,6 +4582,55 @@ static void process_deferred_reenq_users(struct rq *rq)
 	}
 }
 
+#ifdef CONFIG_EXT_SUB_SCHED
+/*
+ * Drain @rq->scx.reject_dsq, reenqueueing each task so the BPF re-decides
+ * from p->scx.reenq_reason_*.
+ *
+ * A task can be re-rejected repeatedly. The reenqueue is bounded per task in
+ * scx_do_enqueue_task(), which ejects the owning sub past SCX_REENQ_MAX_REPEAT.
+ * Rejection can't happen for root.
+ */
+static void scx_reenq_reject(struct rq *rq)
+{
+	LIST_HEAD(tasks);
+	struct task_struct *p, *n;
+
+	lockdep_assert_rq_held(rq);
+
+	if (!scx_has_subs() || list_empty(&rq->scx.reject_dsq.list))
+		return;
+
+	/*
+	 * Move to a private list so a task re-rejected by the
+	 * scx_do_enqueue_task() below isn't revisited this round.
+	 */
+	list_for_each_entry_safe(p, n, &rq->scx.reject_dsq.list, scx.dsq_list.node) {
+		/* migration_pending tasks should have bypassed to local DSQ */
+		if (WARN_ON_ONCE(p->migration_pending))
+			continue;
+
+		scx_dispatch_dequeue(rq, p);
+
+		if (WARN_ON_ONCE(p->scx.flags & SCX_TASK_REENQ_REASON_MASK))
+			p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;
+		p->scx.flags |= SCX_TASK_REENQ_CAP;
+
+		list_add_tail(&p->scx.dsq_list.node, &tasks);
+	}
+
+	list_for_each_entry_safe(p, n, &tasks, scx.dsq_list.node) {
+		list_del_init(&p->scx.dsq_list.node);
+
+		scx_do_enqueue_task(rq, p, SCX_ENQ_REENQ, -1);
+
+		p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;
+	}
+}
+#else
+static void scx_reenq_reject(struct rq *rq) {}
+#endif
+
 static void run_deferred(struct rq *rq)
 {
 	process_ddsp_deferred_locals(rq);
diff --git a/kernel/sched/ext/sub.c b/kernel/sched/ext/sub.c
index 9e1f1afd389f1..2391bb0c0ecb0 100644
--- a/kernel/sched/ext/sub.c
+++ b/kernel/sched/ext/sub.c
@@ -774,51 +774,6 @@ bool scx_task_reenq_on_cap_revoke(struct rq *rq, struct task_struct *p)
 	return true;
 }
 
-/*
- * Drain @rq->scx.reject_dsq, reenqueueing each task so the BPF re-decides
- * from p->scx.reenq_reason_*.
- *
- * A task can be re-rejected repeatedly. The reenqueue is bounded per task in
- * scx_do_enqueue_task(), which ejects the owning sub past SCX_REENQ_MAX_REPEAT.
- * Rejection can't happen for root.
- */
-void scx_reenq_reject(struct rq *rq)
-{
-	LIST_HEAD(tasks);
-	struct task_struct *p, *n;
-
-	lockdep_assert_rq_held(rq);
-
-	if (!scx_has_subs() || list_empty(&rq->scx.reject_dsq.list))
-		return;
-
-	/*
-	 * Move to a private list so a task re-rejected by the
-	 * scx_do_enqueue_task() below isn't revisited this round.
-	 */
-	list_for_each_entry_safe(p, n, &rq->scx.reject_dsq.list, scx.dsq_list.node) {
-		/* migration_pending tasks should have bypassed to local DSQ */
-		if (WARN_ON_ONCE(p->migration_pending))
-			continue;
-
-		scx_dispatch_dequeue(rq, p);
-
-		if (WARN_ON_ONCE(p->scx.flags & SCX_TASK_REENQ_REASON_MASK))
-			p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;
-		p->scx.flags |= SCX_TASK_REENQ_CAP;
-
-		list_add_tail(&p->scx.dsq_list.node, &tasks);
-	}
-
-	list_for_each_entry_safe(p, n, &tasks, scx.dsq_list.node) {
-		list_del_init(&p->scx.dsq_list.node);
-
-		scx_do_enqueue_task(rq, p, SCX_ENQ_REENQ, -1);
-
-		p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;
-	}
-}
-
 /* record a caps change, see struct scx_caps_updated */
 static void caps_updated_record(struct scx_pshard *ps, const struct scx_cmask *cids, u64 caps,
 				struct list_head *to_deliver)
diff --git a/kernel/sched/ext/sub.h b/kernel/sched/ext/sub.h
index f7bcdfda8dd85..8f2425bdb9530 100644
--- a/kernel/sched/ext/sub.h
+++ b/kernel/sched/ext/sub.h
@@ -37,7 +37,6 @@ void scx_discard_stale_ecaps_syncs(void);
 struct scx_dispatch_q *scx_resolve_local_dsq(struct scx_sched *sch, struct rq *rq,
 					     struct task_struct *p, u64 *enq_flags);
 bool scx_task_reenq_on_cap_revoke(struct rq *rq, struct task_struct *p);
-void scx_reenq_reject(struct rq *rq);
 void scx_rescue_charge(struct rq *rq, s64 delta_exec);
 void scx_rescue_end(struct rq *rq);
 bool scx_rescue_keep(struct rq *rq, struct task_struct *p);
@@ -93,7 +92,6 @@ static inline void scx_discard_ecaps_to_sync(s32 cpu, struct scx_sched_pcpu *pcp
 static inline void scx_discard_stale_ecaps_syncs(void) {}
 static inline struct scx_dispatch_q *scx_resolve_local_dsq(struct scx_sched *sch, struct rq *rq, struct task_struct *p, u64 *enq_flags) { return &rq->scx.local_dsq; }
 static inline bool scx_task_reenq_on_cap_revoke(struct rq *rq, struct task_struct *p) { return false; }
-static inline void scx_reenq_reject(struct rq *rq) {}
 static inline void scx_rescue_charge(struct rq *rq, s64 delta_exec) {}
 static inline void scx_rescue_end(struct rq *rq) {}
 static inline bool scx_rescue_keep(struct rq *rq, struct task_struct *p) { return false; }
-- 
2.55.0

[PATCH 09/15] sched_ext: Generalize the reject DSQ reenqueue path

[Andrea Righi]

The reject DSQ is currently specific to sub-scheduler cap failures. Its
storage and initialization depend on CONFIG_EXT_SUB_SCHED, and the drain
path assumes every rejected task was rejected for SCX_TASK_REENQ_CAP.

Other transient placement failures need the same ability to park a task
on its source rq and return it to the owning BPF scheduler. Make the
reject DSQ unconditional and carry the reenqueue reason directly in
p->scx.flags from the rejection site.

This is a preparatory change to support proxy execution with sched_ext.

Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 kernel/sched/ext/ext.c | 38 ++++++++++++++++++--------------------
 kernel/sched/ext/sub.c |  3 +++
 kernel/sched/sched.h   |  2 +-
 3 files changed, 22 insertions(+), 21 deletions(-)

diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 1ad65b8051008..b43b2834141e6 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -1632,11 +1632,10 @@ static void scx_dispatch_enqueue(struct scx_sched *sch, struct rq *rq,
 				 struct scx_dispatch_q *dsq, struct task_struct *p,
 				 u64 slice, u64 vtime, u64 enq_flags)
 {
-	bool is_rq_owned = false;
+	bool is_rq_owned = dsq_is_rq_owned(dsq);
 
 	if (dsq->id == SCX_DSQ_LOCAL) {
 		dsq = scx_resolve_local_dsq(sch, rq, p, &enq_flags);
-		is_rq_owned = true;
 	}
 
 	WARN_ON_ONCE(p->scx.dsq || !list_empty(&p->scx.dsq_list.node));
@@ -1841,6 +1840,9 @@ void scx_dispatch_dequeue(struct rq *rq, struct task_struct *p)
 	}
 	p->scx.dsq = NULL;
 
+	if (dsq->id == SCX_DSQ_REJECT)
+		p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;
+
 	if (!is_rq_owned)
 		raw_spin_unlock(&dsq->lock);
 }
@@ -4582,14 +4584,14 @@ static void process_deferred_reenq_users(struct rq *rq)
 	}
 }
 
-#ifdef CONFIG_EXT_SUB_SCHED
 /*
- * Drain @rq->scx.reject_dsq, reenqueueing each task so the BPF re-decides
- * from p->scx.reenq_reason_*.
+ * Drain @rq->scx.reject_dsq and reenqueue each task so that its owning BPF
+ * scheduler chooses placement again.
  *
- * A task can be re-rejected repeatedly. The reenqueue is bounded per task in
- * scx_do_enqueue_task(), which ejects the owning sub past SCX_REENQ_MAX_REPEAT.
- * Rejection can't happen for root.
+ * A task can be re-rejected repeatedly. Reenqueues are bounded per task by
+ * SCX_REENQ_MAX_REPEAT in scx_do_enqueue_task(), which ejects the owning
+ * scheduler. The private list below prevents a task from being revisited in
+ * the same round.
  */
 static void scx_reenq_reject(struct rq *rq)
 {
@@ -4598,23 +4600,22 @@ static void scx_reenq_reject(struct rq *rq)
 
 	lockdep_assert_rq_held(rq);
 
-	if (!scx_has_subs() || list_empty(&rq->scx.reject_dsq.list))
+	if (list_empty(&rq->scx.reject_dsq.list))
 		return;
 
 	/*
-	 * Move to a private list so a task re-rejected by the
+	 * Move tasks to a private list so a task re-rejected by
 	 * scx_do_enqueue_task() below isn't revisited this round.
 	 */
 	list_for_each_entry_safe(p, n, &rq->scx.reject_dsq.list, scx.dsq_list.node) {
+		u32 reason = p->scx.flags & SCX_TASK_REENQ_REASON_MASK;
+
 		/* migration_pending tasks should have bypassed to local DSQ */
-		if (WARN_ON_ONCE(p->migration_pending))
-			continue;
+		WARN_ON_ONCE(p->migration_pending);
+		WARN_ON_ONCE(!reason);
 
 		scx_dispatch_dequeue(rq, p);
-
-		if (WARN_ON_ONCE(p->scx.flags & SCX_TASK_REENQ_REASON_MASK))
-			p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;
-		p->scx.flags |= SCX_TASK_REENQ_CAP;
+		p->scx.flags |= reason;
 
 		list_add_tail(&p->scx.dsq_list.node, &tasks);
 	}
@@ -4627,9 +4628,6 @@ static void scx_reenq_reject(struct rq *rq)
 		p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;
 	}
 }
-#else
-static void scx_reenq_reject(struct rq *rq) {}
-#endif
 
 static void run_deferred(struct rq *rq)
 {
@@ -8687,8 +8685,8 @@ void __init init_sched_ext_class(void)
 
 		/* local_dsq's sch will be set during scx_root_enable() */
 		BUG_ON(scx_init_dsq(&rq->scx.local_dsq, SCX_DSQ_LOCAL, NULL));
-#ifdef CONFIG_EXT_SUB_SCHED
 		BUG_ON(scx_init_dsq(&rq->scx.reject_dsq, SCX_DSQ_REJECT, NULL));
+#ifdef CONFIG_EXT_SUB_SCHED
 		scx_rescue_init(rq);
 #endif
 
diff --git a/kernel/sched/ext/sub.c b/kernel/sched/ext/sub.c
index 2391bb0c0ecb0..a04eccd837348 100644
--- a/kernel/sched/ext/sub.c
+++ b/kernel/sched/ext/sub.c
@@ -752,6 +752,9 @@ struct scx_dispatch_q *scx_resolve_local_dsq(struct scx_sched *sch, struct rq *r
 
 	p->scx.reenq_reason_caps = missing;
 	p->scx.reenq_reason_cid = cid;
+	if (WARN_ON_ONCE(p->scx.flags & SCX_TASK_REENQ_REASON_MASK))
+		p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;
+	p->scx.flags |= SCX_TASK_REENQ_CAP;
 
 	return &rq->scx.reject_dsq;
 }
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ee3ba7b5b11f5..aa8664e189aff 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -808,8 +808,8 @@ struct scx_rq_rescue {
 
 struct scx_rq {
 	struct scx_dispatch_q	local_dsq;
+	struct scx_dispatch_q	reject_dsq;		/* staging for rejected tasks */
 #ifdef CONFIG_EXT_SUB_SCHED
-	struct scx_dispatch_q	reject_dsq;		/* staging for cap-rejected tasks */
 	struct scx_rq_rescue	rescue;
 #endif
 	struct list_head	runnable_list;		/* runnable tasks on this rq */
-- 
2.55.0

[PATCH 10/15] sched_ext: Handle proxy-exec races in remote DSQ transfers

[Andrea Righi]

Without proxy execution, the DSQ lock and holding_cpu handshake ensure
that a task cannot be dequeued or start running during an rq-lock
handoff without clearing holding_cpu.

Proxy execution is an exception: a task can start physically executing
as a lock owner while its scheduling context remains on a DSQ; its
on-CPU or migration-disabled state can therefore change without clearing
holding_cpu.

Recheck these states after acquiring the source rq lock. If the transfer
can no longer proceed, park the task on the source rq's reject DSQ and
re-enqueue it through its owning scheduler. This preserves the BPF
scheduler's placement policy and keeps descendant tasks within their
sub-scheduler's cap grants.

Implement the scx_proxy_resolved() hook to drain the parked tasks once
proxy resolution has settled and the outgoing owner has switched out.

Without this change and proxy execution enabled, stress-ng --pipeherd
can trigger this race and migrate an active execution context, leading
to sleeping-while-atomic warnings and subsequent lockdep corruption.

This is a preparatory change to support proxy execution with sched_ext.

Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 include/linux/sched/ext.h                     |   2 +
 kernel/sched/ext/ext.c                        | 159 +++++++++++++++---
 kernel/sched/ext/internal.h                   |   8 +
 kernel/sched/ext/sub.c                        |   4 +-
 kernel/sched/sched.h                          |   1 +
 .../sched_ext/include/scx/enum_defs.autogen.h |   1 +
 6 files changed, 151 insertions(+), 24 deletions(-)

diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index c34744c493885..3fe3364604aff 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -137,6 +137,7 @@ enum scx_ent_flags {
 	 * IMMED	reenqueued due to failed ENQ_IMMED
 	 * PREEMPTED	preempted while running
 	 * CAP		sub-sched cap miss, see p->scx.reenq_reason_*
+	 * PROXY	proxy state prevented a remote DSQ transfer
 	 */
 	SCX_TASK_REENQ_REASON_SHIFT = 12,
 	SCX_TASK_REENQ_REASON_BITS = 3,
@@ -147,6 +148,7 @@ enum scx_ent_flags {
 	SCX_TASK_REENQ_IMMED	= 2 << SCX_TASK_REENQ_REASON_SHIFT,
 	SCX_TASK_REENQ_PREEMPTED = 3 << SCX_TASK_REENQ_REASON_SHIFT,
 	SCX_TASK_REENQ_CAP	= 4 << SCX_TASK_REENQ_REASON_SHIFT,
+	SCX_TASK_REENQ_PROXY	= 5 << SCX_TASK_REENQ_REASON_SHIFT,
 
 	/* iteration cursor, not a task */
 	SCX_TASK_CURSOR		= 1 << 31,
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index b43b2834141e6..7b467b666212b 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -1067,8 +1067,17 @@ static void schedule_deferred_locked(struct rq *rq)
 	schedule_deferred(rq);
 }
 
+/*
+ * Proxy resolution happens before rq->curr is switched. Queue deferred work
+ * on the rq so that an outgoing proxy owner has cleared on_cpu by the time
+ * reject_dsq is drained.
+ */
 void scx_proxy_resolved(struct rq *rq)
 {
+	lockdep_assert_rq_held(rq);
+
+	if (rq->scx.flags & SCX_RQ_PROXY_REENQ)
+		schedule_deferred_locked(rq);
 }
 
 void schedule_dsq_reenq(struct scx_sched *sch, struct scx_dispatch_q *dsq,
@@ -1564,12 +1573,18 @@ static void rq_owned_post_enq(struct scx_sched *sch, struct rq *rq,
 	call_task_dequeue(sch, rq, p, 0);
 
 	/*
-	 * Only local inserts get the wakeup treatment below. Rejects kick the
-	 * deferred reenq and rescue parks are paced by the rescue timer.
+	 * Only local inserts get the wakeup treatment below. Proxy-active tasks
+	 * and rescuees remain parked until their respective resolution paths.
+	 * Other rejects can be reenqueued immediately.
 	 */
 	if (unlikely(dsq->id != SCX_DSQ_LOCAL)) {
-		if (dsq->id == SCX_DSQ_REJECT)
-			schedule_deferred_locked(rq);
+		if (dsq->id == SCX_DSQ_REJECT) {
+			if ((p->scx.flags & SCX_TASK_REENQ_REASON_MASK) ==
+			    SCX_TASK_REENQ_PROXY)
+				rq->scx.flags |= SCX_RQ_PROXY_REENQ;
+			else
+				schedule_deferred_locked(rq);
+		}
 		return;
 	}
 
@@ -2513,8 +2528,10 @@ static void move_remote_task_to_local_dsq(struct scx_sched *sch,
  * - The BPF scheduler is bypassed while the rq is offline and we can always say
  *   no to the BPF scheduler initiated migrations while offline.
  *
- * The caller must ensure that @p and @rq are on different CPUs.
- * If enforce == true, caller must hold @p's rq lock.
+ * The caller must ensure that @p and @rq are on different CPUs. If @enforce is
+ * true, report violations attributable to BPF-directed migrations. The caller
+ * must hold @p's rq lock to avoid reporting a transient race as a scheduler
+ * error.
  */
 static bool task_can_run_on_remote_rq(struct scx_sched *sch,
 				      struct task_struct *p, struct rq *rq,
@@ -2522,11 +2539,6 @@ static bool task_can_run_on_remote_rq(struct scx_sched *sch,
 {
 	s32 cpu = cpu_of(rq);
 
-	/*
-	 * To prevent races with @p still running on its old CPU while switching
-	 * out, make sure we're holding @p's rq lock so as not to risk
-	 * erroneously killing the BPF scheduler.
-	 */
 	if (enforce)
 		lockdep_assert_rq_held(task_rq(p));
 
@@ -2573,6 +2585,60 @@ static bool task_can_run_on_remote_rq(struct scx_sched *sch,
 	return true;
 }
 
+/*
+ * Proxy execution can change @p's execution and migration-disabled state
+ * without touching its DSQ entry or clearing holding_cpu. Check those states
+ * with @p's rq locked. Without proxy execution, the holding_cpu handshake is
+ * sufficient and this must not affect the existing migration path.
+ *
+ * A BPF-directed transfer to a remote local DSQ performs a normal task
+ * migration and thus cannot move a migration-disabled task. In contrast,
+ * proxy_migrate_task() moves only a blocked donor's scheduling context towards
+ * the mutex owner and preserves its execution home in wake_cpu. The latter is
+ * therefore allowed even when the donor is migration-disabled.
+ */
+static bool task_move_proxy_raced(struct task_struct *p)
+{
+	struct rq *src_rq = task_rq(p);
+
+	lockdep_assert_rq_held(src_rq);
+
+	if (!sched_proxy_exec())
+		return false;
+
+	/* @p may be rq->curr under another task's scheduling context. */
+	if (task_on_cpu(src_rq, p))
+		return true;
+
+	if (is_migration_disabled(p))
+		return true;
+
+	/* Don't move an active scheduling context off its source rq. */
+	if (task_current_donor(src_rq, p))
+		return true;
+
+	return false;
+}
+
+/*
+ * Park a task whose remote transfer raced with proxy execution. Reenqueueing
+ * from the source rq makes the task's owning scheduler choose its placement
+ * again and preserves sub-scheduler containment.
+ */
+static void scx_reject_task(struct scx_sched *sch, struct rq *rq,
+			    struct task_struct *p, u64 enq_flags)
+{
+	lockdep_assert_rq_held(rq);
+	if (WARN_ON_ONCE(p->scx.flags & SCX_TASK_REENQ_REASON_MASK))
+		p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;
+
+	p->scx.holding_cpu = -1;
+	p->scx.flags |= SCX_TASK_REENQ_PROXY;
+	scx_prepare_dsq_divert(p, &enq_flags);
+
+	scx_dispatch_enqueue(sch, rq, &rq->scx.reject_dsq, p, 0, 0, enq_flags);
+}
+
 /**
  * unlink_dsq_and_switch_rq_lock() - Unlink task and switch to its rq lock
  * @p: target task
@@ -2630,6 +2696,20 @@ static bool consume_remote_task(struct scx_sched *sch, struct rq *this_rq,
 				struct scx_dispatch_q *dsq, struct rq *src_rq)
 {
 	if (unlink_dsq_and_switch_rq_lock(p, dsq, this_rq, src_rq)) {
+		/*
+		 * Proxy execution may have changed @p's running or
+		 * migration-disabled state while switching rq locks without
+		 * clearing holding_cpu. Park it on the source rq and let its
+		 * owning scheduler choose its placement again.
+		 */
+		if (unlikely(task_move_proxy_raced(p))) {
+			p->scx.dsq = NULL;
+			scx_reject_task(sch, src_rq, p,
+					enq_flags | SCX_ENQ_CLEAR_OPSS);
+			switch_rq_lock(src_rq, this_rq);
+			return false;
+		}
+
 		move_remote_task_to_local_dsq(sch, p, enq_flags, src_rq, this_rq);
 		return true;
 	} else {
@@ -2660,6 +2740,7 @@ static struct rq *move_task_between_dsqs(struct scx_sched *sch,
 					 struct scx_dispatch_q *dst_dsq)
 {
 	struct rq *src_rq = task_rq(p), *dst_rq;
+	bool proxy_raced;
 
 	BUG_ON(src_dsq->id == SCX_DSQ_LOCAL);
 	lockdep_assert_held(&src_dsq->lock);
@@ -2667,6 +2748,13 @@ static struct rq *move_task_between_dsqs(struct scx_sched *sch,
 
 	if (dst_dsq->id == SCX_DSQ_LOCAL) {
 		dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq);
+		proxy_raced = src_rq != dst_rq && task_move_proxy_raced(p);
+		if (unlikely(proxy_raced)) {
+			dispatch_dequeue_locked(p, src_dsq);
+			raw_spin_unlock(&src_dsq->lock);
+			scx_reject_task(sch, src_rq, p, enq_flags);
+			return src_rq;
+		}
 		if (src_rq != dst_rq &&
 		    unlikely(!task_can_run_on_remote_rq(sch, p, dst_rq, true))) {
 			dst_dsq = find_global_dsq(sch, task_cpu(p));
@@ -2822,7 +2910,9 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq,
 	/* task_rq couldn't have changed if we're still the holding cpu */
 	if (likely(p->scx.holding_cpu == raw_smp_processor_id()) &&
 	    !WARN_ON_ONCE(src_rq != task_rq(p))) {
+		bool proxy_raced = src_rq != dst_rq && task_move_proxy_raced(p);
 		bool fallback = false;
+
 		/*
 		 * If @p is staying on the same rq, there's no need to go
 		 * through the full deactivate/activate cycle. Optimize by
@@ -2832,9 +2922,13 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq,
 			p->scx.holding_cpu = -1;
 			scx_dispatch_enqueue(sch, dst_rq, &dst_rq->scx.local_dsq, p,
 					     slice, vtime, enq_flags | SCX_ENQ_APPLY_SLICE);
-		} else if (unlikely(!task_can_run_on_remote_rq(sch, p, dst_rq, true))) {
-			p->scx.holding_cpu = -1;
+		} else if (unlikely(proxy_raced)) {
+			fallback = true;
+			scx_reject_task(sch, src_rq, p, enq_flags);
+		} else if (unlikely(!task_can_run_on_remote_rq(sch, p, dst_rq,
+							       true))) {
 			fallback = true;
+			p->scx.holding_cpu = -1;
 			scx_dispatch_enqueue(sch, src_rq, find_global_dsq(sch, task_cpu(p)),
 					     p, slice, vtime,
 					     enq_flags | SCX_ENQ_APPLY_SLICE |
@@ -4585,41 +4679,64 @@ static void process_deferred_reenq_users(struct rq *rq)
 }
 
 /*
- * Drain @rq->scx.reject_dsq and reenqueue each task so that its owning BPF
- * scheduler chooses placement again.
+ * Drain ready tasks from @rq->scx.reject_dsq and reenqueue them so that their
+ * owning BPF schedulers choose placement again. Proxy-active tasks remain
+ * parked until proxy resolution schedules another drain after switch-out.
  *
  * A task can be re-rejected repeatedly. Reenqueues are bounded per task by
  * SCX_REENQ_MAX_REPEAT in scx_do_enqueue_task(), which ejects the owning
- * scheduler. The private list below prevents a task from being revisited in
- * the same round.
+ * scheduler.
  */
 static void scx_reenq_reject(struct rq *rq)
 {
 	LIST_HEAD(tasks);
 	struct task_struct *p, *n;
+	bool proxy_pending = false;
 
 	lockdep_assert_rq_held(rq);
 
-	if (list_empty(&rq->scx.reject_dsq.list))
+	if (list_empty(&rq->scx.reject_dsq.list)) {
+		rq->scx.flags &= ~SCX_RQ_PROXY_REENQ;
 		return;
+	}
 
 	/*
-	 * Move tasks to a private list so a task re-rejected by
+	 * Move ready tasks to a private list so a task re-rejected by
 	 * scx_do_enqueue_task() below isn't revisited this round.
 	 */
 	list_for_each_entry_safe(p, n, &rq->scx.reject_dsq.list, scx.dsq_list.node) {
 		u32 reason = p->scx.flags & SCX_TASK_REENQ_REASON_MASK;
 
-		/* migration_pending tasks should have bypassed to local DSQ */
-		WARN_ON_ONCE(p->migration_pending);
 		WARN_ON_ONCE(!reason);
 
+		/*
+		 * The affinity machinery owns placement while a migration is
+		 * pending and will dequeue and reactivate @p as necessary. Don't
+		 * return it to BPF in the meantime. This isn't a proxy-resolution
+		 * state and thus doesn't contribute to @proxy_pending.
+		 */
+		if (p->migration_pending) {
+			WARN_ON_ONCE(reason != SCX_TASK_REENQ_PROXY);
+			continue;
+		}
+
+		if (reason == SCX_TASK_REENQ_PROXY &&
+		    (task_on_cpu(rq, p) || task_current_donor(rq, p))) {
+			proxy_pending = true;
+			continue;
+		}
+
 		scx_dispatch_dequeue(rq, p);
 		p->scx.flags |= reason;
 
 		list_add_tail(&p->scx.dsq_list.node, &tasks);
 	}
 
+	if (proxy_pending)
+		rq->scx.flags |= SCX_RQ_PROXY_REENQ;
+	else
+		rq->scx.flags &= ~SCX_RQ_PROXY_REENQ;
+
 	list_for_each_entry_safe(p, n, &tasks, scx.dsq_list.node) {
 		list_del_init(&p->scx.dsq_list.node);
 
diff --git a/kernel/sched/ext/internal.h b/kernel/sched/ext/internal.h
index c458a12c64574..f02b384d1fb0d 100644
--- a/kernel/sched/ext/internal.h
+++ b/kernel/sched/ext/internal.h
@@ -1752,6 +1752,14 @@ enum scx_enq_flags {
 	SCX_ENQ_SLICE_DFL	= 1LLU << 62,	/* carried slice is a default refill */
 };
 
+/* Strip priority and carried slice state when diverting from a local DSQ. */
+static inline void scx_prepare_dsq_divert(struct task_struct *p, u64 *enq_flags)
+{
+	*enq_flags &= ~(SCX_ENQ_IMMED | SCX_ENQ_PREEMPT | SCX_ENQ_HEAD |
+			SCX_ENQ_APPLY_SLICE | SCX_ENQ_SLICE_DFL);
+	p->scx.flags &= ~SCX_TASK_IMMED;
+}
+
 enum scx_deq_flags {
 	/* expose select DEQUEUE_* flags as enums */
 	SCX_DEQ_SLEEP		= DEQUEUE_SLEEP,
diff --git a/kernel/sched/ext/sub.c b/kernel/sched/ext/sub.c
index a04eccd837348..1266dcf446349 100644
--- a/kernel/sched/ext/sub.c
+++ b/kernel/sched/ext/sub.c
@@ -735,9 +735,7 @@ struct scx_dispatch_q *scx_resolve_local_dsq(struct scx_sched *sch, struct rq *r
 	 * or HEAD - a diversion has no priority and IMMED is not allowed on
 	 * non-local DSQs. Strip the enq and task flags along with the slice.
 	 */
-	*enq_flags &= ~(SCX_ENQ_IMMED | SCX_ENQ_PREEMPT | SCX_ENQ_HEAD |
-			SCX_ENQ_APPLY_SLICE | SCX_ENQ_SLICE_DFL);
-	p->scx.flags &= ~SCX_TASK_IMMED;
+	scx_prepare_dsq_divert(p, enq_flags);
 
 	/* the enqueuer opted for rescue instead of rejection and reenqueue */
 	if ((*enq_flags & SCX_ENQ_RESCUE) && likely(scx_rescue_bw_1024)) {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index aa8664e189aff..15fc7c4ab73f5 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -789,6 +789,7 @@ enum scx_rq_flags {
 	SCX_RQ_BAL_CB_PENDING	= 1 << 6, /* must queue a cb after dispatching */
 	SCX_RQ_SUB_IDLE_RENOTIFY	= 1 << 7, /* sub-scheds are owed update_idle() */
 	SCX_RQ_ROOT_IDLE_RENOTIFY	= 1 << 8, /* the root is owed update_idle() */
+	SCX_RQ_PROXY_REENQ	= 1 << 9, /* proxy-rejected tasks need reenqueue */
 
 	SCX_RQ_IN_WAKEUP	= 1 << 16,
 	SCX_RQ_IN_BALANCE	= 1 << 17,
diff --git a/tools/sched_ext/include/scx/enum_defs.autogen.h b/tools/sched_ext/include/scx/enum_defs.autogen.h
index c05d4b5729555..ec5e3fbc650fa 100644
--- a/tools/sched_ext/include/scx/enum_defs.autogen.h
+++ b/tools/sched_ext/include/scx/enum_defs.autogen.h
@@ -118,6 +118,7 @@
 #define HAVE_SCX_TASK_REENQ_IMMED
 #define HAVE_SCX_TASK_REENQ_PREEMPTED
 #define HAVE_SCX_TASK_REENQ_CAP
+#define HAVE_SCX_TASK_REENQ_PROXY
 #define HAVE_SCX_TASK_CURSOR
 #define HAVE_SCX_ECODE_RSN_HOTPLUG
 #define HAVE_SCX_ECODE_RSN_CGROUP_OFFLINE
-- 
2.55.0

[PATCH 11/15] sched_ext: Split curr|donor references properly

[Andrea Righi]

With proxy execution, the task selected by the scheduler and the task
physically executing can differ. A blocked mutex waiter donates its
scheduling context to the lock owner:

  D -----------------> M -------------> O ----------------> T
  [donor] blocked on [mutex] owned by [owner] preempted by [task]
     \_________________________________^
          donates scheduling context

where:

  D = blocked donor
  M = mutex
  O = mutex owner
  T = competing runnable task

During a proxy execution switch, D supplies the scheduling class,
priority, and runtime budget, while O supplies the execution context: O
is the task whose code physically executes. T is a competing runnable
task which may preempt the D/O proxy execution.

Consider FAIR and EXT tasks with sched_ext running in partial mode. FAIR
can be replaced with a higher scheduling class such as RT or deadline
without changing the class interaction described here. The possible
combinations are:

  1. D is EXT, O is EXT, T is EXT

     D can interrupt T according to BPF scheduling policy. O executes
     with D's EXT priority and runtime budget, while T waits in EXT.

  2. D is EXT, O is EXT, T is FAIR

     D is visible to the BPF scheduler, but cannot preempt T because
     EXT is below FAIR. Once T stops, BPF can dispatch D and O executes
     with D's EXT priority and runtime budget. If T becomes runnable
     again, it preempts the D/O proxy execution.

  3. D is EXT, O is FAIR, T is EXT

     This cannot represent T preempting O because EXT is below FAIR.

  4. D is EXT, O is FAIR, T is FAIR

     D cannot boost O above T because EXT is below FAIR. O and T
     continue competing under FAIR. Once O releases M, D wakes and
     resumes normal EXT scheduling.

  5. D is FAIR, O is EXT, T is EXT

     D preempts T as the higher-class scheduling context. O executes
     with D's FAIR priority and runtime budget, while T waits in EXT.
     D is not visible to the BPF scheduler.

  6. D is FAIR, O is EXT, T is FAIR

     D competes with T according to its FAIR deadline. When D is
     selected, O executes with D's FAIR priority and runtime budget.
     D is not visible to the BPF scheduler.

  7. D is FAIR, O is FAIR, T is EXT

     This cannot represent T preempting O because EXT is below FAIR.

  8. D is FAIR, O is FAIR, T is FAIR

     O, T, and D all have FAIR scheduling contexts. D remains runnable
     as a blocked proxy donor. When CFS selects D, O executes using D's
     FAIR scheduling context. When CFS selects O, O executes using its
     own FAIR context, and when CFS selects T, T executes normally. D
     is not visible to the BPF scheduler.

Thus, sched_ext policy and accounting must generally use rq->donor, the
scheduler-selected task which supplies the scheduling context, rather
than rq->curr, the task whose code physically executes. Without proxy
execution they are the same task.

On nohz_full CPUs, a blocked proxy donor must retain the scheduler tick
even when it has an infinite slice. Otherwise, a full dynticks CPU could
stop the tick while rq->curr and rq->donor differ, violating assumptions
made by the remote NOHZ tick path.

This is a conservative compromise that keeps the change local to
sched_ext, at the cost of a periodic tick while a blocked proxy donor is
selected. Allowing blocked proxy donors to run tickless would require
making the core scheduler's remote tick handling aware that rq->curr and
rq->donor can differ.

Moreover, extend scx_dump_state() to report both contexts. Each CPU
record now includes a donor= line. If an EXT donor differs from
rq->curr, also emit its detailed task record. The existing '*' marker
continues to identify rq->curr, while the donor= line identifies the
otherwise unmarked donor record.

Note that at this point in the series, CONFIG_SCHED_PROXY_EXEC still
depends on !CONFIG_SCHED_CLASS_EXT, so proxy execution and sched_ext
cannot be enabled together. The scheduling changes are therefore
preparatory. A later patch removes this restriction.

Co-developed-by: John Stultz <jstultz@google.com>
Signed-off-by: John Stultz <jstultz@google.com>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 Documentation/scheduler/sched-ext.rst |   6 ++
 kernel/sched/ext/ext.c                | 116 +++++++++++++++++---------
 kernel/sched/ext/sub.h                |  11 +--
 3 files changed, 88 insertions(+), 45 deletions(-)

diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst
index ad2fff3c05937..db1ef89ed8f2a 100644
--- a/Documentation/scheduler/sched-ext.rst
+++ b/Documentation/scheduler/sched-ext.rst
@@ -487,6 +487,12 @@ and edge cases, to name a few examples:
   class, in which case it will exit the tick-dispatch loop even though it is runnable
   and has a non-zero slice.
 
+* Under proxy execution, sched_ext continues to observe the donor as the current
+  scheduling context. A blocked donor does not enter an ``ops.running()`` /
+  ``ops.stopping()`` session because it does not execute itself, and the lock
+  owner executing on its behalf is intentionally not reported through these
+  callbacks.
+
 See the "Scheduling Cycle" section for a more detailed description of how
 a freshly woken up task gets on a CPU.
 
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 7b467b666212b..39d3e3af05f90 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -1438,23 +1438,30 @@ static void apply_slice_vtime(struct task_struct *p, u64 slice, u64 vtime, u64 e
 
 static void update_curr_scx(struct rq *rq)
 {
-	struct task_struct *curr = rq->curr;
+	struct task_struct *donor;
 	s64 delta_exec;
 
+	/*
+	 * update_curr_scx() is selected through rq->donor->sched_class, not
+	 * rq->curr->sched_class, so @donor is always an EXT task here. If an EXT
+	 * owner executes for a FAIR donor, FAIR's update_curr() runs instead.
+	 */
+	donor = rq->donor;
+
 	/* apply even on 0 delta_exec, callers may still act on the slice */
-	apply_task_slice_oob(rq, curr);
+	apply_task_slice_oob(rq, donor);
 
 	delta_exec = update_curr_common(rq);
 	if (unlikely(delta_exec <= 0))
 		return;
 
-	if (curr->scx.slice != SCX_SLICE_INF) {
-		curr->scx.slice -= min_t(u64, curr->scx.slice, delta_exec);
-		if (!curr->scx.slice)
-			touch_core_sched(rq, curr);
+	if (donor->scx.slice != SCX_SLICE_INF) {
+		donor->scx.slice -= min_t(u64, donor->scx.slice, delta_exec);
+		if (!donor->scx.slice)
+			touch_core_sched(rq, donor);
 	}
 
-	if (unlikely(curr == scx_rescuee(rq)))
+	if (unlikely(donor == scx_rescuee(rq)))
 		scx_rescue_charge(rq, delta_exec);
 
 	dl_server_update(&rq->ext_server, delta_exec);
@@ -1634,9 +1641,9 @@ static void rq_owned_post_enq(struct scx_sched *sch, struct rq *rq,
 	if (rq->scx.flags & SCX_RQ_IN_BALANCE)
 		return;
 
-	if ((enq_flags & SCX_ENQ_PREEMPT) && p != rq->curr &&
-	    rq->curr->sched_class == &ext_sched_class) {
-		if (likely(scx_set_task_slice(rq->curr, 0)))
+	if ((enq_flags & SCX_ENQ_PREEMPT) && p != rq->donor &&
+	    rq->donor->sched_class == &ext_sched_class) {
+		if (likely(scx_set_task_slice(rq->donor, 0)))
 			resched_curr(rq);
 		else
 			__scx_add_event(sch, SCX_EV_SLICE_DENIED, 1);
@@ -2212,13 +2219,14 @@ static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int core_enq_
 		rq->scx.flags |= SCX_RQ_IN_WAKEUP;
 
 	/*
-	 * Restoring a running task will be immediately followed by
-	 * set_next_task_scx() which expects the task to not be on the BPF
+	 * Restoring the current scheduling context will be immediately followed
+	 * by set_next_task_scx() which expects the task to not be on the BPF
 	 * scheduler as tasks can only start running through local DSQs. Force
 	 * direct-dispatch into the local DSQ by setting the sticky_cpu. Mark
 	 * IGNORE_CAPS to force entry into the local DSQ.
 	 */
-	if (unlikely(enq_flags & ENQUEUE_RESTORE) && task_current(rq, p)) {
+	if (unlikely(enq_flags & ENQUEUE_RESTORE) &&
+	    task_current_donor(rq, p)) {
 		sticky_cpu = cpu_of(rq);
 		enq_flags |= SCX_ENQ_IGNORE_CAPS;
 	}
@@ -2941,7 +2949,8 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq,
 		}
 
 		/* if the destination CPU is idle, wake it up */
-		if (!fallback && sched_class_above(p->sched_class, dst_rq->curr->sched_class))
+		if (!fallback && sched_class_above(p->sched_class,
+						      dst_rq->donor->sched_class))
 			resched_curr(dst_rq);
 	}
 
@@ -3165,6 +3174,8 @@ static void scx_start_task_running(struct rq *rq, struct task_struct *p)
 
 static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
 {
+	bool can_stop_tick;
+
 	if (p->scx.flags & SCX_TASK_QUEUED) {
 		/*
 		 * Core-sched might decide to execute @p before it is
@@ -3189,6 +3200,7 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
 
 	/* apply any pending out-of-band slice request before the tick decision */
 	apply_task_slice_oob(rq, p);
+	can_stop_tick = p->scx.slice == SCX_SLICE_INF && !p->is_blocked;
 
 	/*
 	 * @p is getting newly scheduled or got kicked after someone updated its
@@ -3199,7 +3211,7 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
 	 * nohz. In the future, we might want to add a mechanism to update
 	 * load_avgs periodically on tick-stopped CPUs.
 	 */
-	if (p->scx.slice == SCX_SLICE_INF) {
+	if (can_stop_tick) {
 		if (!(rq->scx.flags & SCX_RQ_CAN_STOP_TICK)) {
 			/*
 			 * Bypass mode always assigns finite slices, so @p
@@ -3220,7 +3232,8 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
 
 		/*
 		 * @rq still references the outgoing scheduling context. A finite
-		 * slice is sufficient by itself to require the tick.
+		 * slice or a blocked proxy donor is sufficient by itself to require
+		 * the tick.
 		 */
 		if (tick_nohz_full_cpu(cpu_of(rq)))
 			tick_nohz_dep_set_cpu(cpu_of(rq), TICK_DEP_BIT_SCHED);
@@ -3441,7 +3454,7 @@ static struct task_struct *first_local_task(struct rq *rq)
 static struct task_struct *
 do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx)
 {
-	struct task_struct *prev = rq->curr;
+	struct task_struct *prev = rq->donor;
 	bool keep_prev;
 	struct task_struct *p;
 
@@ -3850,9 +3863,9 @@ void scx_tick(struct rq *rq)
 	update_other_load_avgs(rq);
 }
 
-static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued)
+static void task_tick_scx(struct rq *rq, struct task_struct *donor, int queued)
 {
-	struct scx_sched *sch = scx_task_sched(curr);
+	struct scx_sched *sch = scx_task_sched(donor);
 
 	update_curr_scx(rq);
 
@@ -3861,13 +3874,13 @@ static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued)
 	 * we can't trust the slice management or ops.core_sched_before().
 	 */
 	if (scx_bypassing(sch, cpu_of(rq))) {
-		scx_set_task_slice(curr, 0);
-		touch_core_sched(rq, curr);
+		scx_set_task_slice(donor, 0);
+		touch_core_sched(rq, donor);
 	} else if (SCX_HAS_OP(sch, tick)) {
-		SCX_CALL_OP_TASK(sch, tick, rq, curr);
+		SCX_CALL_OP_TASK(sch, tick, rq, donor);
 	}
 
-	if (!curr->scx.slice)
+	if (!donor->scx.slice)
 		resched_curr(rq);
 }
 
@@ -4512,16 +4525,16 @@ static u32 reenq_local(struct scx_sched *sch, struct rq *rq, u64 reenq_flags)
 	}
 
 	/*
-	 * The revoke that scheduled this scan may have raced the pick: curr
+	 * The revoke that scheduled this scan may have raced the pick: donor
 	 * may be a now-capless task, either one that kept running or one
 	 * promoted off the local DSQ between the ecaps sync and this scan.
 	 * Zero the slice to evict it. The enqueue gate blocks new capless
 	 * inserts, so no later pick can slip through after the scan.
 	 */
 	if ((reenq_flags & SCX_REENQ_CAP_REVOKE) &&
-	    rq->curr->sched_class == &ext_sched_class &&
-	    scx_task_reenq_on_cap_revoke(rq, rq->curr)) {
-		scx_set_task_slice(rq->curr, 0);
+	    rq->donor->sched_class == &ext_sched_class &&
+	    scx_task_reenq_on_cap_revoke(rq, rq->donor)) {
+		scx_set_task_slice(rq->donor, 0);
 		resched_curr(rq);
 	}
 
@@ -4762,14 +4775,18 @@ static void run_deferred(struct rq *rq)
 #ifdef CONFIG_NO_HZ_FULL
 bool scx_can_stop_tick(struct rq *rq)
 {
-	struct task_struct *p = rq->curr;
+	struct task_struct *p = rq->donor;
 	struct scx_sched *sch = scx_task_sched(p);
 
+	/* The remote tick path assumes that proxy execution is not active. */
+	if (rq->curr != rq->donor)
+		return false;
+
 	if (p->sched_class != &ext_sched_class)
 		return true;
 
 	/*
-	 * @rq->curr may still reference an outgoing EXT task after it has been
+	 * @rq->donor may still reference an outgoing EXT task after it has been
 	 * dequeued. If no EXT tasks are accounted on @rq, ignore its stale
 	 * slice state. If another task is dispatched from a DSQ,
 	 * set_next_task_scx() will update the dependency for the incoming task.
@@ -4790,7 +4807,8 @@ bool scx_can_stop_tick(struct rq *rq)
 	/*
 	 * @rq can dispatch from different DSQs, so we can't tell whether it
 	 * needs the tick or not by looking at nr_running. Allow stopping ticks
-	 * iff the BPF scheduler indicated so. See set_next_task_scx().
+	 * iff set_next_task_scx() determined that the selected scheduling context
+	 * can run tickless.
 	 */
 	return rq->scx.flags & SCX_RQ_CAN_STOP_TICK;
 }
@@ -6988,6 +7006,8 @@ static void scx_dump_cpu(struct scx_sched *sch, struct seq_buf *s,
 	scx_rescue_dump(&ns, rq);
 	scx_dump_line(&ns, "          curr=%s[%d] class=%ps",
 		      rq->curr->comm, rq->curr->pid, rq->curr->sched_class);
+	scx_dump_line(&ns, "          donor=%s[%d] class=%ps",
+		      rq->donor->comm, rq->donor->pid, rq->donor->sched_class);
 	if (!cpumask_empty(pcpu->cpus_to_kick))
 		scx_dump_line(&ns, "  cpus_to_kick   : %*pb",
 			      cpumask_pr_args(pcpu->cpus_to_kick));
@@ -7031,6 +7051,10 @@ static void scx_dump_cpu(struct scx_sched *sch, struct seq_buf *s,
 	if (rq->curr->sched_class == &ext_sched_class &&
 	    (dump_all_tasks || scx_task_on_sched(sch, rq->curr)))
 		scx_dump_task(sch, s, dctx, rq, rq->curr, '*');
+	if (rq->donor != rq->curr &&
+	    rq->donor->sched_class == &ext_sched_class &&
+	    (dump_all_tasks || scx_task_on_sched(sch, rq->donor)))
+		scx_dump_task(sch, s, dctx, rq, rq->donor, ' ');
 
 	list_for_each_entry(p, &rq->scx.runnable_list, scx.runnable_node)
 		if (dump_all_tasks || scx_task_on_sched(sch, p))
@@ -8579,7 +8603,7 @@ static bool kick_one_cpu(s32 cpu, struct scx_sched_pcpu *pcpu, struct rq *this_r
 	unsigned long flags;
 
 	raw_spin_rq_lock_irqsave(rq, flags);
-	cur_class = rq->curr->sched_class;
+	cur_class = rq->donor->sched_class;
 
 	/*
 	 * During CPU hotplug, a CPU may depend on kicking itself to make
@@ -8599,7 +8623,7 @@ static bool kick_one_cpu(s32 cpu, struct scx_sched_pcpu *pcpu, struct rq *this_r
 
 				if (unlikely(scx_missing_caps(pcpu->sch, cpu, caps)))
 					__scx_add_event(pcpu->sch, SCX_EV_SUB_PREEMPT_DENIED, 1);
-				else if (unlikely(!scx_set_task_slice(rq->curr, 0)))
+				else if (unlikely(!scx_set_task_slice(rq->donor, 0)))
 					__scx_add_event(pcpu->sch, SCX_EV_SLICE_DENIED, 1);
 			}
 			cpumask_clear_cpu(cpu, pcpu->cpus_to_preempt);
@@ -9575,8 +9599,10 @@ __bpf_kfunc bool scx_bpf_task_set_slice(struct task_struct *p, u64 slice,
 		return false;
 
 	/*
-	 * Directly write only when we hold the lock of the rq @p is queued or
-	 * running on. See the write rules above.
+	 * Directly write only when we hold the lock of the rq @p is queued on or
+	 * provides the current scheduling context for. Under proxy execution,
+	 * rq->donor owns and consumes the slice while rq->curr executes on its
+	 * behalf. See the slice write rules above.
 	 *
 	 * While @p is queued on a user DSQ or in the BPF scheduler,
 	 * synchronization is the scheduler's responsibility. This write can
@@ -9590,7 +9616,7 @@ __bpf_kfunc bool scx_bpf_task_set_slice(struct task_struct *p, u64 slice,
 	locked_rq = scx_locked_rq();
 	if (!locked_rq ||
 	    (READ_ONCE(p->scx.runnable_cpu) != cpu_of(locked_rq) &&
-	     !task_current(locked_rq, p))) {
+	     !task_current_donor(locked_rq, p))) {
 		set_task_slice_oob(sch, p, slice);
 		return true;
 	}
@@ -10478,12 +10504,17 @@ __bpf_kfunc void scx_bpf_put_cpumask(const struct cpumask *cpumask)
 }
 
 /**
- * scx_bpf_task_running - Is task currently running?
+ * scx_bpf_task_running - Is task the current scheduling context?
  * @p: task of interest
+ *
+ * Under proxy execution, this reports the donor rather than the task whose
+ * code is physically executing. The physical execution context is intentionally
+ * not exposed to the BPF scheduler, which continues to observe the donor as the
+ * running scheduling context.
  */
 __bpf_kfunc bool scx_bpf_task_running(const struct task_struct *p)
 {
-	return task_rq(p)->curr == p;
+	return rcu_access_pointer(task_rq(p)->donor) == p;
 }
 
 /**
@@ -10544,10 +10575,15 @@ __bpf_kfunc struct rq *scx_bpf_locked_rq(const struct bpf_prog_aux *aux)
 }
 
 /**
- * scx_bpf_cpu_curr - Return remote CPU's curr task
+ * scx_bpf_cpu_curr - Return remote CPU's current scheduling context
  * @cpu: CPU of interest
  * @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs
  *
+ * Under proxy execution, this returns the donor, which supplies the scheduling
+ * policy and runtime budget, rather than the task whose code is physically
+ * executing. The physical execution context is intentionally not exposed to
+ * the BPF scheduler.
+ *
  * Callers must hold RCU read lock (KF_RCU).
  */
 __bpf_kfunc struct task_struct *scx_bpf_cpu_curr(s32 cpu, const struct bpf_prog_aux *aux)
@@ -10563,7 +10599,7 @@ __bpf_kfunc struct task_struct *scx_bpf_cpu_curr(s32 cpu, const struct bpf_prog_
 	if (!scx_cpu_valid(sch, cpu, NULL))
 		return NULL;
 
-	return rcu_dereference(cpu_rq(cpu)->curr);
+	return rcu_dereference(cpu_rq(cpu)->donor);
 }
 
 /**
@@ -10587,7 +10623,7 @@ __bpf_kfunc struct task_struct *scx_bpf_cid_curr(s32 cid, const struct bpf_prog_
 	cpu = scx_cid_to_cpu(sch, cid);
 	if (cpu < 0)
 		return NULL;
-	return rcu_dereference(cpu_rq(cpu)->curr);
+	return rcu_dereference(cpu_rq(cpu)->donor);
 }
 
 /**
diff --git a/kernel/sched/ext/sub.h b/kernel/sched/ext/sub.h
index 8f2425bdb9530..24357d8c5e335 100644
--- a/kernel/sched/ext/sub.h
+++ b/kernel/sched/ext/sub.h
@@ -167,17 +167,18 @@ static inline u64 scx_caps_for_task(struct task_struct *p)
 	return SCX_CAP_ENQ;
 }
 
-/* the cap @sch needs to preempt @rq's current task, 0 if none */
-static inline u64 scx_caps_for_preempt(struct scx_sched *sch, struct rq *rq, u64 enq_flags)
+/* the cap @sch needs to preempt @rq's current scheduling context, 0 if none */
+static inline u64 scx_caps_for_preempt(struct scx_sched *sch, struct rq *rq,
+				       u64 enq_flags)
 {
-	struct task_struct *curr = rq->curr;
+	struct task_struct *donor = rq->donor;
 
 	/* a kernel-forced placement preempts regardless of caps */
 	if (unlikely(enq_flags & SCX_ENQ_IGNORE_CAPS))
 		return 0;
 	/* a non-ext task can't be preempted by ext, own-subtree needs no cap */
-	if (curr->sched_class != &ext_sched_class ||
-	    scx_is_descendant(scx_task_sched(curr), sch))
+	if (donor->sched_class != &ext_sched_class ||
+	    scx_is_descendant(scx_task_sched(donor), sch))
 		return 0;
 	return SCX_CAP_PREEMPT;
 }
-- 
2.55.0

[PATCH 12/15] sched_ext: Delegate proxy donor admission to BPF schedulers

[Andrea Righi]

Proxy execution keeps a mutex-blocked donor runnable so that its scheduling
context can execute the mutex owner.

Define SCX_OPS_ENQ_BLOCKED as the admission contract for retained donors.
Schedulers without the flag block EXT donors normally. Schedulers with the
flag continue to own blocked donors and receive them through ops.enqueue()
with SCX_ENQ_BLOCKED, allowing BPF to choose their DSQ, CPU and ordering.

After BPF dispatches a donor, proxy execution may move its context
to the rq of the mutex owner. This move is distinct from BPF placement:
wake_cpu continues to identify the callback CPU of the donor, while
task_cpu() identifies the proxy CPU. A proxy-migrated donor returns through
the full wakeup activation path when the mutex is released.

Do not carry a retained proxy session across BPF scheduler ownership
changes. Before root activation, parent-to-child takeover, rehome or punt,
fully deactivate a retained donor unconditionally. The incoming scheduler
then starts with clean task state and applies its own admission policy the
next time the task blocks.

A retained donor that wakes on its callback rq does not pass through
enqueue_task_scx() again. Track full wakeup enqueueing with
SCX_TASK_ENQ_WAKEUP so wakeup_preempt_scx() can request dispatch
reconsideration only for this retained-donor case.

Blocked-donor enqueueing takes precedence over the exiting and
migration-disabled local-DSQ fallbacks, so that an opted-in scheduler sees
every eligible donor request.

Co-developed-by: John Stultz <jstultz@google.com>
Signed-off-by: John Stultz <jstultz@google.com>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 include/linux/sched/ext.h                     |   1 +
 kernel/sched/ext/ext.c                        | 141 ++++++++++++++++--
 kernel/sched/ext/internal.h                   |  23 ++-
 kernel/sched/ext/sub.c                        |   9 +-
 tools/sched_ext/include/scx/compat.h          |   1 +
 .../sched_ext/include/scx/enum_defs.autogen.h |   1 +
 .../sched_ext/include/scx/enums.autogen.bpf.h |   3 +
 tools/sched_ext/include/scx/enums.autogen.h   |   1 +
 8 files changed, 160 insertions(+), 20 deletions(-)

diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index 3fe3364604aff..4ff3186eca9eb 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -105,6 +105,7 @@ enum scx_ent_flags {
 	SCX_TASK_IMMED		= 1 << 5, /* task is on local DSQ with %SCX_ENQ_IMMED */
 	SCX_TASK_PROTECTED	= 1 << 6, /* slice and DSQ head position protected */
 	SCX_TASK_RUN_TRACKED	= 1 << 7, /* task is in an ops.running()/stopping() session */
+	SCX_TASK_ENQ_WAKEUP	= 1 << 11, /* wakeup enqueue awaiting wakeup_preempt() */
 
 	/*
 	 * Bits 8 to 10 are used to carry task state:
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 39d3e3af05f90..8b0c81b59e738 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -26,7 +26,33 @@ DEFINE_RAW_SPINLOCK(scx_sched_lock);
 
 bool scx_allow_proxy_exec(const struct task_struct *p)
 {
-	return p->sched_class != &ext_sched_class;
+	struct scx_sched *sch;
+
+	if (p->sched_class != &ext_sched_class)
+		return true;
+
+	/*
+	 * scx_enabled() may change while __schedule() holds only @p's rq lock.
+	 * Once @p is associated with a scheduler, use that scheduler's policy
+	 * even while the global enable state is transitioning.
+	 */
+	sch = scx_task_sched(p);
+	return !sch || (sch->ops.flags & SCX_OPS_ENQ_BLOCKED);
+}
+
+/*
+ * End retained proxy execution before changing @p's BPF scheduler ownership.
+ * Called with @p's pi and rq locks held immediately before
+ * sched_change_begin(). The caller must pass DEQUEUE_NOCLOCK so the rq clock
+ * is updated only once.
+ */
+void scx_prepare_task_sched_change(struct task_struct *p)
+{
+	lockdep_assert_held(&p->pi_lock);
+	lockdep_assert_rq_held(task_rq(p));
+
+	update_rq_clock(task_rq(p));
+	sched_proxy_block_task(task_rq(p), p);
 }
 
 /*
@@ -2046,6 +2072,7 @@ void scx_do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags,
 	struct scx_sched *sch = scx_task_sched(p);
 	struct task_struct **ddsp_taskp;
 	struct scx_dispatch_q *dsq;
+	bool enq_blocked;
 	unsigned long qseq;
 
 	WARN_ON_ONCE(!(p->scx.flags & SCX_TASK_QUEUED));
@@ -2096,19 +2123,25 @@ void scx_do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags,
 	if (p->scx.ddsp_dsq_id != SCX_DSQ_INVALID)
 		goto direct;
 
-	/* see %SCX_OPS_ENQ_EXITING */
-	if (!(sch->ops.flags & SCX_OPS_ENQ_EXITING) &&
-	    unlikely(p->flags & PF_EXITING)) {
-		__scx_add_event(sch, SCX_EV_ENQ_SKIP_EXITING, 1);
-		enq_flags |= SCX_ENQ_RESCUE;	/* avoid looping on cap rejection */
-		goto local;
-	}
+	enq_blocked = (sch->ops.flags & SCX_OPS_ENQ_BLOCKED) &&
+		      p->is_blocked && !(enq_flags & SCX_ENQ_WAKEUP);
+	if (enq_blocked) {
+		enq_flags |= SCX_ENQ_BLOCKED;
+	} else {
+		/* see %SCX_OPS_ENQ_EXITING */
+		if (!(sch->ops.flags & SCX_OPS_ENQ_EXITING) &&
+		    unlikely(p->flags & PF_EXITING)) {
+			__scx_add_event(sch, SCX_EV_ENQ_SKIP_EXITING, 1);
+			enq_flags |= SCX_ENQ_RESCUE;	/* avoid looping on cap rejection */
+			goto local;
+		}
 
-	/* see %SCX_OPS_ENQ_MIGRATION_DISABLED */
-	if (!(sch->ops.flags & SCX_OPS_ENQ_MIGRATION_DISABLED) &&
-	    is_migration_disabled(p)) {
-		__scx_add_event(sch, SCX_EV_ENQ_SKIP_MIGRATION_DISABLED, 1);
-		goto local;
+		/* see %SCX_OPS_ENQ_MIGRATION_DISABLED */
+		if (!(sch->ops.flags & SCX_OPS_ENQ_MIGRATION_DISABLED) &&
+		    is_migration_disabled(p)) {
+			__scx_add_event(sch, SCX_EV_ENQ_SKIP_MIGRATION_DISABLED, 1);
+			goto local;
+		}
 	}
 
 	if (unlikely(!SCX_HAS_OP(sch, enqueue)))
@@ -2215,8 +2248,17 @@ static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int core_enq_
 	int sticky_cpu = p->scx.sticky_cpu;
 	u64 enq_flags = core_enq_flags | rq->scx.remote_activate_enq_flags;
 
-	if (enq_flags & ENQUEUE_WAKEUP)
+	/*
+	 * p->is_blocked is cleared after wakeup_preempt(), so remember whether
+	 * this is a full wakeup activation. If wakeup_preempt_scx() isn't called,
+	 * set_next_task_scx() or a subsequent non-wakeup enqueue clears the flag.
+	 */
+	if (enq_flags & ENQUEUE_WAKEUP) {
 		rq->scx.flags |= SCX_RQ_IN_WAKEUP;
+		p->scx.flags |= SCX_TASK_ENQ_WAKEUP;
+	} else {
+		p->scx.flags &= ~SCX_TASK_ENQ_WAKEUP;
+	}
 
 	/*
 	 * Restoring the current scheduling context will be immediately followed
@@ -2434,10 +2476,30 @@ static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p, int wake_fl
 	/*
 	 * Preemption between SCX tasks is implemented by resetting the victim
 	 * task's slice to 0 and triggering reschedule on the target CPU.
-	 * Nothing to do.
+	 *
+	 * A mutex waiter can remain on-rq as a proxy donor while logically
+	 * blocked. If it wakes without having been proxy-migrated,
+	 * ttwu_runnable() calls here without another enqueue_task_scx(). Request
+	 * rescheduling so that ops.dispatch() can reconsider the task after
+	 * ttwu_runnable() clears is_blocked.
+	 *
+	 * A proxy-migrated donor instead returns through the full activation
+	 * path, which calls enqueue_task_scx() before arriving here.
+	 * SCX_TASK_ENQ_WAKEUP records that the enqueue already happened and an
+	 * additional reschedule isn't needed.
 	 */
-	if (p->sched_class == &ext_sched_class)
+	if (p->sched_class == &ext_sched_class) {
+		bool enq_wakeup = p->scx.flags & SCX_TASK_ENQ_WAKEUP;
+
+		p->scx.flags &= ~SCX_TASK_ENQ_WAKEUP;
+		if (!enq_wakeup && p->is_blocked) {
+			struct scx_sched *sch = scx_task_sched(p);
+
+			if (sch && (sch->ops.flags & SCX_OPS_ENQ_BLOCKED))
+				resched_curr(rq);
+		}
 		return;
+	}
 
 	/*
 	 * Getting preempted by a higher-priority class. Reenqueue IMMED tasks.
@@ -2552,6 +2614,20 @@ static bool task_can_run_on_remote_rq(struct scx_sched *sch,
 
 	WARN_ON_ONCE(task_cpu(p) == cpu);
 
+	/*
+	 * A blocked donor may be moved normally to select a new callback rq.
+	 * set_task_cpu() updates wake_cpu and makes the destination rq its new
+	 * callback home.
+	 *
+	 * proxy_set_task_cpu() instead preserves wake_cpu when moving a donor to
+	 * its lock owner's CPU. Keep such a donor on the proxy rq until it wakes;
+	 * otherwise normal BPF placement may repeatedly pull it back to its
+	 * callback rq only for proxy execution to move it to the owner again.
+	 */
+	if (sched_proxy_exec() && p->is_blocked &&
+	    task_cpu(p) != p->wake_cpu)
+		return false;
+
 	/*
 	 * If @p has migration disabled, @p->cpus_ptr is updated to contain only
 	 * the pinned CPU in migrate_disable_switch() while @p is being switched
@@ -3176,6 +3252,8 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
 {
 	bool can_stop_tick;
 
+	p->scx.flags &= ~SCX_TASK_ENQ_WAKEUP;
+
 	if (p->scx.flags & SCX_TASK_QUEUED) {
 		/*
 		 * Core-sched might decide to execute @p before it is
@@ -3339,6 +3417,24 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p,
 	if (p->scx.flags & SCX_TASK_QUEUED) {
 		set_task_runnable(rq, p);
 
+		/* Delegate retained donor admission to its owning BPF scheduler. */
+		if (p->is_blocked) {
+			/*
+			 * If the donor is the same and only the mutex owner
+			 * changes, avoid triggering another ops.enqueue(): the
+			 * BPF scheduler has already admitted the donor, so it
+			 * can continue running.
+			 */
+			if (next == p)
+				goto switch_class;
+
+			if (WARN_ON_ONCE(!sch))
+				goto switch_class;
+			WARN_ON_ONCE(!(sch->ops.flags & SCX_OPS_ENQ_BLOCKED));
+			scx_do_enqueue_task(rq, p, 0, -1);
+			goto switch_class;
+		}
+
 		/*
 		 * If @p has slice left and is being put, @p is getting
 		 * preempted by a higher priority scheduler class or core-sched
@@ -7563,6 +7659,11 @@ int scx_validate_ops(struct scx_sched *sch, const struct sched_ext_ops *ops)
 		return -EINVAL;
 	}
 
+	if ((ops->flags & SCX_OPS_ENQ_BLOCKED) && !ops->enqueue) {
+		scx_error(sch, "SCX_OPS_ENQ_BLOCKED requires ops.enqueue() to be implemented");
+		return -EINVAL;
+	}
+
 	/*
 	 * SCX_OPS_TID_TO_TASK is enabled by the root scheduler. A sub-sched
 	 * may set it to declare a dependency; reject if the root hasn't
@@ -7950,6 +8051,14 @@ static void scx_root_enable_workfn(struct kthread_work *work)
 
 		if (old_class != new_class)
 			queue_flags |= DEQUEUE_CLASS;
+		if (old_class == new_class && new_class == &ext_sched_class) {
+			/*
+			 * This is an EXT-to-EXT scheduler ownership change, so
+			 * sched_change_begin() won't end retained proxy execution.
+			 */
+			scx_prepare_task_sched_change(p);
+			queue_flags |= DEQUEUE_NOCLOCK;
+		}
 
 		scoped_guard (sched_change, p, new_class, queue_flags) {
 			scx_set_task_slice(p, READ_ONCE(sch->slice_dfl));
diff --git a/kernel/sched/ext/internal.h b/kernel/sched/ext/internal.h
index f02b384d1fb0d..f33c3601b189d 100644
--- a/kernel/sched/ext/internal.h
+++ b/kernel/sched/ext/internal.h
@@ -215,6 +215,19 @@ enum scx_ops_flags {
 	 */
 	SCX_OPS_TID_TO_TASK		= 1LLU << 8,
 
+	/*
+	 * If set, mutex-blocked tasks remain runnable as proxy donors and are
+	 * passed to ops.enqueue() with %SCX_ENQ_BLOCKED. The BPF scheduler controls
+	 * when donors are dispatched and whether they should preempt other work.
+	 *
+	 * If clear, mutex-blocked tasks are removed from the runqueue normally
+	 * and cannot donate their scheduling context through proxy execution.
+	 *
+	 * For blocked donors, this flag takes precedence over
+	 * %SCX_OPS_ENQ_EXITING and %SCX_OPS_ENQ_MIGRATION_DISABLED.
+	 */
+	SCX_OPS_ENQ_BLOCKED		= 1LLU << 9,
+
 	SCX_OPS_ALL_FLAGS		= SCX_OPS_KEEP_BUILTIN_IDLE |
 					  SCX_OPS_ENQ_LAST |
 					  SCX_OPS_ENQ_EXITING |
@@ -223,7 +236,8 @@ enum scx_ops_flags {
 					  SCX_OPS_SWITCH_PARTIAL |
 					  SCX_OPS_BUILTIN_IDLE_PER_NODE |
 					  SCX_OPS_ALWAYS_ENQ_IMMED |
-					  SCX_OPS_TID_TO_TASK,
+					  SCX_OPS_TID_TO_TASK |
+					  SCX_OPS_ENQ_BLOCKED,
 
 	/* high 8 bits are internal, don't include in SCX_OPS_ALL_FLAGS */
 	__SCX_OPS_INTERNAL_MASK		= 0xffLLU << 56,
@@ -1740,6 +1754,12 @@ enum scx_enq_flags {
 	 */
 	SCX_ENQ_LAST		= 1LLU << 41,
 
+	/*
+	 * The task is blocked on a mutex and is being kept runnable as a proxy
+	 * donor. Only passed to ops.enqueue() when %SCX_OPS_ENQ_BLOCKED is set.
+	 */
+	SCX_ENQ_BLOCKED		= 1LLU << 42,
+
 	/* high 8 bits are internal */
 	__SCX_ENQ_INTERNAL_MASK	= 0xffLLU << 56,
 
@@ -2049,6 +2069,7 @@ struct task_struct *scx_task_iter_next_locked(struct scx_task_iter *iter);
 bool scx_set_task_slice(struct task_struct *p, u64 slice);
 void scx_task_slice_ended(struct rq *rq, struct task_struct *p);
 void scx_task_unlink_from_dsq(struct task_struct *p, struct scx_dispatch_q *dsq);
+void scx_prepare_task_sched_change(struct task_struct *p);
 void scx_dispatch_dequeue(struct rq *rq, struct task_struct *p);
 void scx_do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags,
 			 int sticky_cpu);
diff --git a/kernel/sched/ext/sub.c b/kernel/sched/ext/sub.c
index 1266dcf446349..8ffa38fc6d5eb 100644
--- a/kernel/sched/ext/sub.c
+++ b/kernel/sched/ext/sub.c
@@ -1209,8 +1209,9 @@ static void scx_rehome_task(struct scx_sched *to, struct task_struct *p)
 	lockdep_assert_held(&p->pi_lock);
 	lockdep_assert_rq_held(task_rq(p));
 
+	scx_prepare_task_sched_change(p);
 	scoped_guard (sched_change, p, p->sched_class,
-		      DEQUEUE_SAVE | DEQUEUE_MOVE) {
+		      DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK) {
 		scx_disable_and_exit_task(scx_task_sched(p), p);
 		scx_set_task_state(p, SCX_TASK_INIT_BEGIN);
 		scx_set_task_state(p, SCX_TASK_INIT);
@@ -1240,8 +1241,9 @@ static void scx_punt_task(struct scx_sched *to, struct task_struct *p)
 	lockdep_assert_rq_held(task_rq(p));
 	WARN_ON_ONCE(!READ_ONCE(to->bypass_depth));
 
+	scx_prepare_task_sched_change(p);
 	scoped_guard (sched_change, p, p->sched_class,
-		      DEQUEUE_SAVE | DEQUEUE_MOVE) {
+		      DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK) {
 		scx_disable_and_exit_task(scx_task_sched(p), p);
 		scx_set_task_sched(p, to);
 	}
@@ -1895,8 +1897,9 @@ void scx_sub_enable_workfn(struct kthread_work *work)
 		if (!(p->scx.flags & SCX_TASK_SUB_INIT))
 			continue;
 
+		scx_prepare_task_sched_change(p);
 		scoped_guard (sched_change, p, p->sched_class,
-			      DEQUEUE_SAVE | DEQUEUE_MOVE) {
+			      DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK) {
 			/*
 			 * $p must be either READY or ENABLED. If ENABLED,
 			 * __scx_disabled_and_exit_task() first disables and
diff --git a/tools/sched_ext/include/scx/compat.h b/tools/sched_ext/include/scx/compat.h
index d2e4384df5af7..8313a2f6d03ce 100644
--- a/tools/sched_ext/include/scx/compat.h
+++ b/tools/sched_ext/include/scx/compat.h
@@ -117,6 +117,7 @@ static inline bool __COMPAT_struct_has_field(const char *type, const char *field
 #define SCX_OPS_ALLOW_QUEUED_WAKEUP SCX_OPS_FLAG(SCX_OPS_ALLOW_QUEUED_WAKEUP)
 #define SCX_OPS_BUILTIN_IDLE_PER_NODE SCX_OPS_FLAG(SCX_OPS_BUILTIN_IDLE_PER_NODE)
 #define SCX_OPS_ALWAYS_ENQ_IMMED SCX_OPS_FLAG(SCX_OPS_ALWAYS_ENQ_IMMED)
+#define SCX_OPS_ENQ_BLOCKED SCX_OPS_FLAG(SCX_OPS_ENQ_BLOCKED)
 
 #define SCX_PICK_IDLE_FLAG(name) __COMPAT_ENUM_OR_ZERO("scx_pick_idle_cpu_flags", #name)
 
diff --git a/tools/sched_ext/include/scx/enum_defs.autogen.h b/tools/sched_ext/include/scx/enum_defs.autogen.h
index ec5e3fbc650fa..c4e02ed921574 100644
--- a/tools/sched_ext/include/scx/enum_defs.autogen.h
+++ b/tools/sched_ext/include/scx/enum_defs.autogen.h
@@ -85,6 +85,7 @@
 #define HAVE_SCX_ENQ_RESCUE
 #define HAVE_SCX_ENQ_REENQ
 #define HAVE_SCX_ENQ_LAST
+#define HAVE_SCX_ENQ_BLOCKED
 #define HAVE___SCX_ENQ_INTERNAL_MASK
 #define HAVE_SCX_ENQ_CLEAR_OPSS
 #define HAVE_SCX_ENQ_DSQ_PRIQ
diff --git a/tools/sched_ext/include/scx/enums.autogen.bpf.h b/tools/sched_ext/include/scx/enums.autogen.bpf.h
index 11bd9b70811a8..83f2bba3ff291 100644
--- a/tools/sched_ext/include/scx/enums.autogen.bpf.h
+++ b/tools/sched_ext/include/scx/enums.autogen.bpf.h
@@ -133,6 +133,9 @@ const volatile u64 __SCX_ENQ_REENQ __weak;
 const volatile u64 __SCX_ENQ_LAST __weak;
 #define SCX_ENQ_LAST __SCX_ENQ_LAST
 
+const volatile u64 __SCX_ENQ_BLOCKED __weak;
+#define SCX_ENQ_BLOCKED __SCX_ENQ_BLOCKED
+
 const volatile u64 __SCX_ENQ_CLEAR_OPSS __weak;
 #define SCX_ENQ_CLEAR_OPSS __SCX_ENQ_CLEAR_OPSS
 
diff --git a/tools/sched_ext/include/scx/enums.autogen.h b/tools/sched_ext/include/scx/enums.autogen.h
index 0cc4f21c6b6a5..b36fb41fa783b 100644
--- a/tools/sched_ext/include/scx/enums.autogen.h
+++ b/tools/sched_ext/include/scx/enums.autogen.h
@@ -48,6 +48,7 @@
 	SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_RESCUE); \
 	SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_REENQ); \
 	SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_LAST); \
+	SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_BLOCKED); \
 	SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_CLEAR_OPSS); \
 	SCX_ENUM_SET(skel, scx_enq_flags, SCX_ENQ_DSQ_PRIQ); \
 	SCX_ENUM_SET(skel, scx_deq_flags, SCX_DEQ_SCHED_CHANGE); \
-- 
2.55.0

[PATCH 13/15] sched_ext: Add selftest for blocked donor admission

[Andrea Righi]

SCX_OPS_ENQ_BLOCKED allows BPF schedulers to receive blocked proxy
donors through ops.enqueue(). SCX_ENQ_BLOCKED identifies blocked-donor
admission requests. Add selftest coverage for this interface.

Exercise a priority inversion using a weighted-vruntime BPF scheduler.
A nice +19 owner holds a shared mutex, a nice -20 donor blocks on it,
and nice 0 CPU contenders, one per allowed CPU, keep the system busy.
Test both a same-CPU topology and a cross-CPU topology with the donor
and owner on different CPUs.

Treat blocked donors according to the normal BPF ordering policy and
assign the default slice on every enqueue, as for other tasks. Run each
CPU placement configuration with SCX_OPS_ENQ_BLOCKED first disabled and
then enabled, count blocked-donor enqueues by CPU and report average
mutex hold and wait times. Verify that full wakeups are never reported
as blocked-donor admissions by checking that SCX_ENQ_WAKEUP and
SCX_ENQ_BLOCKED are not set together.

Proxy execution coverage requires CONFIG_SCHED_PROXY_EXEC=y, which the
selftest config selects. Access to the kernel mutex is provided via a
loadable kernel module, built through TEST_GEN_MODS_DIR and managed by
the test.

Acked-by: John Stultz <jstultz@google.com>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 tools/testing/selftests/sched_ext/.gitignore  |   4 +
 tools/testing/selftests/sched_ext/Makefile    |   2 +
 tools/testing/selftests/sched_ext/config      |   2 +
 .../selftests/sched_ext/enq_blocked.bpf.c     | 116 +++
 .../testing/selftests/sched_ext/enq_blocked.c | 917 ++++++++++++++++++
 .../testing/selftests/sched_ext/enq_blocked.h |  28 +
 .../selftests/sched_ext/test_modules/Makefile |  13 +
 .../test_modules/scx_enq_blocked_test.c       | 195 ++++
 8 files changed, 1277 insertions(+)
 create mode 100644 tools/testing/selftests/sched_ext/enq_blocked.bpf.c
 create mode 100644 tools/testing/selftests/sched_ext/enq_blocked.c
 create mode 100644 tools/testing/selftests/sched_ext/enq_blocked.h
 create mode 100644 tools/testing/selftests/sched_ext/test_modules/Makefile
 create mode 100644 tools/testing/selftests/sched_ext/test_modules/scx_enq_blocked_test.c

diff --git a/tools/testing/selftests/sched_ext/.gitignore b/tools/testing/selftests/sched_ext/.gitignore
index ae5491a114c09..54a1fd2af713d 100644
--- a/tools/testing/selftests/sched_ext/.gitignore
+++ b/tools/testing/selftests/sched_ext/.gitignore
@@ -4,3 +4,7 @@
 !Makefile
 !.gitignore
 !config
+!test_modules/
+!test_modules/scx_enq_blocked_test.c
+!test_modules/Makefile
+test_modules/*.mod.c
diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile
index 3cfe90e0f34fa..51a16b3d32d9b 100644
--- a/tools/testing/selftests/sched_ext/Makefile
+++ b/tools/testing/selftests/sched_ext/Makefile
@@ -5,6 +5,7 @@ include ../../../scripts/Makefile.arch
 include ../../../scripts/Makefile.include
 
 TEST_GEN_PROGS := runner
+TEST_GEN_MODS_DIR := test_modules
 
 # override lib.mk's default rules
 OVERRIDE_TARGETS := 1
@@ -164,6 +165,7 @@ all_test_bpfprogs := $(foreach prog,$(wildcard *.bpf.c),$(INCLUDE_DIR)/$(patsubs
 auto-test-targets :=			\
 	create_dsq			\
 	dequeue				\
+	enq_blocked			\
 	enq_last_no_enq_fails		\
 	ddsp_bogus_dsq_fail		\
 	ddsp_vtimelocal_fail		\
diff --git a/tools/testing/selftests/sched_ext/config b/tools/testing/selftests/sched_ext/config
index aa901b05c8ad6..affa3cf33470a 100644
--- a/tools/testing/selftests/sched_ext/config
+++ b/tools/testing/selftests/sched_ext/config
@@ -6,3 +6,5 @@ CONFIG_BPF=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_INFO_BTF=y
+CONFIG_EXPERT=y
+CONFIG_SCHED_PROXY_EXEC=y
diff --git a/tools/testing/selftests/sched_ext/enq_blocked.bpf.c b/tools/testing/selftests/sched_ext/enq_blocked.bpf.c
new file mode 100644
index 0000000000000..212690bf4e07b
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/enq_blocked.bpf.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES
+ *
+ * Verify that SCX_OPS_ENQ_BLOCKED passes blocked proxy donors through
+ * ops.enqueue() and record whether callbacks occur on the donor or owner CPU.
+ */
+
+#include <scx/common.bpf.h>
+
+#define SHARED_DSQ 0
+
+char _license[] SEC("license") = "GPL";
+
+s32 donor_pid;
+s32 donor_cpu = -1;
+s32 owner_cpu = -1;
+u64 nr_blocked_enqueues;
+u64 nr_blocked_enqueues_donor_cpu;
+u64 nr_blocked_enqueues_owner_cpu;
+u64 nr_blocked_enqueues_other_cpu;
+u64 nr_blocked_wakeups;
+static u64 vtime_now;
+
+UEI_DEFINE(uei);
+
+s32 BPF_STRUCT_OPS(enq_blocked_select_cpu,
+		   struct task_struct *p, s32 prev_cpu, u64 wake_flags)
+{
+	return prev_cpu;
+}
+
+void BPF_STRUCT_OPS(enq_blocked_enqueue, struct task_struct *p, u64 enq_flags)
+{
+	u64 vtime = p->scx.dsq_vtime;
+
+	if (enq_flags & SCX_ENQ_BLOCKED) {
+		int cpu = scx_bpf_task_cpu(p);
+
+		if (enq_flags & SCX_ENQ_WAKEUP)
+			__sync_fetch_and_add(&nr_blocked_wakeups, 1);
+
+		if (p->pid == donor_pid) {
+			__sync_fetch_and_add(&nr_blocked_enqueues, 1);
+			if (cpu == donor_cpu)
+				__sync_fetch_and_add(&nr_blocked_enqueues_donor_cpu, 1);
+			else if (cpu == owner_cpu)
+				__sync_fetch_and_add(&nr_blocked_enqueues_owner_cpu, 1);
+			else
+				__sync_fetch_and_add(&nr_blocked_enqueues_other_cpu, 1);
+		}
+	}
+
+	/* Limit the amount of budget an idling task can accumulate. */
+	if (time_before(vtime, vtime_now - SCX_SLICE_DFL))
+		vtime = vtime_now - SCX_SLICE_DFL;
+
+	scx_bpf_dsq_insert_vtime(p, SHARED_DSQ, SCX_SLICE_DFL, vtime,
+				 enq_flags);
+	scx_bpf_kick_cpu(scx_bpf_task_cpu(p), SCX_KICK_IDLE);
+}
+
+void BPF_STRUCT_OPS(enq_blocked_dispatch, s32 cpu, struct task_struct *prev)
+{
+	scx_bpf_dsq_move_to_local(SHARED_DSQ, 0);
+}
+
+void BPF_STRUCT_OPS(enq_blocked_running, struct task_struct *p)
+{
+	if (time_before(vtime_now, p->scx.dsq_vtime))
+		vtime_now = p->scx.dsq_vtime;
+}
+
+void BPF_STRUCT_OPS(enq_blocked_stopping, struct task_struct *p, bool runnable)
+{
+	u64 delta = scale_by_task_weight_inverse(p,
+					 SCX_SLICE_DFL - p->scx.slice);
+
+	scx_bpf_task_set_dsq_vtime(p, p->scx.dsq_vtime + delta);
+}
+
+void BPF_STRUCT_OPS(enq_blocked_enable, struct task_struct *p)
+{
+	scx_bpf_task_set_dsq_vtime(p, vtime_now);
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(enq_blocked_init)
+{
+	int ret;
+
+	ret = scx_bpf_create_dsq(SHARED_DSQ, -1);
+	if (ret) {
+		scx_bpf_error("failed to create DSQ %d (%d)", SHARED_DSQ, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+void BPF_STRUCT_OPS(enq_blocked_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops enq_blocked_ops = {
+	.select_cpu		= (void *)enq_blocked_select_cpu,
+	.enqueue		= (void *)enq_blocked_enqueue,
+	.dispatch		= (void *)enq_blocked_dispatch,
+	.running		= (void *)enq_blocked_running,
+	.stopping		= (void *)enq_blocked_stopping,
+	.enable			= (void *)enq_blocked_enable,
+	.init			= (void *)enq_blocked_init,
+	.exit			= (void *)enq_blocked_exit,
+	.name			= "enq_blocked",
+};
diff --git a/tools/testing/selftests/sched_ext/enq_blocked.c b/tools/testing/selftests/sched_ext/enq_blocked.c
new file mode 100644
index 0000000000000..26204548bbf08
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/enq_blocked.c
@@ -0,0 +1,917 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES
+ *
+ * Exercise a priority inversion with the owner and donor first pinned to the
+ * same CPU, then with each on a different CPU. A high-priority donor blocks on
+ * a mutex held by a low-priority owner while one medium-priority contender per
+ * available CPU keeps the system busy. A weighted-vruntime BPF scheduler runs
+ * both CPU placement configurations with SCX_OPS_ENQ_BLOCKED first disabled
+ * and then enabled. The test validates blocked-donor admission and reports the
+ * average mutex hold and wait times, plus their enabled-minus-disabled deltas,
+ * for each configuration. The timing data is informational.
+ *
+ * CONFIG_SCHED_PROXY_EXEC=y is required to exercise the proxy-execution paths.
+ */
+#define _GNU_SOURCE
+
+#include <bpf/bpf.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <pthread.h>
+#include <sched.h>
+#include <scx/common.h>
+#include <stdatomic.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/resource.h>
+#include <sys/syscall.h>
+#include <time.h>
+#include <unistd.h>
+
+#include "enq_blocked.bpf.skel.h"
+#include "enq_blocked.h"
+#include "scx_test.h"
+
+#define MODULE_NAME	"scx_enq_blocked_test"
+#define MODULE_FILE	"test_modules/" MODULE_NAME ".ko"
+#define DEVICE_PATH	"/dev/scx_enq_blocked"
+#define WAIT_STEP_US	1000
+#define WAIT_TIMEOUT_MS	2000
+#define NR_WARMUP_TRIALS	1
+#define NR_MEASURED_TRIALS	10
+#define NR_TRIALS	(NR_WARMUP_TRIALS + NR_MEASURED_TRIALS)
+#define JOIN_TIMEOUT_MS	((NR_TRIALS + 1) * WAIT_TIMEOUT_MS)
+#define OWNER_NICE	19
+#define DONOR_NICE	-20
+#define CONTENDER_NICE	0
+
+struct thread_ctx {
+	atomic_bool start_donor;
+	atomic_bool abort;
+	atomic_bool stop_contender;
+	atomic_bool measurement_ready;
+	atomic_int donor_pid;
+	atomic_int donor_completed;
+	int fd;
+	int donor_cpu;
+	int owner_cpu;
+};
+
+struct contender_ctx {
+	struct thread_ctx *thread_ctx;
+	atomic_int status;
+	int cpu;
+};
+
+struct run_result {
+	struct enq_blocked_stats stats;
+	u64 nr_blocked_enqueues;
+	u64 nr_blocked_enqueues_donor_cpu;
+	u64 nr_blocked_enqueues_owner_cpu;
+	u64 nr_blocked_enqueues_other_cpu;
+	u64 nr_blocked_wakeups;
+};
+
+static bool parse_bool(const char *value, bool *result)
+{
+	if (!strcasecmp(value, "1") || !strcasecmp(value, "y") ||
+	    !strcasecmp(value, "yes") || !strcasecmp(value, "on") ||
+	    !strcasecmp(value, "true")) {
+		*result = true;
+		return true;
+	}
+
+	if (!strcasecmp(value, "0") || !strcasecmp(value, "n") ||
+	    !strcasecmp(value, "no") || !strcasecmp(value, "off") ||
+	    !strcasecmp(value, "false")) {
+		*result = false;
+		return true;
+	}
+
+	return false;
+}
+
+static bool cmdline_bool(const char *name, bool default_value)
+{
+	char cmdline[4096], *newline, *saveptr = NULL, *token;
+	size_t name_len = strlen(name);
+	bool value = default_value;
+	FILE *file;
+
+	file = fopen("/proc/cmdline", "r");
+	if (!file)
+		return default_value;
+
+	if (!fgets(cmdline, sizeof(cmdline), file)) {
+		fclose(file);
+		return default_value;
+	}
+	fclose(file);
+	newline = strchr(cmdline, '\n');
+	if (newline)
+		*newline = '\0';
+
+	for (token = strtok_r(cmdline, " ", &saveptr); token;
+	     token = strtok_r(NULL, " ", &saveptr)) {
+		bool parsed;
+
+		if (strncmp(token, name, name_len) || token[name_len] != '=')
+			continue;
+		if (parse_bool(token + name_len + 1, &parsed))
+			value = parsed;
+	}
+
+	return value;
+}
+
+static int module_path(char *path, size_t size)
+{
+	ssize_t len;
+	char *slash;
+
+	len = readlink("/proc/self/exe", path, size - 1);
+	if (len < 0)
+		return -errno;
+	path[len] = '\0';
+
+	slash = strrchr(path, '/');
+	if (!slash)
+		return -EINVAL;
+	*slash = '\0';
+
+	if (snprintf(slash, size - (slash - path), "/%s", MODULE_FILE) >=
+	    size - (slash - path))
+		return -ENAMETOOLONG;
+
+	return 0;
+}
+
+static int load_test_module(bool *loaded_here)
+{
+	char path[PATH_MAX];
+	int fd, err;
+
+	err = module_path(path, sizeof(path));
+	if (err)
+		return err;
+
+	fd = open(path, O_RDONLY | O_CLOEXEC);
+	if (fd < 0)
+		return -errno;
+
+	if (syscall(SYS_finit_module, fd, "", 0)) {
+		err = errno;
+		close(fd);
+		if (err == EEXIST)
+			return 0;
+		return -err;
+	}
+
+	close(fd);
+	*loaded_here = true;
+	return 0;
+}
+
+static void unload_test_module(bool loaded_here)
+{
+	if (loaded_here && syscall(SYS_delete_module, MODULE_NAME, O_NONBLOCK))
+		SCX_ERR("Failed to unload %s (%d)", MODULE_NAME, errno);
+}
+
+static int pin_to_cpu(int cpu)
+{
+	cpu_set_t mask;
+
+	CPU_ZERO(&mask);
+	CPU_SET(cpu, &mask);
+	return sched_setaffinity(0, sizeof(mask), &mask) ? errno : 0;
+}
+
+static int select_test_cpus(bool cross_cpu, cpu_set_t *mask, int *donor_cpu,
+			    int *owner_cpu)
+{
+	int cpu, first = -1;
+
+	if (sched_getaffinity(0, sizeof(*mask), mask))
+		return -errno;
+
+	for (cpu = 0; cpu < CPU_SETSIZE; cpu++) {
+		if (!CPU_ISSET(cpu, mask))
+			continue;
+		if (first < 0) {
+			first = cpu;
+			if (!cross_cpu)
+				break;
+		} else {
+			*donor_cpu = first;
+			*owner_cpu = cpu;
+			return 0;
+		}
+	}
+
+	if (first < 0)
+		return -ENODEV;
+	if (cross_cpu)
+		return -EAGAIN;
+
+	*donor_cpu = first;
+	*owner_cpu = first;
+	return 0;
+}
+
+static int set_nice(int nice)
+{
+	return setpriority(PRIO_PROCESS, 0, nice) ? errno : 0;
+}
+
+static bool wait_for_pid(atomic_int *pid)
+{
+	int waited_ms;
+
+	for (waited_ms = 0; waited_ms < WAIT_TIMEOUT_MS; waited_ms++) {
+		if (atomic_load_explicit(pid, memory_order_acquire) > 0)
+			return true;
+		usleep(WAIT_STEP_US);
+	}
+
+	return false;
+}
+
+static int wait_for_contenders(struct contender_ctx *contenders,
+			       size_t nr_contenders)
+{
+	size_t i, nr_ready;
+	int status, waited_ms;
+
+	for (waited_ms = 0; waited_ms < WAIT_TIMEOUT_MS; waited_ms++) {
+		nr_ready = 0;
+		for (i = 0; i < nr_contenders; i++) {
+			status = atomic_load_explicit(&contenders[i].status,
+						      memory_order_acquire);
+			if (status < 0)
+				return status;
+			if (status > 0)
+				nr_ready++;
+		}
+		if (nr_ready == nr_contenders)
+			return 1;
+		usleep(WAIT_STEP_US);
+	}
+
+	return -ETIMEDOUT;
+}
+
+static int wait_for_donor_state(struct thread_ctx *ctx, int expected)
+{
+	int state, waited_ms;
+
+	for (waited_ms = 0; waited_ms < WAIT_TIMEOUT_MS; waited_ms++) {
+		state = ioctl(ctx->fd, ENQ_BLOCKED_IOCTL_DONOR_STATE);
+		if (state == expected)
+			return state;
+		if (state < 0 && errno != ENOENT)
+			return -errno;
+		usleep(WAIT_STEP_US);
+	}
+
+	return -ETIMEDOUT;
+}
+
+static bool wait_for_donor(struct thread_ctx *ctx, int trial)
+{
+	int waited_ms;
+
+	for (waited_ms = 0; waited_ms < WAIT_TIMEOUT_MS; waited_ms++) {
+		if (atomic_load_explicit(&ctx->donor_completed,
+					 memory_order_acquire) >= trial)
+			return true;
+		if (atomic_load_explicit(&ctx->abort, memory_order_relaxed))
+			return false;
+		usleep(WAIT_STEP_US);
+	}
+
+	return false;
+}
+
+static bool wait_for_measurement(struct thread_ctx *ctx)
+{
+	while (!atomic_load_explicit(&ctx->measurement_ready,
+				     memory_order_acquire) &&
+	       !atomic_load_explicit(&ctx->abort, memory_order_relaxed))
+		sched_yield();
+
+	return !atomic_load_explicit(&ctx->abort, memory_order_relaxed);
+}
+
+static void *contender_fn(void *arg)
+{
+	struct contender_ctx *contender = arg;
+	struct thread_ctx *ctx = contender->thread_ctx;
+	int err;
+
+	err = pin_to_cpu(contender->cpu);
+	if (!err)
+		err = set_nice(CONTENDER_NICE);
+	atomic_store_explicit(&contender->status, err ? -err : 1,
+			      memory_order_release);
+	if (err)
+		return (void *)(uintptr_t)err;
+
+	while (!atomic_load_explicit(&ctx->stop_contender,
+				     memory_order_relaxed))
+		;
+
+	return NULL;
+}
+
+static void *owner_fn(void *arg)
+{
+	struct thread_ctx *ctx = arg;
+	int err, i;
+
+	err = pin_to_cpu(ctx->owner_cpu);
+	if (err)
+		return (void *)(uintptr_t)err;
+	err = set_nice(OWNER_NICE);
+	if (err)
+		return (void *)(uintptr_t)err;
+
+	for (i = 0; i < NR_TRIALS; i++) {
+		if (ioctl(ctx->fd, ENQ_BLOCKED_IOCTL_OWNER))
+			return (void *)(uintptr_t)errno;
+		if (!wait_for_donor(ctx, i + 1))
+			return (void *)(uintptr_t)ETIMEDOUT;
+
+		if (i + 1 == NR_WARMUP_TRIALS && !wait_for_measurement(ctx))
+			return NULL;
+	}
+
+	return NULL;
+}
+
+static int run_donor_trial(struct thread_ctx *ctx)
+{
+	int waited_ms;
+
+	for (waited_ms = 0; waited_ms < WAIT_TIMEOUT_MS; waited_ms++) {
+		if (!ioctl(ctx->fd, ENQ_BLOCKED_IOCTL_DONOR))
+			return 0;
+		if (errno != EAGAIN)
+			return -errno;
+		usleep(WAIT_STEP_US);
+	}
+
+	return -ETIMEDOUT;
+}
+
+static void *donor_fn(void *arg)
+{
+	struct thread_ctx *ctx = arg;
+	int err, i;
+
+	err = pin_to_cpu(ctx->donor_cpu);
+	if (err)
+		return (void *)(uintptr_t)err;
+	err = set_nice(DONOR_NICE);
+	if (err)
+		return (void *)(uintptr_t)err;
+
+	atomic_store_explicit(&ctx->donor_pid, syscall(SYS_gettid),
+			      memory_order_release);
+	while (!atomic_load_explicit(&ctx->start_donor, memory_order_acquire) &&
+	       !atomic_load_explicit(&ctx->abort, memory_order_relaxed))
+		sched_yield();
+
+	if (atomic_load_explicit(&ctx->abort, memory_order_relaxed))
+		return NULL;
+
+	for (i = 0; i < NR_TRIALS; i++) {
+		err = run_donor_trial(ctx);
+		if (err)
+			return (void *)(uintptr_t)-err;
+		atomic_store_explicit(&ctx->donor_completed, i + 1,
+				      memory_order_release);
+	}
+
+	return NULL;
+}
+
+static void print_avg_time(const char *name, u64 total_ns, u64 samples)
+{
+	u64 avg_ns = samples ? total_ns / samples : 0;
+
+	printf("  %s_avg_ns=%llu (%llu.%03llu ms, samples=%llu)\n", name,
+	       (unsigned long long)avg_ns,
+	       (unsigned long long)(avg_ns / 1000000),
+	       (unsigned long long)((avg_ns / 1000) % 1000),
+	       (unsigned long long)samples);
+}
+
+static void print_avg_delta(const char *name, u64 disabled_total,
+			    u64 disabled_samples, u64 enabled_total,
+			    u64 enabled_samples)
+{
+	u64 disabled_avg, enabled_avg;
+	s64 delta_ns;
+	double delta_pct;
+
+	if (!disabled_samples || !enabled_samples)
+		return;
+
+	disabled_avg = disabled_total / disabled_samples;
+	enabled_avg = enabled_total / enabled_samples;
+	delta_ns = (s64)enabled_avg - (s64)disabled_avg;
+	delta_pct = disabled_avg ? 100.0 * delta_ns / disabled_avg : 0.0;
+
+	printf("  %s_delta_ns=%+lld (%+.2f%%)\n", name,
+	       (long long)delta_ns, delta_pct);
+}
+
+static int join_thread(pthread_t thread, const struct timespec *deadline,
+		       int *thread_err)
+{
+	void *result;
+	int err;
+
+	err = pthread_timedjoin_np(thread, &result, deadline);
+	if (err)
+		return err;
+
+	*thread_err = (int)(uintptr_t)result;
+	return 0;
+}
+
+static void set_join_deadline(struct timespec *deadline)
+{
+	clock_gettime(CLOCK_REALTIME, deadline);
+	deadline->tv_sec += JOIN_TIMEOUT_MS / 1000;
+	deadline->tv_nsec += (JOIN_TIMEOUT_MS % 1000) * 1000000;
+	if (deadline->tv_nsec >= 1000000000) {
+		deadline->tv_sec++;
+		deadline->tv_nsec -= 1000000000;
+	}
+}
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct enq_blocked *skel;
+	u64 flag;
+
+	skel = enq_blocked__open();
+	SCX_FAIL_IF(!skel, "Failed to open skel");
+	SCX_ENUM_INIT(skel);
+
+	flag = SCX_OPS_ENQ_BLOCKED;
+	if (!flag) {
+		enq_blocked__destroy(skel);
+		fprintf(stderr, "SKIP: SCX_OPS_ENQ_BLOCKED is unavailable\n");
+		return SCX_TEST_SKIP;
+	}
+
+	enq_blocked__destroy(skel);
+	*ctx = NULL;
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run_one(bool enq_blocked, bool cross_cpu,
+				    struct run_result *result)
+{
+	struct enq_blocked *skel;
+	struct thread_ctx thread_ctx = {};
+	struct contender_ctx *contender_ctxs = NULL;
+	struct bpf_link *link = NULL;
+	pthread_t owner, donor, *contenders = NULL;
+	struct timespec join_deadline;
+	cpu_set_t allowed_cpus;
+	bool module_loaded = false;
+	bool owner_started = false, donor_started = false;
+	bool join_timed_out = false;
+	bool proxy_enabled;
+	enum scx_test_status status = SCX_TEST_PASS;
+	int cpu, donor_pid, donor_state, err, thread_err;
+	size_t i, nr_contenders, nr_contenders_started = 0;
+	size_t nr_contenders_joined = 0;
+	u64 nr_blocked, nr_blocked_donor_cpu, nr_blocked_owner_cpu;
+	u64 nr_blocked_other_cpu, nr_blocked_wakeups;
+	struct enq_blocked_stats stats;
+
+	err = select_test_cpus(cross_cpu, &allowed_cpus, &thread_ctx.donor_cpu,
+			       &thread_ctx.owner_cpu);
+	if (err == -EAGAIN) {
+		fprintf(stderr, "SKIP: cross-CPU case requires two allowed CPUs\n");
+		return SCX_TEST_SKIP;
+	}
+	if (err) {
+		SCX_ERR("Failed to select test CPUs (%d)", -err);
+		return SCX_TEST_FAIL;
+	}
+	nr_contenders = CPU_COUNT(&allowed_cpus);
+	contenders = calloc(nr_contenders, sizeof(*contenders));
+	contender_ctxs = calloc(nr_contenders, sizeof(*contender_ctxs));
+	if (!contenders || !contender_ctxs) {
+		SCX_ERR("Failed to allocate %zu contender threads", nr_contenders);
+		status = SCX_TEST_FAIL;
+		goto out_contenders;
+	}
+
+	skel = enq_blocked__open();
+	if (!skel) {
+		SCX_ERR("Failed to open skel");
+		status = SCX_TEST_FAIL;
+		goto out_contenders;
+	}
+	SCX_ENUM_INIT(skel);
+	skel->struct_ops.enq_blocked_ops->flags =
+		SCX_OPS_ENQ_LAST |
+		(enq_blocked ? SCX_OPS_ENQ_BLOCKED : 0);
+	if (enq_blocked__load(skel)) {
+		SCX_ERR("Failed to load skel");
+		status = SCX_TEST_FAIL;
+		goto out_skel;
+	}
+
+	err = load_test_module(&module_loaded);
+	if (err == -EPERM || err == -ENOENT) {
+		fprintf(stderr, "SKIP: cannot load mutex fixture (%d)\n", -err);
+		status = SCX_TEST_SKIP;
+		goto out_skel;
+	}
+	if (err) {
+		SCX_ERR("Failed to load mutex fixture (%d)", -err);
+		status = SCX_TEST_FAIL;
+		goto out_skel;
+	}
+
+	thread_ctx.fd = open(DEVICE_PATH, O_RDONLY | O_CLOEXEC);
+	if (thread_ctx.fd < 0) {
+		SCX_ERR("Failed to open %s (%d)", DEVICE_PATH, errno);
+		status = SCX_TEST_FAIL;
+		goto out_module;
+	}
+	err = ioctl(thread_ctx.fd, ENQ_BLOCKED_IOCTL_PROXY_SUPPORTED);
+	if (err < 0) {
+		SCX_ERR("Failed to query proxy-exec support (%d)", errno);
+		status = SCX_TEST_FAIL;
+		goto out_fd;
+	}
+	proxy_enabled = err && cmdline_bool("sched_proxy_exec", true);
+	if (!proxy_enabled) {
+		fprintf(stderr, "SKIP: proxy execution is not enabled\n");
+		status = SCX_TEST_SKIP;
+		goto out_fd;
+	}
+	if (ioctl(thread_ctx.fd, ENQ_BLOCKED_IOCTL_RESET_STATS)) {
+		SCX_ERR("Failed to reset mutex statistics (%d)", errno);
+		status = SCX_TEST_FAIL;
+		goto out_fd;
+	}
+
+	if (ioctl(thread_ctx.fd, ENQ_BLOCKED_IOCTL_PREP_ATTACH)) {
+		SCX_ERR("Failed to prepare scheduler attachment (%d)", errno);
+		status = SCX_TEST_FAIL;
+		goto out_fd;
+	}
+
+	err = pthread_create(&owner, NULL, owner_fn, &thread_ctx);
+	if (err) {
+		SCX_ERR("Failed to create owner thread (%d)", err);
+		status = SCX_TEST_FAIL;
+		goto out;
+	}
+	owner_started = true;
+
+	err = pthread_create(&donor, NULL, donor_fn, &thread_ctx);
+	if (err) {
+		SCX_ERR("Failed to create donor thread (%d)", err);
+		status = SCX_TEST_FAIL;
+		goto out;
+	}
+	donor_started = true;
+
+	if (!wait_for_pid(&thread_ctx.donor_pid)) {
+		SCX_ERR("Timed out waiting for donor thread");
+		status = SCX_TEST_FAIL;
+		goto out;
+	}
+
+	donor_pid = atomic_load_explicit(&thread_ctx.donor_pid,
+					 memory_order_acquire);
+	skel->bss->donor_pid = donor_pid;
+	skel->data->donor_cpu = thread_ctx.donor_cpu;
+	skel->data->owner_cpu = thread_ctx.owner_cpu;
+	atomic_store_explicit(&thread_ctx.start_donor, true,
+			      memory_order_release);
+
+	donor_state = ENQ_BLOCKED_DONOR_SLEEPING;
+	if (proxy_enabled)
+		donor_state |= ENQ_BLOCKED_DONOR_ON_RQ;
+	err = wait_for_donor_state(&thread_ctx, donor_state);
+	if (err < 0) {
+		SCX_ERR("Donor did not block before scheduler attachment (%d)", -err);
+		status = SCX_TEST_FAIL;
+		goto out;
+	}
+
+	link = bpf_map__attach_struct_ops(skel->maps.enq_blocked_ops);
+	if (!link) {
+		SCX_ERR("Failed to attach scheduler");
+		status = SCX_TEST_FAIL;
+		goto out;
+	}
+
+	/* Scheduler ownership changes start from a fully blocked donor. */
+	donor_state = ENQ_BLOCKED_DONOR_SLEEPING;
+	err = wait_for_donor_state(&thread_ctx, donor_state);
+	if (err < 0) {
+		SCX_ERR("Unexpected donor state after scheduler attachment (%d)",
+			-err);
+		status = SCX_TEST_FAIL;
+		goto out;
+	}
+
+	if (ioctl(thread_ctx.fd, ENQ_BLOCKED_IOCTL_ATTACH_DONE)) {
+		SCX_ERR("Failed to complete scheduler attachment (%d)", errno);
+		status = SCX_TEST_FAIL;
+		goto out;
+	}
+
+	i = 0;
+	for (cpu = 0; cpu < CPU_SETSIZE; cpu++) {
+		if (!CPU_ISSET(cpu, &allowed_cpus))
+			continue;
+
+		contender_ctxs[i].thread_ctx = &thread_ctx;
+		contender_ctxs[i].cpu = cpu;
+		atomic_init(&contender_ctxs[i].status, 0);
+		err = pthread_create(&contenders[i], NULL, contender_fn,
+				     &contender_ctxs[i]);
+		if (err) {
+			SCX_ERR("Failed to create contender for CPU %d (%d)",
+				cpu, err);
+			status = SCX_TEST_FAIL;
+			goto out;
+		}
+		nr_contenders_started++;
+		i++;
+	}
+
+	err = wait_for_contenders(contender_ctxs, nr_contenders);
+	if (err != 1) {
+		SCX_ERR("Contender threads failed (%d)", -err);
+		status = SCX_TEST_FAIL;
+		goto out;
+	}
+
+	/*
+	 * The first trial spans scheduler attachment and validates the state
+	 * transition, but including it would skew scheduling latency. Exclude it
+	 * from both the mutex and BPF enqueue measurements.
+	 */
+	if (!wait_for_donor(&thread_ctx, NR_WARMUP_TRIALS)) {
+		SCX_ERR("Timed out waiting for warm-up trial");
+		status = SCX_TEST_FAIL;
+		goto out;
+	}
+	if (ioctl(thread_ctx.fd, ENQ_BLOCKED_IOCTL_RESET_STATS)) {
+		SCX_ERR("Failed to reset mutex statistics after warm-up (%d)",
+			errno);
+		status = SCX_TEST_FAIL;
+		goto out;
+	}
+	skel->bss->nr_blocked_enqueues = 0;
+	skel->bss->nr_blocked_enqueues_donor_cpu = 0;
+	skel->bss->nr_blocked_enqueues_owner_cpu = 0;
+	skel->bss->nr_blocked_enqueues_other_cpu = 0;
+	skel->bss->nr_blocked_wakeups = 0;
+	atomic_store_explicit(&thread_ctx.measurement_ready, true,
+			      memory_order_release);
+
+out:
+	ioctl(thread_ctx.fd, ENQ_BLOCKED_IOCTL_ATTACH_DONE);
+	if (status != SCX_TEST_PASS) {
+		atomic_store_explicit(&thread_ctx.abort, true, memory_order_release);
+		atomic_store_explicit(&thread_ctx.start_donor, true,
+				      memory_order_release);
+		atomic_store_explicit(&thread_ctx.measurement_ready, true,
+				      memory_order_release);
+	}
+
+	set_join_deadline(&join_deadline);
+	if (donor_started) {
+		err = join_thread(donor, &join_deadline, &thread_err);
+		if (err == ETIMEDOUT) {
+			SCX_ERR("Timed out waiting for donor thread");
+			join_timed_out = true;
+			status = SCX_TEST_FAIL;
+		} else if (err) {
+			SCX_ERR("Failed to join donor thread (%d)", err);
+			status = SCX_TEST_FAIL;
+		} else {
+			donor_started = false;
+			if (thread_err) {
+				SCX_ERR("Donor thread failed (%d)", thread_err);
+				status = SCX_TEST_FAIL;
+			}
+		}
+	}
+	if (!join_timed_out && owner_started) {
+		err = join_thread(owner, &join_deadline, &thread_err);
+		if (err == ETIMEDOUT) {
+			SCX_ERR("Timed out waiting for owner thread");
+			join_timed_out = true;
+			status = SCX_TEST_FAIL;
+		} else if (err) {
+			SCX_ERR("Failed to join owner thread (%d)", err);
+			status = SCX_TEST_FAIL;
+		} else {
+			owner_started = false;
+			if (thread_err) {
+				SCX_ERR("Owner thread failed (%d)", thread_err);
+				status = SCX_TEST_FAIL;
+			}
+		}
+	}
+	atomic_store_explicit(&thread_ctx.stop_contender, true,
+			      memory_order_release);
+	for (i = 0; !join_timed_out && i < nr_contenders_started; i++) {
+		err = join_thread(contenders[i], &join_deadline, &thread_err);
+		if (err == ETIMEDOUT) {
+			SCX_ERR("Timed out waiting for contender on CPU %d",
+				contender_ctxs[i].cpu);
+			join_timed_out = true;
+			status = SCX_TEST_FAIL;
+		} else if (err) {
+			SCX_ERR("Failed to join contender on CPU %d (%d)",
+				contender_ctxs[i].cpu, err);
+			status = SCX_TEST_FAIL;
+		} else {
+			nr_contenders_joined++;
+			if (thread_err) {
+				SCX_ERR("Contender on CPU %d failed (%d)",
+					contender_ctxs[i].cpu, thread_err);
+				status = SCX_TEST_FAIL;
+			}
+		}
+	}
+
+	/* Restore the fair scheduler before waiting for any stranded thread. */
+	if (join_timed_out) {
+		atomic_store_explicit(&thread_ctx.abort, true,
+				      memory_order_release);
+		if (link) {
+			bpf_link__destroy(link);
+			link = NULL;
+		}
+		if (donor_started)
+			pthread_join(donor, NULL);
+		if (owner_started)
+			pthread_join(owner, NULL);
+		for (i = nr_contenders_joined;
+		     i < nr_contenders_started; i++)
+			pthread_join(contenders[i], NULL);
+	}
+
+	if (ioctl(thread_ctx.fd, ENQ_BLOCKED_IOCTL_GET_STATS, &stats)) {
+		SCX_ERR("Failed to read mutex statistics (%d)", errno);
+		status = SCX_TEST_FAIL;
+	} else {
+		result->stats = stats;
+		printf("\n[topology=%s SCX_OPS_ENQ_BLOCKED=%s]\n",
+		       cross_cpu ? "cross-cpu" : "same-cpu",
+		       enq_blocked ? "enabled" : "disabled");
+		printf("  proxy_exec=%s\n",
+		       proxy_enabled ? "enabled" : "disabled");
+		printf("  donor_cpu=%d\n", thread_ctx.donor_cpu);
+		printf("  owner_cpu=%d\n", thread_ctx.owner_cpu);
+		printf("  nr_contenders=%zu\n", nr_contenders);
+		printf("  measured_trials=%d\n", NR_MEASURED_TRIALS);
+		printf("  owner_nice=%d\n", OWNER_NICE);
+		printf("  donor_nice=%d\n", DONOR_NICE);
+		printf("  contender_nice=%d\n", CONTENDER_NICE);
+		print_avg_time("mutex_hold", stats.hold_time_ns, stats.nr_holds);
+		print_avg_time("mutex_wait", stats.wait_time_ns, stats.nr_waits);
+		if (stats.nr_holds != NR_MEASURED_TRIALS ||
+		    stats.nr_waits != NR_MEASURED_TRIALS) {
+			SCX_ERR("Expected %d measured trials, got %llu holds and %llu waits",
+				NR_MEASURED_TRIALS,
+				(unsigned long long)stats.nr_holds,
+				(unsigned long long)stats.nr_waits);
+			status = SCX_TEST_FAIL;
+		}
+	}
+
+	nr_blocked = skel->bss->nr_blocked_enqueues;
+	nr_blocked_donor_cpu = skel->bss->nr_blocked_enqueues_donor_cpu;
+	nr_blocked_owner_cpu = skel->bss->nr_blocked_enqueues_owner_cpu;
+	nr_blocked_other_cpu = skel->bss->nr_blocked_enqueues_other_cpu;
+	nr_blocked_wakeups = skel->bss->nr_blocked_wakeups;
+	result->nr_blocked_enqueues = nr_blocked;
+	result->nr_blocked_enqueues_donor_cpu = nr_blocked_donor_cpu;
+	result->nr_blocked_enqueues_owner_cpu = nr_blocked_owner_cpu;
+	result->nr_blocked_enqueues_other_cpu = nr_blocked_other_cpu;
+	result->nr_blocked_wakeups = nr_blocked_wakeups;
+	printf("  nr_blocked_enqueues=%llu\n",
+	       (unsigned long long)nr_blocked);
+	printf("  nr_blocked_enqueues_donor_cpu=%llu\n",
+	       (unsigned long long)nr_blocked_donor_cpu);
+	printf("  nr_blocked_enqueues_owner_cpu=%llu\n",
+	       (unsigned long long)nr_blocked_owner_cpu);
+	printf("  nr_blocked_enqueues_other_cpu=%llu\n",
+	       (unsigned long long)nr_blocked_other_cpu);
+	printf("  nr_blocked_wakeups=%llu\n",
+	       (unsigned long long)nr_blocked_wakeups);
+	if (status == SCX_TEST_PASS) {
+		if (enq_blocked && proxy_enabled && !nr_blocked) {
+			SCX_ERR("ops.enqueue() did not receive the blocked donor");
+			status = SCX_TEST_FAIL;
+		} else if ((!enq_blocked || !proxy_enabled) && nr_blocked) {
+			SCX_ERR("ops.enqueue() unexpectedly received %llu blocked donors",
+				(unsigned long long)nr_blocked);
+			status = SCX_TEST_FAIL;
+		} else if (nr_blocked_wakeups) {
+			SCX_ERR("Ordinary wakeups received %llu blocked enqueue flags",
+				(unsigned long long)nr_blocked_wakeups);
+			status = SCX_TEST_FAIL;
+		} else if (nr_blocked_other_cpu) {
+			SCX_ERR("Blocked donor had %llu enqueues on unexpected CPUs",
+				(unsigned long long)nr_blocked_other_cpu);
+			status = SCX_TEST_FAIL;
+		}
+	}
+
+	if (skel->data->uei.kind != EXIT_KIND(SCX_EXIT_NONE)) {
+		SCX_ERR("Scheduler exited unexpectedly (kind=%llu code=%lld)",
+			(unsigned long long)skel->data->uei.kind,
+			(long long)skel->data->uei.exit_code);
+		status = SCX_TEST_FAIL;
+	}
+
+	if (link)
+		bpf_link__destroy(link);
+out_fd:
+	close(thread_ctx.fd);
+out_module:
+	unload_test_module(module_loaded);
+out_skel:
+	enq_blocked__destroy(skel);
+out_contenders:
+	free(contender_ctxs);
+	free(contenders);
+	return status;
+}
+
+static enum scx_test_status run_topology(bool cross_cpu)
+{
+	struct run_result disabled = {}, enabled = {};
+	enum scx_test_status status;
+
+	status = run_one(false, cross_cpu, &disabled);
+	if (status != SCX_TEST_PASS)
+		return status;
+
+	status = run_one(true, cross_cpu, &enabled);
+	if (status != SCX_TEST_PASS)
+		return status;
+
+	printf("\n[topology=%s delta: enabled - disabled]\n",
+	       cross_cpu ? "cross-cpu" : "same-cpu");
+	print_avg_delta("mutex_hold", disabled.stats.hold_time_ns,
+			disabled.stats.nr_holds, enabled.stats.hold_time_ns,
+			enabled.stats.nr_holds);
+	print_avg_delta("mutex_wait", disabled.stats.wait_time_ns,
+			disabled.stats.nr_waits, enabled.stats.wait_time_ns,
+			enabled.stats.nr_waits);
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	enum scx_test_status status;
+
+	(void)ctx;
+
+	status = run_topology(false);
+	if (status != SCX_TEST_PASS)
+		return status;
+
+	status = run_topology(true);
+	if (status == SCX_TEST_SKIP)
+		return SCX_TEST_PASS;
+
+	return status;
+}
+
+struct scx_test enq_blocked = {
+	.name = "enq_blocked",
+	.description = "Verify proxy donor admission under CPU-wide contention",
+	.setup = setup,
+	.run = run,
+};
+
+REGISTER_SCX_TEST(&enq_blocked)
diff --git a/tools/testing/selftests/sched_ext/enq_blocked.h b/tools/testing/selftests/sched_ext/enq_blocked.h
new file mode 100644
index 0000000000000..ef1eb97feebe6
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/enq_blocked.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES */
+#ifndef __ENQ_BLOCKED_H
+#define __ENQ_BLOCKED_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+struct enq_blocked_stats {
+	__u64 hold_time_ns;
+	__u64 wait_time_ns;
+	__u64 nr_holds;
+	__u64 nr_waits;
+};
+
+#define ENQ_BLOCKED_IOCTL_OWNER	_IO('s', 1)
+#define ENQ_BLOCKED_IOCTL_DONOR	_IO('s', 2)
+#define ENQ_BLOCKED_IOCTL_RESET_STATS	_IO('s', 3)
+#define ENQ_BLOCKED_IOCTL_GET_STATS	_IOR('s', 4, struct enq_blocked_stats)
+#define ENQ_BLOCKED_IOCTL_PREP_ATTACH	_IO('s', 5)
+#define ENQ_BLOCKED_IOCTL_ATTACH_DONE	_IO('s', 6)
+#define ENQ_BLOCKED_IOCTL_DONOR_STATE	_IO('s', 7)
+#define ENQ_BLOCKED_IOCTL_PROXY_SUPPORTED _IO('s', 8)
+
+#define ENQ_BLOCKED_DONOR_SLEEPING	(1U << 0)
+#define ENQ_BLOCKED_DONOR_ON_RQ		(1U << 1)
+
+#endif /* __ENQ_BLOCKED_H */
diff --git a/tools/testing/selftests/sched_ext/test_modules/Makefile b/tools/testing/selftests/sched_ext/test_modules/Makefile
new file mode 100644
index 0000000000000..a0e9e9401ead6
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/test_modules/Makefile
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES
+
+TESTMODS_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST)))))
+KDIR ?= $(if $(O),$(O),$(realpath ../../../../..))
+
+obj-m += scx_enq_blocked_test.o
+
+all:
+	+$(Q)$(MAKE) -C $(KDIR) M=$(TESTMODS_DIR) modules
+
+clean:
+	+$(Q)$(MAKE) -C $(KDIR) M=$(TESTMODS_DIR) clean
diff --git a/tools/testing/selftests/sched_ext/test_modules/scx_enq_blocked_test.c b/tools/testing/selftests/sched_ext/test_modules/scx_enq_blocked_test.c
new file mode 100644
index 0000000000000..908689ed55786
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/test_modules/scx_enq_blocked_test.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES
+ *
+ * Kernel mutex fixture for the sched_ext SCX_OPS_ENQ_BLOCKED selftest.
+ */
+
+#include <linux/atomic.h>
+#include <linux/fs.h>
+#include <linux/jiffies.h>
+#include <linux/ktime.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/uaccess.h>
+
+#include "../enq_blocked.h"
+
+#define DONOR_WAIT_TIMEOUT	msecs_to_jiffies(2000)
+#define ATTACH_WAIT_TIMEOUT	msecs_to_jiffies(10000)
+#define MUTEX_HOLD_TIME		msecs_to_jiffies(200)
+
+static DEFINE_MUTEX(test_mutex);
+static DEFINE_SPINLOCK(donor_lock);
+static struct task_struct *donor_task;
+static atomic_t owner_ready = ATOMIC_INIT(0);
+static atomic_t donor_started = ATOMIC_INIT(0);
+static atomic_t attach_pending = ATOMIC_INIT(0);
+static atomic_t attach_done = ATOMIC_INIT(0);
+static atomic64_t hold_time_ns = ATOMIC64_INIT(0);
+static atomic64_t wait_time_ns = ATOMIC64_INIT(0);
+static atomic64_t nr_holds = ATOMIC64_INIT(0);
+static atomic64_t nr_waits = ATOMIC64_INIT(0);
+
+static long run_owner(void)
+{
+	unsigned long timeout;
+	u64 start_ns;
+	long ret = 0;
+
+	atomic_set(&donor_started, 0);
+	mutex_lock(&test_mutex);
+	start_ns = ktime_get_ns();
+	atomic_set(&owner_ready, 1);
+
+	timeout = jiffies + DONOR_WAIT_TIMEOUT;
+	while (!atomic_read(&donor_started)) {
+		if (time_after(jiffies, timeout)) {
+			ret = -ETIMEDOUT;
+			goto out;
+		}
+		cond_resched();
+	}
+	if (atomic_xchg(&attach_pending, 0)) {
+		timeout = jiffies + ATTACH_WAIT_TIMEOUT;
+		while (!atomic_read(&attach_done)) {
+			if (time_after(jiffies, timeout)) {
+				ret = -ETIMEDOUT;
+				goto out;
+			}
+			cond_resched();
+		}
+	}
+
+	/* Keep yielding while the donor blocks on test_mutex. */
+	timeout = jiffies + MUTEX_HOLD_TIME;
+	while (time_before(jiffies, timeout))
+		cond_resched();
+
+out:
+	atomic_set(&owner_ready, 0);
+	atomic64_add(ktime_get_ns() - start_ns, &hold_time_ns);
+	atomic64_inc(&nr_holds);
+	mutex_unlock(&test_mutex);
+	return ret;
+}
+
+static long run_donor(void)
+{
+	unsigned long flags;
+	u64 start_ns;
+
+	if (!atomic_read(&owner_ready))
+		return -EAGAIN;
+
+	get_task_struct(current);
+	spin_lock_irqsave(&donor_lock, flags);
+	WARN_ON_ONCE(donor_task);
+	donor_task = current;
+	spin_unlock_irqrestore(&donor_lock, flags);
+
+	atomic_set(&donor_started, 1);
+	start_ns = ktime_get_ns();
+	mutex_lock(&test_mutex);
+
+	spin_lock_irqsave(&donor_lock, flags);
+	donor_task = NULL;
+	spin_unlock_irqrestore(&donor_lock, flags);
+	put_task_struct(current);
+
+	atomic64_add(ktime_get_ns() - start_ns, &wait_time_ns);
+	atomic64_inc(&nr_waits);
+	mutex_unlock(&test_mutex);
+	return 0;
+}
+
+static long get_donor_state(void)
+{
+	struct task_struct *task;
+	unsigned long flags;
+	long state = 0;
+
+	spin_lock_irqsave(&donor_lock, flags);
+	task = donor_task;
+	if (task)
+		get_task_struct(task);
+	spin_unlock_irqrestore(&donor_lock, flags);
+	if (!task)
+		return -ENOENT;
+
+	if (READ_ONCE(task->__state) != TASK_RUNNING)
+		state |= ENQ_BLOCKED_DONOR_SLEEPING;
+	if (READ_ONCE(task->on_rq))
+		state |= ENQ_BLOCKED_DONOR_ON_RQ;
+	put_task_struct(task);
+	return state;
+}
+
+static void reset_stats(void)
+{
+	atomic64_set(&hold_time_ns, 0);
+	atomic64_set(&wait_time_ns, 0);
+	atomic64_set(&nr_holds, 0);
+	atomic64_set(&nr_waits, 0);
+}
+
+static long get_stats(unsigned long arg)
+{
+	struct enq_blocked_stats stats = {
+		.hold_time_ns = atomic64_read(&hold_time_ns),
+		.wait_time_ns = atomic64_read(&wait_time_ns),
+		.nr_holds = atomic64_read(&nr_holds),
+		.nr_waits = atomic64_read(&nr_waits),
+	};
+
+	return copy_to_user((void __user *)arg, &stats, sizeof(stats)) ?
+		-EFAULT : 0;
+}
+
+static long enq_blocked_ioctl(struct file *file, unsigned int cmd,
+			      unsigned long arg)
+{
+	switch (cmd) {
+	case ENQ_BLOCKED_IOCTL_OWNER:
+		return run_owner();
+	case ENQ_BLOCKED_IOCTL_DONOR:
+		return run_donor();
+	case ENQ_BLOCKED_IOCTL_RESET_STATS:
+		reset_stats();
+		return 0;
+	case ENQ_BLOCKED_IOCTL_GET_STATS:
+		return get_stats(arg);
+	case ENQ_BLOCKED_IOCTL_PREP_ATTACH:
+		atomic_set(&attach_done, 0);
+		atomic_set(&attach_pending, 1);
+		return 0;
+	case ENQ_BLOCKED_IOCTL_ATTACH_DONE:
+		atomic_set(&attach_done, 1);
+		return 0;
+	case ENQ_BLOCKED_IOCTL_DONOR_STATE:
+		return get_donor_state();
+	case ENQ_BLOCKED_IOCTL_PROXY_SUPPORTED:
+		return IS_ENABLED(CONFIG_SCHED_PROXY_EXEC);
+	default:
+		return -EINVAL;
+	}
+}
+
+static const struct file_operations enq_blocked_fops = {
+	.owner			= THIS_MODULE,
+	.unlocked_ioctl		= enq_blocked_ioctl,
+};
+
+static struct miscdevice enq_blocked_device = {
+	.minor	= MISC_DYNAMIC_MINOR,
+	.name	= "scx_enq_blocked",
+	.fops	= &enq_blocked_fops,
+	.mode	= 0600,
+};
+
+module_misc_device(enq_blocked_device);
+MODULE_AUTHOR("Andrea Righi <arighi@nvidia.com>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("sched_ext blocked donor test module");
-- 
2.55.0

[PATCH 14/15] sched_ext: scx_qmap: Add proxy execution support

[Andrea Righi]

Add a -X option to opt scx_qmap into queueing mutex-blocked tasks for
proxy execution. Without the option, SCX_OPS_ENQ_BLOCKED remains clear
and mutex waiters block normally. With -X, blocked donors are passed to
qmap_enqueue() with SCX_ENQ_BLOCKED.

When scx_qmap receives a blocked donor, dispatch it directly to the
local DSQ of its current cid with a fresh slice and SCX_ENQ_PREEMPT.
This places the donor at the head of the DSQ and requests an immediate
reschedule, allowing the core proxy-exec path to run the mutex owner
using the donor's scheduling context as soon as the donor is selected.

The blocked policy is intentionally unfair and can strongly prioritize
tasks using contended mutexes, but scx_qmap is a demo scheduler and such
aggressive behavior makes proxy-exec support easy to observe. Count
these dispatch attempts in nr_enq_blocked and report their per-interval
delta.

Acked-by: John Stultz <jstultz@google.com>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 tools/sched_ext/scx_qmap.bpf.c | 37 ++++++++++++++++++++++++++++++++++
 tools/sched_ext/scx_qmap.c     | 13 +++++++++---
 tools/sched_ext/scx_qmap.h     |  1 +
 3 files changed, 48 insertions(+), 3 deletions(-)

diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index dd04344378356..4cebe9d9e151e 100644
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -447,6 +447,43 @@ void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags)
 	 */
 	taskc->core_sched_seq = qa.core_sched_tail_seqs[idx]++;
 
+	/*
+	 * SCX_OPS_ALWAYS_ENQ_IMMED makes the local insertion below implicitly
+	 * carry SCX_ENQ_IMMED. If the CPU can't run the blocked donor immediately,
+	 * the core returns it through ops.enqueue() with SCX_ENQ_REENQ. Inserting
+	 * it into the same local DSQ would repeat the IMMED handback until the
+	 * scheduler is ejected. Move reenqueued blocked donors to the global DSQ,
+	 * which doesn't carry SCX_ENQ_IMMED, so another CPU can consume them.
+	 */
+	if ((enq_flags & (SCX_ENQ_BLOCKED | SCX_ENQ_REENQ)) ==
+	    (SCX_ENQ_BLOCKED | SCX_ENQ_REENQ)) {
+		taskc->force_local = false;
+		scx_bpf_dsq_insert(p, SHARED_DSQ, 0, enq_flags);
+		cid = cmask_next_and2_set_wrap(&taskc->cpus_allowed,
+					       &qa.idle_cids.mask,
+					       &qa.self_cids.mask, 0);
+		if (cid < scx_bpf_nr_cids())
+			scx_bpf_kick_cid(cid, SCX_KICK_IDLE);
+		return;
+	}
+
+	/*
+	 * Insert a blocked mutex donor at the head of its current cid's local
+	 * DSQ with a fresh slice and %SCX_ENQ_PREEMPT, requesting an immediate
+	 * reschedule. Once selected, the core proxy-exec path can immediately
+	 * run the mutex owner using the donor's scheduling context.
+	 *
+	 * This policy is intentionally unfair and can strongly prioritize tasks
+	 * using contended mutexes; scx_qmap is a demonstration scheduler and
+	 * this behavior makes proxy-exec support easy to observe.
+	 */
+	if (enq_flags & SCX_ENQ_BLOCKED) {
+		__sync_fetch_and_add(&qa.nr_enq_blocked, 1);
+		scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL_ON | scx_bpf_task_cid(p),
+				   slice_ns, enq_flags | SCX_ENQ_PREEMPT);
+		return;
+	}
+
 	/*
 	 * A task of ours that can run on none of our self cids - the parent
 	 * didn't grant them or we delegated them to children - would starve in
diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c
index 988b6931633e9..5b74595d7d452 100644
--- a/tools/sched_ext/scx_qmap.c
+++ b/tools/sched_ext/scx_qmap.c
@@ -46,7 +46,7 @@ const char help_fmt[] =
 "See the top-of-file comment in .bpf.c for the design.\n"
 "\n"
 "Usage: %s [-s SLICE_US] [-e COUNT] [-t COUNT] [-T COUNT] [-l COUNT] [-b COUNT]\n"
-"       [-N COUNT] [-P] [-M] [-H] [-c CG_PATH] [-d PID] [-D LEN] [-S] [-p] [-I]\n"
+"       [-N COUNT] [-P] [-M] [-H] [-c CG_PATH] [-d PID] [-D LEN] [-S] [-p] [-I] [-X]\n"
 "       [-F COUNT] [-i SEC] [-R MS] [-J MODE] [-v]\n"
 "\n"
 "  -s SLICE_US   Override slice duration\n"
@@ -65,6 +65,7 @@ const char help_fmt[] =
 "  -S            Suppress qmap-specific debug dump\n"
 "  -p            Switch only tasks on SCHED_EXT policy instead of all\n"
 "  -I            Turn on SCX_OPS_ALWAYS_ENQ_IMMED\n"
+"  -X            Turn on SCX_OPS_ENQ_BLOCKED\n"
 "  -F COUNT      IMMED stress: force every COUNT'th enqueue to a busy local DSQ (use with -I)\n"
 "  -C MODE       cid-override test (shuffle|bad-dup|bad-range|bad-mono)\n"
 "  -i SEC        Stats interval, seconds (default 5)\n"
@@ -107,6 +108,7 @@ struct hier_prev {
 	u64 nr_dsps[MAX_SUB_SCHEDS];
 	u64 nr_reenq_cap;
 	u64 nr_reenq_immed;
+	u64 nr_enq_blocked;
 	u64 nr_inject_attempts;
 	u64 nr_rescue_dsp;
 };
@@ -190,14 +192,16 @@ static void print_hier(struct qmap_arena *qa, struct hier_prev *prev, u64 own_cg
 	}
 
 	format_cid_ranges(qa, CID_SHARED, ranges, sizeof(ranges));
-	printf("hier   : nsub=%llu excl=%u shared=%s rr=%s reenq cap/immed +%llu/+%llu inj=+%llu rescue=+%llu\n",
+	printf("hier   : nsub=%llu excl=%u shared=%s rr=%s reenq cap/immed +%llu/+%llu blocked=+%llu inj=+%llu rescue=+%llu\n",
 	       (unsigned long long)qa->nr_sub_scheds, qa->part.nr_excl, ranges, rr,
 	       (unsigned long long)(qa->nr_reenq_cap - prev->nr_reenq_cap),
 	       (unsigned long long)(qa->nr_reenq_immed - prev->nr_reenq_immed),
+	       (unsigned long long)(qa->nr_enq_blocked - prev->nr_enq_blocked),
 	       (unsigned long long)(qa->nr_inject_attempts - prev->nr_inject_attempts),
 	       (unsigned long long)(qa->nr_rescue_dsp - prev->nr_rescue_dsp));
 	prev->nr_reenq_cap = qa->nr_reenq_cap;
 	prev->nr_reenq_immed = qa->nr_reenq_immed;
+	prev->nr_enq_blocked = qa->nr_enq_blocked;
 	prev->nr_inject_attempts = qa->nr_inject_attempts;
 	prev->nr_rescue_dsp = qa->nr_rescue_dsp;
 
@@ -262,7 +266,7 @@ int main(int argc, char **argv)
 	skel->rodata->max_tasks = 16384;
 
 	while ((opt = getopt(argc, argv,
-			     "s:e:t:T:l:b:N:PMHc:d:D:SpIF:C:i:R:J:B:q:vh")) != -1) {
+			     "s:e:t:T:l:b:N:PMHc:d:D:SpIXF:C:i:R:J:B:q:vh")) != -1) {
 		switch (opt) {
 		case 's':
 			skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000;
@@ -323,6 +327,9 @@ int main(int argc, char **argv)
 		case 'I':
 			skel->struct_ops.qmap_ops->flags |= SCX_OPS_ALWAYS_ENQ_IMMED;
 			break;
+		case 'X':
+			skel->struct_ops.qmap_ops->flags |= SCX_OPS_ENQ_BLOCKED;
+			break;
 		case 'F':
 			skel->rodata->immed_stress_nth = strtoul(optarg, NULL, 0);
 			break;
diff --git a/tools/sched_ext/scx_qmap.h b/tools/sched_ext/scx_qmap.h
index c8f602d58ca3a..ee054f6775ffa 100644
--- a/tools/sched_ext/scx_qmap.h
+++ b/tools/sched_ext/scx_qmap.h
@@ -174,6 +174,7 @@ struct qmap_arena {
 	/* bpf -> userspace: stats */
 	u64 nr_reenq_cap;		/* SCX_TASK_REENQ_CAP bounces */
 	u64 nr_reenq_immed;		/* SCX_TASK_REENQ_IMMED bounces */
+	u64 nr_enq_blocked;		/* SCX_ENQ_BLOCKED dispatches */
 	u64 nr_inject_attempts;		/* fault-injection: dispatches to an unheld cid */
 	u64 nr_rescue_dsp;		/* SCX_ENQ_RESCUE dispatch attempts */
 	u32 inject_mode;		/* fault-injection mode (QMAP_INJ_*) */
-- 
2.55.0

[PATCH 15/15] sched: Allow enabling proxy exec with sched_ext

[Andrea Righi]

Now that sched_ext can handle proxy donors and BPF schedulers can opt in
to blocked-donor enqueueing with SCX_OPS_ENQ_BLOCKED, remove the
!SCHED_CLASS_EXT dependency from SCHED_PROXY_EXEC and allow both options
to be enabled together.

Acked-by: John Stultz <jstultz@google.com>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 init/Kconfig | 2 --
 1 file changed, 2 deletions(-)

diff --git a/init/Kconfig b/init/Kconfig
index 5230d4879b1c8..0817e62266e03 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -934,8 +934,6 @@ config SCHED_PROXY_EXEC
 	bool "Proxy Execution"
 	# Avoid some build failures w/ PREEMPT_RT until it can be fixed
 	depends on !PREEMPT_RT
-	# Need to investigate how to inform sched_ext of split contexts
-	depends on !SCHED_CLASS_EXT
 	# Not particularly useful until we get to multi-rq proxying
 	depends on EXPERT
 	help
-- 
2.55.0

Re: [PATCH 01/15] sched: Make NOHZ CFS bandwidth checks follow proxy donor

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] NOHZ_FULL isolation is broken for RT tasks that preempt a constrained FAIR task because the tick dependency is erroneously kept active.
--

--- Patch [1]: [PATCH 01/15] sched: Make NOHZ CFS bandwidth checks follow proxy donor ---
commit 4ed25113b5b2751dc0d63ef337fd5d561e7a7554
Author: Andrea Righi <arighi@nvidia.com>

sched: Make NOHZ CFS bandwidth checks follow proxy donor

This commit updates the NOHZ CFS bandwidth checks to evaluate the proxy
donor rather than the physical execution context. This ensures that a
retained proxy donor correctly enforces bandwidth accounting even when
the lock owner is queued in another scheduling class.

Link: https://lore.kernel.org/r/20260713164807.E5ED21F00A3A@smtp.kernel.org

> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 0697ed0f1c3d2..6e835d2780cfd 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c

[ ... ]

> @@ -1431,6 +1428,14 @@ bool sched_can_stop_tick(struct rq *rq)
>  	if (rq->dl.dl_nr_running)
>  		return false;
>  
> +	/*
> +	 * The selected scheduling context can be a constrained FAIR donor even
> +	 * when rq->curr is an RT task. Check it before the RT fast paths below,
> +	 * which may report that the tick can stop for a throttled RT context.
> +	 */
> +	if (__need_bw_check(rq->donor) && cfs_task_bw_constrained(rq->donor))
> +		return false;
> +

[Severity: High]
Does evaluating rq->donor here during enqueue cause an issue when an RT task
wakes up on a NOHZ_FULL CPU that is currently running a bandwidth-constrained
FAIR task?

During the RT task wakeup, the enqueue path reaches this check before the
context switch:

enqueue_task_rt() -> add_nr_running() -> sched_update_tick_dependency() ->
sched_can_stop_tick()

At this point, rq->donor has not yet been updated and still points to the
currently running FAIR task. This causes the check to return false, which
keeps the TICK_DEP_BIT_SCHED dependency set.

After the context switch to the RT task, rq->donor is updated, but
sched_update_tick_dependency() is not called again on context switch, and
set_next_task_rt() does not actively clear the tick dependency.

Could this cause the incoming RT task to run with the timer tick erroneously
enabled, breaking NOHZ_FULL isolation?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260810151523.86994-1-arighi@nvidia.com?part=1

Re: [PATCH 09/15] sched_ext: Generalize the reject DSQ reenqueue path

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Re-rejecting a task triggers false-positive `WARN_ON_ONCE`s and permanently loses the rejection reason due to conflicting mask management.
--

--- Patch [9]: [PATCH 09/15] sched_ext: Generalize the reject DSQ reenqueue path ---
commit 0787bee4f7073d43925067d6fff35bd1a30ed061
Author: Andrea Righi <arighi@nvidia.com>

sched_ext: Generalize the reject DSQ reenqueue path

This commit generalizes the reject DSQ re-enqueue path by making it
unconditional and carrying the re-enqueue reason directly in p->scx.flags.

> diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
> --- a/kernel/sched/ext/ext.c
> +++ b/kernel/sched/ext/ext.c

[ ... ]

> @@ -4598,23 +4600,22 @@ static void scx_reenq_reject(struct rq *rq)
>  
>  	lockdep_assert_rq_held(rq);
>  
> -	if (!scx_has_subs() || list_empty(&rq->scx.reject_dsq.list))
> +	if (list_empty(&rq->scx.reject_dsq.list))
>  		return;
>  
>  	/*
> -	 * Move to a private list so a task re-rejected by the
> +	 * Move tasks to a private list so a task re-rejected by
>  	 * scx_do_enqueue_task() below isn't revisited this round.
>  	 */
>  	list_for_each_entry_safe(p, n, &rq->scx.reject_dsq.list, scx.dsq_list.node) {
> +		u32 reason = p->scx.flags & SCX_TASK_REENQ_REASON_MASK;
> +
>  		/* migration_pending tasks should have bypassed to local DSQ */
> -		if (WARN_ON_ONCE(p->migration_pending))
> -			continue;
> +		WARN_ON_ONCE(p->migration_pending);
> +		WARN_ON_ONCE(!reason);

[Severity: High]
Will this WARN_ON_ONCE(!reason) trigger on the next tick if a task is
synchronously re-rejected during scx_do_enqueue_task()?

When a task is pushed back to the reject_dsq during the enqueue attempt,
its rejection reason mask seems to get cleared immediately after by the code
below, leaving the reason as 0 on the next drain.

>  
>  		scx_dispatch_dequeue(rq, p);
> -
> -		if (WARN_ON_ONCE(p->scx.flags & SCX_TASK_REENQ_REASON_MASK))
> -			p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;
> -		p->scx.flags |= SCX_TASK_REENQ_CAP;
> +		p->scx.flags |= reason;
>  
>  		list_add_tail(&p->scx.dsq_list.node, &tasks);
>  	}
> @@ -4627,9 +4628,6 @@ static void scx_reenq_reject(struct rq *rq)
>  		p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;

[Severity: High]
Does unconditionally clearing the mask here corrupt the state of newly
re-rejected tasks that were just put back on the reject_dsq?

If scx_do_enqueue_task() re-rejects the task, it gets pushed back via
scx_resolve_local_dsq().

Clearing the mask here wipes out the rejection reason while the task sits
on the reject_dsq. Without a valid rejection reason, the BPF scheduler
cannot correct the placement (e.g., missing capabilities).

Could this lead to repeated rejections until the task hits
SCX_REENQ_MAX_REPEAT, triggering __scx_exit() and crashing the BPF scheduler?

A similar issue seems to exist in reenq_local(), where the mask is also
unconditionally cleared after scx_do_enqueue_task() returns.

>  	}
>  }
> -#else
> -static void scx_reenq_reject(struct rq *rq) {}
> -#endif

[ ... ]

> diff --git a/kernel/sched/ext/sub.c b/kernel/sched/ext/sub.c
> --- a/kernel/sched/ext/sub.c
> +++ b/kernel/sched/ext/sub.c
> @@ -752,6 +752,9 @@ struct scx_dispatch_q *scx_resolve_local_dsq(struct scx_sched *sch, struct rq *r
>  
>  	p->scx.reenq_reason_caps = missing;
>  	p->scx.reenq_reason_cid = cid;
> +	if (WARN_ON_ONCE(p->scx.flags & SCX_TASK_REENQ_REASON_MASK))
> +		p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK;
> +	p->scx.flags |= SCX_TASK_REENQ_CAP;

[Severity: High]
Will this WARN_ON_ONCE fire incorrectly on valid re-rejections?

scx_reenq_reject() deliberately preserves the reason mask prior to the
enqueue attempt. If a task gets synchronously re-rejected here, it will
still have its mask set, which triggers this warning.

>  
>  	return &rq->scx.reject_dsq;
>  }

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260810151523.86994-1-arighi@nvidia.com?part=9

Re: [PATCH 10/15] sched_ext: Handle proxy-exec races in remote DSQ transfers

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Tasks can be permanently starved because migration-disabled state is conflated with active proxy execution, bypassing deferred work and BPF scheduler failsafes.
--

--- Patch [10]: [PATCH 10/15] sched_ext: Handle proxy-exec races in remote DSQ transfers ---
commit 4a7a0caa08e0bdff136179deb5a687b13392995f
Author: Andrea Righi <arighi@nvidia.com>

sched_ext: Handle proxy-exec races in remote DSQ transfers

This commit handles proxy execution races during remote DSQ transfers
by re-evaluating task execution and migration-disabled states under the
source rq lock. Tasks that can no longer proceed are parked on the
source rq's reject DSQ to be re-enqueued later, maintaining placement
policies.

> diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
> index b43b2834141e6..7b467b666212b 100644
> --- a/kernel/sched/ext/ext.c
> +++ b/kernel/sched/ext/ext.c

[ ... ]

> @@ -2573,6 +2585,60 @@ static bool task_can_run_on_remote_rq(struct scx_sched *sch,
>  	return true;
>  }
>  
> +/*
> + * Proxy execution can change @p's execution and migration-disabled state
> + * without touching its DSQ entry or clearing holding_cpu. Check those states
> + * with @p's rq locked. Without proxy execution, the holding_cpu handshake is
> + * sufficient and this must not affect the existing migration path.
> + *
> + * A BPF-directed transfer to a remote local DSQ performs a normal task
> + * migration and thus cannot move a migration-disabled task. In contrast,
> + * proxy_migrate_task() moves only a blocked donor's scheduling context towards
> + * the mutex owner and preserves its execution home in wake_cpu. The latter is
> + * therefore allowed even when the donor is migration-disabled.
> + */
> +static bool task_move_proxy_raced(struct task_struct *p)
> +{
> +	struct rq *src_rq = task_rq(p);
> +
> +	lockdep_assert_rq_held(src_rq);
> +
> +	if (!sched_proxy_exec())
> +		return false;
> +
> +	/* @p may be rq->curr under another task's scheduling context. */
> +	if (task_on_cpu(src_rq, p))
> +		return true;
> +
> +	if (is_migration_disabled(p))
> +		return true;

[Severity: High]
Does returning true unconditionally for migration-disabled tasks conflate them
with active proxy execution? 

If a task is migration-disabled but not actively proxying, it will be rejected
with SCX_TASK_REENQ_PROXY. Since rq_owned_post_enq() skips calling
schedule_deferred_locked() for SCX_TASK_REENQ_PROXY rejects:

	if (dsq->id == SCX_DSQ_REJECT) {
		if ((p->scx.flags & SCX_TASK_REENQ_REASON_MASK) ==
		    SCX_TASK_REENQ_PROXY)
			rq->scx.flags |= SCX_RQ_PROXY_REENQ;
		else
			schedule_deferred_locked(rq);
	}

And scx_proxy_resolved() is never called for a task that isn't actively
proxying, could this leave the task permanently stranded on the reject DSQ if
the source rq is idle?

> +
> +	/* Don't move an active scheduling context off its source rq. */
> +	if (task_current_donor(src_rq, p))
> +		return true;
> +
> +	return false;
> +}

[ ... ]

> @@ -2660,6 +2740,7 @@ static struct rq *move_task_between_dsqs(struct scx_sched *sch,
>  					 struct scx_dispatch_q *dst_dsq)
>  {
>  	struct rq *src_rq = task_rq(p), *dst_rq;
> +	bool proxy_raced;
>  
>  	BUG_ON(src_dsq->id == SCX_DSQ_LOCAL);
>  	lockdep_assert_held(&src_dsq->lock);
> @@ -2667,6 +2748,13 @@ static struct rq *move_task_between_dsqs(struct scx_sched *sch,
>  
>  	if (dst_dsq->id == SCX_DSQ_LOCAL) {
>  		dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq);
> +		proxy_raced = src_rq != dst_rq && task_move_proxy_raced(p);
> +		if (unlikely(proxy_raced)) {
> +			dispatch_dequeue_locked(p, src_dsq);
> +			raw_spin_unlock(&src_dsq->lock);
> +			scx_reject_task(sch, src_rq, p, enq_flags);
> +			return src_rq;
> +		}

[Severity: High]
If a BPF scheduler incorrectly attempts to migrate a migration-disabled task to
a remote local DSQ, task_move_proxy_raced() intercepts the dispatch here.

Can this prevent task_can_run_on_remote_rq() from detecting the illegal
migration and triggering scx_error(), bypassing the BPF scheduler failsafe
while leaving the task permanently starved?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260810151523.86994-1-arighi@nvidia.com?part=10

Re: [PATCH 11/15] sched_ext: Split curr|donor references properly

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 4 potential issue(s) to consider:
- [High] rq_is_open() incorrectly inspects rq->curr instead of rq->donor when evaluating SCX_ENQ_PREEMPT constraints.
- [High] scx_rescue_charge() misattributes rescue execution time by dereferencing scx_task_sched(rq->curr) instead of rq->donor.
- [Medium] dequeue_task_scx() and scx_bypass() incorrectly evaluate task_current() instead of task_current_donor().
- [Medium] Blocked proxy donors incorrectly enter ops.running() and ops.stopping() sessions, directly contradicting documentation.
--

--- Patch [11]: [PATCH 11/15] sched_ext: Split curr|donor references properly ---
commit 85eb7af3f37babba254fc28b03cd51fb5e7deb18
Author: Andrea Righi <arighi@nvidia.com>
sched_ext: Split curr|donor references properly

This commit updates sched_ext to correctly differentiate between the physical 
execution task (rq->curr) and the scheduling context donor (rq->donor) during 
proxy execution. It modifies scheduling policy and accounting paths to rely on 
rq->donor, resolving discrepancies when the two tasks differ. It also extends 
scx_dump_state() to explicitly report both contexts.

> diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst
> index ad2fff3c05937..db1ef89ed8f2a 100644
> --- a/Documentation/scheduler/sched-ext.rst
> +++ b/Documentation/scheduler/sched-ext.rst
> @@ -487,6 +487,12 @@ and edge cases, to name a few examples:
>    class, in which case it will exit the tick-dispatch loop even though it is runnable
>    and has a non-zero slice.
>  
> +* Under proxy execution, sched_ext continues to observe the donor as the current
> +  scheduling context. A blocked donor does not enter an ``ops.running()`` /
> +  ``ops.stopping()`` session because it does not execute itself, and the lock
> +  owner executing on its behalf is intentionally not reported through these
> +  callbacks.
> +

[Severity: Medium]
Will blocked proxy donors incorrectly enter ops.running() and ops.stopping() 
sessions, contradicting this documentation?

In set_next_task_scx(), when restoring a previously resolved context (!first):

    if ((p->scx.flags & SCX_TASK_QUEUED) && (!p->is_blocked || !first))
        scx_start_task_running(rq, p);

And in scx_proxy_donor_start():

    if (donor->sched_class == &ext_sched_class &&
        (donor->scx.flags & SCX_TASK_QUEUED))
        scx_start_task_running(rq, donor);

Does calling scx_start_task_running() unconditionally for queued donors here 
mark the task with SCX_TASK_RUN_TRACKED and invoke the BPF running callbacks, 
violating the API contract that blocked donors do not execute themselves?

>  See the "Scheduling Cycle" section for a more detailed description of how
>  a freshly woken up task gets on a CPU.
>  
> diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
> index 7b467b666212b..39d3e3af05f90 100644
> --- a/kernel/sched/ext/ext.c
> +++ b/kernel/sched/ext/ext.c
> @@ -1438,23 +1438,30 @@ static void apply_slice_vtime(struct task_struct *p, u64 slice, u64 vtime, u64 e
>  
>  static void update_curr_scx(struct rq *rq)
>  {
> -	struct task_struct *curr = rq->curr;
> +	struct task_struct *donor;
>  	s64 delta_exec;
>  
> +	/*
> +	 * update_curr_scx() is selected through rq->donor->sched_class, not
> +	 * rq->curr->sched_class, so @donor is always an EXT task here. If an EXT
> +	 * owner executes for a FAIR donor, FAIR's update_curr() runs instead.
> +	 */
> +	donor = rq->donor;
> +
>  	/* apply even on 0 delta_exec, callers may still act on the slice */
> -	apply_task_slice_oob(rq, curr);
> +	apply_task_slice_oob(rq, donor);
>  
>  	delta_exec = update_curr_common(rq);
>  	if (unlikely(delta_exec <= 0))
>  		return;
>  
> -	if (curr->scx.slice != SCX_SLICE_INF) {
> -		curr->scx.slice -= min_t(u64, curr->scx.slice, delta_exec);
> -		if (!curr->scx.slice)
> -			touch_core_sched(rq, curr);
> +	if (donor->scx.slice != SCX_SLICE_INF) {
> +		donor->scx.slice -= min_t(u64, donor->scx.slice, delta_exec);
> +		if (!donor->scx.slice)
> +			touch_core_sched(rq, donor);
>  	}
>  
> -	if (unlikely(curr == scx_rescuee(rq)))
> +	if (unlikely(donor == scx_rescuee(rq)))
>  		scx_rescue_charge(rq, delta_exec);

[Severity: High]
Does scx_rescue_charge() misattribute rescue execution time by dereferencing 
scx_task_sched(rq->curr) instead of rq->donor?

When a proxy donor is placed in the rescue DSQ and consumes time, 
scx_rescue_charge() is called here, but internally it does:

    pcpu = per_cpu_ptr(scx_task_sched(rq->curr)->pcpu, cpu_of(rq));
    pcpu->rescue_avg = scx_rescue_decay_avg(pcpu) + delta_exec;

If rq->curr is a non-ext task (like fair), scx_task_sched() could return 
incorrect scheduler contexts or default structures. Can this lead to accounting 
corruption or potential pointer dereferences when it charges the consumed 
budget to the physical execution task's scheduler instead of the ext donor?

>  
>  	dl_server_update(&rq->ext_server, delta_exec);

[ ... ]

> @@ -1634,9 +1641,9 @@ static void rq_owned_post_enq(struct scx_sched *sch, struct rq *rq,
>  	if (rq->scx.flags & SCX_RQ_IN_BALANCE)
>  		return;
>  
> -	if ((enq_flags & SCX_ENQ_PREEMPT) && p != rq->curr &&
> -	    rq->curr->sched_class == &ext_sched_class) {
> -		if (likely(scx_set_task_slice(rq->curr, 0)))
> +	if ((enq_flags & SCX_ENQ_PREEMPT) && p != rq->donor &&
> +	    rq->donor->sched_class == &ext_sched_class) {
> +		if (likely(scx_set_task_slice(rq->donor, 0)))
>  			resched_curr(rq);
>  		else
>  			__scx_add_event(sch, SCX_EV_SLICE_DENIED, 1);

[Severity: High]
Does rq_is_open() also need to check rq->donor instead of rq->curr when 
evaluating SCX_ENQ_PREEMPT constraints?

Currently, rq_is_open() evaluates the physical execution task (rq->curr):

    struct task_struct *curr = rq->curr;
    return curr->sched_class != &ext_sched_class ||
        likely(!(curr->scx.flags & SCX_TASK_PROTECTED));

Under proxy execution, if rq->curr is a fair task while the donor (rq->donor) 
is an ext task with a protected slice, rq_is_open() would return true, causing 
dsq_inc_nr() to queue an immed task assuming immediate preemption.

However, since rq_owned_post_enq() here correctly checks rq->donor and refuses 
preemption, could this leave the newly queued task stranded on the local DSQ 
without a reschedule kick, causing starvation?

[ ... ]

> @@ -2212,13 +2219,14 @@ static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int core_enq_
>  		rq->scx.flags |= SCX_RQ_IN_WAKEUP;
>  
>  	/*
> -	 * Restoring a running task will be immediately followed by
> -	 * set_next_task_scx() which expects the task to not be on the BPF
> +	 * Restoring the current scheduling context will be immediately followed
> +	 * by set_next_task_scx() which expects the task to not be on the BPF
>  	 * scheduler as tasks can only start running through local DSQs. Force
>  	 * direct-dispatch into the local DSQ by setting the sticky_cpu. Mark
>  	 * IGNORE_CAPS to force entry into the local DSQ.
>  	 */
> -	if (unlikely(enq_flags & ENQUEUE_RESTORE) && task_current(rq, p)) {
> +	if (unlikely(enq_flags & ENQUEUE_RESTORE) &&
> +	    task_current_donor(rq, p)) {
>  		sticky_cpu = cpu_of(rq);
>  		enq_flags |= SCX_ENQ_IGNORE_CAPS;
>  	}

[Severity: Medium]
Are there other places that should use task_current_donor() instead of 
task_current() to avoid stripping the slice from the active proxy donor 
prematurely?

For example, in dequeue_task_scx():

    if (!((deq_flags & DEQUEUE_SAVE) && task_current(rq, p)))
        scx_task_slice_ended(rq, p);

If a proxy donor is dequeued with DEQUEUE_SAVE (e.g. for a priority change), 
the task_current(rq, p) check will fail because the physical execution task is 
not the donor, causing the donor to lose its slice protection.

Similarly in scx_bypass():

    if (bypass && task_current(rq, p))
        scx_task_slice_ended(rq, p);

Could this fail to clear the slice for the active proxy donor because 
task_current() evaluates to false?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260810151523.86994-1-arighi@nvidia.com?part=11