FAILED: patch "[PATCH] sched_ext: Preserve rq tracking across local DSQ dispatch" failed to apply to 7.1-stable tree

FAILED: patch "[PATCH] sched_ext: Preserve rq tracking across local DSQ dispatch" failed to apply to 7.1-stable tree

[gregkh]

The patch below does not apply to the 7.1-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable@vger.kernel.org>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-7.1.y
git checkout FETCH_HEAD
git cherry-pick -x 18d62044cda7a2b40f59d910659c0b0d6accad37
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<stable@vger.kernel.org>' --in-reply-to '2026072116-antivirus-displace-b981@gregkh' --subject-prefix 'PATCH 7.1.y' 'HEAD^..'

Possible dependencies:



thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From 18d62044cda7a2b40f59d910659c0b0d6accad37 Mon Sep 17 00:00:00 2001
From: Andrea Righi <arighi@nvidia.com>
Date: Wed, 8 Jul 2026 10:43:27 +0200
Subject: [PATCH] sched_ext: Preserve rq tracking across local DSQ dispatch

dispatch_to_local_dsq() can run from scx_bpf_dsq_move_to_local() while
ops.dispatch() has recorded the current rq. Moving a task to a local DSQ
may switch to the source or destination rq before synchronously invoking
ops.dequeue() through the following path:

  SCX_CALL_OP(dispatch, rq)
    ops.dispatch()
      scx_bpf_dsq_move_to_local()
        scx_flush_dispatch_buf()
          finish_dispatch()
            dispatch_to_local_dsq()
              scx_dispatch_enqueue()
                local_dsq_post_enq()
                  call_task_dequeue()
                    SCX_CALL_OP_TASK(dequeue, locked_rq, ...)

The nested callback saves the recorded rq and restores it on return. If
the rq tracking does not follow the lock switch, update_locked_rq() can
trigger the following lockdep assertion while restoring an rq which is
no longer held:

  WARNING: kernel/sched/sched.h:1641 at call_task_dequeue+0x160/0x170
  Call Trace:
    scx_dispatch_enqueue+0x2b0/0x460
    dispatch_to_local_dsq+0x138/0x230
    scx_flush_dispatch_buf+0x1af/0x220
    scx_bpf_dsq_move_to_local___v2+0xe2/0x1c0
    bpf__sched_ext_ops_dispatch+0x4b/0xa7
    do_pick_task_scx+0x3b6/0x910
    __pick_next_task+0x105/0x1f0
    __schedule+0x3e7/0x1980

Introduce switch_rq_lock() to update the tracking state together with
each rq lock handoff. Use it in dispatch_to_local_dsq(),
move_remote_task_to_local_dsq() and the in-balance paths of
scx_dsq_move(), ensuring that scx_locked_rq() consistently refers to the
rq whose lock is actually held throughout the lock dance.

Fixes: 7fb39e4eb4c3 ("sched_ext: Save and restore scx_locked_rq across SCX_CALL_OP")
Cc: stable@vger.kernel.org # 7.1+
Signed-off-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index e75e2fd5ab7e..ee66dacfc92c 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -479,6 +479,18 @@ static bool rq_is_open(struct rq *rq, u64 enq_flags)
  */
 DEFINE_PER_CPU(struct rq *, scx_locked_rq_state);
 
+static void switch_rq_lock(struct rq *from, struct rq *to)
+{
+	bool tracked = scx_locked_rq() == from;
+
+	if (tracked)
+		update_locked_rq(NULL);
+	raw_spin_rq_unlock(from);
+	raw_spin_rq_lock(to);
+	if (tracked)
+		update_locked_rq(to);
+}
+
 /*
  * Flipped on enable per sch->is_cid_type. Declared in internal.h so
  * subsystem inlines can read it.
@@ -2274,8 +2286,7 @@ static void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags,
 	deactivate_task(src_rq, p, 0);
 	set_task_cpu(p, cpu_of(dst_rq));
 
-	raw_spin_rq_unlock(src_rq);
-	raw_spin_rq_lock(dst_rq);
+	switch_rq_lock(src_rq, dst_rq);
 
 	/*
 	 * We want to pass scx-specific enq_flags but activate_task() will
@@ -2608,9 +2619,8 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq,
 
 	/* switch to @src_rq lock */
 	if (locked_rq != src_rq) {
-		raw_spin_rq_unlock(locked_rq);
+		switch_rq_lock(locked_rq, src_rq);
 		locked_rq = src_rq;
-		raw_spin_rq_lock(src_rq);
 	}
 
 	/* task_rq couldn't have changed if we're still the holding cpu */
@@ -2644,10 +2654,8 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq,
 	}
 
 	/* switch back to @rq lock */
-	if (locked_rq != rq) {
-		raw_spin_rq_unlock(locked_rq);
-		raw_spin_rq_lock(rq);
-	}
+	if (locked_rq != rq)
+		switch_rq_lock(locked_rq, rq);
 }
 
 /**
@@ -8825,10 +8833,8 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit,
 	in_balance = this_rq->scx.flags & SCX_RQ_IN_BALANCE;
 
 	if (in_balance) {
-		if (this_rq != src_rq) {
-			raw_spin_rq_unlock(this_rq);
-			raw_spin_rq_lock(src_rq);
-		}
+		if (this_rq != src_rq)
+			switch_rq_lock(this_rq, src_rq);
 	} else {
 		raw_spin_rq_lock(src_rq);
 	}
@@ -8860,10 +8866,8 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit,
 	dispatched = true;
 out:
 	if (in_balance) {
-		if (this_rq != locked_rq) {
-			raw_spin_rq_unlock(locked_rq);
-			raw_spin_rq_lock(this_rq);
-		}
+		if (this_rq != locked_rq)
+			switch_rq_lock(locked_rq, this_rq);
 	} else {
 		raw_spin_rq_unlock_irqrestore(locked_rq, flags);
 	}

[PATCH 7.1.y 1/2] sched_ext: Move shared helpers from ext.c into internal.h and cid.h

[Sasha Levin]

From: Tejun Heo <tj@kernel.org>

[ Upstream commit 4437ad129cf5b37c00a5bc9fa5989d1da4d64d07 ]

idle.c and cid.c are included into build_policy.c together with ext.c and
use helpers that ext.c defines. Because the helpers live in ext.c, the two
files can not parse as standalone units and clangd reports errors in them.

Move the helpers to the headers they belong to. The op-dispatch macros and
helpers plus scx_parent() to internal.h, and scx_cpu_arg()/scx_cpu_ret() to
cid.h. No functional change. idle.c and cid.c now parse clean standalone.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Stable-dep-of: 18d62044cda7 ("sched_ext: Preserve rq tracking across local DSQ dispatch")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/sched/ext.c          | 29 -----------------------------
 kernel/sched/ext_internal.h | 30 ++++++++++++++++++++++++++++++
 2 files changed, 30 insertions(+), 29 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 5d2d19473a82e8..dc6138461ae3de 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -218,8 +218,6 @@ static __printf(4, 5) bool scx_exit(struct scx_sched *sch,
 #define scx_error(sch, fmt, args...)	scx_exit((sch), SCX_EXIT_ERROR, 0, fmt, ##args)
 #define scx_verror(sch, fmt, args)	scx_vexit((sch), SCX_EXIT_ERROR, 0, fmt, args)
 
-#define SCX_HAS_OP(sch, op)	test_bit(SCX_OP_IDX(op), (sch)->has_op)
-
 static long jiffies_delta_msecs(unsigned long at, unsigned long now)
 {
 	if (time_after(at, now))
@@ -234,20 +232,6 @@ static bool u32_before(u32 a, u32 b)
 }
 
 #ifdef CONFIG_EXT_SUB_SCHED
-/**
- * scx_parent - Find the parent sched
- * @sch: sched to find the parent of
- *
- * Returns the parent scheduler or %NULL if @sch is root.
- */
-static struct scx_sched *scx_parent(struct scx_sched *sch)
-{
-	if (sch->level)
-		return sch->ancestors[sch->level - 1];
-	else
-		return NULL;
-}
-
 /**
  * scx_next_descendant_pre - find the next descendant for pre-order walk
  * @pos: the current position (%NULL to initiate traversal)
@@ -295,7 +279,6 @@ static void scx_set_task_sched(struct task_struct *p, struct scx_sched *sch)
 	rcu_assign_pointer(p->scx.sched, sch);
 }
 #else	/* CONFIG_EXT_SUB_SCHED */
-static struct scx_sched *scx_parent(struct scx_sched *sch) { return NULL; }
 static struct scx_sched *scx_next_descendant_pre(struct scx_sched *pos, struct scx_sched *root) { return pos ? NULL : root; }
 static void scx_set_task_sched(struct task_struct *p, struct scx_sched *sch) {}
 #endif	/* CONFIG_EXT_SUB_SCHED */
@@ -455,18 +438,6 @@ static bool rq_is_open(struct rq *rq, u64 enq_flags)
  */
 DEFINE_PER_CPU(struct rq *, scx_locked_rq_state);
 
-static inline void update_locked_rq(struct rq *rq)
-{
-	/*
-	 * Check whether @rq is actually locked. This can help expose bugs
-	 * or incorrect assumptions about the context in which a kfunc or
-	 * callback is executed.
-	 */
-	if (rq)
-		lockdep_assert_rq_held(rq);
-	__this_cpu_write(scx_locked_rq_state, rq);
-}
-
 /*
  * SCX ops can recurse via scx_bpf_sub_dispatch() - the inner call must not
  * clobber the outer's scx_locked_rq_state. Save it on entry, restore on exit.
diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h
index a075732d4430d8..6d57f1d0b86f91 100644
--- a/kernel/sched/ext_internal.h
+++ b/kernel/sched/ext_internal.h
@@ -1377,6 +1377,20 @@ static inline struct rq *scx_locked_rq(void)
 	return __this_cpu_read(scx_locked_rq_state);
 }
 
+static inline void update_locked_rq(struct rq *rq)
+{
+	/*
+	 * Check whether @rq is actually locked. This can help expose bugs
+	 * or incorrect assumptions about the context in which a kfunc or
+	 * callback is executed.
+	 */
+	if (rq)
+		lockdep_assert_rq_held(rq);
+	__this_cpu_write(scx_locked_rq_state, rq);
+}
+
+#define SCX_HAS_OP(sch, op)	test_bit(SCX_OP_IDX(op), (sch)->has_op)
+
 static inline bool scx_bypassing(struct scx_sched *sch, s32 cpu)
 {
 	return unlikely(per_cpu_ptr(sch->pcpu, cpu)->flags &
@@ -1457,6 +1471,20 @@ static inline struct scx_sched *scx_prog_sched(const struct bpf_prog_aux *aux)
 
 	return NULL;
 }
+
+/**
+ * scx_parent - Find the parent sched
+ * @sch: sched to find the parent of
+ *
+ * Returns the parent scheduler or %NULL if @sch is root.
+ */
+static inline struct scx_sched *scx_parent(struct scx_sched *sch)
+{
+	if (sch->level)
+		return sch->ancestors[sch->level - 1];
+	else
+		return NULL;
+}
 #else	/* CONFIG_EXT_SUB_SCHED */
 static inline struct scx_sched *scx_task_sched(const struct task_struct *p)
 {
@@ -1480,4 +1508,6 @@ static struct scx_sched *scx_prog_sched(const struct bpf_prog_aux *aux)
 {
 	return rcu_dereference_all(scx_root);
 }
+
+static inline struct scx_sched *scx_parent(struct scx_sched *sch) { return NULL; }
 #endif	/* CONFIG_EXT_SUB_SCHED */
-- 
2.53.0

[PATCH 7.1.y 2/2] sched_ext: Preserve rq tracking across local DSQ dispatch

[Sasha Levin]

From: Andrea Righi <arighi@nvidia.com>

[ Upstream commit 18d62044cda7a2b40f59d910659c0b0d6accad37 ]

dispatch_to_local_dsq() can run from scx_bpf_dsq_move_to_local() while
ops.dispatch() has recorded the current rq. Moving a task to a local DSQ
may switch to the source or destination rq before synchronously invoking
ops.dequeue() through the following path:

  SCX_CALL_OP(dispatch, rq)
    ops.dispatch()
      scx_bpf_dsq_move_to_local()
        scx_flush_dispatch_buf()
          finish_dispatch()
            dispatch_to_local_dsq()
              scx_dispatch_enqueue()
                local_dsq_post_enq()
                  call_task_dequeue()
                    SCX_CALL_OP_TASK(dequeue, locked_rq, ...)

The nested callback saves the recorded rq and restores it on return. If
the rq tracking does not follow the lock switch, update_locked_rq() can
trigger the following lockdep assertion while restoring an rq which is
no longer held:

  WARNING: kernel/sched/sched.h:1641 at call_task_dequeue+0x160/0x170
  Call Trace:
    scx_dispatch_enqueue+0x2b0/0x460
    dispatch_to_local_dsq+0x138/0x230
    scx_flush_dispatch_buf+0x1af/0x220
    scx_bpf_dsq_move_to_local___v2+0xe2/0x1c0
    bpf__sched_ext_ops_dispatch+0x4b/0xa7
    do_pick_task_scx+0x3b6/0x910
    __pick_next_task+0x105/0x1f0
    __schedule+0x3e7/0x1980

Introduce switch_rq_lock() to update the tracking state together with
each rq lock handoff. Use it in dispatch_to_local_dsq(),
move_remote_task_to_local_dsq() and the in-balance paths of
scx_dsq_move(), ensuring that scx_locked_rq() consistently refers to the
rq whose lock is actually held throughout the lock dance.

Fixes: 7fb39e4eb4c3 ("sched_ext: Save and restore scx_locked_rq across SCX_CALL_OP")
Cc: stable@vger.kernel.org # 7.1+
Signed-off-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/sched/ext.c | 36 ++++++++++++++++++++----------------
 1 file changed, 20 insertions(+), 16 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index dc6138461ae3de..07e2c40b788dcc 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -438,6 +438,18 @@ static bool rq_is_open(struct rq *rq, u64 enq_flags)
  */
 DEFINE_PER_CPU(struct rq *, scx_locked_rq_state);
 
+static void switch_rq_lock(struct rq *from, struct rq *to)
+{
+	bool tracked = scx_locked_rq() == from;
+
+	if (tracked)
+		update_locked_rq(NULL);
+	raw_spin_rq_unlock(from);
+	raw_spin_rq_lock(to);
+	if (tracked)
+		update_locked_rq(to);
+}
+
 /*
  * SCX ops can recurse via scx_bpf_sub_dispatch() - the inner call must not
  * clobber the outer's scx_locked_rq_state. Save it on entry, restore on exit.
@@ -2262,8 +2274,7 @@ static void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags,
 	deactivate_task(src_rq, p, 0);
 	set_task_cpu(p, cpu_of(dst_rq));
 
-	raw_spin_rq_unlock(src_rq);
-	raw_spin_rq_lock(dst_rq);
+	switch_rq_lock(src_rq, dst_rq);
 
 	/*
 	 * We want to pass scx-specific enq_flags but activate_task() will
@@ -2594,9 +2605,8 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq,
 
 	/* switch to @src_rq lock */
 	if (locked_rq != src_rq) {
-		raw_spin_rq_unlock(locked_rq);
+		switch_rq_lock(locked_rq, src_rq);
 		locked_rq = src_rq;
-		raw_spin_rq_lock(src_rq);
 	}
 
 	/* task_rq couldn't have changed if we're still the holding cpu */
@@ -2624,10 +2634,8 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq,
 	}
 
 	/* switch back to @rq lock */
-	if (locked_rq != rq) {
-		raw_spin_rq_unlock(locked_rq);
-		raw_spin_rq_lock(rq);
-	}
+	if (locked_rq != rq)
+		switch_rq_lock(locked_rq, rq);
 }
 
 /**
@@ -8360,10 +8368,8 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit,
 	in_balance = this_rq->scx.flags & SCX_RQ_IN_BALANCE;
 
 	if (in_balance) {
-		if (this_rq != src_rq) {
-			raw_spin_rq_unlock(this_rq);
-			raw_spin_rq_lock(src_rq);
-		}
+		if (this_rq != src_rq)
+			switch_rq_lock(this_rq, src_rq);
 	} else {
 		raw_spin_rq_lock(src_rq);
 	}
@@ -8395,10 +8401,8 @@ static bool scx_dsq_move(struct bpf_iter_scx_dsq_kern *kit,
 	dispatched = true;
 out:
 	if (in_balance) {
-		if (this_rq != locked_rq) {
-			raw_spin_rq_unlock(locked_rq);
-			raw_spin_rq_lock(this_rq);
-		}
+		if (this_rq != locked_rq)
+			switch_rq_lock(locked_rq, this_rq);
 	} else {
 		raw_spin_rq_unlock_irqrestore(locked_rq, flags);
 	}
-- 
2.53.0