[PATCH v2] sched_ext: Fix stale direct dispatch state in ddsp_dsq_id

[Andrea Righi]

@p->scx.ddsp_dsq_id can be left set (non-SCX_DSQ_INVALID) triggering a
spurious warning in mark_direct_dispatch() when the next wakeup's
ops.select_cpu() calls scx_bpf_dsq_insert(), such as:

 WARNING: kernel/sched/ext.c:1273 at scx_dsq_insert_commit+0xcd/0x140

The root cause is that ddsp_dsq_id was only cleared in dispatch_enqueue(),
which is not reached in all paths that consume or cancel a direct dispatch
verdict. Instead, clear it at the right places:

 - direct_dispatch(): cache the direct dispatch state in local variables
   and clear it before dispatch_enqueue() on the synchronous path. For
   the deferred path, the direct dispatch state must remain set until
   process_ddsp_deferred_locals() consumes them.

 - process_ddsp_deferred_locals(): cache the dispatch state in local
   variables and clear it before calling dispatch_to_local_dsq(), which
   may migrate the task to another rq.

 - do_enqueue_task(): clear the dispatch state on the enqueue path
   (local/global/bypass fallbacks), where the direct dispatch verdict is
   ignored.

 - dequeue_task_scx(): clear the dispatch state after dispatch_dequeue()
   to handle both the deferred dispatch cancellation and the holding_cpu
   race, covering all cases where a pending direct dispatch is
   cancelled.

 - scx_disable_task(): clear the direct dispatch state when
   transitioning a task out of the current scheduler. Waking tasks may
   have had the direct dispatch state set by the outgoing scheduler's
   ops.select_cpu() and then been queued on a wake_list via
   ttwu_queue_wakelist(), when SCX_OPS_ALLOW_QUEUED_WAKEUP is set. Such
   tasks are not on the runqueue and are not iterated by scx_bypass(),
   so their direct dispatch state won't be cleared. Without this clear,
   when the new scheduler calls scx_enable_task() for these tasks, any
   subsequent ops.select_cpu() call that tries to direct dispatch the
   task will trigger the WARN_ON_ONCE() in mark_direct_dispatch().

Fixes: 5b26f7b920f76 ("sched_ext: Allow SCX_DSQ_LOCAL_ON for direct dispatches")
Cc: stable@xxxxxxxxxxxxxxx # v6.12+
Cc: Daniel Hodges <hodgesd@xxxxxxxx>
Cc: Patrick Somaru <patsomaru@xxxxxxxx>
Signed-off-by: Andrea Righi <arighi@xxxxxxxxxx>
---
Changes in v2:
 - Move clearing of the direct dispatch state out of dispatch_enqueue() to the
   appropriate places (Tejun Heo)
 - Do not unconditionally clear the direct dispatch state in scx_enable_task()
 - Link to v1: https://lore.kernel.org/all/20260401215619.1188194-1-arighi@xxxxxxxxxx

 kernel/sched/ext.c | 44 +++++++++++++++++++++++++++-----------------
 1 file changed, 27 insertions(+), 17 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index d5bdcdb3f7004..71bb83fccd60d 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -1109,15 +1109,6 @@ static void dispatch_enqueue(struct scx_sched *sch, struct scx_dispatch_q *dsq,
 	dsq_mod_nr(dsq, 1);
 	p->scx.dsq = dsq;
 
-	/*
-	 * scx.ddsp_dsq_id and scx.ddsp_enq_flags are only relevant on the
-	 * direct dispatch path, but we clear them here because the direct
-	 * dispatch verdict may be overridden on the enqueue path during e.g.
-	 * bypass.
-	 */
-	p->scx.ddsp_dsq_id = SCX_DSQ_INVALID;
-	p->scx.ddsp_enq_flags = 0;
-
 	/*
 	 * We're transitioning out of QUEUEING or DISPATCHING. store_release to
 	 * match waiters' load_acquire.
@@ -1283,16 +1274,23 @@ static void mark_direct_dispatch(struct scx_sched *sch,
 	p->scx.ddsp_enq_flags = enq_flags;
 }
 
+static inline void clear_direct_dispatch(struct task_struct *p)
+{
+	p->scx.ddsp_dsq_id = SCX_DSQ_INVALID;
+	p->scx.ddsp_enq_flags = 0;
+}
+
 static void direct_dispatch(struct scx_sched *sch, struct task_struct *p,
 			    u64 enq_flags)
 {
 	struct rq *rq = task_rq(p);
-	struct scx_dispatch_q *dsq =
-		find_dsq_for_dispatch(sch, rq, p->scx.ddsp_dsq_id, p);
+	u64 dsq_id = p->scx.ddsp_dsq_id;
+	u64 ddsp_enq_flags = p->scx.ddsp_enq_flags | enq_flags;
+	struct scx_dispatch_q *dsq;
 
 	touch_core_sched_dispatch(rq, p);
 
-	p->scx.ddsp_enq_flags |= enq_flags;
+	dsq = find_dsq_for_dispatch(sch, rq, dsq_id, p);
 
 	/*
 	 * We are in the enqueue path with @rq locked and pinned, and thus can't
@@ -1303,6 +1301,12 @@ static void direct_dispatch(struct scx_sched *sch, struct task_struct *p,
 	if (dsq->id == SCX_DSQ_LOCAL && dsq != &rq->scx.local_dsq) {
 		unsigned long opss;
 
+		/*
+		 * Update the direct dispatch state and keep it until
+		 * process_ddsp_deferred_locals() consumes it.
+		 */
+		p->scx.ddsp_enq_flags = ddsp_enq_flags;
+
 		opss = atomic_long_read(&p->scx.ops_state) & SCX_OPSS_STATE_MASK;
 
 		switch (opss & SCX_OPSS_STATE_MASK) {
@@ -1329,8 +1333,8 @@ static void direct_dispatch(struct scx_sched *sch, struct task_struct *p,
 		return;
 	}
 
-	dispatch_enqueue(sch, dsq, p,
-			 p->scx.ddsp_enq_flags | SCX_ENQ_CLEAR_OPSS);
+	clear_direct_dispatch(p);
+	dispatch_enqueue(sch, dsq, p, ddsp_enq_flags | SCX_ENQ_CLEAR_OPSS);
 }
 
 static bool scx_rq_online(struct rq *rq)
@@ -1439,6 +1443,7 @@ static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags,
 	 */
 	touch_core_sched(rq, p);
 	refill_task_slice_dfl(sch, p);
+	clear_direct_dispatch(p);
 	dispatch_enqueue(sch, dsq, p, enq_flags);
 }
 
@@ -1610,6 +1615,7 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags
 	sub_nr_running(rq, 1);
 
 	dispatch_dequeue(rq, p);
+	clear_direct_dispatch(p);
 	return true;
 }
 
@@ -2293,13 +2299,15 @@ static void process_ddsp_deferred_locals(struct rq *rq)
 				struct task_struct, scx.dsq_list.node))) {
 		struct scx_sched *sch = scx_root;
 		struct scx_dispatch_q *dsq;
+		u64 dsq_id = p->scx.ddsp_dsq_id;
+		u64 enq_flags = p->scx.ddsp_enq_flags;
 
 		list_del_init(&p->scx.dsq_list.node);
+		clear_direct_dispatch(p);
 
-		dsq = find_dsq_for_dispatch(sch, rq, p->scx.ddsp_dsq_id, p);
+		dsq = find_dsq_for_dispatch(sch, rq, dsq_id, p);
 		if (!WARN_ON_ONCE(dsq->id != SCX_DSQ_LOCAL))
-			dispatch_to_local_dsq(sch, rq, dsq, p,
-					      p->scx.ddsp_enq_flags);
+			dispatch_to_local_dsq(sch, rq, dsq, p, enq_flags);
 	}
 }
 
@@ -3147,6 +3155,8 @@ static bool task_dead_and_done(struct task_struct *p)
 
 	lockdep_assert_rq_held(rq);
 
+	clear_direct_dispatch(p);
+
 	/*
 	 * In do_task_dead(), a dying task sets %TASK_DEAD with preemption
 	 * disabled and __schedule(). If @p has %TASK_DEAD set and off CPU, @p
-- 
2.53.0