sched_ext: Fix stale direct dispatch state in ddsp_dsq_id

commit 7e0ffb72de8aa3b25989c2d980e81b829c577010 upstream.

@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.

Fix it by clearing 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,
   any subsequent SCX scheduler that tries to direct dispatch the task
   will trigger the WARN_ON_ONCE() in mark_direct_dispatch().

Fixes: 5b26f7b920f7 ("sched_ext: Allow SCX_DSQ_LOCAL_ON for direct dispatches")
Cc: stable@vger.kernel.org # v6.12+
Cc: Daniel Hodges <hodgesd@meta.com>
Cc: Patrick Somaru <patsomaru@meta.com>
Signed-off-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 35 insertions, 14 deletions

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index ee761650608b..35fa2970abac 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -1104,15 +1104,6 @@ static void dispatch_enqueue(struct scx_sched *sch, struct scx_dispatch_q *dsq,
 	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.
 	 */
@@ -1277,12 +1268,34 @@ static void mark_direct_dispatch(struct scx_sched *sch,
 	p->scx.ddsp_enq_flags = enq_flags;
 }
 
+/*
+ * Clear @p direct dispatch state when leaving the scheduler.
+ *
+ * Direct dispatch state must be cleared in the following cases:
+ *  - direct_dispatch(): cleared on the synchronous enqueue path, deferred
+ *    dispatch keeps the state until consumed
+ *  - process_ddsp_deferred_locals(): cleared after consuming deferred state,
+ *  - do_enqueue_task(): cleared on enqueue fallbacks where the dispatch
+ *    verdict is ignored (local/global/bypass)
+ *  - dequeue_task_scx(): cleared after dispatch_dequeue(), covering deferred
+ *    cancellation and holding_cpu races
+ *  - scx_disable_task(): cleared for queued wakeup tasks, which are excluded by
+ *    the scx_bypass() loop, so that stale state is not reused by a subsequent
+ *    scheduler instance
+ */
+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 ddsp_enq_flags;
 
 	touch_core_sched_dispatch(rq, p);
 
@@ -1323,8 +1336,10 @@ 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);
+	ddsp_enq_flags = p->scx.ddsp_enq_flags;
+	clear_direct_dispatch(p);
+
+	dispatch_enqueue(sch, dsq, p, ddsp_enq_flags | SCX_ENQ_CLEAR_OPSS);
 }
 
 static bool scx_rq_online(struct rq *rq)
@@ -1433,6 +1448,7 @@ enqueue:
 	 */
 	touch_core_sched(rq, p);
 	refill_task_slice_dfl(sch, p);
+	clear_direct_dispatch(p);
 	dispatch_enqueue(sch, dsq, p, enq_flags);
 }
 
@@ -1600,6 +1616,7 @@ 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;
 }
 
@@ -2283,13 +2300,15 @@ 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);
 	}
 }
 
@@ -2978,6 +2997,8 @@ static void scx_disable_task(struct task_struct *p)
 	lockdep_assert_rq_held(rq);
 	WARN_ON_ONCE(scx_get_task_state(p) != SCX_TASK_ENABLED);
 
+	clear_direct_dispatch(p);
+
 	if (SCX_HAS_OP(sch, disable))
 		SCX_CALL_OP_TASK(sch, SCX_KF_REST, disable, rq, p);
 	scx_set_task_state(p, SCX_TASK_READY);