Commit 03f5304a authored by Andrea Righi's avatar Andrea Righi Committed by Tejun Heo
Browse files

sched_ext: Pass full dequeue flags to ops.quiescent() 



ops.quiescent() is invoked with the same deq_flags as ops.dequeue(), so
the BPF scheduler is able to distinguish sleep vs property changes in
both callbacks.

However, dequeue_task_scx() receives deq_flags as an int from the
sched_class interface, so SCX flags above bit 32 (%SCX_DEQ_SCHED_CHANGE)
are truncated. ops_dequeue() reconstructs the full u64 for ops.dequeue(),
but ops.quiescent() is still called with the original int and can never
see %SCX_DEQ_SCHED_CHANGE.

Fix this by constructing the full u64 deq_flags in dequeue_task_scx()
(renaming the int parameter to core_deq_flags) and passing the complete
flags to both ops_dequeue() and ops.quiescent().

Fixes: ebf1ccff ("sched_ext: Fix ops.dequeue() semantics")
Signed-off-by: default avatarAndrea Righi <arighi@nvidia.com>
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
parent f68971bc

kernel/sched/ext.c

+10 −10
Original line number Diff line number Diff line
@@ -1782,14 +1782,6 @@ static void ops_dequeue(struct rq *rq, struct task_struct *p, u64 deq_flags) 
{

	struct scx_sched *sch = scx_task_sched(p);

	unsigned long opss;

	u64 op_deq_flags = deq_flags;



	/*

	 * Set %SCX_DEQ_SCHED_CHANGE when the dequeue is due to a property

	 * change (not sleep or core-sched pick).

	 */

	if (!(op_deq_flags & (DEQUEUE_SLEEP | SCX_DEQ_CORE_SCHED_EXEC)))

		op_deq_flags |= SCX_DEQ_SCHED_CHANGE;



	/* dequeue is always temporary, don't reset runnable_at */

	clr_task_runnable(p, false);
@@ -1846,12 +1838,20 @@ static void ops_dequeue(struct rq *rq, struct task_struct *p, u64 deq_flags) 
	 * NONE but the task may still have %SCX_TASK_IN_CUSTODY set until

	 * it is enqueued on the destination.

	 */

	call_task_dequeue(sch, rq, p, op_deq_flags);

	call_task_dequeue(sch, rq, p, deq_flags);

}



static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags)

static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int core_deq_flags)

{

	struct scx_sched *sch = scx_task_sched(p);

	u64 deq_flags = core_deq_flags;



	/*

	 * Set %SCX_DEQ_SCHED_CHANGE when the dequeue is due to a property

	 * change (not sleep or core-sched pick).

	 */

	if (!(deq_flags & (DEQUEUE_SLEEP | SCX_DEQ_CORE_SCHED_EXEC)))

		deq_flags |= SCX_DEQ_SCHED_CHANGE;



	if (!(p->scx.flags & SCX_TASK_QUEUED)) {

		WARN_ON_ONCE(task_runnable(p));