The BUILD_BUG_ON() which checks that __SCX_DSQ_ITER_ALL_FLAGS doesn't
overlap with the private lnode bits was in scx_task_iter_start() which has
nothing to do with DSQ iteration. Move it to bpf_iter_scx_dsq_new() where it
belongs.

No functional changes.

Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -474,9 +474,6 @@ struct scx_task_iter {
  */
 static void scx_task_iter_start(struct scx_task_iter *iter)
 {
-	BUILD_BUG_ON(__SCX_DSQ_ITER_ALL_FLAGS &
-		     ((1U << __SCX_DSQ_LNODE_PRIV_SHIFT) - 1));
-
 	spin_lock_irq(&scx_tasks_lock);

 	iter->cursor = (struct sched_ext_entity){ .flags = SCX_TASK_CURSOR };
@@ -6218,6 +6215,8 @@ __bpf_kfunc int bpf_iter_scx_dsq_new(str
 		     sizeof(struct bpf_iter_scx_dsq));
 	BUILD_BUG_ON(__alignof__(struct bpf_iter_scx_dsq_kern) !=
 		     __alignof__(struct bpf_iter_scx_dsq));
+	BUILD_BUG_ON(__SCX_DSQ_ITER_ALL_FLAGS &
+		     ((1U << __SCX_DSQ_LNODE_PRIV_SHIFT) - 1));

 	/*
 	 * next() and destroy() will be called regardless of the return value.

> Tejun Heo (2):
>   sched_ext: Move __SCX_DSQ_ITER_ALL_FLAGS BUILD_BUG_ON to the right place
>   sched_ext: Minor cleanups to scx_task_iter

Applied 1-2 to sched_ext/for-6.19.

Thanks.
--
tejun

On Tue, Nov 04, 2025 at 11:40:22AM -1000, Tejun Heo wrote:
> The BUILD_BUG_ON() which checks that __SCX_DSQ_ITER_ALL_FLAGS doesn't
> overlap with the private lnode bits was in scx_task_iter_start() which has
> nothing to do with DSQ iteration. Move it to bpf_iter_scx_dsq_new() where it
> belongs.
> 
> No functional changes.
> 
> Signed-off-by: Tejun Heo <tj@kernel.org>

Looks good (both patches)

Acked-by: Andrea Righi <arighi@nvidia.com>

Thanks,
-Andrea

> ---
>  kernel/sched/ext.c |    5 ++---
>  1 file changed, 2 insertions(+), 3 deletions(-)
> 
> --- a/kernel/sched/ext.c
> +++ b/kernel/sched/ext.c
> @@ -474,9 +474,6 @@ struct scx_task_iter {
>   */
>  static void scx_task_iter_start(struct scx_task_iter *iter)
>  {
> -	BUILD_BUG_ON(__SCX_DSQ_ITER_ALL_FLAGS &
> -		     ((1U << __SCX_DSQ_LNODE_PRIV_SHIFT) - 1));
> -
>  	spin_lock_irq(&scx_tasks_lock);
> 
>  	iter->cursor = (struct sched_ext_entity){ .flags = SCX_TASK_CURSOR };
> @@ -6218,6 +6215,8 @@ __bpf_kfunc int bpf_iter_scx_dsq_new(str
>  		     sizeof(struct bpf_iter_scx_dsq));
>  	BUILD_BUG_ON(__alignof__(struct bpf_iter_scx_dsq_kern) !=
>  		     __alignof__(struct bpf_iter_scx_dsq));
> +	BUILD_BUG_ON(__SCX_DSQ_ITER_ALL_FLAGS &
> +		     ((1U << __SCX_DSQ_LNODE_PRIV_SHIFT) - 1));
> 
>  	/*
>  	 * next() and destroy() will be called regardless of the return value.

- Use memset() in scx_task_iter_start() instead of zeroing fields individually.

- In scx_task_iter_next(), move __scx_task_iter_maybe_relock() after the batch
  check which is simpler.

- Update comment to reflect that tasks are removed from scx_tasks when dead
  (commit 7900aa699c34 ("sched_ext: Fix cgroup exit ordering by moving
  sched_ext_free() to finish_task_switch()")).

No functional changes.

Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c |   11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -470,16 +470,16 @@ struct scx_task_iter {
  * RCU read lock or obtaining a reference count.
  *
  * All tasks which existed when the iteration started are guaranteed to be
- * visited as long as they still exist.
+ * visited as long as they are not dead.
  */
 static void scx_task_iter_start(struct scx_task_iter *iter)
 {
+	memset(iter, 0, sizeof(*iter));
+
 	spin_lock_irq(&scx_tasks_lock);

 	iter->cursor = (struct sched_ext_entity){ .flags = SCX_TASK_CURSOR };
 	list_add(&iter->cursor.tasks_node, &scx_tasks);
-	iter->locked_task = NULL;
-	iter->cnt = 0;
 	iter->list_locked = true;
 }

@@ -545,14 +545,13 @@ static struct task_struct *scx_task_iter
 	struct list_head *cursor = &iter->cursor.tasks_node;
 	struct sched_ext_entity *pos;

-	__scx_task_iter_maybe_relock(iter);
-
 	if (!(++iter->cnt % SCX_TASK_ITER_BATCH)) {
 		scx_task_iter_unlock(iter);
 		cond_resched();
-		__scx_task_iter_maybe_relock(iter);
 	}

+	__scx_task_iter_maybe_relock(iter);
+
 	list_for_each_entry(pos, cursor, tasks_node) {
 		if (&pos->tasks_node == &scx_tasks)
 			return NULL;