Re: [PATCH 2/2] sched_ext: Update demo schedulers and selftests to drop ops.cpu_acquire/release()

[Andrea Righi <arighi@nvidia.com>]

Hi Cheng-Yang,

On Thu, Mar 12, 2026 at 12:20:01PM +0800, Cheng-Yang Chou wrote:
> ops.cpu_acquire() and ops.cpu_release() are deprecated in favor of
> handling CPU preemption via the sched_switch tracepoint. Update scx_qmap
> and the maximal selftest to use the new approach.

We could mention that commit a3f5d4822253 ("sched_ext: Allow
scx_bpf_reenqueue_local() to be called from anywhere") is deprecating
ops.cpu_acquire/relese().

> 
> In scx_qmap, remove the cpu_release fallback and the
> __COMPAT_scx_bpf_reenqueue_local_from_anywhere() compat guard from
> qmap_sched_switch(), unconditionally handling preemption via the TP.
> 
> In the maximal selftest, replace the cpu_acquire and cpu_release stubs
> with a minimal sched_switch TP program.
> 
> Signed-off-by: Cheng-Yang Chou <yphbchou0911@gmail.com>
> ---
>  tools/sched_ext/scx_qmap.bpf.c                  | 15 ++-------------
>  tools/testing/selftests/sched_ext/maximal.bpf.c | 15 ++++++---------
>  2 files changed, 8 insertions(+), 22 deletions(-)
> 
> diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
> index a4a1b84fe359..a11e27c8de77 100644
> --- a/tools/sched_ext/scx_qmap.bpf.c
> +++ b/tools/sched_ext/scx_qmap.bpf.c
> @@ -11,8 +11,8 @@
>   *
>   * - BPF-side queueing using PIDs.
>   * - Sleepable per-task storage allocation using ops.prep_enable().
> - * - Using ops.cpu_release() to handle a higher priority scheduling class taking
> - *   the CPU away.
> + * - Using the sched_switch tracepoint to handle a higher priority scheduling
> + *   class taking the CPU away.
>   * - Core-sched support.
>   *
>   * This scheduler is primarily for demonstration and testing of sched_ext
> @@ -562,9 +562,6 @@ SEC("tp_btf/sched_switch")
>  int BPF_PROG(qmap_sched_switch, bool preempt, struct task_struct *prev,
>  	     struct task_struct *next, unsigned long prev_state)
>  {
> -	if (!__COMPAT_scx_bpf_reenqueue_local_from_anywhere())
> -		return 0;
> -
>  	/*
>  	 * If @cpu is taken by a higher priority scheduling class, it is no
>  	 * longer available for executing sched_ext tasks. As we don't want the
> @@ -586,13 +583,6 @@ int BPF_PROG(qmap_sched_switch, bool preempt, struct task_struct *prev,
>  	return 0;
>  }
>  
> -void BPF_STRUCT_OPS(qmap_cpu_release, s32 cpu, struct scx_cpu_release_args *args)
> -{
> -	/* see qmap_sched_switch() to learn how to do this on newer kernels */
> -	if (!__COMPAT_scx_bpf_reenqueue_local_from_anywhere())
> -		scx_bpf_reenqueue_local();
> -}
> -
>  s32 BPF_STRUCT_OPS(qmap_init_task, struct task_struct *p,
>  		   struct scx_init_task_args *args)
>  {
> @@ -999,7 +989,6 @@ SCX_OPS_DEFINE(qmap_ops,
>  	       .dispatch		= (void *)qmap_dispatch,
>  	       .tick			= (void *)qmap_tick,
>  	       .core_sched_before	= (void *)qmap_core_sched_before,
> -	       .cpu_release		= (void *)qmap_cpu_release,
>  	       .init_task		= (void *)qmap_init_task,
>  	       .dump			= (void *)qmap_dump,
>  	       .dump_cpu		= (void *)qmap_dump_cpu,
> diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c
> index 01cf4f3da4e0..5858f64313e9 100644
> --- a/tools/testing/selftests/sched_ext/maximal.bpf.c
> +++ b/tools/testing/selftests/sched_ext/maximal.bpf.c
> @@ -67,13 +67,12 @@ void BPF_STRUCT_OPS(maximal_set_cpumask, struct task_struct *p,
>  void BPF_STRUCT_OPS(maximal_update_idle, s32 cpu, bool idle)
>  {}
>  
> -void BPF_STRUCT_OPS(maximal_cpu_acquire, s32 cpu,
> -		    struct scx_cpu_acquire_args *args)
> -{}
> -
> -void BPF_STRUCT_OPS(maximal_cpu_release, s32 cpu,
> -		    struct scx_cpu_release_args *args)
> -{}
> +SEC("tp_btf/sched_switch")
> +int BPF_PROG(maximal_sched_switch, bool preempt, struct task_struct *prev,
> +	     struct task_struct *next, unsigned long prev_state)
> +{
> +	return 0;
> +}

I think this tracepoint is never attached. You can verify it by adding a
bpf_printk("hello") here and check if you see any message in
/sys/kernel/tracing/trace_pipe.

To attach this TP you need to do something like this:

diff --git a/tools/testing/selftests/sched_ext/maximal.c b/tools/testing/selftests/sched_ext/maximal.c
index c6be50a9941d5..1dc3692246705 100644
--- a/tools/testing/selftests/sched_ext/maximal.c
+++ b/tools/testing/selftests/sched_ext/maximal.c
@@ -19,6 +19,9 @@ static enum scx_test_status setup(void **ctx)
 	SCX_ENUM_INIT(skel);
 	SCX_FAIL_IF(maximal__load(skel), "Failed to load skel");
 
+	bpf_map__set_autoattach(skel->maps.maximal_ops, false);
+	SCX_FAIL_IF(maximal__attach(skel), "Failed to attach skel");
+
 	*ctx = skel;
 
 	return SCX_TEST_PASS;
diff --git a/tools/testing/selftests/sched_ext/reload_loop.c b/tools/testing/selftests/sched_ext/reload_loop.c
index 308211d804364..49297b83d748d 100644
--- a/tools/testing/selftests/sched_ext/reload_loop.c
+++ b/tools/testing/selftests/sched_ext/reload_loop.c
@@ -23,6 +23,9 @@ static enum scx_test_status setup(void **ctx)
 	SCX_ENUM_INIT(skel);
 	SCX_FAIL_IF(maximal__load(skel), "Failed to load skel");
 
+	bpf_map__set_autoattach(skel->maps.maximal_ops, false);
+	SCX_FAIL_IF(maximal__attach(skel), "Failed to attach skel");
+
 	return SCX_TEST_PASS;
 }
 
>  
>  void BPF_STRUCT_OPS(maximal_cpu_online, s32 cpu)
>  {}
> @@ -150,8 +149,6 @@ struct sched_ext_ops maximal_ops = {
>  	.set_weight		= (void *) maximal_set_weight,
>  	.set_cpumask		= (void *) maximal_set_cpumask,
>  	.update_idle		= (void *) maximal_update_idle,
> -	.cpu_acquire		= (void *) maximal_cpu_acquire,
> -	.cpu_release		= (void *) maximal_cpu_release,
>  	.cpu_online		= (void *) maximal_cpu_online,
>  	.cpu_offline		= (void *) maximal_cpu_offline,
>  	.init_task		= (void *) maximal_init_task,
> -- 
> 2.48.1
> 

Thanks,
-Andrea