Provide scx_bpf_remote_curr() as a way for scx schedulers to check the curr
task of a remote rq without assuming its lock is held.

Many scx schedulers make use of scx_bpf_cpu_rq() to check a remote curr
(e.g. to see if it should be preempted). This is problematic because
scx_bpf_cpu_rq() provides access to all fields of struct rq, most of
which aren't safe to use without holding the associated rq lock.

Signed-off-by: Christian Loehle <christian.loehle@arm.com>
---
 kernel/sched/ext.c                       | 14 ++++++++++++++
 tools/sched_ext/include/scx/common.bpf.h |  1 +
 2 files changed, 15 insertions(+)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 9fcc310d85d5..e242a2520f06 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -7452,6 +7452,19 @@ __bpf_kfunc struct rq *scx_bpf_cpu_rq_locked(void)
 	return rq;
 }
 
+/**
+ * scx_bpf_remote_curr - Return remote CPU's curr task
+ * @cpu: CPU of interest
+ *
+ * Callers must hold RCU read lock (KF_RCU).
+ */
+__bpf_kfunc struct task_struct *scx_bpf_remote_curr(s32 cpu)
+{
+	if (!kf_cpu_valid(cpu, NULL))
+		return NULL;
+	return READ_ONCE(cpu_rq(cpu)->curr);
+}
+
 /**
  * scx_bpf_task_cgroup - Return the sched cgroup of a task
  * @p: task of interest
@@ -7617,6 +7630,7 @@ BTF_ID_FLAGS(func, scx_bpf_task_running, KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_task_cpu, KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_cpu_rq)
 BTF_ID_FLAGS(func, scx_bpf_cpu_rq_locked, KF_RET_NULL)
+BTF_ID_FLAGS(func, scx_bpf_remote_curr, KF_RET_NULL | KF_RCU)
 #ifdef CONFIG_CGROUP_SCHED
 BTF_ID_FLAGS(func, scx_bpf_task_cgroup, KF_RCU | KF_ACQUIRE)
 #endif
diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
index f5be06c93359..dd3d94256c10 100644
--- a/tools/sched_ext/include/scx/common.bpf.h
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -92,6 +92,7 @@ bool scx_bpf_task_running(const struct task_struct *p) __ksym;
 s32 scx_bpf_task_cpu(const struct task_struct *p) __ksym;
 struct rq *scx_bpf_cpu_rq(s32 cpu) __ksym;
 struct rq *scx_bpf_cpu_rq_locked(void) __ksym;
+struct task_struct *scx_bpf_remote_curr(s32 cpu) __ksym;
 struct cgroup *scx_bpf_task_cgroup(struct task_struct *p) __ksym __weak;
 u64 scx_bpf_now(void) __ksym __weak;
 void scx_bpf_events(struct scx_event_stats *events, size_t events__sz) __ksym __weak;
-- 
2.34.1

Hello,

On Mon, Sep 01, 2025 at 02:26:03PM +0100, Christian Loehle wrote:
> +/**
> + * scx_bpf_remote_curr - Return remote CPU's curr task
> + * @cpu: CPU of interest
> + *
> + * Callers must hold RCU read lock (KF_RCU).
> + */
> +__bpf_kfunc struct task_struct *scx_bpf_remote_curr(s32 cpu)

And name this scx_bpf_cpu_curr().

Thanks.

-- 
tejun

Hi Christian,

On Mon, Sep 01, 2025 at 02:26:03PM +0100, Christian Loehle wrote:
> Provide scx_bpf_remote_curr() as a way for scx schedulers to check the curr
> task of a remote rq without assuming its lock is held.
> 
> Many scx schedulers make use of scx_bpf_cpu_rq() to check a remote curr
> (e.g. to see if it should be preempted). This is problematic because
> scx_bpf_cpu_rq() provides access to all fields of struct rq, most of
> which aren't safe to use without holding the associated rq lock.
> 
> Signed-off-by: Christian Loehle <christian.loehle@arm.com>
> ---
>  kernel/sched/ext.c                       | 14 ++++++++++++++
>  tools/sched_ext/include/scx/common.bpf.h |  1 +
>  2 files changed, 15 insertions(+)
> 
> diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
> index 9fcc310d85d5..e242a2520f06 100644
> --- a/kernel/sched/ext.c
> +++ b/kernel/sched/ext.c
> @@ -7452,6 +7452,19 @@ __bpf_kfunc struct rq *scx_bpf_cpu_rq_locked(void)
>  	return rq;
>  }
>  
> +/**
> + * scx_bpf_remote_curr - Return remote CPU's curr task
> + * @cpu: CPU of interest
> + *
> + * Callers must hold RCU read lock (KF_RCU).
> + */
> +__bpf_kfunc struct task_struct *scx_bpf_remote_curr(s32 cpu)
> +{
> +	if (!kf_cpu_valid(cpu, NULL))
> +		return NULL;
> +	return READ_ONCE(cpu_rq(cpu)->curr);

It shouldn't be rcu_dereference(cpu_rq(cpu)->curr)?

Thanks,
-Andrea

> +}
> +
>  /**
>   * scx_bpf_task_cgroup - Return the sched cgroup of a task
>   * @p: task of interest
> @@ -7617,6 +7630,7 @@ BTF_ID_FLAGS(func, scx_bpf_task_running, KF_RCU)
>  BTF_ID_FLAGS(func, scx_bpf_task_cpu, KF_RCU)
>  BTF_ID_FLAGS(func, scx_bpf_cpu_rq)
>  BTF_ID_FLAGS(func, scx_bpf_cpu_rq_locked, KF_RET_NULL)
> +BTF_ID_FLAGS(func, scx_bpf_remote_curr, KF_RET_NULL | KF_RCU)
>  #ifdef CONFIG_CGROUP_SCHED
>  BTF_ID_FLAGS(func, scx_bpf_task_cgroup, KF_RCU | KF_ACQUIRE)
>  #endif
> diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
> index f5be06c93359..dd3d94256c10 100644
> --- a/tools/sched_ext/include/scx/common.bpf.h
> +++ b/tools/sched_ext/include/scx/common.bpf.h
> @@ -92,6 +92,7 @@ bool scx_bpf_task_running(const struct task_struct *p) __ksym;
>  s32 scx_bpf_task_cpu(const struct task_struct *p) __ksym;
>  struct rq *scx_bpf_cpu_rq(s32 cpu) __ksym;
>  struct rq *scx_bpf_cpu_rq_locked(void) __ksym;
> +struct task_struct *scx_bpf_remote_curr(s32 cpu) __ksym;
>  struct cgroup *scx_bpf_task_cgroup(struct task_struct *p) __ksym __weak;
>  u64 scx_bpf_now(void) __ksym __weak;
>  void scx_bpf_events(struct scx_event_stats *events, size_t events__sz) __ksym __weak;
> -- 
> 2.34.1
>