Provide scx_bpf_remote_curr() as a way for scx schedulers to
check the curr task of a remote rq, without assuming its lock
or acquiring any.

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                       | 15 +++++++++++++++
 tools/sched_ext/include/scx/common.bpf.h |  1 +
 2 files changed, 16 insertions(+)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index b734f55f3318..92e66bb0b5f2 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -7436,6 +7436,20 @@ __bpf_kfunc struct rq *scx_bpf_cpu_rq(s32 cpu)
 	return cpu_rq(cpu);
 }
 
+/**
+ * scx_bpf_remote_curr - Fetch the curr of a rq without acquiring its rq lock
+ * @cpu: CPU of the rq
+ *
+ * Neither a rq lock nor a task reference is acquired.
+ */
+__bpf_kfunc struct task_struct *scx_bpf_remote_curr(s32 cpu)
+{
+	if (!kf_cpu_valid(cpu, NULL))
+		return NULL;
+
+	return cpu_rq(cpu)->curr;
+}
+
 /**
  * scx_bpf_task_cgroup - Return the sched cgroup of a task
  * @p: task of interest
@@ -7600,6 +7614,7 @@ BTF_ID_FLAGS(func, scx_bpf_put_cpumask, KF_RELEASE)
 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, KF_RET_NULL)
+BTF_ID_FLAGS(func, scx_bpf_remote_curr, KF_RET_NULL)
 #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 d4e21558e982..e5d4ef124532 100644
--- a/tools/sched_ext/include/scx/common.bpf.h
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -91,6 +91,7 @@ s32 scx_bpf_pick_any_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym;
 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 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

On Fri, Aug 01, 2025 at 03:17:40PM +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
> or acquiring any.
> 
> 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                       | 15 +++++++++++++++
>  tools/sched_ext/include/scx/common.bpf.h |  1 +
>  2 files changed, 16 insertions(+)
> 
> diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
> index b734f55f3318..92e66bb0b5f2 100644
> --- a/kernel/sched/ext.c
> +++ b/kernel/sched/ext.c
> @@ -7436,6 +7436,20 @@ __bpf_kfunc struct rq *scx_bpf_cpu_rq(s32 cpu)
>  	return cpu_rq(cpu);
>  }
>  
> +/**
> + * scx_bpf_remote_curr - Fetch the curr of a rq without acquiring its rq lock
> + * @cpu: CPU of the rq
> + *
> + * Neither a rq lock nor a task reference is acquired.
> + */
> +__bpf_kfunc struct task_struct *scx_bpf_remote_curr(s32 cpu)
> +{
> +	if (!kf_cpu_valid(cpu, NULL))
> +		return NULL;
> +
> +	return cpu_rq(cpu)->curr;
> +}

As mentioned in my previou comment, this should be something like:

 if (!kf_cpu_valid(cpu, NULL))
 	return NULL;

 rcu_read_lock();
 p = cpu_rq(cpu)->curr;
 if (p)
 	p = bpf_task_acquire(p);
 rcu_read_unlock();

 return p;

We may still race with CPU hotplugging, but I think it's not always
possible to use cpus_read_lock/unlock() here. Also, most of the scx
schedulers are restarted on CPU hotplugging events, so... one thing at a
time. :)

> +
>  /**
>   * scx_bpf_task_cgroup - Return the sched cgroup of a task
>   * @p: task of interest
> @@ -7600,6 +7614,7 @@ BTF_ID_FLAGS(func, scx_bpf_put_cpumask, KF_RELEASE)
>  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, KF_RET_NULL)
> +BTF_ID_FLAGS(func, scx_bpf_remote_curr, KF_RET_NULL)
>  #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 d4e21558e982..e5d4ef124532 100644
> --- a/tools/sched_ext/include/scx/common.bpf.h
> +++ b/tools/sched_ext/include/scx/common.bpf.h
> @@ -91,6 +91,7 @@ s32 scx_bpf_pick_any_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym;
>  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 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
> 

-Andrea

On 8/1/25 15:47, Andrea Righi wrote:
> On Fri, Aug 01, 2025 at 03:17:40PM +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
>> or acquiring any.
>>
>> 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                       | 15 +++++++++++++++
>>  tools/sched_ext/include/scx/common.bpf.  |  1 +
>>  2 files changed, 16 insertions(+)
>>
>> diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
>> index b734f55f3318..92e66bb0b5f2 100644
>> --- a/kernel/sched/ext.c
>> +++ b/kernel/sched/ext.c
>> @@ -7436,6 +7436,20 @@ __bpf_kfunc struct rq *scx_bpf_cpu_rq(s32 cpu)
>>  	return cpu_rq(cpu);
>>  }
>>  
>> +/**
>> + * scx_bpf_remote_curr - Fetch the curr of a rq without acquiring its rq lock
>> + * @cpu: CPU of the rq
>> + *
>> + * Neither a rq lock nor a task reference is acquired.
>> + */
>> +__bpf_kfunc struct task_struct *scx_bpf_remote_curr(s32 cpu)
>> +{
>> +	if (!kf_cpu_valid(cpu, NULL))
>> +		return NULL;
>> +
>> +	return cpu_rq(cpu)->curr;
>> +}
> 
> As mentioned in my previou comment, this should be something like:
> 
>  if (!kf_cpu_valid(cpu, NULL))
>  	return NULL;
> 
>  rcu_read_lock();
>  p = cpu_rq(cpu)->curr;
>  if (p)
>  	p = bpf_task_acquire(p);
>  rcu_read_unlock();
> 
>  return p;

Alright, that's actually what I had at first, but went with the
drop-in-replacement that doesn't acquire.
I'll resend with an acquire.
Thanks, Andrea!

> 
> We may still race with CPU hotplugging, but I think it's not always
> possible to use cpus_read_lock/unlock() here. Also, most of the scx
> schedulers are restarted on CPU hotplugging events, so... one thing at a
> time. :)
> 
>> +
>>  /**
>>   * scx_bpf_task_cgroup - Return the sched cgroup of a task
>>   * @p: task of interest
>> @@ -7600,6 +7614,7 @@ BTF_ID_FLAGS(func, scx_bpf_put_cpumask, KF_RELEASE)
>>  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, KF_RET_NULL)
>> +BTF_ID_FLAGS(func, scx_bpf_remote_curr, KF_RET_NULL)
>>  #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 d4e21558e982..e5d4ef124532 100644
>> --- a/tools/sched_ext/include/scx/common.bpf.h
>> +++ b/tools/sched_ext/include/scx/common.bpf.h
>> @@ -91,6 +91,7 @@ s32 scx_bpf_pick_any_cpu(const cpumask_t *cpus_allowed, u64 flags) __ksym;
>>  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 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
>>
> 
> -Andrea