Provide scx_bpf_task_acquire_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                       | 24 ++++++++++++++++++++++++
 tools/sched_ext/include/scx/common.bpf.h |  1 +
 2 files changed, 25 insertions(+)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 3ea3f0f18030..3e2fa0b1eb57 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -7426,6 +7426,29 @@ __bpf_kfunc struct rq *scx_bpf_cpu_rq(s32 cpu)
 	return cpu_rq(cpu);
 }
 
+/**
+ * scx_bpf_task_acquire_remote_curr - Fetch the curr task of a rq without
+ * acquiring its rq lock
+ * @cpu: CPU of the rq
+ *
+ * Increments the refcount of the task_struct which needs to be released using
+ * bpf_task_release().
+ */
+__bpf_kfunc struct task_struct *scx_bpf_task_acquire_remote_curr(s32 cpu)
+{
+	struct task_struct *p;
+
+	if (!kf_cpu_valid(cpu, NULL))
+		return NULL;
+
+	rcu_read_lock();
+	p = cpu_rq(cpu)->curr;
+	if (p)
+		p = refcount_inc_not_zero(&p->rcu_users) ? p : NULL;
+	rcu_read_unlock();
+	return p;
+}
+
 /**
  * scx_bpf_task_cgroup - Return the sched cgroup of a task
  * @p: task of interest
@@ -7590,6 +7613,7 @@ 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_task_acquire_remote_curr, KF_RET_NULL | KF_ACQUIRE)
 #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..bdd68f3100b7 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_task_acquire_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 Tue, Aug 05, 2025 at 12:10:35PM +0100, Christian Loehle wrote:
> Provide scx_bpf_task_acquire_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>

Applied 1-2 to sched_ext/for-6.17-fixes.

Thanks.

-- 
tejun

On Sat, Aug 09, 2025 at 09:01:18AM -1000, Tejun Heo wrote:
> On Tue, Aug 05, 2025 at 12:10:35PM +0100, Christian Loehle wrote:
> > Provide scx_bpf_task_acquire_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>
> 
> Applied 1-2 to sched_ext/for-6.17-fixes.

Reverted due to compatibility issues. Let's try again with warnings as
discussed in the other subthread.

Thanks.

-- 
tejun