sched_ext: Introduce scx_bpf_cpu_curr()

Provide scx_bpf_cpu_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>
Acked-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index a319ea5bb25a3d1353a5396b8f86edcd773ecc7b..4bd9b491b376acc6773fbb8c293398fe65755c0c 100644 (file)
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -6379,6 +6379,19 @@ __bpf_kfunc struct rq *scx_bpf_locked_rq(void)
        return rq;
 }
 
+/**
+ * scx_bpf_cpu_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_cpu_curr(s32 cpu)
+{
+       if (!kf_cpu_valid(cpu, NULL))
+               return NULL;
+       return rcu_dereference(cpu_rq(cpu)->curr);
+}
+
 /**
  * scx_bpf_task_cgroup - Return the sched cgroup of a task
  * @p: task of interest
@@ -6544,6 +6557,7 @@ 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_locked_rq, KF_RET_NULL)
+BTF_ID_FLAGS(func, scx_bpf_cpu_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 e2a57b7458625b60423c4dd3cd90cc857707a73a..342c7c48df5ab6adf1e25507a4f3d6802ef7310c 100644 (file)
--- a/tools/sched_ext/include/scx/common.bpf.h
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -104,6 +104,7 @@ 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_locked_rq(void) __ksym;
+struct task_struct *scx_bpf_cpu_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;