sched_ext: Drop TRACING access to select_cpu kfuncs

The select_cpu kfuncs - scx_bpf_select_cpu_dfl(), scx_bpf_select_cpu_and()
and __scx_bpf_select_cpu_and() - take task_rq_lock() internally. Exposing
them via scx_kfunc_set_idle to BPF_PROG_TYPE_TRACING is unsafe: arbitrary
tracing contexts (kprobes, tracepoints, fentry, LSM) may run with @p's
pi_lock state unknown.

Move them out of scx_kfunc_ids_idle into a new scx_kfunc_ids_select_cpu
set registered only for STRUCT_OPS and SYSCALL.

Extracted from a larger verifier-time kfunc context filter patch
originally written by Juntong Deng.

Original-patch-by: Juntong Deng <juntong.deng@outlook.com>
Cc: Cheng-Yang Chou <yphbchou0911@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>

diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c
index ecf7e09b54ae6dd6adcf1243cdf64cfe1e743233..cd88aee47bd81f6e5be6a5acec2e65af261f9fce 100644 (file)
--- a/kernel/sched/ext_idle.c
+++ b/kernel/sched/ext_idle.c
@@ -1469,9 +1469,6 @@ BTF_ID_FLAGS(func, scx_bpf_pick_idle_cpu_node, KF_IMPLICIT_ARGS | KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_pick_idle_cpu, KF_IMPLICIT_ARGS | KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_pick_any_cpu_node, KF_IMPLICIT_ARGS | KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_pick_any_cpu, KF_IMPLICIT_ARGS | KF_RCU)
-BTF_ID_FLAGS(func, __scx_bpf_select_cpu_and, KF_IMPLICIT_ARGS | KF_RCU)
-BTF_ID_FLAGS(func, scx_bpf_select_cpu_and, KF_RCU)
-BTF_ID_FLAGS(func, scx_bpf_select_cpu_dfl, KF_IMPLICIT_ARGS | KF_RCU)
 BTF_KFUNCS_END(scx_kfunc_ids_idle)
 
 static const struct btf_kfunc_id_set scx_kfunc_set_idle = {
@@ -1479,13 +1476,33 @@ static const struct btf_kfunc_id_set scx_kfunc_set_idle = {
        .set                    = &scx_kfunc_ids_idle,
 };
 
+/*
+ * The select_cpu kfuncs internally call task_rq_lock() when invoked from an
+ * rq-unlocked context, and thus cannot be safely called from arbitrary tracing
+ * contexts where @p's pi_lock state is unknown. Keep them out of
+ * BPF_PROG_TYPE_TRACING by registering them in their own set which is exposed
+ * only to STRUCT_OPS and SYSCALL programs.
+ */
+BTF_KFUNCS_START(scx_kfunc_ids_select_cpu)
+BTF_ID_FLAGS(func, __scx_bpf_select_cpu_and, KF_IMPLICIT_ARGS | KF_RCU)
+BTF_ID_FLAGS(func, scx_bpf_select_cpu_and, KF_RCU)
+BTF_ID_FLAGS(func, scx_bpf_select_cpu_dfl, KF_IMPLICIT_ARGS | KF_RCU)
+BTF_KFUNCS_END(scx_kfunc_ids_select_cpu)
+
+static const struct btf_kfunc_id_set scx_kfunc_set_select_cpu = {
+       .owner                  = THIS_MODULE,
+       .set                    = &scx_kfunc_ids_select_cpu,
+};
+
 int scx_idle_init(void)
 {
        int ret;
 
        ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_idle) ||
              register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &scx_kfunc_set_idle) ||
-             register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &scx_kfunc_set_idle);
+             register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &scx_kfunc_set_idle) ||
+             register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &scx_kfunc_set_select_cpu) ||
+             register_btf_kfunc_id_set(BPF_PROG_TYPE_SYSCALL, &scx_kfunc_set_select_cpu);
 
        return ret;
 }