[PATCH RFC bpf-next 2/5] bpf: add kfunc bpf_tracing_is_exit for TRACE_SESSION

[Menglong Dong <menglong8.dong@gmail.com>]

If TRACE_SESSION exists, we will use extra 8-bytes in the stack of the
trampoline to store the flags that we needed, and the 8-bytes lie before
the function argument count, which means ctx[-2]. And we will store the
flag "is_exit" to the first bit of it.

Introduce the kfunc bpf_tracing_is_exit(), which is used to tell if it
is fexit currently.

Signed-off-by: Menglong Dong <dongml2@chinatelecom.cn>
Co-developed-by: Leon Hwang <leon.hwang@linux.dev>
Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
 kernel/bpf/verifier.c    |  5 ++++-
 kernel/trace/bpf_trace.c | 43 +++++++++++++++++++++++++++++++++++++---
 2 files changed, 44 insertions(+), 4 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 40e3274e8bc2..a1db11818d01 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -12284,6 +12284,7 @@ enum special_kfunc_type {
 	KF___bpf_trap,
 	KF_bpf_task_work_schedule_signal,
 	KF_bpf_task_work_schedule_resume,
+	KF_bpf_tracing_is_exit,
 };
 
 BTF_ID_LIST(special_kfunc_list)
@@ -12356,6 +12357,7 @@ BTF_ID(func, bpf_res_spin_unlock_irqrestore)
 BTF_ID(func, __bpf_trap)
 BTF_ID(func, bpf_task_work_schedule_signal)
 BTF_ID(func, bpf_task_work_schedule_resume)
+BTF_ID(func, bpf_tracing_is_exit)
 
 static bool is_task_work_add_kfunc(u32 func_id)
 {
@@ -12410,7 +12412,8 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env,
 	struct bpf_reg_state *reg = &regs[regno];
 	bool arg_mem_size = false;
 
-	if (meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx])
+	if (meta->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx] ||
+	    meta->func_id == special_kfunc_list[KF_bpf_tracing_is_exit])
 		return KF_ARG_PTR_TO_CTX;
 
 	/* In this function, we verify the kfunc's BTF as per the argument type,
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 4f87c16d915a..6dde48b9d27f 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -3356,12 +3356,49 @@ static const struct btf_kfunc_id_set bpf_kprobe_multi_kfunc_set = {
 	.filter = bpf_kprobe_multi_filter,
 };
 
-static int __init bpf_kprobe_multi_kfuncs_init(void)
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc bool bpf_tracing_is_exit(void *ctx)
+{
+	/* ctx[-2] is the session flags, and the last bit is is_exit */
+	return ((u64 *)ctx)[-2] & 1;
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(tracing_kfunc_set_ids)
+BTF_ID_FLAGS(func, bpf_tracing_is_exit)
+BTF_KFUNCS_END(tracing_kfunc_set_ids)
+
+static int bpf_tracing_filter(const struct bpf_prog *prog, u32 kfunc_id)
+{
+	if (!btf_id_set8_contains(&tracing_kfunc_set_ids, kfunc_id))
+		return 0;
+
+	if (prog->type != BPF_PROG_TYPE_TRACING ||
+	    prog->expected_attach_type != BPF_TRACE_SESSION)
+		return -EINVAL;
+
+	return 0;
+}
+
+static const struct btf_kfunc_id_set bpf_tracing_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set = &tracing_kfunc_set_ids,
+	.filter = bpf_tracing_filter,
+};
+
+static int __init bpf_trace_kfuncs_init(void)
 {
-	return register_btf_kfunc_id_set(BPF_PROG_TYPE_KPROBE, &bpf_kprobe_multi_kfunc_set);
+	int err = 0;
+
+	err = err ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_KPROBE, &bpf_kprobe_multi_kfunc_set);
+	err = err ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_tracing_kfunc_set);
+
+	return err;
 }
 
-late_initcall(bpf_kprobe_multi_kfuncs_init);
+late_initcall(bpf_trace_kfuncs_init);
 
 typedef int (*copy_fn_t)(void *dst, const void *src, u32 size, struct task_struct *tsk);
 
-- 
2.51.0