[PATCH bpf-next v4 3/9] bpf: add the kfunc bpf_fsession_is_return

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

If TRACE_SESSION exists, we will use the bit (1 << BPF_TRAMP_M_IS_RETURN)
in ctx[-1] to store the "is_return" flag.

Introduce the kfunc bpf_fsession_is_return(), which is used to tell if it
is fexit currently. Meanwhile, inline it in the verifier.

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>
---
v4:
- split out the bpf_fsession_cookie() to another patch

v3:
- merge the bpf_tracing_is_exit and bpf_fsession_cookie into a single
  patch

v2:
- store the session flags after return value, instead of before nr_args
- inline the bpf_tracing_is_exit, as Jiri suggested
---
 include/linux/bpf.h      |  3 +++
 kernel/bpf/verifier.c    | 11 +++++++++-
 kernel/trace/bpf_trace.c | 43 +++++++++++++++++++++++++++++++++++++---
 3 files changed, 53 insertions(+), 4 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 3b2273b110b8..d165ace5cc9b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1213,6 +1213,9 @@ enum {
 #endif
 };
 
+#define BPF_TRAMP_M_NR_ARGS	0
+#define BPF_TRAMP_M_IS_RETURN	8
+
 struct bpf_tramp_links {
 	struct bpf_tramp_link *links[BPF_MAX_TRAMP_LINKS];
 	int nr_links;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 96753833c090..b0dcd715150f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -12380,6 +12380,7 @@ enum special_kfunc_type {
 	KF___bpf_trap,
 	KF_bpf_task_work_schedule_signal_impl,
 	KF_bpf_task_work_schedule_resume_impl,
+	KF_bpf_fsession_is_return,
 };
 
 BTF_ID_LIST(special_kfunc_list)
@@ -12454,6 +12455,7 @@ BTF_ID(func, bpf_dynptr_file_discard)
 BTF_ID(func, __bpf_trap)
 BTF_ID(func, bpf_task_work_schedule_signal_impl)
 BTF_ID(func, bpf_task_work_schedule_resume_impl)
+BTF_ID(func, bpf_fsession_is_return)
 
 static bool is_task_work_add_kfunc(u32 func_id)
 {
@@ -12508,7 +12510,8 @@ 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_fsession_is_return])
 		return KF_ARG_PTR_TO_CTX;
 
 	/* In this function, we verify the kfunc's BTF as per the argument type,
@@ -22556,6 +22559,12 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		   desc->func_id == special_kfunc_list[KF_bpf_rdonly_cast]) {
 		insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_1);
 		*cnt = 1;
+	} else if (desc->func_id == special_kfunc_list[KF_bpf_fsession_is_return]) {
+		/* Load nr_args from ctx - 8 */
+		insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
+		insn_buf[1] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, BPF_TRAMP_M_IS_RETURN);
+		insn_buf[2] = BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1);
+		*cnt = 3;
 	}
 
 	if (env->insn_aux_data[insn_idx].arg_prog) {
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 10c9992d2745..0857d77eb34c 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_fsession_is_return(void *ctx)
+{
+	/* This helper call is inlined by verifier. */
+	return !!(((u64 *)ctx)[-1] & (1 << BPF_TRAMP_M_IS_RETURN));
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(tracing_kfunc_set_ids)
+BTF_ID_FLAGS(func, bpf_fsession_is_return, KF_FASTCALL)
+BTF_KFUNCS_END(tracing_kfunc_set_ids)
+
+static int bpf_tracing_filter(const struct bpf_prog *prog, u32 kfunc_id)
 {
-	return register_btf_kfunc_id_set(BPF_PROG_TYPE_KPROBE, &bpf_kprobe_multi_kfunc_set);
+	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)
+{
+	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);
 
-- 
2.52.0