bpf: Reject attaching fexit/fmod_ret to __noreturn functions

If we attach fexit/fmod_ret to __noreturn functions, it will cause an
issue that the bpf trampoline image will be left over even if the bpf
link has been destroyed. Take attaching do_exit() with fexit for example.
The fexit works as follows,

  bpf_trampoline
  + __bpf_tramp_enter
    + percpu_ref_get(&tr->pcref);

  + call do_exit()

  + __bpf_tramp_exit
    + percpu_ref_put(&tr->pcref);

Since do_exit() never returns, the refcnt of the trampoline image is
never decremented, preventing it from being freed. That can be verified
with as follows,

  $ bpftool link show                                   <<<< nothing output
  $ grep "bpf_trampoline_[0-9]" /proc/kallsyms
  ffffffffc04cb000 t bpf_trampoline_6442526459    [bpf] <<<< leftover

In this patch, all functions annotated with __noreturn are rejected, except
for the following cases:
- Functions that result in a system reboot, such as panic,
  machine_real_restart and rust_begin_unwind
- Functions that are never executed by tasks, such as rest_init and
  cpu_startup_entry
- Functions implemented in assembly, such as rewind_stack_and_make_dead and
  xen_cpu_bringup_again, lack an associated BTF ID.

With this change, attaching fexit probes to functions like do_exit() will
be rejected.

$ ./fexit
libbpf: prog 'fexit': BPF program load failed: -EINVAL
libbpf: prog 'fexit': -- BEGIN PROG LOAD LOG --
Attaching fexit/fmod_ret to __noreturn functions is rejected.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Link: https://lore.kernel.org/r/20250318114447.75484-2-laoar.shao@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 3303a3605ee808d9d5e77526668f9090e10b8c42..19ece8893d38d5e69ebdef7fd261c335caba1c4d 100644 (file)
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -23215,6 +23215,33 @@ BTF_ID(func, __rcu_read_unlock)
 #endif
 BTF_SET_END(btf_id_deny)
 
+/* fexit and fmod_ret can't be used to attach to __noreturn functions.
+ * Currently, we must manually list all __noreturn functions here. Once a more
+ * robust solution is implemented, this workaround can be removed.
+ */
+BTF_SET_START(noreturn_deny)
+#ifdef CONFIG_IA32_EMULATION
+BTF_ID(func, __ia32_sys_exit)
+BTF_ID(func, __ia32_sys_exit_group)
+#endif
+#ifdef CONFIG_KUNIT
+BTF_ID(func, __kunit_abort)
+BTF_ID(func, kunit_try_catch_throw)
+#endif
+#ifdef CONFIG_MODULES
+BTF_ID(func, __module_put_and_kthread_exit)
+#endif
+#ifdef CONFIG_X86_64
+BTF_ID(func, __x64_sys_exit)
+BTF_ID(func, __x64_sys_exit_group)
+#endif
+BTF_ID(func, do_exit)
+BTF_ID(func, do_group_exit)
+BTF_ID(func, kthread_complete_and_exit)
+BTF_ID(func, kthread_exit)
+BTF_ID(func, make_task_dead)
+BTF_SET_END(noreturn_deny)
+
 static bool can_be_sleepable(struct bpf_prog *prog)
 {
        if (prog->type == BPF_PROG_TYPE_TRACING) {
@@ -23301,6 +23328,11 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
        } else if (prog->type == BPF_PROG_TYPE_TRACING &&
                   btf_id_set_contains(&btf_id_deny, btf_id)) {
                return -EINVAL;
+       } else if ((prog->expected_attach_type == BPF_TRACE_FEXIT ||
+                  prog->expected_attach_type == BPF_MODIFY_RETURN) &&
+                  btf_id_set_contains(&noreturn_deny, btf_id)) {
+               verbose(env, "Attaching fexit/fmod_ret to __noreturn functions is rejected.\n");
+               return -EINVAL;
        }
 
        key = bpf_trampoline_compute_key(tgt_prog, prog->aux->attach_btf, btf_id);