Message-ID: <CAEf4Bzb33btcH8McsTS7BpC_+GefzEUGUMNdetxAqvDvDDFA9g@mail.gmail.com>
Date:   Thu, 14 Sep 2023 16:26:46 -0700
From:   Andrii Nakryiko <andrii.nakryiko@...il.com>
To:     Chuyi Zhou <zhouchuyi@...edance.com>
Cc:     bpf@...r.kernel.org, ast@...nel.org, daniel@...earbox.net,
        andrii@...nel.org, martin.lau@...nel.org, tj@...nel.org,
        linux-kernel@...r.kernel.org
Subject: Re: [PATCH bpf-next v2 5/6] bpf: teach the verifier to enforce
 css_iter and process_iter in RCU CS

On Tue, Sep 12, 2023 at 12:02 AM Chuyi Zhou <zhouchuyi@...edance.com> wrote:
>
> css_iter and process_iter should be used in rcu section. Specifically, in
> sleepable progs explicit bpf_rcu_read_lock() is needed before use these
> iters. In normal bpf progs that have implicit rcu_read_lock(), it's OK to
> use them directly.
>
> This patch checks whether we are in rcu cs before we want to invoke
> bpf_iter_process_new and bpf_iter_css_{pre, post}_new in
> mark_stack_slots_iter(). If the rcu protection is guaranteed, we would
> let st->type = PTR_TO_STACK | MEM_RCU. is_iter_reg_valid_init() will
> reject if reg->type is UNTRUSTED.

it would be nice to mention where this MEM_RCU is turned into
UNTRUSTED when we do rcu_read_unlock(). For someone unfamiliar with
these parts of verifier (like me) this is completely unobvious.

>
> Signed-off-by: Chuyi Zhou <zhouchuyi@...edance.com>
> ---
>  kernel/bpf/verifier.c | 30 ++++++++++++++++++++++++++++--
>  1 file changed, 28 insertions(+), 2 deletions(-)
>
> diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
> index 2367483bf4c2..6a6827ba7a18 100644
> --- a/kernel/bpf/verifier.c
> +++ b/kernel/bpf/verifier.c
> @@ -1172,7 +1172,13 @@ static bool is_dynptr_type_expected(struct bpf_verifier_env *env, struct bpf_reg
>
>  static void __mark_reg_known_zero(struct bpf_reg_state *reg);
>
> +static bool in_rcu_cs(struct bpf_verifier_env *env);
> +
> +/* check whether we are using bpf_iter_process_*() or bpf_iter_css_*() */
> +static bool is_iter_need_rcu(struct bpf_kfunc_call_arg_meta *meta);
> +
>  static int mark_stack_slots_iter(struct bpf_verifier_env *env,
> +                                struct bpf_kfunc_call_arg_meta *meta,
>                                  struct bpf_reg_state *reg, int insn_idx,
>                                  struct btf *btf, u32 btf_id, int nr_slots)
>  {
> @@ -1193,6 +1199,12 @@ static int mark_stack_slots_iter(struct bpf_verifier_env *env,
>
>                 __mark_reg_known_zero(st);
>                 st->type = PTR_TO_STACK; /* we don't have dedicated reg type */
> +               if (is_iter_need_rcu(meta)) {
> +                       if (in_rcu_cs(env))
> +                               st->type |= MEM_RCU;
> +                       else
> +                               st->type |= PTR_UNTRUSTED;
> +               }
>                 st->live |= REG_LIVE_WRITTEN;
>                 st->ref_obj_id = i == 0 ? id : 0;
>                 st->iter.btf = btf;
> @@ -1281,6 +1293,8 @@ static bool is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_
>                 struct bpf_stack_state *slot = &state->stack[spi - i];
>                 struct bpf_reg_state *st = &slot->spilled_ptr;
>
> +               if (st->type & PTR_UNTRUSTED)
> +                       return false;
>                 /* only main (first) slot has ref_obj_id set */
>                 if (i == 0 && !st->ref_obj_id)
>                         return false;
> @@ -7503,13 +7517,13 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id
>                                 return err;
>                 }
>
> -               err = mark_stack_slots_iter(env, reg, insn_idx, meta->btf, btf_id, nr_slots);
> +               err = mark_stack_slots_iter(env, meta, reg, insn_idx, meta->btf, btf_id, nr_slots);
>                 if (err)
>                         return err;
>         } else {
>                 /* iter_next() or iter_destroy() expect initialized iter state*/
>                 if (!is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots)) {
> -                       verbose(env, "expected an initialized iter_%s as arg #%d\n",
> +                       verbose(env, "expected an initialized iter_%s as arg #%d or without bpf_rcu_read_lock()\n",
>                                 iter_type_str(meta->btf, btf_id), regno);

this message makes no sense, but even if reworded it would be
confusing for users. So maybe do the RCU check separately and report a
clear message that this iterator is expected to be within a single
continuous rcu_read_{lock+unlock} region.

I do think tracking RCU regions explicitly would make for much easier
to follow code, better messages, etc. Probably would be beneficial for
some other RCU-protected features. But that's a separate topic.

>                         return -EINVAL;
>                 }
> @@ -10382,6 +10396,18 @@ BTF_ID(func, bpf_percpu_obj_new_impl)
>  BTF_ID(func, bpf_percpu_obj_drop_impl)
>  BTF_ID(func, bpf_iter_css_task_new)
>
> +BTF_SET_START(rcu_protect_kfuns_set)
> +BTF_ID(func, bpf_iter_process_new)
> +BTF_ID(func, bpf_iter_css_pre_new)
> +BTF_ID(func, bpf_iter_css_post_new)
> +BTF_SET_END(rcu_protect_kfuns_set)
> +

instead of maintaining these extra special sets, why not add a KF
flag, like KF_RCU_PROTECTED?


> +static inline bool is_iter_need_rcu(struct bpf_kfunc_call_arg_meta *meta)
> +{
> +       return btf_id_set_contains(&rcu_protect_kfuns_set, meta->func_id);
> +}
> +
> +
>  static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta)
>  {
>         if (meta->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl] &&
> --
> 2.20.1
>

Powered by blists - more mailing lists