Re: [PATCH bpf-next v4 2/6] netfilter: bpf: Support BPF_F_NETFILTER_IP_DEFRAG in netfilter link

[Alexei Starovoitov]

On Wed, Jul 12, 2023 at 6:22 PM Daniel Xu <dxu@xxxxxxxxx> wrote:
>
> Hi Alexei,
>
> On Wed, Jul 12, 2023 at 05:43:49PM -0700, Alexei Starovoitov wrote:
> > On Wed, Jul 12, 2023 at 4:44 PM Daniel Xu <dxu@xxxxxxxxx> wrote:
> > > +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
> > > +       case NFPROTO_IPV6:
> > > +               rcu_read_lock();
> > > +               v6_hook = rcu_dereference(nf_defrag_v6_hook);
> > > +               if (!v6_hook) {
> > > +                       rcu_read_unlock();
> > > +                       err = request_module("nf_defrag_ipv6");
> > > +                       if (err)
> > > +                               return err < 0 ? err : -EINVAL;
> > > +
> > > +                       rcu_read_lock();
> > > +                       v6_hook = rcu_dereference(nf_defrag_v6_hook);
> > > +                       if (!v6_hook) {
> > > +                               WARN_ONCE(1, "nf_defrag_ipv6_hooks bad registration");
> > > +                               err = -ENOENT;
> > > +                               goto out_v6;
> > > +                       }
> > > +               }
> > > +
> > > +               err = v6_hook->enable(link->net);
> >
> > I was about to apply, but luckily caught this issue in my local test:
> >
> > [   18.462448] BUG: sleeping function called from invalid context at
> > kernel/locking/mutex.c:283
> > [   18.463238] in_atomic(): 0, irqs_disabled(): 0, non_block: 0, pid:
> > 2042, name: test_progs
> > [   18.463927] preempt_count: 0, expected: 0
> > [   18.464249] RCU nest depth: 1, expected: 0
> > [   18.464631] CPU: 15 PID: 2042 Comm: test_progs Tainted: G
> > O       6.4.0-04319-g6f6ec4fa00dc #4896
> > [   18.465480] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
> > BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014
> > [   18.466531] Call Trace:
> > [   18.466767]  <TASK>
> > [   18.466975]  dump_stack_lvl+0x32/0x40
> > [   18.467325]  __might_resched+0x129/0x180
> > [   18.467691]  mutex_lock+0x1a/0x40
> > [   18.468057]  nf_defrag_ipv4_enable+0x16/0x70
> > [   18.468467]  bpf_nf_link_attach+0x141/0x300
> > [   18.468856]  __sys_bpf+0x133e/0x26d0
> >
> > You cannot call mutex under rcu_read_lock.
>
> Whoops, my bad. I think this patch should fix it:
>
> ```
> From 7e8927c44452db07ddd7cf0e30bb49215fc044ed Mon Sep 17 00:00:00 2001
> Message-ID: <7e8927c44452db07ddd7cf0e30bb49215fc044ed.1689211250.git.dxu@xxxxxxxxx>
> From: Daniel Xu <dxu@xxxxxxxxx>
> Date: Wed, 12 Jul 2023 19:17:35 -0600
> Subject: [PATCH] netfilter: bpf: Don't hold rcu_read_lock during
>  enable/disable
>
> ->enable()/->disable() takes a mutex which can sleep. You can't sleep
> during RCU read side critical section.
>
> Our refcnt on the module will protect us from ->enable()/->disable()
> from going away while we call it.
>
> Signed-off-by: Daniel Xu <dxu@xxxxxxxxx>
> ---
>  net/netfilter/nf_bpf_link.c | 10 ++++++++--
>  1 file changed, 8 insertions(+), 2 deletions(-)
>
> diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c
> index 77ffbf26ba3d..79704cc596aa 100644
> --- a/net/netfilter/nf_bpf_link.c
> +++ b/net/netfilter/nf_bpf_link.c
> @@ -60,9 +60,12 @@ static int bpf_nf_enable_defrag(struct bpf_nf_link *link)
>                         goto out_v4;
>                 }
>
> +               rcu_read_unlock();
>                 err = v4_hook->enable(link->net);
>                 if (err)
>                         module_put(v4_hook->owner);
> +
> +               return err;
>  out_v4:
>                 rcu_read_unlock();
>                 return err;
> @@ -92,9 +95,12 @@ static int bpf_nf_enable_defrag(struct bpf_nf_link *link)
>                         goto out_v6;
>                 }
>
> +               rcu_read_unlock();
>                 err = v6_hook->enable(link->net);
>                 if (err)
>                         module_put(v6_hook->owner);
> +
> +               return err;
>  out_v6:
>                 rcu_read_unlock();
>                 return err;
> @@ -114,11 +120,11 @@ static void bpf_nf_disable_defrag(struct bpf_nf_link *link)
>         case NFPROTO_IPV4:
>                 rcu_read_lock();
>                 v4_hook = rcu_dereference(nf_defrag_v4_hook);
> +               rcu_read_unlock();
>                 if (v4_hook) {
>                         v4_hook->disable(link->net);
>                         module_put(v4_hook->owner);
>                 }
> -               rcu_read_unlock();
>
>                 break;
>  #endif
> @@ -126,11 +132,11 @@ static void bpf_nf_disable_defrag(struct bpf_nf_link *link)
>         case NFPROTO_IPV6:
>                 rcu_read_lock();
>                 v6_hook = rcu_dereference(nf_defrag_v6_hook);
> +               rcu_read_unlock();

No. v6_hook is gone as soon as you unlock it.