Re: [PATCH net-next v3 2/4] ipv6: take fib6_sernum from a sequence shared by all netns

[netdev-bot+sashiko]

Thank you for your contribution! Sashiko AI review found 1 potential
issue(s) to consider.

Critical: 0 · High: 1 · Medium: 0 · Low: 0

If you believe none of the issues are legitimate, please reply to each
issue of Medium severity or higher and explain why the AI is wrong.
If any of them are legitimate and you plan to respin, please let patchwork
know by including "pw-bot: cr" as a separate line at the end of your reply
(one such reply per series is enough).

- [High] The fix is incomplete.

--

ipv6: take fib6_sernum from a sequence shared by all netns

This patch makes fib6_new_sernum() take its values from one global atomic
sequence shared by all netns, which only hands out values from 2 up. The
goal is that a per-cpu nexthop route cached in one netns cannot match the
fib6_sernum of another netns after its device moves. Every netns still
starts its fib6_sernum at 1.

> diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
> index e1d49897d6ab0..827051cbf7482 100644
> --- a/net/ipv6/ip6_fib.c
> +++ b/net/ipv6/ip6_fib.c
> @@ -123,13 +123,23 @@ static void fib6_walkers_skip_rt(struct net *net, struct fib6_info *rt)
>  	fib6_walkers_replace_leaf(net, rt, next);
>  }
>  
> +/*
> + * Draw fib6_sernum bumps from one sequence shared by all netns, so that a
> + * route cached against one netns does not match the sernum of another one,
> + * e.g. after its device moved, until the sequence wraps. Every netns starts
> + * at 1 and the sequence only hands out values from 2 up: 0 means no sernum
> + * to check.
> + */
> +static atomic_t fib6_sernum_seq = ATOMIC_INIT(1);
> +
>  static int fib6_new_sernum(struct net *net)
>  {
> -	int new, old = atomic_read(&net->ipv6.fib6_sernum);
> +	int new, old = atomic_read(&fib6_sernum_seq);
>  
>  	do {
> -		new = old < INT_MAX ? old + 1 : 1;
> -	} while (!atomic_try_cmpxchg(&net->ipv6.fib6_sernum, &old, new));
> +		new = old < INT_MAX ? old + 1 : 2;
> +	} while (!atomic_try_cmpxchg(&fib6_sernum_seq, &old, new));
> +	atomic_set(&net->ipv6.fib6_sernum, new);
>  
>  	return new;
>  }

[Severity: High]
Is the value 1 still shared by every netns after this change?

inet6_net_init() in net/ipv6/af_inet6.c still does:

    atomic_set(&net->ipv6.fib6_sernum, 1);

The shared sequence never hands out 1. So a netns that has never changed
its fib6 tree stays at 1, the same value every other fresh netns starts
with.

The commit message says "Inserting a route bumps fib6_sernum, so the
routes a netns caches carry values drawn from the sequence". Does that
hold for routes cached while the insertion is still in progress?
fib6_add() publishes the route before it bumps the sernum:

fib6_add()
  fib6_add_rt2node_nh() / fib6_add_rt2node()
    rcu_assign_pointer(*ins, rt);
    inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags);
  fib6_purge_rt() for each entry on purge_list
  __fib6_update_sernum_upto_root(rt, fib6_new_sernum(info->nl_net));

In that window, a concurrent RCU-only lookup in netns A can find the new
nexthop route and go through
ip6_pol_route()->rt6_make_pcpu_route()->ip6_rt_pcpu_alloc(), which does:

    if (f6i->nh)
        pcpu_rt->sernum = rt_genid_ipv6(dev_net(dev));

If this is the first fib6 change in A, the cached value is 1.
rt6_get_cookie() then gives that value to a socket that connects at that
moment.

Once the bump happens the dst is invalid in A. But suppose the socket
does not send until the device has moved to a netns B that has never
changed its fib6 tree. rt6_is_valid() then evaluates this as 1 == 1:

    return rt6->sernum == rt_genid_ipv6(dev_net(rt6->dst.dev));

and ip6_dst_check() accepts the stale dst. Could the socket in A then
keep sending through B's device until nexthop_free_rcu() releases the
per-cpu routes? None of this needs the sequence to wrap.

Both preconditions look reachable:

In A, the nexthop device only needs IFF_UP and IPv6 enabled. addrconf
adds no routes while the link is not ready (for example a veth with
carrier off), or for IFF_NO_ADDRCONF devices.

In B, disable_ipv6 makes addrconf_notify() stop before it adds any
route. An IPv6-disabled container netns therefore stays at sernum 1
for good.

The later patch in this series, "net: remove rcu_barrier() from
__dev_change_net_namespace()", does not close this window and may make
it longer. Nothing later in the series changes the initial value or the
order of publishing and bumping.

Would it make sense to also seed each netns's initial fib6_sernum from
fib6_sernum_seq in inet6_net_init()? Alternatively, could the sernum be
bumped before the route becomes visible to readers?

-- 
Sashiko AI review · https://netdev-ai.bots.linux.dev/sashiko/#/patchset/20261109-bug-net-netns-move-rcu-barrier-v3-0-6084b02610b3%40linux.dev