diff options
| author | Eric Dumazet <edumazet@google.com> | 2024-05-28 13:43:53 +0200 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2024-05-30 02:34:49 +0200 |
| commit | 92f1655aa2b2294d0b49925f3b875a634bd3b59e (patch) | |
| tree | d4bb375a5cda5ca5a82e3d30a01fc4bbbb616872 /net/ipv6 | |
| parent | nfc/nci: Add the inconsistency check between the input data length and count (diff) | |
| download | linux-92f1655aa2b2294d0b49925f3b875a634bd3b59e.tar.xz linux-92f1655aa2b2294d0b49925f3b875a634bd3b59e.zip | |
net: fix __dst_negative_advice() race
__dst_negative_advice() does not enforce proper RCU rules when
sk->dst_cache must be cleared, leading to possible UAF.
RCU rules are that we must first clear sk->sk_dst_cache,
then call dst_release(old_dst).
Note that sk_dst_reset(sk) is implementing this protocol correctly,
while __dst_negative_advice() uses the wrong order.
Given that ip6_negative_advice() has special logic
against RTF_CACHE, this means each of the three ->negative_advice()
existing methods must perform the sk_dst_reset() themselves.
Note the check against NULL dst is centralized in
__dst_negative_advice(), there is no need to duplicate
it in various callbacks.
Many thanks to Clement Lecigne for tracking this issue.
This old bug became visible after the blamed commit, using UDP sockets.
Fixes: a87cb3e48ee8 ("net: Facility to report route quality of connected sockets")
Reported-by: Clement Lecigne <clecigne@google.com>
Diagnosed-by: Clement Lecigne <clecigne@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tom Herbert <tom@herbertland.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20240528114353.1794151-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net/ipv6')
| -rw-r--r-- | net/ipv6/route.c | 29 |
1 files changed, 15 insertions, 14 deletions
diff --git a/net/ipv6/route.c b/net/ipv6/route.c index bbc2a0dd9314..a504b88ec06b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -87,7 +87,8 @@ struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ip6_mtu(const struct dst_entry *dst); -static struct dst_entry *ip6_negative_advice(struct dst_entry *); +static void ip6_negative_advice(struct sock *sk, + struct dst_entry *dst); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, struct net_device *dev); @@ -2770,24 +2771,24 @@ INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, } EXPORT_INDIRECT_CALLABLE(ip6_dst_check); -static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) +static void ip6_negative_advice(struct sock *sk, + struct dst_entry *dst) { struct rt6_info *rt = dst_rt6_info(dst); - if (rt) { - if (rt->rt6i_flags & RTF_CACHE) { - rcu_read_lock(); - if (rt6_check_expired(rt)) { - rt6_remove_exception_rt(rt); - dst = NULL; - } - rcu_read_unlock(); - } else { - dst_release(dst); - dst = NULL; + if (rt->rt6i_flags & RTF_CACHE) { + rcu_read_lock(); + if (rt6_check_expired(rt)) { + /* counteract the dst_release() in sk_dst_reset() */ + dst_hold(dst); + sk_dst_reset(sk); + + rt6_remove_exception_rt(rt); } + rcu_read_unlock(); + return; } - return dst; + sk_dst_reset(sk); } static void ip6_link_failure(struct sk_buff *skb) |