From: Eric Dumazet edumazet@google.com
__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 (cherry picked from commit 92f1655aa2b2294d0b49925f3b875a634bd3b59e) [Lee: Stable backport] Signed-off-by: Lee Jones lee@kernel.org --- include/net/dst_ops.h | 2 +- include/net/sock.h | 13 +++---------- net/ipv4/route.c | 22 ++++++++-------------- net/ipv6/route.c | 29 +++++++++++++++-------------- net/xfrm/xfrm_policy.c | 11 +++-------- 5 files changed, 30 insertions(+), 47 deletions(-)
diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 6d1c8541183d..3a9001a042a5 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -24,7 +24,7 @@ struct dst_ops { void (*destroy)(struct dst_entry *); void (*ifdown)(struct dst_entry *, struct net_device *dev); - struct dst_entry * (*negative_advice)(struct dst_entry *); + void (*negative_advice)(struct sock *sk, struct dst_entry *); void (*link_failure)(struct sk_buff *); void (*update_pmtu)(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, diff --git a/include/net/sock.h b/include/net/sock.h index 53b81e0a8981..5942b5ff4c78 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2183,17 +2183,10 @@ sk_dst_get(const struct sock *sk)
static inline void __dst_negative_advice(struct sock *sk) { - struct dst_entry *ndst, *dst = __sk_dst_get(sk); + struct dst_entry *dst = __sk_dst_get(sk);
- if (dst && dst->ops->negative_advice) { - ndst = dst->ops->negative_advice(dst); - - if (ndst != dst) { - rcu_assign_pointer(sk->sk_dst_cache, ndst); - sk_tx_queue_clear(sk); - WRITE_ONCE(sk->sk_dst_pending_confirm, 0); - } - } + if (dst && dst->ops->negative_advice) + dst->ops->negative_advice(sk, dst); }
static inline void dst_negative_advice(struct sock *sk) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 7c05cbcd39d3..40b9c579c917 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -132,7 +132,8 @@ struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ipv4_mtu(const struct dst_entry *dst); -static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); +static void ipv4_negative_advice(struct sock *sk, + struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, @@ -837,22 +838,15 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf __ip_do_redirect(rt, skb, &fl4, true); }
-static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) +static void ipv4_negative_advice(struct sock *sk, + struct dst_entry *dst) { struct rtable *rt = (struct rtable *)dst; - struct dst_entry *ret = dst;
- if (rt) { - if (dst->obsolete > 0) { - ip_rt_put(rt); - ret = NULL; - } else if ((rt->rt_flags & RTCF_REDIRECTED) || - rt->dst.expires) { - ip_rt_put(rt); - ret = NULL; - } - } - return ret; + if ((dst->obsolete > 0) || + (rt->rt_flags & RTCF_REDIRECTED) || + rt->dst.expires) + sk_dst_reset(sk); }
/* diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 236a45557ba1..0c0a1a5e4022 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); @@ -2760,24 +2761,24 @@ 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 = (struct 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) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 97d69ec54ff9..0dde08e02887 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3853,15 +3853,10 @@ static void xfrm_link_failure(struct sk_buff *skb) /* Impossible. Such dst must be popped before reaches point of failure. */ }
-static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst) +static void xfrm_negative_advice(struct sock *sk, struct dst_entry *dst) { - if (dst) { - if (dst->obsolete) { - dst_release(dst); - dst = NULL; - } - } - return dst; + if (dst->obsolete) + sk_dst_reset(sk); }
static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr)