net: fix __dst_negative_advice() race

jira VULN-5441
cve CVE-2024-36971
commit-author Eric Dumazet <[email protected]>
commit 92f1655
upstream-diff This change breaks the kabi.  Use the RH_KABI_REPLACE
              macro to define the negative_advice function such that
              check-kabi will still pass.  From rh_kabi.h:

              "The RH_KABI_REPLACE* macros attempt to add the ability
               to use the '_new' element while preserving size
               alignment and kabi agreement with the '_orig' element."

__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: a87cb3e ("net: Facility to report route quality of connected sockets")
	Reported-by: Clement Lecigne <[email protected]>
Diagnosed-by: Clement Lecigne <[email protected]>
	Signed-off-by: Eric Dumazet <[email protected]>
	Cc: Tom Herbert <[email protected]>
	Reviewed-by: David Ahern <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
	Signed-off-by: Jakub Kicinski <[email protected]>
(cherry picked from commit 92f1655)
	Signed-off-by: Brett Mastbergen <[email protected]>

Author: bmastbergen

include/net/dst_ops.h

@@ -26,7 +26,8 @@ struct dst_ops {
 	void			(*destroy)(struct dst_entry *);
 	void			(*ifdown)(struct dst_entry *,
 					  struct net_device *dev, int how);
-	struct dst_entry *	(*negative_advice)(struct dst_entry *);
+	RH_KABI_REPLACE(struct dst_entry *	(*negative_advice)(struct dst_entry *),
+			void			(*negative_advice)(struct sock *sk, struct dst_entry *))
 	void			(*link_failure)(struct sk_buff *);
 	RH_KABI_REPLACE(void	(*update_pmtu)(struct dst_entry *dst, struct sock *sk,
 					       struct sk_buff *skb, u32 mtu),

include/net/sock.h

@@ -2008,17 +2008,10 @@ sk_dst_get(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);
-			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)

net/ipv4/route.c

@@ -140,7 +140,8 @@ static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
 static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie);
 static unsigned int	 ipv4_default_advmss(const struct dst_entry *dst);
 static 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,
@@ -857,22 +858,15 @@ 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);
 }
 
 /*

net/ipv6/route.c

@@ -89,7 +89,8 @@ enum rt6_nud_state {
 static struct dst_entry	*ip6_dst_check(struct dst_entry *dst, u32 cookie);
 static unsigned int	 ip6_default_advmss(const struct dst_entry *dst);
 static 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, int how);
@@ -2399,24 +2400,24 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 	return dst_ret;
 }
 
-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)

net/xfrm/xfrm_policy.c

@@ -3561,15 +3561,10 @@ 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)