Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 079d4f3f authored by Eric Dumazet's avatar Eric Dumazet Committed by Treehugger Robot
Browse files

BACKPORT: 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.

Bug: 343727534
Fixes: a87cb3e4 ("net: Facility to report route quality of connected sockets")
Reported-by: default avatarClement Lecigne <clecigne@google.com>
Diagnosed-by: default avatarClement Lecigne <clecigne@google.com>
Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
Cc: Tom Herbert <tom@herbertland.com>
Reviewed-by: default avatarDavid Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20240528114353.1794151-1-edumazet@google.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
(cherry picked from commit 92f1655aa2b2294d0b49925f3b875a634bd3b59e)
[Lee: Trivial/unrelated conflict - no change to the patch]
Signed-off-by: default avatarLee Jones <joneslee@google.com>
Change-Id: I293734dca1b81fcb712e1de294f51e96a405f7e4
parent 8ccbe208

include/net/dst_ops.h

+1 −1
Original line number Diff line number Diff line
@@ -24,7 +24,7 @@ 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 *);

	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,

include/net/sock.h

+3 −10
Original line number Diff line number Diff line
@@ -1919,19 +1919,12 @@ 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);



	sk_rethink_txhash(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

net/ipv4/route.c

+8 −14
Original line number Diff line number Diff line
@@ -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,
@@ -848,22 +849,15 @@ 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

+15 −14
Original line number Diff line number Diff line
@@ -88,7 +88,8 @@ 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);
@@ -2281,24 +2282,24 @@ 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)) {

			/* counteract the dst_release() in sk_dst_reset() */

			dst_hold(dst);

			sk_dst_reset(sk);



			rt6_remove_exception_rt(rt);

				dst = NULL;

		}

		rcu_read_unlock();

		} else {

			dst_release(dst);

			dst = NULL;

		}

		return;

	}

	return dst;

	sk_dst_reset(sk);

}



static void ip6_link_failure(struct sk_buff *skb)

net/xfrm/xfrm_policy.c

+3 −8
Original line number Diff line number Diff line
@@ -2558,15 +2558,10 @@ 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)