From 1688b4ce3ed9959e79a5e3a1e9be331184a1b65d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 28 May 2024 11:43:53 +0000
Subject: [PATCH 1/2] 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: 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: Trivial/unrelated conflict - no change to the patch]
Signed-off-by: Lee Jones <joneslee@google.com>
Change-Id: I293734dca1b81fcb712e1de294f51e96a405f7e4
[mkbestas: Non trivial backport to 4.14]
Signed-off-by: Michael Bestas <mkbestas@lineageos.org>
---
 include/net/dst_ops.h  |  2 +-
 include/net/sock.h     | 12 +++---------
 net/ipv4/route.c       | 22 ++++++++--------------
 net/ipv6/route.c       | 25 +++++++++++++------------
 net/xfrm/xfrm_policy.c | 11 +++--------
 5 files changed, 28 insertions(+), 44 deletions(-)

diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
index a0d443ca16fc..c3cd125032fa 100644
--- a/include/net/dst_ops.h
+++ b/include/net/dst_ops.h
@@ -23,7 +23,7 @@ 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);
diff --git a/include/net/sock.h b/include/net/sock.h
index 8fe71ee1935a..8c29e159972e 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1719,18 +1719,12 @@ 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);
-		}
-	}
+	if (dst && dst->ops->negative_advice)
+		dst->ops->negative_advice(sk, dst);
 }
 
 static inline void
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ec3d6750bbf1..18483e6c3897 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -138,7 +138,8 @@ 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);
@@ -821,22 +822,15 @@ 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 cf05b953f8b8..f841528ae658 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -81,7 +81,8 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort);
 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);
@@ -1311,22 +1312,22 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 		return rt6_check(rt, cookie);
 }
 
-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) {
-			if (rt6_check_expired(rt)) {
-				ip6_del_rt(rt);
-				dst = NULL;
-			}
-		} else {
-			dst_release(dst);
-			dst = NULL;
+	if (rt->rt6i_flags & RTF_CACHE) {
+		if (rt6_check_expired(rt)) {
+			/* counteract the dst_release() in sk_dst_reset() */
+			dst_hold(dst);
+			sk_dst_reset(sk);
+
+			ip6_del_rt(rt);
 		}
+		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 e090ff476cdf..2a4f77b01936 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2725,15 +2725,10 @@ 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);
 }
 
 void xfrm_garbage_collect(struct net *net)
-- 
2.34.1

From 4d12c66b108d4c0cddc2948c9deeb5e3b0728b93 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@google.com>
Date: Sat, 1 Jun 2024 09:33:51 +0000
Subject: [PATCH 2/2] ANDROID: ABI fixup for abi break in struct dst_ops

In commit 92f1655aa2b2 ("net: fix __dst_negative_advice() race") the
struct dst_ops callback negative_advice is callback changes function
parameters.  But as this pointer is part of a structure that is tracked
in the ABI checker, the tool triggers when this is changed.

However, the callback pointer is internal to the networking stack, so
changing the function type is safe, so needing to preserve this is not
required.  To do so, switch the function pointer type back to the old
one so that the checking tools pass, AND then do a hard cast of the
function pointer to the new type when assigning and calling the
function.

Bug: 343727534
Fixes: 92f1655aa2b2 ("net: fix __dst_negative_advice() race")
Change-Id: I48d4ab4bbd29f8edc8fbd7923828b7f78a23e12e
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
---
 include/net/dst_ops.h  | 12 +++++++++++-
 include/net/sock.h     | 12 ++++++++++--
 net/ipv4/route.c       |  2 +-
 net/ipv6/route.c       |  2 +-
 net/xfrm/xfrm_policy.c |  2 +-
 5 files changed, 24 insertions(+), 6 deletions(-)

diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
index c3cd125032fa..64e06d90c7a5 100644
--- a/include/net/dst_ops.h
+++ b/include/net/dst_ops.h
@@ -11,6 +11,16 @@ struct sk_buff;
 struct sock;
 struct net;
 
+/* *** ANDROID FIXUP ***
+ * These typedefs are used to help fixup the ABI break caused by commit
+ * 92f1655aa2b2 ("net: fix __dst_negative_advice() race") where the
+ * negative_advice callback changed function signatures.
+ * See b/343727534 for more details.
+ * *** ANDROID FIXUP ***
+ */
+typedef void (*android_dst_ops_negative_advice_new_t)(struct sock *sk, struct dst_entry *);
+typedef struct dst_entry * (*android_dst_ops_negative_advice_old_t)(struct dst_entry *);
+
 struct dst_ops {
 	unsigned short		family;
 	unsigned int		gc_thresh;
@@ -23,7 +33,7 @@ struct dst_ops {
 	void			(*destroy)(struct dst_entry *);
 	void			(*ifdown)(struct dst_entry *,
 					  struct net_device *dev, int how);
-	void			(*negative_advice)(struct sock *sk, struct dst_entry *);
+	struct dst_entry *	(*negative_advice)(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 8c29e159972e..8a71f74e6bd9 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1719,12 +1719,20 @@ sk_dst_get(struct sock *sk)
 
 static inline void dst_negative_advice(struct sock *sk)
 {
+	/* *** ANDROID FIXUP ***
+	 * See b/343727534 for more details why this typedef is needed here.
+	 * *** ANDROID FIXUP ***
+	 */
+	android_dst_ops_negative_advice_new_t negative_advice;
+
 	struct dst_entry *dst = __sk_dst_get(sk);
 
 	sk_rethink_txhash(sk);
 
-	if (dst && dst->ops->negative_advice)
-		dst->ops->negative_advice(sk, dst);
+	if (dst && dst->ops->negative_advice) {
+		negative_advice = (android_dst_ops_negative_advice_new_t)dst->ops->negative_advice;
+		negative_advice(sk, dst);
+	}
 }
 
 static inline void
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 18483e6c3897..395108c7338e 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -164,7 +164,7 @@ static struct dst_ops ipv4_dst_ops = {
 	.mtu =			ipv4_mtu,
 	.cow_metrics =		ipv4_cow_metrics,
 	.destroy =		ipv4_dst_destroy,
-	.negative_advice =	ipv4_negative_advice,
+	.negative_advice =	(android_dst_ops_negative_advice_old_t)ipv4_negative_advice,
 	.link_failure =		ipv4_link_failure,
 	.update_pmtu =		ip_rt_update_pmtu,
 	.redirect =		ip_do_redirect,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index f841528ae658..b6a31e83e1e3 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -228,7 +228,7 @@ static struct dst_ops ip6_dst_ops_template = {
 	.cow_metrics		=	ipv6_cow_metrics,
 	.destroy		=	ip6_dst_destroy,
 	.ifdown			=	ip6_dst_ifdown,
-	.negative_advice	=	ip6_negative_advice,
+	.negative_advice	=	(android_dst_ops_negative_advice_old_t)ip6_negative_advice,
 	.link_failure		=	ip6_link_failure,
 	.update_pmtu		=	ip6_rt_update_pmtu,
 	.redirect		=	rt6_do_redirect,
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 2a4f77b01936..7855827323e5 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2872,7 +2872,7 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo)
 		if (likely(dst_ops->mtu == NULL))
 			dst_ops->mtu = xfrm_mtu;
 		if (likely(dst_ops->negative_advice == NULL))
-			dst_ops->negative_advice = xfrm_negative_advice;
+			dst_ops->negative_advice = (android_dst_ops_negative_advice_old_t)xfrm_negative_advice;
 		if (likely(dst_ops->link_failure == NULL))
 			dst_ops->link_failure = xfrm_link_failure;
 		if (likely(dst_ops->neigh_lookup == NULL))
-- 
2.34.1