Merge branch 'ipv6-dgram-dst-cache'

Martin KaFai Lau says:

====================
ipv6: datagram: Update dst cache of a connected udp sk during pmtu update

v2:
~ Protect __sk_dst_get() operations with rcu_read_lock in
  release_cb() because another thread may do ip6_dst_store()
  for a udp sk without taking the sk lock (e.g. in sendmsg).
~ Do a ipv6_addr_v4mapped(&sk->sk_v6_daddr) check before
  calling ip6_datagram_dst_update() in patch 3 and 4.  It is
  similar to how __ip6_datagram_connect handles it.
~ One fix in ip6_datagram_dst_update() in patch 2.  It needs
  to check (np->flow_label & IPV6_FLOWLABEL_MASK) before
  doing fl6_sock_lookup.  I was confused with the naming
  of IPV6_FLOWLABEL_MASK and IPV6_FLOWINFO_MASK.
~ Check dst->obsolete just on the safe side, although I think it
  should at least have DST_OBSOLETE_FORCE_CHK by now.
~ Add Fixes tag to patch 3 and 4
~ Add some points from the previous discussion about holding
  sk lock to the commit message in patch 3.

v1:
There is a case in connected UDP socket such that
getsockopt(IPV6_MTU) will return a stale MTU value. The reproducible
sequence could be the following:
1. Create a connected UDP socket
2. Send some datagrams out
3. Receive a ICMPV6_PKT_TOOBIG
4. No new outgoing datagrams to trigger the sk_dst_check()
   logic to update the sk->sk_dst_cache.
5. getsockopt(IPV6_MTU) returns the mtu from the invalid
   sk->sk_dst_cache instead of the newly created RTF_CACHE clone.

Patch 1 and 2 are the prep work.
Patch 3 and 4 are the fixes.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 121 insertions, 63 deletions

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index d0aeb97aec5d..1be050ada8c5 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -959,6 +959,8 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname,
 int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len);
 int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *addr,
 				 int addr_len);
+int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr);
+void ip6_datagram_release_cb(struct sock *sk);
 
 int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len,
 		    int *addr_len);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 428162155280..9dd3882fe6bf 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -40,18 +40,114 @@ static bool ipv6_mapped_addr_any(const struct in6_addr *a)
 	return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0);
 }
 
+static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk)
+{
+	struct inet_sock *inet = inet_sk(sk);
+	struct ipv6_pinfo *np = inet6_sk(sk);
+
+	memset(fl6, 0, sizeof(*fl6));
+	fl6->flowi6_proto = sk->sk_protocol;
+	fl6->daddr = sk->sk_v6_daddr;
+	fl6->saddr = np->saddr;
+	fl6->flowi6_oif = sk->sk_bound_dev_if;
+	fl6->flowi6_mark = sk->sk_mark;
+	fl6->fl6_dport = inet->inet_dport;
+	fl6->fl6_sport = inet->inet_sport;
+	fl6->flowlabel = np->flow_label;
+
+	if (!fl6->flowi6_oif)
+		fl6->flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
+
+	if (!fl6->flowi6_oif && ipv6_addr_is_multicast(&fl6->daddr))
+		fl6->flowi6_oif = np->mcast_oif;
+
+	security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
+}
+
+int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr)
+{
+	struct ip6_flowlabel *flowlabel = NULL;
+	struct in6_addr *final_p, final;
+	struct ipv6_txoptions *opt;
+	struct dst_entry *dst;
+	struct inet_sock *inet = inet_sk(sk);
+	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct flowi6 fl6;
+	int err = 0;
+
+	if (np->sndflow && (np->flow_label & IPV6_FLOWLABEL_MASK)) {
+		flowlabel = fl6_sock_lookup(sk, np->flow_label);
+		if (!flowlabel)
+			return -EINVAL;
+	}
+	ip6_datagram_flow_key_init(&fl6, sk);
+
+	rcu_read_lock();
+	opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt);
+	final_p = fl6_update_dst(&fl6, opt, &final);
+	rcu_read_unlock();
+
+	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
+	if (IS_ERR(dst)) {
+		err = PTR_ERR(dst);
+		goto out;
+	}
+
+	if (fix_sk_saddr) {
+		if (ipv6_addr_any(&np->saddr))
+			np->saddr = fl6.saddr;
+
+		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
+			sk->sk_v6_rcv_saddr = fl6.saddr;
+			inet->inet_rcv_saddr = LOOPBACK4_IPV6;
+			if (sk->sk_prot->rehash)
+				sk->sk_prot->rehash(sk);
+		}
+	}
+
+	ip6_dst_store(sk, dst,
+		      ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ?
+		      &sk->sk_v6_daddr : NULL,
+#ifdef CONFIG_IPV6_SUBTREES
+		      ipv6_addr_equal(&fl6.saddr, &np->saddr) ?
+		      &np->saddr :
+#endif
+		      NULL);
+
+out:
+	fl6_sock_release(flowlabel);
+	return err;
+}
+
+void ip6_datagram_release_cb(struct sock *sk)
+{
+	struct dst_entry *dst;
+
+	if (ipv6_addr_v4mapped(&sk->sk_v6_daddr))
+		return;
+
+	rcu_read_lock();
+	dst = __sk_dst_get(sk);
+	if (!dst || !dst->obsolete ||
+	    dst->ops->check(dst, inet6_sk(sk)->dst_cookie)) {
+		rcu_read_unlock();
+		return;
+	}
+	rcu_read_unlock();
+
+	ip6_datagram_dst_update(sk, false);
+}
+EXPORT_SYMBOL_GPL(ip6_datagram_release_cb);
+
 static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct sockaddr_in6	*usin = (struct sockaddr_in6 *) uaddr;
 	struct inet_sock	*inet = inet_sk(sk);
 	struct ipv6_pinfo	*np = inet6_sk(sk);
-	struct in6_addr	*daddr, *final_p, final;
-	struct dst_entry	*dst;
-	struct flowi6		fl6;
-	struct ip6_flowlabel	*flowlabel = NULL;
-	struct ipv6_txoptions	*opt;
+	struct in6_addr		*daddr;
 	int			addr_type;
 	int			err;
+	__be32			fl6_flowlabel = 0;
 
 	if (usin->sin6_family == AF_INET) {
 		if (__ipv6_only_sock(sk))
@@ -66,15 +162,8 @@ static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int a
 	if (usin->sin6_family != AF_INET6)
 		return -EAFNOSUPPORT;
 
-	memset(&fl6, 0, sizeof(fl6));
-	if (np->sndflow) {
-		fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
-		if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
-			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
-			if (!flowlabel)
-				return -EINVAL;
-		}
-	}
+	if (np->sndflow)
+		fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK;
 
 	addr_type = ipv6_addr_type(&usin->sin6_addr);
 
@@ -145,7 +234,7 @@ ipv4_connected:
 	}
 
 	sk->sk_v6_daddr = *daddr;
-	np->flow_label = fl6.flowlabel;
+	np->flow_label = fl6_flowlabel;
 
 	inet->inet_dport = usin->sin6_port;
 
@@ -154,59 +243,13 @@ ipv4_connected:
 	 *	destination cache for it.
 	 */
 
-	fl6.flowi6_proto = sk->sk_protocol;
-	fl6.daddr = sk->sk_v6_daddr;
-	fl6.saddr = np->saddr;
-	fl6.flowi6_oif = sk->sk_bound_dev_if;
-	fl6.flowi6_mark = sk->sk_mark;
-	fl6.fl6_dport = inet->inet_dport;
-	fl6.fl6_sport = inet->inet_sport;
-
-	if (!fl6.flowi6_oif)
-		fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
-
-	if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST))
-		fl6.flowi6_oif = np->mcast_oif;
-
-	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
-
-	rcu_read_lock();
-	opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt);
-	final_p = fl6_update_dst(&fl6, opt, &final);
-	rcu_read_unlock();
-
-	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
-	err = 0;
-	if (IS_ERR(dst)) {
-		err = PTR_ERR(dst);
+	err = ip6_datagram_dst_update(sk, true);
+	if (err)
 		goto out;
-	}
-
-	/* source address lookup done in ip6_dst_lookup */
-
-	if (ipv6_addr_any(&np->saddr))
-		np->saddr = fl6.saddr;
-
-	if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
-		sk->sk_v6_rcv_saddr = fl6.saddr;
-		inet->inet_rcv_saddr = LOOPBACK4_IPV6;
-		if (sk->sk_prot->rehash)
-			sk->sk_prot->rehash(sk);
-	}
-
-	ip6_dst_store(sk, dst,
-		      ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ?
-		      &sk->sk_v6_daddr : NULL,
-#ifdef CONFIG_IPV6_SUBTREES
-		      ipv6_addr_equal(&fl6.saddr, &np->saddr) ?
-		      &np->saddr :
-#endif
-		      NULL);
 
 	sk->sk_state = TCP_ESTABLISHED;
 	sk_set_txhash(sk);
 out:
-	fl6_sock_release(flowlabel);
 	return err;
 }
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 1d8871a5ed20..d916d6ab9ad2 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1418,8 +1418,20 @@ EXPORT_SYMBOL_GPL(ip6_update_pmtu);
 
 void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
 {
+	struct dst_entry *dst;
+
 	ip6_update_pmtu(skb, sock_net(sk), mtu,
 			sk->sk_bound_dev_if, sk->sk_mark);
+
+	dst = __sk_dst_get(sk);
+	if (!dst || !dst->obsolete ||
+	    dst->ops->check(dst, inet6_sk(sk)->dst_cookie))
+		return;
+
+	bh_lock_sock(sk);
+	if (!sock_owned_by_user(sk) && !ipv6_addr_v4mapped(&sk->sk_v6_daddr))
+		ip6_datagram_dst_update(sk, false);
+	bh_unlock_sock(sk);
 }
 EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu);
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 8125931106be..6bc5c664fa46 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1539,6 +1539,7 @@ struct proto udpv6_prot = {
 	.sendmsg	   = udpv6_sendmsg,
 	.recvmsg	   = udpv6_recvmsg,
 	.backlog_rcv	   = __udpv6_queue_rcv_skb,
+	.release_cb	   = ip6_datagram_release_cb,
 	.hash		   = udp_lib_hash,
 	.unhash		   = udp_lib_unhash,
 	.rehash		   = udp_v6_rehash,