Merging upstream version 4.19.269.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

9 files changed, 63 insertions, 34 deletions

diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index c7dc8b2de..7fdd433b9 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -437,6 +437,7 @@ static void ip6addrlbl_putmsg(struct nlmsghdr *nlh,
 {
 	struct ifaddrlblmsg *ifal = nlmsg_data(nlh);
 	ifal->ifal_family = AF_INET6;
+	ifal->__ifal_reserved = 0;
 	ifal->ifal_prefixlen = prefixlen;
 	ifal->ifal_flags = 0;
 	ifal->ifal_index = ifindex;
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 57d84accb..2bdb03a45 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -47,18 +47,25 @@
 #include <net/inet_ecn.h>
 #include <net/dst_metadata.h>
 
+void udp_v6_early_demux(struct sk_buff *);
+void tcp_v6_early_demux(struct sk_buff *);
 static void ip6_rcv_finish_core(struct net *net, struct sock *sk,
 				struct sk_buff *skb)
 {
-	void (*edemux)(struct sk_buff *skb);
-
-	if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
-		const struct inet6_protocol *ipprot;
-
-		ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]);
-		if (ipprot && (edemux = READ_ONCE(ipprot->early_demux)))
-			edemux(skb);
+	if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) &&
+	    !skb_dst(skb) && !skb->sk) {
+		switch (ipv6_hdr(skb)->nexthdr) {
+		case IPPROTO_TCP:
+			if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux))
+				tcp_v6_early_demux(skb);
+			break;
+		case IPPROTO_UDP:
+			if (READ_ONCE(net->ipv4.sysctl_udp_early_demux))
+				udp_v6_early_demux(skb);
+			break;
+		}
 	}
+
 	if (!skb_valid_dst(skb))
 		ip6_route_input(skb);
 }
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 6fd1a4b61..70820d049 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -734,6 +734,9 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		ipv6_hdr(skb)->payload_len = htons(first_len -
 						   sizeof(struct ipv6hdr));
 
+		/* We prevent @rt from being freed. */
+		rcu_read_lock();
+
 		for (;;) {
 			/* Prepare header of the next frame,
 			 * before previous one went down. */
@@ -776,6 +779,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		if (err == 0) {
 			IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
 				      IPSTATS_MIB_FRAGOKS);
+			rcu_read_unlock();
 			return 0;
 		}
 
@@ -783,6 +787,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 
 		IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
 			      IPSTATS_MIB_FRAGFAILS);
+		rcu_read_unlock();
 		return err;
 
 slow_path_clean:
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 4e1da6cb9..4f958d24f 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -166,6 +166,12 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		rtnl_lock();
 	lock_sock(sk);
 
+	/* Another thread has converted the socket into IPv4 with
+	 * IPV6_ADDRFORM concurrently.
+	 */
+	if (unlikely(sk->sk_family != AF_INET6))
+		goto unlock;
+
 	switch (optname) {
 
 	case IPV6_ADDRFORM:
@@ -913,6 +919,7 @@ pref_skip_coa:
 		break;
 	}
 
+unlock:
 	release_sock(sk);
 	if (needs_rtnl)
 		rtnl_unlock();
diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c
index 36be3cf0a..fa71e4078 100644
--- a/net/ipv6/netfilter/nft_fib_ipv6.c
+++ b/net/ipv6/netfilter/nft_fib_ipv6.c
@@ -41,6 +41,9 @@ static int nft_fib6_flowi_init(struct flowi6 *fl6, const struct nft_fib *priv,
 	if (ipv6_addr_type(&fl6->daddr) & IPV6_ADDR_LINKLOCAL) {
 		lookup_flags |= RT6_LOOKUP_F_IFACE;
 		fl6->flowi6_oif = get_ifindex(dev ? dev : pkt->skb->dev);
+	} else if ((priv->flags & NFTA_FIB_F_IIF) &&
+		   (netif_is_l3_master(dev) || netif_is_l3_slave(dev))) {
+		fl6->flowi6_oif = dev->ifindex;
 	}
 
 	if (ipv6_addr_type(&fl6->saddr) & IPV6_ADDR_UNICAST)
@@ -189,7 +192,8 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs,
 	if (rt->rt6i_flags & (RTF_REJECT | RTF_ANYCAST | RTF_LOCAL))
 		goto put_rt_err;
 
-	if (oif && oif != rt->rt6i_idev->dev)
+	if (oif && oif != rt->rt6i_idev->dev &&
+	    l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) != oif->ifindex)
 		goto put_rt_err;
 
 	switch (priv->result) {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index b940285a1..7b41d5d35 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -5374,10 +5374,16 @@ static void __net_exit ip6_route_net_exit(struct net *net)
 static int __net_init ip6_route_net_init_late(struct net *net)
 {
 #ifdef CONFIG_PROC_FS
-	proc_create_net("ipv6_route", 0, net->proc_net, &ipv6_route_seq_ops,
-			sizeof(struct ipv6_route_iter));
-	proc_create_net_single("rt6_stats", 0444, net->proc_net,
-			rt6_stats_seq_show, NULL);
+	if (!proc_create_net("ipv6_route", 0, net->proc_net,
+			     &ipv6_route_seq_ops,
+			     sizeof(struct ipv6_route_iter)))
+		return -ENOMEM;
+
+	if (!proc_create_net_single("rt6_stats", 0444, net->proc_net,
+				    rt6_stats_seq_show, NULL)) {
+		remove_proc_entry("ipv6_route", net->proc_net);
+		return -ENOMEM;
+	}
 #endif
 	return 0;
 }
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index c9ba827ad..babf69b24 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -97,7 +97,7 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 	if (dst && dst_hold_safe(dst)) {
 		const struct rt6_info *rt = (const struct rt6_info *)dst;
 
-		sk->sk_rx_dst = dst;
+		rcu_assign_pointer(sk->sk_rx_dst, dst);
 		inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
 		inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt);
 	}
@@ -327,6 +327,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 late_failure:
 	tcp_set_state(sk, TCP_CLOSE);
+	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
+		inet_reset_saddr(sk);
 failure:
 	inet->inet_dport = 0;
 	sk->sk_route_caps = 0;
@@ -1344,15 +1346,18 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 		opt_skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC));
 
 	if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
-		struct dst_entry *dst = sk->sk_rx_dst;
+		struct dst_entry *dst;
+
+		dst = rcu_dereference_protected(sk->sk_rx_dst,
+						lockdep_sock_is_held(sk));
 
 		sock_rps_save_rxhash(sk, skb);
 		sk_mark_napi_id(sk, skb);
 		if (dst) {
 			if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
 			    dst->ops->check(dst, np->rx_dst_cookie) == NULL) {
+				RCU_INIT_POINTER(sk->sk_rx_dst, NULL);
 				dst_release(dst);
-				sk->sk_rx_dst = NULL;
 			}
 		}
 
@@ -1670,7 +1675,7 @@ do_time_wait:
 	goto discard_it;
 }
 
-static void tcp_v6_early_demux(struct sk_buff *skb)
+void tcp_v6_early_demux(struct sk_buff *skb)
 {
 	const struct ipv6hdr *hdr;
 	const struct tcphdr *th;
@@ -1697,7 +1702,7 @@ static void tcp_v6_early_demux(struct sk_buff *skb)
 		skb->sk = sk;
 		skb->destructor = sock_edemux;
 		if (sk_fullsock(sk)) {
-			struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst);
+			struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst);
 
 			if (dst)
 				dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie);
@@ -2025,12 +2030,7 @@ struct proto tcpv6_prot = {
 	.diag_destroy		= tcp_abort,
 };
 
-/* thinking of making this const? Don't.
- * early_demux can change based on sysctl.
- */
-static struct inet6_protocol tcpv6_protocol = {
-	.early_demux	=	tcp_v6_early_demux,
-	.early_demux_handler =  tcp_v6_early_demux,
+static const struct inet6_protocol tcpv6_protocol = {
 	.handler	=	tcp_v6_rcv,
 	.err_handler	=	tcp_v6_err,
 	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 7d3caafdf..9b0cae403 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -828,7 +828,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		struct dst_entry *dst = skb_dst(skb);
 		int ret;
 
-		if (unlikely(sk->sk_rx_dst != dst))
+		if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst))
 			udp6_sk_rx_dst_set(sk, dst);
 
 		if (!uh->check && !udp_sk(sk)->no_check6_rx) {
@@ -912,7 +912,7 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net,
 	return NULL;
 }
 
-static void udp_v6_early_demux(struct sk_buff *skb)
+void udp_v6_early_demux(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
 	const struct udphdr *uh;
@@ -940,7 +940,7 @@ static void udp_v6_early_demux(struct sk_buff *skb)
 
 	skb->sk = sk;
 	skb->destructor = sock_efree;
-	dst = READ_ONCE(sk->sk_rx_dst);
+	dst = rcu_dereference(sk->sk_rx_dst);
 
 	if (dst)
 		dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie);
@@ -1533,12 +1533,7 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
 }
 #endif
 
-/* thinking of making this const? Don't.
- * early_demux can change based on sysctl.
- */
-static struct inet6_protocol udpv6_protocol = {
-	.early_demux	=	udp_v6_early_demux,
-	.early_demux_handler =  udp_v6_early_demux,
+static const struct inet6_protocol udpv6_protocol = {
 	.handler	=	udpv6_rcv,
 	.err_handler	=	udpv6_err,
 	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 30232591c..1925fb91e 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -416,9 +416,13 @@ int __init xfrm6_init(void)
 	if (ret)
 		goto out_state;
 
-	register_pernet_subsys(&xfrm6_net_ops);
+	ret = register_pernet_subsys(&xfrm6_net_ops);
+	if (ret)
+		goto out_protocol;
 out:
 	return ret;
+out_protocol:
+	xfrm6_protocol_fini();
 out_state:
 	xfrm6_state_fini();
 out_policy: