Merging upstream version 4.19.282.

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

13 files changed, 75 insertions, 32 deletions

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 1885a2fba..9aa48b4c4 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -557,6 +557,9 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt,
 			cfg->fc_scope = RT_SCOPE_UNIVERSE;
 	}
 
+	if (!cfg->fc_table)
+		cfg->fc_table = RT_TABLE_MAIN;
+
 	if (cmd == SIOCDELRT)
 		return 0;
 
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index aa179e646..af0ddaa55 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -759,6 +759,11 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 		room = 576;
 	room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen;
 	room -= sizeof(struct icmphdr);
+	/* Guard against tiny mtu. We need to include at least one
+	 * IP network header for this message to make any sense.
+	 */
+	if (room <= (int)sizeof(struct iphdr))
+		goto ende;
 
 	icmp_param.data_len = skb_in->len - icmp_param.offset;
 	if (icmp_param.data_len > room)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 0a69f92da..0f9085220 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -903,11 +903,25 @@ void inet_csk_prepare_forced_close(struct sock *sk)
 }
 EXPORT_SYMBOL(inet_csk_prepare_forced_close);
 
+static int inet_ulp_can_listen(const struct sock *sk)
+{
+	const struct inet_connection_sock *icsk = inet_csk(sk);
+
+	if (icsk->icsk_ulp_ops)
+		return -EINVAL;
+
+	return 0;
+}
+
 int inet_csk_listen_start(struct sock *sk, int backlog)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct inet_sock *inet = inet_sk(sk);
-	int err = -EADDRINUSE;
+	int err;
+
+	err = inet_ulp_can_listen(sk);
+	if (unlikely(err))
+		return err;
 
 	reqsk_queue_alloc(&icsk->icsk_accept_queue);
 
@@ -920,6 +934,7 @@ int inet_csk_listen_start(struct sock *sk, int backlog)
 	 * It is OK, because this socket enters to hash table only
 	 * after validation is complete.
 	 */
+	err = -EADDRINUSE;
 	inet_sk_state_store(sk, TCP_LISTEN);
 	if (!sk->sk_prot->get_port(sk, inet->inet_num)) {
 		inet->inet_sport = htons(inet->inet_num);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 3c58019f0..5a272d09b 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -579,8 +579,20 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
 	spin_lock(lock);
 	if (osk) {
 		WARN_ON_ONCE(sk->sk_hash != osk->sk_hash);
-		ret = sk_nulls_del_node_init_rcu(osk);
-	} else if (found_dup_sk) {
+		ret = sk_hashed(osk);
+		if (ret) {
+			/* Before deleting the node, we insert a new one to make
+			 * sure that the look-up-sk process would not miss either
+			 * of them and that at least one node would exist in ehash
+			 * table all the time. Otherwise there's a tiny chance
+			 * that lookup process could find nothing in ehash table.
+			 */
+			__sk_nulls_add_node_tail_rcu(sk, list);
+			sk_nulls_del_node_init_rcu(osk);
+		}
+		goto unlock;
+	}
+	if (found_dup_sk) {
 		*found_dup_sk = inet_ehash_lookup_by_sk(sk, list);
 		if (*found_dup_sk)
 			ret = false;
@@ -589,6 +601,7 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
 	if (ret)
 		__sk_nulls_add_node_rcu(sk, list);
 
+unlock:
 	spin_unlock(lock);
 
 	return ret;
@@ -743,17 +756,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 	u32 index;
 
 	if (port) {
-		head = &hinfo->bhash[inet_bhashfn(net, port,
-						  hinfo->bhash_size)];
-		tb = inet_csk(sk)->icsk_bind_hash;
-		spin_lock_bh(&head->lock);
-		if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
-			inet_ehash_nolisten(sk, NULL, NULL);
-			spin_unlock_bh(&head->lock);
-			return 0;
-		}
-		spin_unlock(&head->lock);
-		/* No definite answer... Walk to established hash table */
+		local_bh_disable();
 		ret = check_established(death_row, sk, port, NULL);
 		local_bh_enable();
 		return ret;
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 88c5069b5..fedd19c22 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -80,10 +80,10 @@ void inet_twsk_put(struct inet_timewait_sock *tw)
 }
 EXPORT_SYMBOL_GPL(inet_twsk_put);
 
-static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
-				   struct hlist_nulls_head *list)
+static void inet_twsk_add_node_tail_rcu(struct inet_timewait_sock *tw,
+					struct hlist_nulls_head *list)
 {
-	hlist_nulls_add_head_rcu(&tw->tw_node, list);
+	hlist_nulls_add_tail_rcu(&tw->tw_node, list);
 }
 
 static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
@@ -119,7 +119,7 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 
 	spin_lock(lock);
 
-	inet_twsk_add_node_rcu(tw, &ehead->chain);
+	inet_twsk_add_node_tail_rcu(tw, &ehead->chain);
 
 	/* Step 3: Remove SK from hash chain */
 	if (__sk_nulls_del_node_init_rcu(sk))
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index c72432ce9..898753328 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -603,7 +603,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev)
 		truncate = true;
 	}
 
-	nhoff = skb_network_header(skb) - skb_mac_header(skb);
+	nhoff = skb_network_offset(skb);
 	if (skb->protocol == htons(ETH_P_IP) &&
 	    (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff))
 		truncate = true;
@@ -612,7 +612,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev)
 		int thoff;
 
 		if (skb_transport_header_was_set(skb))
-			thoff = skb_transport_header(skb) - skb_mac_header(skb);
+			thoff = skb_transport_offset(skb);
 		else
 			thoff = nhoff + sizeof(struct ipv6hdr);
 		if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 30e93b4f8..9c2381cf6 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -609,10 +609,10 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto)
 	else if (skb->protocol == htons(ETH_P_IP))
 		df = inner_iph->frag_off & htons(IP_DF);
 	headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len;
-	if (headroom > dev->needed_headroom)
-		dev->needed_headroom = headroom;
+	if (headroom > READ_ONCE(dev->needed_headroom))
+		WRITE_ONCE(dev->needed_headroom, headroom);
 
-	if (skb_cow_head(skb, dev->needed_headroom)) {
+	if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) {
 		ip_rt_put(rt);
 		goto tx_dropped;
 	}
@@ -777,10 +777,10 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 
 	max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
 			+ rt->dst.header_len + ip_encap_hlen(&tunnel->encap);
-	if (max_headroom > dev->needed_headroom)
-		dev->needed_headroom = max_headroom;
+	if (max_headroom > READ_ONCE(dev->needed_headroom))
+		WRITE_ONCE(dev->needed_headroom, max_headroom);
 
-	if (skb_cow_head(skb, dev->needed_headroom)) {
+	if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) {
 		ip_rt_put(rt);
 		dev->stats.tx_dropped++;
 		kfree_skb(skb);
diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c
index 04311f706..9a6b01d85 100644
--- a/net/ipv4/metrics.c
+++ b/net/ipv4/metrics.c
@@ -1,4 +1,5 @@
 #include <linux/netlink.h>
+#include <linux/nospec.h>
 #include <linux/rtnetlink.h>
 #include <linux/types.h>
 #include <net/ip.h>
@@ -24,6 +25,7 @@ int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, int fc_mx_len,
 		if (type > RTAX_MAX)
 			return -EINVAL;
 
+		type = array_index_nospec(type, RTAX_MAX + 1);
 		if (type == RTAX_CC_ALGO) {
 			char tmp[TCP_CA_NAME_MAX];
 
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 0fc238d79..bae0199a9 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -582,6 +582,9 @@ EXPORT_SYMBOL(tcp_create_openreq_child);
  * validation and inside tcp_v4_reqsk_send_ack(). Can we do better?
  *
  * We don't need to initialize tmp_opt.sack_ok as we don't use the results
+ *
+ * Note: If @fastopen is true, this can be called from process context.
+ *       Otherwise, this is from BH context.
  */
 
 struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
@@ -734,7 +737,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 					  &tcp_rsk(req)->last_oow_ack_time))
 			req->rsk_ops->send_ack(sk, skb, req);
 		if (paws_reject)
-			__NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
 		return NULL;
 	}
 
@@ -753,7 +756,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	 *	   "fourth, check the SYN bit"
 	 */
 	if (flg & (TCP_FLAG_RST|TCP_FLAG_SYN)) {
-		__TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS);
+		TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS);
 		goto embryonic_reset;
 	}
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 896286422..9299de0da 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3307,7 +3307,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	th->window = htons(min(req->rsk_rcv_wnd, 65535U));
 	tcp_options_write((__be32 *)(th + 1), NULL, &opts);
 	th->doff = (tcp_header_size >> 2);
-	__TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
+	TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
 
 #ifdef CONFIG_TCP_MD5SIG
 	/* Okay, we have all we need - do the md5 hash if needed */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index dd3fa0ff8..a6048cc7f 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1458,7 +1458,7 @@ drop:
 }
 EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb);
 
-void udp_destruct_sock(struct sock *sk)
+void udp_destruct_common(struct sock *sk)
 {
 	/* reclaim completely the forward allocated memory */
 	struct udp_sock *up = udp_sk(sk);
@@ -1471,10 +1471,14 @@ void udp_destruct_sock(struct sock *sk)
 		kfree_skb(skb);
 	}
 	udp_rmem_release(sk, total, 0, true);
+}
+EXPORT_SYMBOL_GPL(udp_destruct_common);
 
+static void udp_destruct_sock(struct sock *sk)
+{
+	udp_destruct_common(sk);
 	inet_sock_destruct(sk);
 }
-EXPORT_SYMBOL_GPL(udp_destruct_sock);
 
 int udp_init_sock(struct sock *sk)
 {
@@ -1482,7 +1486,6 @@ int udp_init_sock(struct sock *sk)
 	sk->sk_destruct = udp_destruct_sock;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(udp_init_sock);
 
 void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
 {
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 6539ff15e..d03d74388 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -186,6 +186,7 @@ EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb);
 void udp_tunnel_sock_release(struct socket *sock)
 {
 	rcu_assign_sk_user_data(sock->sk, NULL);
+	synchronize_rcu();
 	kernel_sock_shutdown(sock, SHUT_RDWR);
 	sock_release(sock);
 }
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index 854545775..6beab353b 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -20,6 +20,14 @@
 struct udp_table 	udplite_table __read_mostly;
 EXPORT_SYMBOL(udplite_table);
 
+/* Designate sk as UDP-Lite socket */
+static int udplite_sk_init(struct sock *sk)
+{
+	udp_init_sock(sk);
+	udp_sk(sk)->pcflag = UDPLITE_BIT;
+	return 0;
+}
+
 static int udplite_rcv(struct sk_buff *skb)
 {
 	return __udp4_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE);