9 files changed, 29 insertions, 12 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 6c0ec2789943..cf11f10927e1 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -347,6 +347,7 @@ lookup_protocol:
 	sk->sk_destruct	   = inet_sock_destruct;
 	sk->sk_protocol	   = protocol;
 	sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;
+	sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash);
 
 	inet->uc_ttl	= -1;
 	inet->mc_loop	= 1;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index ce9ff3c62e84..3bb890a40ed7 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -30,6 +30,7 @@
 #include <linux/slab.h>
 #include <linux/netlink.h>
 #include <linux/hash.h>
+#include <linux/nospec.h>
 
 #include <net/arp.h>
 #include <net/inet_dscp.h>
@@ -1022,6 +1023,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
 		if (type > RTAX_MAX)
 			return false;
 
+		type = array_index_nospec(type, RTAX_MAX + 1);
 		if (type == RTAX_CC_ALGO) {
 			char tmp[TCP_CA_NAME_MAX];
 			bool ecn_ca = false;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index d1f837579398..f2c43f67187d 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1225,9 +1225,6 @@ int inet_csk_listen_start(struct sock *sk)
 	sk->sk_ack_backlog = 0;
 	inet_csk_delack_init(sk);
 
-	if (sk->sk_txrehash == SOCK_TXREHASH_DEFAULT)
-		sk->sk_txrehash = READ_ONCE(sock_net(sk)->core.sysctl_txrehash);
-
 	/* There is race window here: we announce ourselves listening,
 	 * but this transition is still not validated by get_port().
 	 * It is OK, because this socket enters to hash table only
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 24a38b56fab9..f58d73888638 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -650,8 +650,20 @@ 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;
@@ -660,6 +672,7 @@ 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;
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 1d77d992e6e7..beed32fff484 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -91,10 +91,10 @@ 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,
@@ -147,7 +147,7 @@ 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/metrics.c b/net/ipv4/metrics.c
index 7fcfdfd8f9de..0e3ee1532848 100644
--- a/net/ipv4/metrics.c
+++ b/net/ipv4/metrics.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 #include <linux/netlink.h>
+#include <linux/nospec.h>
 #include <linux/rtnetlink.h>
 #include <linux/types.h>
 #include <net/ip.h>
@@ -25,6 +26,7 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
 			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.c b/net/ipv4/tcp.c
index c567d5e8053e..33f559f491c8 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -435,6 +435,7 @@ void tcp_init_sock(struct sock *sk)
 
 	/* There's a bubble in the pipe until at least the first ACK. */
 	tp->app_limited = ~0U;
+	tp->rate_app_limited = 1;
 
 	/* See draft-stevens-tcpca-spec-01 for discussion of the
 	 * initialization of these values.
@@ -3178,6 +3179,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->plb_rehash = 0;
 	/* There's a bubble in the pipe until at least the first ACK. */
 	tp->app_limited = ~0U;
+	tp->rate_app_limited = 1;
 	tp->rack.mstamp = 0;
 	tp->rack.advanced = 0;
 	tp->rack.reo_wnd_steps = 1;
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 94aad3870c5f..cf26d65ca389 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -6,6 +6,7 @@
 #include <linux/bpf.h>
 #include <linux/init.h>
 #include <linux/wait.h>
+#include <linux/util_macros.h>
 
 #include <net/inet_common.h>
 #include <net/tls.h>
@@ -639,10 +640,9 @@ EXPORT_SYMBOL_GPL(tcp_bpf_update_proto);
  */
 void tcp_bpf_clone(const struct sock *sk, struct sock *newsk)
 {
-	int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
 	struct proto *prot = newsk->sk_prot;
 
-	if (prot == &tcp_bpf_prots[family][TCP_BPF_BASE])
+	if (is_insidevar(prot, tcp_bpf_prots))
 		newsk->sk_prot = sk->sk_prot_creator;
 }
 #endif /* CONFIG_BPF_SYSCALL */
diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c
index 05b6077b9f2c..2aa442128630 100644
--- a/net/ipv4/tcp_ulp.c
+++ b/net/ipv4/tcp_ulp.c
@@ -139,7 +139,7 @@ static int __tcp_set_ulp(struct sock *sk, const struct tcp_ulp_ops *ulp_ops)
 	if (sk->sk_socket)
 		clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
 
-	err = -EINVAL;
+	err = -ENOTCONN;
 	if (!ulp_ops->clone && sk->sk_state == TCP_LISTEN)
 		goto out_err;