28 files changed, 205 insertions, 109 deletions

diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index e983bb0c5012..2dfb12230f08 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -402,6 +402,16 @@ config INET_IPCOMP
 
 	  If unsure, say Y.
 
+config INET_TABLE_PERTURB_ORDER
+	int "INET: Source port perturbation table size (as power of 2)" if EXPERT
+	default 16
+	help
+	  Source port perturbation table size (as power of 2) for
+	  RFC 6056 3.3.4.  Algorithm 4: Double-Hash Port Selection Algorithm.
+
+	  The default is almost always what you want.
+	  Only change this if you know what you are doing.
+
 config INET_XFRM_TUNNEL
 	tristate
 	select INET_TUNNEL
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 3dd02396517d..0da679411330 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -754,6 +754,8 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags,
 		  (TCPF_ESTABLISHED | TCPF_SYN_RECV |
 		  TCPF_CLOSE_WAIT | TCPF_CLOSE)));
 
+	if (test_bit(SOCK_SUPPORT_ZC, &sock->flags))
+		set_bit(SOCK_SUPPORT_ZC, &newsock->flags);
 	sock_graft(sk2, newsock);
 
 	newsock->state = SS_CONNECTED;
@@ -1228,7 +1230,6 @@ EXPORT_SYMBOL(inet_unregister_protosw);
 
 static int inet_sk_reselect_saddr(struct sock *sk)
 {
-	struct inet_bind_hashbucket *prev_addr_hashbucket;
 	struct inet_sock *inet = inet_sk(sk);
 	__be32 old_saddr = inet->inet_saddr;
 	__be32 daddr = inet->inet_daddr;
@@ -1258,16 +1259,8 @@ static int inet_sk_reselect_saddr(struct sock *sk)
 		return 0;
 	}
 
-	prev_addr_hashbucket =
-		inet_bhashfn_portaddr(tcp_or_dccp_get_hashinfo(sk), sk,
-				      sock_net(sk), inet->inet_num);
-
-	inet->inet_saddr = inet->inet_rcv_saddr = new_saddr;
-
-	err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk);
+	err = inet_bhash2_update_saddr(sk, &new_saddr, AF_INET);
 	if (err) {
-		inet->inet_saddr = old_saddr;
-		inet->inet_rcv_saddr = old_saddr;
 		ip_rt_put(rt);
 		return err;
 	}
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 0ee7fd259730..4d1af0cd7d99 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -70,7 +70,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
 	}
 	inet->inet_daddr = fl4->daddr;
 	inet->inet_dport = usin->sin_port;
-	reuseport_has_conns(sk, true);
+	reuseport_has_conns_set(sk);
 	sk->sk_state = TCP_ESTABLISHED;
 	sk_set_txhash(sk);
 	inet->inet_id = get_random_u16();
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index e8b9a9202fec..b0acf6e19aed 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -234,13 +234,20 @@ static void inet_free_ifa(struct in_ifaddr *ifa)
 	call_rcu(&ifa->rcu_head, inet_rcu_free_ifa);
 }
 
+static void in_dev_free_rcu(struct rcu_head *head)
+{
+	struct in_device *idev = container_of(head, struct in_device, rcu_head);
+
+	kfree(rcu_dereference_protected(idev->mc_hash, 1));
+	kfree(idev);
+}
+
 void in_dev_finish_destroy(struct in_device *idev)
 {
 	struct net_device *dev = idev->dev;
 
 	WARN_ON(idev->ifa_list);
 	WARN_ON(idev->mc_list);
-	kfree(rcu_dereference_protected(idev->mc_hash, 1));
 #ifdef NET_REFCNT_DEBUG
 	pr_debug("%s: %p=%s\n", __func__, idev, dev ? dev->name : "NIL");
 #endif
@@ -248,7 +255,7 @@ void in_dev_finish_destroy(struct in_device *idev)
 	if (!idev->dead)
 		pr_err("Freeing alive in_device %p\n", idev);
 	else
-		kfree(idev);
+		call_rcu(&idev->rcu_head, in_dev_free_rcu);
 }
 EXPORT_SYMBOL(in_dev_finish_destroy);
 
@@ -298,12 +305,6 @@ out_kfree:
 	goto out;
 }
 
-static void in_dev_rcu_put(struct rcu_head *head)
-{
-	struct in_device *idev = container_of(head, struct in_device, rcu_head);
-	in_dev_put(idev);
-}
-
 static void inetdev_destroy(struct in_device *in_dev)
 {
 	struct net_device *dev;
@@ -328,7 +329,7 @@ static void inetdev_destroy(struct in_device *in_dev)
 	neigh_parms_release(&arp_tbl, in_dev->arp_parms);
 	arp_ifdown(dev);
 
-	call_rcu(&in_dev->rcu_head, in_dev_rcu_put);
+	in_dev_put(in_dev);
 }
 
 int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b)
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 170152772d33..3969fa805679 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -314,6 +314,9 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb,  netdev_features_
 			xo->seq.low += skb_shinfo(skb)->gso_segs;
 	}
 
+	if (xo->seq.low < seq)
+		xo->seq.hi++;
+
 	esp.seqno = cpu_to_be64(seq + ((u64)xo->seq.hi << 32));
 
 	ip_hdr(skb)->tot_len = htons(skb->len);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 943edf4ad4db..b5736ef16ed2 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -389,7 +389,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	dev_match = dev_match || (res.type == RTN_LOCAL &&
 				  dev == net->loopback_dev);
 	if (dev_match) {
-		ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_LINK;
+		ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
 		return ret;
 	}
 	if (no_addr)
@@ -401,7 +401,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	ret = 0;
 	if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) {
 		if (res.type == RTN_UNICAST)
-			ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_LINK;
+			ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
 	}
 	return ret;
 
@@ -841,6 +841,9 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 		return -EINVAL;
 	}
 
+	if (!cfg->fc_table)
+		cfg->fc_table = RT_TABLE_MAIN;
+
 	return 0;
 errout:
 	return err;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index e9a7f70a54df..ce9ff3c62e84 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -423,6 +423,7 @@ static struct fib_info *fib_find_info(struct fib_info *nfi)
 		    nfi->fib_prefsrc == fi->fib_prefsrc &&
 		    nfi->fib_priority == fi->fib_priority &&
 		    nfi->fib_type == fi->fib_type &&
+		    nfi->fib_tb_id == fi->fib_tb_id &&
 		    memcmp(nfi->fib_metrics, fi->fib_metrics,
 			   sizeof(u32) * RTAX_MAX) == 0 &&
 		    !((nfi->fib_flags ^ fi->fib_flags) & ~RTNH_COMPARE_MASK) &&
@@ -888,9 +889,11 @@ int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi,
 		return 1;
 	}
 
-	/* cannot match on nexthop object attributes */
-	if (fi->nh)
-		return 1;
+	if (fi->nh) {
+		if (cfg->fc_oif || cfg->fc_gw_family || cfg->fc_mp)
+			return 1;
+		return 0;
+	}
 
 	if (cfg->fc_oif || cfg->fc_gw_family) {
 		struct fib_nh *nh;
@@ -1231,7 +1234,7 @@ static int fib_check_nh_nongw(struct net *net, struct fib_nh *nh,
 
 	nh->fib_nh_dev = in_dev->dev;
 	netdev_hold(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC);
-	nh->fib_nh_scope = RT_SCOPE_LINK;
+	nh->fib_nh_scope = RT_SCOPE_HOST;
 	if (!netif_carrier_ok(nh->fib_nh_dev))
 		nh->fib_nh_flags |= RTNH_F_LINKDOWN;
 	err = 0;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 452ff177e4da..74d403dbd2b4 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -126,7 +126,7 @@ struct key_vector {
 		/* This list pointer if valid if (pos | bits) == 0 (LEAF) */
 		struct hlist_head leaf;
 		/* This array is valid if (pos | bits) > 0 (TNODE) */
-		struct key_vector __rcu *tnode[0];
+		DECLARE_FLEX_ARRAY(struct key_vector __rcu *, tnode);
 	};
 };
 
@@ -1381,8 +1381,10 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
 
 	/* The alias was already inserted, so the node must exist. */
 	l = l ? l : fib_find_node(t, &tp, key);
-	if (WARN_ON_ONCE(!l))
+	if (WARN_ON_ONCE(!l)) {
+		err = -ENOENT;
 		goto out_free_new_fa;
+	}
 
 	if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) ==
 	    new_fa) {
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index d5d745c3e345..46aa2d65e40a 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -263,7 +263,7 @@ bool icmp_global_allow(void)
 		/* We want to use a credit of one in average, but need to randomize
 		 * it for security reasons.
 		 */
-		credit = max_t(int, credit - prandom_u32_max(3), 0);
+		credit = max_t(int, credit - get_random_u32_below(3), 0);
 		rc = true;
 	}
 	WRITE_ONCE(icmp_global.credit, credit);
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 81be3e0f0e70..c920aa9a62a9 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -213,7 +213,7 @@ static void igmp_stop_timer(struct ip_mc_list *im)
 /* It must be called with locked im->lock */
 static void igmp_start_timer(struct ip_mc_list *im, int max_delay)
 {
-	int tv = prandom_u32_max(max_delay);
+	int tv = get_random_u32_below(max_delay);
 
 	im->tm_running = 1;
 	if (!mod_timer(&im->timer, jiffies+tv+2))
@@ -222,7 +222,7 @@ static void igmp_start_timer(struct ip_mc_list *im, int max_delay)
 
 static void igmp_gq_start_timer(struct in_device *in_dev)
 {
-	int tv = prandom_u32_max(in_dev->mr_maxdelay);
+	int tv = get_random_u32_below(in_dev->mr_maxdelay);
 	unsigned long exp = jiffies + tv + 2;
 
 	if (in_dev->mr_gq_running &&
@@ -236,7 +236,7 @@ static void igmp_gq_start_timer(struct in_device *in_dev)
 
 static void igmp_ifc_start_timer(struct in_device *in_dev, int delay)
 {
-	int tv = prandom_u32_max(delay);
+	int tv = get_random_u32_below(delay);
 
 	if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2))
 		in_dev_hold(in_dev);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 4e84ed21d16f..f22051219b50 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -314,7 +314,7 @@ other_half_scan:
 	if (likely(remaining > 1))
 		remaining &= ~1U;
 
-	offset = prandom_u32_max(remaining);
+	offset = get_random_u32_below(remaining);
 	/* __inet_hash_connect() favors ports having @low parity
 	 * We do the opposite to not pollute connect() users.
 	 */
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index d3dc28156622..d039b4e732a3 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -858,34 +858,80 @@ inet_bhash2_addr_any_hashbucket(const struct sock *sk, const struct net *net, in
 	return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)];
 }
 
-int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct sock *sk)
+static void inet_update_saddr(struct sock *sk, void *saddr, int family)
+{
+	if (family == AF_INET) {
+		inet_sk(sk)->inet_saddr = *(__be32 *)saddr;
+		sk_rcv_saddr_set(sk, inet_sk(sk)->inet_saddr);
+	}
+#if IS_ENABLED(CONFIG_IPV6)
+	else {
+		sk->sk_v6_rcv_saddr = *(struct in6_addr *)saddr;
+	}
+#endif
+}
+
+static int __inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family, bool reset)
 {
 	struct inet_hashinfo *hinfo = tcp_or_dccp_get_hashinfo(sk);
+	struct inet_bind_hashbucket *head, *head2;
 	struct inet_bind2_bucket *tb2, *new_tb2;
 	int l3mdev = inet_sk_bound_l3mdev(sk);
-	struct inet_bind_hashbucket *head2;
 	int port = inet_sk(sk)->inet_num;
 	struct net *net = sock_net(sk);
+	int bhash;
+
+	if (!inet_csk(sk)->icsk_bind2_hash) {
+		/* Not bind()ed before. */
+		if (reset)
+			inet_reset_saddr(sk);
+		else
+			inet_update_saddr(sk, saddr, family);
+
+		return 0;
+	}
 
 	/* Allocate a bind2 bucket ahead of time to avoid permanently putting
 	 * the bhash2 table in an inconsistent state if a new tb2 bucket
 	 * allocation fails.
 	 */
 	new_tb2 = kmem_cache_alloc(hinfo->bind2_bucket_cachep, GFP_ATOMIC);
-	if (!new_tb2)
+	if (!new_tb2) {
+		if (reset) {
+			/* The (INADDR_ANY, port) bucket might have already
+			 * been freed, then we cannot fixup icsk_bind2_hash,
+			 * so we give up and unlink sk from bhash/bhash2 not
+			 * to leave inconsistency in bhash2.
+			 */
+			inet_put_port(sk);
+			inet_reset_saddr(sk);
+		}
+
 		return -ENOMEM;
+	}
 
+	bhash = inet_bhashfn(net, port, hinfo->bhash_size);
+	head = &hinfo->bhash[bhash];
 	head2 = inet_bhashfn_portaddr(hinfo, sk, net, port);
 
-	if (prev_saddr) {
-		spin_lock_bh(&prev_saddr->lock);
-		__sk_del_bind2_node(sk);
-		inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep,
-					  inet_csk(sk)->icsk_bind2_hash);
-		spin_unlock_bh(&prev_saddr->lock);
-	}
+	/* If we change saddr locklessly, another thread
+	 * iterating over bhash might see corrupted address.
+	 */
+	spin_lock_bh(&head->lock);
 
-	spin_lock_bh(&head2->lock);
+	spin_lock(&head2->lock);
+	__sk_del_bind2_node(sk);
+	inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, inet_csk(sk)->icsk_bind2_hash);
+	spin_unlock(&head2->lock);
+
+	if (reset)
+		inet_reset_saddr(sk);
+	else
+		inet_update_saddr(sk, saddr, family);
+
+	head2 = inet_bhashfn_portaddr(hinfo, sk, net, port);
+
+	spin_lock(&head2->lock);
 	tb2 = inet_bind2_bucket_find(head2, net, port, l3mdev, sk);
 	if (!tb2) {
 		tb2 = new_tb2;
@@ -893,26 +939,40 @@ int inet_bhash2_update_saddr(struct inet_bind_hashbucket *prev_saddr, struct soc
 	}
 	sk_add_bind2_node(sk, &tb2->owners);
 	inet_csk(sk)->icsk_bind2_hash = tb2;
-	spin_unlock_bh(&head2->lock);
+	spin_unlock(&head2->lock);
+
+	spin_unlock_bh(&head->lock);
 
 	if (tb2 != new_tb2)
 		kmem_cache_free(hinfo->bind2_bucket_cachep, new_tb2);
 
 	return 0;
 }
+
+int inet_bhash2_update_saddr(struct sock *sk, void *saddr, int family)
+{
+	return __inet_bhash2_update_saddr(sk, saddr, family, false);
+}
 EXPORT_SYMBOL_GPL(inet_bhash2_update_saddr);
 
+void inet_bhash2_reset_saddr(struct sock *sk)
+{
+	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
+		__inet_bhash2_update_saddr(sk, NULL, 0, true);
+}
+EXPORT_SYMBOL_GPL(inet_bhash2_reset_saddr);
+
 /* RFC 6056 3.3.4.  Algorithm 4: Double-Hash Port Selection Algorithm
  * Note that we use 32bit integers (vs RFC 'short integers')
  * because 2^16 is not a multiple of num_ephemeral and this
  * property might be used by clever attacker.
+ *
  * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, though
- * attacks were since demonstrated, thus we use 65536 instead to really
- * give more isolation and privacy, at the expense of 256kB of kernel
- * memory.
+ * attacks were since demonstrated, thus we use 65536 by default instead
+ * to really give more isolation and privacy, at the expense of 256kB
+ * of kernel memory.
  */
-#define INET_TABLE_PERTURB_SHIFT 16
-#define INET_TABLE_PERTURB_SIZE (1 << INET_TABLE_PERTURB_SHIFT)
+#define INET_TABLE_PERTURB_SIZE (1 << CONFIG_INET_TABLE_PERTURB_ORDER)
 static u32 *table_perturb;
 
 int __inet_hash_connect(struct inet_timewait_death_row *death_row,
@@ -1037,7 +1097,7 @@ ok:
 	 * on low contention the randomness is maximal and on high contention
 	 * it may be inexistent.
 	 */
-	i = max_t(int, i, prandom_u32_max(8) * 2);
+	i = max_t(int, i, get_random_u32_below(8) * 2);
 	WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2);
 
 	/* Head lock still held and bh's disabled */
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index f866d6282b2b..cae9f1a4e059 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1492,24 +1492,6 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	struct ip_tunnel_parm *p = &t->parms;
 	__be16 o_flags = p->o_flags;
 
-	if (t->erspan_ver <= 2) {
-		if (t->erspan_ver != 0 && !t->collect_md)
-			o_flags |= TUNNEL_KEY;
-
-		if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver))
-			goto nla_put_failure;
-
-		if (t->erspan_ver == 1) {
-			if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index))
-				goto nla_put_failure;
-		} else if (t->erspan_ver == 2) {
-			if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir))
-				goto nla_put_failure;
-			if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid))
-				goto nla_put_failure;
-		}
-	}
-
 	if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) ||
 	    nla_put_be16(skb, IFLA_GRE_IFLAGS,
 			 gre_tnl_flags_to_gre_flags(p->i_flags)) ||
@@ -1550,6 +1532,34 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+static int erspan_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+	struct ip_tunnel *t = netdev_priv(dev);
+
+	if (t->erspan_ver <= 2) {
+		if (t->erspan_ver != 0 && !t->collect_md)
+			t->parms.o_flags |= TUNNEL_KEY;
+
+		if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver))
+			goto nla_put_failure;
+
+		if (t->erspan_ver == 1) {
+			if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index))
+				goto nla_put_failure;
+		} else if (t->erspan_ver == 2) {
+			if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir))
+				goto nla_put_failure;
+			if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid))
+				goto nla_put_failure;
+		}
+	}
+
+	return ipgre_fill_info(skb, dev);
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
 static void erspan_setup(struct net_device *dev)
 {
 	struct ip_tunnel *t = netdev_priv(dev);
@@ -1628,7 +1638,7 @@ static struct rtnl_link_ops erspan_link_ops __read_mostly = {
 	.changelink	= erspan_changelink,
 	.dellink	= ip_tunnel_dellink,
 	.get_size	= ipgre_get_size,
-	.fill_info	= ipgre_fill_info,
+	.fill_info	= erspan_fill_info,
 	.get_link_net	= ip_tunnel_get_link_net,
 };
 
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 1b512390b3cf..e880ce77322a 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -366,6 +366,11 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
 					   iph->tos, dev);
 		if (unlikely(err))
 			goto drop_error;
+	} else {
+		struct in_device *in_dev = __in_dev_get_rcu(dev);
+
+		if (in_dev && IN_DEV_ORCONF(in_dev, NOPOLICY))
+			IPCB(skb)->flags |= IPSKB_NOPOLICY;
 	}
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index f8e176c77d1c..b3cc416ed292 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -435,7 +435,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par)
 
 	switch (ctinfo) {
 	case IP_CT_NEW:
-		ct->mark = hash;
+		WRITE_ONCE(ct->mark, hash);
 		break;
 	case IP_CT_RELATED:
 	case IP_CT_RELATED_REPLY:
@@ -452,7 +452,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par)
 #ifdef DEBUG
 	nf_ct_dump_tuple_ip(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
 #endif
-	pr_debug("hash=%u ct_hash=%u ", hash, ct->mark);
+	pr_debug("hash=%u ct_hash=%u ", hash, READ_ONCE(ct->mark));
 	if (!clusterip_responsible(cipinfo->config, hash)) {
 		pr_debug("not responsible\n");
 		return NF_DROP;
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index ff85db52b2e5..ded5bef02f77 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -78,6 +78,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	flow.flowi4_tos = iph->tos & IPTOS_RT_MASK;
 	flow.flowi4_scope = RT_SCOPE_UNIVERSE;
 	flow.flowi4_l3mdev = l3mdev_master_ifindex_rcu(xt_in(par));
+	flow.flowi4_uid = sock_net_uid(xt_net(par), NULL);
 
 	return rpfilter_lookup_reverse(xt_net(par), &flow, xt_in(par), info->flags) ^ invert;
 }
diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c
index e886147eed11..fc65d69f23e1 100644
--- a/net/ipv4/netfilter/nft_fib_ipv4.c
+++ b/net/ipv4/netfilter/nft_fib_ipv4.c
@@ -65,6 +65,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs,
 	struct flowi4 fl4 = {
 		.flowi4_scope = RT_SCOPE_UNIVERSE,
 		.flowi4_iif = LOOPBACK_IFINDEX,
+		.flowi4_uid = sock_net_uid(nft_net(pkt), NULL),
 	};
 	const struct net_device *oif;
 	const struct net_device *found;
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 853a75a8fbaf..d8ef05347fd9 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -2534,7 +2534,7 @@ static int nh_create_ipv4(struct net *net, struct nexthop *nh,
 	if (!err) {
 		nh->nh_flags = fib_nh->fib_nh_flags;
 		fib_info_update_nhc_saddr(net, &fib_nh->nh_common,
-					  fib_nh->fib_nh_scope);
+					  !fib_nh->fib_nh_scope ? 0 : fib_nh->fib_nh_scope - 1);
 	} else {
 		fib_nh_release(net, fib_nh);
 	}
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index bde333b24837..04b4ec07bb06 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -49,6 +49,11 @@
 #include <net/transp_v6.h>
 #endif
 
+#define ping_portaddr_for_each_entry(__sk, node, list) \
+	hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node)
+#define ping_portaddr_for_each_entry_rcu(__sk, node, list) \
+	hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node)
+
 struct ping_table {
 	struct hlist_nulls_head	hash[PING_HTABLE_SIZE];
 	spinlock_t		lock;
@@ -192,7 +197,7 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
 		return NULL;
 	}
 
-	ping_portaddr_for_each_entry(sk, hnode, hslot) {
+	ping_portaddr_for_each_entry_rcu(sk, hnode, hslot) {
 		isk = inet_sk(sk);
 
 		pr_debug("iterate\n");
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index cd1fa9f70f1a..de6e3515ab4f 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -471,7 +471,7 @@ static u32 ip_idents_reserve(u32 hash, int segs)
 	old = READ_ONCE(*p_tstamp);
 
 	if (old != now && cmpxchg(p_tstamp, old, now) == old)
-		delta = prandom_u32_max(now - old);
+		delta = get_random_u32_below(now - old);
 
 	/* If UBSAN reports an error there, please make sure your compiler
 	 * supports -fno-strict-overflow before reporting it that was a bug
@@ -689,7 +689,7 @@ static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr,
 	} else {
 		/* Randomize max depth to avoid some side channels attacks. */
 		int max_depth = FNHE_RECLAIM_DEPTH +
-				prandom_u32_max(FNHE_RECLAIM_DEPTH);
+				get_random_u32_below(FNHE_RECLAIM_DEPTH);
 
 		while (depth > max_depth) {
 			fnhe_remove_oldest(hash);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f8232811a5be..3f570b25c53d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -457,6 +457,7 @@ void tcp_init_sock(struct sock *sk)
 	WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]));
 	WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]));
 
+	set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
 	sk_sockets_allocated_inc(sk);
 }
 EXPORT_SYMBOL(tcp_init_sock);
@@ -1999,7 +2000,7 @@ static int receive_fallback_to_copy(struct sock *sk,
 	if (copy_address != zc->copybuf_address)
 		return -EINVAL;
 
-	err = import_single_range(READ, (void __user *)copy_address,
+	err = import_single_range(ITER_DEST, (void __user *)copy_address,
 				  inq, &iov, &msg.msg_iter);
 	if (err)
 		return err;
@@ -2033,7 +2034,7 @@ static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc,
 	if (copy_address != zc->copybuf_address)
 		return -EINVAL;
 
-	err = import_single_range(READ, (void __user *)copy_address,
+	err = import_single_range(ITER_DEST, (void __user *)copy_address,
 				  copylen, &iov, &msg.msg_iter);
 	if (err)
 		return err;
@@ -3113,8 +3114,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 
 	inet->inet_dport = 0;
 
-	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
-		inet_reset_saddr(sk);
+	inet_bhash2_reset_saddr(sk);
 
 	sk->sk_shutdown = 0;
 	sock_reset_flag(sk, SOCK_DONE);
@@ -3646,7 +3646,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 	case TCP_REPAIR_OPTIONS:
 		if (!tp->repair)
 			err = -EINVAL;
-		else if (sk->sk_state == TCP_ESTABLISHED)
+		else if (sk->sk_state == TCP_ESTABLISHED && !tp->bytes_sent)
 			err = tcp_repair_options_est(sk, optval, optlen);
 		else
 			err = -EPERM;
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 54eec33c6e1c..d2c470524e58 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -618,7 +618,7 @@ static void bbr_reset_probe_bw_mode(struct sock *sk)
 	struct bbr *bbr = inet_csk_ca(sk);
 
 	bbr->mode = BBR_PROBE_BW;
-	bbr->cycle_idx = CYCLE_LEN - 1 - prandom_u32_max(bbr_cycle_rand);
+	bbr->cycle_idx = CYCLE_LEN - 1 - get_random_u32_below(bbr_cycle_rand);
 	bbr_advance_cycle_phase(sk);	/* flip to next phase of gain cycle */
 }
 
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index a1626afe87a1..cf9c3e8f7ccb 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -278,7 +278,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
 {
 	bool cork = false, enospc = sk_msg_full(msg);
 	struct sock *sk_redir;
-	u32 tosend, delta = 0;
+	u32 tosend, origsize, sent, delta = 0;
 	u32 eval = __SK_NONE;
 	int ret;
 
@@ -333,10 +333,12 @@ more_data:
 			cork = true;
 			psock->cork = NULL;
 		}
-		sk_msg_return(sk, msg, msg->sg.size);
+		sk_msg_return(sk, msg, tosend);
 		release_sock(sk);
 
+		origsize = msg->sg.size;
 		ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags);
+		sent = origsize - msg->sg.size;
 
 		if (eval == __SK_REDIRECT)
 			sock_put(sk_redir);
@@ -375,7 +377,7 @@ more_data:
 		    msg->sg.data[msg->sg.start].page_link &&
 		    msg->sg.data[msg->sg.start].length) {
 			if (eval == __SK_REDIRECT)
-				sk_mem_charge(sk, msg->sg.size);
+				sk_mem_charge(sk, tosend - sent);
 			goto more_data;
 		}
 	}
@@ -607,7 +609,7 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 		} else {
 			sk->sk_write_space = psock->saved_write_space;
 			/* Pairs with lockless read in sk_clone_lock() */
-			WRITE_ONCE(sk->sk_prot, psock->sk_proto);
+			sock_replace_proto(sk, psock->sk_proto);
 		}
 		return 0;
 	}
@@ -620,7 +622,7 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 	}
 
 	/* Pairs with lockless read in sk_clone_lock() */
-	WRITE_ONCE(sk->sk_prot, &tcp_bpf_prots[family][config]);
+	sock_replace_proto(sk, &tcp_bpf_prots[family][config]);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(tcp_bpf_update_proto);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index bc2ea12221f9..23cf418efe4f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2192,7 +2192,8 @@ void tcp_enter_loss(struct sock *sk)
  */
 static bool tcp_check_sack_reneging(struct sock *sk, int flag)
 {
-	if (flag & FLAG_SACK_RENEGING) {
+	if (flag & FLAG_SACK_RENEGING &&
+	    flag & FLAG_SND_UNA_ADVANCED) {
 		struct tcp_sock *tp = tcp_sk(sk);
 		unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4),
 					  msecs_to_jiffies(10));
@@ -3645,7 +3646,8 @@ static void tcp_send_challenge_ack(struct sock *sk)
 		u32 half = (ack_limit + 1) >> 1;
 
 		WRITE_ONCE(net->ipv4.tcp_challenge_timestamp, now);
-		WRITE_ONCE(net->ipv4.tcp_challenge_count, half + prandom_u32_max(ack_limit));
+		WRITE_ONCE(net->ipv4.tcp_challenge_count,
+			   get_random_u32_inclusive(half, ack_limit + half - 1));
 	}
 	count = READ_ONCE(net->ipv4.tcp_challenge_count);
 	if (count > 0) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7a250ef9d1b7..da46357f501b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -199,15 +199,14 @@ static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr,
 /* This will initiate an outgoing connection. */
 int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
-	struct inet_bind_hashbucket *prev_addr_hashbucket = NULL;
 	struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
 	struct inet_timewait_death_row *tcp_death_row;
-	__be32 daddr, nexthop, prev_sk_rcv_saddr;
 	struct inet_sock *inet = inet_sk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct ip_options_rcu *inet_opt;
 	struct net *net = sock_net(sk);
 	__be16 orig_sport, orig_dport;
+	__be32 daddr, nexthop;
 	struct flowi4 *fl4;
 	struct rtable *rt;
 	int err;
@@ -251,24 +250,13 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
 
 	if (!inet->inet_saddr) {
-		if (inet_csk(sk)->icsk_bind2_hash) {
-			prev_addr_hashbucket = inet_bhashfn_portaddr(tcp_death_row->hashinfo,
-								     sk, net, inet->inet_num);
-			prev_sk_rcv_saddr = sk->sk_rcv_saddr;
-		}
-		inet->inet_saddr = fl4->saddr;
-	}
-
-	sk_rcv_saddr_set(sk, inet->inet_saddr);
-
-	if (prev_addr_hashbucket) {
-		err = inet_bhash2_update_saddr(prev_addr_hashbucket, sk);
+		err = inet_bhash2_update_saddr(sk,  &fl4->saddr, AF_INET);
 		if (err) {
-			inet->inet_saddr = 0;
-			sk_rcv_saddr_set(sk, prev_sk_rcv_saddr);
 			ip_rt_put(rt);
 			return err;
 		}
+	} else {
+		sk_rcv_saddr_set(sk, inet->inet_saddr);
 	}
 
 	if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) {
@@ -343,6 +331,7 @@ failure:
 	 * if necessary.
 	 */
 	tcp_set_state(sk, TCP_CLOSE);
+	inet_bhash2_reset_saddr(sk);
 	ip_rt_put(rt);
 	sk->sk_route_caps = 0;
 	inet->inet_dport = 0;
@@ -1874,11 +1863,13 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
 	__skb_push(skb, hdrlen);
 
 no_coalesce:
+	limit = (u32)READ_ONCE(sk->sk_rcvbuf) + (u32)(READ_ONCE(sk->sk_sndbuf) >> 1);
+
 	/* Only socket owner can try to collapse/prune rx queues
 	 * to reduce memory overhead, so add a little headroom here.
 	 * Few sockets backlog are possibly concurrently non empty.
 	 */
-	limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf) + 64*1024;
+	limit += 64 * 1024;
 
 	if (unlikely(sk_add_backlog(sk, skb, limit))) {
 		bh_unlock_sock(sk);
diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c
index 7c27aa629af1..9ae50b1bd844 100644
--- a/net/ipv4/tcp_ulp.c
+++ b/net/ipv4/tcp_ulp.c
@@ -136,6 +136,9 @@ static int __tcp_set_ulp(struct sock *sk, const struct tcp_ulp_ops *ulp_ops)
 	if (icsk->icsk_ulp_ops)
 		goto out_err;
 
+	if (sk->sk_socket)
+		clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
+
 	err = ulp_ops->init(sk);
 	if (err)
 		goto out_err;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 662d717d5123..6a320a614e54 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -448,7 +448,7 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 			result = lookup_reuseport(net, sk, skb,
 						  saddr, sport, daddr, hnum);
 			/* Fall back to scoring if group has connections */
-			if (result && !reuseport_has_conns(sk, false))
+			if (result && !reuseport_has_conns(sk))
 				return result;
 
 			result = result ? : sk;
@@ -1624,6 +1624,7 @@ int udp_init_sock(struct sock *sk)
 {
 	skb_queue_head_init(&udp_sk(sk)->reader_queue);
 	sk->sk_destruct = udp_destruct_sock;
+	set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
 	return 0;
 }
 
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index ff15918b7bdc..e5dc91d0e079 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -141,14 +141,14 @@ int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 
 	if (restore) {
 		sk->sk_write_space = psock->saved_write_space;
-		WRITE_ONCE(sk->sk_prot, psock->sk_proto);
+		sock_replace_proto(sk, psock->sk_proto);
 		return 0;
 	}
 
 	if (sk->sk_family == AF_INET6)
 		udp_bpf_check_v6_needs_rebuild(psock->sk_proto);
 
-	WRITE_ONCE(sk->sk_prot, &udp_bpf_prots[family]);
+	sock_replace_proto(sk, &udp_bpf_prots[family]);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(udp_bpf_update_proto);