16 files changed, 75 insertions, 74 deletions

diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index f915abff1350..300921417f89 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -42,7 +42,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
 	oif = sk->sk_bound_dev_if;
 	saddr = inet->inet_saddr;
 	if (ipv4_is_multicast(usin->sin_addr.s_addr)) {
-		if (!oif)
+		if (!oif || netif_index_is_l3_master(sock_net(sk), oif))
 			oif = inet->mc_index;
 		if (!saddr)
 			saddr = inet->mc_addr;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index bee8db979195..f8c7ec8171a8 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -208,7 +208,6 @@ static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp)
 static void free_fib_info_rcu(struct rcu_head *head)
 {
 	struct fib_info *fi = container_of(head, struct fib_info, rcu);
-	struct dst_metrics *m;
 
 	change_nexthops(fi) {
 		if (nexthop_nh->nh_dev)
@@ -219,9 +218,8 @@ static void free_fib_info_rcu(struct rcu_head *head)
 		rt_fibinfo_free(&nexthop_nh->nh_rth_input);
 	} endfor_nexthops(fi);
 
-	m = fi->fib_metrics;
-	if (m != &dst_default_metrics && refcount_dec_and_test(&m->refcnt))
-		kfree(m);
+	ip_fib_metrics_put(fi->fib_metrics);
+
 	kfree(fi);
 }
 
@@ -1020,13 +1018,6 @@ static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc)
 	return true;
 }
 
-static int
-fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)
-{
-	return ip_metrics_convert(fi->fib_net, cfg->fc_mx, cfg->fc_mx_len,
-				  fi->fib_metrics->metrics);
-}
-
 struct fib_info *fib_create_info(struct fib_config *cfg,
 				 struct netlink_ext_ack *extack)
 {
@@ -1084,16 +1075,14 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
 	if (!fi)
 		goto failure;
-	if (cfg->fc_mx) {
-		fi->fib_metrics = kzalloc(sizeof(*fi->fib_metrics), GFP_KERNEL);
-		if (unlikely(!fi->fib_metrics)) {
-			kfree(fi);
-			return ERR_PTR(err);
-		}
-		refcount_set(&fi->fib_metrics->refcnt, 1);
-	} else {
-		fi->fib_metrics = (struct dst_metrics *)&dst_default_metrics;
+	fi->fib_metrics = ip_fib_metrics_init(fi->fib_net, cfg->fc_mx,
+					      cfg->fc_mx_len);
+	if (unlikely(IS_ERR(fi->fib_metrics))) {
+		err = PTR_ERR(fi->fib_metrics);
+		kfree(fi);
+		return ERR_PTR(err);
 	}
+
 	fib_info_cnt++;
 	fi->fib_net = net;
 	fi->fib_protocol = cfg->fc_protocol;
@@ -1112,10 +1101,6 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 			goto failure;
 	} endfor_nexthops(fi)
 
-	err = fib_convert_metrics(fi, cfg);
-	if (err)
-		goto failure;
-
 	if (cfg->fc_mp) {
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 		err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg, extack);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index dfd5009f96ef..15e7f7915a21 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -544,7 +544,8 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 	struct ip_options_rcu *opt;
 	struct rtable *rt;
 
-	opt = ireq_opt_deref(ireq);
+	rcu_read_lock();
+	opt = rcu_dereference(ireq->ireq_opt);
 
 	flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
 			   RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
@@ -558,11 +559,13 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 		goto no_route;
 	if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto route_err;
+	rcu_read_unlock();
 	return &rt->dst;
 
 route_err:
 	ip_rt_put(rt);
 no_route:
+	rcu_read_unlock();
 	__IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
 	return NULL;
 }
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index c0fe5ad996f2..26c36cccabdc 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -149,7 +149,6 @@ static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb)
 static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 {
 	struct sockaddr_in sin;
-	const struct iphdr *iph = ip_hdr(skb);
 	__be16 *ports;
 	int end;
 
@@ -164,7 +163,7 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 	ports = (__be16 *)skb_transport_header(skb);
 
 	sin.sin_family = AF_INET;
-	sin.sin_addr.s_addr = iph->daddr;
+	sin.sin_addr.s_addr = ip_hdr(skb)->daddr;
 	sin.sin_port = ports[1];
 	memset(sin.sin_zero, 0, sizeof(sin.sin_zero));
 
diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c
index 04311f7067e2..6d218f5a2e71 100644
--- a/net/ipv4/metrics.c
+++ b/net/ipv4/metrics.c
@@ -5,8 +5,8 @@
 #include <net/net_namespace.h>
 #include <net/tcp.h>
 
-int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, int fc_mx_len,
-		       u32 *metrics)
+static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
+			      int fc_mx_len, u32 *metrics)
 {
 	bool ecn_ca = false;
 	struct nlattr *nla;
@@ -52,4 +52,28 @@ int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, int fc_mx_len,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(ip_metrics_convert);
+
+struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx,
+					int fc_mx_len)
+{
+	struct dst_metrics *fib_metrics;
+	int err;
+
+	if (!fc_mx)
+		return (struct dst_metrics *)&dst_default_metrics;
+
+	fib_metrics = kzalloc(sizeof(*fib_metrics), GFP_KERNEL);
+	if (unlikely(!fib_metrics))
+		return ERR_PTR(-ENOMEM);
+
+	err = ip_metrics_convert(net, fc_mx, fc_mx_len, fib_metrics->metrics);
+	if (!err) {
+		refcount_set(&fib_metrics->refcnt, 1);
+	} else {
+		kfree(fib_metrics);
+		fib_metrics = ERR_PTR(err);
+	}
+
+	return fib_metrics;
+}
+EXPORT_SYMBOL_GPL(ip_fib_metrics_init);
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 8d7aaf118a30..7ccb5f87f70b 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -779,7 +779,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	}
 
 	if (ipv4_is_multicast(daddr)) {
-		if (!ipc.oif)
+		if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))
 			ipc.oif = inet->mc_index;
 		if (!saddr)
 			saddr = inet->mc_addr;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 33df4d76db2d..8ca3eb06ba04 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -608,7 +608,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		tos |= RTO_ONLINK;
 
 	if (ipv4_is_multicast(daddr)) {
-		if (!ipc.oif)
+		if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))
 			ipc.oif = inet->mc_index;
 		if (!saddr)
 			saddr = inet->mc_addr;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index dce2ed66ebe1..f71d2395c428 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1217,18 +1217,15 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt)
 		src = ip_hdr(skb)->saddr;
 	else {
 		struct fib_result res;
-		struct flowi4 fl4;
-		struct iphdr *iph;
-
-		iph = ip_hdr(skb);
-
-		memset(&fl4, 0, sizeof(fl4));
-		fl4.daddr = iph->daddr;
-		fl4.saddr = iph->saddr;
-		fl4.flowi4_tos = RT_TOS(iph->tos);
-		fl4.flowi4_oif = rt->dst.dev->ifindex;
-		fl4.flowi4_iif = skb->dev->ifindex;
-		fl4.flowi4_mark = skb->mark;
+		struct iphdr *iph = ip_hdr(skb);
+		struct flowi4 fl4 = {
+			.daddr = iph->daddr,
+			.saddr = iph->saddr,
+			.flowi4_tos = RT_TOS(iph->tos),
+			.flowi4_oif = rt->dst.dev->ifindex,
+			.flowi4_iif = skb->dev->ifindex,
+			.flowi4_mark = skb->mark,
+		};
 
 		rcu_read_lock();
 		if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res, 0) == 0)
@@ -1479,12 +1476,9 @@ void rt_del_uncached_list(struct rtable *rt)
 
 static void ipv4_dst_destroy(struct dst_entry *dst)
 {
-	struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst);
 	struct rtable *rt = (struct rtable *)dst;
 
-	if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt))
-		kfree(p);
-
+	ip_dst_metrics_put(dst);
 	rt_del_uncached_list(rt);
 }
 
@@ -1531,11 +1525,8 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 			rt->rt_gateway = nh->nh_gw;
 			rt->rt_uses_gateway = 1;
 		}
-		dst_init_metrics(&rt->dst, fi->fib_metrics->metrics, true);
-		if (fi->fib_metrics != &dst_default_metrics) {
-			rt->dst._metrics |= DST_METRICS_REFCOUNTED;
-			refcount_inc(&fi->fib_metrics->refcnt);
-		}
+		ip_dst_init_metrics(&rt->dst, fi->fib_metrics);
+
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		rt->dst.tclassid = nh->nh_tclassid;
 #endif
@@ -2783,7 +2774,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	struct rtable *rt = NULL;
 	struct sk_buff *skb;
 	struct rtmsg *rtm;
-	struct flowi4 fl4;
+	struct flowi4 fl4 = {};
 	__be32 dst = 0;
 	__be32 src = 0;
 	kuid_t uid;
@@ -2823,7 +2814,6 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	if (!skb)
 		return -ENOBUFS;
 
-	memset(&fl4, 0, sizeof(fl4));
 	fl4.daddr = dst;
 	fl4.saddr = src;
 	fl4.flowi4_tos = rtm->rtm_tos;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index b92f422f2fa8..891ed2f91467 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -48,6 +48,7 @@ static int tcp_syn_retries_max = MAX_TCP_SYNCNT;
 static int ip_ping_group_range_min[] = { 0, 0 };
 static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
 static int comp_sack_nr_max = 255;
+static u32 u32_max_div_HZ = UINT_MAX / HZ;
 
 /* obsolete */
 static int sysctl_tcp_low_latency __read_mostly;
@@ -745,9 +746,10 @@ static struct ctl_table ipv4_net_table[] = {
 	{
 		.procname	= "tcp_probe_interval",
 		.data		= &init_net.ipv4.sysctl_tcp_probe_interval,
-		.maxlen		= sizeof(int),
+		.maxlen		= sizeof(u32),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_douintvec_minmax,
+		.extra2		= &u32_max_div_HZ,
 	},
 	{
 		.procname	= "igmp_link_local_mcast_reports",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2827fa5643bd..43ef83b2330e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2416,16 +2416,10 @@ adjudge_to_death:
 	sock_hold(sk);
 	sock_orphan(sk);
 
-	/* It is the last release_sock in its life. It will remove backlog. */
-	release_sock(sk);
-
-
-	/* Now socket is owned by kernel and we acquire BH lock
-	 *  to finish close. No need to check for user refs.
-	 */
 	local_bh_disable();
 	bh_lock_sock(sk);
-	WARN_ON(sock_owned_by_user(sk));
+	/* remove backlog if any, without releasing ownership. */
+	__release_sock(sk);
 
 	percpu_counter_inc(sk->sk_prot->orphan_count);
 
@@ -2494,6 +2488,7 @@ adjudge_to_death:
 out:
 	bh_unlock_sock(sk);
 	local_bh_enable();
+	release_sock(sk);
 	sock_put(sk);
 }
 EXPORT_SYMBOL(tcp_close);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index bf1aac315490..188980c58f87 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6002,11 +6002,13 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			if (th->fin)
 				goto discard;
 			/* It is possible that we process SYN packets from backlog,
-			 * so we need to make sure to disable BH right there.
+			 * so we need to make sure to disable BH and RCU right there.
 			 */
+			rcu_read_lock();
 			local_bh_disable();
 			acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0;
 			local_bh_enable();
+			rcu_read_unlock();
 
 			if (!acceptable)
 				return 1;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 1f2496e8620d..de47038afdf0 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -943,9 +943,11 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 	if (skb) {
 		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
 
+		rcu_read_lock();
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    ireq_opt_deref(ireq));
+					    rcu_dereference(ireq->ireq_opt));
+		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 7d69dd6fa7e8..1bec2203d558 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1042,7 +1042,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	}
 
 	if (ipv4_is_multicast(daddr)) {
-		if (!ipc.oif)
+		if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))
 			ipc.oif = inet->mc_index;
 		if (!saddr)
 			saddr = inet->mc_addr;
@@ -1889,7 +1889,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	return 0;
 }
 
-static DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key);
+DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key);
 void udp_encap_enable(void)
 {
 	static_branch_enable(&udp_encap_needed_key);
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 0c0522b79b43..802f2bc00d69 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -405,7 +405,7 @@ static struct sk_buff *udp4_gro_receive(struct list_head *head,
 {
 	struct udphdr *uh = udp_gro_udphdr(skb);
 
-	if (unlikely(!uh))
+	if (unlikely(!uh) || !static_branch_unlikely(&udp_encap_needed_key))
 		goto flush;
 
 	/* Don't bother verifying checksum if we're going to flush anyway. */
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index bcfc00e88756..f8de2482a529 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -67,6 +67,7 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async)
 
 	if (xo && (xo->flags & XFRM_GRO)) {
 		skb_mac_header_rebuild(skb);
+		skb_reset_transport_header(skb);
 		return 0;
 	}
 
diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c
index 3d36644890bb..1ad2c2c4e250 100644
--- a/net/ipv4/xfrm4_mode_transport.c
+++ b/net/ipv4/xfrm4_mode_transport.c
@@ -46,7 +46,6 @@ static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb)
 static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
 {
 	int ihl = skb->data - skb_transport_header(skb);
-	struct xfrm_offload *xo = xfrm_offload(skb);
 
 	if (skb->transport_header != skb->network_header) {
 		memmove(skb_transport_header(skb),
@@ -54,8 +53,7 @@ static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
 		skb->network_header = skb->transport_header;
 	}
 	ip_hdr(skb)->tot_len = htons(skb->len + ihl);
-	if (!xo || !(xo->flags & XFRM_GRO))
-		skb_reset_transport_header(skb);
+	skb_reset_transport_header(skb);
 	return 0;
 }