1 files changed, 408 insertions, 139 deletions

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 265c42cf963..7d5a8661df7 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -103,12 +103,14 @@
 #include <linux/seq_file.h>
 #include <net/net_namespace.h>
 #include <net/icmp.h>
+#include <net/inet_hashtables.h>
 #include <net/route.h>
 #include <net/checksum.h>
 #include <net/xfrm.h>
 #include <trace/events/udp.h>
 #include <linux/static_key.h>
 #include <trace/events/skb.h>
+#include <net/busy_poll.h>
 #include "udp_impl.h"
 
 struct udp_table udp_table __read_mostly;
@@ -218,10 +220,10 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
 		unsigned short first, last;
 		DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN);
 
-		inet_get_local_port_range(&low, &high);
+		inet_get_local_port_range(net, &low, &high);
 		remaining = (high - low) + 1;
 
-		rand = net_random();
+		rand = prandom_u32();
 		first = (((u64)rand * remaining) >> 32) + low;
 		/*
 		 * force rand to be an odd multiple of UDP_HTABLE_SIZE
@@ -244,7 +246,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
 			do {
 				if (low <= snum && snum <= high &&
 				    !test_bit(snum >> udptable->log, bitmap) &&
-				    !inet_is_reserved_local_port(snum))
+				    !inet_is_local_reserved_port(net, snum))
 					goto found;
 				snum += rand;
 			} while (snum != first);
@@ -405,6 +407,18 @@ static inline int compute_score2(struct sock *sk, struct net *net,
 	return score;
 }
 
+static unsigned int udp_ehashfn(struct net *net, const __be32 laddr,
+				 const __u16 lport, const __be32 faddr,
+				 const __be16 fport)
+{
+	static u32 udp_ehash_secret __read_mostly;
+
+	net_get_random_once(&udp_ehash_secret, sizeof(udp_ehash_secret));
+
+	return __inet_ehashfn(laddr, lport, faddr, fport,
+			      udp_ehash_secret + net_hash_mix(net));
+}
+
 
 /* called with read_rcu_lock() */
 static struct sock *udp4_lib_lookup2(struct net *net,
@@ -428,8 +442,8 @@ begin:
 			badness = score;
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
-				hash = inet_ehashfn(net, daddr, hnum,
-						    saddr, htons(sport));
+				hash = udp_ehashfn(net, daddr, hnum,
+						   saddr, sport);
 				matches = 1;
 			}
 		} else if (score == badness && reuseport) {
@@ -509,8 +523,8 @@ begin:
 			badness = score;
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
-				hash = inet_ehashfn(net, daddr, hnum,
-						    saddr, htons(sport));
+				hash = udp_ehashfn(net, daddr, hnum,
+						   saddr, sport);
 				matches = 1;
 			}
 		} else if (score == badness && reuseport) {
@@ -546,15 +560,11 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
 						 __be16 sport, __be16 dport,
 						 struct udp_table *udptable)
 {
-	struct sock *sk;
 	const struct iphdr *iph = ip_hdr(skb);
 
-	if (unlikely(sk = skb_steal_sock(skb)))
-		return sk;
-	else
-		return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport,
-					 iph->daddr, dport, inet_iif(skb),
-					 udptable);
+	return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport,
+				 iph->daddr, dport, inet_iif(skb),
+				 udptable);
 }
 
 struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
@@ -564,6 +574,26 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
 }
 EXPORT_SYMBOL_GPL(udp4_lib_lookup);
 
+static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
+				       __be16 loc_port, __be32 loc_addr,
+				       __be16 rmt_port, __be32 rmt_addr,
+				       int dif, unsigned short hnum)
+{
+	struct inet_sock *inet = inet_sk(sk);
+
+	if (!net_eq(sock_net(sk), net) ||
+	    udp_sk(sk)->udp_port_hash != hnum ||
+	    (inet->inet_daddr && inet->inet_daddr != rmt_addr) ||
+	    (inet->inet_dport != rmt_port && inet->inet_dport) ||
+	    (inet->inet_rcv_saddr && inet->inet_rcv_saddr != loc_addr) ||
+	    ipv6_only_sock(sk) ||
+	    (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
+		return false;
+	if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, dif))
+		return false;
+	return true;
+}
+
 static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk,
 					     __be16 loc_port, __be32 loc_addr,
 					     __be16 rmt_port, __be32 rmt_addr,
@@ -574,20 +604,11 @@ static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk,
 	unsigned short hnum = ntohs(loc_port);
 
 	sk_nulls_for_each_from(s, node) {
-		struct inet_sock *inet = inet_sk(s);
-
-		if (!net_eq(sock_net(s), net) ||
-		    udp_sk(s)->udp_port_hash != hnum ||
-		    (inet->inet_daddr && inet->inet_daddr != rmt_addr) ||
-		    (inet->inet_dport != rmt_port && inet->inet_dport) ||
-		    (inet->inet_rcv_saddr &&
-		     inet->inet_rcv_saddr != loc_addr) ||
-		    ipv6_only_sock(s) ||
-		    (s->sk_bound_dev_if && s->sk_bound_dev_if != dif))
-			continue;
-		if (!ip_mc_sf_allow(s, loc_addr, rmt_addr, dif))
-			continue;
-		goto found;
+		if (__udp_is_mcast_sock(net, s,
+					loc_port, loc_addr,
+					rmt_port, rmt_addr,
+					dif, hnum))
+			goto found;
 	}
 	s = NULL;
 found:
@@ -657,7 +678,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 		break;
 	case ICMP_REDIRECT:
 		ipv4_sk_redirect(skb, sk);
-		break;
+		goto out;
 	}
 
 	/*
@@ -703,16 +724,15 @@ EXPORT_SYMBOL(udp_flush_pending_frames);
  *	@src:	source IP address
  *	@dst:	destination IP address
  */
-static void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst)
+void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst)
 {
 	struct udphdr *uh = udp_hdr(skb);
-	struct sk_buff *frags = skb_shinfo(skb)->frag_list;
 	int offset = skb_transport_offset(skb);
 	int len = skb->len - offset;
 	int hlen = len;
 	__wsum csum = 0;
 
-	if (!frags) {
+	if (!skb_has_frag_list(skb)) {
 		/*
 		 * Only one fragment on the socket.
 		 */
@@ -721,15 +741,17 @@ static void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst)
 		uh->check = ~csum_tcpudp_magic(src, dst, len,
 					       IPPROTO_UDP, 0);
 	} else {
+		struct sk_buff *frags;
+
 		/*
 		 * HW-checksum won't work as there are two or more
 		 * fragments on the socket so that all csums of sk_buffs
 		 * should be together
 		 */
-		do {
+		skb_walk_frags(skb, frags) {
 			csum = csum_add(csum, frags->csum);
 			hlen -= frags->len;
-		} while ((frags = frags->next));
+		}
 
 		csum = skb_checksum(skb, offset, hlen, csum);
 		skb->ip_summed = CHECKSUM_NONE;
@@ -739,6 +761,44 @@ static void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst)
 			uh->check = CSUM_MANGLED_0;
 	}
 }
+EXPORT_SYMBOL_GPL(udp4_hwcsum);
+
+/* Function to set UDP checksum for an IPv4 UDP packet. This is intended
+ * for the simple case like when setting the checksum for a UDP tunnel.
+ */
+void udp_set_csum(bool nocheck, struct sk_buff *skb,
+		  __be32 saddr, __be32 daddr, int len)
+{
+	struct udphdr *uh = udp_hdr(skb);
+
+	if (nocheck)
+		uh->check = 0;
+	else if (skb_is_gso(skb))
+		uh->check = ~udp_v4_check(len, saddr, daddr, 0);
+	else if (skb_dst(skb) && skb_dst(skb)->dev &&
+		 (skb_dst(skb)->dev->features & NETIF_F_V4_CSUM)) {
+
+		BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL);
+
+		skb->ip_summed = CHECKSUM_PARTIAL;
+		skb->csum_start = skb_transport_header(skb) - skb->head;
+		skb->csum_offset = offsetof(struct udphdr, check);
+		uh->check = ~udp_v4_check(len, saddr, daddr, 0);
+	} else {
+		__wsum csum;
+
+		BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL);
+
+		uh->check = 0;
+		csum = skb_checksum(skb, 0, len, 0);
+		uh->check = udp_v4_check(len, saddr, daddr, csum);
+		if (uh->check == 0)
+			uh->check = CSUM_MANGLED_0;
+
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	}
+}
+EXPORT_SYMBOL(udp_set_csum);
 
 static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4)
 {
@@ -763,7 +823,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4)
 	if (is_udplite)  				 /*     UDP-Lite      */
 		csum = udplite_csum(skb);
 
-	else if (sk->sk_no_check == UDP_CSUM_NOXMIT) {   /* UDP csum disabled */
+	else if (sk->sk_no_check_tx) {   /* UDP csum disabled */
 
 		skb->ip_summed = CHECKSUM_NONE;
 		goto send;
@@ -799,7 +859,7 @@ send:
 /*
  * Push out all pending data as one UDP datagram. Socket is locked.
  */
-static int udp_push_pending_frames(struct sock *sk)
+int udp_push_pending_frames(struct sock *sk)
 {
 	struct udp_sock  *up = udp_sk(sk);
 	struct inet_sock *inet = inet_sk(sk);
@@ -818,6 +878,7 @@ out:
 	up->pending = 0;
 	return err;
 }
+EXPORT_SYMBOL(udp_push_pending_frames);
 
 int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		size_t len)
@@ -852,6 +913,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	ipc.opt = NULL;
 	ipc.tx_flags = 0;
+	ipc.ttl = 0;
+	ipc.tos = -1;
 
 	getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
 
@@ -877,7 +940,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	 *	Get and verify the address.
 	 */
 	if (msg->msg_name) {
-		struct sockaddr_in *usin = (struct sockaddr_in *)msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name);
 		if (msg->msg_namelen < sizeof(*usin))
 			return -EINVAL;
 		if (usin->sin_family != AF_INET) {
@@ -902,11 +965,12 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	ipc.addr = inet->inet_saddr;
 
 	ipc.oif = sk->sk_bound_dev_if;
-	err = sock_tx_timestamp(sk, &ipc.tx_flags);
-	if (err)
-		return err;
+
+	sock_tx_timestamp(sk, &ipc.tx_flags);
+
 	if (msg->msg_controllen) {
-		err = ip_cmsg_send(sock_net(sk), msg, &ipc);
+		err = ip_cmsg_send(sock_net(sk), msg, &ipc,
+				   sk->sk_family == AF_INET6);
 		if (err)
 			return err;
 		if (ipc.opt)
@@ -935,7 +999,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		faddr = ipc.opt->opt.faddr;
 		connected = 0;
 	}
-	tos = RT_TOS(inet->tos);
+	tos = get_rttos(&ipc, inet);
 	if (sock_flag(sk, SOCK_LOCALROUTE) ||
 	    (msg->msg_flags & MSG_DONTROUTE) ||
 	    (ipc.opt && ipc.opt->opt.is_strictroute)) {
@@ -961,7 +1025,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		fl4 = &fl4_stack;
 		flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos,
 				   RT_SCOPE_UNIVERSE, sk->sk_protocol,
-				   inet_sk_flowi_flags(sk)|FLOWI_FLAG_CAN_SLEEP,
+				   inet_sk_flowi_flags(sk),
 				   faddr, saddr, dport, inet->inet_sport);
 
 		security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
@@ -970,7 +1034,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			err = PTR_ERR(rt);
 			rt = NULL;
 			if (err == -ENETUNREACH)
-				IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
+				IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
 			goto out;
 		}
 
@@ -1069,6 +1133,9 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset,
 	struct udp_sock *up = udp_sk(sk);
 	int ret;
 
+	if (flags & MSG_SENDPAGE_NOTLAST)
+		flags |= MSG_MORE;
+
 	if (!up->pending) {
 		struct msghdr msg = {	.msg_flags = flags|MSG_MORE };
 
@@ -1131,6 +1198,8 @@ static unsigned int first_packet_length(struct sock *sk)
 	spin_lock_bh(&rcvq->lock);
 	while ((skb = skb_peek(rcvq)) != NULL &&
 		udp_lib_checksum_complete(skb)) {
+		UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_CSUMERRORS,
+				 IS_UDPLITE(sk));
 		UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS,
 				 IS_UDPLITE(sk));
 		atomic_inc(&sk->sk_drops);
@@ -1196,7 +1265,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		size_t len, int noblock, int flags, int *addr_len)
 {
 	struct inet_sock *inet = inet_sk(sk);
-	struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
 	struct sk_buff *skb;
 	unsigned int ulen, copied;
 	int peeked, off = 0;
@@ -1204,14 +1273,8 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	int is_udplite = IS_UDPLITE(sk);
 	bool slow;
 
-	/*
-	 *	Check any passed addresses
-	 */
-	if (addr_len)
-		*addr_len = sizeof(*sin);
-
 	if (flags & MSG_ERRQUEUE)
-		return ip_recv_error(sk, msg, len);
+		return ip_recv_error(sk, msg, len, addr_len);
 
 try_again:
 	skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
@@ -1271,6 +1334,7 @@ try_again:
 		sin->sin_port = udp_hdr(skb)->source;
 		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
 		memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+		*addr_len = sizeof(*sin);
 	}
 	if (inet->cmsg_flags)
 		ip_cmsg_recv(msg, skb);
@@ -1286,8 +1350,10 @@ out:
 
 csum_copy_err:
 	slow = lock_sock_fast(sk);
-	if (!skb_kill_datagram(sk, skb, flags))
+	if (!skb_kill_datagram(sk, skb, flags)) {
+		UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
 		UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
+	}
 	unlock_sock_fast(sk, slow);
 
 	if (noblock)
@@ -1396,8 +1462,10 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	int rc;
 
-	if (inet_sk(sk)->inet_daddr)
+	if (inet_sk(sk)->inet_daddr) {
 		sock_rps_save_rxhash(sk, skb);
+		sk_mark_napi_id(sk, skb);
+	}
 
 	rc = sock_queue_rcv_skb(sk, skb);
 	if (rc < 0) {
@@ -1465,6 +1533,10 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		if (skb->len > sizeof(struct udphdr) && encap_rcv != NULL) {
 			int ret;
 
+			/* Verify checksum before giving to encap */
+			if (udp_lib_checksum_complete(skb))
+				goto csum_error;
+
 			ret = encap_rcv(sk, skb);
 			if (ret <= 0) {
 				UDP_INC_STATS_BH(sock_net(sk),
@@ -1513,15 +1585,18 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 	if (rcu_access_pointer(sk->sk_filter) &&
 	    udp_lib_checksum_complete(skb))
-		goto drop;
+		goto csum_error;
 
 
-	if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf))
+	if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) {
+		UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS,
+				 is_udplite);
 		goto drop;
+	}
 
 	rc = 0;
 
-	ipv4_pktinfo_prepare(skb);
+	ipv4_pktinfo_prepare(sk, skb);
 	bh_lock_sock(sk);
 	if (!sock_owned_by_user(sk))
 		rc = __udp_queue_rcv_skb(sk, skb);
@@ -1533,6 +1608,8 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 	return rc;
 
+csum_error:
+	UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
 drop:
 	UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
 	atomic_inc(&sk->sk_drops);
@@ -1568,6 +1645,18 @@ static void flush_stack(struct sock **stack, unsigned int count,
 		kfree_skb(skb1);
 }
 
+/* For TCP sockets, sk_rx_dst is protected by socket lock
+ * For UDP, we use xchg() to guard against concurrent changes.
+ */
+static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
+{
+	struct dst_entry *old;
+
+	dst_hold(dst);
+	old = xchg(&sk->sk_rx_dst, dst);
+	dst_release(old);
+}
+
 /*
  *	Multicasts and broadcasts go to each listener.
  *
@@ -1628,7 +1717,6 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
 				 int proto)
 {
-	const struct iphdr *iph;
 	int err;
 
 	UDP_SKB_CB(skb)->partial_cov = 0;
@@ -1640,22 +1728,8 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
 			return err;
 	}
 
-	iph = ip_hdr(skb);
-	if (uh->check == 0) {
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-	} else if (skb->ip_summed == CHECKSUM_COMPLETE) {
-		if (!csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
-				      proto, skb->csum))
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-	}
-	if (!skb_csum_unnecessary(skb))
-		skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
-					       skb->len, proto, 0);
-	/* Probably, we should checksum udp header (it should be in cache
-	 * in any case) and data in tiny packets (< rx copybreak).
-	 */
-
-	return 0;
+	return skb_checksum_init_zero_check(skb, proto, uh->check,
+					    inet_compute_pseudo);
 }
 
 /*
@@ -1696,14 +1770,34 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (udp4_csum_init(skb, uh, proto))
 		goto csum_error;
 
-	if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
-		return __udp4_lib_mcast_deliver(net, skb, uh,
-				saddr, daddr, udptable);
+	sk = skb_steal_sock(skb);
+	if (sk) {
+		struct dst_entry *dst = skb_dst(skb);
+		int ret;
 
-	sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
+		if (unlikely(sk->sk_rx_dst != dst))
+			udp_sk_rx_dst_set(sk, dst);
+
+		ret = udp_queue_rcv_skb(sk, skb);
+		sock_put(sk);
+		/* a return value > 0 means to resubmit the input, but
+		 * it wants the return to be -protocol, or 0
+		 */
+		if (ret > 0)
+			return -ret;
+		return 0;
+	} else {
+		if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
+			return __udp4_lib_mcast_deliver(net, skb, uh,
+					saddr, daddr, udptable);
+
+		sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
+	}
 
 	if (sk != NULL) {
-		int ret = udp_queue_rcv_skb(sk, skb);
+		int ret;
+
+		ret = udp_queue_rcv_skb(sk, skb);
 		sock_put(sk);
 
 		/* a return value > 0 means to resubmit the input, but
@@ -1749,12 +1843,149 @@ csum_error:
 		       proto == IPPROTO_UDPLITE ? "Lite" : "",
 		       &saddr, ntohs(uh->source), &daddr, ntohs(uh->dest),
 		       ulen);
+	UDP_INC_STATS_BH(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE);
 drop:
 	UDP_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
 	kfree_skb(skb);
 	return 0;
 }
 
+/* We can only early demux multicast if there is a single matching socket.
+ * If more than one socket found returns NULL
+ */
+static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
+						  __be16 loc_port, __be32 loc_addr,
+						  __be16 rmt_port, __be32 rmt_addr,
+						  int dif)
+{
+	struct sock *sk, *result;
+	struct hlist_nulls_node *node;
+	unsigned short hnum = ntohs(loc_port);
+	unsigned int count, slot = udp_hashfn(net, hnum, udp_table.mask);
+	struct udp_hslot *hslot = &udp_table.hash[slot];
+
+	/* Do not bother scanning a too big list */
+	if (hslot->count > 10)
+		return NULL;
+
+	rcu_read_lock();
+begin:
+	count = 0;
+	result = NULL;
+	sk_nulls_for_each_rcu(sk, node, &hslot->head) {
+		if (__udp_is_mcast_sock(net, sk,
+					loc_port, loc_addr,
+					rmt_port, rmt_addr,
+					dif, hnum)) {
+			result = sk;
+			++count;
+		}
+	}
+	/*
+	 * if the nulls value we got at the end of this lookup is
+	 * not the expected one, we must restart lookup.
+	 * We probably met an item that was moved to another chain.
+	 */
+	if (get_nulls_value(node) != slot)
+		goto begin;
+
+	if (result) {
+		if (count != 1 ||
+		    unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2)))
+			result = NULL;
+		else if (unlikely(!__udp_is_mcast_sock(net, result,
+						       loc_port, loc_addr,
+						       rmt_port, rmt_addr,
+						       dif, hnum))) {
+			sock_put(result);
+			result = NULL;
+		}
+	}
+	rcu_read_unlock();
+	return result;
+}
+
+/* For unicast we should only early demux connected sockets or we can
+ * break forwarding setups.  The chains here can be long so only check
+ * if the first socket is an exact match and if not move on.
+ */
+static struct sock *__udp4_lib_demux_lookup(struct net *net,
+					    __be16 loc_port, __be32 loc_addr,
+					    __be16 rmt_port, __be32 rmt_addr,
+					    int dif)
+{
+	struct sock *sk, *result;
+	struct hlist_nulls_node *node;
+	unsigned short hnum = ntohs(loc_port);
+	unsigned int hash2 = udp4_portaddr_hash(net, loc_addr, hnum);
+	unsigned int slot2 = hash2 & udp_table.mask;
+	struct udp_hslot *hslot2 = &udp_table.hash2[slot2];
+	INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr);
+	const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum);
+
+	rcu_read_lock();
+	result = NULL;
+	udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) {
+		if (INET_MATCH(sk, net, acookie,
+			       rmt_addr, loc_addr, ports, dif))
+			result = sk;
+		/* Only check first socket in chain */
+		break;
+	}
+
+	if (result) {
+		if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2)))
+			result = NULL;
+		else if (unlikely(!INET_MATCH(sk, net, acookie,
+					      rmt_addr, loc_addr,
+					      ports, dif))) {
+			sock_put(result);
+			result = NULL;
+		}
+	}
+	rcu_read_unlock();
+	return result;
+}
+
+void udp_v4_early_demux(struct sk_buff *skb)
+{
+	struct net *net = dev_net(skb->dev);
+	const struct iphdr *iph;
+	const struct udphdr *uh;
+	struct sock *sk;
+	struct dst_entry *dst;
+	int dif = skb->dev->ifindex;
+
+	/* validate the packet */
+	if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
+		return;
+
+	iph = ip_hdr(skb);
+	uh = udp_hdr(skb);
+
+	if (skb->pkt_type == PACKET_BROADCAST ||
+	    skb->pkt_type == PACKET_MULTICAST)
+		sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
+						   uh->source, iph->saddr, dif);
+	else if (skb->pkt_type == PACKET_HOST)
+		sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr,
+					     uh->source, iph->saddr, dif);
+	else
+		return;
+
+	if (!sk)
+		return;
+
+	skb->sk = sk;
+	skb->destructor = sock_edemux;
+	dst = sk->sk_rx_dst;
+
+	if (dst)
+		dst = dst_check(dst, 0);
+	if (dst)
+		skb_dst_set_noref(skb, dst);
+}
+
 int udp_rcv(struct sk_buff *skb)
 {
 	return __udp4_lib_rcv(skb, &udp_table, IPPROTO_UDP);
@@ -1762,9 +1993,16 @@ int udp_rcv(struct sk_buff *skb)
 
 void udp_destroy_sock(struct sock *sk)
 {
+	struct udp_sock *up = udp_sk(sk);
 	bool slow = lock_sock_fast(sk);
 	udp_flush_pending_frames(sk);
 	unlock_sock_fast(sk, slow);
+	if (static_key_false(&udp_encap_needed) && up->encap_type) {
+		void (*encap_destroy)(struct sock *sk);
+		encap_destroy = ACCESS_ONCE(up->encap_destroy);
+		if (encap_destroy)
+			encap_destroy(sk);
+	}
 }
 
 /*
@@ -1775,7 +2013,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 		       int (*push_pending_frames)(struct sock *))
 {
 	struct udp_sock *up = udp_sk(sk);
-	int val;
+	int val, valbool;
 	int err = 0;
 	int is_udplite = IS_UDPLITE(sk);
 
@@ -1785,6 +2023,8 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 	if (get_user(val, (int __user *)optval))
 		return -EFAULT;
 
+	valbool = val ? 1 : 0;
+
 	switch (optname) {
 	case UDP_CORK:
 		if (val != 0) {
@@ -1814,6 +2054,14 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 		}
 		break;
 
+	case UDP_NO_CHECK6_TX:
+		up->no_check6_tx = valbool;
+		break;
+
+	case UDP_NO_CHECK6_RX:
+		up->no_check6_rx = valbool;
+		break;
+
 	/*
 	 * 	UDP-Lite's partial checksum coverage (RFC 3828).
 	 */
@@ -1896,6 +2144,14 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname,
 		val = up->encap_type;
 		break;
 
+	case UDP_NO_CHECK6_TX:
+		val = up->no_check6_tx;
+		break;
+
+	case UDP_NO_CHECK6_RX:
+		val = up->no_check6_rx;
+		break;
+
 	/* The following two cannot be changed on UDP sockets, the return is
 	 * always 0 (which corresponds to the full checksum coverage of UDP). */
 	case UDPLITE_SEND_CSCOV:
@@ -1953,6 +2209,8 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	unsigned int mask = datagram_poll(file, sock, wait);
 	struct sock *sk = sock->sk;
 
+	sock_rps_record_flow(sk);
+
 	/* Check for false positives due to checksum errors */
 	if ((mask & POLLRDNORM) && !(file->f_flags & O_NONBLOCK) &&
 	    !(sk->sk_shutdown & RCV_SHUTDOWN) && !first_packet_length(sk))
@@ -2086,7 +2344,7 @@ static void udp_seq_stop(struct seq_file *seq, void *v)
 
 int udp_seq_open(struct inode *inode, struct file *file)
 {
-	struct udp_seq_afinfo *afinfo = PDE(inode)->data;
+	struct udp_seq_afinfo *afinfo = PDE_DATA(inode);
 	struct udp_iter_state *s;
 	int err;
 
@@ -2128,7 +2386,7 @@ EXPORT_SYMBOL(udp_proc_unregister);
 
 /* ------------------------------------------------------------------------ */
 static void udp4_format_sock(struct sock *sp, struct seq_file *f,
-		int bucket, int *len)
+		int bucket)
 {
 	struct inet_sock *inet = inet_sk(sp);
 	__be32 dest = inet->inet_daddr;
@@ -2137,7 +2395,7 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f,
 	__u16 srcp	  = ntohs(inet->inet_sport);
 
 	seq_printf(f, "%5d: %08X:%04X %08X:%04X"
-		" %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d%n",
+		" %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %d",
 		bucket, src, srcp, dest, destp, sp->sk_state,
 		sk_wmem_alloc_get(sp),
 		sk_rmem_alloc_get(sp),
@@ -2145,23 +2403,22 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f,
 		from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)),
 		0, sock_i_ino(sp),
 		atomic_read(&sp->sk_refcnt), sp,
-		atomic_read(&sp->sk_drops), len);
+		atomic_read(&sp->sk_drops));
 }
 
 int udp4_seq_show(struct seq_file *seq, void *v)
 {
+	seq_setwidth(seq, 127);
 	if (v == SEQ_START_TOKEN)
-		seq_printf(seq, "%-127s\n",
-			   "  sl  local_address rem_address   st tx_queue "
+		seq_puts(seq, "  sl  local_address rem_address   st tx_queue "
 			   "rx_queue tr tm->when retrnsmt   uid  timeout "
 			   "inode ref pointer drops");
 	else {
 		struct udp_iter_state *state = seq->private;
-		int len;
 
-		udp4_format_sock(v, seq, state->bucket, &len);
-		seq_printf(seq, "%*s\n", 127 - len, "");
+		udp4_format_sock(v, seq, state->bucket);
 	}
+	seq_pad(seq, '\n');
 	return 0;
 }
 
@@ -2270,66 +2527,78 @@ void __init udp_init(void)
 	sysctl_udp_wmem_min = SK_MEM_QUANTUM;
 }
 
-int udp4_ufo_send_check(struct sk_buff *skb)
+struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
+				       netdev_features_t features)
 {
-	const struct iphdr *iph;
-	struct udphdr *uh;
+	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	u16 mac_offset = skb->mac_header;
+	int mac_len = skb->mac_len;
+	int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
+	__be16 protocol = skb->protocol;
+	netdev_features_t enc_features;
+	int udp_offset, outer_hlen;
+	unsigned int oldlen;
+	bool need_csum;
+
+	oldlen = (u16)~skb->len;
+
+	if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
+		goto out;
 
-	if (!pskb_may_pull(skb, sizeof(*uh)))
-		return -EINVAL;
+	skb->encapsulation = 0;
+	__skb_pull(skb, tnl_hlen);
+	skb_reset_mac_header(skb);
+	skb_set_network_header(skb, skb_inner_network_offset(skb));
+	skb->mac_len = skb_inner_network_offset(skb);
+	skb->protocol = htons(ETH_P_TEB);
+
+	need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM);
+	if (need_csum)
+		skb->encap_hdr_csum = 1;
+
+	/* segment inner packet. */
+	enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
+	segs = skb_mac_gso_segment(skb, enc_features);
+	if (!segs || IS_ERR(segs)) {
+		skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset,
+				     mac_len);
+		goto out;
+	}
 
-	iph = ip_hdr(skb);
-	uh = udp_hdr(skb);
+	outer_hlen = skb_tnl_header_len(skb);
+	udp_offset = outer_hlen - tnl_hlen;
+	skb = segs;
+	do {
+		struct udphdr *uh;
+		int len;
 
-	uh->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
-				       IPPROTO_UDP, 0);
-	skb->csum_start = skb_transport_header(skb) - skb->head;
-	skb->csum_offset = offsetof(struct udphdr, check);
-	skb->ip_summed = CHECKSUM_PARTIAL;
-	return 0;
-}
+		skb_reset_inner_headers(skb);
+		skb->encapsulation = 1;
 
-struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
-	netdev_features_t features)
-{
-	struct sk_buff *segs = ERR_PTR(-EINVAL);
-	unsigned int mss;
-	int offset;
-	__wsum csum;
-
-	mss = skb_shinfo(skb)->gso_size;
-	if (unlikely(skb->len <= mss))
-		goto out;
+		skb->mac_len = mac_len;
 
-	if (skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) {
-		/* Packet is from an untrusted source, reset gso_segs. */
-		int type = skb_shinfo(skb)->gso_type;
+		skb_push(skb, outer_hlen);
+		skb_reset_mac_header(skb);
+		skb_set_network_header(skb, mac_len);
+		skb_set_transport_header(skb, udp_offset);
+		len = skb->len - udp_offset;
+		uh = udp_hdr(skb);
+		uh->len = htons(len);
 
-		if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY |
-				      SKB_GSO_GRE) ||
-			     !(type & (SKB_GSO_UDP))))
-			goto out;
+		if (need_csum) {
+			__be32 delta = htonl(oldlen + len);
 
-		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
+			uh->check = ~csum_fold((__force __wsum)
+					       ((__force u32)uh->check +
+						(__force u32)delta));
+			uh->check = gso_make_checksum(skb, ~uh->check);
 
-		segs = NULL;
-		goto out;
-	}
+			if (uh->check == 0)
+				uh->check = CSUM_MANGLED_0;
+		}
 
-	/* Do software UFO. Complete and fill in the UDP checksum as HW cannot
-	 * do checksum of UDP packets sent as multiple IP fragments.
-	 */
-	offset = skb_checksum_start_offset(skb);
-	csum = skb_checksum(skb, offset, skb->len - offset, 0);
-	offset += skb->csum_offset;
-	*(__sum16 *)(skb->data + offset) = csum_fold(csum);
-	skb->ip_summed = CHECKSUM_NONE;
-
-	/* Fragment the skb. IP headers of the fragments are updated in
-	 * inet_gso_segment()
-	 */
-	segs = skb_segment(skb, features);
+		skb->protocol = protocol;
+	} while ((skb = skb->next));
 out:
 	return segs;
 }
-