1 files changed, 160 insertions, 52 deletions

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1f4d405eafba..0bf5d399a03c 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -139,6 +139,7 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num,
 {
 	struct sock *sk2;
 	struct hlist_nulls_node *node;
+	kuid_t uid = sock_i_uid(sk);
 
 	sk_nulls_for_each(sk2, node, &hslot->head)
 		if (net_eq(sock_net(sk2), net) &&
@@ -147,6 +148,8 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num,
 		    (!sk2->sk_reuse || !sk->sk_reuse) &&
 		    (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if ||
 		     sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
+		    (!sk2->sk_reuseport || !sk->sk_reuseport ||
+		      !uid_eq(uid, sock_i_uid(sk2))) &&
 		    (*saddr_comp)(sk, sk2)) {
 			if (bitmap)
 				__set_bit(udp_sk(sk2)->udp_port_hash >> log,
@@ -169,6 +172,7 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num,
 {
 	struct sock *sk2;
 	struct hlist_nulls_node *node;
+	kuid_t uid = sock_i_uid(sk);
 	int res = 0;
 
 	spin_lock(&hslot2->lock);
@@ -179,6 +183,8 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num,
 		    (!sk2->sk_reuse || !sk->sk_reuse) &&
 		    (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if ||
 		     sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
+		    (!sk2->sk_reuseport || !sk->sk_reuseport ||
+		      !uid_eq(uid, sock_i_uid(sk2))) &&
 		    (*saddr_comp)(sk, sk2)) {
 			res = 1;
 			break;
@@ -337,26 +343,26 @@ static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr,
 			!ipv6_only_sock(sk)) {
 		struct inet_sock *inet = inet_sk(sk);
 
-		score = (sk->sk_family == PF_INET ? 1 : 0);
+		score = (sk->sk_family == PF_INET ? 2 : 1);
 		if (inet->inet_rcv_saddr) {
 			if (inet->inet_rcv_saddr != daddr)
 				return -1;
-			score += 2;
+			score += 4;
 		}
 		if (inet->inet_daddr) {
 			if (inet->inet_daddr != saddr)
 				return -1;
-			score += 2;
+			score += 4;
 		}
 		if (inet->inet_dport) {
 			if (inet->inet_dport != sport)
 				return -1;
-			score += 2;
+			score += 4;
 		}
 		if (sk->sk_bound_dev_if) {
 			if (sk->sk_bound_dev_if != dif)
 				return -1;
-			score += 2;
+			score += 4;
 		}
 	}
 	return score;
@@ -365,7 +371,6 @@ static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr,
 /*
  * In this second variant, we check (daddr, dport) matches (inet_rcv_sadd, inet_num)
  */
-#define SCORE2_MAX (1 + 2 + 2 + 2)
 static inline int compute_score2(struct sock *sk, struct net *net,
 				 __be32 saddr, __be16 sport,
 				 __be32 daddr, unsigned int hnum, int dif)
@@ -380,21 +385,21 @@ static inline int compute_score2(struct sock *sk, struct net *net,
 		if (inet->inet_num != hnum)
 			return -1;
 
-		score = (sk->sk_family == PF_INET ? 1 : 0);
+		score = (sk->sk_family == PF_INET ? 2 : 1);
 		if (inet->inet_daddr) {
 			if (inet->inet_daddr != saddr)
 				return -1;
-			score += 2;
+			score += 4;
 		}
 		if (inet->inet_dport) {
 			if (inet->inet_dport != sport)
 				return -1;
-			score += 2;
+			score += 4;
 		}
 		if (sk->sk_bound_dev_if) {
 			if (sk->sk_bound_dev_if != dif)
 				return -1;
-			score += 2;
+			score += 4;
 		}
 	}
 	return score;
@@ -409,19 +414,29 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 {
 	struct sock *sk, *result;
 	struct hlist_nulls_node *node;
-	int score, badness;
+	int score, badness, matches = 0, reuseport = 0;
+	u32 hash = 0;
 
 begin:
 	result = NULL;
-	badness = -1;
+	badness = 0;
 	udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) {
 		score = compute_score2(sk, net, saddr, sport,
 				      daddr, hnum, dif);
 		if (score > badness) {
 			result = sk;
 			badness = score;
-			if (score == SCORE2_MAX)
-				goto exact_match;
+			reuseport = sk->sk_reuseport;
+			if (reuseport) {
+				hash = inet_ehashfn(net, daddr, hnum,
+						    saddr, htons(sport));
+				matches = 1;
+			}
+		} else if (score == badness && reuseport) {
+			matches++;
+			if (((u64)hash * matches) >> 32 == 0)
+				result = sk;
+			hash = next_pseudo_random32(hash);
 		}
 	}
 	/*
@@ -431,9 +446,7 @@ begin:
 	 */
 	if (get_nulls_value(node) != slot2)
 		goto begin;
-
 	if (result) {
-exact_match:
 		if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2)))
 			result = NULL;
 		else if (unlikely(compute_score2(result, net, saddr, sport,
@@ -457,7 +470,8 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 	unsigned short hnum = ntohs(dport);
 	unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
 	struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
-	int score, badness;
+	int score, badness, matches = 0, reuseport = 0;
+	u32 hash = 0;
 
 	rcu_read_lock();
 	if (hslot->count > 10) {
@@ -486,13 +500,24 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 	}
 begin:
 	result = NULL;
-	badness = -1;
+	badness = 0;
 	sk_nulls_for_each_rcu(sk, node, &hslot->head) {
 		score = compute_score(sk, net, saddr, hnum, sport,
 				      daddr, dport, dif);
 		if (score > badness) {
 			result = sk;
 			badness = score;
+			reuseport = sk->sk_reuseport;
+			if (reuseport) {
+				hash = inet_ehashfn(net, daddr, hnum,
+						    saddr, htons(sport));
+				matches = 1;
+			}
+		} else if (score == badness && reuseport) {
+			matches++;
+			if (((u64)hash * matches) >> 32 == 0)
+				result = sk;
+			hash = next_pseudo_random32(hash);
 		}
 	}
 	/*
@@ -877,9 +902,9 @@ 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);
 		if (err)
@@ -971,7 +996,7 @@ back_from_confirm:
 				  sizeof(struct udphdr), &ipc, &rt,
 				  msg->msg_flags);
 		err = PTR_ERR(skb);
-		if (skb && !IS_ERR(skb))
+		if (!IS_ERR_OR_NULL(skb))
 			err = udp_send_skb(skb, fl4);
 		goto out;
 	}
@@ -1106,6 +1131,8 @@ 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);
@@ -1261,8 +1288,10 @@ 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)
@@ -1488,7 +1517,7 @@ 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))
@@ -1508,6 +1537,8 @@ 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);
@@ -1724,6 +1755,7 @@ 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);
@@ -1737,9 +1769,16 @@ 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);
+	}
 }
 
 /*
@@ -2061,7 +2100,7 @@ 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;
 
@@ -2097,7 +2136,7 @@ EXPORT_SYMBOL(udp_proc_register);
 
 void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo)
 {
-	proc_net_remove(net, afinfo->name);
+	remove_proc_entry(afinfo->name, net->proc_net);
 }
 EXPORT_SYMBOL(udp_proc_unregister);
 
@@ -2247,31 +2286,91 @@ void __init udp_init(void)
 
 int udp4_ufo_send_check(struct sk_buff *skb)
 {
-	const struct iphdr *iph;
-	struct udphdr *uh;
-
-	if (!pskb_may_pull(skb, sizeof(*uh)))
+	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
 		return -EINVAL;
 
-	iph = ip_hdr(skb);
-	uh = udp_hdr(skb);
+	if (likely(!skb->encapsulation)) {
+		const struct iphdr *iph;
+		struct udphdr *uh;
 
-	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;
+		iph = ip_hdr(skb);
+		uh = udp_hdr(skb);
+
+		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;
 }
 
+static struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
+		netdev_features_t features)
+{
+	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	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 outer_hlen;
+
+	if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
+		goto out;
+
+	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);
+
+	/* 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))
+		goto out;
+
+	outer_hlen = skb_tnl_header_len(skb);
+	skb = segs;
+	do {
+		struct udphdr *uh;
+		int udp_offset = outer_hlen - tnl_hlen;
+
+		skb->mac_len = mac_len;
+
+		skb_push(skb, outer_hlen);
+		skb_reset_mac_header(skb);
+		skb_set_network_header(skb, mac_len);
+		skb_set_transport_header(skb, udp_offset);
+		uh = udp_hdr(skb);
+		uh->len = htons(skb->len - udp_offset);
+
+		/* csum segment if tunnel sets skb with csum. */
+		if (unlikely(uh->check)) {
+			struct iphdr *iph = ip_hdr(skb);
+
+			uh->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
+						       skb->len - udp_offset,
+						       IPPROTO_UDP, 0);
+			uh->check = csum_fold(skb_checksum(skb, udp_offset,
+							   skb->len - udp_offset, 0));
+			if (uh->check == 0)
+				uh->check = CSUM_MANGLED_0;
+
+		}
+		skb->ip_summed = CHECKSUM_NONE;
+		skb->protocol = protocol;
+	} while ((skb = skb->next));
+out:
+	return segs;
+}
+
 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;
@@ -2280,7 +2379,9 @@ struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 		/* Packet is from an untrusted source, reset gso_segs. */
 		int type = skb_shinfo(skb)->gso_type;
 
-		if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) ||
+		if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY |
+				      SKB_GSO_UDP_TUNNEL |
+				      SKB_GSO_GRE) ||
 			     !(type & (SKB_GSO_UDP))))
 			goto out;
 
@@ -2290,20 +2391,27 @@ struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 		goto out;
 	}
 
-	/* 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);
+	if (skb->encapsulation && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL)
+		segs = skb_udp_tunnel_segment(skb, features);
+	else {
+		int offset;
+		__wsum csum;
+
+		/* 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;
+
+		segs = skb_segment(skb, features);
+	}
 out:
 	return segs;
 }
-