1 files changed, 41 insertions, 26 deletions

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index c02bf011d4a6f4..189c9113fe9a18 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -427,15 +427,21 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 {
 	struct sock *sk, *result;
 	int score, badness;
+	bool need_rescore;
 
 	result = NULL;
 	badness = 0;
 	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
-		score = compute_score(sk, net, saddr, sport,
-				      daddr, hnum, dif, sdif);
+		need_rescore = false;
+rescore:
+		score = compute_score(need_rescore ? result : sk, net, saddr,
+				      sport, daddr, hnum, dif, sdif);
 		if (score > badness) {
 			badness = score;
 
+			if (need_rescore)
+				continue;
+
 			if (sk->sk_state == TCP_ESTABLISHED) {
 				result = sk;
 				continue;
@@ -456,9 +462,14 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 			if (IS_ERR(result))
 				continue;
 
-			badness = compute_score(result, net, saddr, sport,
-						daddr, hnum, dif, sdif);
-
+			/* compute_score is too long of a function to be
+			 * inlined, and calling it again here yields
+			 * measureable overhead for some
+			 * workloads. Work around it by jumping
+			 * backwards to rescore 'result'.
+			 */
+			need_rescore = true;
+			goto rescore;
 		}
 	}
 	return result;
@@ -532,7 +543,8 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
 struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
 				 __be16 sport, __be16 dport)
 {
-	const struct iphdr *iph = ip_hdr(skb);
+	const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
+	const struct iphdr *iph = (struct iphdr *)(skb->data + offset);
 	struct net *net = dev_net(skb->dev);
 	int iif, sdif;
 
@@ -1123,16 +1135,17 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	if (msg->msg_controllen) {
 		err = udp_cmsg_send(sk, msg, &ipc.gso_size);
-		if (err > 0)
+		if (err > 0) {
 			err = ip_cmsg_send(sk, msg, &ipc,
 					   sk->sk_family == AF_INET6);
+			connected = 0;
+		}
 		if (unlikely(err < 0)) {
 			kfree(ipc.opt);
 			return err;
 		}
 		if (ipc.opt)
 			free = 1;
-		connected = 0;
 	}
 	if (!ipc.opt) {
 		struct ip_options_rcu *inet_opt;
@@ -1205,7 +1218,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	}
 
 	if (connected)
-		rt = (struct rtable *)sk_dst_check(sk, 0);
+		rt = dst_rtable(sk_dst_check(sk, 0));
 
 	if (!rt) {
 		struct net *net = sock_net(sk);
@@ -1499,13 +1512,15 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 	struct sk_buff_head *list = &sk->sk_receive_queue;
 	int rmem, err = -ENOMEM;
 	spinlock_t *busy = NULL;
-	int size;
+	bool becomes_readable;
+	int size, rcvbuf;
 
-	/* try to avoid the costly atomic add/sub pair when the receive
-	 * queue is full; always allow at least a packet
+	/* Immediately drop when the receive queue is full.
+	 * Always allow at least one packet.
 	 */
 	rmem = atomic_read(&sk->sk_rmem_alloc);
-	if (rmem > sk->sk_rcvbuf)
+	rcvbuf = READ_ONCE(sk->sk_rcvbuf);
+	if (rmem > rcvbuf)
 		goto drop;
 
 	/* Under mem pressure, it might be helpful to help udp_recvmsg()
@@ -1514,7 +1529,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 	 * - Less cache line misses at copyout() time
 	 * - Less work at consume_skb() (less alien page frag freeing)
 	 */
-	if (rmem > (sk->sk_rcvbuf >> 1)) {
+	if (rmem > (rcvbuf >> 1)) {
 		skb_condense(skb);
 
 		busy = busylock_acquire(sk);
@@ -1522,12 +1537,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 	size = skb->truesize;
 	udp_set_dev_scratch(skb);
 
-	/* we drop only if the receive buf is full and the receive
-	 * queue contains some other skb
-	 */
-	rmem = atomic_add_return(size, &sk->sk_rmem_alloc);
-	if (rmem > (size + (unsigned int)sk->sk_rcvbuf))
-		goto uncharge_drop;
+	atomic_add(size, &sk->sk_rmem_alloc);
 
 	spin_lock(&list->lock);
 	err = udp_rmem_schedule(sk, size);
@@ -1543,12 +1553,19 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 	 */
 	sock_skb_set_dropcount(sk, skb);
 
+	becomes_readable = skb_queue_empty(list);
 	__skb_queue_tail(list, skb);
 	spin_unlock(&list->lock);
 
-	if (!sock_flag(sk, SOCK_DEAD))
-		INDIRECT_CALL_1(sk->sk_data_ready, sock_def_readable, sk);
-
+	if (!sock_flag(sk, SOCK_DEAD)) {
+		if (becomes_readable ||
+		    sk->sk_data_ready != sock_def_readable ||
+		    READ_ONCE(sk->sk_peek_off) >= 0)
+			INDIRECT_CALL_1(sk->sk_data_ready,
+					sock_def_readable, sk);
+		else
+			sk_wake_async_rcu(sk, SOCK_WAKE_WAITD, POLL_IN);
+	}
 	busylock_release(busy);
 	return 0;
 
@@ -2056,8 +2073,8 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 			drop_reason = SKB_DROP_REASON_PROTO_MEM;
 		}
 		UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
+		trace_udp_fail_queue_rcv_skb(rc, sk, skb);
 		kfree_skb_reason(skb, drop_reason);
-		trace_udp_fail_queue_rcv_skb(rc, sk);
 		return -1;
 	}
 
@@ -2695,8 +2712,6 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 #ifdef CONFIG_XFRM
 		case UDP_ENCAP_ESPINUDP:
 			set_xfrm_gro_udp_encap_rcv(val, sk->sk_family, sk);
-			fallthrough;
-		case UDP_ENCAP_ESPINUDP_NON_IKE:
 #if IS_ENABLED(CONFIG_IPV6)
 			if (sk->sk_family == AF_INET6)
 				WRITE_ONCE(up->encap_rcv,