Merge branch 'udp-gro-L4'

Paolo Abeni says:

====================
udp: GRO L4 improvements

This series improves the UDP L4 - either 'forward' or 'frag_list' -
co-existence with UDP tunnel GRO, allowing the first to take place
correctly even for encapsulated UDP traffic.

The first for patches are mostly bugfixes, addressing some GRO
edge-cases when both tunnels and L4 are present, enabled and in use.

The next 3 patches avoid unneeded segmentation when UDP GRO
traffic traverses in the receive path UDP tunnels.

Finally, some self-tests are included, covering the relevant
GRO scenarios.

Even if most patches are actually bugfixes, this series is
targeting net-next, as overall it makes available a new feature.

v2 -> v3:
 - no code changes, more verbose commit messages and comment in
   patch 1/8

v1 -> v2:
 - restrict post segmentation csum fixup to the only the relevant pkts
 - use individual 'accept_gso_type' fields instead of whole gso bitmask
   (Willem)
 - use only ipv6 addesses from test range in self-tests (Willem)
 - hopefully clarified most individual patches commit messages
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/bareudp.c

@@ -218,6 +218,7 @@ static struct socket *bareudp_create_sock(struct net *net, __be16 port)
 	if (err < 0)
 		return ERR_PTR(err);
 
+	udp_allow_gso(sock->sk);
 	return sock;
 }
 

drivers/net/geneve.c

@@ -461,6 +461,7 @@ static struct socket *geneve_create_sock(struct net *net, bool ipv6,
 	if (err < 0)
 		return ERR_PTR(err);
 
+	udp_allow_gso(sock->sk);
 	return sock;
 }
 

drivers/net/vxlan.c

@@ -3484,6 +3484,7 @@ static struct socket *vxlan_create_sock(struct net *net, bool ipv6,
 	if (err < 0)
 		return ERR_PTR(err);
 
+	udp_allow_gso(sock->sk);
 	return sock;
 }
 

include/linux/udp.h

@@ -51,7 +51,9 @@ struct udp_sock {
 					   * different encapsulation layer set
 					   * this
 					   */
-			 gro_enabled:1;	/* Can accept GRO packets */
+			 gro_enabled:1,	/* Request GRO aggregation */
+			 accept_udp_l4:1,
+			 accept_udp_fraglist:1;
 	/*
 	 * Following member retains the information to create a UDP header
 	 * when the socket is uncorked.
@@ -131,8 +133,22 @@ static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk,
 
 static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb)
 {
-	return !udp_sk(sk)->gro_enabled && skb_is_gso(skb) &&
-	       skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4;
+	if (!skb_is_gso(skb))
+		return false;
+
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && !udp_sk(sk)->accept_udp_l4)
+		return true;
+
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST && !udp_sk(sk)->accept_udp_fraglist)
+		return true;
+
+	return false;
+}
+
+static inline void udp_allow_gso(struct sock *sk)
+{
+	udp_sk(sk)->accept_udp_l4 = 1;
+	udp_sk(sk)->accept_udp_fraglist = 1;
 }
 
 #define udp_portaddr_for_each_entry(__sk, list) \

include/net/udp.h

@@ -515,6 +515,29 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
 	return segs;
 }
 
+static inline void udp_post_segment_fix_csum(struct sk_buff *skb)
+{
+	/* UDP-lite can't land here - no GRO */
+	WARN_ON_ONCE(UDP_SKB_CB(skb)->partial_cov);
+
+	/* UDP packets generated with UDP_SEGMENT and traversing:
+	 *
+	 * UDP tunnel(xmit) -> veth (segmentation) -> veth (gro) -> UDP tunnel (rx)
+	 *
+	 * can reach an UDP socket with CHECKSUM_NONE, because
+	 * __iptunnel_pull_header() converts CHECKSUM_PARTIAL into NONE.
+	 * SKB_GSO_UDP_L4 or SKB_GSO_FRAGLIST packets with no UDP tunnel will
+	 * have a valid checksum, as the GRO engine validates the UDP csum
+	 * before the aggregation and nobody strips such info in between.
+	 * Instead of adding another check in the tunnel fastpath, we can force
+	 * a valid csum after the segmentation.
+	 * Additionally fixup the UDP CB.
+	 */
+	UDP_SKB_CB(skb)->cscov = skb->len;
+	if (skb->ip_summed == CHECKSUM_NONE && !skb->csum_valid)
+		skb->csum_valid = 1;
+}
+
 #ifdef CONFIG_BPF_SYSCALL
 struct sk_psock;
 struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock);

net/ipv4/udp.c

@@ -2178,6 +2178,8 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	segs = udp_rcv_segment(sk, skb, true);
 	skb_list_walk_safe(segs, skb, next) {
 		__skb_pull(skb, skb_transport_offset(skb));
+
+		udp_post_segment_fix_csum(skb);
 		ret = udp_queue_rcv_one_skb(sk, skb);
 		if (ret > 0)
 			ip_protocol_deliver_rcu(dev_net(skb->dev), skb, ret);
@@ -2664,9 +2666,12 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 
 	case UDP_GRO:
 		lock_sock(sk);
+
+		/* when enabling GRO, accept the related GSO packet type */
 		if (valbool)
 			udp_tunnel_encap_enable(sk->sk_socket);
 		up->gro_enabled = valbool;
+		up->accept_udp_l4 = valbool;
 		release_sock(sk);
 		break;
 

net/ipv4/udp_offload.c

@@ -515,21 +515,24 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
 	unsigned int off = skb_gro_offset(skb);
 	int flush = 1;
 
+	/* we can do L4 aggregation only if the packet can't land in a tunnel
+	 * otherwise we could corrupt the inner stream
+	 */
 	NAPI_GRO_CB(skb)->is_flist = 0;
-	if (skb->dev->features & NETIF_F_GRO_FRAGLIST)
-		NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled: 1;
+	if (!sk || !udp_sk(sk)->gro_receive) {
+		if (skb->dev->features & NETIF_F_GRO_FRAGLIST)
+			NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled : 1;
 
-	if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) ||
-	    (sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist) {
-		pp = call_gro_receive(udp_gro_receive_segment, head, skb);
+		if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) ||
+		    (sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist)
+			pp = call_gro_receive(udp_gro_receive_segment, head, skb);
 		return pp;
 	}
 
-	if (!sk || NAPI_GRO_CB(skb)->encap_mark ||
+	if (NAPI_GRO_CB(skb)->encap_mark ||
 	    (uh->check && skb->ip_summed != CHECKSUM_PARTIAL &&
 	     NAPI_GRO_CB(skb)->csum_cnt == 0 &&
-	     !NAPI_GRO_CB(skb)->csum_valid) ||
-	    !udp_sk(sk)->gro_receive)
+	     !NAPI_GRO_CB(skb)->csum_valid))
 		goto out;
 
 	/* mark that this skb passed once through the tunnel gro layer */
@@ -639,6 +642,11 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff,
 		skb_shinfo(skb)->gso_type = uh->check ? SKB_GSO_UDP_TUNNEL_CSUM
 					: SKB_GSO_UDP_TUNNEL;
 
+		/* clear the encap mark, so that inner frag_list gro_complete
+		 * can take place
+		 */
+		NAPI_GRO_CB(skb)->encap_mark = 0;
+
 		/* Set encapsulation before calling into inner gro_complete()
 		 * functions to make them set up the inner offsets.
 		 */
@@ -662,7 +670,8 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff)
 	const struct iphdr *iph = ip_hdr(skb);
 	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
 
-	if (NAPI_GRO_CB(skb)->is_flist) {
+	/* do fraglist only if there is no outer UDP encap (or we already processed it) */
+	if (NAPI_GRO_CB(skb)->is_flist && !NAPI_GRO_CB(skb)->encap_mark) {
 		uh->len = htons(skb->len - nhoff);
 
 		skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4);

net/ipv6/udp.c

@@ -749,6 +749,7 @@ static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	skb_list_walk_safe(segs, skb, next) {
 		__skb_pull(skb, skb_transport_offset(skb));
 
+		udp_post_segment_fix_csum(skb);
 		ret = udpv6_queue_rcv_one_skb(sk, skb);
 		if (ret > 0)
 			ip6_protocol_deliver_rcu(dev_net(skb->dev), skb, ret,

net/ipv6/udp_offload.c

@@ -163,7 +163,8 @@ INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff)
 	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
 
-	if (NAPI_GRO_CB(skb)->is_flist) {
+	/* do fraglist only if there is no outer UDP encap (or we already processed it) */
+	if (NAPI_GRO_CB(skb)->is_flist && !NAPI_GRO_CB(skb)->encap_mark) {
 		uh->len = htons(skb->len - nhoff);
 
 		skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4);

tools/testing/selftests/net/Makefile

@@ -23,6 +23,7 @@ TEST_PROGS += drop_monitor_tests.sh
 TEST_PROGS += vrf_route_leaking.sh
 TEST_PROGS += bareudp.sh
 TEST_PROGS += unicast_extensions.sh
+TEST_PROGS += udpgro_fwd.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any