Merge branch 'gro-in-udp'

Tom Herbert says:

====================
udp: GRO in UDP sockets

This patch set adds GRO functions (gro_receive and gro_complete) to UDP
sockets and removes udp_offload infrastructure.

Add GRO functions (gro_receive and gro_complete) to UDP sockets. In
udp_gro_receive and udp_gro_complete a socket lookup is done instead of
looking up the port number in udp_offloads.  If a socket is found and
there are GRO functions for it then those are called. This feature
allows binding GRO functions to more than just a port number.
Eventually, we will be able to use this technique to allow application
defined GRO for an application protocol by attaching BPF porgrams to UDP
sockets for doing GRO.

In order to implement these functions, we added exported
udp6_lib_lookup_skb and udp4_lib_lookup_skb functions in ipv4/udp.c and
ipv6/udp.c. Also, inet_iif and references to skb_dst() were changed to
check that dst is set in skbuf before derefencing. In the GRO path there
is now a UDP socket lookup performed before dst is set, to the get the
device in that case we simply use skb->dev.

Tested:

Ran various combinations of VXLAN and GUE TCP_STREAM and TCP_RR tests.
Did not see any material regression.
====================

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

drivers/net/geneve.c

@@ -87,7 +87,6 @@ struct geneve_sock {
 	struct socket		*sock;
 	struct rcu_head		rcu;
 	int			refcnt;
-	struct udp_offload	udp_offloads;
 	struct hlist_head	vni_list[VNI_HASH_SIZE];
 	u32			flags;
 };
@@ -409,14 +408,6 @@ static void geneve_notify_add_rx_port(struct geneve_sock *gs)
 	struct net *net = sock_net(sk);
 	sa_family_t sa_family = geneve_get_sk_family(gs);
 	__be16 port = inet_sk(sk)->inet_sport;
-	int err;
-
-	if (sa_family == AF_INET) {
-		err = udp_add_offload(sock_net(sk), &gs->udp_offloads);
-		if (err)
-			pr_warn("geneve: udp_add_offload failed with status %d\n",
-				err);
-	}
 
 	rcu_read_lock();
 	for_each_netdev_rcu(net, dev) {
@@ -432,9 +423,9 @@ static int geneve_hlen(struct genevehdr *gh)
 	return sizeof(*gh) + gh->opt_len * 4;
 }
 
-static struct sk_buff **geneve_gro_receive(struct sk_buff **head,
-					   struct sk_buff *skb,
-					   struct udp_offload *uoff)
+static struct sk_buff **geneve_gro_receive(struct sock *sk,
+					   struct sk_buff **head,
+					   struct sk_buff *skb)
 {
 	struct sk_buff *p, **pp = NULL;
 	struct genevehdr *gh, *gh2;
@@ -495,8 +486,8 @@ static struct sk_buff **geneve_gro_receive(struct sk_buff **head,
 	return pp;
 }
 
-static int geneve_gro_complete(struct sk_buff *skb, int nhoff,
-			       struct udp_offload *uoff)
+static int geneve_gro_complete(struct sock *sk, struct sk_buff *skb,
+			       int nhoff)
 {
 	struct genevehdr *gh;
 	struct packet_offload *ptype;
@@ -545,14 +536,14 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
 		INIT_HLIST_HEAD(&gs->vni_list[h]);
 
 	/* Initialize the geneve udp offloads structure */
-	gs->udp_offloads.port = port;
-	gs->udp_offloads.callbacks.gro_receive  = geneve_gro_receive;
-	gs->udp_offloads.callbacks.gro_complete = geneve_gro_complete;
 	geneve_notify_add_rx_port(gs);
 
 	/* Mark socket as an encapsulation socket */
+	memset(&tunnel_cfg, 0, sizeof(tunnel_cfg));
 	tunnel_cfg.sk_user_data = gs;
 	tunnel_cfg.encap_type = 1;
+	tunnel_cfg.gro_receive = geneve_gro_receive;
+	tunnel_cfg.gro_complete = geneve_gro_complete;
 	tunnel_cfg.encap_rcv = geneve_udp_encap_recv;
 	tunnel_cfg.encap_destroy = NULL;
 	setup_udp_tunnel_sock(net, sock, &tunnel_cfg);
@@ -576,9 +567,6 @@ static void geneve_notify_del_rx_port(struct geneve_sock *gs)
 	}
 
 	rcu_read_unlock();
-
-	if (sa_family == AF_INET)
-		udp_del_offload(&gs->udp_offloads);
 }
 
 static void __geneve_sock_release(struct geneve_sock *gs)

drivers/net/vxlan.c

@@ -551,16 +551,15 @@ static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb,
 	return vh;
 }
 
-static struct sk_buff **vxlan_gro_receive(struct sk_buff **head,
-					  struct sk_buff *skb,
-					  struct udp_offload *uoff)
+static struct sk_buff **vxlan_gro_receive(struct sock *sk,
+					  struct sk_buff **head,
+					  struct sk_buff *skb)
 {
 	struct sk_buff *p, **pp = NULL;
 	struct vxlanhdr *vh, *vh2;
 	unsigned int hlen, off_vx;
 	int flush = 1;
-	struct vxlan_sock *vs = container_of(uoff, struct vxlan_sock,
-					     udp_offloads);
+	struct vxlan_sock *vs = rcu_dereference_sk_user_data(sk);
 	__be32 flags;
 	struct gro_remcsum grc;
 
@@ -613,8 +612,7 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head,
 	return pp;
 }
 
-static int vxlan_gro_complete(struct sk_buff *skb, int nhoff,
-			      struct udp_offload *uoff)
+static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff)
 {
 	udp_tunnel_gro_complete(skb, nhoff);
 
@@ -629,13 +627,6 @@ static void vxlan_notify_add_rx_port(struct vxlan_sock *vs)
 	struct net *net = sock_net(sk);
 	sa_family_t sa_family = vxlan_get_sk_family(vs);
 	__be16 port = inet_sk(sk)->inet_sport;
-	int err;
-
-	if (sa_family == AF_INET) {
-		err = udp_add_offload(net, &vs->udp_offloads);
-		if (err)
-			pr_warn("vxlan: udp_add_offload failed with status %d\n", err);
-	}
 
 	rcu_read_lock();
 	for_each_netdev_rcu(net, dev) {
@@ -662,9 +653,6 @@ static void vxlan_notify_del_rx_port(struct vxlan_sock *vs)
 							    port);
 	}
 	rcu_read_unlock();
-
-	if (sa_family == AF_INET)
-		udp_del_offload(&vs->udp_offloads);
 }
 
 /* Add new entry to forwarding table -- assumes lock held */
@@ -2752,21 +2740,19 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6,
 	atomic_set(&vs->refcnt, 1);
 	vs->flags = (flags & VXLAN_F_RCV_FLAGS);
 
-	/* Initialize the vxlan udp offloads structure */
-	vs->udp_offloads.port = port;
-	vs->udp_offloads.callbacks.gro_receive  = vxlan_gro_receive;
-	vs->udp_offloads.callbacks.gro_complete = vxlan_gro_complete;
-
 	spin_lock(&vn->sock_lock);
 	hlist_add_head_rcu(&vs->hlist, vs_head(net, port));
 	vxlan_notify_add_rx_port(vs);
 	spin_unlock(&vn->sock_lock);
 
 	/* Mark socket as an encapsulation socket. */
+	memset(&tunnel_cfg, 0, sizeof(tunnel_cfg));
 	tunnel_cfg.sk_user_data = vs;
 	tunnel_cfg.encap_type = 1;
 	tunnel_cfg.encap_rcv = vxlan_rcv;
 	tunnel_cfg.encap_destroy = NULL;
+	tunnel_cfg.gro_receive = vxlan_gro_receive;
+	tunnel_cfg.gro_complete = vxlan_gro_complete;
 
 	setup_udp_tunnel_sock(net, sock, &tunnel_cfg);
 

include/linux/netdevice.h

@@ -2159,23 +2159,6 @@ struct packet_offload {
 	struct list_head	 list;
 };
 
-struct udp_offload;
-
-struct udp_offload_callbacks {
-	struct sk_buff		**(*gro_receive)(struct sk_buff **head,
-						 struct sk_buff *skb,
-						 struct udp_offload *uoff);
-	int			(*gro_complete)(struct sk_buff *skb,
-						int nhoff,
-						struct udp_offload *uoff);
-};
-
-struct udp_offload {
-	__be16			 port;
-	u8			 ipproto;
-	struct udp_offload_callbacks callbacks;
-};
-
 /* often modified stats are per-CPU, other are shared (netdev->stats) */
 struct pcpu_sw_netstats {
 	u64     rx_packets;

include/linux/udp.h

@@ -71,6 +71,14 @@ struct udp_sock {
 	 */
 	int (*encap_rcv)(struct sock *sk, struct sk_buff *skb);
 	void (*encap_destroy)(struct sock *sk);
+
+	/* GRO functions for UDP socket */
+	struct sk_buff **	(*gro_receive)(struct sock *sk,
+					       struct sk_buff **head,
+					       struct sk_buff *skb);
+	int			(*gro_complete)(struct sock *sk,
+						struct sk_buff *skb,
+						int nhoff);
 };
 
 static inline struct udp_sock *udp_sk(const struct sock *sk)

include/net/protocol.h

@@ -107,9 +107,6 @@ int inet_del_offload(const struct net_offload *prot, unsigned char num);
 void inet_register_protosw(struct inet_protosw *p);
 void inet_unregister_protosw(struct inet_protosw *p);
 
-int  udp_add_offload(struct net *net, struct udp_offload *prot);
-void udp_del_offload(struct udp_offload *prot);
-
 #if IS_ENABLED(CONFIG_IPV6)
 int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char num);
 int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char num);

include/net/route.h

@@ -322,10 +322,11 @@ static inline struct rtable *ip_route_newports(struct flowi4 *fl4, struct rtable
 
 static inline int inet_iif(const struct sk_buff *skb)
 {
-	int iif = skb_rtable(skb)->rt_iif;
+	struct rtable *rt = skb_rtable(skb);
+
+	if (rt && rt->rt_iif)
+		return rt->rt_iif;
 
-	if (iif)
-		return iif;
 	return skb->skb_iif;
 }
 

include/net/udp.h

@@ -167,9 +167,12 @@ static inline void udp_csum_pull_header(struct sk_buff *skb)
 	UDP_SKB_CB(skb)->cscov -= sizeof(struct udphdr);
 }
 
+typedef struct sock *(*udp_lookup_t)(struct sk_buff *skb, __be16 sport,
+				     __be16 dport);
+
 struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
-				 struct udphdr *uh);
-int udp_gro_complete(struct sk_buff *skb, int nhoff);
+				 struct udphdr *uh, udp_lookup_t lookup);
+int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup);
 
 static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb)
 {
@@ -269,6 +272,8 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
 struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
 			       __be32 daddr, __be16 dport, int dif,
 			       struct udp_table *tbl, struct sk_buff *skb);
+struct sock *udp4_lib_lookup_skb(struct sk_buff *skb,
+				 __be16 sport, __be16 dport);
 struct sock *udp6_lib_lookup(struct net *net,
 			     const struct in6_addr *saddr, __be16 sport,
 			     const struct in6_addr *daddr, __be16 dport,
@@ -278,6 +283,8 @@ struct sock *__udp6_lib_lookup(struct net *net,
 			       const struct in6_addr *daddr, __be16 dport,
 			       int dif, struct udp_table *tbl,
 			       struct sk_buff *skb);
+struct sock *udp6_lib_lookup_skb(struct sk_buff *skb,
+				 __be16 sport, __be16 dport);
 
 /*
  * 	SNMP statistics for UDP and UDP-Lite

include/net/udp_tunnel.h

@@ -64,13 +64,20 @@ static inline int udp_sock_create(struct net *net,
 
 typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb);
 typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk);
+typedef struct sk_buff **(*udp_tunnel_gro_receive_t)(struct sock *sk,
+						     struct sk_buff **head,
+						     struct sk_buff *skb);
+typedef int (*udp_tunnel_gro_complete_t)(struct sock *sk, struct sk_buff *skb,
+					 int nhoff);
 
 struct udp_tunnel_sock_cfg {
 	void *sk_user_data;     /* user data used by encap_rcv call back */
 	/* Used for setting up udp_sock fields, see udp.h for details */
 	__u8  encap_type;
 	udp_tunnel_encap_rcv_t encap_rcv;
 	udp_tunnel_encap_destroy_t encap_destroy;
+	udp_tunnel_gro_receive_t gro_receive;
+	udp_tunnel_gro_complete_t gro_complete;
 };
 
 /* Setup the given (UDP) sock to receive UDP encapsulated packets */

include/net/vxlan.h

@@ -189,7 +189,6 @@ struct vxlan_sock {
 	struct rcu_head	  rcu;
 	struct hlist_head vni_list[VNI_HASH_SIZE];
 	atomic_t	  refcnt;
-	struct udp_offload udp_offloads;
 	u32		  flags;
 };