udp: Add GRO functions to UDP socket

This patch adds GRO functions (gro_receive and gro_complete) to UDP
sockets. udp_gro_receive is changed to perform socket lookup on a
packet. If a socket is found the related GRO functions are called.

This features obsoletes using UDP offload infrastructure for GRO
(udp_offload). This has the advantage of not being limited to provide
offload on a per port basis, GRO is now applied to whatever individual
UDP sockets are bound to.  This also allows the possbility of
"application defined GRO"-- that is we can attach something like
a BPF program to a UDP socket to perfrom GRO on an application
layer protocol.

Signed-off-by: Tom Herbert <tom@herbertland.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 54 insertions, 42 deletions

diff --git a/include/linux/udp.h b/include/linux/udp.h
index 32342754643a..d1fd8cd39478 100644
--- a/include/linux/udp.h
+++ b/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)
diff --git a/include/net/udp.h b/include/net/udp.h
index 3aa0b3ec1fb0..3c5a65e0946d 100644
--- a/include/net/udp.h
+++ b/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)
 {
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 0ed2dafb7cc4..65c3fd34b363 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -179,6 +179,7 @@ out_unlock:
 
         return segs;
 }
+EXPORT_SYMBOL(skb_udp_tunnel_segment);
 
 static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
                                          netdev_features_t features)
@@ -304,13 +305,13 @@ unlock:
 EXPORT_SYMBOL(udp_del_offload);
 
 struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
-                                 struct udphdr *uh)
+                                 struct udphdr *uh, udp_lookup_t lookup)
 {
-        struct udp_offload_priv *uo_priv;
         struct sk_buff *p, **pp = NULL;
         struct udphdr *uh2;
         unsigned int off = skb_gro_offset(skb);
         int flush = 1;
+        struct sock *sk;
 
         if (NAPI_GRO_CB(skb)->encap_mark ||
             (skb->ip_summed != CHECKSUM_PARTIAL &&
@@ -322,13 +323,11 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
         NAPI_GRO_CB(skb)->encap_mark = 1;
 
         rcu_read_lock();
-        uo_priv = rcu_dereference(udp_offload_base);
-        for (; uo_priv != NULL; uo_priv = rcu_dereference(uo_priv->next)) {
-                if (net_eq(read_pnet(&uo_priv->net), dev_net(skb->dev)) &&
-                    uo_priv->offload->port == uh->dest &&
-                    uo_priv->offload->callbacks.gro_receive)
-                        goto unflush;
-        }
+        sk = (*lookup)(skb, uh->source, uh->dest);
+
+        if (sk && udp_sk(sk)->gro_receive)
+                goto unflush;
+
         goto out_unlock;
 
 unflush:
@@ -352,9 +351,7 @@ unflush:
 
         skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */
         skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
-        NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto;
-        pp = uo_priv->offload->callbacks.gro_receive(head, skb,
-                                                     uo_priv->offload);
+        pp = udp_sk(sk)->gro_receive(sk, head, skb);
 
 out_unlock:
         rcu_read_unlock();
@@ -362,6 +359,7 @@ out:
         NAPI_GRO_CB(skb)->flush |= flush;
         return pp;
 }
+EXPORT_SYMBOL(udp_gro_receive);
 
 static struct sk_buff **udp4_gro_receive(struct sk_buff **head,
                                          struct sk_buff *skb)
@@ -383,39 +381,28 @@ static struct sk_buff **udp4_gro_receive(struct sk_buff **head,
                                              inet_gro_compute_pseudo);
 skip:
         NAPI_GRO_CB(skb)->is_ipv6 = 0;
-        return udp_gro_receive(head, skb, uh);
+        return udp_gro_receive(head, skb, uh, udp4_lib_lookup_skb);
 
 flush:
         NAPI_GRO_CB(skb)->flush = 1;
         return NULL;
 }
 
-int udp_gro_complete(struct sk_buff *skb, int nhoff)
+int udp_gro_complete(struct sk_buff *skb, int nhoff,
+                     udp_lookup_t lookup)
 {
-        struct udp_offload_priv *uo_priv;
         __be16 newlen = htons(skb->len - nhoff);
         struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
         int err = -ENOSYS;
+        struct sock *sk;
 
         uh->len = newlen;
 
         rcu_read_lock();
-
-        uo_priv = rcu_dereference(udp_offload_base);
-        for (; uo_priv != NULL; uo_priv = rcu_dereference(uo_priv->next)) {
-                if (net_eq(read_pnet(&uo_priv->net), dev_net(skb->dev)) &&
-                    uo_priv->offload->port == uh->dest &&
-                    uo_priv->offload->callbacks.gro_complete)
-                        break;
-        }
-
-        if (uo_priv) {
-                NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto;
-                err = uo_priv->offload->callbacks.gro_complete(skb,
-                                nhoff + sizeof(struct udphdr),
-                                uo_priv->offload);
-        }
-
+        sk = (*lookup)(skb, uh->source, uh->dest);
+        if (sk && udp_sk(sk)->gro_complete)
+                err = udp_sk(sk)->gro_complete(sk, skb,
+                                nhoff + sizeof(struct udphdr));
         rcu_read_unlock();
 
         if (skb->remcsum_offload)
@@ -426,6 +413,7 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff)
 
         return err;
 }
+EXPORT_SYMBOL(udp_gro_complete);
 
 static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
 {
@@ -440,7 +428,7 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
                 skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
         }
 
-        return udp_gro_complete(skb, nhoff);
+        return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb);
 }
 
 static const struct net_offload udpv4_offload = {
diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile
index 2fbd90bf8d33..5e9d6bf4aaca 100644
--- a/net/ipv6/Makefile
+++ b/net/ipv6/Makefile
@@ -8,9 +8,10 @@ ipv6-objs :=	af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \
                 addrlabel.o \
                 route.o ip6_fib.o ipv6_sockglue.o ndisc.o udp.o udplite.o \
                 raw.o icmp.o mcast.o reassembly.o tcp_ipv6.o ping.o \
-                exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o
+                exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o \
+                udp_offload.o
 
-ipv6-offload := ip6_offload.o tcpv6_offload.o udp_offload.o exthdrs_offload.o
+ipv6-offload := ip6_offload.o tcpv6_offload.o exthdrs_offload.o
 
 ipv6-$(CONFIG_SYSCTL) = sysctl_net_ipv6.o
 ipv6-$(CONFIG_IPV6_MROUTE) += ip6mr.o
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 2b78aad0d52f..bfa86f040c16 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -64,6 +64,8 @@
 #include <asm/uaccess.h>
 #include <linux/mroute6.h>
 
+#include "ip6_offload.h"
+
 MODULE_AUTHOR("Cast of dozens");
 MODULE_DESCRIPTION("IPv6 protocol stack for Linux");
 MODULE_LICENSE("GPL");
@@ -959,6 +961,10 @@ static int __init inet6_init(void)
         if (err)
                 goto udplitev6_fail;
 
+        err = udpv6_offload_init();
+        if (err)
+                goto udpv6_offload_fail;
+
         err = tcpv6_init();
         if (err)
                 goto tcpv6_fail;
@@ -988,6 +994,8 @@ pingv6_fail:
 ipv6_packet_fail:
         tcpv6_exit();
 tcpv6_fail:
+        udpv6_offload_exit();
+udpv6_offload_fail:
         udplitev6_exit();
 udplitev6_fail:
         udpv6_exit();
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 82e9f3076028..204af2219471 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -325,8 +325,6 @@ static int __init ipv6_offload_init(void)
 
         if (tcpv6_offload_init() < 0)
                 pr_crit("%s: Cannot add TCP protocol offload\n", __func__);
-        if (udp_offload_init() < 0)
-                pr_crit("%s: Cannot add UDP protocol offload\n", __func__);
         if (ipv6_exthdrs_offload_init() < 0)
                 pr_crit("%s: Cannot add EXTHDRS protocol offload\n", __func__);
 
diff --git a/net/ipv6/ip6_offload.h b/net/ipv6/ip6_offload.h
index 2e155c651b35..96b40e41ac53 100644
--- a/net/ipv6/ip6_offload.h
+++ b/net/ipv6/ip6_offload.h
@@ -12,7 +12,8 @@
 #define __ip6_offload_h
 
 int ipv6_exthdrs_offload_init(void);
-int udp_offload_init(void);
+int udpv6_offload_init(void);
+int udpv6_offload_exit(void);
 int tcpv6_offload_init(void);
 
 #endif
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 2b0fbe6929e8..5429f6bcf047 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -153,7 +153,7 @@ static struct sk_buff **udp6_gro_receive(struct sk_buff **head,
 
 skip:
         NAPI_GRO_CB(skb)->is_ipv6 = 1;
-        return udp_gro_receive(head, skb, uh);
+        return udp_gro_receive(head, skb, uh, udp6_lib_lookup_skb);
 
 flush:
         NAPI_GRO_CB(skb)->flush = 1;
@@ -173,7 +173,7 @@ static int udp6_gro_complete(struct sk_buff *skb, int nhoff)
                 skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
         }
 
-        return udp_gro_complete(skb, nhoff);
+        return udp_gro_complete(skb, nhoff, udp6_lib_lookup_skb);
 }
 
 static const struct net_offload udpv6_offload = {
@@ -184,7 +184,12 @@ static const struct net_offload udpv6_offload = {
         },
 };
 
-int __init udp_offload_init(void)
+int udpv6_offload_init(void)
 {
         return inet6_add_offload(&udpv6_offload, IPPROTO_UDP);
 }
+
+int udpv6_offload_exit(void)
+{
+        return inet6_del_offload(&udpv6_offload, IPPROTO_UDP);
+}