Commit a6024562 authored by Tom Herbert's avatar Tom Herbert Committed by David S. Miller
Browse files

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: default avatarTom Herbert <tom@herbertland.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 63058308

include/linux/udp.h

+8 −0
Original line number Diff line number Diff line
@@ -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/udp.h

+5 −2
Original line number Diff line number Diff line
@@ -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)

{

net/ipv4/udp_offload.c

+20 −32
Original line number Diff line number Diff line
@@ -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)

	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 = {

net/ipv6/Makefile

+3 −2
Original line number Diff line number Diff line
@@ -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

net/ipv6/af_inet6.c

+8 −0
Original line number Diff line number Diff line
@@ -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();

CRA Git | Maintained and supported by SUSTech CRA and CCSE