From ba4e58eca8aa9473b44fdfd312f26c4a2e7798b3 Mon Sep 17 00:00:00 2001
From: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Date: Mon, 27 Nov 2006 11:10:57 -0800
Subject: [NET]: Supporting UDP-Lite (RFC 3828) in Linux

This is a revision of the previously submitted patch, which alters
the way files are organized and compiled in the following manner:

	* UDP and UDP-Lite now use separate object files
	* source file dependencies resolved via header files
	  net/ipv{4,6}/udp_impl.h
	* order of inclusion files in udp.c/udplite.c adapted
	  accordingly

[NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828)

This patch adds support for UDP-Lite to the IPv4 stack, provided as an
extension to the existing UDPv4 code:
        * generic routines are all located in net/ipv4/udp.c
        * UDP-Lite specific routines are in net/ipv4/udplite.c
        * MIB/statistics support in /proc/net/snmp and /proc/net/udplite
        * shared API with extensions for partial checksum coverage

[NET/IPv6]: Extension for UDP-Lite over IPv6

It extends the existing UDPv6 code base with support for UDP-Lite
in the same manner as per UDPv4. In particular,
        * UDPv6 generic and shared code is in net/ipv6/udp.c
        * UDP-Litev6 specific extensions are in net/ipv6/udplite.c
        * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6
        * support for IPV6_ADDRFORM
        * aligned the coding style of protocol initialisation with af_inet6.c
        * made the error handling in udpv6_queue_rcv_skb consistent;
          to return `-1' on error on all error cases
        * consolidation of shared code

[NET]: UDP-Lite Documentation and basic XFRM/Netfilter support

The UDP-Lite patch further provides
        * API documentation for UDP-Lite
        * basic xfrm support
        * basic netfilter support for IPv4 and IPv6 (LOG target)

Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 518 +++++++++++++++++++++++++++++++++------------------------
 1 file changed, 300 insertions(+), 218 deletions(-)

(limited to 'net/ipv4/udp.c')

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 9e1bd374875e..98ba75096175 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -92,22 +92,16 @@
 #include <linux/timer.h>
 #include <linux/mm.h>
 #include <linux/inet.h>
-#include <linux/ipv6.h>
 #include <linux/netdevice.h>
-#include <net/snmp.h>
-#include <net/ip.h>
 #include <net/tcp_states.h>
-#include <net/protocol.h>
 #include <linux/skbuff.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
-#include <net/sock.h>
-#include <net/udp.h>
 #include <net/icmp.h>
 #include <net/route.h>
-#include <net/inet_common.h>
 #include <net/checksum.h>
 #include <net/xfrm.h>
+#include "udp_impl.h"
 
 /*
  *	Snmp MIB for the UDP layer
@@ -120,26 +114,30 @@ DEFINE_RWLOCK(udp_hash_lock);
 
 static int udp_port_rover;
 
-static inline int udp_lport_inuse(u16 num)
+static inline int __udp_lib_lport_inuse(__be16 num, struct hlist_head udptable[])
 {
 	struct sock *sk;
 	struct hlist_node *node;
 
-	sk_for_each(sk, node, &udp_hash[num & (UDP_HTABLE_SIZE - 1)])
+	sk_for_each(sk, node, &udptable[num & (UDP_HTABLE_SIZE - 1)])
 		if (inet_sk(sk)->num == num)
 			return 1;
 	return 0;
 }
 
 /**
- *  udp_get_port  -  common port lookup for IPv4 and IPv6
+ *  __udp_lib_get_port  -  UDP/-Lite port lookup for IPv4 and IPv6
  *
  *  @sk:          socket struct in question
  *  @snum:        port number to look up
+ *  @udptable:    hash list table, must be of UDP_HTABLE_SIZE
+ *  @port_rover:  pointer to record of last unallocated port
  *  @saddr_comp:  AF-dependent comparison of bound local IP addresses
  */
-int udp_get_port(struct sock *sk, unsigned short snum,
-		 int (*saddr_cmp)(const struct sock *sk1, const struct sock *sk2))
+int __udp_lib_get_port(struct sock *sk, unsigned short snum,
+		       struct hlist_head udptable[], int *port_rover,
+		       int (*saddr_comp)(const struct sock *sk1,
+					 const struct sock *sk2 )    )
 {
 	struct hlist_node *node;
 	struct hlist_head *head;
@@ -150,15 +148,15 @@ int udp_get_port(struct sock *sk, unsigned short snum,
 	if (snum == 0) {
 		int best_size_so_far, best, result, i;
 
-		if (udp_port_rover > sysctl_local_port_range[1] ||
-		    udp_port_rover < sysctl_local_port_range[0])
-			udp_port_rover = sysctl_local_port_range[0];
+		if (*port_rover > sysctl_local_port_range[1] ||
+		    *port_rover < sysctl_local_port_range[0])
+			*port_rover = sysctl_local_port_range[0];
 		best_size_so_far = 32767;
-		best = result = udp_port_rover;
+		best = result = *port_rover;
 		for (i = 0; i < UDP_HTABLE_SIZE; i++, result++) {
 			int size;
 
-			head = &udp_hash[result & (UDP_HTABLE_SIZE - 1)];
+			head = &udptable[result & (UDP_HTABLE_SIZE - 1)];
 			if (hlist_empty(head)) {
 				if (result > sysctl_local_port_range[1])
 					result = sysctl_local_port_range[0] +
@@ -179,15 +177,15 @@ int udp_get_port(struct sock *sk, unsigned short snum,
 				result = sysctl_local_port_range[0]
 					+ ((result - sysctl_local_port_range[0]) &
 					   (UDP_HTABLE_SIZE - 1));
-			if (!udp_lport_inuse(result))
+			if (! __udp_lib_lport_inuse(result, udptable))
 				break;
 		}
 		if (i >= (1 << 16) / UDP_HTABLE_SIZE)
 			goto fail;
 gotit:
-		udp_port_rover = snum = result;
+		*port_rover = snum = result;
 	} else {
-		head = &udp_hash[snum & (UDP_HTABLE_SIZE - 1)];
+		head = &udptable[snum & (UDP_HTABLE_SIZE - 1)];
 
 		sk_for_each(sk2, node, head)
 			if (inet_sk(sk2)->num == snum                        &&
@@ -195,12 +193,12 @@ gotit:
 			    (!sk2->sk_reuse        || !sk->sk_reuse)         &&
 			    (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if
 			     || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
-			    (*saddr_cmp)(sk, sk2)                              )
+			    (*saddr_comp)(sk, sk2)                             )
 				goto fail;
 	}
 	inet_sk(sk)->num = snum;
 	if (sk_unhashed(sk)) {
-		head = &udp_hash[snum & (UDP_HTABLE_SIZE - 1)];
+		head = &udptable[snum & (UDP_HTABLE_SIZE - 1)];
 		sk_add_node(sk, head);
 		sock_prot_inc_use(sk->sk_prot);
 	}
@@ -210,7 +208,13 @@ fail:
 	return error;
 }
 
-static inline int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
+__inline__ int udp_get_port(struct sock *sk, unsigned short snum,
+			int (*scmp)(const struct sock *, const struct sock *))
+{
+	return  __udp_lib_get_port(sk, snum, udp_hash, &udp_port_rover, scmp);
+}
+
+inline int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
 {
 	struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2);
 
@@ -224,34 +228,20 @@ static inline int udp_v4_get_port(struct sock *sk, unsigned short snum)
 	return udp_get_port(sk, snum, ipv4_rcv_saddr_equal);
 }
 
-
-static void udp_v4_hash(struct sock *sk)
-{
-	BUG();
-}
-
-static void udp_v4_unhash(struct sock *sk)
-{
-	write_lock_bh(&udp_hash_lock);
-	if (sk_del_node_init(sk)) {
-		inet_sk(sk)->num = 0;
-		sock_prot_dec_use(sk->sk_prot);
-	}
-	write_unlock_bh(&udp_hash_lock);
-}
-
 /* UDP is nearly always wildcards out the wazoo, it makes no sense to try
  * harder than this. -DaveM
  */
-static struct sock *udp_v4_lookup_longway(__be32 saddr, __be16 sport,
-					  __be32 daddr, __be16 dport, int dif)
+static struct sock *__udp4_lib_lookup(__be32 saddr, __be16 sport,
+				      __be32 daddr, __be16 dport,
+				      int dif, struct hlist_head udptable[])
 {
 	struct sock *sk, *result = NULL;
 	struct hlist_node *node;
 	unsigned short hnum = ntohs(dport);
 	int badness = -1;
 
-	sk_for_each(sk, node, &udp_hash[hnum & (UDP_HTABLE_SIZE - 1)]) {
+	read_lock(&udp_hash_lock);
+	sk_for_each(sk, node, &udptable[hnum & (UDP_HTABLE_SIZE - 1)]) {
 		struct inet_sock *inet = inet_sk(sk);
 
 		if (inet->num == hnum && !ipv6_only_sock(sk)) {
@@ -285,20 +275,10 @@ static struct sock *udp_v4_lookup_longway(__be32 saddr, __be16 sport,
 			}
 		}
 	}
-	return result;
-}
-
-static __inline__ struct sock *udp_v4_lookup(__be32 saddr, __be16 sport,
-					     __be32 daddr, __be16 dport, int dif)
-{
-	struct sock *sk;
-
-	read_lock(&udp_hash_lock);
-	sk = udp_v4_lookup_longway(saddr, sport, daddr, dport, dif);
-	if (sk)
-		sock_hold(sk);
+	if (result)
+		sock_hold(result);
 	read_unlock(&udp_hash_lock);
-	return sk;
+	return result;
 }
 
 static inline struct sock *udp_v4_mcast_next(struct sock *sk,
@@ -340,7 +320,7 @@ found:
  * to find the appropriate port.
  */
 
-void udp_err(struct sk_buff *skb, u32 info)
+void __udp4_lib_err(struct sk_buff *skb, u32 info, struct hlist_head udptable[])
 {
 	struct inet_sock *inet;
 	struct iphdr *iph = (struct iphdr*)skb->data;
@@ -351,7 +331,8 @@ void udp_err(struct sk_buff *skb, u32 info)
 	int harderr;
 	int err;
 
-	sk = udp_v4_lookup(iph->daddr, uh->dest, iph->saddr, uh->source, skb->dev->ifindex);
+	sk = __udp4_lib_lookup(iph->daddr, uh->dest, iph->saddr, uh->source,
+			       skb->dev->ifindex, udptable		    );
 	if (sk == NULL) {
 		ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
     	  	return;	/* No socket for error */
@@ -405,6 +386,11 @@ out:
 	sock_put(sk);
 }
 
+__inline__ void udp_err(struct sk_buff *skb, u32 info)
+{
+	return __udp4_lib_err(skb, info, udp_hash);
+}
+
 /*
  * Throw away all pending data and cancel the corking. Socket is locked.
  */
@@ -419,16 +405,56 @@ static void udp_flush_pending_frames(struct sock *sk)
 	}
 }
 
+/**
+ * 	udp4_hwcsum_outgoing  -  handle outgoing HW checksumming
+ * 	@sk: 	socket we are sending on
+ * 	@skb: 	sk_buff containing the filled-in UDP header
+ * 	        (checksum field must be zeroed out)
+ */
+static void udp4_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
+				 __be32 src, __be32 dst, int len      )
+{
+	unsigned int csum = 0, offset;
+	struct udphdr *uh = skb->h.uh;
+
+	if (skb_queue_len(&sk->sk_write_queue) == 1) {
+		/*
+		 * Only one fragment on the socket.
+		 */
+		skb->csum = offsetof(struct udphdr, check);
+		uh->check = ~csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, 0);
+	} else {
+		/*
+		 * HW-checksum won't work as there are two or more
+		 * fragments on the socket so that all csums of sk_buffs
+		 * should be together
+		 */
+		offset = skb->h.raw - skb->data;
+		skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
+
+		skb->ip_summed = CHECKSUM_NONE;
+
+		skb_queue_walk(&sk->sk_write_queue, skb) {
+			csum = csum_add(csum, skb->csum);
+		}
+
+		uh->check = csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, csum);
+		if (uh->check == 0)
+			uh->check = -1;
+	}
+}
+
 /*
  * Push out all pending data as one UDP datagram. Socket is locked.
  */
-static int udp_push_pending_frames(struct sock *sk, struct udp_sock *up)
+int udp_push_pending_frames(struct sock *sk, struct udp_sock *up)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct flowi *fl = &inet->cork.fl;
 	struct sk_buff *skb;
 	struct udphdr *uh;
 	int err = 0;
+	u32 csum = 0;
 
 	/* Grab the skbuff where UDP header space exists. */
 	if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
@@ -443,52 +469,28 @@ static int udp_push_pending_frames(struct sock *sk, struct udp_sock *up)
 	uh->len = htons(up->len);
 	uh->check = 0;
 
-	if (sk->sk_no_check == UDP_CSUM_NOXMIT) {
+	if (up->pcflag)  				 /*     UDP-Lite      */
+		csum  = udplite_csum_outgoing(sk, skb);
+
+	else if (sk->sk_no_check == UDP_CSUM_NOXMIT) {   /* UDP csum disabled */
+
 		skb->ip_summed = CHECKSUM_NONE;
 		goto send;
-	}
 
-	if (skb_queue_len(&sk->sk_write_queue) == 1) {
-		/*
-		 * Only one fragment on the socket.
-		 */
-		if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			skb->csum = offsetof(struct udphdr, check);
-			uh->check = ~csum_tcpudp_magic(fl->fl4_src, fl->fl4_dst,
-					up->len, IPPROTO_UDP, 0);
-		} else {
-			skb->csum = csum_partial((char *)uh,
-					sizeof(struct udphdr), skb->csum);
-			uh->check = csum_tcpudp_magic(fl->fl4_src, fl->fl4_dst,
-					up->len, IPPROTO_UDP, skb->csum);
-			if (uh->check == 0)
-				uh->check = -1;
-		}
-	} else {
-		unsigned int csum = 0;
-		/*
-		 * HW-checksum won't work as there are two or more 
-		 * fragments on the socket so that all csums of sk_buffs
-		 * should be together.
-		 */
-		if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			int offset = (unsigned char *)uh - skb->data;
-			skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
+	} else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */
 
-			skb->ip_summed = CHECKSUM_NONE;
-		} else {
-			skb->csum = csum_partial((char *)uh,
-					sizeof(struct udphdr), skb->csum);
-		}
+		udp4_hwcsum_outgoing(sk, skb, fl->fl4_src,fl->fl4_dst, up->len);
+		goto send;
+
+	} else						 /*   `normal' UDP    */
+		csum = udp_csum_outgoing(sk, skb);
+
+	/* add protocol-dependent pseudo-header */
+	uh->check = csum_tcpudp_magic(fl->fl4_src, fl->fl4_dst, up->len,
+				      sk->sk_protocol, csum             );
+	if (uh->check == 0)
+		uh->check = -1;
 
-		skb_queue_walk(&sk->sk_write_queue, skb) {
-			csum = csum_add(csum, skb->csum);
-		}
-		uh->check = csum_tcpudp_magic(fl->fl4_src, fl->fl4_dst,
-				up->len, IPPROTO_UDP, csum);
-		if (uh->check == 0)
-			uh->check = -1;
-	}
 send:
 	err = ip_push_pending_frames(sk);
 out:
@@ -497,12 +499,6 @@ out:
 	return err;
 }
 
-
-static unsigned short udp_check(struct udphdr *uh, int len, __be32 saddr, __be32 daddr, unsigned long base)
-{
-	return(csum_tcpudp_magic(saddr, daddr, len, IPPROTO_UDP, base));
-}
-
 int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		size_t len)
 {
@@ -516,8 +512,9 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	__be32 daddr, faddr, saddr;
 	__be16 dport;
 	u8  tos;
-	int err;
+	int err, is_udplite = up->pcflag;
 	int corkreq = up->corkflag || msg->msg_flags&MSG_MORE;
+	int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
 
 	if (len > 0xFFFF)
 		return -EMSGSIZE;
@@ -622,7 +619,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 					      { .daddr = faddr,
 						.saddr = saddr,
 						.tos = tos } },
-				    .proto = IPPROTO_UDP,
+				    .proto = sk->sk_protocol,
 				    .uli_u = { .ports =
 					       { .sport = inet->sport,
 						 .dport = dport } } };
@@ -668,8 +665,9 @@ back_from_confirm:
 
 do_append_data:
 	up->len += ulen;
-	err = ip_append_data(sk, ip_generic_getfrag, msg->msg_iov, ulen, 
-			sizeof(struct udphdr), &ipc, rt, 
+	getfrag  =  is_udplite ?  udplite_getfrag : ip_generic_getfrag;
+	err = ip_append_data(sk, getfrag, msg->msg_iov, ulen,
+			sizeof(struct udphdr), &ipc, rt,
 			corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
 	if (err)
 		udp_flush_pending_frames(sk);
@@ -684,7 +682,7 @@ out:
 	if (free)
 		kfree(ipc.opt);
 	if (!err) {
-		UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS);
+		UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite);
 		return len;
 	}
 	/*
@@ -695,7 +693,7 @@ out:
 	 * seems like overkill.
 	 */
 	if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
-		UDP_INC_STATS_USER(UDP_MIB_SNDBUFERRORS);
+		UDP_INC_STATS_USER(UDP_MIB_SNDBUFERRORS, is_udplite);
 	}
 	return err;
 
@@ -707,8 +705,8 @@ do_confirm:
 	goto out;
 }
 
-static int udp_sendpage(struct sock *sk, struct page *page, int offset,
-			size_t size, int flags)
+int udp_sendpage(struct sock *sk, struct page *page, int offset,
+		 size_t size, int flags)
 {
 	struct udp_sock *up = udp_sk(sk);
 	int ret;
@@ -795,29 +793,18 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 	return(0);
 }
 
-static __inline__ int __udp_checksum_complete(struct sk_buff *skb)
-{
-	return __skb_checksum_complete(skb);
-}
-
-static __inline__ int udp_checksum_complete(struct sk_buff *skb)
-{
-	return skb->ip_summed != CHECKSUM_UNNECESSARY &&
-		__udp_checksum_complete(skb);
-}
-
 /*
  * 	This should be easy, if there is something there we
  * 	return it, otherwise we block.
  */
 
-static int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
-		       size_t len, int noblock, int flags, int *addr_len)
+int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+	        size_t len, int noblock, int flags, int *addr_len)
 {
 	struct inet_sock *inet = inet_sk(sk);
   	struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
   	struct sk_buff *skb;
-  	int copied, err;
+	int copied, err, copy_only, is_udplite = IS_UDPLITE(sk);
 
 	/*
 	 *	Check any passed addresses
@@ -839,15 +826,25 @@ try_again:
 		msg->msg_flags |= MSG_TRUNC;
 	}
 
-	if (skb->ip_summed==CHECKSUM_UNNECESSARY) {
-		err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov,
-					      copied);
-	} else if (msg->msg_flags&MSG_TRUNC) {
-		if (__udp_checksum_complete(skb))
+	/*
+	 * 	Decide whether to checksum and/or copy data.
+	 *
+	 * 	UDP:      checksum may have been computed in HW,
+	 * 	          (re-)compute it if message is truncated.
+	 * 	UDP-Lite: always needs to checksum, no HW support.
+	 */
+	copy_only = (skb->ip_summed==CHECKSUM_UNNECESSARY);
+
+	if (is_udplite  ||  (!copy_only  &&  msg->msg_flags&MSG_TRUNC)) {
+		if (__udp_lib_checksum_complete(skb))
 			goto csum_copy_err;
-		err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov,
-					      copied);
-	} else {
+		copy_only = 1;
+	}
+
+	if (copy_only)
+		err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr),
+					      msg->msg_iov, copied       );
+	else {
 		err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov);
 
 		if (err == -EINVAL)
@@ -880,7 +877,7 @@ out:
   	return err;
 
 csum_copy_err:
-	UDP_INC_STATS_BH(UDP_MIB_INERRORS);
+	UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite);
 
 	skb_kill_datagram(sk, skb, flags);
 
@@ -912,11 +909,6 @@ int udp_disconnect(struct sock *sk, int flags)
 	return 0;
 }
 
-static void udp_close(struct sock *sk, long timeout)
-{
-	sk_common_release(sk);
-}
-
 /* return:
  * 	1  if the the UDP system should process it
  *	0  if we should drop this packet
@@ -1022,7 +1014,7 @@ static int udp_encap_rcv(struct sock * sk, struct sk_buff *skb)
  * Note that in the success and error cases, the skb is assumed to
  * have either been requeued or freed.
  */
-static int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
+int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
 {
 	struct udp_sock *up = udp_sk(sk);
 	int rc;
@@ -1030,10 +1022,8 @@ static int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
 	/*
 	 *	Charge it to the socket, dropping if the queue is full.
 	 */
-	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) {
-		kfree_skb(skb);
-		return -1;
-	}
+	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
+		goto drop;
 	nf_reset(skb);
 
 	if (up->encap_type) {
@@ -1057,31 +1047,68 @@ static int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
 		if (ret < 0) {
 			/* process the ESP packet */
 			ret = xfrm4_rcv_encap(skb, up->encap_type);
-			UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS);
+			UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS, up->pcflag);
 			return -ret;
 		}
 		/* FALLTHROUGH -- it's a UDP Packet */
 	}
 
-	if (sk->sk_filter && skb->ip_summed != CHECKSUM_UNNECESSARY) {
-		if (__udp_checksum_complete(skb)) {
-			UDP_INC_STATS_BH(UDP_MIB_INERRORS);
-			kfree_skb(skb);
-			return -1;
+	/*
+	 * 	UDP-Lite specific tests, ignored on UDP sockets
+	 */
+	if ((up->pcflag & UDPLITE_RECV_CC)  &&  UDP_SKB_CB(skb)->partial_cov) {
+
+		/*
+		 * MIB statistics other than incrementing the error count are
+		 * disabled for the following two types of errors: these depend
+		 * on the application settings, not on the functioning of the
+		 * protocol stack as such.
+		 *
+		 * RFC 3828 here recommends (sec 3.3): "There should also be a
+		 * way ... to ... at least let the receiving application block
+		 * delivery of packets with coverage values less than a value
+		 * provided by the application."
+		 */
+		if (up->pcrlen == 0) {          /* full coverage was set  */
+			LIMIT_NETDEBUG(KERN_WARNING "UDPLITE: partial coverage "
+				"%d while full coverage %d requested\n",
+				UDP_SKB_CB(skb)->cscov, skb->len);
+			goto drop;
 		}
+		/* The next case involves violating the min. coverage requested
+		 * by the receiver. This is subtle: if receiver wants x and x is
+		 * greater than the buffersize/MTU then receiver will complain
+		 * that it wants x while sender emits packets of smaller size y.
+		 * Therefore the above ...()->partial_cov statement is essential.
+		 */
+		if (UDP_SKB_CB(skb)->cscov  <  up->pcrlen) {
+			LIMIT_NETDEBUG(KERN_WARNING
+				"UDPLITE: coverage %d too small, need min %d\n",
+				UDP_SKB_CB(skb)->cscov, up->pcrlen);
+			goto drop;
+		}
+	}
+
+	if (sk->sk_filter && skb->ip_summed != CHECKSUM_UNNECESSARY) {
+		if (__udp_lib_checksum_complete(skb))
+			goto drop;
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 	}
 
 	if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) {
 		/* Note that an ENOMEM error is charged twice */
 		if (rc == -ENOMEM)
-			UDP_INC_STATS_BH(UDP_MIB_RCVBUFERRORS);
-		UDP_INC_STATS_BH(UDP_MIB_INERRORS);
-		kfree_skb(skb);
-		return -1;
+			UDP_INC_STATS_BH(UDP_MIB_RCVBUFERRORS, up->pcflag);
+		goto drop;
 	}
-	UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS);
+
+	UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS, up->pcflag);
 	return 0;
+
+drop:
+	UDP_INC_STATS_BH(UDP_MIB_INERRORS, up->pcflag);
+	kfree_skb(skb);
+	return -1;
 }
 
 /*
@@ -1090,14 +1117,16 @@ static int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
  *	Note: called only from the BH handler context,
  *	so we don't need to lock the hashes.
  */
-static int udp_v4_mcast_deliver(struct sk_buff *skb, struct udphdr *uh,
-				 __be32 saddr, __be32 daddr)
+static int __udp4_lib_mcast_deliver(struct sk_buff *skb,
+				    struct udphdr  *uh,
+				    __be32 saddr, __be32 daddr,
+				    struct hlist_head udptable[])
 {
 	struct sock *sk;
 	int dif;
 
 	read_lock(&udp_hash_lock);
-	sk = sk_head(&udp_hash[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]);
+	sk = sk_head(&udptable[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]);
 	dif = skb->dev->ifindex;
 	sk = udp_v4_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif);
 	if (sk) {
@@ -1131,65 +1160,75 @@ static int udp_v4_mcast_deliver(struct sk_buff *skb, struct udphdr *uh,
  * Otherwise, csum completion requires chacksumming packet body,
  * including udp header and folding it to skb->csum.
  */
-static void udp_checksum_init(struct sk_buff *skb, struct udphdr *uh,
-			     unsigned short ulen, __be32 saddr, __be32 daddr)
+static inline void udp4_csum_init(struct sk_buff *skb, struct udphdr *uh)
 {
 	if (uh->check == 0) {
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 	} else if (skb->ip_summed == CHECKSUM_COMPLETE) {
-		if (!udp_check(uh, ulen, saddr, daddr, skb->csum))
+	       if (!csum_tcpudp_magic(skb->nh.iph->saddr, skb->nh.iph->daddr,
+				      skb->len, IPPROTO_UDP, skb->csum       ))
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 	}
 	if (skb->ip_summed != CHECKSUM_UNNECESSARY)
-		skb->csum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0);
+		skb->csum = csum_tcpudp_nofold(skb->nh.iph->saddr,
+					       skb->nh.iph->daddr,
+					       skb->len, IPPROTO_UDP, 0);
 	/* Probably, we should checksum udp header (it should be in cache
 	 * in any case) and data in tiny packets (< rx copybreak).
 	 */
+
+	/* UDP = UDP-Lite with a non-partial checksum coverage */
+	UDP_SKB_CB(skb)->partial_cov = 0;
 }
 
 /*
  *	All we need to do is get the socket, and then do a checksum. 
  */
  
-int udp_rcv(struct sk_buff *skb)
+int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
+		   int is_udplite)
 {
   	struct sock *sk;
-  	struct udphdr *uh;
+  	struct udphdr *uh = skb->h.uh;
 	unsigned short ulen;
 	struct rtable *rt = (struct rtable*)skb->dst;
 	__be32 saddr = skb->nh.iph->saddr;
 	__be32 daddr = skb->nh.iph->daddr;
-	int len = skb->len;
 
 	/*
-	 *	Validate the packet and the UDP length.
+	 *  Validate the packet.
 	 */
 	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
-		goto no_header;
-
-	uh = skb->h.uh;
+		goto drop;		/* No space for header. */
 
 	ulen = ntohs(uh->len);
-
-	if (ulen > len || ulen < sizeof(*uh))
+	if (ulen > skb->len)
 		goto short_packet;
 
-	if (pskb_trim_rcsum(skb, ulen))
-		goto short_packet;
+	if(! is_udplite ) {		/* UDP validates ulen. */
+
+		if (ulen < sizeof(*uh) || pskb_trim_rcsum(skb, ulen))
+			goto short_packet;
 
-	udp_checksum_init(skb, uh, ulen, saddr, daddr);
+		udp4_csum_init(skb, uh);
+
+	} else 	{			/* UDP-Lite validates cscov. */
+		if (udplite4_csum_init(skb, uh))
+			goto csum_error;
+	}
 
 	if(rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
-		return udp_v4_mcast_deliver(skb, uh, saddr, daddr);
+		return __udp4_lib_mcast_deliver(skb, uh, saddr, daddr, udptable);
 
-	sk = udp_v4_lookup(saddr, uh->source, daddr, uh->dest, skb->dev->ifindex);
+	sk = __udp4_lib_lookup(saddr, uh->source, daddr, uh->dest,
+			       skb->dev->ifindex, udptable        );
 
 	if (sk != NULL) {
 		int ret = udp_queue_rcv_skb(sk, skb);
 		sock_put(sk);
 
 		/* a return value > 0 means to resubmit the input, but
-		 * it it wants the return to be -protocol, or 0
+		 * it wants the return to be -protocol, or 0
 		 */
 		if (ret > 0)
 			return -ret;
@@ -1201,10 +1240,10 @@ int udp_rcv(struct sk_buff *skb)
 	nf_reset(skb);
 
 	/* No socket. Drop packet silently, if checksum is wrong */
-	if (udp_checksum_complete(skb))
+	if (udp_lib_checksum_complete(skb))
 		goto csum_error;
 
-	UDP_INC_STATS_BH(UDP_MIB_NOPORTS);
+	UDP_INC_STATS_BH(UDP_MIB_NOPORTS, is_udplite);
 	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
 
 	/*
@@ -1215,36 +1254,40 @@ int udp_rcv(struct sk_buff *skb)
 	return(0);
 
 short_packet:
-	LIMIT_NETDEBUG(KERN_DEBUG "UDP: short packet: From %u.%u.%u.%u:%u %d/%d to %u.%u.%u.%u:%u\n",
+	LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: short packet: From %u.%u.%u.%u:%u %d/%d to %u.%u.%u.%u:%u\n",
+		       is_udplite? "-Lite" : "",
 		       NIPQUAD(saddr),
 		       ntohs(uh->source),
 		       ulen,
-		       len,
+		       skb->len,
 		       NIPQUAD(daddr),
 		       ntohs(uh->dest));
-no_header:
-	UDP_INC_STATS_BH(UDP_MIB_INERRORS);
-	kfree_skb(skb);
-	return(0);
+	goto drop;
 
 csum_error:
 	/* 
 	 * RFC1122: OK.  Discards the bad packet silently (as far as 
 	 * the network is concerned, anyway) as per 4.1.3.4 (MUST). 
 	 */
-	LIMIT_NETDEBUG(KERN_DEBUG "UDP: bad checksum. From %d.%d.%d.%d:%d to %d.%d.%d.%d:%d ulen %d\n",
+	LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: bad checksum. From %d.%d.%d.%d:%d to %d.%d.%d.%d:%d ulen %d\n",
+		       is_udplite? "-Lite" : "",
 		       NIPQUAD(saddr),
 		       ntohs(uh->source),
 		       NIPQUAD(daddr),
 		       ntohs(uh->dest),
 		       ulen);
 drop:
-	UDP_INC_STATS_BH(UDP_MIB_INERRORS);
+	UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite);
 	kfree_skb(skb);
 	return(0);
 }
 
-static int udp_destroy_sock(struct sock *sk)
+__inline__ int udp_rcv(struct sk_buff *skb)
+{
+	return __udp4_lib_rcv(skb, udp_hash, 0);
+}
+
+int udp_destroy_sock(struct sock *sk)
 {
 	lock_sock(sk);
 	udp_flush_pending_frames(sk);
@@ -1293,6 +1336,32 @@ static int do_udp_setsockopt(struct sock *sk, int level, int optname,
 		}
 		break;
 
+	/*
+	 * 	UDP-Lite's partial checksum coverage (RFC 3828).
+	 */
+	/* The sender sets actual checksum coverage length via this option.
+	 * The case coverage > packet length is handled by send module. */
+	case UDPLITE_SEND_CSCOV:
+		if (!up->pcflag)         /* Disable the option on UDP sockets */
+			return -ENOPROTOOPT;
+		if (val != 0 && val < 8) /* Illegal coverage: use default (8) */
+			val = 8;
+		up->pcslen = val;
+		up->pcflag |= UDPLITE_SEND_CC;
+		break;
+
+        /* The receiver specifies a minimum checksum coverage value. To make
+         * sense, this should be set to at least 8 (as done below). If zero is
+	 * used, this again means full checksum coverage.                     */
+	case UDPLITE_RECV_CSCOV:
+		if (!up->pcflag)         /* Disable the option on UDP sockets */
+			return -ENOPROTOOPT;
+		if (val != 0 && val < 8) /* Avoid silly minimal values.       */
+			val = 8;
+		up->pcrlen = val;
+		up->pcflag |= UDPLITE_RECV_CC;
+		break;
+
 	default:
 		err = -ENOPROTOOPT;
 		break;
@@ -1301,21 +1370,21 @@ static int do_udp_setsockopt(struct sock *sk, int level, int optname,
 	return err;
 }
 
-static int udp_setsockopt(struct sock *sk, int level, int optname,
-			  char __user *optval, int optlen)
+int udp_setsockopt(struct sock *sk, int level, int optname,
+		   char __user *optval, int optlen)
 {
-	if (level != SOL_UDP)
-		return ip_setsockopt(sk, level, optname, optval, optlen);
-	return do_udp_setsockopt(sk, level, optname, optval, optlen);
+	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
+		return do_udp_setsockopt(sk, level, optname, optval, optlen);
+	return ip_setsockopt(sk, level, optname, optval, optlen);
 }
 
 #ifdef CONFIG_COMPAT
-static int compat_udp_setsockopt(struct sock *sk, int level, int optname,
-				 char __user *optval, int optlen)
+int compat_udp_setsockopt(struct sock *sk, int level, int optname,
+			  char __user *optval, int optlen)
 {
-	if (level != SOL_UDP)
-		return compat_ip_setsockopt(sk, level, optname, optval, optlen);
-	return do_udp_setsockopt(sk, level, optname, optval, optlen);
+	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
+		return do_udp_setsockopt(sk, level, optname, optval, optlen);
+	return compat_ip_setsockopt(sk, level, optname, optval, optlen);
 }
 #endif
 
@@ -1342,6 +1411,16 @@ static int do_udp_getsockopt(struct sock *sk, int level, int optname,
 		val = up->encap_type;
 		break;
 
+	/* The following two cannot be changed on UDP sockets, the return is
+	 * always 0 (which corresponds to the full checksum coverage of UDP). */
+	case UDPLITE_SEND_CSCOV:
+		val = up->pcslen;
+		break;
+
+	case UDPLITE_RECV_CSCOV:
+		val = up->pcrlen;
+		break;
+
 	default:
 		return -ENOPROTOOPT;
 	};
@@ -1353,21 +1432,21 @@ static int do_udp_getsockopt(struct sock *sk, int level, int optname,
   	return 0;
 }
 
-static int udp_getsockopt(struct sock *sk, int level, int optname,
-			  char __user *optval, int __user *optlen)
+int udp_getsockopt(struct sock *sk, int level, int optname,
+		   char __user *optval, int __user *optlen)
 {
-	if (level != SOL_UDP)
-		return ip_getsockopt(sk, level, optname, optval, optlen);
-	return do_udp_getsockopt(sk, level, optname, optval, optlen);
+	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
+		return do_udp_getsockopt(sk, level, optname, optval, optlen);
+	return ip_getsockopt(sk, level, optname, optval, optlen);
 }
 
 #ifdef CONFIG_COMPAT
-static int compat_udp_getsockopt(struct sock *sk, int level, int optname,
+int compat_udp_getsockopt(struct sock *sk, int level, int optname,
 				 char __user *optval, int __user *optlen)
 {
-	if (level != SOL_UDP)
-		return compat_ip_getsockopt(sk, level, optname, optval, optlen);
-	return do_udp_getsockopt(sk, level, optname, optval, optlen);
+	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
+		return do_udp_getsockopt(sk, level, optname, optval, optlen);
+	return compat_ip_getsockopt(sk, level, optname, optval, optlen);
 }
 #endif
 /**
@@ -1387,7 +1466,8 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
 {
 	unsigned int mask = datagram_poll(file, sock, wait);
 	struct sock *sk = sock->sk;
-	
+	int 	is_lite = IS_UDPLITE(sk);
+
 	/* Check for false positives due to checksum errors */
 	if ( (mask & POLLRDNORM) &&
 	     !(file->f_flags & O_NONBLOCK) &&
@@ -1397,8 +1477,8 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
 
 		spin_lock_bh(&rcvq->lock);
 		while ((skb = skb_peek(rcvq)) != NULL) {
-			if (udp_checksum_complete(skb)) {
-				UDP_INC_STATS_BH(UDP_MIB_INERRORS);
+			if (udp_lib_checksum_complete(skb)) {
+				UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_lite);
 				__skb_unlink(skb, rcvq);
 				kfree_skb(skb);
 			} else {
@@ -1420,7 +1500,7 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
 struct proto udp_prot = {
  	.name		   = "UDP",
 	.owner		   = THIS_MODULE,
-	.close		   = udp_close,
+	.close		   = udp_lib_close,
 	.connect	   = ip4_datagram_connect,
 	.disconnect	   = udp_disconnect,
 	.ioctl		   = udp_ioctl,
@@ -1431,8 +1511,8 @@ struct proto udp_prot = {
 	.recvmsg	   = udp_recvmsg,
 	.sendpage	   = udp_sendpage,
 	.backlog_rcv	   = udp_queue_rcv_skb,
-	.hash		   = udp_v4_hash,
-	.unhash		   = udp_v4_unhash,
+	.hash		   = udp_lib_hash,
+	.unhash		   = udp_lib_unhash,
 	.get_port	   = udp_v4_get_port,
 	.obj_size	   = sizeof(struct udp_sock),
 #ifdef CONFIG_COMPAT
@@ -1451,7 +1531,7 @@ static struct sock *udp_get_first(struct seq_file *seq)
 
 	for (state->bucket = 0; state->bucket < UDP_HTABLE_SIZE; ++state->bucket) {
 		struct hlist_node *node;
-		sk_for_each(sk, node, &udp_hash[state->bucket]) {
+		sk_for_each(sk, node, state->hashtable + state->bucket) {
 			if (sk->sk_family == state->family)
 				goto found;
 		}
@@ -1472,7 +1552,7 @@ try_again:
 	} while (sk && sk->sk_family != state->family);
 
 	if (!sk && ++state->bucket < UDP_HTABLE_SIZE) {
-		sk = sk_head(&udp_hash[state->bucket]);
+		sk = sk_head(state->hashtable + state->bucket);
 		goto try_again;
 	}
 	return sk;
@@ -1522,6 +1602,7 @@ static int udp_seq_open(struct inode *inode, struct file *file)
 	if (!s)
 		goto out;
 	s->family		= afinfo->family;
+	s->hashtable		= afinfo->hashtable;
 	s->seq_ops.start	= udp_seq_start;
 	s->seq_ops.next		= udp_seq_next;
 	s->seq_ops.show		= afinfo->seq_show;
@@ -1588,7 +1669,7 @@ static void udp4_format_sock(struct sock *sp, char *tmpbuf, int bucket)
 		atomic_read(&sp->sk_refcnt), sp);
 }
 
-static int udp4_seq_show(struct seq_file *seq, void *v)
+int udp4_seq_show(struct seq_file *seq, void *v)
 {
 	if (v == SEQ_START_TOKEN)
 		seq_printf(seq, "%-127s\n",
@@ -1611,6 +1692,7 @@ static struct udp_seq_afinfo udp4_seq_afinfo = {
 	.owner		= THIS_MODULE,
 	.name		= "udp",
 	.family		= AF_INET,
+	.hashtable	= udp_hash,
 	.seq_show	= udp4_seq_show,
 	.seq_fops	= &udp4_seq_fops,
 };
-- 
cgit v1.2.3


From 6b11687ef003ed595033da89643c8995676f929d Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 14 Nov 2006 21:28:24 -0800
Subject: [NET]: Annotate csum_tcpudp_magic() callers in net/*

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 6 +++---
 net/ipv4/udp.c    | 3 ++-
 2 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'net/ipv4/udp.c')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 363960872de0..826aaecdb994 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -807,9 +807,9 @@ static inline void tcp_update_wl(struct tcp_sock *tp, u32 ack, u32 seq)
 /*
  * Calculate(/check) TCP checksum
  */
-static inline u16 tcp_v4_check(struct tcphdr *th, int len,
-			       unsigned long saddr, unsigned long daddr, 
-			       unsigned long base)
+static inline __sum16 tcp_v4_check(struct tcphdr *th, int len,
+			       __be32 saddr, __be32 daddr,
+			       __wsum base)
 {
 	return csum_tcpudp_magic(saddr,daddr,len,IPPROTO_TCP,base);
 }
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 98ba75096175..f9c4ed7207bb 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -414,8 +414,9 @@ static void udp_flush_pending_frames(struct sock *sk)
 static void udp4_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
 				 __be32 src, __be32 dst, int len      )
 {
-	unsigned int csum = 0, offset;
+	unsigned int offset;
 	struct udphdr *uh = skb->h.uh;
+	__wsum csum = 0;
 
 	if (skb_queue_len(&sk->sk_write_queue) == 1) {
 		/*
-- 
cgit v1.2.3


From f6ab028804bdc580fe0915494dbf31f5ea473ca7 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 16 Nov 2006 02:36:50 -0800
Subject: [NET]: Make mangling a checksum (0 -> 0xffff on the wire) explicit.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/checksum.h                | 1 +
 net/ipv4/ipvs/ip_vs_proto_udp.c       | 6 +++---
 net/ipv4/netfilter/ip_nat_helper.c    | 2 +-
 net/ipv4/netfilter/ip_nat_proto_udp.c | 2 +-
 net/ipv4/udp.c                        | 4 ++--
 net/ipv6/raw.c                        | 4 ++--
 net/ipv6/udp.c                        | 2 +-
 7 files changed, 11 insertions(+), 10 deletions(-)

(limited to 'net/ipv4/udp.c')

diff --git a/include/net/checksum.h b/include/net/checksum.h
index 2b3c8dc6c11d..124246172a88 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -92,4 +92,5 @@ static inline __wsum csum_unfold(__sum16 n)
 	return (__force __wsum)n;
 }
 
+#define CSUM_MANGLED_0 ((__force __sum16)0xffff)
 #endif
diff --git a/net/ipv4/ipvs/ip_vs_proto_udp.c b/net/ipv4/ipvs/ip_vs_proto_udp.c
index 261581e6a814..3647397e416d 100644
--- a/net/ipv4/ipvs/ip_vs_proto_udp.c
+++ b/net/ipv4/ipvs/ip_vs_proto_udp.c
@@ -125,7 +125,7 @@ udp_fast_csum_update(struct udphdr *uhdr, __be32 oldip, __be32 newip,
 				 ip_vs_check_diff(oldport ^ htons(0xFFFF),
 						  newport, uhdr->check));
 	if (!uhdr->check)
-		uhdr->check = -1;
+		uhdr->check = CSUM_MANGLED_0;
 }
 
 static int
@@ -173,7 +173,7 @@ udp_snat_handler(struct sk_buff **pskb,
 						cp->protocol,
 						(*pskb)->csum);
 		if (udph->check == 0)
-			udph->check = -1;
+			udph->check = CSUM_MANGLED_0;
 		IP_VS_DBG(11, "O-pkt: %s O-csum=%d (+%zd)\n",
 			  pp->name, udph->check,
 			  (char*)&(udph->check) - (char*)udph);
@@ -228,7 +228,7 @@ udp_dnat_handler(struct sk_buff **pskb,
 						cp->protocol,
 						(*pskb)->csum);
 		if (udph->check == 0)
-			udph->check = -1;
+			udph->check = CSUM_MANGLED_0;
 		(*pskb)->ip_summed = CHECKSUM_UNNECESSARY;
 	}
 	return 1;
diff --git a/net/ipv4/netfilter/ip_nat_helper.c b/net/ipv4/netfilter/ip_nat_helper.c
index 3bf858480558..3e7fd64c2162 100644
--- a/net/ipv4/netfilter/ip_nat_helper.c
+++ b/net/ipv4/netfilter/ip_nat_helper.c
@@ -264,7 +264,7 @@ ip_nat_mangle_udp_packet(struct sk_buff **pskb,
 		                                csum_partial((char *)udph,
 		                                             datalen, 0));
 		if (!udph->check)
-			udph->check = -1;
+			udph->check = CSUM_MANGLED_0;
 	} else
 		udph->check = nf_proto_csum_update(*pskb,
 						   htons(oldlen) ^ htons(0xFFFF),
diff --git a/net/ipv4/netfilter/ip_nat_proto_udp.c b/net/ipv4/netfilter/ip_nat_proto_udp.c
index 4bbec7730d18..82f8a6ab07ec 100644
--- a/net/ipv4/netfilter/ip_nat_proto_udp.c
+++ b/net/ipv4/netfilter/ip_nat_proto_udp.c
@@ -121,7 +121,7 @@ udp_manip_pkt(struct sk_buff **pskb,
 						  *portptr ^ htons(0xFFFF), newport,
 						  hdr->check, 0);
 		if (!hdr->check)
-			hdr->check = -1;
+			hdr->check = CSUM_MANGLED_0;
 	}
 	*portptr = newport;
 	return 1;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index f9c4ed7207bb..dc19ba1e73b5 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -441,7 +441,7 @@ static void udp4_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
 
 		uh->check = csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, csum);
 		if (uh->check == 0)
-			uh->check = -1;
+			uh->check = CSUM_MANGLED_0;
 	}
 }
 
@@ -490,7 +490,7 @@ int udp_push_pending_frames(struct sock *sk, struct udp_sock *up)
 	uh->check = csum_tcpudp_magic(fl->fl4_src, fl->fl4_dst, up->len,
 				      sk->sk_protocol, csum             );
 	if (uh->check == 0)
-		uh->check = -1;
+		uh->check = CSUM_MANGLED_0;
 
 send:
 	err = ip_push_pending_frames(sk);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 9b21d67ca48c..c2e629d6aea4 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -536,8 +536,8 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi *fl,
 				   &fl->fl6_dst,
 				   total_len, fl->proto, tmp_csum);
 
-	if (tmp_csum == 0 && fl->proto == IPPROTO_UDP)
-		tmp_csum = -1;
+	if (csum == 0 && fl->proto == IPPROTO_UDP)
+		csum = CSUM_MANGLED_0;
 
 	if (skb_store_bits(skb, offset, &csum, 2))
 		BUG();
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 0d22008d522e..bb45b9b7cbd9 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -536,7 +536,7 @@ static int udp_v6_push_pending_frames(struct sock *sk, struct udp_sock *up)
 	uh->check = csum_ipv6_magic(&fl->fl6_src, &fl->fl6_dst,
 				    up->len, fl->proto, csum   );
 	if (uh->check == 0)
-		uh->check = -1;
+		uh->check = CSUM_MANGLED_0;
 
 	err = ip6_push_pending_frames(sk);
 out:
-- 
cgit v1.2.3


From 078250d68d883495f31d0e6ce8321292f2dc1cfa Mon Sep 17 00:00:00 2001
From: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Date: Wed, 15 Nov 2006 00:44:49 -0800
Subject: [NET/IPv4]: Make udp_push_pending_frames static

udp_push_pending_frames is only referenced within
net/ipv4/udp.c and hence can remain static.

Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'net/ipv4/udp.c')

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index dc19ba1e73b5..7eb76fbf1b4b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -448,7 +448,7 @@ static void udp4_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
 /*
  * Push out all pending data as one UDP datagram. Socket is locked.
  */
-int udp_push_pending_frames(struct sock *sk, struct udp_sock *up)
+static int udp_push_pending_frames(struct sock *sk, struct udp_sock *up)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct flowi *fl = &inet->cork.fl;
-- 
cgit v1.2.3


From 8e5200f54062b8af0ed1d186ea0f113854786d89 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 20 Nov 2006 18:06:37 -0800
Subject: [NET]: Fix assorted misannotations (from md5 and udplite merges).

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     | 2 +-
 include/net/udp.h     | 2 +-
 include/net/udplite.h | 4 ++--
 net/ipv4/tcp_ipv4.c   | 2 +-
 net/ipv4/udp.c        | 4 ++--
 net/ipv6/tcp_ipv6.c   | 4 ++--
 net/ipv6/udp.c        | 2 +-
 net/ipv6/udplite.c    | 2 +-
 8 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'net/ipv4/udp.c')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index aa7989c53791..c99774f15eba 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1154,7 +1154,7 @@ extern int			tcp_v4_md5_do_add(struct sock *sk,
 						  u8 newkeylen);
 
 extern int			tcp_v4_md5_do_del(struct sock *sk,
-						  u32 addr);
+						  __be32 addr);
 
 extern struct tcp_md5sig_pool	**tcp_alloc_md5sig_pool(void);
 extern void			tcp_free_md5sig_pool(void);
diff --git a/include/net/udp.h b/include/net/udp.h
index c5ccd9a3387b..eac69ff0582c 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -77,7 +77,7 @@ static inline __sum16 __udp_lib_checksum_complete(struct sk_buff *skb)
 				      skb->csum));
 }
 
-static inline __sum16 udp_lib_checksum_complete(struct sk_buff *skb)
+static inline int udp_lib_checksum_complete(struct sk_buff *skb)
 {
 	return skb->ip_summed != CHECKSUM_UNNECESSARY &&
 		__udp_lib_checksum_complete(skb);
diff --git a/include/net/udplite.h b/include/net/udplite.h
index 3abaab7b78c6..67ac51424307 100644
--- a/include/net/udplite.h
+++ b/include/net/udplite.h
@@ -90,9 +90,9 @@ static __inline__ int udplite6_csum_init(struct sk_buff *skb, struct udphdr *uh)
 	int rc = udplite_checksum_init(skb, uh);
 
 	if (!rc)
-		skb->csum = ~csum_ipv6_magic(&skb->nh.ipv6h->saddr,
+		skb->csum = ~csum_unfold(csum_ipv6_magic(&skb->nh.ipv6h->saddr,
 					     &skb->nh.ipv6h->daddr,
-					     skb->len, IPPROTO_UDPLITE, 0);
+					     skb->len, IPPROTO_UDPLITE, 0));
 	return rc;
 }
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index b7d5522092eb..e9d467124c4d 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1020,7 +1020,7 @@ static int tcp_v4_do_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key,
 #ifdef CONFIG_TCP_MD5SIG_DEBUG
 	int i;
 #endif
-	__u16 old_checksum;
+	__sum16 old_checksum;
 	struct tcp_md5sig_pool *hp;
 	struct tcp4_pseudohdr *bp;
 	struct hash_desc *desc;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 7eb76fbf1b4b..28e4cf662ce0 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -114,7 +114,7 @@ DEFINE_RWLOCK(udp_hash_lock);
 
 static int udp_port_rover;
 
-static inline int __udp_lib_lport_inuse(__be16 num, struct hlist_head udptable[])
+static inline int __udp_lib_lport_inuse(__u16 num, struct hlist_head udptable[])
 {
 	struct sock *sk;
 	struct hlist_node *node;
@@ -455,7 +455,7 @@ static int udp_push_pending_frames(struct sock *sk, struct udp_sock *up)
 	struct sk_buff *skb;
 	struct udphdr *uh;
 	int err = 0;
-	u32 csum = 0;
+	__wsum csum = 0;
 
 	/* Grab the skbuff where UDP header space exists. */
 	if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index d2170da77e5b..0adb337c4b7e 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -739,7 +739,7 @@ static int tcp_v6_do_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key,
 	struct scatterlist sg[4];
 	__u16 data_len;
 	int block = 0;
-	__u16 cksum;
+	__sum16 cksum;
 	struct tcp_md5sig_pool *hp;
 	struct tcp6_pseudohdr *bp;
 	struct hash_desc *desc;
@@ -1032,7 +1032,7 @@ static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb)
 
 #ifdef CONFIG_TCP_MD5SIG
 	if (key) {
-		u32 *opt = (u32*)(t1 + 1);
+		__be32 *opt = (__be32*)(t1 + 1);
 		opt[0] = htonl((TCPOPT_NOP << 24) |
 			       (TCPOPT_NOP << 16) |
 			       (TCPOPT_MD5SIG << 8) |
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index efa8950ddd30..b3ea8af50a9b 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -248,7 +248,7 @@ out:
 
 static __inline__ void udpv6_err(struct sk_buff *skb,
 				 struct inet6_skb_parm *opt, int type,
-				 int code, int offset, __u32 info     )
+				 int code, int offset, __be32 info     )
 {
 	return __udp6_lib_err(skb, opt, type, code, offset, info, udp_hash);
 }
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index e0ec5e63004a..d4cafacc235b 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -24,7 +24,7 @@ static __inline__ int udplitev6_rcv(struct sk_buff **pskb)
 
 static __inline__ void udplitev6_err(struct sk_buff *skb,
 				     struct inet6_skb_parm *opt,
-				     int type, int code, int offset, __u32 info)
+				     int type, int code, int offset, __be32 info)
 {
 	return __udp6_lib_err(skb, opt, type, code, offset, info, udplite_hash);
 }
-- 
cgit v1.2.3


From ff1dcadb1b55dbf471c5ed109dbbdf06bd19ef3b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 20 Nov 2006 18:07:29 -0800
Subject: [NET]: Split skb->csum

... into anonymous union of __wsum and __u32 (csum and csum_offset resp.)

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/cassini.c           | 2 +-
 drivers/net/e1000/e1000_main.c  | 2 +-
 drivers/net/ixgb/ixgb_main.c    | 2 +-
 drivers/net/myri10ge/myri10ge.c | 2 +-
 drivers/net/sk98lin/skge.c      | 4 ++--
 drivers/net/skge.c              | 2 +-
 drivers/net/sky2.c              | 2 +-
 drivers/net/sungem.c            | 2 +-
 drivers/net/sunhme.c            | 2 +-
 include/linux/skbuff.h          | 5 ++++-
 net/core/dev.c                  | 4 ++--
 net/core/skbuff.c               | 2 +-
 net/ipv4/tcp_ipv4.c             | 4 ++--
 net/ipv4/udp.c                  | 2 +-
 net/ipv6/tcp_ipv6.c             | 4 ++--
 15 files changed, 22 insertions(+), 19 deletions(-)

(limited to 'net/ipv4/udp.c')

diff --git a/drivers/net/cassini.c b/drivers/net/cassini.c
index 521c5b71023c..fd2cc13f7d97 100644
--- a/drivers/net/cassini.c
+++ b/drivers/net/cassini.c
@@ -2825,7 +2825,7 @@ static inline int cas_xmit_tx_ringN(struct cas *cp, int ring,
 		u64 csum_start_off, csum_stuff_off;
 
 		csum_start_off = (u64) (skb->h.raw - skb->data);
-		csum_stuff_off = (u64) ((skb->h.raw + skb->csum) - skb->data);
+		csum_stuff_off = csum_start_off + skb->csum_offset;
 
 		ctrl =  TX_DESC_CSUM_EN |
 			CAS_BASE(TX_DESC_CSUM_START, csum_start_off) |
diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c
index 7a0828869ecf..32dde0adb683 100644
--- a/drivers/net/e1000/e1000_main.c
+++ b/drivers/net/e1000/e1000_main.c
@@ -2826,7 +2826,7 @@ e1000_tx_csum(struct e1000_adapter *adapter, struct e1000_tx_ring *tx_ring,
 		context_desc = E1000_CONTEXT_DESC(*tx_ring, i);
 
 		context_desc->upper_setup.tcp_fields.tucss = css;
-		context_desc->upper_setup.tcp_fields.tucso = css + skb->csum;
+		context_desc->upper_setup.tcp_fields.tucso = css + skb->csum_offset;
 		context_desc->upper_setup.tcp_fields.tucse = 0;
 		context_desc->tcp_seg_setup.data = 0;
 		context_desc->cmd_and_length = cpu_to_le32(E1000_TXD_CMD_DEXT);
diff --git a/drivers/net/ixgb/ixgb_main.c b/drivers/net/ixgb/ixgb_main.c
index e09f575a3a38..7b127212e62b 100644
--- a/drivers/net/ixgb/ixgb_main.c
+++ b/drivers/net/ixgb/ixgb_main.c
@@ -1249,7 +1249,7 @@ ixgb_tx_csum(struct ixgb_adapter *adapter, struct sk_buff *skb)
 	if(likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
 		struct ixgb_buffer *buffer_info;
 		css = skb->h.raw - skb->data;
-		cso = (skb->h.raw + skb->csum) - skb->data;
+		cso = css + skb->csum_offset;
 
 		i = adapter->tx_ring.next_to_use;
 		context_desc = IXGB_CONTEXT_DESC(adapter->tx_ring, i);
diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c
index 806081b59733..36350e6db1c1 100644
--- a/drivers/net/myri10ge/myri10ge.c
+++ b/drivers/net/myri10ge/myri10ge.c
@@ -1955,7 +1955,7 @@ again:
 	flags = (MXGEFW_FLAGS_NO_TSO | MXGEFW_FLAGS_FIRST);
 	if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
 		cksum_offset = (skb->h.raw - skb->data);
-		pseudo_hdr_offset = (skb->h.raw + skb->csum) - skb->data;
+		pseudo_hdr_offset = cksum_offset + skb->csum_offset;
 		/* If the headers are excessively large, then we must
 		 * fall back to a software checksum */
 		if (unlikely(cksum_offset > 255 || pseudo_hdr_offset > 127)) {
diff --git a/drivers/net/sk98lin/skge.c b/drivers/net/sk98lin/skge.c
index a5d41ebc9fb4..12cbfd190dd7 100644
--- a/drivers/net/sk98lin/skge.c
+++ b/drivers/net/sk98lin/skge.c
@@ -1562,7 +1562,7 @@ struct sk_buff	*pMessage)	/* pointer to send-message              */
 
 	if (pMessage->ip_summed == CHECKSUM_PARTIAL) {
 		u16 hdrlen = pMessage->h.raw - pMessage->data;
-		u16 offset = hdrlen + pMessage->csum;
+		u16 offset = hdrlen + pMessage->csum_offset;
 
 		if ((pMessage->h.ipiph->protocol == IPPROTO_UDP ) &&
 			(pAC->GIni.GIChipRev == 0) &&
@@ -1681,7 +1681,7 @@ struct sk_buff	*pMessage)	/* pointer to send-message              */
 	*/
 	if (pMessage->ip_summed == CHECKSUM_PARTIAL) {
 		u16 hdrlen = pMessage->h.raw - pMessage->data;
-		u16 offset = hdrlen + pMessage->csum;
+		u16 offset = hdrlen + pMessage->csum_offset;
 
 		Control = BMU_STFWD;
 
diff --git a/drivers/net/skge.c b/drivers/net/skge.c
index 27b537c8d5e3..5513907e8393 100644
--- a/drivers/net/skge.c
+++ b/drivers/net/skge.c
@@ -2565,7 +2565,7 @@ static int skge_xmit_frame(struct sk_buff *skb, struct net_device *dev)
 
 		td->csum_offs = 0;
 		td->csum_start = offset;
-		td->csum_write = offset + skb->csum;
+		td->csum_write = offset + skb->csum_offset;
 	} else
 		control = BMU_CHECK;
 
diff --git a/drivers/net/sky2.c b/drivers/net/sky2.c
index 0ef1848b9761..842abd9396c6 100644
--- a/drivers/net/sky2.c
+++ b/drivers/net/sky2.c
@@ -1350,7 +1350,7 @@ static int sky2_xmit_frame(struct sk_buff *skb, struct net_device *dev)
 		u32 tcpsum;
 
 		tcpsum = offset << 16;		/* sum start */
-		tcpsum |= offset + skb->csum;	/* sum write */
+		tcpsum |= offset + skb->csum_offset;	/* sum write */
 
 		ctrl = CALSUM | WR_SUM | INIT_SUM | LOCK_SUM;
 		if (skb->nh.iph->protocol == IPPROTO_UDP)
diff --git a/drivers/net/sungem.c b/drivers/net/sungem.c
index 253e96e7ad20..334c6cfd6595 100644
--- a/drivers/net/sungem.c
+++ b/drivers/net/sungem.c
@@ -1030,7 +1030,7 @@ static int gem_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		u64 csum_start_off, csum_stuff_off;
 
 		csum_start_off = (u64) (skb->h.raw - skb->data);
-		csum_stuff_off = (u64) ((skb->h.raw + skb->csum) - skb->data);
+		csum_stuff_off = csum_start_off + skb->csum_offset;
 
 		ctrl = (TXDCTRL_CENAB |
 			(csum_start_off << 15) |
diff --git a/drivers/net/sunhme.c b/drivers/net/sunhme.c
index 9d7cd130c19d..ec432ea879fb 100644
--- a/drivers/net/sunhme.c
+++ b/drivers/net/sunhme.c
@@ -2272,7 +2272,7 @@ static int happy_meal_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		u32 csum_start_off, csum_stuff_off;
 
 		csum_start_off = (u32) (skb->h.raw - skb->data);
-		csum_stuff_off = (u32) ((skb->h.raw + skb->csum) - skb->data);
+		csum_stuff_off = csum_start_off + skb->csum_offset;
 
 		tx_flags = (TXFLAG_OWN | TXFLAG_CSENABLE |
 			    ((csum_start_off << 14) & TXFLAG_CSBUFBEGIN) |
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index fcab543d79ac..14ec16d2d9ba 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -274,7 +274,10 @@ struct sk_buff {
 	unsigned int		len,
 				data_len,
 				mac_len;
-	__wsum			csum;
+	union {
+		__wsum		csum;
+		__u32		csum_offset;
+	};
 	__u32			priority;
 	__u8			local_df:1,
 				cloned:1,
diff --git a/net/core/dev.c b/net/core/dev.c
index 1a36b17f4b51..59d058a3b504 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1191,9 +1191,9 @@ int skb_checksum_help(struct sk_buff *skb)
 
 	offset = skb->tail - skb->h.raw;
 	BUG_ON(offset <= 0);
-	BUG_ON(skb->csum + 2 > offset);
+	BUG_ON(skb->csum_offset + 2 > offset);
 
-	*(__sum16*)(skb->h.raw + skb->csum) = csum_fold(csum);
+	*(__sum16*)(skb->h.raw + skb->csum_offset) = csum_fold(csum);
 
 out_set_summed:
 	skb->ip_summed = CHECKSUM_NONE;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 07c25d601922..a90bc439488e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1414,7 +1414,7 @@ void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to)
 					      skb->len - csstart, 0);
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
-		long csstuff = csstart + skb->csum;
+		long csstuff = csstart + skb->csum_offset;
 
 		*((__sum16 *)(to + csstuff)) = csum_fold(csum);
 	}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index e9d467124c4d..4913f25e5ad5 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -504,7 +504,7 @@ void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb)
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		th->check = ~tcp_v4_check(th, len,
 					  inet->saddr, inet->daddr, 0);
-		skb->csum = offsetof(struct tcphdr, check);
+		skb->csum_offset = offsetof(struct tcphdr, check);
 	} else {
 		th->check = tcp_v4_check(th, len, inet->saddr, inet->daddr,
 					 csum_partial((char *)th,
@@ -526,7 +526,7 @@ int tcp_v4_gso_send_check(struct sk_buff *skb)
 
 	th->check = 0;
 	th->check = ~tcp_v4_check(th, skb->len, iph->saddr, iph->daddr, 0);
-	skb->csum = offsetof(struct tcphdr, check);
+	skb->csum_offset = offsetof(struct tcphdr, check);
 	skb->ip_summed = CHECKSUM_PARTIAL;
 	return 0;
 }
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 28e4cf662ce0..1807a30694d9 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -422,7 +422,7 @@ static void udp4_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
 		/*
 		 * Only one fragment on the socket.
 		 */
-		skb->csum = offsetof(struct udphdr, check);
+		skb->csum_offset = offsetof(struct udphdr, check);
 		uh->check = ~csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, 0);
 	} else {
 		/*
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 0adb337c4b7e..517c50024bfc 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -948,7 +948,7 @@ static void tcp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb)
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		th->check = ~csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP,  0);
-		skb->csum = offsetof(struct tcphdr, check);
+		skb->csum_offset = offsetof(struct tcphdr, check);
 	} else {
 		th->check = csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP, 
 					    csum_partial((char *)th, th->doff<<2, 
@@ -970,7 +970,7 @@ static int tcp_v6_gso_send_check(struct sk_buff *skb)
 	th->check = 0;
 	th->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, skb->len,
 				     IPPROTO_TCP, 0);
-	skb->csum = offsetof(struct tcphdr, check);
+	skb->csum_offset = offsetof(struct tcphdr, check);
 	skb->ip_summed = CHECKSUM_PARTIAL;
 	return 0;
 }
-- 
cgit v1.2.3


From 4c0a6cb0db19de411c4bf7fcdc79d4c7c4ccafb1 Mon Sep 17 00:00:00 2001
From: Gerrit Renker <gerrit@erg.abdn.ac.uk>
Date: Mon, 27 Nov 2006 09:29:59 -0800
Subject: [UDP(-Lite)]: consolidate v4 and v6 get|setsockopt code

This patch consolidates set/getsockopt code between UDP(-Lite) v4 and 6. The
justification is that UDP(-Lite) is a transport-layer protocol and therefore
the socket option code (at least in theory) should be AF-independent.

Furthermore, there is the following code reduplication:
 * do_udp{,v6}_getsockopt is 100% identical between v4 and v6
 * do_udp{,v6}_setsockopt is identical up to the following differerence
	--v4 in contrast to v4 additionally allows the experimental encapsulation
          types  UDP_ENCAP_ESPINUDP and UDP_ENCAP_ESPINUDP_NON_IKE
	--the remainder is identical between v4 and v6
   I believe that this difference is of little relevance.

The advantages in not duplicating twice almost completely identical code.

The patch further simplifies the interface of udp{,v6}_push_pending_frames,
since for the second argument (struct udp_sock *up) it always holds that
up = udp_sk(sk); where sk is the first function argument.

Signed-off-by: Gerrit Renker  <gerrit@erg.abdn.ac.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/udp.h |   5 +++
 net/ipv4/udp.c    |  30 ++++++++------
 net/ipv6/udp.c    | 118 +++++-------------------------------------------------
 3 files changed, 32 insertions(+), 121 deletions(-)

(limited to 'net/ipv4/udp.c')

diff --git a/include/net/udp.h b/include/net/udp.h
index eac69ff0582c..1548d68d45da 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -134,6 +134,11 @@ extern int	udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
 extern int	udp_disconnect(struct sock *sk, int flags);
 extern unsigned int udp_poll(struct file *file, struct socket *sock,
 			     poll_table *wait);
+extern int 	udp_lib_getsockopt(struct sock *sk, int level, int optname,
+			           char __user *optval, int __user *optlen);
+extern int 	udp_lib_setsockopt(struct sock *sk, int level, int optname,
+				   char __user *optval, int optlen,
+				   int (*push_pending_frames)(struct sock *));
 
 DECLARE_SNMP_STAT(struct udp_mib, udp_statistics);
 /*
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1807a30694d9..035915fc9ed3 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -448,8 +448,9 @@ static void udp4_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
 /*
  * Push out all pending data as one UDP datagram. Socket is locked.
  */
-static int udp_push_pending_frames(struct sock *sk, struct udp_sock *up)
+static int udp_push_pending_frames(struct sock *sk)
 {
+	struct udp_sock  *up = udp_sk(sk);
 	struct inet_sock *inet = inet_sk(sk);
 	struct flowi *fl = &inet->cork.fl;
 	struct sk_buff *skb;
@@ -673,7 +674,7 @@ do_append_data:
 	if (err)
 		udp_flush_pending_frames(sk);
 	else if (!corkreq)
-		err = udp_push_pending_frames(sk, up);
+		err = udp_push_pending_frames(sk);
 	else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
 		up->pending = 0;
 	release_sock(sk);
@@ -746,7 +747,7 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset,
 
 	up->len += size;
 	if (!(up->corkflag || (flags&MSG_MORE)))
-		ret = udp_push_pending_frames(sk, up);
+		ret = udp_push_pending_frames(sk);
 	if (!ret)
 		ret = size;
 out:
@@ -1299,8 +1300,9 @@ int udp_destroy_sock(struct sock *sk)
 /*
  *	Socket option code for UDP
  */
-static int do_udp_setsockopt(struct sock *sk, int level, int optname,
-			  char __user *optval, int optlen)
+int udp_lib_setsockopt(struct sock *sk, int level, int optname,
+		       char __user *optval, int optlen,
+		       int (*push_pending_frames)(struct sock *))
 {
 	struct udp_sock *up = udp_sk(sk);
 	int val;
@@ -1319,7 +1321,7 @@ static int do_udp_setsockopt(struct sock *sk, int level, int optname,
 		} else {
 			up->corkflag = 0;
 			lock_sock(sk);
-			udp_push_pending_frames(sk, up);
+			(*push_pending_frames)(sk);
 			release_sock(sk);
 		}
 		break;
@@ -1375,7 +1377,8 @@ int udp_setsockopt(struct sock *sk, int level, int optname,
 		   char __user *optval, int optlen)
 {
 	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
-		return do_udp_setsockopt(sk, level, optname, optval, optlen);
+		return udp_lib_setsockopt(sk, level, optname, optval, optlen,
+					  udp_push_pending_frames);
 	return ip_setsockopt(sk, level, optname, optval, optlen);
 }
 
@@ -1384,13 +1387,14 @@ int compat_udp_setsockopt(struct sock *sk, int level, int optname,
 			  char __user *optval, int optlen)
 {
 	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
-		return do_udp_setsockopt(sk, level, optname, optval, optlen);
+		return udp_lib_setsockopt(sk, level, optname, optval, optlen,
+					  udp_push_pending_frames);
 	return compat_ip_setsockopt(sk, level, optname, optval, optlen);
 }
 #endif
 
-static int do_udp_getsockopt(struct sock *sk, int level, int optname,
-			  char __user *optval, int __user *optlen)
+int udp_lib_getsockopt(struct sock *sk, int level, int optname,
+		       char __user *optval, int __user *optlen)
 {
 	struct udp_sock *up = udp_sk(sk);
 	int val, len;
@@ -1437,7 +1441,7 @@ int udp_getsockopt(struct sock *sk, int level, int optname,
 		   char __user *optval, int __user *optlen)
 {
 	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
-		return do_udp_getsockopt(sk, level, optname, optval, optlen);
+		return udp_lib_getsockopt(sk, level, optname, optval, optlen);
 	return ip_getsockopt(sk, level, optname, optval, optlen);
 }
 
@@ -1446,7 +1450,7 @@ int compat_udp_getsockopt(struct sock *sk, int level, int optname,
 				 char __user *optval, int __user *optlen)
 {
 	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
-		return do_udp_getsockopt(sk, level, optname, optval, optlen);
+		return udp_lib_getsockopt(sk, level, optname, optval, optlen);
 	return compat_ip_getsockopt(sk, level, optname, optval, optlen);
 }
 #endif
@@ -1716,6 +1720,8 @@ EXPORT_SYMBOL(udp_ioctl);
 EXPORT_SYMBOL(udp_get_port);
 EXPORT_SYMBOL(udp_prot);
 EXPORT_SYMBOL(udp_sendmsg);
+EXPORT_SYMBOL(udp_lib_getsockopt);
+EXPORT_SYMBOL(udp_lib_setsockopt);
 EXPORT_SYMBOL(udp_poll);
 
 #ifdef CONFIG_PROC_FS
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index b3ea8af50a9b..f52a5c3cc0a3 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -505,10 +505,11 @@ static void udp_v6_flush_pending_frames(struct sock *sk)
  *	Sending
  */
 
-static int udp_v6_push_pending_frames(struct sock *sk, struct udp_sock *up)
+static int udp_v6_push_pending_frames(struct sock *sk)
 {
 	struct sk_buff *skb;
 	struct udphdr *uh;
+	struct udp_sock  *up = udp_sk(sk);
 	struct inet_sock *inet = inet_sk(sk);
 	struct flowi *fl = &inet->cork.fl;
 	int err = 0;
@@ -782,7 +783,7 @@ do_append_data:
 	if (err)
 		udp_v6_flush_pending_frames(sk);
 	else if (!corkreq)
-		err = udp_v6_push_pending_frames(sk, up);
+		err = udp_v6_push_pending_frames(sk);
 	else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
 		up->pending = 0;
 
@@ -844,72 +845,12 @@ int udpv6_destroy_sock(struct sock *sk)
 /*
  *	Socket option code for UDP
  */
-static int do_udpv6_setsockopt(struct sock *sk, int level, int optname,
-			  char __user *optval, int optlen)
-{
-	struct udp_sock *up = udp_sk(sk);
-	int val;
-	int err = 0;
-
-	if(optlen<sizeof(int))
-		return -EINVAL;
-
-	if (get_user(val, (int __user *)optval))
-		return -EFAULT;
-
-	switch(optname) {
-	case UDP_CORK:
-		if (val != 0) {
-			up->corkflag = 1;
-		} else {
-			up->corkflag = 0;
-			lock_sock(sk);
-			udp_v6_push_pending_frames(sk, up);
-			release_sock(sk);
-		}
-		break;
-	case UDP_ENCAP:
-		switch (val) {
-		case 0:
-			up->encap_type = val;
-			break;
-		default:
-			err = -ENOPROTOOPT;
-			break;
-		}
-		break;
-
-	case UDPLITE_SEND_CSCOV:
-		if (!up->pcflag)         /* Disable the option on UDP sockets */
-			return -ENOPROTOOPT;
-		if (val != 0 && val < 8) /* Illegal coverage: use default (8) */
-			val = 8;
-		up->pcslen = val;
-		up->pcflag |= UDPLITE_SEND_CC;
-		break;
-
-	case UDPLITE_RECV_CSCOV:
-		if (!up->pcflag)         /* Disable the option on UDP sockets */
-			return -ENOPROTOOPT;
-		if (val != 0 && val < 8) /* Avoid silly minimal values.       */
-			val = 8;
-		up->pcrlen = val;
-		up->pcflag |= UDPLITE_RECV_CC;
-		break;
-
-	default:
-		err = -ENOPROTOOPT;
-		break;
-	};
-
-	return err;
-}
-
 int udpv6_setsockopt(struct sock *sk, int level, int optname,
 		     char __user *optval, int optlen)
 {
 	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
-		return do_udpv6_setsockopt(sk, level, optname, optval, optlen);
+		return udp_lib_setsockopt(sk, level, optname, optval, optlen,
+					  udp_v6_push_pending_frames);
 	return ipv6_setsockopt(sk, level, optname, optval, optlen);
 }
 
@@ -918,58 +859,17 @@ int compat_udpv6_setsockopt(struct sock *sk, int level, int optname,
 			    char __user *optval, int optlen)
 {
 	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
-		return do_udpv6_setsockopt(sk, level, optname, optval, optlen);
+		return udp_lib_setsockopt(sk, level, optname, optval, optlen,
+					  udp_v6_push_pending_frames);
 	return compat_ipv6_setsockopt(sk, level, optname, optval, optlen);
 }
 #endif
 
-static int do_udpv6_getsockopt(struct sock *sk, int level, int optname,
-			  char __user *optval, int __user *optlen)
-{
-	struct udp_sock *up = udp_sk(sk);
-	int val, len;
-
-	if(get_user(len,optlen))
-		return -EFAULT;
-
-	len = min_t(unsigned int, len, sizeof(int));
-	
-	if(len < 0)
-		return -EINVAL;
-
-	switch(optname) {
-	case UDP_CORK:
-		val = up->corkflag;
-		break;
-
-	case UDP_ENCAP:
-		val = up->encap_type;
-		break;
-
-	case UDPLITE_SEND_CSCOV:
-		val = up->pcslen;
-		break;
-
-	case UDPLITE_RECV_CSCOV:
-		val = up->pcrlen;
-		break;
-
-	default:
-		return -ENOPROTOOPT;
-	};
-
-  	if(put_user(len, optlen))
-  		return -EFAULT;
-	if(copy_to_user(optval, &val,len))
-		return -EFAULT;
-  	return 0;
-}
-
 int udpv6_getsockopt(struct sock *sk, int level, int optname,
 		     char __user *optval, int __user *optlen)
 {
 	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
-		return do_udpv6_getsockopt(sk, level, optname, optval, optlen);
+		return udp_lib_getsockopt(sk, level, optname, optval, optlen);
 	return ipv6_getsockopt(sk, level, optname, optval, optlen);
 }
 
@@ -978,7 +878,7 @@ int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
 			    char __user *optval, int __user *optlen)
 {
 	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
-		return do_udpv6_getsockopt(sk, level, optname, optval, optlen);
+		return udp_lib_getsockopt(sk, level, optname, optval, optlen);
 	return compat_ipv6_getsockopt(sk, level, optname, optval, optlen);
 }
 #endif
-- 
cgit v1.2.3


From 5c668704b7fa5a4ebf21a490ddfbd6dc2e01fc97 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@sunset.davemloft.net>
Date: Fri, 22 Dec 2006 11:42:26 -0800
Subject: [UDP]: Fix reversed logic in udp_get_port().

When this code was converted to use sk_for_each() the
logic for the "best hash chain length" code was reversed,
breaking everything.

The original code was of the form:

			size = 0;
			do {
				if (++size >= best_size_so_far)
					goto next;
			} while ((sk = sk->next) != NULL);
			best_size_so_far = size;
			best = result;
		next:;

and this got converted into:

			sk_for_each(sk2, node, head)
				if (++size < best_size_so_far) {
					best_size_so_far = size;
					best = result;
				}

Which does something very very different from the original.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/udp.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

(limited to 'net/ipv4/udp.c')

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 035915fc9ed3..cfff930f2baf 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -165,11 +165,14 @@ int __udp_lib_get_port(struct sock *sk, unsigned short snum,
 				goto gotit;
 			}
 			size = 0;
-			sk_for_each(sk2, node, head)
-				if (++size < best_size_so_far) {
-					best_size_so_far = size;
-					best = result;
-				}
+			sk_for_each(sk2, node, head) {
+				if (++size >= best_size_so_far)
+					goto next;
+			}
+			best_size_so_far = size;
+			best = result;
+		next:
+			;
 		}
 		result = best;
 		for(i = 0; i < (1 << 16) / UDP_HTABLE_SIZE; i++, result += UDP_HTABLE_SIZE) {
-- 
cgit v1.2.3