/*
* UDP over IPv6
- * Linux INET6 implementation
+ * Linux INET6 implementation
*
* Authors:
- * Pedro Roque <roque@di.fc.ul.pt>
+ * Pedro Roque <roque@di.fc.ul.pt>
*
* Based on linux/ipv4/udp.c
*
- * $Id: udp.c,v 1.65 2002/02/01 22:01:04 davem Exp $
- *
* Fixes:
* Hideaki YOSHIFUJI : sin6_scope_id support
* YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
-#include <linux/sched.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/init.h>
+#include <linux/module.h>
#include <linux/skbuff.h>
#include <asm/uaccess.h>
-#include <net/sock.h>
-#include <net/snmp.h>
-
-#include <net/ipv6.h>
#include <net/ndisc.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
-#include <net/addrconf.h>
-#include <net/ip.h>
-#include <net/udp.h>
#include <net/raw.h>
-#include <net/inet_common.h>
#include <net/tcp_states.h>
-
#include <net/ip6_checksum.h>
#include <net/xfrm.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
+#include "udp_impl.h"
-DEFINE_SNMP_STAT(struct udp_mib, udp_stats_in6) __read_mostly;
-
-static inline int udp_v6_get_port(struct sock *sk, unsigned short snum)
+int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
{
- return udp_get_port(sk, snum, ipv6_rcv_saddr_equal);
+ const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr;
+ const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2);
+ __be32 sk_rcv_saddr = inet_sk(sk)->rcv_saddr;
+ __be32 sk2_rcv_saddr = inet_rcv_saddr(sk2);
+ int sk_ipv6only = ipv6_only_sock(sk);
+ int sk2_ipv6only = inet_v6_ipv6only(sk2);
+ int addr_type = ipv6_addr_type(sk_rcv_saddr6);
+ int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;
+
+ /* if both are mapped, treat as IPv4 */
+ if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED)
+ return (!sk2_ipv6only &&
+ (!sk_rcv_saddr || !sk2_rcv_saddr ||
+ sk_rcv_saddr == sk2_rcv_saddr));
+
+ if (addr_type2 == IPV6_ADDR_ANY &&
+ !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
+ return 1;
+
+ if (addr_type == IPV6_ADDR_ANY &&
+ !(sk_ipv6only && addr_type2 == IPV6_ADDR_MAPPED))
+ return 1;
+
+ if (sk2_rcv_saddr6 &&
+ ipv6_addr_equal(sk_rcv_saddr6, sk2_rcv_saddr6))
+ return 1;
+
+ return 0;
}
-static void udp_v6_hash(struct sock *sk)
+int udp_v6_get_port(struct sock *sk, unsigned short snum)
{
- BUG();
+ return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal);
}
-static void udp_v6_unhash(struct sock *sk)
+static inline int compute_score(struct sock *sk, struct net *net,
+ unsigned short hnum,
+ struct in6_addr *saddr, __be16 sport,
+ struct in6_addr *daddr, __be16 dport,
+ int dif)
{
- write_lock_bh(&udp_hash_lock);
- if (sk_del_node_init(sk)) {
- inet_sk(sk)->num = 0;
- sock_prot_dec_use(sk->sk_prot);
+ int score = -1;
+
+ if (net_eq(sock_net(sk), net) && sk->sk_hash == hnum &&
+ sk->sk_family == PF_INET6) {
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct inet_sock *inet = inet_sk(sk);
+
+ score = 0;
+ if (inet->dport) {
+ if (inet->dport != sport)
+ return -1;
+ score++;
+ }
+ if (!ipv6_addr_any(&np->rcv_saddr)) {
+ if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
+ return -1;
+ score++;
+ }
+ if (!ipv6_addr_any(&np->daddr)) {
+ if (!ipv6_addr_equal(&np->daddr, saddr))
+ return -1;
+ score++;
+ }
+ if (sk->sk_bound_dev_if) {
+ if (sk->sk_bound_dev_if != dif)
+ return -1;
+ score++;
+ }
}
- write_unlock_bh(&udp_hash_lock);
+ return score;
}
-static struct sock *udp_v6_lookup(struct in6_addr *saddr, u16 sport,
- struct in6_addr *daddr, u16 dport, int dif)
+static struct sock *__udp6_lib_lookup(struct net *net,
+ struct in6_addr *saddr, __be16 sport,
+ struct in6_addr *daddr, __be16 dport,
+ int dif, struct udp_table *udptable)
{
- struct sock *sk, *result = NULL;
- struct hlist_node *node;
+ struct sock *sk, *result;
+ struct hlist_nulls_node *node;
unsigned short hnum = ntohs(dport);
- int badness = -1;
-
- read_lock(&udp_hash_lock);
- sk_for_each(sk, node, &udp_hash[hnum & (UDP_HTABLE_SIZE - 1)]) {
- struct inet_sock *inet = inet_sk(sk);
-
- if (inet->num == hnum && sk->sk_family == PF_INET6) {
- struct ipv6_pinfo *np = inet6_sk(sk);
- int score = 0;
- if (inet->dport) {
- if (inet->dport != sport)
- continue;
- score++;
- }
- if (!ipv6_addr_any(&np->rcv_saddr)) {
- if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
- continue;
- score++;
- }
- if (!ipv6_addr_any(&np->daddr)) {
- if (!ipv6_addr_equal(&np->daddr, saddr))
- continue;
- score++;
- }
- if (sk->sk_bound_dev_if) {
- if (sk->sk_bound_dev_if != dif)
- continue;
- score++;
- }
- if(score == 4) {
- result = sk;
- break;
- } else if(score > badness) {
- result = sk;
- badness = score;
- }
+ unsigned int hash = udp_hashfn(net, hnum);
+ struct udp_hslot *hslot = &udptable->hash[hash];
+ int score, badness;
+
+ rcu_read_lock();
+begin:
+ result = NULL;
+ badness = -1;
+ sk_nulls_for_each_rcu(sk, node, &hslot->head) {
+ score = compute_score(sk, net, hnum, saddr, sport, daddr, dport, dif);
+ if (score > badness) {
+ result = sk;
+ badness = score;
+ }
+ }
+ /*
+ * if the nulls value we got at the end of this lookup is
+ * not the expected one, we must restart lookup.
+ * We probably met an item that was moved to another chain.
+ */
+ if (get_nulls_value(node) != hash)
+ goto begin;
+
+ if (result) {
+ if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt)))
+ result = NULL;
+ else if (unlikely(compute_score(result, net, hnum, saddr, sport,
+ daddr, dport, dif) < badness)) {
+ sock_put(result);
+ goto begin;
}
}
- if (result)
- sock_hold(result);
- read_unlock(&udp_hash_lock);
+ rcu_read_unlock();
return result;
}
-/*
- *
- */
-
-static void udpv6_close(struct sock *sk, long timeout)
+static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
+ __be16 sport, __be16 dport,
+ struct udp_table *udptable)
{
- sk_common_release(sk);
+ struct sock *sk;
+ struct ipv6hdr *iph = ipv6_hdr(skb);
+
+ if (unlikely(sk = skb_steal_sock(skb)))
+ return sk;
+ else
+ return __udp6_lib_lookup(dev_net(skb->dst->dev), &iph->saddr, sport,
+ &iph->daddr, dport, inet6_iif(skb),
+ udptable);
}
/*
* return it, otherwise we block.
*/
-static int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
+int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg, size_t len,
int noblock, int flags, int *addr_len)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet_sock *inet = inet_sk(sk);
- struct sk_buff *skb;
- size_t copied;
- int err;
+ struct sk_buff *skb;
+ unsigned int ulen, copied;
+ int peeked;
+ int err;
+ int is_udplite = IS_UDPLITE(sk);
+ int is_udp4;
+
+ if (addr_len)
+ *addr_len=sizeof(struct sockaddr_in6);
- if (addr_len)
- *addr_len=sizeof(struct sockaddr_in6);
-
if (flags & MSG_ERRQUEUE)
return ipv6_recv_error(sk, msg, len);
try_again:
- skb = skb_recv_datagram(sk, flags, noblock, &err);
+ skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
+ &peeked, &err);
if (!skb)
goto out;
- copied = skb->len - sizeof(struct udphdr);
- if (copied > len) {
- copied = len;
- 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 (__skb_checksum_complete(skb))
+ ulen = skb->len - sizeof(struct udphdr);
+ copied = len;
+ if (copied > ulen)
+ copied = ulen;
+ else if (copied < ulen)
+ msg->msg_flags |= MSG_TRUNC;
+
+ is_udp4 = (skb->protocol == htons(ETH_P_IP));
+
+ /*
+ * If checksum is needed at all, try to do it while copying the
+ * data. If the data is truncated, or if we only want a partial
+ * coverage checksum (UDP-Lite), do it before the copy.
+ */
+
+ if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) {
+ if (udp_lib_checksum_complete(skb))
goto csum_copy_err;
- err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov,
- copied);
- } else {
+ }
+
+ if (skb_csum_unnecessary(skb))
+ 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)
goto csum_copy_err;
if (err)
goto out_free;
+ if (!peeked) {
+ if (is_udp4)
+ UDP_INC_STATS_USER(sock_net(sk),
+ UDP_MIB_INDATAGRAMS, is_udplite);
+ else
+ UDP6_INC_STATS_USER(sock_net(sk),
+ UDP_MIB_INDATAGRAMS, is_udplite);
+ }
+
sock_recv_timestamp(msg, sk, skb);
/* Copy the address. */
if (msg->msg_name) {
struct sockaddr_in6 *sin6;
-
+
sin6 = (struct sockaddr_in6 *) msg->msg_name;
sin6->sin6_family = AF_INET6;
- sin6->sin6_port = skb->h.uh->source;
+ sin6->sin6_port = udp_hdr(skb)->source;
sin6->sin6_flowinfo = 0;
sin6->sin6_scope_id = 0;
- if (skb->protocol == htons(ETH_P_IP))
+ if (is_udp4)
ipv6_addr_set(&sin6->sin6_addr, 0, 0,
- htonl(0xffff), skb->nh.iph->saddr);
+ htonl(0xffff), ip_hdr(skb)->saddr);
else {
- ipv6_addr_copy(&sin6->sin6_addr, &skb->nh.ipv6h->saddr);
+ ipv6_addr_copy(&sin6->sin6_addr,
+ &ipv6_hdr(skb)->saddr);
if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
sin6->sin6_scope_id = IP6CB(skb)->iif;
}
}
- if (skb->protocol == htons(ETH_P_IP)) {
+ if (is_udp4) {
if (inet->cmsg_flags)
ip_cmsg_recv(msg, skb);
} else {
if (np->rxopt.all)
datagram_recv_ctl(sk, msg, skb);
- }
+ }
err = copied;
if (flags & MSG_TRUNC)
- err = skb->len - sizeof(struct udphdr);
+ err = ulen;
out_free:
+ lock_sock(sk);
skb_free_datagram(sk, skb);
+ release_sock(sk);
out:
return err;
csum_copy_err:
- skb_kill_datagram(sk, skb, flags);
+ lock_sock(sk);
+ if (!skb_kill_datagram(sk, skb, flags)) {
+ if (is_udp4)
+ UDP_INC_STATS_USER(sock_net(sk),
+ UDP_MIB_INERRORS, is_udplite);
+ else
+ UDP6_INC_STATS_USER(sock_net(sk),
+ UDP_MIB_INERRORS, is_udplite);
+ }
+ release_sock(sk);
- if (flags & MSG_DONTWAIT) {
- UDP6_INC_STATS_USER(UDP_MIB_INERRORS);
+ if (flags & MSG_DONTWAIT)
return -EAGAIN;
- }
goto try_again;
}
-static void udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
- int type, int code, int offset, __u32 info)
+void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+ int type, int code, int offset, __be32 info,
+ struct udp_table *udptable)
{
struct ipv6_pinfo *np;
struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data;
- struct net_device *dev = skb->dev;
struct in6_addr *saddr = &hdr->saddr;
struct in6_addr *daddr = &hdr->daddr;
struct udphdr *uh = (struct udphdr*)(skb->data+offset);
struct sock *sk;
int err;
- sk = udp_v6_lookup(daddr, uh->dest, saddr, uh->source, dev->ifindex);
-
+ sk = __udp6_lib_lookup(dev_net(skb->dev), daddr, uh->dest,
+ saddr, uh->source, inet6_iif(skb), udptable);
if (sk == NULL)
return;
sock_put(sk);
}
-static inline int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
+static __inline__ void udpv6_err(struct sk_buff *skb,
+ struct inet6_skb_parm *opt, int type,
+ int code, int offset, __be32 info )
{
+ __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table);
+}
+
+int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
+{
+ struct udp_sock *up = udp_sk(sk);
int rc;
+ int is_udplite = IS_UDPLITE(sk);
- if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) {
- kfree_skb(skb);
- return -1;
+ if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
+ goto drop;
+
+ /*
+ * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c).
+ */
+ if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) {
+
+ if (up->pcrlen == 0) { /* full coverage was set */
+ LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: partial coverage"
+ " %d while full coverage %d requested\n",
+ UDP_SKB_CB(skb)->cscov, skb->len);
+ goto drop;
+ }
+ if (UDP_SKB_CB(skb)->cscov < up->pcrlen) {
+ LIMIT_NETDEBUG(KERN_WARNING "UDPLITE6: coverage %d "
+ "too small, need min %d\n",
+ UDP_SKB_CB(skb)->cscov, up->pcrlen);
+ goto drop;
+ }
}
- if (skb_checksum_complete(skb)) {
- UDP6_INC_STATS_BH(UDP_MIB_INERRORS);
- kfree_skb(skb);
- return 0;
+ if (sk->sk_filter) {
+ if (udp_lib_checksum_complete(skb))
+ goto drop;
}
if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) {
/* Note that an ENOMEM error is charged twice */
- if (rc == -ENOMEM)
- UDP6_INC_STATS_BH(UDP_MIB_RCVBUFERRORS);
- UDP6_INC_STATS_BH(UDP_MIB_INERRORS);
- kfree_skb(skb);
- return 0;
+ if (rc == -ENOMEM) {
+ UDP6_INC_STATS_BH(sock_net(sk),
+ UDP_MIB_RCVBUFERRORS, is_udplite);
+ atomic_inc(&sk->sk_drops);
+ }
+ goto drop;
}
- UDP6_INC_STATS_BH(UDP_MIB_INDATAGRAMS);
+
return 0;
+drop:
+ UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
+ kfree_skb(skb);
+ return -1;
}
-static struct sock *udp_v6_mcast_next(struct sock *sk,
- u16 loc_port, struct in6_addr *loc_addr,
- u16 rmt_port, struct in6_addr *rmt_addr,
+static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk,
+ __be16 loc_port, struct in6_addr *loc_addr,
+ __be16 rmt_port, struct in6_addr *rmt_addr,
int dif)
{
- struct hlist_node *node;
+ struct hlist_nulls_node *node;
struct sock *s = sk;
unsigned short num = ntohs(loc_port);
- sk_for_each_from(s, node) {
+ sk_nulls_for_each_from(s, node) {
struct inet_sock *inet = inet_sk(s);
- if (inet->num == num && s->sk_family == PF_INET6) {
+ if (!net_eq(sock_net(s), net))
+ continue;
+
+ if (s->sk_hash == num && s->sk_family == PF_INET6) {
struct ipv6_pinfo *np = inet6_sk(s);
if (inet->dport) {
if (inet->dport != rmt_port)
if (!ipv6_addr_equal(&np->rcv_saddr, loc_addr))
continue;
}
- if(!inet6_mc_check(s, loc_addr, rmt_addr))
+ if (!inet6_mc_check(s, loc_addr, rmt_addr))
continue;
return s;
}
* Note: called only from the BH handler context,
* so we don't need to lock the hashes.
*/
-static void udpv6_mcast_deliver(struct udphdr *uh,
- struct in6_addr *saddr, struct in6_addr *daddr,
- struct sk_buff *skb)
+static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
+ struct in6_addr *saddr, struct in6_addr *daddr,
+ struct udp_table *udptable)
{
struct sock *sk, *sk2;
+ const struct udphdr *uh = udp_hdr(skb);
+ struct udp_hslot *hslot = &udptable->hash[udp_hashfn(net, ntohs(uh->dest))];
int dif;
- read_lock(&udp_hash_lock);
- sk = sk_head(&udp_hash[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]);
- dif = skb->dev->ifindex;
- sk = udp_v6_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif);
+ spin_lock(&hslot->lock);
+ sk = sk_nulls_head(&hslot->head);
+ dif = inet6_iif(skb);
+ sk = udp_v6_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif);
if (!sk) {
kfree_skb(skb);
goto out;
}
sk2 = sk;
- while ((sk2 = udp_v6_mcast_next(sk_next(sk2), uh->dest, daddr,
+ while ((sk2 = udp_v6_mcast_next(net, sk_nulls_next(sk2), uh->dest, daddr,
uh->source, saddr, dif))) {
struct sk_buff *buff = skb_clone(skb, GFP_ATOMIC);
- if (buff)
- udpv6_queue_rcv_skb(sk2, buff);
+ if (buff) {
+ bh_lock_sock(sk2);
+ if (!sock_owned_by_user(sk2))
+ udpv6_queue_rcv_skb(sk2, buff);
+ else
+ sk_add_backlog(sk2, buff);
+ bh_unlock_sock(sk2);
+ }
}
- udpv6_queue_rcv_skb(sk, skb);
+ bh_lock_sock(sk);
+ if (!sock_owned_by_user(sk))
+ udpv6_queue_rcv_skb(sk, skb);
+ else
+ sk_add_backlog(sk, skb);
+ bh_unlock_sock(sk);
out:
- read_unlock(&udp_hash_lock);
+ spin_unlock(&hslot->lock);
+ return 0;
+}
+
+static inline int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh,
+ int proto)
+{
+ int err;
+
+ UDP_SKB_CB(skb)->partial_cov = 0;
+ UDP_SKB_CB(skb)->cscov = skb->len;
+
+ if (proto == IPPROTO_UDPLITE) {
+ err = udplite_checksum_init(skb, uh);
+ if (err)
+ return err;
+ }
+
+ if (uh->check == 0) {
+ /* RFC 2460 section 8.1 says that we SHOULD log
+ this error. Well, it is reasonable.
+ */
+ LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0\n");
+ return 1;
+ }
+ if (skb->ip_summed == CHECKSUM_COMPLETE &&
+ !csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
+ skb->len, proto, skb->csum))
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+ if (!skb_csum_unnecessary(skb))
+ skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+ &ipv6_hdr(skb)->daddr,
+ skb->len, proto, 0));
+
+ return 0;
}
-static int udpv6_rcv(struct sk_buff **pskb)
+int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
+ int proto)
{
- struct sk_buff *skb = *pskb;
struct sock *sk;
- struct udphdr *uh;
+ struct udphdr *uh;
struct net_device *dev = skb->dev;
struct in6_addr *saddr, *daddr;
u32 ulen = 0;
+ struct net *net = dev_net(skb->dev);
if (!pskb_may_pull(skb, sizeof(struct udphdr)))
goto short_packet;
- saddr = &skb->nh.ipv6h->saddr;
- daddr = &skb->nh.ipv6h->daddr;
- uh = skb->h.uh;
+ saddr = &ipv6_hdr(skb)->saddr;
+ daddr = &ipv6_hdr(skb)->daddr;
+ uh = udp_hdr(skb);
ulen = ntohs(uh->len);
+ if (ulen > skb->len)
+ goto short_packet;
- /* Check for jumbo payload */
- if (ulen == 0)
- ulen = skb->len;
+ if (proto == IPPROTO_UDP) {
+ /* UDP validates ulen. */
- if (ulen > skb->len || ulen < sizeof(*uh))
- goto short_packet;
+ /* Check for jumbo payload */
+ if (ulen == 0)
+ ulen = skb->len;
- if (uh->check == 0) {
- /* RFC 2460 section 8.1 says that we SHOULD log
- this error. Well, it is reasonable.
- */
- LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0\n");
- goto discard;
- }
+ if (ulen < sizeof(*uh))
+ goto short_packet;
- if (ulen < skb->len) {
- if (pskb_trim_rcsum(skb, ulen))
- goto discard;
- saddr = &skb->nh.ipv6h->saddr;
- daddr = &skb->nh.ipv6h->daddr;
- uh = skb->h.uh;
+ if (ulen < skb->len) {
+ if (pskb_trim_rcsum(skb, ulen))
+ goto short_packet;
+ saddr = &ipv6_hdr(skb)->saddr;
+ daddr = &ipv6_hdr(skb)->daddr;
+ uh = udp_hdr(skb);
+ }
}
- if (skb->ip_summed == CHECKSUM_COMPLETE &&
- !csum_ipv6_magic(saddr, daddr, ulen, IPPROTO_UDP, skb->csum))
- skb->ip_summed = CHECKSUM_UNNECESSARY;
-
- if (skb->ip_summed != CHECKSUM_UNNECESSARY)
- skb->csum = ~csum_ipv6_magic(saddr, daddr, ulen, IPPROTO_UDP, 0);
+ if (udp6_csum_init(skb, uh, proto))
+ goto discard;
- /*
- * Multicast receive code
+ /*
+ * Multicast receive code
*/
- if (ipv6_addr_is_multicast(daddr)) {
- udpv6_mcast_deliver(uh, saddr, daddr, skb);
- return 0;
- }
+ if (ipv6_addr_is_multicast(daddr))
+ return __udp6_lib_mcast_deliver(net, skb,
+ saddr, daddr, udptable);
/* Unicast */
- /*
+ /*
* check socket cache ... must talk to Alan about his plans
* for sock caches... i'll skip this for now.
*/
- sk = udp_v6_lookup(saddr, uh->source, daddr, uh->dest, dev->ifindex);
+ sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
if (sk == NULL) {
if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard;
- if (skb_checksum_complete(skb))
+ if (udp_lib_checksum_complete(skb))
goto discard;
- UDP6_INC_STATS_BH(UDP_MIB_NOPORTS);
+ UDP6_INC_STATS_BH(net, UDP_MIB_NOPORTS,
+ proto == IPPROTO_UDPLITE);
icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, dev);
kfree_skb(skb);
- return(0);
+ return 0;
}
-
+
/* deliver */
-
- udpv6_queue_rcv_skb(sk, skb);
+
+ bh_lock_sock(sk);
+ if (!sock_owned_by_user(sk))
+ udpv6_queue_rcv_skb(sk, skb);
+ else
+ sk_add_backlog(sk, skb);
+ bh_unlock_sock(sk);
sock_put(sk);
- return(0);
+ return 0;
-short_packet:
- if (net_ratelimit())
- printk(KERN_DEBUG "UDP: short packet: %d/%u\n", ulen, skb->len);
+short_packet:
+ LIMIT_NETDEBUG(KERN_DEBUG "UDP%sv6: short packet: %d/%u\n",
+ proto == IPPROTO_UDPLITE ? "-Lite" : "",
+ ulen, skb->len);
discard:
- UDP6_INC_STATS_BH(UDP_MIB_INERRORS);
+ UDP6_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
kfree_skb(skb);
- return(0);
+ return 0;
+}
+
+static __inline__ int udpv6_rcv(struct sk_buff *skb)
+{
+ return __udp6_lib_rcv(skb, &udp_table, IPPROTO_UDP);
}
+
/*
* Throw away all pending data and cancel the corking. Socket is locked.
*/
{
struct udp_sock *up = udp_sk(sk);
- if (up->pending) {
+ if (up->pending == AF_INET)
+ udp_flush_pending_frames(sk);
+ else if (up->pending) {
up->len = 0;
up->pending = 0;
ip6_flush_pending_frames(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;
+ int is_udplite = IS_UDPLITE(sk);
+ __wsum csum = 0;
/* Grab the skbuff where UDP header space exists. */
if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
/*
* Create a UDP header
*/
- uh = skb->h.uh;
+ uh = udp_hdr(skb);
uh->source = fl->fl_ip_sport;
uh->dest = fl->fl_ip_dport;
uh->len = htons(up->len);
uh->check = 0;
- if (sk->sk_no_check == UDP_CSUM_NOXMIT) {
- skb->ip_summed = CHECKSUM_NONE;
- goto send;
- }
-
- if (skb_queue_len(&sk->sk_write_queue) == 1) {
- skb->csum = csum_partial((char *)uh,
- sizeof(struct udphdr), skb->csum);
- uh->check = csum_ipv6_magic(&fl->fl6_src,
- &fl->fl6_dst,
- up->len, fl->proto, skb->csum);
- } else {
- u32 tmp_csum = 0;
-
- skb_queue_walk(&sk->sk_write_queue, skb) {
- tmp_csum = csum_add(tmp_csum, skb->csum);
- }
- tmp_csum = csum_partial((char *)uh,
- sizeof(struct udphdr), tmp_csum);
- tmp_csum = csum_ipv6_magic(&fl->fl6_src,
- &fl->fl6_dst,
- up->len, fl->proto, tmp_csum);
- uh->check = tmp_csum;
+ if (is_udplite)
+ csum = udplite_csum_outgoing(sk, skb);
+ else
+ csum = udp_csum_outgoing(sk, skb);
- }
+ /* add protocol-dependent pseudo-header */
+ 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;
-send:
err = ip6_push_pending_frames(sk);
out:
up->len = 0;
up->pending = 0;
+ if (!err)
+ UDP6_INC_STATS_USER(sock_net(sk),
+ UDP_MIB_OUTDATAGRAMS, is_udplite);
return err;
}
-static int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk,
+int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg, size_t len)
{
struct ipv6_txoptions opt_space;
int corkreq = up->corkflag || msg->msg_flags&MSG_MORE;
int err;
int connected = 0;
+ int is_udplite = IS_UDPLITE(sk);
+ int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
/* destination address check */
if (sin6) {
if (sk->sk_state != TCP_ESTABLISHED)
return -EDESTADDRREQ;
daddr = &np->daddr;
- } else
+ } else
daddr = NULL;
if (daddr) {
- if (ipv6_addr_type(daddr) == IPV6_ADDR_MAPPED) {
+ if (ipv6_addr_v4mapped(daddr)) {
struct sockaddr_in sin;
sin.sin_family = AF_INET;
sin.sin_port = sin6 ? sin6->sin6_port : inet->dport;
return udp_sendmsg(iocb, sk, msg, len);
/* Rough check on arithmetic overflow,
- better check is made in ip6_build_xmit
+ better check is made in ip6_append_data().
*/
if (len > INT_MAX - sizeof(struct udphdr))
return -EMSGSIZE;
-
+
if (up->pending) {
/*
* There are pending frames.
if (!fl.oif)
fl.oif = sk->sk_bound_dev_if;
+ if (!fl.oif)
+ fl.oif = np->sticky_pktinfo.ipi6_ifindex;
+
if (msg->msg_controllen) {
opt = &opt_space;
memset(opt, 0, sizeof(struct ipv6_txoptions));
opt->tot_len = sizeof(*opt);
- err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass);
+ err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass);
if (err < 0) {
fl6_sock_release(flowlabel);
return err;
opt = fl6_merge_options(&opt_space, flowlabel, opt);
opt = ipv6_fixup_options(&opt_space, opt);
- fl.proto = IPPROTO_UDP;
- ipv6_addr_copy(&fl.fl6_dst, daddr);
+ fl.proto = sk->sk_protocol;
+ if (!ipv6_addr_any(daddr))
+ ipv6_addr_copy(&fl.fl6_dst, daddr);
+ else
+ fl.fl6_dst.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr))
ipv6_addr_copy(&fl.fl6_src, &np->saddr);
fl.fl_ip_sport = inet->sport;
-
+
/* merge ip6_build_xmit from ip6_output */
if (opt && opt->srcrt) {
struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt;
if (final_p)
ipv6_addr_copy(&fl.fl6_dst, final_p);
- if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0)
- goto out;
+ err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT);
+ if (err < 0) {
+ if (err == -EREMOTE)
+ err = ip6_dst_blackhole(sk, &dst, &fl);
+ if (err < 0)
+ goto out;
+ }
if (hlimit < 0) {
if (ipv6_addr_is_multicast(&fl.fl6_dst))
else
hlimit = np->hop_limit;
if (hlimit < 0)
- hlimit = dst_metric(dst, RTAX_HOPLIMIT);
- if (hlimit < 0)
- hlimit = ipv6_get_hoplimit(dst->dev);
+ hlimit = ip6_dst_hoplimit(dst);
}
if (tclass < 0) {
do_append_data:
up->len += ulen;
- err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov, ulen,
+ getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
+ err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen,
sizeof(struct udphdr), hlimit, tclass, opt, &fl,
(struct rt6_info*)dst,
corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
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;
} else {
dst_release(dst);
}
+ dst = NULL;
}
if (err > 0)
err = np->recverr ? net_xmit_errno(err) : 0;
release_sock(sk);
out:
+ dst_release(dst);
fl6_sock_release(flowlabel);
- if (!err) {
- UDP6_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS);
+ if (!err)
return len;
- }
/*
* ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space. Reporting
* ENOBUFS might not be good (it's not tunable per se), but otherwise
* seems like overkill.
*/
if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
- UDP6_INC_STATS_USER(UDP_MIB_SNDBUFERRORS);
+ UDP6_INC_STATS_USER(sock_net(sk),
+ UDP_MIB_SNDBUFERRORS, is_udplite);
}
return err;
goto out;
}
-static int udpv6_destroy_sock(struct sock *sk)
+void udpv6_destroy_sock(struct sock *sk)
{
lock_sock(sk);
udp_v6_flush_pending_frames(sk);
release_sock(sk);
inet6_destroy_sock(sk);
-
- return 0;
}
/*
* 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;
-
- default:
- err = -ENOPROTOOPT;
- break;
- };
-
- return err;
-}
-
-static int udpv6_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int optlen)
+int udpv6_setsockopt(struct sock *sk, int level, int optname,
+ char __user *optval, int optlen)
{
- if (level != SOL_UDP)
- return ipv6_setsockopt(sk, level, optname, optval, optlen);
- return do_udpv6_setsockopt(sk, level, optname, optval, optlen);
+ if (level == SOL_UDP || level == SOL_UDPLITE)
+ return udp_lib_setsockopt(sk, level, optname, optval, optlen,
+ udp_v6_push_pending_frames);
+ return ipv6_setsockopt(sk, level, optname, optval, optlen);
}
#ifdef CONFIG_COMPAT
-static int compat_udpv6_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int optlen)
+int compat_udpv6_setsockopt(struct sock *sk, int level, int optname,
+ char __user *optval, int optlen)
{
- if (level != SOL_UDP)
- return compat_ipv6_setsockopt(sk, level, optname,
- optval, optlen);
- return do_udpv6_setsockopt(sk, level, optname, optval, optlen);
+ if (level == SOL_UDP || level == SOL_UDPLITE)
+ 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)
+int 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;
-
- default:
- return -ENOPROTOOPT;
- };
-
- if(put_user(len, optlen))
- return -EFAULT;
- if(copy_to_user(optval, &val,len))
- return -EFAULT;
- return 0;
-}
-
-static int udpv6_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen)
-{
- if (level != SOL_UDP)
- return ipv6_getsockopt(sk, level, optname, optval, optlen);
- return do_udpv6_getsockopt(sk, level, optname, optval, optlen);
+ if (level == SOL_UDP || level == SOL_UDPLITE)
+ return udp_lib_getsockopt(sk, level, optname, optval, optlen);
+ return ipv6_getsockopt(sk, level, optname, optval, optlen);
}
#ifdef CONFIG_COMPAT
-static int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen)
+int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
+ char __user *optval, int __user *optlen)
{
- if (level != SOL_UDP)
- return compat_ipv6_getsockopt(sk, level, optname,
- optval, optlen);
- return do_udpv6_getsockopt(sk, level, optname, optval, optlen);
+ if (level == SOL_UDP || level == SOL_UDPLITE)
+ return udp_lib_getsockopt(sk, level, optname, optval, optlen);
+ return compat_ipv6_getsockopt(sk, level, optname, optval, optlen);
}
#endif
srcp = ntohs(inet->sport);
seq_printf(seq,
"%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
- "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p\n",
+ "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n",
bucket,
src->s6_addr32[0], src->s6_addr32[1],
src->s6_addr32[2], src->s6_addr32[3], srcp,
dest->s6_addr32[0], dest->s6_addr32[1],
dest->s6_addr32[2], dest->s6_addr32[3], destp,
- sp->sk_state,
+ sp->sk_state,
atomic_read(&sp->sk_wmem_alloc),
atomic_read(&sp->sk_rmem_alloc),
0, 0L, 0,
sock_i_uid(sp), 0,
sock_i_ino(sp),
- atomic_read(&sp->sk_refcnt), sp);
+ atomic_read(&sp->sk_refcnt), sp,
+ atomic_read(&sp->sk_drops));
}
-static int udp6_seq_show(struct seq_file *seq, void *v)
+int udp6_seq_show(struct seq_file *seq, void *v)
{
if (v == SEQ_START_TOKEN)
seq_printf(seq,
"local_address "
"remote_address "
"st tx_queue rx_queue tr tm->when retrnsmt"
- " uid timeout inode\n");
+ " uid timeout inode ref pointer drops\n");
else
udp6_sock_seq_show(seq, v, ((struct udp_iter_state *)seq->private)->bucket);
return 0;
}
-static struct file_operations udp6_seq_fops;
static struct udp_seq_afinfo udp6_seq_afinfo = {
- .owner = THIS_MODULE,
.name = "udp6",
.family = AF_INET6,
- .seq_show = udp6_seq_show,
- .seq_fops = &udp6_seq_fops,
+ .udp_table = &udp_table,
+ .seq_fops = {
+ .owner = THIS_MODULE,
+ },
+ .seq_ops = {
+ .show = udp6_seq_show,
+ },
};
-int __init udp6_proc_init(void)
+int udp6_proc_init(struct net *net)
{
- return udp_proc_register(&udp6_seq_afinfo);
+ return udp_proc_register(net, &udp6_seq_afinfo);
}
-void udp6_proc_exit(void) {
- udp_proc_unregister(&udp6_seq_afinfo);
+void udp6_proc_exit(struct net *net) {
+ udp_proc_unregister(net, &udp6_seq_afinfo);
}
#endif /* CONFIG_PROC_FS */
struct proto udpv6_prot = {
.name = "UDPv6",
.owner = THIS_MODULE,
- .close = udpv6_close,
+ .close = udp_lib_close,
.connect = ip6_datagram_connect,
.disconnect = udp_disconnect,
.ioctl = udp_ioctl,
.sendmsg = udpv6_sendmsg,
.recvmsg = udpv6_recvmsg,
.backlog_rcv = udpv6_queue_rcv_skb,
- .hash = udp_v6_hash,
- .unhash = udp_v6_unhash,
+ .hash = udp_lib_hash,
+ .unhash = udp_lib_unhash,
.get_port = udp_v6_get_port,
+ .memory_allocated = &udp_memory_allocated,
+ .sysctl_mem = sysctl_udp_mem,
+ .sysctl_wmem = &sysctl_udp_wmem_min,
+ .sysctl_rmem = &sysctl_udp_rmem_min,
.obj_size = sizeof(struct udp6_sock),
+ .slab_flags = SLAB_DESTROY_BY_RCU,
+ .h.udp_table = &udp_table,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_udpv6_setsockopt,
.compat_getsockopt = compat_udpv6_getsockopt,
};
-void __init udpv6_init(void)
+int __init udpv6_init(void)
+{
+ int ret;
+
+ ret = inet6_add_protocol(&udpv6_protocol, IPPROTO_UDP);
+ if (ret)
+ goto out;
+
+ ret = inet6_register_protosw(&udpv6_protosw);
+ if (ret)
+ goto out_udpv6_protocol;
+out:
+ return ret;
+
+out_udpv6_protocol:
+ inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP);
+ goto out;
+}
+
+void udpv6_exit(void)
{
- if (inet6_add_protocol(&udpv6_protocol, IPPROTO_UDP) < 0)
- printk(KERN_ERR "udpv6_init: Could not register protocol\n");
- inet6_register_protosw(&udpv6_protosw);
+ inet6_unregister_protosw(&udpv6_protosw);
+ inet6_del_protocol(&udpv6_protocol, IPPROTO_UDP);
}