summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/Kconfig10
-rw-r--r--net/ipv4/Makefile3
-rw-r--r--net/ipv4/af_inet.c19
-rw-r--r--net/ipv4/arp.c9
-rw-r--r--net/ipv4/devinet.c21
-rw-r--r--net/ipv4/icmp.c101
-rw-r--r--net/ipv4/igmp.c39
-rw-r--r--net/ipv4/inet_connection_sock.c2
-rw-r--r--net/ipv4/ip_options.c5
-rw-r--r--net/ipv4/ipconfig.c7
-rw-r--r--net/ipv4/netfilter/arp_tables.c5
-rw-r--r--net/ipv4/netfilter/ipt_MASQUERADE.c14
-rw-r--r--net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c2
-rw-r--r--net/ipv4/proc.c5
-rw-r--r--net/ipv4/route.c75
-rw-r--r--net/ipv4/syncookies.c11
-rw-r--r--net/ipv4/tcp_cubic.c35
-rw-r--r--net/ipv4/tcp_input.c1
-rw-r--r--net/ipv4/tcp_ipv4.c30
-rw-r--r--net/ipv4/tcp_minisocks.c4
-rw-r--r--net/ipv4/tcp_output.c1
-rw-r--r--net/ipv4/udp.c1090
-rw-r--r--net/ipv4/udp_ipv4.c1134
-rw-r--r--net/ipv4/udplite_ipv4.c (renamed from net/ipv4/udplite.c)0
24 files changed, 1381 insertions, 1242 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 9c7e5ffb223..5098fd2ff4d 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -632,5 +632,15 @@ config TCP_MD5SIG
If unsure, say N.
+config IP_UDPLITE
+ bool "IP: UDP-Lite Protocol (RFC 3828)"
+ default n
+ ---help---
+ UDP-Lite (RFC 3828) is a UDP-like protocol with variable-length
+ checksum. Read <file:Documentation/networking/udplite.txt> for
+ details.
+
+ If unsure, say N.
+
source "net/ipv4/ipvs/Kconfig"
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index ad40ef3f9eb..d5226241d5e 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -8,7 +8,7 @@ obj-y := route.o inetpeer.o protocol.o \
inet_timewait_sock.o inet_connection_sock.o \
tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \
tcp_minisocks.o tcp_cong.o \
- datagram.o raw.o udp.o udplite.o \
+ datagram.o raw.o udp.o udp_ipv4.o \
arp.o icmp.o devinet.o af_inet.o igmp.o \
fib_frontend.o fib_semantics.o \
inet_fragment.o
@@ -49,6 +49,7 @@ obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o
obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o
obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o
obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o
+obj-$(CONFIG_IP_UDPLITE) += udplite_ipv4.o
obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 09ca5293d08..67260c0eaaa 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -784,6 +784,7 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
struct sock *sk = sock->sk;
int err = 0;
+ struct net *net = sk->sk_net;
switch (cmd) {
case SIOCGSTAMP:
@@ -795,12 +796,12 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
case SIOCADDRT:
case SIOCDELRT:
case SIOCRTMSG:
- err = ip_rt_ioctl(sk->sk_net, cmd, (void __user *)arg);
+ err = ip_rt_ioctl(net, cmd, (void __user *)arg);
break;
case SIOCDARP:
case SIOCGARP:
case SIOCSARP:
- err = arp_ioctl(sk->sk_net, cmd, (void __user *)arg);
+ err = arp_ioctl(net, cmd, (void __user *)arg);
break;
case SIOCGIFADDR:
case SIOCSIFADDR:
@@ -813,7 +814,7 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
case SIOCSIFPFLAGS:
case SIOCGIFPFLAGS:
case SIOCSIFFLAGS:
- err = devinet_ioctl(cmd, (void __user *)arg);
+ err = devinet_ioctl(net, cmd, (void __user *)arg);
break;
default:
if (sk->sk_prot->ioctl)
@@ -1316,15 +1317,18 @@ static int __init init_ipv4_mibs(void)
if (snmp_mib_init((void **)udp_statistics,
sizeof(struct udp_mib)) < 0)
goto err_udp_mib;
+#ifdef CONFIG_IP_UDPLITE
if (snmp_mib_init((void **)udplite_statistics,
sizeof(struct udp_mib)) < 0)
goto err_udplite_mib;
-
+#endif
tcp_mib_init();
return 0;
+#ifdef CONFIG_IP_UDPLITE
err_udplite_mib:
+#endif
snmp_mib_free((void **)udp_statistics);
err_udp_mib:
snmp_mib_free((void **)tcp_statistics);
@@ -1414,7 +1418,7 @@ static int __init inet_init(void)
ip_init();
- tcp_v4_init(&inet_family_ops);
+ tcp_v4_init();
/* Setup TCP slab cache for open requests. */
tcp_init();
@@ -1422,14 +1426,17 @@ static int __init inet_init(void)
/* Setup UDP memory threshold */
udp_init();
+#ifdef CONFIG_IP_UDPLITE
/* Add UDP-Lite (RFC 3828) */
udplite4_register();
+#endif
/*
* Set the ICMP layer up
*/
- icmp_init(&inet_family_ops);
+ if (icmp_init() < 0)
+ panic("Failed to create the ICMP control socket.\n");
/*
* Initialise the multicast router
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 8e17f65f400..69e80bd9774 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -570,14 +570,13 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip,
* Allocate a buffer
*/
- skb = alloc_skb(sizeof(struct arphdr)+ 2*(dev->addr_len+4)
- + LL_RESERVED_SPACE(dev), GFP_ATOMIC);
+ skb = alloc_skb(arp_hdr_len(dev) + LL_RESERVED_SPACE(dev), GFP_ATOMIC);
if (skb == NULL)
return NULL;
skb_reserve(skb, LL_RESERVED_SPACE(dev));
skb_reset_network_header(skb);
- arp = (struct arphdr *) skb_put(skb,sizeof(struct arphdr) + 2*(dev->addr_len+4));
+ arp = (struct arphdr *) skb_put(skb, arp_hdr_len(dev));
skb->dev = dev;
skb->protocol = htons(ETH_P_ARP);
if (src_hw == NULL)
@@ -916,9 +915,7 @@ static int arp_rcv(struct sk_buff *skb, struct net_device *dev,
goto freeskb;
/* ARP header, plus 2 device addresses, plus 2 IP addresses. */
- if (!pskb_may_pull(skb, (sizeof(struct arphdr) +
- (2 * dev->addr_len) +
- (2 * sizeof(u32)))))
+ if (!pskb_may_pull(skb, arp_hdr_len(dev)))
goto freeskb;
arp = arp_hdr(skb);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 87490f7bb0f..4a10dbbbe0a 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -446,9 +446,6 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg
ASSERT_RTNL();
- if (net != &init_net)
- return -EINVAL;
-
err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy);
if (err < 0)
goto errout;
@@ -560,9 +557,6 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg
ASSERT_RTNL();
- if (net != &init_net)
- return -EINVAL;
-
ifa = rtm_to_ifaddr(net, nlh);
if (IS_ERR(ifa))
return PTR_ERR(ifa);
@@ -595,7 +589,7 @@ static __inline__ int inet_abc_len(__be32 addr)
}
-int devinet_ioctl(unsigned int cmd, void __user *arg)
+int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
{
struct ifreq ifr;
struct sockaddr_in sin_orig;
@@ -624,7 +618,7 @@ int devinet_ioctl(unsigned int cmd, void __user *arg)
*colon = 0;
#ifdef CONFIG_KMOD
- dev_load(&init_net, ifr.ifr_name);
+ dev_load(net, ifr.ifr_name);
#endif
switch (cmd) {
@@ -665,7 +659,7 @@ int devinet_ioctl(unsigned int cmd, void __user *arg)
rtnl_lock();
ret = -ENODEV;
- if ((dev = __dev_get_by_name(&init_net, ifr.ifr_name)) == NULL)
+ if ((dev = __dev_get_by_name(net, ifr.ifr_name)) == NULL)
goto done;
if (colon)
@@ -878,6 +872,7 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope)
{
__be32 addr = 0;
struct in_device *in_dev;
+ struct net *net = dev->nd_net;
rcu_read_lock();
in_dev = __in_dev_get_rcu(dev);
@@ -906,7 +901,7 @@ no_in_dev:
*/
read_lock(&dev_base_lock);
rcu_read_lock();
- for_each_netdev(&init_net, dev) {
+ for_each_netdev(net, dev) {
if ((in_dev = __in_dev_get_rcu(dev)) == NULL)
continue;
@@ -1045,9 +1040,6 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
struct net_device *dev = ptr;
struct in_device *in_dev = __in_dev_get_rtnl(dev);
- if (dev->nd_net != &init_net)
- return NOTIFY_DONE;
-
ASSERT_RTNL();
if (!in_dev) {
@@ -1173,9 +1165,6 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
struct in_ifaddr *ifa;
int s_ip_idx, s_idx = cb->args[0];
- if (net != &init_net)
- return 0;
-
s_ip_idx = ip_idx = cb->args[1];
idx = 0;
for_each_netdev(net, dev) {
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index a13c074dac0..cee77d606fb 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -229,14 +229,16 @@ static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1];
*
* On SMP we have one ICMP socket per-cpu.
*/
-static DEFINE_PER_CPU(struct socket *, __icmp_socket) = NULL;
-#define icmp_socket __get_cpu_var(__icmp_socket)
+static struct sock *icmp_sk(struct net *net)
+{
+ return net->ipv4.icmp_sk[smp_processor_id()];
+}
-static inline int icmp_xmit_lock(void)
+static inline int icmp_xmit_lock(struct sock *sk)
{
local_bh_disable();
- if (unlikely(!spin_trylock(&icmp_socket->sk->sk_lock.slock))) {
+ if (unlikely(!spin_trylock(&sk->sk_lock.slock))) {
/* This can happen if the output path signals a
* dst_link_failure() for an outgoing ICMP packet.
*/
@@ -246,9 +248,9 @@ static inline int icmp_xmit_lock(void)
return 0;
}
-static inline void icmp_xmit_unlock(void)
+static inline void icmp_xmit_unlock(struct sock *sk)
{
- spin_unlock_bh(&icmp_socket->sk->sk_lock.slock);
+ spin_unlock_bh(&sk->sk_lock.slock);
}
/*
@@ -346,19 +348,21 @@ static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd,
static void icmp_push_reply(struct icmp_bxm *icmp_param,
struct ipcm_cookie *ipc, struct rtable *rt)
{
+ struct sock *sk;
struct sk_buff *skb;
- if (ip_append_data(icmp_socket->sk, icmp_glue_bits, icmp_param,
+ sk = icmp_sk(rt->u.dst.dev->nd_net);
+ if (ip_append_data(sk, icmp_glue_bits, icmp_param,
icmp_param->data_len+icmp_param->head_len,
icmp_param->head_len,
ipc, rt, MSG_DONTWAIT) < 0)
- ip_flush_pending_frames(icmp_socket->sk);
- else if ((skb = skb_peek(&icmp_socket->sk->sk_write_queue)) != NULL) {
+ ip_flush_pending_frames(sk);
+ else if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) {
struct icmphdr *icmph = icmp_hdr(skb);
__wsum csum = 0;
struct sk_buff *skb1;
- skb_queue_walk(&icmp_socket->sk->sk_write_queue, skb1) {
+ skb_queue_walk(&sk->sk_write_queue, skb1) {
csum = csum_add(csum, skb1->csum);
}
csum = csum_partial_copy_nocheck((void *)&icmp_param->data,
@@ -366,7 +370,7 @@ static void icmp_push_reply(struct icmp_bxm *icmp_param,
icmp_param->head_len, csum);
icmph->checksum = csum_fold(csum);
skb->ip_summed = CHECKSUM_NONE;
- ip_push_pending_frames(icmp_socket->sk);
+ ip_push_pending_frames(sk);
}
}
@@ -376,16 +380,17 @@ static void icmp_push_reply(struct icmp_bxm *icmp_param,
static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
{
- struct sock *sk = icmp_socket->sk;
- struct inet_sock *inet = inet_sk(sk);
struct ipcm_cookie ipc;
struct rtable *rt = (struct rtable *)skb->dst;
+ struct net *net = rt->u.dst.dev->nd_net;
+ struct sock *sk = icmp_sk(net);
+ struct inet_sock *inet = inet_sk(sk);
__be32 daddr;
if (ip_options_echo(&icmp_param->replyopts, skb))
return;
- if (icmp_xmit_lock())
+ if (icmp_xmit_lock(sk))
return;
icmp_param->data.icmph.checksum = 0;
@@ -405,7 +410,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
.tos = RT_TOS(ip_hdr(skb)->tos) } },
.proto = IPPROTO_ICMP };
security_skb_classify_flow(skb, &fl);
- if (ip_route_output_key(rt->u.dst.dev->nd_net, &rt, &fl))
+ if (ip_route_output_key(net, &rt, &fl))
goto out_unlock;
}
if (icmpv4_xrlim_allow(rt, icmp_param->data.icmph.type,
@@ -413,7 +418,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
icmp_push_reply(icmp_param, &ipc, rt);
ip_rt_put(rt);
out_unlock:
- icmp_xmit_unlock();
+ icmp_xmit_unlock(sk);
}
@@ -438,10 +443,12 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
__be32 saddr;
u8 tos;
struct net *net;
+ struct sock *sk;
if (!rt)
goto out;
net = rt->u.dst.dev->nd_net;
+ sk = icmp_sk(net);
/*
* Find the original header. It is expected to be valid, of course.
@@ -505,7 +512,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
}
}
- if (icmp_xmit_lock())
+ if (icmp_xmit_lock(sk))
return;
/*
@@ -544,7 +551,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
icmp_param.data.icmph.checksum = 0;
icmp_param.skb = skb_in;
icmp_param.offset = skb_network_offset(skb_in);
- inet_sk(icmp_socket->sk)->tos = tos;
+ inet_sk(sk)->tos = tos;
ipc.addr = iph->saddr;
ipc.opt = &icmp_param.replyopts;
@@ -652,7 +659,7 @@ route_done:
ende:
ip_rt_put(rt);
out_unlock:
- icmp_xmit_unlock();
+ icmp_xmit_unlock(sk);
out:;
}
@@ -1139,29 +1146,46 @@ static const struct icmp_control icmp_pointers[NR_ICMP_TYPES + 1] = {
},
};
-void __init icmp_init(struct net_proto_family *ops)
+static void __net_exit icmp_sk_exit(struct net *net)
{
- struct inet_sock *inet;
int i;
- for_each_possible_cpu(i) {
- int err;
+ for_each_possible_cpu(i)
+ sk_release_kernel(net->ipv4.icmp_sk[i]);
+ kfree(net->ipv4.icmp_sk);
+ net->ipv4.icmp_sk = NULL;
+}
- err = sock_create_kern(PF_INET, SOCK_RAW, IPPROTO_ICMP,
- &per_cpu(__icmp_socket, i));
+int __net_init icmp_sk_init(struct net *net)
+{
+ int i, err;
+ net->ipv4.icmp_sk =
+ kzalloc(nr_cpu_ids * sizeof(struct sock *), GFP_KERNEL);
+ if (net->ipv4.icmp_sk == NULL)
+ return -ENOMEM;
+
+ for_each_possible_cpu(i) {
+ struct sock *sk;
+ struct socket *sock;
+ struct inet_sock *inet;
+
+ err = sock_create_kern(PF_INET, SOCK_RAW, IPPROTO_ICMP, &sock);
if (err < 0)
- panic("Failed to create the ICMP control socket.\n");
+ goto fail;
+
+ net->ipv4.icmp_sk[i] = sk = sock->sk;
+ sk_change_net(sk, net);
- per_cpu(__icmp_socket, i)->sk->sk_allocation = GFP_ATOMIC;
+ sk->sk_allocation = GFP_ATOMIC;
/* Enough space for 2 64K ICMP packets, including
* sk_buff struct overhead.
*/
- per_cpu(__icmp_socket, i)->sk->sk_sndbuf =
+ sk->sk_sndbuf =
(2 * ((64 * 1024) + sizeof(struct sk_buff)));
- inet = inet_sk(per_cpu(__icmp_socket, i)->sk);
+ inet = inet_sk(sk);
inet->uc_ttl = -1;
inet->pmtudisc = IP_PMTUDISC_DONT;
@@ -1169,8 +1193,25 @@ void __init icmp_init(struct net_proto_family *ops)
* see it, we do not wish this socket to see incoming
* packets.
*/
- per_cpu(__icmp_socket, i)->sk->sk_prot->unhash(per_cpu(__icmp_socket, i)->sk);
+ sk->sk_prot->unhash(sk);
}
+ return 0;
+
+fail:
+ for_each_possible_cpu(i)
+ sk_release_kernel(net->ipv4.icmp_sk[i]);
+ kfree(net->ipv4.icmp_sk);
+ return err;
+}
+
+static struct pernet_operations __net_initdata icmp_sk_ops = {
+ .init = icmp_sk_init,
+ .exit = icmp_sk_exit,
+};
+
+int __init icmp_init(void)
+{
+ return register_pernet_device(&icmp_sk_ops);
}
EXPORT_SYMBOL(icmp_err_convert);
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 732cd07e607..d3f34a772f3 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1198,6 +1198,9 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
ASSERT_RTNL();
+ if (in_dev->dev->nd_net != &init_net)
+ return;
+
for (im=in_dev->mc_list; im; im=im->next) {
if (im->multiaddr == addr) {
im->users++;
@@ -1277,6 +1280,9 @@ void ip_mc_dec_group(struct in_device *in_dev, __be32 addr)
ASSERT_RTNL();
+ if (in_dev->dev->nd_net != &init_net)
+ return;
+
for (ip=&in_dev->mc_list; (i=*ip)!=NULL; ip=&i->next) {
if (i->multiaddr==addr) {
if (--i->users == 0) {
@@ -1304,6 +1310,9 @@ void ip_mc_down(struct in_device *in_dev)
ASSERT_RTNL();
+ if (in_dev->dev->nd_net != &init_net)
+ return;
+
for (i=in_dev->mc_list; i; i=i->next)
igmp_group_dropped(i);
@@ -1324,6 +1333,9 @@ void ip_mc_init_dev(struct in_device *in_dev)
{
ASSERT_RTNL();
+ if (in_dev->dev->nd_net != &init_net)
+ return;
+
in_dev->mc_tomb = NULL;
#ifdef CONFIG_IP_MULTICAST
in_dev->mr_gq_running = 0;
@@ -1347,6 +1359,9 @@ void ip_mc_up(struct in_device *in_dev)
ASSERT_RTNL();
+ if (in_dev->dev->nd_net != &init_net)
+ return;
+
ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS);
for (i=in_dev->mc_list; i; i=i->next)
@@ -1363,6 +1378,9 @@ void ip_mc_destroy_dev(struct in_device *in_dev)
ASSERT_RTNL();
+ if (in_dev->dev->nd_net != &init_net)
+ return;
+
/* Deactivate timers */
ip_mc_down(in_dev);
@@ -1744,6 +1762,9 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr)
if (!ipv4_is_multicast(addr))
return -EINVAL;
+ if (sk->sk_net != &init_net)
+ return -EPROTONOSUPPORT;
+
rtnl_lock();
in_dev = ip_mc_find_dev(imr);
@@ -1812,6 +1833,9 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr)
u32 ifindex;
int ret = -EADDRNOTAVAIL;
+ if (sk->sk_net != &init_net)
+ return -EPROTONOSUPPORT;
+
rtnl_lock();
in_dev = ip_mc_find_dev(imr);
ifindex = imr->imr_ifindex;
@@ -1857,6 +1881,9 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct
if (!ipv4_is_multicast(addr))
return -EINVAL;
+ if (sk->sk_net != &init_net)
+ return -EPROTONOSUPPORT;
+
rtnl_lock();
imr.imr_multiaddr.s_addr = mreqs->imr_multiaddr;
@@ -1990,6 +2017,9 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex)
msf->imsf_fmode != MCAST_EXCLUDE)
return -EINVAL;
+ if (sk->sk_net != &init_net)
+ return -EPROTONOSUPPORT;
+
rtnl_lock();
imr.imr_multiaddr.s_addr = msf->imsf_multiaddr;
@@ -2070,6 +2100,9 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf,
if (!ipv4_is_multicast(addr))
return -EINVAL;
+ if (sk->sk_net != &init_net)
+ return -EPROTONOSUPPORT;
+
rtnl_lock();
imr.imr_multiaddr.s_addr = msf->imsf_multiaddr;
@@ -2132,6 +2165,9 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf,
if (!ipv4_is_multicast(addr))
return -EINVAL;
+ if (sk->sk_net != &init_net)
+ return -EPROTONOSUPPORT;
+
rtnl_lock();
err = -EADDRNOTAVAIL;
@@ -2216,6 +2252,9 @@ void ip_mc_drop_socket(struct sock *sk)
if (inet->mc_list == NULL)
return;
+ if (sk->sk_net != &init_net)
+ return;
+
rtnl_lock();
while ((iml = inet->mc_list) != NULL) {
struct in_device *in_dev;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b189278c7bc..c0e0fa03fce 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -463,7 +463,7 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
if (time_after_eq(now, req->expires)) {
if ((req->retrans < thresh ||
(inet_rsk(req)->acked && req->retrans < max_retries))
- && !req->rsk_ops->rtx_syn_ack(parent, req, NULL)) {
+ && !req->rsk_ops->rtx_syn_ack(parent, req)) {
unsigned long timeo;
if (req->retrans++ == 0)
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 4d315158fd3..baaedd9689a 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -107,10 +107,7 @@ int ip_options_echo(struct ip_options * dopt, struct sk_buff * skb)
sptr = skb_network_header(skb);
dptr = dopt->__data;
- if (skb->dst)
- daddr = ((struct rtable*)skb->dst)->rt_spec_dst;
- else
- daddr = ip_hdr(skb)->daddr;
+ daddr = ((struct rtable*)skb->dst)->rt_spec_dst;
if (sopt->rr) {
optlen = sptr[sopt->rr+1];
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 5dd938579ee..4afce057280 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -291,7 +291,7 @@ static int __init ic_dev_ioctl(unsigned int cmd, struct ifreq *arg)
mm_segment_t oldfs = get_fs();
set_fs(get_ds());
- res = devinet_ioctl(cmd, (struct ifreq __user *) arg);
+ res = devinet_ioctl(&init_net, cmd, (struct ifreq __user *) arg);
set_fs(oldfs);
return res;
}
@@ -459,10 +459,7 @@ ic_rarp_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
if (rarp->ar_pro != htons(ETH_P_IP))
goto drop;
- if (!pskb_may_pull(skb,
- sizeof(struct arphdr) +
- (2 * dev->addr_len) +
- (2 * 4)))
+ if (!pskb_may_pull(skb, arp_hdr_len(dev)))
goto drop;
/* OK, it is all there and looks valid, process... */
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index a7591ce344d..9b590448618 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -233,10 +233,7 @@ unsigned int arpt_do_table(struct sk_buff *skb,
void *table_base;
struct xt_table_info *private;
- /* ARP header, plus 2 device addresses, plus 2 IP addresses. */
- if (!pskb_may_pull(skb, (sizeof(struct arphdr) +
- (2 * skb->dev->addr_len) +
- (2 * sizeof(u32)))))
+ if (!pskb_may_pull(skb, arp_hdr_len(skb->dev)))
return NF_DROP;
indev = in ? in->name : nulldevname;
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index d80fee8327e..313b3fcf387 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -139,18 +139,8 @@ static int masq_inet_event(struct notifier_block *this,
unsigned long event,
void *ptr)
{
- const struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev;
-
- if (event == NETDEV_DOWN) {
- /* IP address was deleted. Search entire table for
- conntracks which were associated with that device,
- and forget them. */
- NF_CT_ASSERT(dev->ifindex != 0);
-
- nf_ct_iterate_cleanup(device_cmp, (void *)(long)dev->ifindex);
- }
-
- return NOTIFY_DONE;
+ struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev;
+ return masq_device_event(this, event, dev);
}
static struct notifier_block masq_dev_notifier = {
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index 089252e82c0..9668c3a23ef 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -379,7 +379,7 @@ static const struct file_operations ct_cpu_seq_fops = {
.open = ct_cpu_seq_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = seq_release,
};
int __init nf_conntrack_ipv4_compat_init(void)
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index d63474c6b40..d75ddb7fa4b 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -59,7 +59,9 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
atomic_read(&tcp_memory_allocated));
seq_printf(seq, "UDP: inuse %d mem %d\n", sock_prot_inuse_get(&udp_prot),
atomic_read(&udp_memory_allocated));
+#ifdef CONFIG_IP_UDPLITE
seq_printf(seq, "UDPLITE: inuse %d\n", sock_prot_inuse_get(&udplite_prot));
+#endif
seq_printf(seq, "RAW: inuse %d\n", sock_prot_inuse_get(&raw_prot));
seq_printf(seq, "FRAG: inuse %d memory %d\n",
ip_frag_nqueues(&init_net), ip_frag_mem(&init_net));
@@ -349,6 +351,7 @@ static int snmp_seq_show(struct seq_file *seq, void *v)
snmp_fold_field((void **)udp_statistics,
snmp4_udp_list[i].entry));
+#ifdef CONFIG_IP_UDPLITE
/* the UDP and UDP-Lite MIBs are the same */
seq_puts(seq, "\nUdpLite:");
for (i = 0; snmp4_udp_list[i].name != NULL; i++)
@@ -359,7 +362,7 @@ static int snmp_seq_show(struct seq_file *seq, void *v)
seq_printf(seq, " %lu",
snmp_fold_field((void **)udplite_statistics,
snmp4_udp_list[i].entry));
-
+#endif
seq_putc(seq, '\n');
return 0;
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 7b5e8e1d94b..8c3e165f003 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -273,6 +273,7 @@ static unsigned int rt_hash_code(u32 daddr, u32 saddr)
#ifdef CONFIG_PROC_FS
struct rt_cache_iter_state {
+ struct seq_net_private p;
int bucket;
int genid;
};
@@ -285,7 +286,8 @@ static struct rtable *rt_cache_get_first(struct rt_cache_iter_state *st)
rcu_read_lock_bh();
r = rcu_dereference(rt_hash_table[st->bucket].chain);
while (r) {
- if (r->rt_genid == st->genid)
+ if (r->u.dst.dev->nd_net == st->p.net &&
+ r->rt_genid == st->genid)
return r;
r = rcu_dereference(r->u.dst.rt_next);
}
@@ -294,7 +296,8 @@ static struct rtable *rt_cache_get_first(struct rt_cache_iter_state *st)
return r;
}
-static struct rtable *rt_cache_get_next(struct rt_cache_iter_state *st, struct rtable *r)
+static struct rtable *__rt_cache_get_next(struct rt_cache_iter_state *st,
+ struct rtable *r)
{
r = r->u.dst.rt_next;
while (!r) {
@@ -307,16 +310,25 @@ static struct rtable *rt_cache_get_next(struct rt_cache_iter_state *st, struct r
return rcu_dereference(r);
}
+static struct rtable *rt_cache_get_next(struct rt_cache_iter_state *st,
+ struct rtable *r)
+{
+ while ((r = __rt_cache_get_next(st, r)) != NULL) {
+ if (r->u.dst.dev->nd_net != st->p.net)
+ continue;
+ if (r->rt_genid == st->genid)
+ break;
+ }
+ return r;
+}
+
static struct rtable *rt_cache_get_idx(struct rt_cache_iter_state *st, loff_t pos)
{
struct rtable *r = rt_cache_get_first(st);
if (r)
- while (pos && (r = rt_cache_get_next(st, r))) {
- if (r->rt_genid != st->genid)
- continue;
+ while (pos && (r = rt_cache_get_next(st, r)))
--pos;
- }
return pos ? NULL : r;
}
@@ -390,7 +402,7 @@ static const struct seq_operations rt_cache_seq_ops = {
static int rt_cache_seq_open(struct inode *inode, struct file *file)
{
- return seq_open_private(file, &rt_cache_seq_ops,
+ return seq_open_net(inode, file, &rt_cache_seq_ops,
sizeof(struct rt_cache_iter_state));
}
@@ -399,7 +411,7 @@ static const struct file_operations rt_cache_seq_fops = {
.open = rt_cache_seq_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
+ .release = seq_release_net,
};
@@ -533,7 +545,7 @@ static int ip_rt_acct_read(char *buffer, char **start, off_t offset,
}
#endif
-static __init int ip_rt_proc_init(struct net *net)
+static int __net_init ip_rt_do_proc_init(struct net *net)
{
struct proc_dir_entry *pde;
@@ -564,8 +576,26 @@ err2:
err1:
return -ENOMEM;
}
+
+static void __net_exit ip_rt_do_proc_exit(struct net *net)
+{
+ remove_proc_entry("rt_cache", net->proc_net_stat);
+ remove_proc_entry("rt_cache", net->proc_net);
+ remove_proc_entry("rt_acct", net->proc_net);
+}
+
+static struct pernet_operations ip_rt_proc_ops __net_initdata = {
+ .init = ip_rt_do_proc_init,
+ .exit = ip_rt_do_proc_exit,
+};
+
+static int __init ip_rt_proc_init(void)
+{
+ return register_pernet_subsys(&ip_rt_proc_ops);
+}
+
#else
-static inline int ip_rt_proc_init(struct net *net)
+static inline int ip_rt_proc_init(void)
{
return 0;
}
@@ -1131,10 +1161,12 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
__be32 skeys[2] = { saddr, 0 };
int ikeys[2] = { dev->ifindex, 0 };
struct netevent_redirect netevent;
+ struct net *net;
if (!in_dev)
return;
+ net = dev->nd_net;
if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev)
|| ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw)
|| ipv4_is_zeronet(new_gw))
@@ -1146,7 +1178,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
if (IN_DEV_SEC_REDIRECTS(in_dev) && ip_fib_check_default(new_gw, dev))
goto reject_redirect;
} else {
- if (inet_addr_type(&init_net, new_gw) != RTN_UNICAST)
+ if (inet_addr_type(net, new_gw) != RTN_UNICAST)
goto reject_redirect;
}
@@ -1164,7 +1196,8 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
rth->fl.fl4_src != skeys[i] ||
rth->fl.oif != ikeys[k] ||
rth->fl.iif != 0 ||
- rth->rt_genid != atomic_read(&rt_genid)) {
+ rth->rt_genid != atomic_read(&rt_genid) ||
+ rth->u.dst.dev->nd_net != net) {
rthp = &rth->u.dst.rt_next;
continue;
}
@@ -2668,9 +2701,6 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
int err;
struct sk_buff *skb;
- if (net != &init_net)
- return -EINVAL;
-
err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy);
if (err < 0)
goto errout;
@@ -2700,7 +2730,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
if (iif) {
struct net_device *dev;
- dev = __dev_get_by_index(&init_net, iif);
+ dev = __dev_get_by_index(net, iif);
if (dev == NULL) {
err = -ENODEV;
goto errout_free;
@@ -2726,7 +2756,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
},
.oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0,
};
- err = ip_route_output_key(&init_net, &rt, &fl);
+ err = ip_route_output_key(net, &rt, &fl);
}
if (err)
@@ -2737,11 +2767,11 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
rt->rt_flags |= RTCF_NOTIFY;
err = rt_fill_info(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq,
- RTM_NEWROUTE, 0, 0);
+ RTM_NEWROUTE, 0, 0);
if (err <= 0)
goto errout_free;
- err = rtnl_unicast(skb, &init_net, NETLINK_CB(in_skb).pid);
+ err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid);
errout:
return err;
@@ -2755,6 +2785,9 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb)
struct rtable *rt;
int h, s_h;
int idx, s_idx;
+ struct net *net;
+
+ net = skb->sk->sk_net;
s_h = cb->args[0];
if (s_h < 0)
@@ -2764,7 +2797,7 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb)
rcu_read_lock_bh();
for (rt = rcu_dereference(rt_hash_table[h].chain), idx = 0; rt;
rt = rcu_dereference(rt->u.dst.rt_next), idx++) {
- if (idx < s_idx)
+ if (rt->u.dst.dev->nd_net != net || idx < s_idx)
continue;
if (rt->rt_genid != atomic_read(&rt_genid))
continue;
@@ -3040,7 +3073,7 @@ int __init ip_rt_init(void)
ip_rt_secret_interval;
add_timer(&rt_secret_timer);
- if (ip_rt_proc_init(&init_net))
+ if (ip_rt_proc_init())
printk(KERN_ERR "Unable to create route proc files\n");
#ifdef CONFIG_XFRM
xfrm_init();
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index f470fe4511d..4704f27f6c0 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -10,8 +10,6 @@
* 2 of the License, or (at your option) any later version.
*
* $Id: syncookies.c,v 1.18 2002/02/01 22:01:04 davem Exp $
- *
- * Missing: IPv6 support.
*/
#include <linux/tcp.h>
@@ -23,22 +21,25 @@
extern int sysctl_tcp_syncookies;
-static __u32 syncookie_secret[2][16-3+SHA_DIGEST_WORDS];
+__u32 syncookie_secret[2][16-3+SHA_DIGEST_WORDS];
+EXPORT_SYMBOL(syncookie_secret);
static __init int init_syncookies(void)
{
get_random_bytes(syncookie_secret, sizeof(syncookie_secret));
return 0;
}
-module_init(init_syncookies);
+__initcall(init_syncookies);
#define COOKIEBITS 24 /* Upper bits store count */
#define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
+static DEFINE_PER_CPU(__u32, cookie_scratch)[16 + 5 + SHA_WORKSPACE_WORDS];
+
static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport,
u32 count, int c)
{
- __u32 tmp[16 + 5 + SHA_WORKSPACE_WORDS];
+ __u32 *tmp = __get_cpu_var(cookie_scratch);
memcpy(tmp + 3, syncookie_secret[c], sizeof(syncookie_secret[c]));
tmp[0] = (__force u32)saddr;
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 3aa0b23c1ea..eb5b9854c8c 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -1,12 +1,13 @@
/*
- * TCP CUBIC: Binary Increase Congestion control for TCP v2.1
- *
+ * TCP CUBIC: Binary Increase Congestion control for TCP v2.2
+ * Home page:
+ * http://netsrv.csc.ncsu.edu/twiki/bin/view/Main/BIC
* This is from the implementation of CUBIC TCP in
* Injong Rhee, Lisong Xu.
* "CUBIC: A New TCP-Friendly High-Speed TCP Variant
* in PFLDnet 2005
* Available from:
- * http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/cubic-paper.pdf
+ * http://netsrv.csc.ncsu.edu/export/cubic-paper.pdf
*
* Unless CUBIC is enabled and congestion window is large
* this behaves the same as the original Reno.
@@ -20,15 +21,10 @@
#define BICTCP_BETA_SCALE 1024 /* Scale factor beta calculation
* max_cwnd = snd_cwnd * beta
*/
-#define BICTCP_B 4 /*
- * In binary search,
- * go to point (max+min)/N
- */
#define BICTCP_HZ 10 /* BIC HZ 2^10 = 1024 */
static int fast_convergence __read_mostly = 1;
-static int max_increment __read_mostly = 16;
-static int beta __read_mostly = 819; /* = 819/1024 (BICTCP_BETA_SCALE) */
+static int beta __read_mostly = 717; /* = 717/1024 (BICTCP_BETA_SCALE) */
static int initial_ssthresh __read_mostly;
static int bic_scale __read_mostly = 41;
static int tcp_friendliness __read_mostly = 1;
@@ -40,9 +36,7 @@ static u64 cube_factor __read_mostly;
/* Note parameters that are used for precomputing scale factors are read-only */
module_param(fast_convergence, int, 0644);
MODULE_PARM_DESC(fast_convergence, "turn on/off fast convergence");
-module_param(max_increment, int, 0644);
-MODULE_PARM_DESC(max_increment, "Limit on increment allowed during binary search");
-module_param(beta, int, 0444);
+module_param(beta, int, 0644);
MODULE_PARM_DESC(beta, "beta for multiplicative increase");
module_param(initial_ssthresh, int, 0644);
MODULE_PARM_DESC(initial_ssthresh, "initial value of slow start threshold");
@@ -145,7 +139,7 @@ static u32 cubic_root(u64 a)
static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
{
u64 offs;
- u32 delta, t, bic_target, min_cnt, max_cnt;
+ u32 delta, t, bic_target, max_cnt;
ca->ack_cnt++; /* count the number of ACKs */
@@ -211,19 +205,6 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
ca->cnt = 100 * cwnd; /* very small increment*/
}
- if (ca->delay_min > 0) {
- /* max increment = Smax * rtt / 0.1 */
- min_cnt = (cwnd * HZ * 8)/(10 * max_increment * ca->delay_min);
-
- /* use concave growth when the target is above the origin */
- if (ca->cnt < min_cnt && t >= ca->bic_K)
- ca->cnt = min_cnt;
- }
-
- /* slow start and low utilization */
- if (ca->loss_cwnd == 0) /* could be aggressive in slow start */
- ca->cnt = 50;
-
/* TCP Friendly */
if (tcp_friendliness) {
u32 scale = beta_scale;
@@ -391,4 +372,4 @@ module_exit(cubictcp_unregister);
MODULE_AUTHOR("Sangtae Ha, Stephen Hemminger");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("CUBIC TCP");
-MODULE_VERSION("2.1");
+MODULE_VERSION("2.2");
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 7facdb0f696..c4679f34367 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5330,6 +5330,7 @@ discard:
EXPORT_SYMBOL(sysctl_tcp_ecn);
EXPORT_SYMBOL(sysctl_tcp_reordering);
+EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
EXPORT_SYMBOL(tcp_parse_options);
EXPORT_SYMBOL(tcp_rcv_established);
EXPORT_SYMBOL(tcp_rcv_state_process);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 00156bf421c..3873c4dbeae 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -723,8 +723,8 @@ static void tcp_v4_reqsk_send_ack(struct sk_buff *skb,
* This still operates on a request_sock only, not on a big
* socket.
*/
-static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
- struct dst_entry *dst)
+static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
+ struct dst_entry *dst)
{
const struct inet_request_sock *ireq = inet_rsk(req);
int err = -1;
@@ -732,7 +732,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
/* First, grab a route. */
if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL)
- goto out;
+ return -1;
skb = tcp_make_synack(sk, dst, req);
@@ -751,11 +751,15 @@ static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
err = net_xmit_eval(err);
}
-out:
dst_release(dst);
return err;
}
+static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req)
+{
+ return __tcp_v4_send_synack(sk, req, NULL);
+}
+
/*
* IPv4 request_sock destructor.
*/
@@ -1351,8 +1355,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
(s32)(peer->tcp_ts - req->ts_recent) >
TCP_PAWS_WINDOW) {
NET_INC_STATS_BH(LINUX_MIB_PAWSPASSIVEREJECTED);
- dst_release(dst);
- goto drop_and_free;
+ goto drop_and_release;
}
}
/* Kill the following clause, if you dislike this way. */
@@ -1372,24 +1375,21 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
"request from %u.%u.%u.%u/%u\n",
NIPQUAD(saddr),
ntohs(tcp_hdr(skb)->source));
- dst_release(dst);
- goto drop_and_free;
+ goto drop_and_release;
}
isn = tcp_v4_init_sequence(skb);
}
tcp_rsk(req)->snt_isn = isn;
- if (tcp_v4_send_synack(sk, req, dst))
+ if (__tcp_v4_send_synack(sk, req, dst) || want_cookie)
goto drop_and_free;
- if (want_cookie) {
- reqsk_free(req);
- } else {
- inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
- }
+ inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
return 0;
+drop_and_release:
+ dst_release(dst);
drop_and_free:
reqsk_free(req);
drop:
@@ -2443,7 +2443,7 @@ struct proto tcp_prot = {
REF_PROTO_INUSE(tcp)
};
-void __init tcp_v4_init(struct net_proto_family *ops)
+void __init tcp_v4_init(void)
{
if (inet_csk_ctl_sock_create(&tcp_socket, PF_INET, SOCK_RAW,
IPPROTO_TCP) < 0)
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index b61b76847ad..8245247a6ce 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -35,6 +35,8 @@
#endif
int sysctl_tcp_syncookies __read_mostly = SYNC_INIT;
+EXPORT_SYMBOL(sysctl_tcp_syncookies);
+
int sysctl_tcp_abort_on_overflow __read_mostly;
struct inet_timewait_death_row tcp_death_row = {
@@ -536,7 +538,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb,
* Enforce "SYN-ACK" according to figure 8, figure 6
* of RFC793, fixed by RFC1122.
*/
- req->rsk_ops->rtx_syn_ack(sk, req, NULL);
+ req->rsk_ops->rtx_syn_ack(sk, req);
return NULL;
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index ed750f9ceb0..cbfef8b1f5e 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2560,6 +2560,7 @@ void tcp_send_probe0(struct sock *sk)
}
}
+EXPORT_SYMBOL(tcp_select_initial_window);
EXPORT_SYMBOL(tcp_connect);
EXPORT_SYMBOL(tcp_make_synack);
EXPORT_SYMBOL(tcp_simple_retransmit);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 7ea1b67b6de..c53d7673b57 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -246,553 +246,6 @@ int udp_get_port(struct sock *sk, unsigned short snum,
return __udp_lib_get_port(sk, snum, udp_hash, scmp);
}
-int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
-{
- struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2);
-
- return ( !ipv6_only_sock(sk2) &&
- (!inet1->rcv_saddr || !inet2->rcv_saddr ||
- inet1->rcv_saddr == inet2->rcv_saddr ));
-}
-
-static inline int udp_v4_get_port(struct sock *sk, unsigned short snum)
-{
- return udp_get_port(sk, snum, ipv4_rcv_saddr_equal);
-}
-
-/* UDP is nearly always wildcards out the wazoo, it makes no sense to try
- * harder than this. -DaveM
- */
-static struct sock *__udp4_lib_lookup(struct net *net, __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;
-
- read_lock(&udp_hash_lock);
- sk_for_each(sk, node, &udptable[hnum & (UDP_HTABLE_SIZE - 1)]) {
- struct inet_sock *inet = inet_sk(sk);
-
- if (sk->sk_net == net && sk->sk_hash == hnum &&
- !ipv6_only_sock(sk)) {
- int score = (sk->sk_family == PF_INET ? 1 : 0);
- if (inet->rcv_saddr) {
- if (inet->rcv_saddr != daddr)
- continue;
- score+=2;
- }
- if (inet->daddr) {
- if (inet->daddr != saddr)
- continue;
- score+=2;
- }
- if (inet->dport) {
- if (inet->dport != sport)
- continue;
- score+=2;
- }
- if (sk->sk_bound_dev_if) {
- if (sk->sk_bound_dev_if != dif)
- continue;
- score+=2;
- }
- if (score == 9) {
- result = sk;
- break;
- } else if (score > badness) {
- result = sk;
- badness = score;
- }
- }
- }
- if (result)
- sock_hold(result);
- read_unlock(&udp_hash_lock);
- return result;
-}
-
-static inline struct sock *udp_v4_mcast_next(struct sock *sk,
- __be16 loc_port, __be32 loc_addr,
- __be16 rmt_port, __be32 rmt_addr,
- int dif)
-{
- struct hlist_node *node;
- struct sock *s = sk;
- unsigned short hnum = ntohs(loc_port);
-
- sk_for_each_from(s, node) {
- struct inet_sock *inet = inet_sk(s);
-
- if (s->sk_hash != hnum ||
- (inet->daddr && inet->daddr != rmt_addr) ||
- (inet->dport != rmt_port && inet->dport) ||
- (inet->rcv_saddr && inet->rcv_saddr != loc_addr) ||
- ipv6_only_sock(s) ||
- (s->sk_bound_dev_if && s->sk_bound_dev_if != dif))
- continue;
- if (!ip_mc_sf_allow(s, loc_addr, rmt_addr, dif))
- continue;
- goto found;
- }
- s = NULL;
-found:
- return s;
-}
-
-/*
- * This routine is called by the ICMP module when it gets some
- * sort of error condition. If err < 0 then the socket should
- * be closed and the error returned to the user. If err > 0
- * it's just the icmp type << 8 | icmp code.
- * Header points to the ip header of the error packet. We move
- * on past this. Then (as it used to claim before adjustment)
- * header points to the first 8 bytes of the udp header. We need
- * to find the appropriate port.
- */
-
-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;
- struct udphdr *uh = (struct udphdr*)(skb->data+(iph->ihl<<2));
- const int type = icmp_hdr(skb)->type;
- const int code = icmp_hdr(skb)->code;
- struct sock *sk;
- int harderr;
- int err;
-
- sk = __udp4_lib_lookup(skb->dev->nd_net, 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 */
- }
-
- err = 0;
- harderr = 0;
- inet = inet_sk(sk);
-
- switch (type) {
- default:
- case ICMP_TIME_EXCEEDED:
- err = EHOSTUNREACH;
- break;
- case ICMP_SOURCE_QUENCH:
- goto out;
- case ICMP_PARAMETERPROB:
- err = EPROTO;
- harderr = 1;
- break;
- case ICMP_DEST_UNREACH:
- if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
- if (inet->pmtudisc != IP_PMTUDISC_DONT) {
- err = EMSGSIZE;
- harderr = 1;
- break;
- }
- goto out;
- }
- err = EHOSTUNREACH;
- if (code <= NR_ICMP_UNREACH) {
- harderr = icmp_err_convert[code].fatal;
- err = icmp_err_convert[code].errno;
- }
- break;
- }
-
- /*
- * RFC1122: OK. Passes ICMP errors back to application, as per
- * 4.1.3.3.
- */
- if (!inet->recverr) {
- if (!harderr || sk->sk_state != TCP_ESTABLISHED)
- goto out;
- } else {
- ip_icmp_error(sk, skb, err, uh->dest, info, (u8*)(uh+1));
- }
- sk->sk_err = err;
- sk->sk_error_report(sk);
-out:
- sock_put(sk);
-}
-
-void udp_err(struct sk_buff *skb, u32 info)
-{
- __udp4_lib_err(skb, info, udp_hash);
-}
-
-/*
- * Throw away all pending data and cancel the corking. Socket is locked.
- */
-static void udp_flush_pending_frames(struct sock *sk)
-{
- struct udp_sock *up = udp_sk(sk);
-
- if (up->pending) {
- up->len = 0;
- up->pending = 0;
- ip_flush_pending_frames(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 offset;
- struct udphdr *uh = udp_hdr(skb);
- __wsum csum = 0;
-
- if (skb_queue_len(&sk->sk_write_queue) == 1) {
- /*
- * Only one fragment on the socket.
- */
- skb->csum_start = skb_transport_header(skb) - skb->head;
- skb->csum_offset = 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_transport_offset(skb);
- 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 = CSUM_MANGLED_0;
- }
-}
-
-/*
- * 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 = udp_sk(sk);
- struct inet_sock *inet = inet_sk(sk);
- struct flowi *fl = &inet->cork.fl;
- struct sk_buff *skb;
- struct udphdr *uh;
- 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)
- goto out;
-
- /*
- * Create a UDP header
- */
- 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 (is_udplite) /* 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;
-
- } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware 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 = CSUM_MANGLED_0;
-
-send:
- err = ip_push_pending_frames(sk);
-out:
- up->len = 0;
- up->pending = 0;
- if (!err)
- UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite);
- return err;
-}
-
-int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
- size_t len)
-{
- struct inet_sock *inet = inet_sk(sk);
- struct udp_sock *up = udp_sk(sk);
- int ulen = len;
- struct ipcm_cookie ipc;
- struct rtable *rt = NULL;
- int free = 0;
- int connected = 0;
- __be32 daddr, faddr, saddr;
- __be16 dport;
- u8 tos;
- int err, is_udplite = IS_UDPLITE(sk);
- int corkreq = up->corkflag || msg->msg_flags&MSG_MORE;
- int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
-
- if (len > 0xFFFF)
- return -EMSGSIZE;
-
- /*
- * Check the flags.
- */
-
- if (msg->msg_flags&MSG_OOB) /* Mirror BSD error message compatibility */
- return -EOPNOTSUPP;
-
- ipc.opt = NULL;
-
- if (up->pending) {
- /*
- * There are pending frames.
- * The socket lock must be held while it's corked.
- */
- lock_sock(sk);
- if (likely(up->pending)) {
- if (unlikely(up->pending != AF_INET)) {
- release_sock(sk);
- return -EINVAL;
- }
- goto do_append_data;
- }
- release_sock(sk);
- }
- ulen += sizeof(struct udphdr);
-
- /*
- * Get and verify the address.
- */
- if (msg->msg_name) {
- struct sockaddr_in * usin = (struct sockaddr_in*)msg->msg_name;
- if (msg->msg_namelen < sizeof(*usin))
- return -EINVAL;
- if (usin->sin_family != AF_INET) {
- if (usin->sin_family != AF_UNSPEC)
- return -EAFNOSUPPORT;
- }
-
- daddr = usin->sin_addr.s_addr;
- dport = usin->sin_port;
- if (dport == 0)
- return -EINVAL;
- } else {
- if (sk->sk_state != TCP_ESTABLISHED)
- return -EDESTADDRREQ;
- daddr = inet->daddr;
- dport = inet->dport;
- /* Open fast path for connected socket.
- Route will not be used, if at least one option is set.
- */
- connected = 1;
- }
- ipc.addr = inet->saddr;
-
- ipc.oif = sk->sk_bound_dev_if;
- if (msg->msg_controllen) {
- err = ip_cmsg_send(msg, &ipc);
- if (err)
- return err;
- if (ipc.opt)
- free = 1;
- connected = 0;
- }
- if (!ipc.opt)
- ipc.opt = inet->opt;
-
- saddr = ipc.addr;
- ipc.addr = faddr = daddr;
-
- if (ipc.opt && ipc.opt->srr) {
- if (!daddr)
- return -EINVAL;
- faddr = ipc.opt->faddr;
- connected = 0;
- }
- tos = RT_TOS(inet->tos);
- if (sock_flag(sk, SOCK_LOCALROUTE) ||
- (msg->msg_flags & MSG_DONTROUTE) ||
- (ipc.opt && ipc.opt->is_strictroute)) {
- tos |= RTO_ONLINK;
- connected = 0;
- }
-
- if (ipv4_is_multicast(daddr)) {
- if (!ipc.oif)
- ipc.oif = inet->mc_index;
- if (!saddr)
- saddr = inet->mc_addr;
- connected = 0;
- }
-
- if (connected)
- rt = (struct rtable*)sk_dst_check(sk, 0);
-
- if (rt == NULL) {
- struct flowi fl = { .oif = ipc.oif,
- .nl_u = { .ip4_u =
- { .daddr = faddr,
- .saddr = saddr,
- .tos = tos } },
- .proto = sk->sk_protocol,
- .uli_u = { .ports =
- { .sport = inet->sport,
- .dport = dport } } };
- security_sk_classify_flow(sk, &fl);
- err = ip_route_output_flow(&init_net, &rt, &fl, sk, 1);
- if (err) {
- if (err == -ENETUNREACH)
- IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
- goto out;
- }
-
- err = -EACCES;
- if ((rt->rt_flags & RTCF_BROADCAST) &&
- !sock_flag(sk, SOCK_BROADCAST))
- goto out;
- if (connected)
- sk_dst_set(sk, dst_clone(&rt->u.dst));
- }
-
- if (msg->msg_flags&MSG_CONFIRM)
- goto do_confirm;
-back_from_confirm:
-
- saddr = rt->rt_src;
- if (!ipc.addr)
- daddr = ipc.addr = rt->rt_dst;
-
- lock_sock(sk);
- if (unlikely(up->pending)) {
- /* The socket is already corked while preparing it. */
- /* ... which is an evident application bug. --ANK */
- release_sock(sk);
-
- LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 2\n");
- err = -EINVAL;
- goto out;
- }
- /*
- * Now cork the socket to pend data.
- */
- inet->cork.fl.fl4_dst = daddr;
- inet->cork.fl.fl_ip_dport = dport;
- inet->cork.fl.fl4_src = saddr;
- inet->cork.fl.fl_ip_sport = inet->sport;
- up->pending = AF_INET;
-
-do_append_data:
- up->len += ulen;
- 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);
- else if (!corkreq)
- err = udp_push_pending_frames(sk);
- else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
- up->pending = 0;
- release_sock(sk);
-
-out:
- ip_rt_put(rt);
- if (free)
- kfree(ipc.opt);
- 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
- * we don't have a good statistic (IpOutDiscards but it can be too many
- * things). We could add another new stat but at least for now that
- * seems like overkill.
- */
- if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
- UDP_INC_STATS_USER(UDP_MIB_SNDBUFERRORS, is_udplite);
- }
- return err;
-
-do_confirm:
- dst_confirm(&rt->u.dst);
- if (!(msg->msg_flags&MSG_PROBE) || len)
- goto back_from_confirm;
- err = 0;
- goto out;
-}
-
-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;
-
- if (!up->pending) {
- struct msghdr msg = { .msg_flags = flags|MSG_MORE };
-
- /* Call udp_sendmsg to specify destination address which
- * sendpage interface can't pass.
- * This will succeed only when the socket is connected.
- */
- ret = udp_sendmsg(NULL, sk, &msg, 0);
- if (ret < 0)
- return ret;
- }
-
- lock_sock(sk);
-
- if (unlikely(!up->pending)) {
- release_sock(sk);
-
- LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 3\n");
- return -EINVAL;
- }
-
- ret = ip_append_page(sk, page, offset, size, flags);
- if (ret == -EOPNOTSUPP) {
- release_sock(sk);
- return sock_no_sendpage(sk->sk_socket, page, offset,
- size, flags);
- }
- if (ret < 0) {
- udp_flush_pending_frames(sk);
- goto out;
- }
-
- up->len += size;
- if (!(up->corkflag || (flags&MSG_MORE)))
- ret = udp_push_pending_frames(sk);
- if (!ret)
- ret = size;
-out:
- release_sock(sk);
- return ret;
-}
-
/*
* IOCTL requests applicable to the UDP protocol
*/
@@ -833,107 +286,6 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg)
return 0;
}
-/*
- * This should be easy, if there is something there we
- * return it, otherwise we block.
- */
-
-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;
- unsigned int ulen, copied;
- int peeked;
- int err;
- int is_udplite = IS_UDPLITE(sk);
-
- /*
- * Check any passed addresses
- */
- if (addr_len)
- *addr_len=sizeof(*sin);
-
- if (flags & MSG_ERRQUEUE)
- return ip_recv_error(sk, msg, len);
-
-try_again:
- skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
- &peeked, &err);
- if (!skb)
- goto out;
-
- ulen = skb->len - sizeof(struct udphdr);
- copied = len;
- if (copied > ulen)
- copied = ulen;
- else if (copied < ulen)
- msg->msg_flags |= MSG_TRUNC;
-
- /*
- * 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;
- }
-
- 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)
- UDP_INC_STATS_USER(UDP_MIB_INDATAGRAMS, is_udplite);
-
- sock_recv_timestamp(msg, sk, skb);
-
- /* Copy the address. */
- if (sin)
- {
- sin->sin_family = AF_INET;
- sin->sin_port = udp_hdr(skb)->source;
- sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
- memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
- }
- if (inet->cmsg_flags)
- ip_cmsg_recv(msg, skb);
-
- err = copied;
- if (flags & MSG_TRUNC)
- err = ulen;
-
-out_free:
- lock_sock(sk);
- skb_free_datagram(sk, skb);
- release_sock(sk);
-out:
- return err;
-
-csum_copy_err:
- lock_sock(sk);
- if (!skb_kill_datagram(sk, skb, flags))
- UDP_INC_STATS_USER(UDP_MIB_INERRORS, is_udplite);
- release_sock(sk);
-
- if (noblock)
- return -EAGAIN;
- goto try_again;
-}
-
-
int udp_disconnect(struct sock *sk, int flags)
{
struct inet_sock *inet = inet_sk(sk);
@@ -956,319 +308,6 @@ int udp_disconnect(struct sock *sk, int flags)
return 0;
}
-/* returns:
- * -1: error
- * 0: success
- * >0: "udp encap" protocol resubmission
- *
- * Note that in the success and error cases, the skb is assumed to
- * have either been requeued or freed.
- */
-int udp_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);
-
- /*
- * Charge it to the socket, dropping if the queue is full.
- */
- if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
- goto drop;
- nf_reset(skb);
-
- if (up->encap_type) {
- /*
- * This is an encapsulation socket so pass the skb to
- * the socket's udp_encap_rcv() hook. Otherwise, just
- * fall through and pass this up the UDP socket.
- * up->encap_rcv() returns the following value:
- * =0 if skb was successfully passed to the encap
- * handler or was discarded by it.
- * >0 if skb should be passed on to UDP.
- * <0 if skb should be resubmitted as proto -N
- */
-
- /* if we're overly short, let UDP handle it */
- if (skb->len > sizeof(struct udphdr) &&
- up->encap_rcv != NULL) {
- int ret;
-
- ret = (*up->encap_rcv)(sk, skb);
- if (ret <= 0) {
- UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS,
- is_udplite);
- return -ret;
- }
- }
-
- /* FALLTHROUGH -- it's a UDP Packet */
- }
-
- /*
- * UDP-Lite specific tests, ignored on UDP sockets
- */
- if ((is_udplite & 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) {
- 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)
- UDP_INC_STATS_BH(UDP_MIB_RCVBUFERRORS, is_udplite);
- goto drop;
- }
-
- return 0;
-
-drop:
- UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite);
- kfree_skb(skb);
- return -1;
-}
-
-/*
- * Multicasts and broadcasts go to each listener.
- *
- * Note: called only from the BH handler context,
- * so we don't need to lock the hashes.
- */
-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(&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) {
- struct sock *sknext = NULL;
-
- do {
- struct sk_buff *skb1 = skb;
-
- sknext = udp_v4_mcast_next(sk_next(sk), uh->dest, daddr,
- uh->source, saddr, dif);
- if (sknext)
- skb1 = skb_clone(skb, GFP_ATOMIC);
-
- if (skb1) {
- int ret = 0;
-
- bh_lock_sock_nested(sk);
- if (!sock_owned_by_user(sk))
- ret = udp_queue_rcv_skb(sk, skb1);
- else
- sk_add_backlog(sk, skb1);
- bh_unlock_sock(sk);
-
- if (ret > 0)
- /* we should probably re-process instead
- * of dropping packets here. */
- kfree_skb(skb1);
- }
- sk = sknext;
- } while (sknext);
- } else
- kfree_skb(skb);
- read_unlock(&udp_hash_lock);
- return 0;
-}
-
-/* Initialize UDP checksum. If exited with zero value (success),
- * CHECKSUM_UNNECESSARY means, that no more checks are required.
- * Otherwise, csum completion requires chacksumming packet body,
- * including udp header and folding it to skb->csum.
- */
-static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
- int proto)
-{
- const struct iphdr *iph;
- 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;
- }
-
- iph = ip_hdr(skb);
- if (uh->check == 0) {
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- } else if (skb->ip_summed == CHECKSUM_COMPLETE) {
- if (!csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
- proto, skb->csum))
- skb->ip_summed = CHECKSUM_UNNECESSARY;
- }
- if (!skb_csum_unnecessary(skb))
- skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
- skb->len, proto, 0);
- /* Probably, we should checksum udp header (it should be in cache
- * in any case) and data in tiny packets (< rx copybreak).
- */
-
- return 0;
-}
-
-/*
- * All we need to do is get the socket, and then do a checksum.
- */
-
-int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
- int proto)
-{
- struct sock *sk;
- struct udphdr *uh = udp_hdr(skb);
- unsigned short ulen;
- struct rtable *rt = (struct rtable*)skb->dst;
- __be32 saddr = ip_hdr(skb)->saddr;
- __be32 daddr = ip_hdr(skb)->daddr;
-
- /*
- * Validate the packet.
- */
- if (!pskb_may_pull(skb, sizeof(struct udphdr)))
- goto drop; /* No space for header. */
-
- ulen = ntohs(uh->len);
- if (ulen > skb->len)
- goto short_packet;
-
- if (proto == IPPROTO_UDP) {
- /* UDP validates ulen. */
- if (ulen < sizeof(*uh) || pskb_trim_rcsum(skb, ulen))
- goto short_packet;
- uh = udp_hdr(skb);
- }
-
- if (udp4_csum_init(skb, uh, proto))
- goto csum_error;
-
- if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
- return __udp4_lib_mcast_deliver(skb, uh, saddr, daddr, udptable);
-
- sk = __udp4_lib_lookup(skb->dev->nd_net, saddr, uh->source, daddr,
- uh->dest, inet_iif(skb), udptable);
-
- if (sk != NULL) {
- int ret = 0;
- bh_lock_sock_nested(sk);
- if (!sock_owned_by_user(sk))
- ret = udp_queue_rcv_skb(sk, skb);
- else
- sk_add_backlog(sk, skb);
- bh_unlock_sock(sk);
- sock_put(sk);
-
- /* a return value > 0 means to resubmit the input, but
- * it wants the return to be -protocol, or 0
- */
- if (ret > 0)
- return -ret;
- return 0;
- }
-
- if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
- goto drop;
- nf_reset(skb);
-
- /* No socket. Drop packet silently, if checksum is wrong */
- if (udp_lib_checksum_complete(skb))
- goto csum_error;
-
- UDP_INC_STATS_BH(UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE);
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
-
- /*
- * Hmm. We got an UDP packet to a port to which we
- * don't wanna listen. Ignore it.
- */
- kfree_skb(skb);
- return 0;
-
-short_packet:
- LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: short packet: From %u.%u.%u.%u:%u %d/%d to %u.%u.%u.%u:%u\n",
- proto == IPPROTO_UDPLITE ? "-Lite" : "",
- NIPQUAD(saddr),
- ntohs(uh->source),
- ulen,
- skb->len,
- NIPQUAD(daddr),
- ntohs(uh->dest));
- 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%s: bad checksum. From %d.%d.%d.%d:%d to %d.%d.%d.%d:%d ulen %d\n",
- proto == IPPROTO_UDPLITE ? "-Lite" : "",
- NIPQUAD(saddr),
- ntohs(uh->source),
- NIPQUAD(daddr),
- ntohs(uh->dest),
- ulen);
-drop:
- UDP_INC_STATS_BH(UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
- kfree_skb(skb);
- return 0;
-}
-
-int udp_rcv(struct sk_buff *skb)
-{
- return __udp4_lib_rcv(skb, udp_hash, IPPROTO_UDP);
-}
-
-int udp_destroy_sock(struct sock *sk)
-{
- lock_sock(sk);
- udp_flush_pending_frames(sk);
- release_sock(sk);
- return 0;
-}
-
/*
* Socket option code for UDP
*/
@@ -1279,7 +318,9 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
struct udp_sock *up = udp_sk(sk);
int val;
int err = 0;
+#ifdef CONFIG_IP_UDPLITE
int is_udplite = IS_UDPLITE(sk);
+#endif
if (optlen<sizeof(int))
return -EINVAL;
@@ -1315,6 +356,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
}
break;
+#ifdef CONFIG_IP_UDPLITE
/*
* UDP-Lite's partial checksum coverage (RFC 3828).
*/
@@ -1340,6 +382,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
up->pcrlen = val;
up->pcflag |= UDPLITE_RECV_CC;
break;
+#endif
default:
err = -ENOPROTOOPT;
@@ -1349,26 +392,6 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
return err;
}
-int udp_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int optlen)
-{
- if (level == SOL_UDP || level == SOL_UDPLITE)
- return udp_lib_setsockopt(sk, level, optname, optval, optlen,
- udp_push_pending_frames);
- return ip_setsockopt(sk, level, optname, optval, optlen);
-}
-
-#ifdef CONFIG_COMPAT
-int compat_udp_setsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int optlen)
-{
- if (level == SOL_UDP || level == SOL_UDPLITE)
- return udp_lib_setsockopt(sk, level, optname, optval, optlen,
- udp_push_pending_frames);
- return compat_ip_setsockopt(sk, level, optname, optval, optlen);
-}
-#endif
-
int udp_lib_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
@@ -1413,23 +436,6 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname,
return 0;
}
-int udp_getsockopt(struct sock *sk, int level, int optname,
- char __user *optval, int __user *optlen)
-{
- if (level == SOL_UDP || level == SOL_UDPLITE)
- return udp_lib_getsockopt(sk, level, optname, optval, optlen);
- return ip_getsockopt(sk, level, optname, optval, optlen);
-}
-
-#ifdef CONFIG_COMPAT
-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 udp_lib_getsockopt(sk, level, optname, optval, optlen);
- return compat_ip_getsockopt(sk, level, optname, optval, optlen);
-}
-#endif
/**
* udp_poll - wait for a UDP event.
* @file - file struct
@@ -1474,36 +480,6 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
}
-DEFINE_PROTO_INUSE(udp)
-
-struct proto udp_prot = {
- .name = "UDP",
- .owner = THIS_MODULE,
- .close = udp_lib_close,
- .connect = ip4_datagram_connect,
- .disconnect = udp_disconnect,
- .ioctl = udp_ioctl,
- .destroy = udp_destroy_sock,
- .setsockopt = udp_setsockopt,
- .getsockopt = udp_getsockopt,
- .sendmsg = udp_sendmsg,
- .recvmsg = udp_recvmsg,
- .sendpage = udp_sendpage,
- .backlog_rcv = udp_queue_rcv_skb,
- .hash = udp_lib_hash,
- .unhash = udp_lib_unhash,
- .get_port = udp_v4_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 udp_sock),
-#ifdef CONFIG_COMPAT
- .compat_setsockopt = compat_udp_setsockopt,
- .compat_getsockopt = compat_udp_getsockopt,
-#endif
- REF_PROTO_INUSE(udp)
-};
/* ------------------------------------------------------------------------ */
#ifdef CONFIG_PROC_FS
@@ -1636,62 +612,6 @@ void udp_proc_unregister(struct udp_seq_afinfo *afinfo)
proc_net_remove(&init_net, afinfo->name);
memset(afinfo->seq_fops, 0, sizeof(*afinfo->seq_fops));
}
-
-/* ------------------------------------------------------------------------ */
-static void udp4_format_sock(struct sock *sp, char *tmpbuf, int bucket)
-{
- struct inet_sock *inet = inet_sk(sp);
- __be32 dest = inet->daddr;
- __be32 src = inet->rcv_saddr;
- __u16 destp = ntohs(inet->dport);
- __u16 srcp = ntohs(inet->sport);
-
- sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X"
- " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p",
- bucket, src, srcp, dest, destp, 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);
-}
-
-int udp4_seq_show(struct seq_file *seq, void *v)
-{
- if (v == SEQ_START_TOKEN)
- seq_printf(seq, "%-127s\n",
- " sl local_address rem_address st tx_queue "
- "rx_queue tr tm->when retrnsmt uid timeout "
- "inode");
- else {
- char tmpbuf[129];
- struct udp_iter_state *state = seq->private;
-
- udp4_format_sock(v, tmpbuf, state->bucket);
- seq_printf(seq, "%-127s\n", tmpbuf);
- }
- return 0;
-}
-
-/* ------------------------------------------------------------------------ */
-static struct file_operations udp4_seq_fops;
-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,
-};
-
-int __init udp4_proc_init(void)
-{
- return udp_proc_register(&udp4_seq_afinfo);
-}
-
-void udp4_proc_exit(void)
-{
- udp_proc_unregister(&udp4_seq_afinfo);
-}
#endif /* CONFIG_PROC_FS */
void __init udp_init(void)
@@ -1718,8 +638,6 @@ EXPORT_SYMBOL(udp_hash);
EXPORT_SYMBOL(udp_hash_lock);
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);
diff --git a/net/ipv4/udp_ipv4.c b/net/ipv4/udp_ipv4.c
new file mode 100644
index 00000000000..40978de7fb5
--- /dev/null
+++ b/net/ipv4/udp_ipv4.c
@@ -0,0 +1,1134 @@
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * UDP for IPv4.
+ *
+ * For full credits, see net/ipv4/udp.c.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/ioctls.h>
+#include <linux/bootmem.h>
+#include <linux/types.h>
+#include <linux/fcntl.h>
+#include <linux/module.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <linux/igmp.h>
+#include <linux/in.h>
+#include <linux/errno.h>
+#include <linux/timer.h>
+#include <linux/mm.h>
+#include <linux/inet.h>
+#include <linux/netdevice.h>
+#include <net/tcp_states.h>
+#include <linux/skbuff.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <net/net_namespace.h>
+#include <net/icmp.h>
+#include <net/route.h>
+#include <net/checksum.h>
+#include <net/xfrm.h>
+#include "udp_impl.h"
+
+int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
+{
+ struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2);
+
+ return ( !ipv6_only_sock(sk2) &&
+ (!inet1->rcv_saddr || !inet2->rcv_saddr ||
+ inet1->rcv_saddr == inet2->rcv_saddr ));
+}
+
+static inline int udp_v4_get_port(struct sock *sk, unsigned short snum)
+{
+ return udp_get_port(sk, snum, ipv4_rcv_saddr_equal);
+}
+
+/* UDP is nearly always wildcards out the wazoo, it makes no sense to try
+ * harder than this. -DaveM
+ */
+static struct sock *__udp4_lib_lookup(struct net *net, __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;
+
+ read_lock(&udp_hash_lock);
+ sk_for_each(sk, node, &udptable[hnum & (UDP_HTABLE_SIZE - 1)]) {
+ struct inet_sock *inet = inet_sk(sk);
+
+ if (sk->sk_net == net && sk->sk_hash == hnum &&
+ !ipv6_only_sock(sk)) {
+ int score = (sk->sk_family == PF_INET ? 1 : 0);
+ if (inet->rcv_saddr) {
+ if (inet->rcv_saddr != daddr)
+ continue;
+ score+=2;
+ }
+ if (inet->daddr) {
+ if (inet->daddr != saddr)
+ continue;
+ score+=2;
+ }
+ if (inet->dport) {
+ if (inet->dport != sport)
+ continue;
+ score+=2;
+ }
+ if (sk->sk_bound_dev_if) {
+ if (sk->sk_bound_dev_if != dif)
+ continue;
+ score+=2;
+ }
+ if (score == 9) {
+ result = sk;
+ break;
+ } else if (score > badness) {
+ result = sk;
+ badness = score;
+ }
+ }
+ }
+ if (result)
+ sock_hold(result);
+ read_unlock(&udp_hash_lock);
+ return result;
+}
+
+static inline struct sock *udp_v4_mcast_next(struct sock *sk,
+ __be16 loc_port, __be32 loc_addr,
+ __be16 rmt_port, __be32 rmt_addr,
+ int dif)
+{
+ struct hlist_node *node;
+ struct sock *s = sk;
+ unsigned short hnum = ntohs(loc_port);
+
+ sk_for_each_from(s, node) {
+ struct inet_sock *inet = inet_sk(s);
+
+ if (s->sk_hash != hnum ||
+ (inet->daddr && inet->daddr != rmt_addr) ||
+ (inet->dport != rmt_port && inet->dport) ||
+ (inet->rcv_saddr && inet->rcv_saddr != loc_addr) ||
+ ipv6_only_sock(s) ||
+ (s->sk_bound_dev_if && s->sk_bound_dev_if != dif))
+ continue;
+ if (!ip_mc_sf_allow(s, loc_addr, rmt_addr, dif))
+ continue;
+ goto found;
+ }
+ s = NULL;
+found:
+ return s;
+}
+
+/*
+ * This routine is called by the ICMP module when it gets some
+ * sort of error condition. If err < 0 then the socket should
+ * be closed and the error returned to the user. If err > 0
+ * it's just the icmp type << 8 | icmp code.
+ * Header points to the ip header of the error packet. We move
+ * on past this. Then (as it used to claim before adjustment)
+ * header points to the first 8 bytes of the udp header. We need
+ * to find the appropriate port.
+ */
+
+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;
+ struct udphdr *uh = (struct udphdr*)(skb->data+(iph->ihl<<2));
+ const int type = icmp_hdr(skb)->type;
+ const int code = icmp_hdr(skb)->code;
+ struct sock *sk;
+ int harderr;
+ int err;
+
+ sk = __udp4_lib_lookup(skb->dev->nd_net, 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 */
+ }
+
+ err = 0;
+ harderr = 0;
+ inet = inet_sk(sk);
+
+ switch (type) {
+ default:
+ case ICMP_TIME_EXCEEDED:
+ err = EHOSTUNREACH;
+ break;
+ case ICMP_SOURCE_QUENCH:
+ goto out;
+ case ICMP_PARAMETERPROB:
+ err = EPROTO;
+ harderr = 1;
+ break;
+ case ICMP_DEST_UNREACH:
+ if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
+ if (inet->pmtudisc != IP_PMTUDISC_DONT) {
+ err = EMSGSIZE;
+ harderr = 1;
+ break;
+ }
+ goto out;
+ }
+ err = EHOSTUNREACH;
+ if (code <= NR_ICMP_UNREACH) {
+ harderr = icmp_err_convert[code].fatal;
+ err = icmp_err_convert[code].errno;
+ }
+ break;
+ }
+
+ /*
+ * RFC1122: OK. Passes ICMP errors back to application, as per
+ * 4.1.3.3.
+ */
+ if (!inet->recverr) {
+ if (!harderr || sk->sk_state != TCP_ESTABLISHED)
+ goto out;
+ } else {
+ ip_icmp_error(sk, skb, err, uh->dest, info, (u8*)(uh+1));
+ }
+ sk->sk_err = err;
+ sk->sk_error_report(sk);
+out:
+ sock_put(sk);
+}
+
+void udp_err(struct sk_buff *skb, u32 info)
+{
+ __udp4_lib_err(skb, info, udp_hash);
+}
+
+/*
+ * Throw away all pending data and cancel the corking. Socket is locked.
+ */
+static void udp_flush_pending_frames(struct sock *sk)
+{
+ struct udp_sock *up = udp_sk(sk);
+
+ if (up->pending) {
+ up->len = 0;
+ up->pending = 0;
+ ip_flush_pending_frames(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 offset;
+ struct udphdr *uh = udp_hdr(skb);
+ __wsum csum = 0;
+
+ if (skb_queue_len(&sk->sk_write_queue) == 1) {
+ /*
+ * Only one fragment on the socket.
+ */
+ skb->csum_start = skb_transport_header(skb) - skb->head;
+ skb->csum_offset = 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_transport_offset(skb);
+ 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 = CSUM_MANGLED_0;
+ }
+}
+
+/*
+ * 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 = udp_sk(sk);
+ struct inet_sock *inet = inet_sk(sk);
+ struct flowi *fl = &inet->cork.fl;
+ struct sk_buff *skb;
+ struct udphdr *uh;
+ 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)
+ goto out;
+
+ /*
+ * Create a UDP header
+ */
+ 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 (is_udplite) /* 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;
+
+ } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware 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 = CSUM_MANGLED_0;
+
+send:
+ err = ip_push_pending_frames(sk);
+out:
+ up->len = 0;
+ up->pending = 0;
+ if (!err)
+ UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite);
+ return err;
+}
+
+int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+ size_t len)
+{
+ struct inet_sock *inet = inet_sk(sk);
+ struct udp_sock *up = udp_sk(sk);
+ int ulen = len;
+ struct ipcm_cookie ipc;
+ struct rtable *rt = NULL;
+ int free = 0;
+ int connected = 0;
+ __be32 daddr, faddr, saddr;
+ __be16 dport;
+ u8 tos;
+ int err, is_udplite = IS_UDPLITE(sk);
+ int corkreq = up->corkflag || msg->msg_flags&MSG_MORE;
+ int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
+
+ if (len > 0xFFFF)
+ return -EMSGSIZE;
+
+ /*
+ * Check the flags.
+ */
+
+ if (msg->msg_flags&MSG_OOB) /* Mirror BSD error message compatibility */
+ return -EOPNOTSUPP;
+
+ ipc.opt = NULL;
+
+ if (up->pending) {
+ /*
+ * There are pending frames.
+ * The socket lock must be held while it's corked.
+ */
+ lock_sock(sk);
+ if (likely(up->pending)) {
+ if (unlikely(up->pending != AF_INET)) {
+ release_sock(sk);
+ return -EINVAL;
+ }
+ goto do_append_data;
+ }
+ release_sock(sk);
+ }
+ ulen += sizeof(struct udphdr);
+
+ /*
+ * Get and verify the address.
+ */
+ if (msg->msg_name) {
+ struct sockaddr_in * usin = (struct sockaddr_in*)msg->msg_name;
+ if (msg->msg_namelen < sizeof(*usin))
+ return -EINVAL;
+ if (usin->sin_family != AF_INET) {
+ if (usin->sin_family != AF_UNSPEC)
+ return -EAFNOSUPPORT;
+ }
+
+ daddr = usin->sin_addr.s_addr;
+ dport = usin->sin_port;
+ if (dport == 0)
+ return -EINVAL;
+ } else {
+ if (sk->sk_state != TCP_ESTABLISHED)
+ return -EDESTADDRREQ;
+ daddr = inet->daddr;
+ dport = inet->dport;
+ /* Open fast path for connected socket.
+ Route will not be used, if at least one option is set.
+ */
+ connected = 1;
+ }
+ ipc.addr = inet->saddr;
+
+ ipc.oif = sk->sk_bound_dev_if;
+ if (msg->msg_controllen) {
+ err = ip_cmsg_send(msg, &ipc);
+ if (err)
+ return err;
+ if (ipc.opt)
+ free = 1;
+ connected = 0;
+ }
+ if (!ipc.opt)
+ ipc.opt = inet->opt;
+
+ saddr = ipc.addr;
+ ipc.addr = faddr = daddr;
+
+ if (ipc.opt && ipc.opt->srr) {
+ if (!daddr)
+ return -EINVAL;
+ faddr = ipc.opt->faddr;
+ connected = 0;
+ }
+ tos = RT_TOS(inet->tos);
+ if (sock_flag(sk, SOCK_LOCALROUTE) ||
+ (msg->msg_flags & MSG_DONTROUTE) ||
+ (ipc.opt && ipc.opt->is_strictroute)) {
+ tos |= RTO_ONLINK;
+ connected = 0;
+ }
+
+ if (ipv4_is_multicast(daddr)) {
+ if (!ipc.oif)
+ ipc.oif = inet->mc_index;
+ if (!saddr)
+ saddr = inet->mc_addr;
+ connected = 0;
+ }
+
+ if (connected)
+ rt = (struct rtable*)sk_dst_check(sk, 0);
+
+ if (rt == NULL) {
+ struct flowi fl = { .oif = ipc.oif,
+ .nl_u = { .ip4_u =
+ { .daddr = faddr,
+ .saddr = saddr,
+ .tos = tos } },
+ .proto = sk->sk_protocol,
+ .uli_u = { .ports =
+ { .sport = inet->sport,
+ .dport = dport } } };
+ security_sk_classify_flow(sk, &fl);
+ err = ip_route_output_flow(&init_net, &rt, &fl, sk, 1);
+ if (err) {
+ if (err == -ENETUNREACH)
+ IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
+ goto out;
+ }
+
+ err = -EACCES;
+ if ((rt->rt_flags & RTCF_BROADCAST) &&
+ !sock_flag(sk, SOCK_BROADCAST))
+ goto out;
+ if (connected)
+ sk_dst_set(sk, dst_clone(&rt->u.dst));
+ }
+
+ if (msg->msg_flags&MSG_CONFIRM)
+ goto do_confirm;
+back_from_confirm:
+
+ saddr = rt->rt_src;
+ if (!ipc.addr)
+ daddr = ipc.addr = rt->rt_dst;
+
+ lock_sock(sk);
+ if (unlikely(up->pending)) {
+ /* The socket is already corked while preparing it. */
+ /* ... which is an evident application bug. --ANK */
+ release_sock(sk);
+
+ LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 2\n");
+ err = -EINVAL;
+ goto out;
+ }
+ /*
+ * Now cork the socket to pend data.
+ */
+ inet->cork.fl.fl4_dst = daddr;
+ inet->cork.fl.fl_ip_dport = dport;
+ inet->cork.fl.fl4_src = saddr;
+ inet->cork.fl.fl_ip_sport = inet->sport;
+ up->pending = AF_INET;
+
+do_append_data:
+ up->len += ulen;
+ 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);
+ else if (!corkreq)
+ err = udp_push_pending_frames(sk);
+ else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
+ up->pending = 0;
+ release_sock(sk);
+
+out:
+ ip_rt_put(rt);
+ if (free)
+ kfree(ipc.opt);
+ 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
+ * we don't have a good statistic (IpOutDiscards but it can be too many
+ * things). We could add another new stat but at least for now that
+ * seems like overkill.
+ */
+ if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
+ UDP_INC_STATS_USER(UDP_MIB_SNDBUFERRORS, is_udplite);
+ }
+ return err;
+
+do_confirm:
+ dst_confirm(&rt->u.dst);
+ if (!(msg->msg_flags&MSG_PROBE) || len)
+ goto back_from_confirm;
+ err = 0;
+ goto out;
+}
+
+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;
+
+ if (!up->pending) {
+ struct msghdr msg = { .msg_flags = flags|MSG_MORE };
+
+ /* Call udp_sendmsg to specify destination address which
+ * sendpage interface can't pass.
+ * This will succeed only when the socket is connected.
+ */
+ ret = udp_sendmsg(NULL, sk, &msg, 0);
+ if (ret < 0)
+ return ret;
+ }
+
+ lock_sock(sk);
+
+ if (unlikely(!up->pending)) {
+ release_sock(sk);
+
+ LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 3\n");
+ return -EINVAL;
+ }
+
+ ret = ip_append_page(sk, page, offset, size, flags);
+ if (ret == -EOPNOTSUPP) {
+ release_sock(sk);
+ return sock_no_sendpage(sk->sk_socket, page, offset,
+ size, flags);
+ }
+ if (ret < 0) {
+ udp_flush_pending_frames(sk);
+ goto out;
+ }
+
+ up->len += size;
+ if (!(up->corkflag || (flags&MSG_MORE)))
+ ret = udp_push_pending_frames(sk);
+ if (!ret)
+ ret = size;
+out:
+ release_sock(sk);
+ return ret;
+}
+
+/*
+ * This should be easy, if there is something there we
+ * return it, otherwise we block.
+ */
+
+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;
+ unsigned int ulen, copied;
+ int peeked;
+ int err;
+ int is_udplite = IS_UDPLITE(sk);
+
+ /*
+ * Check any passed addresses
+ */
+ if (addr_len)
+ *addr_len=sizeof(*sin);
+
+ if (flags & MSG_ERRQUEUE)
+ return ip_recv_error(sk, msg, len);
+
+try_again:
+ skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
+ &peeked, &err);
+ if (!skb)
+ goto out;
+
+ ulen = skb->len - sizeof(struct udphdr);
+ copied = len;
+ if (copied > ulen)
+ copied = ulen;
+ else if (copied < ulen)
+ msg->msg_flags |= MSG_TRUNC;
+
+ /*
+ * 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;
+ }
+
+ 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)
+ UDP_INC_STATS_USER(UDP_MIB_INDATAGRAMS, is_udplite);
+
+ sock_recv_timestamp(msg, sk, skb);
+
+ /* Copy the address. */
+ if (sin)
+ {
+ sin->sin_family = AF_INET;
+ sin->sin_port = udp_hdr(skb)->source;
+ sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
+ memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+ }
+ if (inet->cmsg_flags)
+ ip_cmsg_recv(msg, skb);
+
+ err = copied;
+ if (flags & MSG_TRUNC)
+ err = ulen;
+
+out_free:
+ lock_sock(sk);
+ skb_free_datagram(sk, skb);
+ release_sock(sk);
+out:
+ return err;
+
+csum_copy_err:
+ lock_sock(sk);
+ if (!skb_kill_datagram(sk, skb, flags))
+ UDP_INC_STATS_USER(UDP_MIB_INERRORS, is_udplite);
+ release_sock(sk);
+
+ if (noblock)
+ return -EAGAIN;
+ goto try_again;
+}
+
+
+/* returns:
+ * -1: error
+ * 0: success
+ * >0: "udp encap" protocol resubmission
+ *
+ * Note that in the success and error cases, the skb is assumed to
+ * have either been requeued or freed.
+ */
+int udp_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);
+
+ /*
+ * Charge it to the socket, dropping if the queue is full.
+ */
+ if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
+ goto drop;
+ nf_reset(skb);
+
+ if (up->encap_type) {
+ /*
+ * This is an encapsulation socket so pass the skb to
+ * the socket's udp_encap_rcv() hook. Otherwise, just
+ * fall through and pass this up the UDP socket.
+ * up->encap_rcv() returns the following value:
+ * =0 if skb was successfully passed to the encap
+ * handler or was discarded by it.
+ * >0 if skb should be passed on to UDP.
+ * <0 if skb should be resubmitted as proto -N
+ */
+
+ /* if we're overly short, let UDP handle it */
+ if (skb->len > sizeof(struct udphdr) &&
+ up->encap_rcv != NULL) {
+ int ret;
+
+ ret = (*up->encap_rcv)(sk, skb);
+ if (ret <= 0) {
+ UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS,
+ is_udplite);
+ return -ret;
+ }
+ }
+
+ /* FALLTHROUGH -- it's a UDP Packet */
+ }
+
+ /*
+ * UDP-Lite specific tests, ignored on UDP sockets
+ */
+ if ((is_udplite & 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) {
+ 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)
+ UDP_INC_STATS_BH(UDP_MIB_RCVBUFERRORS, is_udplite);
+ goto drop;
+ }
+
+ return 0;
+
+drop:
+ UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite);
+ kfree_skb(skb);
+ return -1;
+}
+
+/*
+ * Multicasts and broadcasts go to each listener.
+ *
+ * Note: called only from the BH handler context,
+ * so we don't need to lock the hashes.
+ */
+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(&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) {
+ struct sock *sknext = NULL;
+
+ do {
+ struct sk_buff *skb1 = skb;
+
+ sknext = udp_v4_mcast_next(sk_next(sk), uh->dest, daddr,
+ uh->source, saddr, dif);
+ if (sknext)
+ skb1 = skb_clone(skb, GFP_ATOMIC);
+
+ if (skb1) {
+ int ret = 0;
+
+ bh_lock_sock_nested(sk);
+ if (!sock_owned_by_user(sk))
+ ret = udp_queue_rcv_skb(sk, skb1);
+ else
+ sk_add_backlog(sk, skb1);
+ bh_unlock_sock(sk);
+
+ if (ret > 0)
+ /* we should probably re-process instead
+ * of dropping packets here. */
+ kfree_skb(skb1);
+ }
+ sk = sknext;
+ } while (sknext);
+ } else
+ kfree_skb(skb);
+ read_unlock(&udp_hash_lock);
+ return 0;
+}
+
+/* Initialize UDP checksum. If exited with zero value (success),
+ * CHECKSUM_UNNECESSARY means, that no more checks are required.
+ * Otherwise, csum completion requires chacksumming packet body,
+ * including udp header and folding it to skb->csum.
+ */
+static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
+ int proto)
+{
+ const struct iphdr *iph;
+ int err;
+
+ UDP_SKB_CB(skb)->partial_cov = 0;
+ UDP_SKB_CB(skb)->cscov = skb->len;
+
+ if (IS_PROTO_UDPLITE(proto)) {
+ err = udplite_checksum_init(skb, uh);
+ if (err)
+ return err;
+ }
+
+ iph = ip_hdr(skb);
+ if (uh->check == 0) {
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ } else if (skb->ip_summed == CHECKSUM_COMPLETE) {
+ if (!csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
+ proto, skb->csum))
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ }
+ if (!skb_csum_unnecessary(skb))
+ skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
+ skb->len, proto, 0);
+ /* Probably, we should checksum udp header (it should be in cache
+ * in any case) and data in tiny packets (< rx copybreak).
+ */
+
+ return 0;
+}
+
+/*
+ * All we need to do is get the socket, and then do a checksum.
+ */
+
+int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
+ int proto)
+{
+ struct sock *sk;
+ struct udphdr *uh = udp_hdr(skb);
+ unsigned short ulen;
+ struct rtable *rt = (struct rtable*)skb->dst;
+ __be32 saddr = ip_hdr(skb)->saddr;
+ __be32 daddr = ip_hdr(skb)->daddr;
+
+ /*
+ * Validate the packet.
+ */
+ if (!pskb_may_pull(skb, sizeof(struct udphdr)))
+ goto drop; /* No space for header. */
+
+ ulen = ntohs(uh->len);
+ if (ulen > skb->len)
+ goto short_packet;
+
+ if (IS_PROTO_UDPLITE(proto)) {
+ /* UDP validates ulen. */
+ if (ulen < sizeof(*uh) || pskb_trim_rcsum(skb, ulen))
+ goto short_packet;
+ uh = udp_hdr(skb);
+ }
+
+ if (udp4_csum_init(skb, uh, proto))
+ goto csum_error;
+
+ if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
+ return __udp4_lib_mcast_deliver(skb, uh, saddr, daddr, udptable);
+
+ sk = __udp4_lib_lookup(skb->dev->nd_net, saddr, uh->source, daddr,
+ uh->dest, inet_iif(skb), udptable);
+
+ if (sk != NULL) {
+ int ret = 0;
+ bh_lock_sock_nested(sk);
+ if (!sock_owned_by_user(sk))
+ ret = udp_queue_rcv_skb(sk, skb);
+ else
+ sk_add_backlog(sk, skb);
+ bh_unlock_sock(sk);
+ sock_put(sk);
+
+ /* a return value > 0 means to resubmit the input, but
+ * it wants the return to be -protocol, or 0
+ */
+ if (ret > 0)
+ return -ret;
+ return 0;
+ }
+
+ if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+ goto drop;
+ nf_reset(skb);
+
+ /* No socket. Drop packet silently, if checksum is wrong */
+ if (udp_lib_checksum_complete(skb))
+ goto csum_error;
+
+ UDP_INC_STATS_BH(UDP_MIB_NOPORTS, IS_PROTO_UDPLITE(proto));
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
+
+ /*
+ * Hmm. We got an UDP packet to a port to which we
+ * don't wanna listen. Ignore it.
+ */
+ kfree_skb(skb);
+ return 0;
+
+short_packet:
+ LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: short packet: From %u.%u.%u.%u:%u %d/%d to %u.%u.%u.%u:%u\n",
+ IS_PROTO_UDPLITE(proto) ? "-Lite" : "",
+ NIPQUAD(saddr),
+ ntohs(uh->source),
+ ulen,
+ skb->len,
+ NIPQUAD(daddr),
+ ntohs(uh->dest));
+ 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%s: bad checksum. From %d.%d.%d.%d:%d to %d.%d.%d.%d:%d ulen %d\n",
+ IS_PROTO_UDPLITE(proto) ? "-Lite" : "",
+ NIPQUAD(saddr),
+ ntohs(uh->source),
+ NIPQUAD(daddr),
+ ntohs(uh->dest),
+ ulen);
+drop:
+ UDP_INC_STATS_BH(UDP_MIB_INERRORS, IS_PROTO_UDPLITE(proto));
+ kfree_skb(skb);
+ return 0;
+}
+
+int udp_rcv(struct sk_buff *skb)
+{
+ return __udp4_lib_rcv(skb, udp_hash, IPPROTO_UDP);
+}
+
+int udp_destroy_sock(struct sock *sk)
+{
+ lock_sock(sk);
+ udp_flush_pending_frames(sk);
+ release_sock(sk);
+ return 0;
+}
+
+int udp_setsockopt(struct sock *sk, int level, int optname,
+ char __user *optval, int optlen)
+{
+ if (IS_SOL_UDPFAMILY(level))
+ return udp_lib_setsockopt(sk, level, optname, optval, optlen,
+ udp_push_pending_frames);
+ return ip_setsockopt(sk, level, optname, optval, optlen);
+}
+
+#ifdef CONFIG_COMPAT
+int compat_udp_setsockopt(struct sock *sk, int level, int optname,
+ char __user *optval, int optlen)
+{
+ if (IS_SOL_UDPFAMILY(level))
+ return udp_lib_setsockopt(sk, level, optname, optval, optlen,
+ udp_push_pending_frames);
+ return compat_ip_setsockopt(sk, level, optname, optval, optlen);
+}
+#endif
+
+int udp_getsockopt(struct sock *sk, int level, int optname,
+ char __user *optval, int __user *optlen)
+{
+ if (IS_SOL_UDPFAMILY(level))
+ return udp_lib_getsockopt(sk, level, optname, optval, optlen);
+ return ip_getsockopt(sk, level, optname, optval, optlen);
+}
+
+#ifdef CONFIG_COMPAT
+int compat_udp_getsockopt(struct sock *sk, int level, int optname,
+ char __user *optval, int __user *optlen)
+{
+ if (IS_SOL_UDPFAMILY(level))
+ return udp_lib_getsockopt(sk, level, optname, optval, optlen);
+ return compat_ip_getsockopt(sk, level, optname, optval, optlen);
+}
+#endif
+
+/* ------------------------------------------------------------------------ */
+DEFINE_PROTO_INUSE(udp)
+
+struct proto udp_prot = {
+ .name = "UDP",
+ .owner = THIS_MODULE,
+ .close = udp_lib_close,
+ .connect = ip4_datagram_connect,
+ .disconnect = udp_disconnect,
+ .ioctl = udp_ioctl,
+ .destroy = udp_destroy_sock,
+ .setsockopt = udp_setsockopt,
+ .getsockopt = udp_getsockopt,
+ .sendmsg = udp_sendmsg,
+ .recvmsg = udp_recvmsg,
+ .sendpage = udp_sendpage,
+ .backlog_rcv = udp_queue_rcv_skb,
+ .hash = udp_lib_hash,
+ .unhash = udp_lib_unhash,
+ .get_port = udp_v4_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 udp_sock),
+#ifdef CONFIG_COMPAT
+ .compat_setsockopt = compat_udp_setsockopt,
+ .compat_getsockopt = compat_udp_getsockopt,
+#endif
+ REF_PROTO_INUSE(udp)
+};
+
+/* ------------------------------------------------------------------------ */
+static void udp4_format_sock(struct sock *sp, char *tmpbuf, int bucket)
+{
+ struct inet_sock *inet = inet_sk(sp);
+ __be32 dest = inet->daddr;
+ __be32 src = inet->rcv_saddr;
+ __u16 destp = ntohs(inet->dport);
+ __u16 srcp = ntohs(inet->sport);
+
+ sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X"
+ " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p",
+ bucket, src, srcp, dest, destp, 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);
+}
+
+int udp4_seq_show(struct seq_file *seq, void *v)
+{
+ if (v == SEQ_START_TOKEN)
+ seq_printf(seq, "%-127s\n",
+ " sl local_address rem_address st tx_queue "
+ "rx_queue tr tm->when retrnsmt uid timeout "
+ "inode");
+ else {
+ char tmpbuf[129];
+ struct udp_iter_state *state = seq->private;
+
+ udp4_format_sock(v, tmpbuf, state->bucket);
+ seq_printf(seq, "%-127s\n", tmpbuf);
+ }
+ return 0;
+}
+
+/* ------------------------------------------------------------------------ */
+#ifdef CONFIG_PROC_FS
+static struct file_operations udp4_seq_fops;
+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,
+};
+
+int __init udp4_proc_init(void)
+{
+ return udp_proc_register(&udp4_seq_afinfo);
+}
+
+void udp4_proc_exit(void)
+{
+ udp_proc_unregister(&udp4_seq_afinfo);
+}
+#endif /* CONFIG_PROC_FS */
+
+EXPORT_SYMBOL(udp_prot);
+EXPORT_SYMBOL(udp_sendmsg);
+
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite_ipv4.c
index 001b881ca36..001b881ca36 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite_ipv4.c
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-14 15:12:08 +0000