summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/devinet.c15
-rw-r--r--net/ipv4/icmp.c22
-rw-r--r--net/ipv4/inet_timewait_sock.c35
-rw-r--r--net/ipv4/route.c24
-rw-r--r--net/ipv4/tcp_ipv4.c3
-rw-r--r--net/ipv4/tcp_output.c6
-rw-r--r--net/ipv4/udp.c62
7 files changed, 120 insertions, 47 deletions
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 91d3d96805d0..b12dae2b0b2d 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1029,6 +1029,11 @@ skip:
}
}
+static inline bool inetdev_valid_mtu(unsigned mtu)
+{
+ return mtu >= 68;
+}
+
/* Called only under RTNL semaphore */
static int inetdev_event(struct notifier_block *this, unsigned long event,
@@ -1048,6 +1053,10 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
IN_DEV_CONF_SET(in_dev, NOXFRM, 1);
IN_DEV_CONF_SET(in_dev, NOPOLICY, 1);
}
+ } else if (event == NETDEV_CHANGEMTU) {
+ /* Re-enabling IP */
+ if (inetdev_valid_mtu(dev->mtu))
+ in_dev = inetdev_init(dev);
}
goto out;
}
@@ -1058,7 +1067,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
dev->ip_ptr = NULL;
break;
case NETDEV_UP:
- if (dev->mtu < 68)
+ if (!inetdev_valid_mtu(dev->mtu))
break;
if (dev->flags & IFF_LOOPBACK) {
struct in_ifaddr *ifa;
@@ -1080,9 +1089,9 @@ static int inetdev_event(struct notifier_block *this, unsigned long event,
ip_mc_down(in_dev);
break;
case NETDEV_CHANGEMTU:
- if (dev->mtu >= 68)
+ if (inetdev_valid_mtu(dev->mtu))
break;
- /* MTU falled under 68, disable IP */
+ /* disable IP when MTU is not enough */
case NETDEV_UNREGISTER:
inetdev_destroy(in_dev);
break;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 860558633b2c..55c355e63234 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -204,18 +204,22 @@ static struct sock *icmp_sk(struct net *net)
return net->ipv4.icmp_sk[smp_processor_id()];
}
-static inline int icmp_xmit_lock(struct sock *sk)
+static inline struct sock *icmp_xmit_lock(struct net *net)
{
+ struct sock *sk;
+
local_bh_disable();
+ sk = icmp_sk(net);
+
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.
*/
local_bh_enable();
- return 1;
+ return NULL;
}
- return 0;
+ return sk;
}
static inline void icmp_xmit_unlock(struct sock *sk)
@@ -354,15 +358,17 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
struct ipcm_cookie ipc;
struct rtable *rt = skb->rtable;
struct net *net = dev_net(rt->u.dst.dev);
- struct sock *sk = icmp_sk(net);
- struct inet_sock *inet = inet_sk(sk);
+ struct sock *sk;
+ struct inet_sock *inet;
__be32 daddr;
if (ip_options_echo(&icmp_param->replyopts, skb))
return;
- if (icmp_xmit_lock(sk))
+ sk = icmp_xmit_lock(net);
+ if (sk == NULL)
return;
+ inet = inet_sk(sk);
icmp_param->data.icmph.checksum = 0;
@@ -419,7 +425,6 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
if (!rt)
goto out;
net = dev_net(rt->u.dst.dev);
- sk = icmp_sk(net);
/*
* Find the original header. It is expected to be valid, of course.
@@ -483,7 +488,8 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
}
}
- if (icmp_xmit_lock(sk))
+ sk = icmp_xmit_lock(net);
+ if (sk == NULL)
return;
/*
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index d985bd613d25..743f011b9a84 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -409,3 +409,38 @@ out:
}
EXPORT_SYMBOL_GPL(inet_twdr_twcal_tick);
+
+void inet_twsk_purge(struct net *net, struct inet_hashinfo *hashinfo,
+ struct inet_timewait_death_row *twdr, int family)
+{
+ struct inet_timewait_sock *tw;
+ struct sock *sk;
+ struct hlist_node *node;
+ int h;
+
+ local_bh_disable();
+ for (h = 0; h < (hashinfo->ehash_size); h++) {
+ struct inet_ehash_bucket *head =
+ inet_ehash_bucket(hashinfo, h);
+ rwlock_t *lock = inet_ehash_lockp(hashinfo, h);
+restart:
+ write_lock(lock);
+ sk_for_each(sk, node, &head->twchain) {
+
+ tw = inet_twsk(sk);
+ if (!net_eq(twsk_net(tw), net) ||
+ tw->tw_family != family)
+ continue;
+
+ atomic_inc(&tw->tw_refcnt);
+ write_unlock(lock);
+ inet_twsk_deschedule(tw, twdr);
+ inet_twsk_put(tw);
+
+ goto restart;
+ }
+ write_unlock(lock);
+ }
+ local_bh_enable();
+}
+EXPORT_SYMBOL_GPL(inet_twsk_purge);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index cca921ea8550..6ee5354c9aa1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -3116,14 +3116,23 @@ static ctl_table ipv4_route_table[] = {
{ .ctl_name = 0 }
};
-static __net_initdata struct ctl_path ipv4_route_path[] = {
+static struct ctl_table empty[1];
+
+static struct ctl_table ipv4_skeleton[] =
+{
+ { .procname = "route", .ctl_name = NET_IPV4_ROUTE,
+ .mode = 0555, .child = ipv4_route_table},
+ { .procname = "neigh", .ctl_name = NET_IPV4_NEIGH,
+ .mode = 0555, .child = empty},
+ { }
+};
+
+static __net_initdata struct ctl_path ipv4_path[] = {
{ .procname = "net", .ctl_name = CTL_NET, },
{ .procname = "ipv4", .ctl_name = NET_IPV4, },
- { .procname = "route", .ctl_name = NET_IPV4_ROUTE, },
{ },
};
-
static struct ctl_table ipv4_route_flush_table[] = {
{
.ctl_name = NET_IPV4_ROUTE_FLUSH,
@@ -3136,6 +3145,13 @@ static struct ctl_table ipv4_route_flush_table[] = {
{ .ctl_name = 0 },
};
+static __net_initdata struct ctl_path ipv4_route_path[] = {
+ { .procname = "net", .ctl_name = CTL_NET, },
+ { .procname = "ipv4", .ctl_name = NET_IPV4, },
+ { .procname = "route", .ctl_name = NET_IPV4_ROUTE, },
+ { },
+};
+
static __net_init int sysctl_route_net_init(struct net *net)
{
struct ctl_table *tbl;
@@ -3287,7 +3303,7 @@ int __init ip_rt_init(void)
*/
void __init ip_static_sysctl_init(void)
{
- register_sysctl_paths(ipv4_route_path, ipv4_route_table);
+ register_sysctl_paths(ipv4_path, ipv4_skeleton);
}
#endif
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 44c1e934824b..011478e46c40 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -618,7 +618,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
];
} rep;
struct ip_reply_arg arg;
- struct net *net = dev_net(skb->dev);
+ struct net *net = dev_net(skb->dst->dev);
memset(&rep.th, 0, sizeof(struct tcphdr));
memset(&arg, 0, sizeof(arg));
@@ -2376,6 +2376,7 @@ static int __net_init tcp_sk_init(struct net *net)
static void __net_exit tcp_sk_exit(struct net *net)
{
inet_ctl_sock_destroy(net->ipv4.tcp_sock);
+ inet_twsk_purge(net, &tcp_hashinfo, &tcp_death_row, AF_INET);
}
static struct pernet_operations __net_initdata tcp_sk_ops = {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index a00532de2a8c..8165f5aa8c71 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -468,7 +468,8 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
}
if (likely(sysctl_tcp_window_scaling)) {
opts->ws = tp->rx_opt.rcv_wscale;
- size += TCPOLEN_WSCALE_ALIGNED;
+ if(likely(opts->ws))
+ size += TCPOLEN_WSCALE_ALIGNED;
}
if (likely(sysctl_tcp_sack)) {
opts->options |= OPTION_SACK_ADVERTISE;
@@ -509,7 +510,8 @@ static unsigned tcp_synack_options(struct sock *sk,
if (likely(ireq->wscale_ok)) {
opts->ws = ireq->rcv_wscale;
- size += TCPOLEN_WSCALE_ALIGNED;
+ if(likely(opts->ws))
+ size += TCPOLEN_WSCALE_ALIGNED;
}
if (likely(doing_ts)) {
opts->options |= OPTION_TS;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 8e42fbbd5761..57e26fa66185 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -951,6 +951,27 @@ int udp_disconnect(struct sock *sk, int flags)
return 0;
}
+static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+ int is_udplite = IS_UDPLITE(sk);
+ int rc;
+
+ if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) {
+ /* Note that an ENOMEM error is charged twice */
+ if (rc == -ENOMEM)
+ UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS,
+ is_udplite);
+ goto drop;
+ }
+
+ return 0;
+
+drop:
+ UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
+ kfree_skb(skb);
+ return -1;
+}
+
/* returns:
* -1: error
* 0: success
@@ -989,9 +1010,7 @@ int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
up->encap_rcv != NULL) {
int ret;
- bh_unlock_sock(sk);
ret = (*up->encap_rcv)(sk, skb);
- bh_lock_sock(sk);
if (ret <= 0) {
UDP_INC_STATS_BH(sock_net(sk),
UDP_MIB_INDATAGRAMS,
@@ -1044,17 +1063,16 @@ int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *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(sock_net(sk),
- UDP_MIB_RCVBUFERRORS, is_udplite);
- atomic_inc(&sk->sk_drops);
- }
- goto drop;
- }
+ rc = 0;
- return 0;
+ bh_lock_sock(sk);
+ if (!sock_owned_by_user(sk))
+ rc = __udp_queue_rcv_skb(sk, skb);
+ else
+ sk_add_backlog(sk, skb);
+ bh_unlock_sock(sk);
+
+ return rc;
drop:
UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
@@ -1092,15 +1110,7 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
skb1 = skb_clone(skb, GFP_ATOMIC);
if (skb1) {
- int ret = 0;
-
- bh_lock_sock(sk);
- if (!sock_owned_by_user(sk))
- ret = udp_queue_rcv_skb(sk, skb1);
- else
- sk_add_backlog(sk, skb1);
- bh_unlock_sock(sk);
-
+ int ret = udp_queue_rcv_skb(sk, skb1);
if (ret > 0)
/* we should probably re-process instead
* of dropping packets here. */
@@ -1195,13 +1205,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
uh->dest, inet_iif(skb), udptable);
if (sk != NULL) {
- int ret = 0;
- bh_lock_sock(sk);
- if (!sock_owned_by_user(sk))
- ret = udp_queue_rcv_skb(sk, skb);
- else
- sk_add_backlog(sk, skb);
- bh_unlock_sock(sk);
+ int ret = udp_queue_rcv_skb(sk, skb);
sock_put(sk);
/* a return value > 0 means to resubmit the input, but
@@ -1494,7 +1498,7 @@ struct proto udp_prot = {
.sendmsg = udp_sendmsg,
.recvmsg = udp_recvmsg,
.sendpage = udp_sendpage,
- .backlog_rcv = udp_queue_rcv_skb,
+ .backlog_rcv = __udp_queue_rcv_skb,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
.get_port = udp_v4_get_port,