summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c7
-rw-r--r--net/ipv4/arp.c4
-rw-r--r--net/ipv4/devinet.c35
-rw-r--r--net/ipv4/fib_frontend.c19
-rw-r--r--net/ipv4/fib_hash.c8
-rw-r--r--net/ipv4/fib_rules.c4
-rw-r--r--net/ipv4/fib_semantics.c2
-rw-r--r--net/ipv4/fib_trie.c8
-rw-r--r--net/ipv4/icmp.c2
-rw-r--r--net/ipv4/igmp.c2
-rw-r--r--net/ipv4/inet_connection_sock.c6
-rw-r--r--net/ipv4/inet_diag.c2
-rw-r--r--net/ipv4/inet_hashtables.c19
-rw-r--r--net/ipv4/inet_timewait_sock.c6
-rw-r--r--net/ipv4/inetpeer.c2
-rw-r--r--net/ipv4/ip_forward.c5
-rw-r--r--net/ipv4/ip_fragment.c36
-rw-r--r--net/ipv4/ip_gre.c32
-rw-r--r--net/ipv4/ip_input.c2
-rw-r--r--net/ipv4/ip_options.c2
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/ip_sockglue.c2
-rw-r--r--net/ipv4/ipconfig.c2
-rw-r--r--net/ipv4/ipip.c24
-rw-r--r--net/ipv4/ipmr.c59
-rw-r--r--net/ipv4/ipvs/ip_vs_app.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_conn.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_core.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_ctl.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_dh.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_est.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_ftp.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_lblc.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_lblcr.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_lc.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_nq.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_proto.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_proto_ah.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_proto_esp.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_proto_tcp.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_proto_udp.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_rr.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_sched.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_sed.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_sh.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_sync.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_wlc.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_wrr.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_xmit.c2
-rw-r--r--net/ipv4/netfilter/Kconfig15
-rw-r--r--net/ipv4/netfilter/Makefile1
-rw-r--r--net/ipv4/netfilter/ip_queue.c3
-rw-r--r--net/ipv4/netfilter/iptable_security.c180
-rw-r--r--net/ipv4/netfilter/nf_conntrack_proto_icmp.c5
-rw-r--r--net/ipv4/proc.c2
-rw-r--r--net/ipv4/protocol.c2
-rw-r--r--net/ipv4/raw.c7
-rw-r--r--net/ipv4/route.c259
-rw-r--r--net/ipv4/syncookies.c2
-rw-r--r--net/ipv4/sysctl_net_ipv4.c5
-rw-r--r--net/ipv4/tcp.c72
-rw-r--r--net/ipv4/tcp_diag.c2
-rw-r--r--net/ipv4/tcp_input.c88
-rw-r--r--net/ipv4/tcp_ipv4.c170
-rw-r--r--net/ipv4/tcp_minisocks.c2
-rw-r--r--net/ipv4/tcp_output.c12
-rw-r--r--net/ipv4/tcp_timer.c17
-rw-r--r--net/ipv4/udp.c62
-rw-r--r--net/ipv4/udp_impl.h2
-rw-r--r--net/ipv4/udplite.c2
70 files changed, 766 insertions, 484 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 24eca23c2db..dc411335c14 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -5,8 +5,6 @@
*
* PF_INET protocol family socket handler.
*
- * Version: $Id: af_inet.c,v 1.137 2002/02/01 22:01:03 davem Exp $
- *
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Florian La Roche, <flla@stud.uni-sb.de>
@@ -1481,14 +1479,15 @@ static int __init inet_init(void)
* Initialise the multicast router
*/
#if defined(CONFIG_IP_MROUTE)
- ip_mr_init();
+ if (ip_mr_init())
+ printk(KERN_CRIT "inet_init: Cannot init ipv4 mroute\n");
#endif
/*
* Initialise per-cpu ipv4 mibs
*/
if (init_ipv4_mibs())
- printk(KERN_CRIT "inet_init: Cannot init ipv4 mibs\n"); ;
+ printk(KERN_CRIT "inet_init: Cannot init ipv4 mibs\n");
ipv4_proc_init();
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 9b539fa9fe1..29df75a6bcc 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1,7 +1,5 @@
/* linux/net/ipv4/arp.c
*
- * Version: $Id: arp.c,v 1.99 2001/08/30 22:55:42 davem Exp $
- *
* Copyright (C) 1994 by Florian La Roche
*
* This module implements the Address Resolution Protocol ARP (RFC 826),
@@ -1199,7 +1197,7 @@ static int arp_netdev_event(struct notifier_block *this, unsigned long event, vo
switch (event) {
case NETDEV_CHANGEADDR:
neigh_changeaddr(&arp_tbl, dev);
- rt_cache_flush(0);
+ rt_cache_flush(dev_net(dev), 0);
break;
default:
break;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 79a7ef6209f..2e667e2f90d 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1,8 +1,6 @@
/*
* NET3 IP device support routines.
*
- * Version: $Id: devinet.c,v 1.44 2001/10/31 21:55:54 davem Exp $
- *
* 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
@@ -170,6 +168,8 @@ static struct in_device *inetdev_init(struct net_device *dev)
in_dev->dev = dev;
if ((in_dev->arp_parms = neigh_parms_alloc(dev, &arp_tbl)) == NULL)
goto out_kfree;
+ if (IPV4_DEVCONF(in_dev->cnf, FORWARDING))
+ dev_disable_lro(dev);
/* Reference in_dev->dev */
dev_hold(dev);
/* Account for reference dev->ip_ptr (below) */
@@ -1013,7 +1013,7 @@ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev)
memcpy(old, ifa->ifa_label, IFNAMSIZ);
memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
if (named++ == 0)
- continue;
+ goto skip;
dot = strchr(old, ':');
if (dot == NULL) {
sprintf(old, ":%d", named);
@@ -1024,6 +1024,8 @@ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev)
} else {
strcpy(ifa->ifa_label + (IFNAMSIZ - strlen(dot) - 1), dot);
}
+skip:
+ rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0);
}
}
@@ -1241,6 +1243,8 @@ static void inet_forward_change(struct net *net)
read_lock(&dev_base_lock);
for_each_netdev(net, dev) {
struct in_device *in_dev;
+ if (on)
+ dev_disable_lro(dev);
rcu_read_lock();
in_dev = __in_dev_get_rcu(dev);
if (in_dev)
@@ -1248,8 +1252,6 @@ static void inet_forward_change(struct net *net)
rcu_read_unlock();
}
read_unlock(&dev_base_lock);
-
- rt_cache_flush(0);
}
static int devinet_conf_proc(ctl_table *ctl, int write,
@@ -1335,10 +1337,19 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write,
if (write && *valp != val) {
struct net *net = ctl->extra2;
- if (valp == &IPV4_DEVCONF_ALL(net, FORWARDING))
- inet_forward_change(net);
- else if (valp != &IPV4_DEVCONF_DFLT(net, FORWARDING))
- rt_cache_flush(0);
+ if (valp != &IPV4_DEVCONF_DFLT(net, FORWARDING)) {
+ rtnl_lock();
+ if (valp == &IPV4_DEVCONF_ALL(net, FORWARDING)) {
+ inet_forward_change(net);
+ } else if (*valp) {
+ struct ipv4_devconf *cnf = ctl->extra1;
+ struct in_device *idev =
+ container_of(cnf, struct in_device, cnf);
+ dev_disable_lro(idev->dev);
+ }
+ rtnl_unlock();
+ rt_cache_flush(net, 0);
+ }
}
return ret;
@@ -1351,9 +1362,10 @@ int ipv4_doint_and_flush(ctl_table *ctl, int write,
int *valp = ctl->data;
int val = *valp;
int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
+ struct net *net = ctl->extra2;
if (write && *valp != val)
- rt_cache_flush(0);
+ rt_cache_flush(net, 0);
return ret;
}
@@ -1364,9 +1376,10 @@ int ipv4_doint_and_flush_strategy(ctl_table *table, int __user *name, int nlen,
{
int ret = devinet_conf_sysctl(table, name, nlen, oldval, oldlenp,
newval, newlen);
+ struct net *net = table->extra2;
if (ret == 1)
- rt_cache_flush(0);
+ rt_cache_flush(net, 0);
return ret;
}
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 0b2ac6a3d90..65c1503f8cc 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -5,8 +5,6 @@
*
* IPv4 Forwarding Information Base: FIB frontend.
*
- * Version: $Id: fib_frontend.c,v 1.26 2001/10/31 21:55:54 davem Exp $
- *
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* This program is free software; you can redistribute it and/or
@@ -146,7 +144,7 @@ static void fib_flush(struct net *net)
}
if (flushed)
- rt_cache_flush(-1);
+ rt_cache_flush(net, -1);
}
/*
@@ -899,21 +897,22 @@ static void fib_disable_ip(struct net_device *dev, int force)
{
if (fib_sync_down_dev(dev, force))
fib_flush(dev_net(dev));
- rt_cache_flush(0);
+ rt_cache_flush(dev_net(dev), 0);
arp_ifdown(dev);
}
static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr)
{
struct in_ifaddr *ifa = (struct in_ifaddr*)ptr;
+ struct net_device *dev = ifa->ifa_dev->dev;
switch (event) {
case NETDEV_UP:
fib_add_ifaddr(ifa);
#ifdef CONFIG_IP_ROUTE_MULTIPATH
- fib_sync_up(ifa->ifa_dev->dev);
+ fib_sync_up(dev);
#endif
- rt_cache_flush(-1);
+ rt_cache_flush(dev_net(dev), -1);
break;
case NETDEV_DOWN:
fib_del_ifaddr(ifa);
@@ -921,9 +920,9 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
/* Last address was deleted from this interface.
Disable IP.
*/
- fib_disable_ip(ifa->ifa_dev->dev, 1);
+ fib_disable_ip(dev, 1);
} else {
- rt_cache_flush(-1);
+ rt_cache_flush(dev_net(dev), -1);
}
break;
}
@@ -951,14 +950,14 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
#ifdef CONFIG_IP_ROUTE_MULTIPATH
fib_sync_up(dev);
#endif
- rt_cache_flush(-1);
+ rt_cache_flush(dev_net(dev), -1);
break;
case NETDEV_DOWN:
fib_disable_ip(dev, 0);
break;
case NETDEV_CHANGEMTU:
case NETDEV_CHANGE:
- rt_cache_flush(0);
+ rt_cache_flush(dev_net(dev), 0);
break;
}
return NOTIFY_DONE;
diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c
index 2e2fc3376ac..c8cac6c7f88 100644
--- a/net/ipv4/fib_hash.c
+++ b/net/ipv4/fib_hash.c
@@ -5,8 +5,6 @@
*
* IPv4 FIB: lookup engine and maintenance routines.
*
- * Version: $Id: fib_hash.c,v 1.13 2001/10/31 21:55:54 davem Exp $
- *
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* This program is free software; you can redistribute it and/or
@@ -474,7 +472,7 @@ static int fn_hash_insert(struct fib_table *tb, struct fib_config *cfg)
fib_release_info(fi_drop);
if (state & FA_S_ACCESSED)
- rt_cache_flush(-1);
+ rt_cache_flush(cfg->fc_nlinfo.nl_net, -1);
rtmsg_fib(RTM_NEWROUTE, key, fa, cfg->fc_dst_len, tb->tb_id,
&cfg->fc_nlinfo, NLM_F_REPLACE);
return 0;
@@ -534,7 +532,7 @@ static int fn_hash_insert(struct fib_table *tb, struct fib_config *cfg)
if (new_f)
fz->fz_nent++;
- rt_cache_flush(-1);
+ rt_cache_flush(cfg->fc_nlinfo.nl_net, -1);
rtmsg_fib(RTM_NEWROUTE, key, new_fa, cfg->fc_dst_len, tb->tb_id,
&cfg->fc_nlinfo, 0);
@@ -616,7 +614,7 @@ static int fn_hash_delete(struct fib_table *tb, struct fib_config *cfg)
write_unlock_bh(&fib_hash_lock);
if (fa->fa_state & FA_S_ACCESSED)
- rt_cache_flush(-1);
+ rt_cache_flush(cfg->fc_nlinfo.nl_net, -1);
fn_free_alias(fa, f);
if (kill_fn) {
fn_free_node(f);
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 1fb56876be5..6080d712082 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -258,9 +258,9 @@ static size_t fib4_rule_nlmsg_payload(struct fib_rule *rule)
+ nla_total_size(4); /* flow */
}
-static void fib4_rule_flush_cache(void)
+static void fib4_rule_flush_cache(struct fib_rules_ops *ops)
{
- rt_cache_flush(-1);
+ rt_cache_flush(ops->fro_net, -1);
}
static struct fib_rules_ops fib4_rules_ops_template = {
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 0d4d72827e4..ded2ae34eab 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -5,8 +5,6 @@
*
* IPv4 Forwarding Information Base: semantics.
*
- * Version: $Id: fib_semantics.c,v 1.19 2002/01/12 07:54:56 davem Exp $
- *
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* This program is free software; you can redistribute it and/or
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index e1600ad8fb0..f155a66d6eb 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -22,8 +22,6 @@
* IP-address lookup using LC-tries. Stefan Nilsson and Gunnar Karlsson
* IEEE Journal on Selected Areas in Communications, 17(6):1083-1092, June 1999
*
- * Version: $Id: fib_trie.c,v 1.3 2005/06/08 14:20:01 robert Exp $
- *
*
* Code from fib_hash has been reused which includes the following header:
*
@@ -1273,7 +1271,7 @@ static int fn_trie_insert(struct fib_table *tb, struct fib_config *cfg)
fib_release_info(fi_drop);
if (state & FA_S_ACCESSED)
- rt_cache_flush(-1);
+ rt_cache_flush(cfg->fc_nlinfo.nl_net, -1);
rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen,
tb->tb_id, &cfg->fc_nlinfo, NLM_F_REPLACE);
@@ -1318,7 +1316,7 @@ static int fn_trie_insert(struct fib_table *tb, struct fib_config *cfg)
list_add_tail_rcu(&new_fa->fa_list,
(fa ? &fa->fa_list : fa_head));
- rt_cache_flush(-1);
+ rt_cache_flush(cfg->fc_nlinfo.nl_net, -1);
rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id,
&cfg->fc_nlinfo, 0);
succeeded:
@@ -1661,7 +1659,7 @@ static int fn_trie_delete(struct fib_table *tb, struct fib_config *cfg)
trie_leaf_remove(t, l);
if (fa->fa_state & FA_S_ACCESSED)
- rt_cache_flush(-1);
+ rt_cache_flush(cfg->fc_nlinfo.nl_net, -1);
fib_release_info(fa->fa_info);
alias_free_mem_rcu(fa);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 87397351dda..aa7cf46853b 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -3,8 +3,6 @@
*
* Alan Cox, <alan@redhat.com>
*
- * Version: $Id: icmp.c,v 1.85 2002/02/01 22:01:03 davem Exp $
- *
* 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
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 2769dc4a4c8..68e84a933e9 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -8,8 +8,6 @@
* the older version didn't come out right using gcc 2.5.8, the newer one
* seems to fall out with gcc 2.6.2.
*
- * Version: $Id: igmp.c,v 1.47 2002/02/01 22:01:03 davem Exp $
- *
* Authors:
* Alan Cox <Alan.Cox@linux.org>
*
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index ec834480abe..5bbf0005151 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -103,7 +103,8 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
rover = net_random() % remaining + low;
do {
- head = &hashinfo->bhash[inet_bhashfn(rover, hashinfo->bhash_size)];
+ head = &hashinfo->bhash[inet_bhashfn(net, rover,
+ hashinfo->bhash_size)];
spin_lock(&head->lock);
inet_bind_bucket_for_each(tb, node, &head->chain)
if (tb->ib_net == net && tb->port == rover)
@@ -130,7 +131,8 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
*/
snum = rover;
} else {
- head = &hashinfo->bhash[inet_bhashfn(snum, hashinfo->bhash_size)];
+ head = &hashinfo->bhash[inet_bhashfn(net, snum,
+ hashinfo->bhash_size)];
spin_lock(&head->lock);
inet_bind_bucket_for_each(tb, node, &head->chain)
if (tb->ib_net == net && tb->port == snum)
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index da97695e709..c10036e7a46 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -1,8 +1,6 @@
/*
* inet_diag.c Module for monitoring INET transport protocols sockets.
*
- * Version: $Id: inet_diag.c,v 1.3 2002/02/01 22:01:04 davem Exp $
- *
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* This program is free software; you can redistribute it and/or
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 2023d37b270..eca5899729e 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -70,7 +70,8 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
static void __inet_put_port(struct sock *sk)
{
struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
- const int bhash = inet_bhashfn(inet_sk(sk)->num, hashinfo->bhash_size);
+ const int bhash = inet_bhashfn(sock_net(sk), inet_sk(sk)->num,
+ hashinfo->bhash_size);
struct inet_bind_hashbucket *head = &hashinfo->bhash[bhash];
struct inet_bind_bucket *tb;
@@ -95,7 +96,8 @@ EXPORT_SYMBOL(inet_put_port);
void __inet_inherit_port(struct sock *sk, struct sock *child)
{
struct inet_hashinfo *table = sk->sk_prot->h.hashinfo;
- const int bhash = inet_bhashfn(inet_sk(child)->num, table->bhash_size);
+ const int bhash = inet_bhashfn(sock_net(sk), inet_sk(child)->num,
+ table->bhash_size);
struct inet_bind_hashbucket *head = &table->bhash[bhash];
struct inet_bind_bucket *tb;
@@ -192,7 +194,7 @@ struct sock *__inet_lookup_listener(struct net *net,
const struct hlist_head *head;
read_lock(&hashinfo->lhash_lock);
- head = &hashinfo->listening_hash[inet_lhashfn(hnum)];
+ head = &hashinfo->listening_hash[inet_lhashfn(net, hnum)];
if (!hlist_empty(head)) {
const struct inet_sock *inet = inet_sk((sk = __sk_head(head)));
@@ -225,7 +227,7 @@ struct sock * __inet_lookup_established(struct net *net,
/* Optimize here for direct hit, only listening connections can
* have wildcards anyways.
*/
- unsigned int hash = inet_ehashfn(daddr, hnum, saddr, sport);
+ unsigned int hash = inet_ehashfn(net, daddr, hnum, saddr, sport);
struct inet_ehash_bucket *head = inet_ehash_bucket(hashinfo, hash);
rwlock_t *lock = inet_ehash_lockp(hashinfo, hash);
@@ -265,13 +267,13 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
int dif = sk->sk_bound_dev_if;
INET_ADDR_COOKIE(acookie, saddr, daddr)
const __portpair ports = INET_COMBINED_PORTS(inet->dport, lport);
- unsigned int hash = inet_ehashfn(daddr, lport, saddr, inet->dport);
+ struct net *net = sock_net(sk);
+ unsigned int hash = inet_ehashfn(net, daddr, lport, saddr, inet->dport);
struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
rwlock_t *lock = inet_ehash_lockp(hinfo, hash);
struct sock *sk2;
const struct hlist_node *node;
struct inet_timewait_sock *tw;
- struct net *net = sock_net(sk);
prefetch(head->chain.first);
write_lock(lock);
@@ -438,7 +440,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
local_bh_disable();
for (i = 1; i <= remaining; i++) {
port = low + (i + offset) % remaining;
- head = &hinfo->bhash[inet_bhashfn(port, hinfo->bhash_size)];
+ head = &hinfo->bhash[inet_bhashfn(net, port,
+ hinfo->bhash_size)];
spin_lock(&head->lock);
/* Does not bother with rcv_saddr checks,
@@ -493,7 +496,7 @@ ok:
goto out;
}
- head = &hinfo->bhash[inet_bhashfn(snum, hinfo->bhash_size)];
+ head = &hinfo->bhash[inet_bhashfn(net, snum, hinfo->bhash_size)];
tb = inet_csk(sk)->icsk_bind_hash;
spin_lock_bh(&head->lock);
if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index ce16e9ac24c..06006a5ac8b 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -32,7 +32,8 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw,
write_unlock(lock);
/* Disassociate with bind bucket. */
- bhead = &hashinfo->bhash[inet_bhashfn(tw->tw_num, hashinfo->bhash_size)];
+ bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num,
+ hashinfo->bhash_size)];
spin_lock(&bhead->lock);
tb = tw->tw_tb;
__hlist_del(&tw->tw_bind_node);
@@ -81,7 +82,8 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
Note, that any socket with inet->num != 0 MUST be bound in
binding cache, even if it is closed.
*/
- bhead = &hashinfo->bhash[inet_bhashfn(inet->num, hashinfo->bhash_size)];
+ bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->num,
+ hashinfo->bhash_size)];
spin_lock(&bhead->lock);
tw->tw_tb = icsk->icsk_bind_hash;
BUG_TRAP(icsk->icsk_bind_hash);
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index af995198f64..a456ceeac3f 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -3,8 +3,6 @@
*
* This source is covered by the GNU GPL, the same as all kernel sources.
*
- * Version: $Id: inetpeer.c,v 1.7 2001/09/20 21:22:50 davem Exp $
- *
* Authors: Andrey V. Savochkin <saw@msu.ru>
*/
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 4813c39b438..da14725916d 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -5,8 +5,6 @@
*
* The IP forwarding functionality.
*
- * Version: $Id: ip_forward.c,v 1.48 2000/12/13 18:31:48 davem Exp $
- *
* Authors: see ip.c
*
* Fixes:
@@ -58,6 +56,9 @@ int ip_forward(struct sk_buff *skb)
struct rtable *rt; /* Route we use */
struct ip_options * opt = &(IPCB(skb)->opt);
+ if (skb_warn_if_lro(skb))
+ goto drop;
+
if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb))
goto drop;
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 37221f65915..fbd5804b5d8 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -5,8 +5,6 @@
*
* The IP fragmentation functionality.
*
- * Version: $Id: ip_fragment.c,v 1.59 2002/01/12 07:54:56 davem Exp $
- *
* Authors: Fred N. van Kempen <waltje@uWalt.NL.Mugnet.ORG>
* Alan Cox <Alan.Cox@linux.org>
*
@@ -600,7 +598,7 @@ int ip_defrag(struct sk_buff *skb, u32 user)
#ifdef CONFIG_SYSCTL
static int zero;
-static struct ctl_table ip4_frags_ctl_table[] = {
+static struct ctl_table ip4_frags_ns_ctl_table[] = {
{
.ctl_name = NET_IPV4_IPFRAG_HIGH_THRESH,
.procname = "ipfrag_high_thresh",
@@ -626,6 +624,10 @@ static struct ctl_table ip4_frags_ctl_table[] = {
.proc_handler = &proc_dointvec_jiffies,
.strategy = &sysctl_jiffies
},
+ { }
+};
+
+static struct ctl_table ip4_frags_ctl_table[] = {
{
.ctl_name = NET_IPV4_IPFRAG_SECRET_INTERVAL,
.procname = "ipfrag_secret_interval",
@@ -646,22 +648,20 @@ static struct ctl_table ip4_frags_ctl_table[] = {
{ }
};
-static int ip4_frags_ctl_register(struct net *net)
+static int ip4_frags_ns_ctl_register(struct net *net)
{
struct ctl_table *table;
struct ctl_table_header *hdr;
- table = ip4_frags_ctl_table;
+ table = ip4_frags_ns_ctl_table;
if (net != &init_net) {
- table = kmemdup(table, sizeof(ip4_frags_ctl_table), GFP_KERNEL);
+ table = kmemdup(table, sizeof(ip4_frags_ns_ctl_table), GFP_KERNEL);
if (table == NULL)
goto err_alloc;
table[0].data = &net->ipv4.frags.high_thresh;
table[1].data = &net->ipv4.frags.low_thresh;
table[2].data = &net->ipv4.frags.timeout;
- table[3].mode &= ~0222;
- table[4].mode &= ~0222;
}
hdr = register_net_sysctl_table(net, net_ipv4_ctl_path, table);
@@ -678,7 +678,7 @@ err_alloc:
return -ENOMEM;
}
-static void ip4_frags_ctl_unregister(struct net *net)
+static void ip4_frags_ns_ctl_unregister(struct net *net)
{
struct ctl_table *table;
@@ -686,13 +686,22 @@ static void ip4_frags_ctl_unregister(struct net *net)
unregister_net_sysctl_table(net->ipv4.frags_hdr);
kfree(table);
}
+
+static void ip4_frags_ctl_register(void)
+{
+ register_net_sysctl_rotable(net_ipv4_ctl_path, ip4_frags_ctl_table);
+}
#else
-static inline int ip4_frags_ctl_register(struct net *net)
+static inline int ip4_frags_ns_ctl_register(struct net *net)
{
return 0;
}
-static inline void ip4_frags_ctl_unregister(struct net *net)
+static inline void ip4_frags_ns_ctl_unregister(struct net *net)
+{
+}
+
+static inline void ip4_frags_ctl_register(void)
{
}
#endif
@@ -716,12 +725,12 @@ static int ipv4_frags_init_net(struct net *net)
inet_frags_init_net(&net->ipv4.frags);
- return ip4_frags_ctl_register(net);
+ return ip4_frags_ns_ctl_register(net);
}
static void ipv4_frags_exit_net(struct net *net)
{
- ip4_frags_ctl_unregister(net);
+ ip4_frags_ns_ctl_unregister(net);
inet_frags_exit_net(&net->ipv4.frags, &ip4_frags);
}
@@ -732,6 +741,7 @@ static struct pernet_operations ip4_frags_ops = {
void __init ipfrag_init(void)
{
+ ip4_frags_ctl_register();
register_pernet_subsys(&ip4_frags_ops);
ip4_frags.hashfn = ip4_hashfn;
ip4_frags.constructor = ip4_frag_init;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 4342cba4ff8..2a61158ea72 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -473,6 +473,8 @@ static int ipgre_rcv(struct sk_buff *skb)
read_lock(&ipgre_lock);
if ((tunnel = ipgre_tunnel_lookup(dev_net(skb->dev),
iph->saddr, iph->daddr, key)) != NULL) {
+ struct net_device_stats *stats = &tunnel->dev->stats;
+
secpath_reset(skb);
skb->protocol = *(__be16*)(h + 2);
@@ -497,28 +499,28 @@ static int ipgre_rcv(struct sk_buff *skb)
/* Looped back packet, drop it! */
if (skb->rtable->fl.iif == 0)
goto drop;
- tunnel->stat.multicast++;
+ stats->multicast++;
skb->pkt_type = PACKET_BROADCAST;
}
#endif
if (((flags&GRE_CSUM) && csum) ||
(!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) {
- tunnel->stat.rx_crc_errors++;
- tunnel->stat.rx_errors++;
+ stats->rx_crc_errors++;
+ stats->rx_errors++;
goto drop;
}
if (tunnel->parms.i_flags&GRE_SEQ) {
if (!(flags&GRE_SEQ) ||
(tunnel->i_seqno && (s32)(seqno - tunnel->i_seqno) < 0)) {
- tunnel->stat.rx_fifo_errors++;
- tunnel->stat.rx_errors++;
+ stats->rx_fifo_errors++;
+ stats->rx_errors++;
goto drop;
}
tunnel->i_seqno = seqno + 1;
}
- tunnel->stat.rx_packets++;
- tunnel->stat.rx_bytes += skb->len;
+ stats->rx_packets++;
+ stats->rx_bytes += skb->len;
skb->dev = tunnel->dev;
dst_release(skb->dst);
skb->dst = NULL;
@@ -540,7 +542,7 @@ drop_nolock:
static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
- struct net_device_stats *stats = &tunnel->stat;
+ struct net_device_stats *stats = &tunnel->dev->stats;
struct iphdr *old_iph = ip_hdr(skb);
struct iphdr *tiph;
u8 tos;
@@ -554,7 +556,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
int mtu;
if (tunnel->recursion++) {
- tunnel->stat.collisions++;
+ stats->collisions++;
goto tx_error;
}
@@ -570,7 +572,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
/* NBMA tunnel */
if (skb->dst == NULL) {
- tunnel->stat.tx_fifo_errors++;
+ stats->tx_fifo_errors++;
goto tx_error;
}
@@ -621,7 +623,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
.tos = RT_TOS(tos) } },
.proto = IPPROTO_GRE };
if (ip_route_output_key(dev_net(dev), &rt, &fl)) {
- tunnel->stat.tx_carrier_errors++;
+ stats->tx_carrier_errors++;
goto tx_error;
}
}
@@ -629,7 +631,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
if (tdev == dev) {
ip_rt_put(rt);
- tunnel->stat.collisions++;
+ stats->collisions++;
goto tx_error;
}
@@ -954,11 +956,6 @@ done:
return err;
}
-static struct net_device_stats *ipgre_tunnel_get_stats(struct net_device *dev)
-{
- return &(((struct ip_tunnel*)netdev_priv(dev))->stat);
-}
-
static int ipgre_tunnel_change_mtu(struct net_device *dev, int new_mtu)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
@@ -1084,7 +1081,6 @@ static void ipgre_tunnel_setup(struct net_device *dev)
dev->uninit = ipgre_tunnel_uninit;
dev->destructor = free_netdev;
dev->hard_start_xmit = ipgre_tunnel_xmit;
- dev->get_stats = ipgre_tunnel_get_stats;
dev->do_ioctl = ipgre_tunnel_ioctl;
dev->change_mtu = ipgre_tunnel_change_mtu;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index ff77a4a7f9e..7c26428ea67 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -5,8 +5,6 @@
*
* The Internet Protocol (IP) module.
*
- * Version: $Id: ip_input.c,v 1.55 2002/01/12 07:39:45 davem Exp $
- *
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Donald Becker, <becker@super.org>
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 33126ad2cfd..be3f18a7a40 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -5,8 +5,6 @@
*
* The options processing module for ip.c
*
- * Version: $Id: ip_options.c,v 1.21 2001/09/01 00:31:50 davem Exp $
- *
* Authors: A.N.Kuznetsov
*
*/
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index e527628f56c..f1278eecf56 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -5,8 +5,6 @@
*
* The Internet Protocol (IP) output module.
*
- * Version: $Id: ip_output.c,v 1.100 2002/02/01 22:01:03 davem Exp $
- *
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Donald Becker, <becker@super.org>
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index e0514e82308..105d92a039b 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -5,8 +5,6 @@
*
* The IP to API glue.
*
- * Version: $Id: ip_sockglue.c,v 1.62 2002/02/01 22:01:04 davem Exp $
- *
* Authors: see ip.c
*
* Fixes:
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index ed45037ce9b..b88aa9afa42 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1,6 +1,4 @@
/*
- * $Id: ipconfig.c,v 1.46 2002/02/01 22:01:04 davem Exp $
- *
* Automatic Configuration of IP -- use DHCP, BOOTP, RARP, or
* user-supplied information to configure own IP address and routes.
*
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index af5cb53da5c..4c6d2caf920 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -1,8 +1,6 @@
/*
* Linux NET3: IP/IP protocol decoder.
*
- * Version: $Id: ipip.c,v 1.50 2001/10/02 02:22:36 davem Exp $
- *
* Authors:
* Sam Lantinga (slouken@cs.ucdavis.edu) 02/01/95
*
@@ -368,8 +366,8 @@ static int ipip_rcv(struct sk_buff *skb)
skb->protocol = htons(ETH_P_IP);
skb->pkt_type = PACKET_HOST;
- tunnel->stat.rx_packets++;
- tunnel->stat.rx_bytes += skb->len;
+ tunnel->dev->stats.rx_packets++;
+ tunnel->dev->stats.rx_bytes += skb->len;
skb->dev = tunnel->dev;
dst_release(skb->dst);
skb->dst = NULL;
@@ -392,7 +390,7 @@ static int ipip_rcv(struct sk_buff *skb)
static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
- struct net_device_stats *stats = &tunnel->stat;
+ struct net_device_stats *stats = &tunnel->dev->stats;
struct iphdr *tiph = &tunnel->parms.iph;
u8 tos = tunnel->parms.iph.tos;
__be16 df = tiph->frag_off;
@@ -405,7 +403,7 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
int mtu;
if (tunnel->recursion++) {
- tunnel->stat.collisions++;
+ stats->collisions++;
goto tx_error;
}
@@ -418,7 +416,7 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
if (!dst) {
/* NBMA tunnel */
if ((rt = skb->rtable) == NULL) {
- tunnel->stat.tx_fifo_errors++;
+ stats->tx_fifo_errors++;
goto tx_error;
}
if ((dst = rt->rt_gateway) == 0)
@@ -433,7 +431,7 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
.tos = RT_TOS(tos) } },
.proto = IPPROTO_IPIP };
if (ip_route_output_key(dev_net(dev), &rt, &fl)) {
- tunnel->stat.tx_carrier_errors++;
+ stats->tx_carrier_errors++;
goto tx_error_icmp;
}
}
@@ -441,7 +439,7 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
if (tdev == dev) {
ip_rt_put(rt);
- tunnel->stat.collisions++;
+ stats->collisions++;
goto tx_error;
}
@@ -451,7 +449,7 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
mtu = skb->dst ? dst_mtu(skb->dst) : dev->mtu;
if (mtu < 68) {
- tunnel->stat.collisions++;
+ stats->collisions++;
ip_rt_put(rt);
goto tx_error;
}
@@ -685,11 +683,6 @@ done:
return err;
}
-static struct net_device_stats *ipip_tunnel_get_stats(struct net_device *dev)
-{
- return &(((struct ip_tunnel*)netdev_priv(dev))->stat);
-}
-
static int ipip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
{
if (new_mtu < 68 || new_mtu > 0xFFF8 - sizeof(struct iphdr))
@@ -702,7 +695,6 @@ static void ipip_tunnel_setup(struct net_device *dev)
{
dev->uninit = ipip_tunnel_uninit;
dev->hard_start_xmit = ipip_tunnel_xmit;
- dev->get_stats = ipip_tunnel_get_stats;
dev->do_ioctl = ipip_tunnel_ioctl;
dev->change_mtu = ipip_tunnel_change_mtu;
dev->destructor = free_netdev;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 11700a4dcd9..438fab9c62a 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -9,8 +9,6 @@
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
- * Version: $Id: ipmr.c,v 1.65 2001/10/31 21:55:54 davem Exp $
- *
* Fixes:
* Michael Chastain : Incorrect size of copying.
* Alan Cox : Added the cache manager code
@@ -181,26 +179,20 @@ static int reg_vif_num = -1;
static int reg_vif_xmit(struct sk_buff *skb, struct net_device *dev)
{
read_lock(&mrt_lock);
- ((struct net_device_stats*)netdev_priv(dev))->tx_bytes += skb->len;
- ((struct net_device_stats*)netdev_priv(dev))->tx_packets++;
+ dev->stats.tx_bytes += skb->len;
+ dev->stats.tx_packets++;
ipmr_cache_report(skb, reg_vif_num, IGMPMSG_WHOLEPKT);
read_unlock(&mrt_lock);
kfree_skb(skb);
return 0;
}
-static struct net_device_stats *reg_vif_get_stats(struct net_device *dev)
-{
- return (struct net_device_stats*)netdev_priv(dev);
-}
-
static void reg_vif_setup(struct net_device *dev)
{
dev->type = ARPHRD_PIMREG;
dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr) - 8;
dev->flags = IFF_NOARP;
dev->hard_start_xmit = reg_vif_xmit;
- dev->get_stats = reg_vif_get_stats;
dev->destructor = free_netdev;
}
@@ -209,8 +201,7 @@ static struct net_device *ipmr_reg_vif(void)
struct net_device *dev;
struct in_device *in_dev;
- dev = alloc_netdev(sizeof(struct net_device_stats), "pimreg",
- reg_vif_setup);
+ dev = alloc_netdev(0, "pimreg", reg_vif_setup);
if (dev == NULL)
return NULL;
@@ -1170,8 +1161,8 @@ static void ipmr_queue_xmit(struct sk_buff *skb, struct mfc_cache *c, int vifi)
if (vif->flags & VIFF_REGISTER) {
vif->pkt_out++;
vif->bytes_out+=skb->len;
- ((struct net_device_stats*)netdev_priv(vif->dev))->tx_bytes += skb->len;
- ((struct net_device_stats*)netdev_priv(vif->dev))->tx_packets++;
+ vif->dev->stats.tx_bytes += skb->len;
+ vif->dev->stats.tx_packets++;
ipmr_cache_report(skb, vifi, IGMPMSG_WHOLEPKT);
kfree_skb(skb);
return;
@@ -1230,8 +1221,8 @@ static void ipmr_queue_xmit(struct sk_buff *skb, struct mfc_cache *c, int vifi)
if (vif->flags & VIFF_TUNNEL) {
ip_encap(skb, vif->local, vif->remote);
/* FIXME: extra output firewall step used to be here. --RR */
- ((struct ip_tunnel *)netdev_priv(vif->dev))->stat.tx_packets++;
- ((struct ip_tunnel *)netdev_priv(vif->dev))->stat.tx_bytes+=skb->len;
+ vif->dev->stats.tx_packets++;
+ vif->dev->stats.tx_bytes += skb->len;
}
IPCB(skb)->flags |= IPSKB_FORWARDED;
@@ -1487,8 +1478,8 @@ int pim_rcv_v1(struct sk_buff * skb)
skb->pkt_type = PACKET_HOST;
dst_release(skb->dst);
skb->dst = NULL;
- ((struct net_device_stats*)netdev_priv(reg_dev))->rx_bytes += skb->len;
- ((struct net_device_stats*)netdev_priv(reg_dev))->rx_packets++;
+ reg_dev->stats.rx_bytes += skb->len;
+ reg_dev->stats.rx_packets++;
nf_reset(skb);
netif_rx(skb);
dev_put(reg_dev);
@@ -1542,8 +1533,8 @@ static int pim_rcv(struct sk_buff * skb)
skb->ip_summed = 0;
skb->pkt_type = PACKET_HOST;
dst_release(skb->dst);
- ((struct net_device_stats*)netdev_priv(reg_dev))->rx_bytes += skb->len;
- ((struct net_device_stats*)netdev_priv(reg_dev))->rx_packets++;
+ reg_dev->stats.rx_bytes += skb->len;
+ reg_dev->stats.rx_packets++;
skb->dst = NULL;
nf_reset(skb);
netif_rx(skb);
@@ -1887,16 +1878,36 @@ static struct net_protocol pim_protocol = {
* Setup for IP multicast routing
*/
-void __init ip_mr_init(void)
+int __init ip_mr_init(void)
{
+ int err;
+
mrt_cachep = kmem_cache_create("ip_mrt_cache",
sizeof(struct mfc_cache),
0, SLAB_HWCACHE_ALIGN|SLAB_PANIC,
NULL);
+ if (!mrt_cachep)
+ return -ENOMEM;
+
setup_timer(&ipmr_expire_timer, ipmr_expire_process, 0);
- register_netdevice_notifier(&ip_mr_notifier);
+ err = register_netdevice_notifier(&ip_mr_notifier);
+ if (err)
+ goto reg_notif_fail;
+#ifdef CONFIG_PROC_FS
+ err = -ENOMEM;
+ if (!proc_net_fops_create(&init_net, "ip_mr_vif", 0, &ipmr_vif_fops))
+ goto proc_vif_fail;
+ if (!proc_net_fops_create(&init_net, "ip_mr_cache", 0, &ipmr_mfc_fops))
+ goto proc_cache_fail;
+#endif
+ return 0;
+reg_notif_fail:
+ kmem_cache_destroy(mrt_cachep);
#ifdef CONFIG_PROC_FS
- proc_net_fops_create(&init_net, "ip_mr_vif", 0, &ipmr_vif_fops);
- proc_net_fops_create(&init_net, "ip_mr_cache", 0, &ipmr_mfc_fops);
+proc_vif_fail:
+ unregister_netdevice_notifier(&ip_mr_notifier);
+proc_cache_fail:
+ proc_net_remove(&init_net, "ip_mr_vif");
#endif
+ return err;
}
diff --git a/net/ipv4/ipvs/ip_vs_app.c b/net/ipv4/ipvs/ip_vs_app.c
index 535abe0c45e..1f1897a1a70 100644
--- a/net/ipv4/ipvs/ip_vs_app.c
+++ b/net/ipv4/ipvs/ip_vs_app.c
@@ -1,8 +1,6 @@
/*
* ip_vs_app.c: Application module support for IPVS
*
- * Version: $Id: ip_vs_app.c,v 1.17 2003/03/22 06:31:21 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
*
* This program is free software; you can redistribute it and/or
diff --git a/net/ipv4/ipvs/ip_vs_conn.c b/net/ipv4/ipvs/ip_vs_conn.c
index 65f1ba11275..f8bdae47a77 100644
--- a/net/ipv4/ipvs/ip_vs_conn.c
+++ b/net/ipv4/ipvs/ip_vs_conn.c
@@ -5,8 +5,6 @@
* high-performance and highly available server based on a
* cluster of servers.
*
- * Version: $Id: ip_vs_conn.c,v 1.31 2003/04/18 09:03:16 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
* Peter Kese <peter.kese@ijs.si>
* Julian Anastasov <ja@ssi.bg>
diff --git a/net/ipv4/ipvs/ip_vs_core.c b/net/ipv4/ipvs/ip_vs_core.c
index 963981a9d50..bcf6276ba4b 100644
--- a/net/ipv4/ipvs/ip_vs_core.c
+++ b/net/ipv4/ipvs/ip_vs_core.c
@@ -5,8 +5,6 @@
* high-performance and highly available server based on a
* cluster of servers.
*
- * Version: $Id: ip_vs_core.c,v 1.34 2003/05/10 03:05:23 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
* Peter Kese <peter.kese@ijs.si>
* Julian Anastasov <ja@ssi.bg>
diff --git a/net/ipv4/ipvs/ip_vs_ctl.c b/net/ipv4/ipvs/ip_vs_ctl.c
index 94c5767c8e0..9a5ace0b4dd 100644
--- a/net/ipv4/ipvs/ip_vs_ctl.c
+++ b/net/ipv4/ipvs/ip_vs_ctl.c
@@ -5,8 +5,6 @@
* high-performance and highly available server based on a
* cluster of servers.
*
- * Version: $Id: ip_vs_ctl.c,v 1.36 2003/06/08 09:31:19 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
* Peter Kese <peter.kese@ijs.si>
* Julian Anastasov <ja@ssi.bg>
diff --git a/net/ipv4/ipvs/ip_vs_dh.c b/net/ipv4/ipvs/ip_vs_dh.c
index dcf5d46aaa5..8afc1503ed2 100644
--- a/net/ipv4/ipvs/ip_vs_dh.c
+++ b/net/ipv4/ipvs/ip_vs_dh.c
@@ -1,8 +1,6 @@
/*
* IPVS: Destination Hashing scheduling module
*
- * Version: $Id: ip_vs_dh.c,v 1.5 2002/09/15 08:14:08 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@gnuchina.org>
*
* Inspired by the consistent hashing scheduler patch from
diff --git a/net/ipv4/ipvs/ip_vs_est.c b/net/ipv4/ipvs/ip_vs_est.c
index dfa0d713c80..bc04eedd6db 100644
--- a/net/ipv4/ipvs/ip_vs_est.c
+++ b/net/ipv4/ipvs/ip_vs_est.c
@@ -1,8 +1,6 @@
/*
* ip_vs_est.c: simple rate estimator for IPVS
*
- * Version: $Id: ip_vs_est.c,v 1.4 2002/11/30 01:50:35 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
*
* This program is free software; you can redistribute it and/or
diff --git a/net/ipv4/ipvs/ip_vs_ftp.c b/net/ipv4/ipvs/ip_vs_ftp.c
index 59aa166b767..c1c758e4f73 100644
--- a/net/ipv4/ipvs/ip_vs_ftp.c
+++ b/net/ipv4/ipvs/ip_vs_ftp.c
@@ -1,8 +1,6 @@
/*
* ip_vs_ftp.c: IPVS ftp application module
*
- * Version: $Id: ip_vs_ftp.c,v 1.13 2002/09/15 08:14:08 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
*
* Changes:
diff --git a/net/ipv4/ipvs/ip_vs_lblc.c b/net/ipv4/ipvs/ip_vs_lblc.c
index 3888642706a..0efa3db4b18 100644
--- a/net/ipv4/ipvs/ip_vs_lblc.c
+++ b/net/ipv4/ipvs/ip_vs_lblc.c
@@ -1,8 +1,6 @@
/*
* IPVS: Locality-Based Least-Connection scheduling module
*
- * Version: $Id: ip_vs_lblc.c,v 1.10 2002/09/15 08:14:08 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@gnuchina.org>
*
* This program is free software; you can redistribute it and/or
diff --git a/net/ipv4/ipvs/ip_vs_lblcr.c b/net/ipv4/ipvs/ip_vs_lblcr.c
index daa260eb21c..8e3bbeb4513 100644
--- a/net/ipv4/ipvs/ip_vs_lblcr.c
+++ b/net/ipv4/ipvs/ip_vs_lblcr.c
@@ -1,8 +1,6 @@
/*
* IPVS: Locality-Based Least-Connection with Replication scheduler
*
- * Version: $Id: ip_vs_lblcr.c,v 1.11 2002/09/15 08:14:08 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@gnuchina.org>
*
* This program is free software; you can redistribute it and/or
diff --git a/net/ipv4/ipvs/ip_vs_lc.c b/net/ipv4/ipvs/ip_vs_lc.c
index d88fef90a64..ac9f08e065d 100644
--- a/net/ipv4/ipvs/ip_vs_lc.c
+++ b/net/ipv4/ipvs/ip_vs_lc.c
@@ -1,8 +1,6 @@
/*
* IPVS: Least-Connection Scheduling module
*
- * Version: $Id: ip_vs_lc.c,v 1.10 2003/04/18 09:03:16 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
*
* This program is free software; you can redistribute it and/or
diff --git a/net/ipv4/ipvs/ip_vs_nq.c b/net/ipv4/ipvs/ip_vs_nq.c
index bc2a9e5f2a7..a46bf258d42 100644
--- a/net/ipv4/ipvs/ip_vs_nq.c
+++ b/net/ipv4/ipvs/ip_vs_nq.c
@@ -1,8 +1,6 @@
/*
* IPVS: Never Queue scheduling module
*
- * Version: $Id: ip_vs_nq.c,v 1.2 2003/06/08 09:31:19 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
*
* This program is free software; you can redistribute it and/or
diff --git a/net/ipv4/ipvs/ip_vs_proto.c b/net/ipv4/ipvs/ip_vs_proto.c
index 4b1c16cbb16..876714f23d6 100644
--- a/net/ipv4/ipvs/ip_vs_proto.c
+++ b/net/ipv4/ipvs/ip_vs_proto.c
@@ -1,8 +1,6 @@
/*
* ip_vs_proto.c: transport protocol load balancing support for IPVS
*
- * Version: $Id: ip_vs_proto.c,v 1.2 2003/04/18 09:03:16 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
* Julian Anastasov <ja@ssi.bg>
*
diff --git a/net/ipv4/ipvs/ip_vs_proto_ah.c b/net/ipv4/ipvs/ip_vs_proto_ah.c
index 4bf835e1d86..73e0ea87c1f 100644
--- a/net/ipv4/ipvs/ip_vs_proto_ah.c
+++ b/net/ipv4/ipvs/ip_vs_proto_ah.c
@@ -1,8 +1,6 @@
/*
* ip_vs_proto_ah.c: AH IPSec load balancing support for IPVS
*
- * Version: $Id: ip_vs_proto_ah.c,v 1.1 2003/07/04 15:04:37 wensong Exp $
- *
* Authors: Julian Anastasov <ja@ssi.bg>, February 2002
* Wensong Zhang <wensong@linuxvirtualserver.org>
*
diff --git a/net/ipv4/ipvs/ip_vs_proto_esp.c b/net/ipv4/ipvs/ip_vs_proto_esp.c
index db6a6b7b1a0..21d70c8ffa5 100644
--- a/net/ipv4/ipvs/ip_vs_proto_esp.c
+++ b/net/ipv4/ipvs/ip_vs_proto_esp.c
@@ -1,8 +1,6 @@
/*
* ip_vs_proto_esp.c: ESP IPSec load balancing support for IPVS
*
- * Version: $Id: ip_vs_proto_esp.c,v 1.1 2003/07/04 15:04:37 wensong Exp $
- *
* Authors: Julian Anastasov <ja@ssi.bg>, February 2002
* Wensong Zhang <wensong@linuxvirtualserver.org>
*
diff --git a/net/ipv4/ipvs/ip_vs_proto_tcp.c b/net/ipv4/ipvs/ip_vs_proto_tcp.c
index b83dc14b0a4..d0ea467986a 100644
--- a/net/ipv4/ipvs/ip_vs_proto_tcp.c
+++ b/net/ipv4/ipvs/ip_vs_proto_tcp.c
@@ -1,8 +1,6 @@
/*
* ip_vs_proto_tcp.c: TCP load balancing support for IPVS
*
- * Version: $Id: ip_vs_proto_tcp.c,v 1.3 2002/11/30 01:50:35 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
* Julian Anastasov <ja@ssi.bg>
*
diff --git a/net/ipv4/ipvs/ip_vs_proto_udp.c b/net/ipv4/ipvs/ip_vs_proto_udp.c
index 75771cb3cd6..c6be5d56823 100644
--- a/net/ipv4/ipvs/ip_vs_proto_udp.c
+++ b/net/ipv4/ipvs/ip_vs_proto_udp.c
@@ -1,8 +1,6 @@
/*
* ip_vs_proto_udp.c: UDP load balancing support for IPVS
*
- * Version: $Id: ip_vs_proto_udp.c,v 1.3 2002/11/30 01:50:35 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
* Julian Anastasov <ja@ssi.bg>
*
diff --git a/net/ipv4/ipvs/ip_vs_rr.c b/net/ipv4/ipvs/ip_vs_rr.c
index 433f8a94792..c8db12d39e6 100644
--- a/net/ipv4/ipvs/ip_vs_rr.c
+++ b/net/ipv4/ipvs/ip_vs_rr.c
@@ -1,8 +1,6 @@
/*
* IPVS: Round-Robin Scheduling module
*
- * Version: $Id: ip_vs_rr.c,v 1.9 2002/09/15 08:14:08 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
* Peter Kese <peter.kese@ijs.si>
*
diff --git a/net/ipv4/ipvs/ip_vs_sched.c b/net/ipv4/ipvs/ip_vs_sched.c
index 121a32b1b75..b6476730985 100644
--- a/net/ipv4/ipvs/ip_vs_sched.c
+++ b/net/ipv4/ipvs/ip_vs_sched.c
@@ -5,8 +5,6 @@
* high-performance and highly available server based on a
* cluster of servers.
*
- * Version: $Id: ip_vs_sched.c,v 1.13 2003/05/10 03:05:23 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
* Peter Kese <peter.kese@ijs.si>
*
diff --git a/net/ipv4/ipvs/ip_vs_sed.c b/net/ipv4/ipvs/ip_vs_sed.c
index dd7c128f9db..2a7d3135818 100644
--- a/net/ipv4/ipvs/ip_vs_sed.c
+++ b/net/ipv4/ipvs/ip_vs_sed.c
@@ -1,8 +1,6 @@
/*
* IPVS: Shortest Expected Delay scheduling module
*
- * Version: $Id: ip_vs_sed.c,v 1.1 2003/05/10 03:06:08 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
*
* This program is free software; you can redistribute it and/or
diff --git a/net/ipv4/ipvs/ip_vs_sh.c b/net/ipv4/ipvs/ip_vs_sh.c
index 1b25b00ef1e..b8fdfac6500 100644
--- a/net/ipv4/ipvs/ip_vs_sh.c
+++ b/net/ipv4/ipvs/ip_vs_sh.c
@@ -1,8 +1,6 @@
/*
* IPVS: Source Hashing scheduling module
*
- * Version: $Id: ip_vs_sh.c,v 1.5 2002/09/15 08:14:08 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@gnuchina.org>
*
* This program is free software; you can redistribute it and/or
diff --git a/net/ipv4/ipvs/ip_vs_sync.c b/net/ipv4/ipvs/ip_vs_sync.c
index eff54efe035..2d4a86f7332 100644
--- a/net/ipv4/ipvs/ip_vs_sync.c
+++ b/net/ipv4/ipvs/ip_vs_sync.c
@@ -5,8 +5,6 @@
* high-performance and highly available server based on a
* cluster of servers.
*
- * Version: $Id: ip_vs_sync.c,v 1.13 2003/06/08 09:31:19 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
*
* ip_vs_sync: sync connection info from master load balancer to backups
diff --git a/net/ipv4/ipvs/ip_vs_wlc.c b/net/ipv4/ipvs/ip_vs_wlc.c
index 8a9d913261d..772c3cb4eca 100644
--- a/net/ipv4/ipvs/ip_vs_wlc.c
+++ b/net/ipv4/ipvs/ip_vs_wlc.c
@@ -1,8 +1,6 @@
/*
* IPVS: Weighted Least-Connection Scheduling module
*
- * Version: $Id: ip_vs_wlc.c,v 1.13 2003/04/18 09:03:16 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
* Peter Kese <peter.kese@ijs.si>
*
diff --git a/net/ipv4/ipvs/ip_vs_wrr.c b/net/ipv4/ipvs/ip_vs_wrr.c
index 85c680add6d..1d6932d7dc9 100644
--- a/net/ipv4/ipvs/ip_vs_wrr.c
+++ b/net/ipv4/ipvs/ip_vs_wrr.c
@@ -1,8 +1,6 @@
/*
* IPVS: Weighted Round-Robin Scheduling module
*
- * Version: $Id: ip_vs_wrr.c,v 1.12 2002/09/15 08:14:08 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
*
* This program is free software; you can redistribute it and/or
diff --git a/net/ipv4/ipvs/ip_vs_xmit.c b/net/ipv4/ipvs/ip_vs_xmit.c
index f63006caea0..9892d4aca42 100644
--- a/net/ipv4/ipvs/ip_vs_xmit.c
+++ b/net/ipv4/ipvs/ip_vs_xmit.c
@@ -1,8 +1,6 @@
/*
* ip_vs_xmit.c: various packet transmitters for IPVS
*
- * Version: $Id: ip_vs_xmit.c,v 1.2 2002/11/30 01:50:35 wensong Exp $
- *
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
* Julian Anastasov <ja@ssi.bg>
*
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 2767841a8ce..f23e60c93ef 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -213,8 +213,7 @@ config IP_NF_TARGET_NETMAP
help
NETMAP is an implementation of static 1:1 NAT mapping of network
addresses. It maps the network address part, while keeping the host
- address part intact. It is similar to Fast NAT, except that
- Netfilter's connection tracking doesn't work well with Fast NAT.
+ address part intact.
To compile it as a module, choose M here. If unsure, say N.
@@ -365,6 +364,18 @@ config IP_NF_RAW
If you want to compile it as a module, say M here and read
<file:Documentation/kbuild/modules.txt>. If unsure, say `N'.
+# security table for MAC policy
+config IP_NF_SECURITY
+ tristate "Security table"
+ depends on IP_NF_IPTABLES
+ depends on SECURITY
+ default m if NETFILTER_ADVANCED=n
+ help
+ This option adds a `security' table to iptables, for use
+ with Mandatory Access Control (MAC) policy.
+
+ If unsure, say N.
+
# ARP tables
config IP_NF_ARPTABLES
tristate "ARP tables support"
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index d9b92fbf557..3f31291f37c 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -42,6 +42,7 @@ obj-$(CONFIG_IP_NF_FILTER) += iptable_filter.o
obj-$(CONFIG_IP_NF_MANGLE) += iptable_mangle.o
obj-$(CONFIG_NF_NAT) += iptable_nat.o
obj-$(CONFIG_IP_NF_RAW) += iptable_raw.o
+obj-$(CONFIG_IP_NF_SECURITY) += iptable_security.o
# matches
obj-$(CONFIG_IP_NF_MATCH_ADDRTYPE) += ipt_addrtype.o
diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c
index 26a37cedcf2..aa33a4a7a71 100644
--- a/net/ipv4/netfilter/ip_queue.c
+++ b/net/ipv4/netfilter/ip_queue.c
@@ -156,7 +156,6 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp)
case IPQ_COPY_META:
case IPQ_COPY_NONE:
size = NLMSG_SPACE(sizeof(*pmsg));
- data_len = 0;
break;
case IPQ_COPY_PACKET:
@@ -224,8 +223,6 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp)
return skb;
nlmsg_failure:
- if (skb)
- kfree_skb(skb);
*errp = -EINVAL;
printk(KERN_ERR "ip_queue: error creating packet message\n");
return NULL;
diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c
new file mode 100644
index 00000000000..2b472ac2263
--- /dev/null
+++ b/net/ipv4/netfilter/iptable_security.c
@@ -0,0 +1,180 @@
+/*
+ * "security" table
+ *
+ * This is for use by Mandatory Access Control (MAC) security models,
+ * which need to be able to manage security policy in separate context
+ * to DAC.
+ *
+ * Based on iptable_mangle.c
+ *
+ * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling
+ * Copyright (C) 2000-2004 Netfilter Core Team <coreteam <at> netfilter.org>
+ * Copyright (C) 2008 Red Hat, Inc., James Morris <jmorris <at> redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/module.h>
+#include <linux/netfilter_ipv4/ip_tables.h>
+#include <net/ip.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("James Morris <jmorris <at> redhat.com>");
+MODULE_DESCRIPTION("iptables security table, for MAC rules");
+
+#define SECURITY_VALID_HOOKS (1 << NF_INET_LOCAL_IN) | \
+ (1 << NF_INET_FORWARD) | \
+ (1 << NF_INET_LOCAL_OUT)
+
+static struct
+{
+ struct ipt_replace repl;
+ struct ipt_standard entries[3];
+ struct ipt_error term;
+} initial_table __initdata = {
+ .repl = {
+ .name = "security",
+ .valid_hooks = SECURITY_VALID_HOOKS,
+ .num_entries = 4,
+ .size = sizeof(struct ipt_standard) * 3 + sizeof(struct ipt_error),
+ .hook_entry = {
+ [NF_INET_LOCAL_IN] = 0,
+ [NF_INET_FORWARD] = sizeof(struct ipt_standard),
+ [NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) * 2,
+ },
+ .underflow = {
+ [NF_INET_LOCAL_IN] = 0,
+ [NF_INET_FORWARD] = sizeof(struct ipt_standard),
+ [NF_INET_LOCAL_OUT] = sizeof(struct ipt_standard) * 2,
+ },
+ },
+ .entries = {
+ IPT_STANDARD_INIT(NF_ACCEPT), /* LOCAL_IN */
+ IPT_STANDARD_INIT(NF_ACCEPT), /* FORWARD */
+ IPT_STANDARD_INIT(NF_ACCEPT), /* LOCAL_OUT */
+ },
+ .term = IPT_ERROR_INIT, /* ERROR */
+};
+
+static struct xt_table security_table = {
+ .name = "security",
+ .valid_hooks = SECURITY_VALID_HOOKS,
+ .lock = __RW_LOCK_UNLOCKED(security_table.lock),
+ .me = THIS_MODULE,
+ .af = AF_INET,
+};
+
+static unsigned int
+ipt_local_in_hook(unsigned int hook,
+ struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ return ipt_do_table(skb, hook, in, out,
+ nf_local_in_net(in, out)->ipv4.iptable_security);
+}
+
+static unsigned int
+ipt_forward_hook(unsigned int hook,
+ struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ return ipt_do_table(skb, hook, in, out,
+ nf_forward_net(in, out)->ipv4.iptable_security);
+}
+
+static unsigned int
+ipt_local_out_hook(unsigned int hook,
+ struct sk_buff *skb,
+ const struct net_device *in,
+ const struct net_device *out,
+ int (*okfn)(struct sk_buff *))
+{
+ /* Somebody is playing with raw sockets. */
+ if (skb->len < sizeof(struct iphdr)
+ || ip_hdrlen(skb) < sizeof(struct iphdr)) {
+ if (net_ratelimit())
+ printk(KERN_INFO "iptable_security: ignoring short "
+ "SOCK_RAW packet.\n");
+ return NF_ACCEPT;
+ }
+ return ipt_do_table(skb, hook, in, out,
+ nf_local_out_net(in, out)->ipv4.iptable_security);
+}
+
+static struct nf_hook_ops ipt_ops[] __read_mostly = {
+ {
+ .hook = ipt_local_in_hook,
+ .owner = THIS_MODULE,
+ .pf = PF_INET,
+ .hooknum = NF_INET_LOCAL_IN,
+ .priority = NF_IP_PRI_SECURITY,
+ },
+ {
+ .hook = ipt_forward_hook,
+ .owner = THIS_MODULE,
+ .pf = PF_INET,
+ .hooknum = NF_INET_FORWARD,
+ .priority = NF_IP_PRI_SECURITY,
+ },
+ {
+ .hook = ipt_local_out_hook,
+ .owner = THIS_MODULE,
+ .pf = PF_INET,
+ .hooknum = NF_INET_LOCAL_OUT,
+ .priority = NF_IP_PRI_SECURITY,
+ },
+};
+
+static int __net_init iptable_security_net_init(struct net *net)
+{
+ net->ipv4.iptable_security =
+ ipt_register_table(net, &security_table, &initial_table.repl);
+
+ if (IS_ERR(net->ipv4.iptable_security))
+ return PTR_ERR(net->ipv4.iptable_security);
+
+ return 0;
+}
+
+static void __net_exit iptable_security_net_exit(struct net *net)
+{
+ ipt_unregister_table(net->ipv4.iptable_security);
+}
+
+static struct pernet_operations iptable_security_net_ops = {
+ .init = iptable_security_net_init,
+ .exit = iptable_security_net_exit,
+};
+
+static int __init iptable_security_init(void)
+{
+ int ret;
+
+ ret = register_pernet_subsys(&iptable_security_net_ops);
+ if (ret < 0)
+ return ret;
+
+ ret = nf_register_hooks(ipt_ops, ARRAY_SIZE(ipt_ops));
+ if (ret < 0)
+ goto cleanup_table;
+
+ return ret;
+
+cleanup_table:
+ unregister_pernet_subsys(&iptable_security_net_ops);
+ return ret;
+}
+
+static void __exit iptable_security_fini(void)
+{
+ nf_unregister_hooks(ipt_ops, ARRAY_SIZE(ipt_ops));
+ unregister_pernet_subsys(&iptable_security_net_ops);
+}
+
+module_init(iptable_security_init);
+module_exit(iptable_security_fini);
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index 78ab19accac..97791048fa9 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -87,9 +87,8 @@ static int icmp_packet(struct nf_conn *ct,
means this will only run once even if count hits zero twice
(theoretically possible with SMP) */
if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) {
- if (atomic_dec_and_test(&ct->proto.icmp.count)
- && del_timer(&ct->timeout))
- ct->timeout.function((unsigned long)ct);
+ if (atomic_dec_and_test(&ct->proto.icmp.count))
+ nf_ct_kill_acct(ct, ctinfo, skb);
} else {
atomic_inc(&ct->proto.icmp.count);
nf_conntrack_event_cache(IPCT_PROTOINFO_VOLATILE, skb);
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 552169b41b1..eb5cee279c5 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -7,8 +7,6 @@
* PROC file system. It is mainly used for debugging and
* statistics.
*
- * Version: $Id: proc.c,v 1.45 2001/05/16 16:45:35 davem Exp $
- *
* Authors: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Gerald J. Heim, <heim@peanuts.informatik.uni-tuebingen.de>
* Fred Baumgarten, <dc6iq@insu1.etec.uni-karlsruhe.de>
diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c
index 971ab9356e5..ea50da0649f 100644
--- a/net/ipv4/protocol.c
+++ b/net/ipv4/protocol.c
@@ -5,8 +5,6 @@
*
* INET protocol dispatch tables.
*
- * Version: $Id: protocol.c,v 1.14 2001/05/18 02:25:49 davem Exp $
- *
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
*
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 37a1ecd9d60..925fdf18cf9 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -5,8 +5,6 @@
*
* RAW - implementation of IP "raw" sockets.
*
- * Version: $Id: raw.c,v 1.64 2002/02/01 22:01:04 davem Exp $
- *
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
*
@@ -608,12 +606,11 @@ static void raw_close(struct sock *sk, long timeout)
sk_common_release(sk);
}
-static int raw_destroy(struct sock *sk)
+static void raw_destroy(struct sock *sk)
{
lock_sock(sk);
ip_flush_pending_frames(sk);
release_sock(sk);
- return 0;
}
/* This gets rid of all the nasties in af_inet. -DaveM */
@@ -947,7 +944,7 @@ static int raw_seq_show(struct seq_file *seq, void *v)
if (v == SEQ_START_TOKEN)
seq_printf(seq, " sl local_address rem_address st tx_queue "
"rx_queue tr tm->when retrnsmt uid timeout "
- "inode drops\n");
+ "inode ref pointer drops\n");
else
raw_sock_seq_show(seq, v, raw_seq_private(seq)->bucket);
return 0;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 96be336064f..79c1e74263a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -5,8 +5,6 @@
*
* ROUTE - implementation of the IP router.
*
- * Version: $Id: route.c,v 1.103 2002/01/12 07:44:09 davem Exp $
- *
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Alan Cox, <gw4pts@gw4pts.ampr.org>
@@ -134,7 +132,6 @@ static int ip_rt_secret_interval __read_mostly = 10 * 60 * HZ;
static void rt_worker_func(struct work_struct *work);
static DECLARE_DELAYED_WORK(expires_work, rt_worker_func);
-static struct timer_list rt_secret_timer;
/*
* Interface to generic destination cache.
@@ -253,20 +250,25 @@ static inline void rt_hash_lock_init(void)
static struct rt_hash_bucket *rt_hash_table __read_mostly;
static unsigned rt_hash_mask __read_mostly;
static unsigned int rt_hash_log __read_mostly;
-static atomic_t rt_genid __read_mostly;
static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
#define RT_CACHE_STAT_INC(field) \
(__raw_get_cpu_var(rt_cache_stat).field++)
-static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx)
+static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx,
+ int genid)
{
return jhash_3words((__force u32)(__be32)(daddr),
(__force u32)(__be32)(saddr),
- idx, atomic_read(&rt_genid))
+ idx, genid)
& rt_hash_mask;
}
+static inline int rt_genid(struct net *net)
+{
+ return atomic_read(&net->ipv4.rt_genid);
+}
+
#ifdef CONFIG_PROC_FS
struct rt_cache_iter_state {
struct seq_net_private p;
@@ -336,7 +338,7 @@ static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos)
struct rt_cache_iter_state *st = seq->private;
if (*pos)
return rt_cache_get_idx(seq, *pos - 1);
- st->genid = atomic_read(&rt_genid);
+ st->genid = rt_genid(seq_file_net(seq));
return SEQ_START_TOKEN;
}
@@ -683,6 +685,11 @@ static inline int compare_netns(struct rtable *rt1, struct rtable *rt2)
return dev_net(rt1->u.dst.dev) == dev_net(rt2->u.dst.dev);
}
+static inline int rt_is_expired(struct rtable *rth)
+{
+ return rth->rt_genid != rt_genid(dev_net(rth->u.dst.dev));
+}
+
/*
* Perform a full scan of hash table and free all entries.
* Can be called by a softirq or a process.
@@ -692,6 +699,7 @@ static void rt_do_flush(int process_context)
{
unsigned int i;
struct rtable *rth, *next;
+ struct rtable * tail;
for (i = 0; i <= rt_hash_mask; i++) {
if (process_context && need_resched())
@@ -701,11 +709,39 @@ static void rt_do_flush(int process_context)
continue;
spin_lock_bh(rt_hash_lock_addr(i));
+#ifdef CONFIG_NET_NS
+ {
+ struct rtable ** prev, * p;
+
+ rth = rt_hash_table[i].chain;
+
+ /* defer releasing the head of the list after spin_unlock */
+ for (tail = rth; tail; tail = tail->u.dst.rt_next)
+ if (!rt_is_expired(tail))
+ break;
+ if (rth != tail)
+ rt_hash_table[i].chain = tail;
+
+ /* call rt_free on entries after the tail requiring flush */
+ prev = &rt_hash_table[i].chain;
+ for (p = *prev; p; p = next) {
+ next = p->u.dst.rt_next;
+ if (!rt_is_expired(p)) {
+ prev = &p->u.dst.rt_next;
+ } else {
+ *prev = next;
+ rt_free(p);
+ }
+ }
+ }
+#else
rth = rt_hash_table[i].chain;
rt_hash_table[i].chain = NULL;
+ tail = NULL;
+#endif
spin_unlock_bh(rt_hash_lock_addr(i));
- for (; rth; rth = next) {
+ for (; rth != tail; rth = next) {
next = rth->u.dst.rt_next;
rt_free(rth);
}
@@ -738,7 +774,7 @@ static void rt_check_expire(void)
continue;
spin_lock_bh(rt_hash_lock_addr(i));
while ((rth = *rthp) != NULL) {
- if (rth->rt_genid != atomic_read(&rt_genid)) {
+ if (rt_is_expired(rth)) {
*rthp = rth->u.dst.rt_next;
rt_free(rth);
continue;
@@ -781,21 +817,21 @@ static void rt_worker_func(struct work_struct *work)
* many times (2^24) without giving recent rt_genid.
* Jenkins hash is strong enough that litle changes of rt_genid are OK.
*/
-static void rt_cache_invalidate(void)
+static void rt_cache_invalidate(struct net *net)
{
unsigned char shuffle;
get_random_bytes(&shuffle, sizeof(shuffle));
- atomic_add(shuffle + 1U, &rt_genid);
+ atomic_add(shuffle + 1U, &net->ipv4.rt_genid);
}
/*
* delay < 0 : invalidate cache (fast : entries will be deleted later)
* delay >= 0 : invalidate & flush cache (can be long)
*/
-void rt_cache_flush(int delay)
+void rt_cache_flush(struct net *net, int delay)
{
- rt_cache_invalidate();
+ rt_cache_invalidate(net);
if (delay >= 0)
rt_do_flush(!in_softirq());
}
@@ -803,10 +839,11 @@ void rt_cache_flush(int delay)
/*
* We change rt_genid and let gc do the cleanup
*/
-static void rt_secret_rebuild(unsigned long dummy)
+static void rt_secret_rebuild(unsigned long __net)
{
- rt_cache_invalidate();
- mod_timer(&rt_secret_timer, jiffies + ip_rt_secret_interval);
+ struct net *net = (struct net *)__net;
+ rt_cache_invalidate(net);
+ mod_timer(&net->ipv4.rt_secret_timer, jiffies + ip_rt_secret_interval);
}
/*
@@ -882,7 +919,7 @@ static int rt_garbage_collect(struct dst_ops *ops)
rthp = &rt_hash_table[k].chain;
spin_lock_bh(rt_hash_lock_addr(k));
while ((rth = *rthp) != NULL) {
- if (rth->rt_genid == atomic_read(&rt_genid) &&
+ if (!rt_is_expired(rth) &&
!rt_may_expire(rth, tmo, expire)) {
tmo >>= 1;
rthp = &rth->u.dst.rt_next;
@@ -964,7 +1001,7 @@ restart:
spin_lock_bh(rt_hash_lock_addr(hash));
while ((rth = *rthp) != NULL) {
- if (rth->rt_genid != atomic_read(&rt_genid)) {
+ if (rt_is_expired(rth)) {
*rthp = rth->u.dst.rt_next;
rt_free(rth);
continue;
@@ -1140,7 +1177,7 @@ static void rt_del(unsigned hash, struct rtable *rt)
spin_lock_bh(rt_hash_lock_addr(hash));
ip_rt_put(rt);
while ((aux = *rthp) != NULL) {
- if (aux == rt || (aux->rt_genid != atomic_read(&rt_genid))) {
+ if (aux == rt || rt_is_expired(aux)) {
*rthp = aux->u.dst.rt_next;
rt_free(aux);
continue;
@@ -1182,7 +1219,8 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
for (i = 0; i < 2; i++) {
for (k = 0; k < 2; k++) {
- unsigned hash = rt_hash(daddr, skeys[i], ikeys[k]);
+ unsigned hash = rt_hash(daddr, skeys[i], ikeys[k],
+ rt_genid(net));
rthp=&rt_hash_table[hash].chain;
@@ -1194,7 +1232,7 @@ 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) ||
+ rt_is_expired(rth) ||
!net_eq(dev_net(rth->u.dst.dev), net)) {
rthp = &rth->u.dst.rt_next;
continue;
@@ -1233,7 +1271,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
rt->u.dst.neighbour = NULL;
rt->u.dst.hh = NULL;
rt->u.dst.xfrm = NULL;
- rt->rt_genid = atomic_read(&rt_genid);
+ rt->rt_genid = rt_genid(net);
rt->rt_flags |= RTCF_REDIRECTED;
/* Gateway is different ... */
@@ -1297,7 +1335,8 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
} else if ((rt->rt_flags & RTCF_REDIRECTED) ||
rt->u.dst.expires) {
unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
- rt->fl.oif);
+ rt->fl.oif,
+ rt_genid(dev_net(dst->dev)));
#if RT_CACHE_DEBUG >= 1
printk(KERN_DEBUG "ipv4_negative_advice: redirect to "
NIPQUAD_FMT "/%02x dropped\n",
@@ -1446,7 +1485,8 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph,
for (k = 0; k < 2; k++) {
for (i = 0; i < 2; i++) {
- unsigned hash = rt_hash(daddr, skeys[i], ikeys[k]);
+ unsigned hash = rt_hash(daddr, skeys[i], ikeys[k],
+ rt_genid(net));
rcu_read_lock();
for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
@@ -1461,7 +1501,7 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph,
rth->fl.iif != 0 ||
dst_metric_locked(&rth->u.dst, RTAX_MTU) ||
!net_eq(dev_net(rth->u.dst.dev), net) ||
- rth->rt_genid != atomic_read(&rt_genid))
+ !rt_is_expired(rth))
continue;
if (new_mtu < 68 || new_mtu >= old_mtu) {
@@ -1696,7 +1736,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rth->fl.oif = 0;
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
- rth->rt_genid = atomic_read(&rt_genid);
+ rth->rt_genid = rt_genid(dev_net(dev));
rth->rt_flags = RTCF_MULTICAST;
rth->rt_type = RTN_MULTICAST;
if (our) {
@@ -1711,7 +1751,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
RT_CACHE_STAT_INC(in_slow_mc);
in_dev_put(in_dev);
- hash = rt_hash(daddr, saddr, dev->ifindex);
+ hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev)));
return rt_intern_hash(hash, rth, &skb->rtable);
e_nobufs:
@@ -1837,7 +1877,7 @@ static int __mkroute_input(struct sk_buff *skb,
rth->u.dst.input = ip_forward;
rth->u.dst.output = ip_output;
- rth->rt_genid = atomic_read(&rt_genid);
+ rth->rt_genid = rt_genid(dev_net(rth->u.dst.dev));
rt_set_nexthop(rth, res, itag);
@@ -1872,7 +1912,8 @@ static int ip_mkroute_input(struct sk_buff *skb,
return err;
/* put it into the cache */
- hash = rt_hash(daddr, saddr, fl->iif);
+ hash = rt_hash(daddr, saddr, fl->iif,
+ rt_genid(dev_net(rth->u.dst.dev)));
return rt_intern_hash(hash, rth, &skb->rtable);
}
@@ -1998,7 +2039,7 @@ local_input:
goto e_nobufs;
rth->u.dst.output= ip_rt_bug;
- rth->rt_genid = atomic_read(&rt_genid);
+ rth->rt_genid = rt_genid(net);
atomic_set(&rth->u.dst.__refcnt, 1);
rth->u.dst.flags= DST_HOST;
@@ -2028,7 +2069,7 @@ local_input:
rth->rt_flags &= ~RTCF_LOCAL;
}
rth->rt_type = res.type;
- hash = rt_hash(daddr, saddr, fl.iif);
+ hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net));
err = rt_intern_hash(hash, rth, &skb->rtable);
goto done;
@@ -2079,7 +2120,7 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr,
net = dev_net(dev);
tos &= IPTOS_RT_MASK;
- hash = rt_hash(daddr, saddr, iif);
+ hash = rt_hash(daddr, saddr, iif, rt_genid(net));
rcu_read_lock();
for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
@@ -2091,7 +2132,7 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr,
(rth->fl.fl4_tos ^ tos)) == 0 &&
rth->fl.mark == skb->mark &&
net_eq(dev_net(rth->u.dst.dev), net) &&
- rth->rt_genid == atomic_read(&rt_genid)) {
+ !rt_is_expired(rth)) {
dst_use(&rth->u.dst, jiffies);
RT_CACHE_STAT_INC(in_hit);
rcu_read_unlock();
@@ -2219,7 +2260,7 @@ static int __mkroute_output(struct rtable **result,
rth->rt_spec_dst= fl->fl4_src;
rth->u.dst.output=ip_output;
- rth->rt_genid = atomic_read(&rt_genid);
+ rth->rt_genid = rt_genid(dev_net(dev_out));
RT_CACHE_STAT_INC(out_slow_tot);
@@ -2268,7 +2309,8 @@ static int ip_mkroute_output(struct rtable **rp,
int err = __mkroute_output(&rth, res, fl, oldflp, dev_out, flags);
unsigned hash;
if (err == 0) {
- hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif);
+ hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif,
+ rt_genid(dev_net(dev_out)));
err = rt_intern_hash(hash, rth, rp);
}
@@ -2480,7 +2522,7 @@ int __ip_route_output_key(struct net *net, struct rtable **rp,
unsigned hash;
struct rtable *rth;
- hash = rt_hash(flp->fl4_dst, flp->fl4_src, flp->oif);
+ hash = rt_hash(flp->fl4_dst, flp->fl4_src, flp->oif, rt_genid(net));
rcu_read_lock_bh();
for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
@@ -2493,7 +2535,7 @@ int __ip_route_output_key(struct net *net, struct rtable **rp,
!((rth->fl.fl4_tos ^ flp->fl4_tos) &
(IPTOS_RT_MASK | RTO_ONLINK)) &&
net_eq(dev_net(rth->u.dst.dev), net) &&
- rth->rt_genid == atomic_read(&rt_genid)) {
+ !rt_is_expired(rth)) {
dst_use(&rth->u.dst, jiffies);
RT_CACHE_STAT_INC(out_hit);
rcu_read_unlock_bh();
@@ -2524,7 +2566,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = {
};
-static int ipv4_dst_blackhole(struct rtable **rp, struct flowi *flp)
+static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi *flp)
{
struct rtable *ort = *rp;
struct rtable *rt = (struct rtable *)
@@ -2548,7 +2590,7 @@ static int ipv4_dst_blackhole(struct rtable **rp, struct flowi *flp)
rt->idev = ort->idev;
if (rt->idev)
in_dev_hold(rt->idev);
- rt->rt_genid = atomic_read(&rt_genid);
+ rt->rt_genid = rt_genid(net);
rt->rt_flags = ort->rt_flags;
rt->rt_type = ort->rt_type;
rt->rt_dst = ort->rt_dst;
@@ -2584,7 +2626,7 @@ int ip_route_output_flow(struct net *net, struct rtable **rp, struct flowi *flp,
err = __xfrm_lookup((struct dst_entry **)rp, flp, sk,
flags ? XFRM_LOOKUP_WAIT : 0);
if (err == -EREMOTE)
- err = ipv4_dst_blackhole(rp, flp);
+ err = ipv4_dst_blackhole(net, rp, flp);
return err;
}
@@ -2803,7 +2845,7 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb)
rt = rcu_dereference(rt->u.dst.rt_next), idx++) {
if (!net_eq(dev_net(rt->u.dst.dev), net) || idx < s_idx)
continue;
- if (rt->rt_genid != atomic_read(&rt_genid))
+ if (rt_is_expired(rt))
continue;
skb->dst = dst_clone(&rt->u.dst);
if (rt_fill_info(skb, NETLINK_CB(cb->skb).pid,
@@ -2827,19 +2869,25 @@ done:
void ip_rt_multicast_event(struct in_device *in_dev)
{
- rt_cache_flush(0);
+ rt_cache_flush(dev_net(in_dev->dev), 0);
}
#ifdef CONFIG_SYSCTL
-static int flush_delay;
-
-static int ipv4_sysctl_rtcache_flush(ctl_table *ctl, int write,
+static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write,
struct file *filp, void __user *buffer,
size_t *lenp, loff_t *ppos)
{
if (write) {
- proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
- rt_cache_flush(flush_delay);
+ int flush_delay;
+ ctl_table ctl;
+ struct net *net;
+
+ memcpy(&ctl, __ctl, sizeof(ctl));
+ ctl.data = &flush_delay;
+ proc_dointvec(&ctl, write, filp, buffer, lenp, ppos);
+
+ net = (struct net *)__ctl->extra1;
+ rt_cache_flush(net, flush_delay);
return 0;
}
@@ -2855,25 +2903,18 @@ static int ipv4_sysctl_rtcache_flush_strategy(ctl_table *table,
size_t newlen)
{
int delay;
+ struct net *net;
if (newlen != sizeof(int))
return -EINVAL;
if (get_user(delay, (int __user *)newval))
return -EFAULT;
- rt_cache_flush(delay);
+ net = (struct net *)table->extra1;
+ rt_cache_flush(net, delay);
return 0;
}
ctl_table ipv4_route_table[] = {
{
- .ctl_name = NET_IPV4_ROUTE_FLUSH,
- .procname = "flush",
- .data = &flush_delay,
- .maxlen = sizeof(int),
- .mode = 0200,
- .proc_handler = &ipv4_sysctl_rtcache_flush,
- .strategy = &ipv4_sysctl_rtcache_flush_strategy,
- },
- {
.ctl_name = NET_IPV4_ROUTE_GC_THRESH,
.procname = "gc_thresh",
.data = &ipv4_dst_ops.gc_thresh,
@@ -3011,8 +3052,97 @@ ctl_table ipv4_route_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 struct ctl_table ipv4_route_flush_table[] = {
+ {
+ .ctl_name = NET_IPV4_ROUTE_FLUSH,
+ .procname = "flush",
+ .maxlen = sizeof(int),
+ .mode = 0200,
+ .proc_handler = &ipv4_sysctl_rtcache_flush,
+ .strategy = &ipv4_sysctl_rtcache_flush_strategy,
+ },
+ { .ctl_name = 0 },
+};
+
+static __net_init int sysctl_route_net_init(struct net *net)
+{
+ struct ctl_table *tbl;
+
+ tbl = ipv4_route_flush_table;
+ if (net != &init_net) {
+ tbl = kmemdup(tbl, sizeof(ipv4_route_flush_table), GFP_KERNEL);
+ if (tbl == NULL)
+ goto err_dup;
+ }
+ tbl[0].extra1 = net;
+
+ net->ipv4.route_hdr =
+ register_net_sysctl_table(net, ipv4_route_path, tbl);
+ if (net->ipv4.route_hdr == NULL)
+ goto err_reg;
+ return 0;
+
+err_reg:
+ if (tbl != ipv4_route_flush_table)
+ kfree(tbl);
+err_dup:
+ return -ENOMEM;
+}
+
+static __net_exit void sysctl_route_net_exit(struct net *net)
+{
+ struct ctl_table *tbl;
+
+ tbl = net->ipv4.route_hdr->ctl_table_arg;
+ unregister_net_sysctl_table(net->ipv4.route_hdr);
+ BUG_ON(tbl == ipv4_route_flush_table);
+ kfree(tbl);
+}
+
+static __net_initdata struct pernet_operations sysctl_route_ops = {
+ .init = sysctl_route_net_init,
+ .exit = sysctl_route_net_exit,
+};
#endif
+
+static __net_init int rt_secret_timer_init(struct net *net)
+{
+ atomic_set(&net->ipv4.rt_genid,
+ (int) ((num_physpages ^ (num_physpages>>8)) ^
+ (jiffies ^ (jiffies >> 7))));
+
+ net->ipv4.rt_secret_timer.function = rt_secret_rebuild;
+ net->ipv4.rt_secret_timer.data = (unsigned long)net;
+ init_timer_deferrable(&net->ipv4.rt_secret_timer);
+
+ net->ipv4.rt_secret_timer.expires =
+ jiffies + net_random() % ip_rt_secret_interval +
+ ip_rt_secret_interval;
+ add_timer(&net->ipv4.rt_secret_timer);
+ return 0;
+}
+
+static __net_exit void rt_secret_timer_exit(struct net *net)
+{
+ del_timer_sync(&net->ipv4.rt_secret_timer);
+}
+
+static __net_initdata struct pernet_operations rt_secret_timer_ops = {
+ .init = rt_secret_timer_init,
+ .exit = rt_secret_timer_exit,
+};
+
+
#ifdef CONFIG_NET_CLS_ROUTE
struct ip_rt_acct *ip_rt_acct __read_mostly;
#endif /* CONFIG_NET_CLS_ROUTE */
@@ -3031,9 +3161,6 @@ int __init ip_rt_init(void)
{
int rc = 0;
- atomic_set(&rt_genid, (int) ((num_physpages ^ (num_physpages>>8)) ^
- (jiffies ^ (jiffies >> 7))));
-
#ifdef CONFIG_NET_CLS_ROUTE
ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct));
if (!ip_rt_acct)
@@ -3065,19 +3192,14 @@ int __init ip_rt_init(void)
devinet_init();
ip_fib_init();
- rt_secret_timer.function = rt_secret_rebuild;
- rt_secret_timer.data = 0;
- init_timer_deferrable(&rt_secret_timer);
-
/* All the timers, started at system startup tend
to synchronize. Perturb it a bit.
*/
schedule_delayed_work(&expires_work,
net_random() % ip_rt_gc_interval + ip_rt_gc_interval);
- rt_secret_timer.expires = jiffies + net_random() % ip_rt_secret_interval +
- ip_rt_secret_interval;
- add_timer(&rt_secret_timer);
+ if (register_pernet_subsys(&rt_secret_timer_ops))
+ printk(KERN_ERR "Unable to setup rt_secret_timer\n");
if (ip_rt_proc_init())
printk(KERN_ERR "Unable to create route proc files\n");
@@ -3087,6 +3209,9 @@ int __init ip_rt_init(void)
#endif
rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL);
+#ifdef CONFIG_SYSCTL
+ register_pernet_subsys(&sysctl_route_ops);
+#endif
return rc;
}
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index d182a2a2629..fdde2ae07e2 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -8,8 +8,6 @@
* 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.
- *
- * $Id: syncookies.c,v 1.18 2002/02/01 22:01:04 davem Exp $
*/
#include <linux/tcp.h>
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index c437f804ee3..14ef202a225 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -1,8 +1,6 @@
/*
* sysctl_net_ipv4.c: sysctl interface to net IPV4 subsystem.
*
- * $Id: sysctl_net_ipv4.c,v 1.50 2001/10/20 00:00:11 davem Exp $
- *
* Begun April 1, 1996, Mike Shaver.
* Added /proc/sys/net/ipv4 directory entry (empty =) ). [MS]
*/
@@ -795,7 +793,8 @@ static struct ctl_table ipv4_net_table[] = {
.data = &init_net.ipv4.sysctl_icmp_ratelimit,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = &proc_dointvec
+ .proc_handler = &proc_dointvec_ms_jiffies,
+ .strategy = &sysctl_ms_jiffies
},
{
.ctl_name = NET_IPV4_ICMP_RATEMASK,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1d723de1868..56a133c6145 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -5,8 +5,6 @@
*
* Implementation of the Transmission Control Protocol(TCP).
*
- * Version: $Id: tcp.c,v 1.216 2002/02/01 22:01:04 davem Exp $
- *
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
@@ -2467,6 +2465,76 @@ static unsigned long tcp_md5sig_users;
static struct tcp_md5sig_pool **tcp_md5sig_pool;
static DEFINE_SPINLOCK(tcp_md5sig_pool_lock);
+int tcp_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key,
+ int bplen,
+ struct tcphdr *th, unsigned int tcplen,
+ struct tcp_md5sig_pool *hp)
+{
+ struct scatterlist sg[4];
+ __u16 data_len;
+ int block = 0;
+ __sum16 cksum;
+ struct hash_desc *desc = &hp->md5_desc;
+ int err;
+ unsigned int nbytes = 0;
+
+ sg_init_table(sg, 4);
+
+ /* 1. The TCP pseudo-header */
+ sg_set_buf(&sg[block++], &hp->md5_blk, bplen);
+ nbytes += bplen;
+
+ /* 2. The TCP header, excluding options, and assuming a
+ * checksum of zero
+ */
+ cksum = th->check;
+ th->check = 0;
+ sg_set_buf(&sg[block++], th, sizeof(*th));
+ nbytes += sizeof(*th);
+
+ /* 3. The TCP segment data (if any) */
+ data_len = tcplen - (th->doff << 2);
+ if (data_len > 0) {
+ u8 *data = (u8 *)th + (th->doff << 2);
+ sg_set_buf(&sg[block++], data, data_len);
+ nbytes += data_len;
+ }
+
+ /* 4. an independently-specified key or password, known to both
+ * TCPs and presumably connection-specific
+ */
+ sg_set_buf(&sg[block++], key->key, key->keylen);
+ nbytes += key->keylen;
+
+ sg_mark_end(&sg[block - 1]);
+
+ /* Now store the hash into the packet */
+ err = crypto_hash_init(desc);
+ if (err) {
+ if (net_ratelimit())
+ printk(KERN_WARNING "%s(): hash_init failed\n", __func__);
+ return -1;
+ }
+ err = crypto_hash_update(desc, sg, nbytes);
+ if (err) {
+ if (net_ratelimit())
+ printk(KERN_WARNING "%s(): hash_update failed\n", __func__);
+ return -1;
+ }
+ err = crypto_hash_final(desc, md5_hash);
+ if (err) {
+ if (net_ratelimit())
+ printk(KERN_WARNING "%s(): hash_final failed\n", __func__);
+ return -1;
+ }
+
+ /* Reset header */
+ th->check = cksum;
+
+ return 0;
+}
+EXPORT_SYMBOL(tcp_calc_md5_hash);
+
static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool **pool)
{
int cpu;
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 2fbcc7d1b1a..838d491dfda 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -1,8 +1,6 @@
/*
* tcp_diag.c Module for monitoring TCP transport protocols sockets.
*
- * Version: $Id: tcp_diag.c,v 1.3 2002/02/01 22:01:04 davem Exp $
- *
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* This program is free software; you can redistribute it and/or
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index cad73b7dfef..d6ea970a151 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5,8 +5,6 @@
*
* Implementation of the Transmission Control Protocol(TCP).
*
- * Version: $Id: tcp_input.c,v 1.243 2002/02/01 22:01:04 davem Exp $
- *
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
@@ -949,17 +947,21 @@ static void tcp_update_reordering(struct sock *sk, const int metric,
{
struct tcp_sock *tp = tcp_sk(sk);
if (metric > tp->reordering) {
+ int mib_idx;
+
tp->reordering = min(TCP_MAX_REORDERING, metric);
/* This exciting event is worth to be remembered. 8) */
if (ts)
- NET_INC_STATS_BH(LINUX_MIB_TCPTSREORDER);
+ mib_idx = LINUX_MIB_TCPTSREORDER;
else if (tcp_is_reno(tp))
- NET_INC_STATS_BH(LINUX_MIB_TCPRENOREORDER);
+ mib_idx = LINUX_MIB_TCPRENOREORDER;
else if (tcp_is_fack(tp))
- NET_INC_STATS_BH(LINUX_MIB_TCPFACKREORDER);
+ mib_idx = LINUX_MIB_TCPFACKREORDER;
else
- NET_INC_STATS_BH(LINUX_MIB_TCPSACKREORDER);
+ mib_idx = LINUX_MIB_TCPSACKREORDER;
+
+ NET_INC_STATS_BH(mib_idx);
#if FASTRETRANS_DEBUG > 1
printk(KERN_DEBUG "Disorder%d %d %u f%u s%u rr%d\n",
tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state,
@@ -1458,18 +1460,22 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb,
if (!tcp_is_sackblock_valid(tp, dup_sack,
sp[used_sacks].start_seq,
sp[used_sacks].end_seq)) {
+ int mib_idx;
+
if (dup_sack) {
if (!tp->undo_marker)
- NET_INC_STATS_BH(LINUX_MIB_TCPDSACKIGNOREDNOUNDO);
+ mib_idx = LINUX_MIB_TCPDSACKIGNOREDNOUNDO;
else
- NET_INC_STATS_BH(LINUX_MIB_TCPDSACKIGNOREDOLD);
+ mib_idx = LINUX_MIB_TCPDSACKIGNOREDOLD;
} else {
/* Don't count olds caused by ACK reordering */
if ((TCP_SKB_CB(ack_skb)->ack_seq != tp->snd_una) &&
!after(sp[used_sacks].end_seq, tp->snd_una))
continue;
- NET_INC_STATS_BH(LINUX_MIB_TCPSACKDISCARD);
+ mib_idx = LINUX_MIB_TCPSACKDISCARD;
}
+
+ NET_INC_STATS_BH(mib_idx);
if (i == 0)
first_sack_index = -1;
continue;
@@ -2382,15 +2388,19 @@ static int tcp_try_undo_recovery(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
if (tcp_may_undo(tp)) {
+ int mib_idx;
+
/* Happy end! We did not retransmit anything
* or our original transmission succeeded.
*/
DBGUNDO(sk, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans");
tcp_undo_cwr(sk, 1);
if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
- NET_INC_STATS_BH(LINUX_MIB_TCPLOSSUNDO);
+ mib_idx = LINUX_MIB_TCPLOSSUNDO;
else
- NET_INC_STATS_BH(LINUX_MIB_TCPFULLUNDO);
+ mib_idx = LINUX_MIB_TCPFULLUNDO;
+
+ NET_INC_STATS_BH(mib_idx);
tp->undo_marker = 0;
}
if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
@@ -2562,7 +2572,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag)
int is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
int do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
(tcp_fackets_out(tp) > tp->reordering));
- int fast_rexmit = 0;
+ int fast_rexmit = 0, mib_idx;
if (WARN_ON(!tp->packets_out && tp->sacked_out))
tp->sacked_out = 0;
@@ -2685,9 +2695,11 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag)
/* Otherwise enter Recovery state */
if (tcp_is_reno(tp))
- NET_INC_STATS_BH(LINUX_MIB_TCPRENORECOVERY);
+ mib_idx = LINUX_MIB_TCPRENORECOVERY;
else
- NET_INC_STATS_BH(LINUX_MIB_TCPSACKRECOVERY);
+ mib_idx = LINUX_MIB_TCPSACKRECOVERY;
+
+ NET_INC_STATS_BH(mib_idx);
tp->high_seq = tp->snd_nxt;
tp->prior_ssthresh = 0;
@@ -3450,6 +3462,43 @@ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th,
return 1;
}
+#ifdef CONFIG_TCP_MD5SIG
+/*
+ * Parse MD5 Signature option
+ */
+u8 *tcp_parse_md5sig_option(struct tcphdr *th)
+{
+ int length = (th->doff << 2) - sizeof (*th);
+ u8 *ptr = (u8*)(th + 1);
+
+ /* If the TCP option is too short, we can short cut */
+ if (length < TCPOLEN_MD5SIG)
+ return NULL;
+
+ while (length > 0) {
+ int opcode = *ptr++;
+ int opsize;
+
+ switch(opcode) {
+ case TCPOPT_EOL:
+ return NULL;
+ case TCPOPT_NOP:
+ length--;
+ continue;
+ default:
+ opsize = *ptr++;
+ if (opsize < 2 || opsize > length)
+ return NULL;
+ if (opcode == TCPOPT_MD5SIG)
+ return ptr;
+ }
+ ptr += opsize - 2;
+ length -= opsize;
+ }
+ return NULL;
+}
+#endif
+
static inline void tcp_store_ts_recent(struct tcp_sock *tp)
{
tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval;
@@ -3665,10 +3714,14 @@ static inline int tcp_sack_extend(struct tcp_sack_block *sp, u32 seq,
static void tcp_dsack_set(struct tcp_sock *tp, u32 seq, u32 end_seq)
{
if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
+ int mib_idx;
+
if (before(seq, tp->rcv_nxt))
- NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOLDSENT);
+ mib_idx = LINUX_MIB_TCPDSACKOLDSENT;
else
- NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOFOSENT);
+ mib_idx = LINUX_MIB_TCPDSACKOFOSENT;
+
+ NET_INC_STATS_BH(mib_idx);
tp->rx_opt.dsack = 1;
tp->duplicate_sack[0].start_seq = seq;
@@ -5422,6 +5475,9 @@ EXPORT_SYMBOL(sysctl_tcp_ecn);
EXPORT_SYMBOL(sysctl_tcp_reordering);
EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
EXPORT_SYMBOL(tcp_parse_options);
+#ifdef CONFIG_TCP_MD5SIG
+EXPORT_SYMBOL(tcp_parse_md5sig_option);
+#endif
EXPORT_SYMBOL(tcp_rcv_established);
EXPORT_SYMBOL(tcp_rcv_state_process);
EXPORT_SYMBOL(tcp_initialize_rcv_mss);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ffe869ac1bc..4300bcf2cea 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -5,8 +5,6 @@
*
* Implementation of the Transmission Control Protocol(TCP).
*
- * Version: $Id: tcp_ipv4.c,v 1.240 2002/02/01 22:01:04 davem Exp $
- *
* IPv4 specific functions
*
*
@@ -91,8 +89,13 @@ static struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk,
__be32 addr);
static int tcp_v4_do_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key,
__be32 saddr, __be32 daddr,
- struct tcphdr *th, int protocol,
- unsigned int tcplen);
+ struct tcphdr *th, unsigned int tcplen);
+#else
+static inline
+struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr)
+{
+ return NULL;
+}
#endif
struct inet_hashinfo __cacheline_aligned tcp_hashinfo = {
@@ -582,8 +585,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
key,
ip_hdr(skb)->daddr,
ip_hdr(skb)->saddr,
- &rep.th, IPPROTO_TCP,
- arg.iov[0].iov_len);
+ &rep.th, arg.iov[0].iov_len);
}
#endif
arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr,
@@ -602,9 +604,9 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
outside socket context is ugly, certainly. What can I do?
*/
-static void tcp_v4_send_ack(struct tcp_timewait_sock *twsk,
- struct sk_buff *skb, u32 seq, u32 ack,
- u32 win, u32 ts)
+static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
+ u32 win, u32 ts, int oif,
+ struct tcp_md5sig_key *key)
{
struct tcphdr *th = tcp_hdr(skb);
struct {
@@ -616,10 +618,6 @@ static void tcp_v4_send_ack(struct tcp_timewait_sock *twsk,
];
} rep;
struct ip_reply_arg arg;
-#ifdef CONFIG_TCP_MD5SIG
- struct tcp_md5sig_key *key;
- struct tcp_md5sig_key tw_key;
-#endif
memset(&rep.th, 0, sizeof(struct tcphdr));
memset(&arg, 0, sizeof(arg));
@@ -645,23 +643,6 @@ static void tcp_v4_send_ack(struct tcp_timewait_sock *twsk,
rep.th.window = htons(win);
#ifdef CONFIG_TCP_MD5SIG
- /*
- * The SKB holds an imcoming packet, but may not have a valid ->sk
- * pointer. This is especially the case when we're dealing with a
- * TIME_WAIT ack, because the sk structure is long gone, and only
- * the tcp_timewait_sock remains. So the md5 key is stashed in that
- * structure, and we use it in preference. I believe that (twsk ||
- * skb->sk) holds true, but we program defensively.
- */
- if (!twsk && skb->sk) {
- key = tcp_v4_md5_do_lookup(skb->sk, ip_hdr(skb)->daddr);
- } else if (twsk && twsk->tw_md5_keylen) {
- tw_key.key = twsk->tw_md5_key;
- tw_key.keylen = twsk->tw_md5_keylen;
- key = &tw_key;
- } else
- key = NULL;
-
if (key) {
int offset = (ts) ? 3 : 0;
@@ -676,16 +657,15 @@ static void tcp_v4_send_ack(struct tcp_timewait_sock *twsk,
key,
ip_hdr(skb)->daddr,
ip_hdr(skb)->saddr,
- &rep.th, IPPROTO_TCP,
- arg.iov[0].iov_len);
+ &rep.th, arg.iov[0].iov_len);
}
#endif
arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr,
ip_hdr(skb)->saddr, /* XXX */
arg.iov[0].iov_len, IPPROTO_TCP, 0);
arg.csumoffset = offsetof(struct tcphdr, check) / 2;
- if (twsk)
- arg.bound_dev_if = twsk->tw_sk.tw_bound_dev_if;
+ if (oif)
+ arg.bound_dev_if = oif;
ip_send_reply(dev_net(skb->dev)->ipv4.tcp_sock, skb,
&arg, arg.iov[0].iov_len);
@@ -698,9 +678,12 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
struct inet_timewait_sock *tw = inet_twsk(sk);
struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
- tcp_v4_send_ack(tcptw, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+ tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
- tcptw->tw_ts_recent);
+ tcptw->tw_ts_recent,
+ tw->tw_bound_dev_if,
+ tcp_twsk_md5_key(tcptw)
+ );
inet_twsk_put(tw);
}
@@ -708,9 +691,11 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
static void tcp_v4_reqsk_send_ack(struct sk_buff *skb,
struct request_sock *req)
{
- tcp_v4_send_ack(NULL, skb, tcp_rsk(req)->snt_isn + 1,
+ tcp_v4_send_ack(skb, tcp_rsk(req)->snt_isn + 1,
tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd,
- req->ts_recent);
+ req->ts_recent,
+ 0,
+ tcp_v4_md5_do_lookup(skb->sk, ip_hdr(skb)->daddr));
}
/*
@@ -1002,18 +987,12 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval,
static int tcp_v4_do_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key,
__be32 saddr, __be32 daddr,
- struct tcphdr *th, int protocol,
+ struct tcphdr *th,
unsigned int tcplen)
{
- struct scatterlist sg[4];
- __u16 data_len;
- int block = 0;
- __sum16 old_checksum;
struct tcp_md5sig_pool *hp;
struct tcp4_pseudohdr *bp;
- struct hash_desc *desc;
int err;
- unsigned int nbytes = 0;
/*
* Okay, so RFC2385 is turned on for this connection,
@@ -1025,63 +1004,25 @@ static int tcp_v4_do_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key,
goto clear_hash_noput;
bp = &hp->md5_blk.ip4;
- desc = &hp->md5_desc;
/*
- * 1. the TCP pseudo-header (in the order: source IP address,
+ * The TCP pseudo-header (in the order: source IP address,
* destination IP address, zero-padded protocol number, and
* segment length)
*/
bp->saddr = saddr;
bp->daddr = daddr;
bp->pad = 0;
- bp->protocol = protocol;
+ bp->protocol = IPPROTO_TCP;
bp->len = htons(tcplen);
- sg_init_table(sg, 4);
-
- sg_set_buf(&sg[block++], bp, sizeof(*bp));
- nbytes += sizeof(*bp);
-
- /* 2. the TCP header, excluding options, and assuming a
- * checksum of zero/
- */
- old_checksum = th->check;
- th->check = 0;
- sg_set_buf(&sg[block++], th, sizeof(struct tcphdr));
- nbytes += sizeof(struct tcphdr);
-
- /* 3. the TCP segment data (if any) */
- data_len = tcplen - (th->doff << 2);
- if (data_len > 0) {
- unsigned char *data = (unsigned char *)th + (th->doff << 2);
- sg_set_buf(&sg[block++], data, data_len);
- nbytes += data_len;
- }
-
- /* 4. an independently-specified key or password, known to both
- * TCPs and presumably connection-specific
- */
- sg_set_buf(&sg[block++], key->key, key->keylen);
- nbytes += key->keylen;
-
- sg_mark_end(&sg[block - 1]);
-
- /* Now store the Hash into the packet */
- err = crypto_hash_init(desc);
- if (err)
- goto clear_hash;
- err = crypto_hash_update(desc, sg, nbytes);
- if (err)
- goto clear_hash;
- err = crypto_hash_final(desc, md5_hash);
+ err = tcp_calc_md5_hash(md5_hash, key, sizeof(*bp),
+ th, tcplen, hp);
if (err)
goto clear_hash;
- /* Reset header, and free up the crypto */
+ /* Free up the crypto pool */
tcp_put_md5sig_pool();
- th->check = old_checksum;
-
out:
return 0;
clear_hash:
@@ -1095,7 +1036,7 @@ int tcp_v4_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key,
struct sock *sk,
struct dst_entry *dst,
struct request_sock *req,
- struct tcphdr *th, int protocol,
+ struct tcphdr *th,
unsigned int tcplen)
{
__be32 saddr, daddr;
@@ -1111,7 +1052,7 @@ int tcp_v4_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key,
}
return tcp_v4_do_calc_md5_hash(md5_hash, key,
saddr, daddr,
- th, protocol, tcplen);
+ th, tcplen);
}
EXPORT_SYMBOL(tcp_v4_calc_md5_hash);
@@ -1130,52 +1071,12 @@ static int tcp_v4_inbound_md5_hash(struct sock *sk, struct sk_buff *skb)
struct tcp_md5sig_key *hash_expected;
const struct iphdr *iph = ip_hdr(skb);
struct tcphdr *th = tcp_hdr(skb);
- int length = (th->doff << 2) - sizeof(struct tcphdr);
int genhash;
- unsigned char *ptr;
unsigned char newhash[16];
hash_expected = tcp_v4_md5_do_lookup(sk, iph->saddr);
+ hash_location = tcp_parse_md5sig_option(th);
- /*
- * If the TCP option length is less than the TCP_MD5SIG
- * option length, then we can shortcut
- */
- if (length < TCPOLEN_MD5SIG) {
- if (hash_expected)
- return 1;
- else
- return 0;
- }
-
- /* Okay, we can't shortcut - we have to grub through the options */
- ptr = (unsigned char *)(th + 1);
- while (length > 0) {
- int opcode = *ptr++;
- int opsize;
-
- switch (opcode) {
- case TCPOPT_EOL:
- goto done_opts;
- case TCPOPT_NOP:
- length--;
- continue;
- default:
- opsize = *ptr++;
- if (opsize < 2)
- goto done_opts;
- if (opsize > length)
- goto done_opts;
-
- if (opcode == TCPOPT_MD5SIG) {
- hash_location = ptr;
- goto done_opts;
- }
- }
- ptr += opsize-2;
- length -= opsize;
- }
-done_opts:
/* We've parsed the options - do we have a hash? */
if (!hash_expected && !hash_location)
return 0;
@@ -1202,8 +1103,7 @@ done_opts:
genhash = tcp_v4_do_calc_md5_hash(newhash,
hash_expected,
iph->saddr, iph->daddr,
- th, sk->sk_protocol,
- skb->len);
+ th, skb->len);
if (genhash || memcmp(hash_location, newhash, 16) != 0) {
if (net_ratelimit()) {
@@ -1871,7 +1771,7 @@ static int tcp_v4_init_sock(struct sock *sk)
return 0;
}
-int tcp_v4_destroy_sock(struct sock *sk)
+void tcp_v4_destroy_sock(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -1915,8 +1815,6 @@ int tcp_v4_destroy_sock(struct sock *sk)
}
atomic_dec(&tcp_sockets_allocated);
-
- return 0;
}
EXPORT_SYMBOL(tcp_v4_destroy_sock);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 8245247a6ce..ea68a478fad 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -5,8 +5,6 @@
*
* Implementation of the Transmission Control Protocol(TCP).
*
- * Version: $Id: tcp_minisocks.c,v 1.15 2002/02/01 22:01:04 davem Exp $
- *
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index ad993ecb481..edef2afe905 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -5,8 +5,6 @@
*
* Implementation of the Transmission Control Protocol(TCP).
*
- * Version: $Id: tcp_output.c,v 1.146 2002/02/01 22:01:04 davem Exp $
- *
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
@@ -607,7 +605,6 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
md5,
sk, NULL, NULL,
tcp_hdr(skb),
- sk->sk_protocol,
skb->len);
}
#endif
@@ -1988,14 +1985,17 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
if (sacked & TCPCB_LOST) {
if (!(sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS))) {
+ int mib_idx;
+
if (tcp_retransmit_skb(sk, skb)) {
tp->retransmit_skb_hint = NULL;
return;
}
if (icsk->icsk_ca_state != TCP_CA_Loss)
- NET_INC_STATS_BH(LINUX_MIB_TCPFASTRETRANS);
+ mib_idx = LINUX_MIB_TCPFASTRETRANS;
else
- NET_INC_STATS_BH(LINUX_MIB_TCPSLOWSTARTRETRANS);
+ mib_idx = LINUX_MIB_TCPSLOWSTARTRETRANS;
+ NET_INC_STATS_BH(mib_idx);
if (skb == tcp_write_queue_head(sk))
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
@@ -2266,7 +2266,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
tp->af_specific->calc_md5_hash(md5_hash_location,
md5,
NULL, dst, req,
- tcp_hdr(skb), sk->sk_protocol,
+ tcp_hdr(skb),
skb->len);
}
#endif
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 63ed9d6830e..6a480d1fd8f 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -5,8 +5,6 @@
*
* Implementation of the Transmission Control Protocol(TCP).
*
- * Version: $Id: tcp_timer.c,v 1.88 2002/02/01 22:01:04 davem Exp $
- *
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
@@ -328,24 +326,27 @@ static void tcp_retransmit_timer(struct sock *sk)
goto out;
if (icsk->icsk_retransmits == 0) {
+ int mib_idx;
+
if (icsk->icsk_ca_state == TCP_CA_Disorder ||
icsk->icsk_ca_state == TCP_CA_Recovery) {
if (tcp_is_sack(tp)) {
if (icsk->icsk_ca_state == TCP_CA_Recovery)
- NET_INC_STATS_BH(LINUX_MIB_TCPSACKRECOVERYFAIL);
+ mib_idx = LINUX_MIB_TCPSACKRECOVERYFAIL;
else
- NET_INC_STATS_BH(LINUX_MIB_TCPSACKFAILURES);
+ mib_idx = LINUX_MIB_TCPSACKFAILURES;
} else {
if (icsk->icsk_ca_state == TCP_CA_Recovery)
- NET_INC_STATS_BH(LINUX_MIB_TCPRENORECOVERYFAIL);
+ mib_idx = LINUX_MIB_TCPRENORECOVERYFAIL;
else
- NET_INC_STATS_BH(LINUX_MIB_TCPRENOFAILURES);
+ mib_idx = LINUX_MIB_TCPRENOFAILURES;
}
} else if (icsk->icsk_ca_state == TCP_CA_Loss) {
- NET_INC_STATS_BH(LINUX_MIB_TCPLOSSFAILURES);
+ mib_idx = LINUX_MIB_TCPLOSSFAILURES;
} else {
- NET_INC_STATS_BH(LINUX_MIB_TCPTIMEOUTS);
+ mib_idx = LINUX_MIB_TCPTIMEOUTS;
}
+ NET_INC_STATS_BH(mib_idx);
}
if (tcp_use_frto(sk)) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 56fcda3694b..7187121e922 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -5,8 +5,6 @@
*
* The User Datagram Protocol (UDP).
*
- * Version: $Id: udp.c,v 1.102 2002/02/01 22:01:04 davem Exp $
- *
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Arnt Gulbrandsen, <agulbra@nvg.unit.no>
@@ -136,7 +134,7 @@ static inline int __udp_lib_lport_inuse(struct net *net, __u16 num,
struct sock *sk;
struct hlist_node *node;
- sk_for_each(sk, node, &udptable[num & (UDP_HTABLE_SIZE - 1)])
+ sk_for_each(sk, node, &udptable[udp_hashfn(net, num)])
if (net_eq(sock_net(sk), net) && sk->sk_hash == num)
return 1;
return 0;
@@ -176,7 +174,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
for (i = 0; i < UDP_HTABLE_SIZE; i++) {
int size = 0;
- head = &udptable[rover & (UDP_HTABLE_SIZE - 1)];
+ head = &udptable[udp_hashfn(net, rover)];
if (hlist_empty(head))
goto gotit;
@@ -213,7 +211,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
gotit:
snum = rover;
} else {
- head = &udptable[snum & (UDP_HTABLE_SIZE - 1)];
+ head = &udptable[udp_hashfn(net, snum)];
sk_for_each(sk2, node, head)
if (sk2->sk_hash == snum &&
@@ -229,7 +227,7 @@ gotit:
inet_sk(sk)->num = snum;
sk->sk_hash = snum;
if (sk_unhashed(sk)) {
- head = &udptable[snum & (UDP_HTABLE_SIZE - 1)];
+ head = &udptable[udp_hashfn(net, snum)];
sk_add_node(sk, head);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
}
@@ -266,7 +264,7 @@ static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
int badness = -1;
read_lock(&udp_hash_lock);
- sk_for_each(sk, node, &udptable[hnum & (UDP_HTABLE_SIZE - 1)]) {
+ sk_for_each(sk, node, &udptable[udp_hashfn(net, hnum)]) {
struct inet_sock *inet = inet_sk(sk);
if (net_eq(sock_net(sk), net) && sk->sk_hash == hnum &&
@@ -528,7 +526,8 @@ out:
up->len = 0;
up->pending = 0;
if (!err)
- UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite);
+ UDP_INC_STATS_USER(sock_net(sk),
+ UDP_MIB_OUTDATAGRAMS, is_udplite);
return err;
}
@@ -727,7 +726,8 @@ out:
* seems like overkill.
*/
if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
- UDP_INC_STATS_USER(UDP_MIB_SNDBUFERRORS, is_udplite);
+ UDP_INC_STATS_USER(sock_net(sk),
+ UDP_MIB_SNDBUFERRORS, is_udplite);
}
return err;
@@ -890,7 +890,8 @@ try_again:
goto out_free;
if (!peeked)
- UDP_INC_STATS_USER(UDP_MIB_INDATAGRAMS, is_udplite);
+ UDP_INC_STATS_USER(sock_net(sk),
+ UDP_MIB_INDATAGRAMS, is_udplite);
sock_recv_timestamp(msg, sk, skb);
@@ -919,7 +920,7 @@ out:
csum_copy_err:
lock_sock(sk);
if (!skb_kill_datagram(sk, skb, flags))
- UDP_INC_STATS_USER(UDP_MIB_INERRORS, is_udplite);
+ UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
release_sock(sk);
if (noblock)
@@ -990,7 +991,8 @@ int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
ret = (*up->encap_rcv)(sk, skb);
if (ret <= 0) {
- UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS,
+ UDP_INC_STATS_BH(sock_net(sk),
+ UDP_MIB_INDATAGRAMS,
is_udplite);
return -ret;
}
@@ -1042,15 +1044,18 @@ int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
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);
+ if (rc == -ENOMEM) {
+ UDP_INC_STATS_BH(sock_net(sk),
+ UDP_MIB_RCVBUFERRORS, is_udplite);
+ atomic_inc(&sk->sk_drops);
+ }
goto drop;
}
return 0;
drop:
- UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite);
+ UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
kfree_skb(skb);
return -1;
}
@@ -1061,7 +1066,7 @@ drop:
* 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,
+static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
struct udphdr *uh,
__be32 saddr, __be32 daddr,
struct hlist_head udptable[])
@@ -1070,7 +1075,7 @@ static int __udp4_lib_mcast_deliver(struct sk_buff *skb,
int dif;
read_lock(&udp_hash_lock);
- sk = sk_head(&udptable[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]);
+ sk = sk_head(&udptable[udp_hashfn(net, ntohs(uh->dest))]);
dif = skb->dev->ifindex;
sk = udp_v4_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif);
if (sk) {
@@ -1158,6 +1163,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
struct rtable *rt = (struct rtable*)skb->dst;
__be32 saddr = ip_hdr(skb)->saddr;
__be32 daddr = ip_hdr(skb)->daddr;
+ struct net *net = dev_net(skb->dev);
/*
* Validate the packet.
@@ -1180,9 +1186,10 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
goto csum_error;
if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
- return __udp4_lib_mcast_deliver(skb, uh, saddr, daddr, udptable);
+ return __udp4_lib_mcast_deliver(net, skb, uh,
+ saddr, daddr, udptable);
- sk = __udp4_lib_lookup(dev_net(skb->dev), saddr, uh->source, daddr,
+ sk = __udp4_lib_lookup(net, saddr, uh->source, daddr,
uh->dest, inet_iif(skb), udptable);
if (sk != NULL) {
@@ -1211,7 +1218,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
if (udp_lib_checksum_complete(skb))
goto csum_error;
- UDP_INC_STATS_BH(UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE);
+ UDP_INC_STATS_BH(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
/*
@@ -1245,7 +1252,7 @@ csum_error:
ntohs(uh->dest),
ulen);
drop:
- UDP_INC_STATS_BH(UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
+ UDP_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE);
kfree_skb(skb);
return 0;
}
@@ -1255,12 +1262,11 @@ int udp_rcv(struct sk_buff *skb)
return __udp4_lib_rcv(skb, udp_hash, IPPROTO_UDP);
}
-int udp_destroy_sock(struct sock *sk)
+void udp_destroy_sock(struct sock *sk)
{
lock_sock(sk);
udp_flush_pending_frames(sk);
release_sock(sk);
- return 0;
}
/*
@@ -1453,7 +1459,8 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
spin_lock_bh(&rcvq->lock);
while ((skb = skb_peek(rcvq)) != NULL &&
udp_lib_checksum_complete(skb)) {
- UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_lite);
+ UDP_INC_STATS_BH(sock_net(sk),
+ UDP_MIB_INERRORS, is_lite);
__skb_unlink(skb, rcvq);
kfree_skb(skb);
}
@@ -1629,12 +1636,13 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f,
__u16 srcp = ntohs(inet->sport);
seq_printf(f, "%4d: %08X:%04X %08X:%04X"
- " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p%n",
+ " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d%n",
bucket, src, 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, len);
+ atomic_read(&sp->sk_refcnt), sp,
+ atomic_read(&sp->sk_drops), len);
}
int udp4_seq_show(struct seq_file *seq, void *v)
@@ -1643,7 +1651,7 @@ int udp4_seq_show(struct seq_file *seq, void *v)
seq_printf(seq, "%-127s\n",
" sl local_address rem_address st tx_queue "
"rx_queue tr tm->when retrnsmt uid timeout "
- "inode");
+ "inode ref pointer drops");
else {
struct udp_iter_state *state = seq->private;
int len;
diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h
index 7288bf7977f..2e9bad2fa1b 100644
--- a/net/ipv4/udp_impl.h
+++ b/net/ipv4/udp_impl.h
@@ -26,7 +26,7 @@ extern int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
extern int udp_sendpage(struct sock *sk, struct page *page, int offset,
size_t size, int flags);
extern int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb);
-extern int udp_destroy_sock(struct sock *sk);
+extern void udp_destroy_sock(struct sock *sk);
#ifdef CONFIG_PROC_FS
extern int udp4_seq_show(struct seq_file *seq, void *v);
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index 72ce26b6c4d..4ad16b6d513 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -1,8 +1,6 @@
/*
* UDPLITE An implementation of the UDP-Lite protocol (RFC 3828).
*
- * Version: $Id: udplite.c,v 1.25 2006/10/19 07:22:36 gerrit Exp $
- *
* Authors: Gerrit Renker <gerrit@erg.abdn.ac.uk>
*
* Changes: