summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2012-08-23 05:48:21 +0400
committerDavid S. Miller <davem@davemloft.net>2012-08-23 05:48:52 +0400
commitbf277b0ccea7d2422b85e232017ce3fddbe9c49c (patch)
tree252232255b8a6024eccf2fea668bb89de5ae3073 /net
parentbba6ec7e4963e30366359686f34e5bdb00b1a066 (diff)
parent90efbed18a30d78145419cdbd44f9ec152efeb16 (diff)
downloadlinux-bf277b0ccea7d2422b85e232017ce3fddbe9c49c.tar.xz
Merge git://1984.lsi.us.es/nf-next
Pablo Neira Ayuso says: ==================== This is the first batch of Netfilter and IPVS updates for your net-next tree. Mostly cleanups for the Netfilter side. They are: * Remove unnecessary RTNL locking now that we have support for namespace in nf_conntrack, from Patrick McHardy. * Cleanup to eliminate unnecessary goto in the initialization path of several Netfilter tables, from Jean Sacren. * Another cleanup from Wu Fengguang, this time to PTR_RET instead of if IS_ERR then return PTR_ERR. * Use list_for_each_entry_continue_rcu in nf_iterate, from Michael Wang. * Add pmtu_disc sysctl option to disable PMTU in their tunneling transmitter, from Julian Anastasov. * Generalize application protocol registration in IPVS and modify IPVS FTP helper to use it, from Julian Anastasov. * update Kconfig. The IPVS FTP helper depends on the Netfilter FTP helper for NAT support, from Julian Anastasov. * Add logic to update PMTU for IPIP packets in IPVS, again from Julian Anastasov. * A couple of sparse warning fixes for IPVS and Netfilter from Claudiu Ghioc and Patrick McHardy respectively. Patrick's IPv6 NAT changes will follow after this batch, I need to flush this batch first before refreshing my tree. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net')
-rw-r--r--net/bridge/netfilter/ebtable_filter.c4
-rw-r--r--net/bridge/netfilter/ebtable_nat.c4
-rw-r--r--net/ipv4/netfilter/iptable_filter.c10
-rw-r--r--net/ipv4/netfilter/iptable_mangle.c10
-rw-r--r--net/ipv4/netfilter/iptable_raw.c10
-rw-r--r--net/ipv4/netfilter/iptable_security.c5
-rw-r--r--net/ipv6/netfilter/ip6table_filter.c4
-rw-r--r--net/ipv6/netfilter/ip6table_mangle.c4
-rw-r--r--net/ipv6/netfilter/ip6table_raw.c4
-rw-r--r--net/ipv6/netfilter/ip6table_security.c5
-rw-r--r--net/netfilter/core.c10
-rw-r--r--net/netfilter/ipvs/Kconfig3
-rw-r--r--net/netfilter/ipvs/ip_vs_app.c58
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c76
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c16
-rw-r--r--net/netfilter/ipvs/ip_vs_ftp.c21
-rw-r--r--net/netfilter/ipvs/ip_vs_xmit.c83
-rw-r--r--net/netfilter/nf_conntrack_proto.c5
-rw-r--r--net/netfilter/nfnetlink_acct.c4
-rw-r--r--net/netfilter/nfnetlink_cthelper.c2
-rw-r--r--net/netfilter/xt_NFQUEUE.c8
-rw-r--r--net/netfilter/xt_osf.c2
22 files changed, 219 insertions, 129 deletions
diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c
index 42e6bd094574..3c2e9dced9e0 100644
--- a/net/bridge/netfilter/ebtable_filter.c
+++ b/net/bridge/netfilter/ebtable_filter.c
@@ -100,9 +100,7 @@ static struct nf_hook_ops ebt_ops_filter[] __read_mostly = {
static int __net_init frame_filter_net_init(struct net *net)
{
net->xt.frame_filter = ebt_register_table(net, &frame_filter);
- if (IS_ERR(net->xt.frame_filter))
- return PTR_ERR(net->xt.frame_filter);
- return 0;
+ return PTR_RET(net->xt.frame_filter);
}
static void __net_exit frame_filter_net_exit(struct net *net)
diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c
index 6dc2f878ae05..10871bc77908 100644
--- a/net/bridge/netfilter/ebtable_nat.c
+++ b/net/bridge/netfilter/ebtable_nat.c
@@ -100,9 +100,7 @@ static struct nf_hook_ops ebt_ops_nat[] __read_mostly = {
static int __net_init frame_nat_net_init(struct net *net)
{
net->xt.frame_nat = ebt_register_table(net, &frame_nat);
- if (IS_ERR(net->xt.frame_nat))
- return PTR_ERR(net->xt.frame_nat);
- return 0;
+ return PTR_RET(net->xt.frame_nat);
}
static void __net_exit frame_nat_net_exit(struct net *net)
diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c
index 851acec852d2..6b3da5cf54e9 100644
--- a/net/ipv4/netfilter/iptable_filter.c
+++ b/net/ipv4/netfilter/iptable_filter.c
@@ -69,9 +69,7 @@ static int __net_init iptable_filter_net_init(struct net *net)
net->ipv4.iptable_filter =
ipt_register_table(net, &packet_filter, repl);
kfree(repl);
- if (IS_ERR(net->ipv4.iptable_filter))
- return PTR_ERR(net->ipv4.iptable_filter);
- return 0;
+ return PTR_RET(net->ipv4.iptable_filter);
}
static void __net_exit iptable_filter_net_exit(struct net *net)
@@ -96,14 +94,10 @@ static int __init iptable_filter_init(void)
filter_ops = xt_hook_link(&packet_filter, iptable_filter_hook);
if (IS_ERR(filter_ops)) {
ret = PTR_ERR(filter_ops);
- goto cleanup_table;
+ unregister_pernet_subsys(&iptable_filter_net_ops);
}
return ret;
-
- cleanup_table:
- unregister_pernet_subsys(&iptable_filter_net_ops);
- return ret;
}
static void __exit iptable_filter_fini(void)
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index aef5d1fbe77d..85d88f206447 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -104,9 +104,7 @@ static int __net_init iptable_mangle_net_init(struct net *net)
net->ipv4.iptable_mangle =
ipt_register_table(net, &packet_mangler, repl);
kfree(repl);
- if (IS_ERR(net->ipv4.iptable_mangle))
- return PTR_ERR(net->ipv4.iptable_mangle);
- return 0;
+ return PTR_RET(net->ipv4.iptable_mangle);
}
static void __net_exit iptable_mangle_net_exit(struct net *net)
@@ -131,14 +129,10 @@ static int __init iptable_mangle_init(void)
mangle_ops = xt_hook_link(&packet_mangler, iptable_mangle_hook);
if (IS_ERR(mangle_ops)) {
ret = PTR_ERR(mangle_ops);
- goto cleanup_table;
+ unregister_pernet_subsys(&iptable_mangle_net_ops);
}
return ret;
-
- cleanup_table:
- unregister_pernet_subsys(&iptable_mangle_net_ops);
- return ret;
}
static void __exit iptable_mangle_fini(void)
diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c
index 07fb710cd722..03d9696d3c6e 100644
--- a/net/ipv4/netfilter/iptable_raw.c
+++ b/net/ipv4/netfilter/iptable_raw.c
@@ -48,9 +48,7 @@ static int __net_init iptable_raw_net_init(struct net *net)
net->ipv4.iptable_raw =
ipt_register_table(net, &packet_raw, repl);
kfree(repl);
- if (IS_ERR(net->ipv4.iptable_raw))
- return PTR_ERR(net->ipv4.iptable_raw);
- return 0;
+ return PTR_RET(net->ipv4.iptable_raw);
}
static void __net_exit iptable_raw_net_exit(struct net *net)
@@ -75,14 +73,10 @@ static int __init iptable_raw_init(void)
rawtable_ops = xt_hook_link(&packet_raw, iptable_raw_hook);
if (IS_ERR(rawtable_ops)) {
ret = PTR_ERR(rawtable_ops);
- goto cleanup_table;
+ unregister_pernet_subsys(&iptable_raw_net_ops);
}
return ret;
-
- cleanup_table:
- unregister_pernet_subsys(&iptable_raw_net_ops);
- return ret;
}
static void __exit iptable_raw_fini(void)
diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c
index be45bdc4c602..b283d8e2601a 100644
--- a/net/ipv4/netfilter/iptable_security.c
+++ b/net/ipv4/netfilter/iptable_security.c
@@ -66,10 +66,7 @@ static int __net_init iptable_security_net_init(struct net *net)
net->ipv4.iptable_security =
ipt_register_table(net, &security_table, repl);
kfree(repl);
- if (IS_ERR(net->ipv4.iptable_security))
- return PTR_ERR(net->ipv4.iptable_security);
-
- return 0;
+ return PTR_RET(net->ipv4.iptable_security);
}
static void __net_exit iptable_security_net_exit(struct net *net)
diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c
index 325e59a0224f..beb5777d2043 100644
--- a/net/ipv6/netfilter/ip6table_filter.c
+++ b/net/ipv6/netfilter/ip6table_filter.c
@@ -61,9 +61,7 @@ static int __net_init ip6table_filter_net_init(struct net *net)
net->ipv6.ip6table_filter =
ip6t_register_table(net, &packet_filter, repl);
kfree(repl);
- if (IS_ERR(net->ipv6.ip6table_filter))
- return PTR_ERR(net->ipv6.ip6table_filter);
- return 0;
+ return PTR_RET(net->ipv6.ip6table_filter);
}
static void __net_exit ip6table_filter_net_exit(struct net *net)
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index 4d782405f125..7431121b87de 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -97,9 +97,7 @@ static int __net_init ip6table_mangle_net_init(struct net *net)
net->ipv6.ip6table_mangle =
ip6t_register_table(net, &packet_mangler, repl);
kfree(repl);
- if (IS_ERR(net->ipv6.ip6table_mangle))
- return PTR_ERR(net->ipv6.ip6table_mangle);
- return 0;
+ return PTR_RET(net->ipv6.ip6table_mangle);
}
static void __net_exit ip6table_mangle_net_exit(struct net *net)
diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c
index 5b9926a011bd..60d1bddff7a0 100644
--- a/net/ipv6/netfilter/ip6table_raw.c
+++ b/net/ipv6/netfilter/ip6table_raw.c
@@ -40,9 +40,7 @@ static int __net_init ip6table_raw_net_init(struct net *net)
net->ipv6.ip6table_raw =
ip6t_register_table(net, &packet_raw, repl);
kfree(repl);
- if (IS_ERR(net->ipv6.ip6table_raw))
- return PTR_ERR(net->ipv6.ip6table_raw);
- return 0;
+ return PTR_RET(net->ipv6.ip6table_raw);
}
static void __net_exit ip6table_raw_net_exit(struct net *net)
diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c
index 91aa2b4d83c9..db155351339c 100644
--- a/net/ipv6/netfilter/ip6table_security.c
+++ b/net/ipv6/netfilter/ip6table_security.c
@@ -58,10 +58,7 @@ static int __net_init ip6table_security_net_init(struct net *net)
net->ipv6.ip6table_security =
ip6t_register_table(net, &security_table, repl);
kfree(repl);
- if (IS_ERR(net->ipv6.ip6table_security))
- return PTR_ERR(net->ipv6.ip6table_security);
-
- return 0;
+ return PTR_RET(net->ipv6.ip6table_security);
}
static void __net_exit ip6table_security_net_exit(struct net *net)
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 0bc6b60db4df..8f4b0b2b6f80 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -131,14 +131,13 @@ unsigned int nf_iterate(struct list_head *head,
int hook_thresh)
{
unsigned int verdict;
+ struct nf_hook_ops *elem = list_entry_rcu(*i, struct nf_hook_ops, list);
/*
* The caller must not block between calls to this
* function because of risk of continuing from deleted element.
*/
- list_for_each_continue_rcu(*i, head) {
- struct nf_hook_ops *elem = (struct nf_hook_ops *)*i;
-
+ list_for_each_entry_continue_rcu(elem, head, list) {
if (hook_thresh > elem->priority)
continue;
@@ -155,11 +154,14 @@ repeat:
continue;
}
#endif
- if (verdict != NF_REPEAT)
+ if (verdict != NF_REPEAT) {
+ *i = &elem->list;
return verdict;
+ }
goto repeat;
}
}
+ *i = &elem->list;
return NF_ACCEPT;
}
diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index f9871385a65e..8b2cffdfdd99 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -250,7 +250,8 @@ comment 'IPVS application helper'
config IP_VS_FTP
tristate "FTP protocol helper"
- depends on IP_VS_PROTO_TCP && NF_CONNTRACK && NF_NAT
+ depends on IP_VS_PROTO_TCP && NF_CONNTRACK && NF_NAT && \
+ NF_CONNTRACK_FTP
select IP_VS_NFCT
---help---
FTP is a protocol that transfers IP address and/or port number in
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 64f9e8f13207..9713e6e86d47 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -180,22 +180,38 @@ register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto,
}
-/*
- * ip_vs_app registration routine
- */
-int register_ip_vs_app(struct net *net, struct ip_vs_app *app)
+/* Register application for netns */
+struct ip_vs_app *register_ip_vs_app(struct net *net, struct ip_vs_app *app)
{
struct netns_ipvs *ipvs = net_ipvs(net);
- /* increase the module use count */
- ip_vs_use_count_inc();
+ struct ip_vs_app *a;
+ int err = 0;
+
+ if (!ipvs)
+ return ERR_PTR(-ENOENT);
mutex_lock(&__ip_vs_app_mutex);
- list_add(&app->a_list, &ipvs->app_list);
+ list_for_each_entry(a, &ipvs->app_list, a_list) {
+ if (!strcmp(app->name, a->name)) {
+ err = -EEXIST;
+ goto out_unlock;
+ }
+ }
+ a = kmemdup(app, sizeof(*app), GFP_KERNEL);
+ if (!a) {
+ err = -ENOMEM;
+ goto out_unlock;
+ }
+ INIT_LIST_HEAD(&a->incs_list);
+ list_add(&a->a_list, &ipvs->app_list);
+ /* increase the module use count */
+ ip_vs_use_count_inc();
+out_unlock:
mutex_unlock(&__ip_vs_app_mutex);
- return 0;
+ return err ? ERR_PTR(err) : a;
}
@@ -205,20 +221,29 @@ int register_ip_vs_app(struct net *net, struct ip_vs_app *app)
*/
void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app)
{
- struct ip_vs_app *inc, *nxt;
+ struct netns_ipvs *ipvs = net_ipvs(net);
+ struct ip_vs_app *a, *anxt, *inc, *nxt;
+
+ if (!ipvs)
+ return;
mutex_lock(&__ip_vs_app_mutex);
- list_for_each_entry_safe(inc, nxt, &app->incs_list, a_list) {
- ip_vs_app_inc_release(net, inc);
- }
+ list_for_each_entry_safe(a, anxt, &ipvs->app_list, a_list) {
+ if (app && strcmp(app->name, a->name))
+ continue;
+ list_for_each_entry_safe(inc, nxt, &a->incs_list, a_list) {
+ ip_vs_app_inc_release(net, inc);
+ }
- list_del(&app->a_list);
+ list_del(&a->a_list);
+ kfree(a);
- mutex_unlock(&__ip_vs_app_mutex);
+ /* decrease the module use count */
+ ip_vs_use_count_dec();
+ }
- /* decrease the module use count */
- ip_vs_use_count_dec();
+ mutex_unlock(&__ip_vs_app_mutex);
}
@@ -586,5 +611,6 @@ int __net_init ip_vs_app_net_init(struct net *net)
void __net_exit ip_vs_app_net_cleanup(struct net *net)
{
+ unregister_ip_vs_app(net, NULL /* all */);
proc_net_remove(net, "ip_vs_app");
}
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index b54eccef40b5..58918e20f9d5 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1303,7 +1303,8 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
struct ip_vs_conn *cp;
struct ip_vs_protocol *pp;
struct ip_vs_proto_data *pd;
- unsigned int offset, ihl, verdict;
+ unsigned int offset, offset2, ihl, verdict;
+ bool ipip;
*related = 1;
@@ -1345,6 +1346,21 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
net = skb_net(skb);
+ /* Special case for errors for IPIP packets */
+ ipip = false;
+ if (cih->protocol == IPPROTO_IPIP) {
+ if (unlikely(cih->frag_off & htons(IP_OFFSET)))
+ return NF_ACCEPT;
+ /* Error for our IPIP must arrive at LOCAL_IN */
+ if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL))
+ return NF_ACCEPT;
+ offset += cih->ihl * 4;
+ cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph);
+ if (cih == NULL)
+ return NF_ACCEPT; /* The packet looks wrong, ignore */
+ ipip = true;
+ }
+
pd = ip_vs_proto_data_get(net, cih->protocol);
if (!pd)
return NF_ACCEPT;
@@ -1358,11 +1374,14 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset,
"Checking incoming ICMP for");
+ offset2 = offset;
offset += cih->ihl * 4;
ip_vs_fill_iphdr(AF_INET, cih, &ciph);
- /* The embedded headers contain source and dest in reverse order */
- cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, 1);
+ /* The embedded headers contain source and dest in reverse order.
+ * For IPIP this is error for request, not for reply.
+ */
+ cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, ipip ? 0 : 1);
if (!cp)
return NF_ACCEPT;
@@ -1376,6 +1395,57 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum)
goto out;
}
+ if (ipip) {
+ __be32 info = ic->un.gateway;
+
+ /* Update the MTU */
+ if (ic->type == ICMP_DEST_UNREACH &&
+ ic->code == ICMP_FRAG_NEEDED) {
+ struct ip_vs_dest *dest = cp->dest;
+ u32 mtu = ntohs(ic->un.frag.mtu);
+
+ /* Strip outer IP and ICMP, go to IPIP header */
+ __skb_pull(skb, ihl + sizeof(_icmph));
+ offset2 -= ihl + sizeof(_icmph);
+ skb_reset_network_header(skb);
+ IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n",
+ &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu);
+ rcu_read_lock();
+ ipv4_update_pmtu(skb, dev_net(skb->dev),
+ mtu, 0, 0, 0, 0);
+ rcu_read_unlock();
+ /* Client uses PMTUD? */
+ if (!(cih->frag_off & htons(IP_DF)))
+ goto ignore_ipip;
+ /* Prefer the resulting PMTU */
+ if (dest) {
+ spin_lock(&dest->dst_lock);
+ if (dest->dst_cache)
+ mtu = dst_mtu(dest->dst_cache);
+ spin_unlock(&dest->dst_lock);
+ }
+ if (mtu > 68 + sizeof(struct iphdr))
+ mtu -= sizeof(struct iphdr);
+ info = htonl(mtu);
+ }
+ /* Strip outer IP, ICMP and IPIP, go to IP header of
+ * original request.
+ */
+ __skb_pull(skb, offset2);
+ skb_reset_network_header(skb);
+ IP_VS_DBG(12, "Sending ICMP for %pI4->%pI4: t=%u, c=%u, i=%u\n",
+ &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
+ ic->type, ic->code, ntohl(info));
+ icmp_send(skb, ic->type, ic->code, info);
+ /* ICMP can be shorter but anyways, account it */
+ ip_vs_out_stats(cp, skb);
+
+ignore_ipip:
+ consume_skb(skb);
+ verdict = NF_STOLEN;
+ goto out;
+ }
+
/* do the statistics and put it back */
ip_vs_in_stats(cp, skb);
if (IPPROTO_TCP == cih->protocol || IPPROTO_UDP == cih->protocol)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 72bf32a84874..3c601378d27e 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1801,6 +1801,12 @@ static struct ctl_table vs_vars[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "pmtu_disc",
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
#ifdef CONFIG_IP_VS_DEBUG
{
.procname = "debug_level",
@@ -3676,7 +3682,7 @@ static void ip_vs_genl_unregister(void)
* per netns intit/exit func.
*/
#ifdef CONFIG_SYSCTL
-int __net_init ip_vs_control_net_init_sysctl(struct net *net)
+static int __net_init ip_vs_control_net_init_sysctl(struct net *net)
{
int idx;
struct netns_ipvs *ipvs = net_ipvs(net);
@@ -3727,6 +3733,8 @@ int __net_init ip_vs_control_net_init_sysctl(struct net *net)
ipvs->sysctl_sync_retries = clamp_t(int, DEFAULT_SYNC_RETRIES, 0, 3);
tbl[idx++].data = &ipvs->sysctl_sync_retries;
tbl[idx++].data = &ipvs->sysctl_nat_icmp_send;
+ ipvs->sysctl_pmtu_disc = 1;
+ tbl[idx++].data = &ipvs->sysctl_pmtu_disc;
ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl);
@@ -3744,7 +3752,7 @@ int __net_init ip_vs_control_net_init_sysctl(struct net *net)
return 0;
}
-void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net)
+static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net)
{
struct netns_ipvs *ipvs = net_ipvs(net);
@@ -3755,8 +3763,8 @@ void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net)
#else
-int __net_init ip_vs_control_net_init_sysctl(struct net *net) { return 0; }
-void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) { }
+static int __net_init ip_vs_control_net_init_sysctl(struct net *net) { return 0; }
+static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) { }
#endif
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index b20b29c903ef..ad70b7e4ac4a 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -441,16 +441,10 @@ static int __net_init __ip_vs_ftp_init(struct net *net)
if (!ipvs)
return -ENOENT;
- app = kmemdup(&ip_vs_ftp, sizeof(struct ip_vs_app), GFP_KERNEL);
- if (!app)
- return -ENOMEM;
- INIT_LIST_HEAD(&app->a_list);
- INIT_LIST_HEAD(&app->incs_list);
- ipvs->ftp_app = app;
- ret = register_ip_vs_app(net, app);
- if (ret)
- goto err_exit;
+ app = register_ip_vs_app(net, &ip_vs_ftp);
+ if (IS_ERR(app))
+ return PTR_ERR(app);
for (i = 0; i < ports_count; i++) {
if (!ports[i])
@@ -464,9 +458,7 @@ static int __net_init __ip_vs_ftp_init(struct net *net)
return 0;
err_unreg:
- unregister_ip_vs_app(net, app);
-err_exit:
- kfree(ipvs->ftp_app);
+ unregister_ip_vs_app(net, &ip_vs_ftp);
return ret;
}
/*
@@ -474,10 +466,7 @@ err_exit:
*/
static void __ip_vs_ftp_exit(struct net *net)
{
- struct netns_ipvs *ipvs = net_ipvs(net);
-
- unregister_ip_vs_app(net, ipvs->ftp_app);
- kfree(ipvs->ftp_app);
+ unregister_ip_vs_app(net, &ip_vs_ftp);
}
static struct pernet_operations ip_vs_ftp_ops = {
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 65b616ae1716..543a554008af 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -49,6 +49,7 @@ enum {
IP_VS_RT_MODE_RDR = 4, /* Allow redirect from remote daddr to
* local
*/
+ IP_VS_RT_MODE_CONNECT = 8, /* Always bind route to saddr */
};
/*
@@ -84,6 +85,42 @@ __ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos)
return dst;
}
+/* Get route to daddr, update *saddr, optionally bind route to saddr */
+static struct rtable *do_output_route4(struct net *net, __be32 daddr,
+ u32 rtos, int rt_mode, __be32 *saddr)
+{
+ struct flowi4 fl4;
+ struct rtable *rt;
+ int loop = 0;
+
+ memset(&fl4, 0, sizeof(fl4));
+ fl4.daddr = daddr;
+ fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0;
+ fl4.flowi4_tos = rtos;
+
+retry:
+ rt = ip_route_output_key(net, &fl4);
+ if (IS_ERR(rt)) {
+ /* Invalid saddr ? */
+ if (PTR_ERR(rt) == -EINVAL && *saddr &&
+ rt_mode & IP_VS_RT_MODE_CONNECT && !loop) {
+ *saddr = 0;
+ flowi4_update_output(&fl4, 0, rtos, daddr, 0);
+ goto retry;
+ }
+ IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr);
+ return NULL;
+ } else if (!*saddr && rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) {
+ ip_rt_put(rt);
+ *saddr = fl4.saddr;
+ flowi4_update_output(&fl4, 0, rtos, daddr, fl4.saddr);
+ loop++;
+ goto retry;
+ }
+ *saddr = fl4.saddr;
+ return rt;
+}
+
/* Get route to destination or remote server */
static struct rtable *
__ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
@@ -98,20 +135,13 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
spin_lock(&dest->dst_lock);
if (!(rt = (struct rtable *)
__ip_vs_dst_check(dest, rtos))) {
- struct flowi4 fl4;
-
- memset(&fl4, 0, sizeof(fl4));
- fl4.daddr = dest->addr.ip;
- fl4.flowi4_tos = rtos;
- rt = ip_route_output_key(net, &fl4);
- if (IS_ERR(rt)) {
+ rt = do_output_route4(net, dest->addr.ip, rtos,
+ rt_mode, &dest->dst_saddr.ip);
+ if (!rt) {
spin_unlock(&dest->dst_lock);
- IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
- &dest->addr.ip);
return NULL;
}
__ip_vs_dst_set(dest, rtos, dst_clone(&rt->dst), 0);
- dest->dst_saddr.ip = fl4.saddr;
IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d, "
"rtos=%X\n",
&dest->addr.ip, &dest->dst_saddr.ip,
@@ -122,19 +152,17 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
*ret_saddr = dest->dst_saddr.ip;
spin_unlock(&dest->dst_lock);
} else {
- struct flowi4 fl4;
+ __be32 saddr = htonl(INADDR_ANY);
- memset(&fl4, 0, sizeof(fl4));
- fl4.daddr = daddr;
- fl4.flowi4_tos = rtos;
- rt = ip_route_output_key(net, &fl4);
- if (IS_ERR(rt)) {
- IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
- &daddr);
+ /* For such unconfigured boxes avoid many route lookups
+ * for performance reasons because we do not remember saddr
+ */
+ rt_mode &= ~IP_VS_RT_MODE_CONNECT;
+ rt = do_output_route4(net, daddr, rtos, rt_mode, &saddr);
+ if (!rt)
return NULL;
- }
if (ret_saddr)
- *ret_saddr = fl4.saddr;
+ *ret_saddr = saddr;
}
local = rt->rt_flags & RTCF_LOCAL;
@@ -331,6 +359,7 @@ ip_vs_dst_reset(struct ip_vs_dest *dest)
old_dst = dest->dst_cache;
dest->dst_cache = NULL;
dst_release(old_dst);
+ dest->dst_saddr.ip = 0;
}
#define IP_VS_XMIT_TUNNEL(skb, cp) \
@@ -766,12 +795,13 @@ int
ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
+ struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
struct rtable *rt; /* Route to the other host */
__be32 saddr; /* Source for tunnel */
struct net_device *tdev; /* Device to other host */
struct iphdr *old_iph = ip_hdr(skb);
u8 tos = old_iph->tos;
- __be16 df = old_iph->frag_off;
+ __be16 df;
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
int mtu;
@@ -781,7 +811,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
RT_TOS(tos), IP_VS_RT_MODE_LOCAL |
- IP_VS_RT_MODE_NON_LOCAL,
+ IP_VS_RT_MODE_NON_LOCAL |
+ IP_VS_RT_MODE_CONNECT,
&saddr)))
goto tx_error_icmp;
if (rt->rt_flags & RTCF_LOCAL) {
@@ -796,13 +827,13 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
goto tx_error_put;
}
- if (skb_dst(skb))
+ if (rt_is_output_route(skb_rtable(skb)))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
- df |= (old_iph->frag_off & htons(IP_DF));
+ /* Copy DF, reset fragment offset and MF */
+ df = sysctl_pmtu_disc(ipvs) ? old_iph->frag_off & htons(IP_DF) : 0;
- if ((old_iph->frag_off & htons(IP_DF) &&
- mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb))) {
+ if (df && mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb)) {
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
goto tx_error_put;
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 0dc63854390f..51e928db48c8 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -21,7 +21,6 @@
#include <linux/notifier.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
-#include <linux/rtnetlink.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_l3proto.h>
@@ -294,9 +293,7 @@ void nf_conntrack_l3proto_unregister(struct net *net,
nf_ct_l3proto_unregister_sysctl(net, proto);
/* Remove all contrack entries for this protocol */
- rtnl_lock();
nf_ct_iterate_cleanup(net, kill_l3proto, proto);
- rtnl_unlock();
}
EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_unregister);
@@ -502,9 +499,7 @@ void nf_conntrack_l4proto_unregister(struct net *net,
nf_ct_l4proto_unregister_sysctl(net, pn, l4proto);
/* Remove all contrack entries for this protocol */
- rtnl_lock();
nf_ct_iterate_cleanup(net, kill_l4proto, l4proto);
- rtnl_unlock();
}
EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_unregister);
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index b2e7310ca0b8..d7ec92879071 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -79,11 +79,11 @@ nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb,
if (tb[NFACCT_BYTES]) {
atomic64_set(&nfacct->bytes,
- be64_to_cpu(nla_get_u64(tb[NFACCT_BYTES])));
+ be64_to_cpu(nla_get_be64(tb[NFACCT_BYTES])));
}
if (tb[NFACCT_PKTS]) {
atomic64_set(&nfacct->pkts,
- be64_to_cpu(nla_get_u64(tb[NFACCT_PKTS])));
+ be64_to_cpu(nla_get_be64(tb[NFACCT_PKTS])));
}
atomic_set(&nfacct->refcnt, 1);
list_add_tail_rcu(&nfacct->head, &nfnl_acct_list);
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index d6836193d479..32a1ba3f3e27 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -74,7 +74,7 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple,
if (!tb[NFCTH_TUPLE_L3PROTONUM] || !tb[NFCTH_TUPLE_L4PROTONUM])
return -EINVAL;
- tuple->src.l3num = ntohs(nla_get_u16(tb[NFCTH_TUPLE_L3PROTONUM]));
+ tuple->src.l3num = ntohs(nla_get_be16(tb[NFCTH_TUPLE_L3PROTONUM]));
tuple->dst.protonum = nla_get_u8(tb[NFCTH_TUPLE_L4PROTONUM]);
return 0;
diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c
index 7babe7d68716..817f9e9f2b16 100644
--- a/net/netfilter/xt_NFQUEUE.c
+++ b/net/netfilter/xt_NFQUEUE.c
@@ -43,7 +43,7 @@ static u32 hash_v4(const struct sk_buff *skb)
const struct iphdr *iph = ip_hdr(skb);
/* packets in either direction go into same queue */
- if (iph->saddr < iph->daddr)
+ if ((__force u32)iph->saddr < (__force u32)iph->daddr)
return jhash_3words((__force u32)iph->saddr,
(__force u32)iph->daddr, iph->protocol, jhash_initval);
@@ -57,7 +57,8 @@ static u32 hash_v6(const struct sk_buff *skb)
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
u32 a, b, c;
- if (ip6h->saddr.s6_addr32[3] < ip6h->daddr.s6_addr32[3]) {
+ if ((__force u32)ip6h->saddr.s6_addr32[3] <
+ (__force u32)ip6h->daddr.s6_addr32[3]) {
a = (__force u32) ip6h->saddr.s6_addr32[3];
b = (__force u32) ip6h->daddr.s6_addr32[3];
} else {
@@ -65,7 +66,8 @@ static u32 hash_v6(const struct sk_buff *skb)
a = (__force u32) ip6h->daddr.s6_addr32[3];
}
- if (ip6h->saddr.s6_addr32[1] < ip6h->daddr.s6_addr32[1])
+ if ((__force u32)ip6h->saddr.s6_addr32[1] <
+ (__force u32)ip6h->daddr.s6_addr32[1])
c = (__force u32) ip6h->saddr.s6_addr32[1];
else
c = (__force u32) ip6h->daddr.s6_addr32[1];
diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c
index 846f895cb656..a5e673d32bda 100644
--- a/net/netfilter/xt_osf.c
+++ b/net/netfilter/xt_osf.c
@@ -269,7 +269,7 @@ xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p)
mss <<= 8;
mss |= optp[2];
- mss = ntohs(mss);
+ mss = ntohs((__force __be16)mss);
break;
case OSFOPT_TS:
loop_cont = 1;