aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/ah4.c18
-rw-r--r--net/ipv4/esp4.c24
-rw-r--r--net/ipv4/ip_fragment.c2
-rw-r--r--net/ipv4/ipcomp.c3
-rw-r--r--net/ipv4/ipconfig.c1
-rw-r--r--net/ipv4/netfilter/Kconfig20
-rw-r--r--net/ipv4/netfilter/Makefile1
-rw-r--r--net/ipv4/netfilter/ip_conntrack_amanda.c1
-rw-r--r--net/ipv4/netfilter/ip_conntrack_core.c38
-rw-r--r--net/ipv4/netfilter/ip_conntrack_ftp.c1
-rw-r--r--net/ipv4/netfilter/ip_conntrack_irc.c1
-rw-r--r--net/ipv4/netfilter/ip_conntrack_netbios_ns.c131
-rw-r--r--net/ipv4/netfilter/ip_conntrack_netlink.c13
-rw-r--r--net/ipv4/netfilter/ip_conntrack_proto_tcp.c1
-rw-r--r--net/ipv4/netfilter/ip_conntrack_standalone.c2
-rw-r--r--net/ipv4/netfilter/ip_conntrack_tftp.c1
-rw-r--r--net/ipv4/netfilter/ip_nat_rule.c21
-rw-r--r--net/ipv4/netfilter/ip_nat_standalone.c8
-rw-r--r--net/ipv4/netfilter/ipt_CLUSTERIP.c2
-rw-r--r--net/ipv4/tcp.c17
-rw-r--r--net/ipv4/tcp_input.c36
-rw-r--r--net/ipv4/tcp_output.c55
22 files changed, 284 insertions, 113 deletions
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 514c85b2631..035ad2c9e1b 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -263,10 +263,8 @@ static int ah_init_state(struct xfrm_state *x)
error:
if (ahp) {
- if (ahp->work_icv)
- kfree(ahp->work_icv);
- if (ahp->tfm)
- crypto_free_tfm(ahp->tfm);
+ kfree(ahp->work_icv);
+ crypto_free_tfm(ahp->tfm);
kfree(ahp);
}
return -EINVAL;
@@ -279,14 +277,10 @@ static void ah_destroy(struct xfrm_state *x)
if (!ahp)
return;
- if (ahp->work_icv) {
- kfree(ahp->work_icv);
- ahp->work_icv = NULL;
- }
- if (ahp->tfm) {
- crypto_free_tfm(ahp->tfm);
- ahp->tfm = NULL;
- }
+ kfree(ahp->work_icv);
+ ahp->work_icv = NULL;
+ crypto_free_tfm(ahp->tfm);
+ ahp->tfm = NULL;
kfree(ahp);
}
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index b31ffc5053d..1b5a09d1b90 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -343,22 +343,14 @@ static void esp_destroy(struct xfrm_state *x)
if (!esp)
return;
- if (esp->conf.tfm) {
- crypto_free_tfm(esp->conf.tfm);
- esp->conf.tfm = NULL;
- }
- if (esp->conf.ivec) {
- kfree(esp->conf.ivec);
- esp->conf.ivec = NULL;
- }
- if (esp->auth.tfm) {
- crypto_free_tfm(esp->auth.tfm);
- esp->auth.tfm = NULL;
- }
- if (esp->auth.work_icv) {
- kfree(esp->auth.work_icv);
- esp->auth.work_icv = NULL;
- }
+ crypto_free_tfm(esp->conf.tfm);
+ esp->conf.tfm = NULL;
+ kfree(esp->conf.ivec);
+ esp->conf.ivec = NULL;
+ crypto_free_tfm(esp->auth.tfm);
+ esp->auth.tfm = NULL;
+ kfree(esp->auth.work_icv);
+ esp->auth.work_icv = NULL;
kfree(esp);
}
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 9e6e683cc34..e7d26d9943c 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -457,7 +457,7 @@ static void ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
if (pskb_pull(skb, ihl) == NULL)
goto err;
- if (pskb_trim(skb, end-offset))
+ if (pskb_trim_rcsum(skb, end-offset))
goto err;
/* Find out which fragments are in front and at the back of us
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index dcb7ee6c485..fc718df17b4 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -345,8 +345,7 @@ static void ipcomp_free_tfms(struct crypto_tfm **tfms)
for_each_cpu(cpu) {
struct crypto_tfm *tfm = *per_cpu_ptr(tfms, cpu);
- if (tfm)
- crypto_free_tfm(tfm);
+ crypto_free_tfm(tfm);
}
free_percpu(tfms);
}
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 63e106605f2..953129d392d 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -54,6 +54,7 @@
#include <linux/major.h>
#include <linux/root_dev.h>
#include <linux/delay.h>
+#include <linux/nfs_fs.h>
#include <net/arp.h>
#include <net/ip.h>
#include <net/ipconfig.h>
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index e046f552181..30aa8e2ee21 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -34,6 +34,7 @@ config IP_NF_CT_ACCT
config IP_NF_CONNTRACK_MARK
bool 'Connection mark tracking support'
+ depends on IP_NF_CONNTRACK
help
This option enables support for connection marks, used by the
`CONNMARK' target and `connmark' match. Similar to the mark value
@@ -85,6 +86,25 @@ config IP_NF_IRC
To compile it as a module, choose M here. If unsure, say Y.
+config IP_NF_NETBIOS_NS
+ tristate "NetBIOS name service protocol support (EXPERIMENTAL)"
+ depends on IP_NF_CONNTRACK && EXPERIMENTAL
+ help
+ NetBIOS name service requests are sent as broadcast messages from an
+ unprivileged port and responded to with unicast messages to the
+ same port. This make them hard to firewall properly because connection
+ tracking doesn't deal with broadcasts. This helper tracks locally
+ originating NetBIOS name service requests and the corresponding
+ responses. It relies on correct IP address configuration, specifically
+ netmask and broadcast address. When properly configured, the output
+ of "ip address show" should look similar to this:
+
+ $ ip -4 address show eth0
+ 4: eth0: <BROADCAST,MULTICAST,UP> mtu 1500 qdisc pfifo_fast qlen 1000
+ inet 172.16.2.252/24 brd 172.16.2.255 scope global eth0
+
+ To compile it as a module, choose M here. If unsure, say N.
+
config IP_NF_TFTP
tristate "TFTP protocol support"
depends on IP_NF_CONNTRACK
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index a7bd38f5052..1ba0db74681 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -21,6 +21,7 @@ obj-$(CONFIG_IP_NF_AMANDA) += ip_conntrack_amanda.o
obj-$(CONFIG_IP_NF_TFTP) += ip_conntrack_tftp.o
obj-$(CONFIG_IP_NF_FTP) += ip_conntrack_ftp.o
obj-$(CONFIG_IP_NF_IRC) += ip_conntrack_irc.o
+obj-$(CONFIG_IP_NF_NETBIOS_NS) += ip_conntrack_netbios_ns.o
# NAT helpers
obj-$(CONFIG_IP_NF_NAT_AMANDA) += ip_nat_amanda.o
diff --git a/net/ipv4/netfilter/ip_conntrack_amanda.c b/net/ipv4/netfilter/ip_conntrack_amanda.c
index be4c9eb3243..dc20881004b 100644
--- a/net/ipv4/netfilter/ip_conntrack_amanda.c
+++ b/net/ipv4/netfilter/ip_conntrack_amanda.c
@@ -108,6 +108,7 @@ static int help(struct sk_buff **pskb,
}
exp->expectfn = NULL;
+ exp->flags = 0;
exp->tuple.src.ip = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.ip;
exp->tuple.src.u.tcp.port = 0;
diff --git a/net/ipv4/netfilter/ip_conntrack_core.c b/net/ipv4/netfilter/ip_conntrack_core.c
index a0648600190..19cba16e6e1 100644
--- a/net/ipv4/netfilter/ip_conntrack_core.c
+++ b/net/ipv4/netfilter/ip_conntrack_core.c
@@ -197,7 +197,7 @@ ip_ct_invert_tuple(struct ip_conntrack_tuple *inverse,
/* ip_conntrack_expect helper functions */
-static void unlink_expect(struct ip_conntrack_expect *exp)
+void ip_ct_unlink_expect(struct ip_conntrack_expect *exp)
{
ASSERT_WRITE_LOCK(&ip_conntrack_lock);
IP_NF_ASSERT(!timer_pending(&exp->timeout));
@@ -207,18 +207,12 @@ static void unlink_expect(struct ip_conntrack_expect *exp)
ip_conntrack_expect_put(exp);
}
-void __ip_ct_expect_unlink_destroy(struct ip_conntrack_expect *exp)
-{
- unlink_expect(exp);
- ip_conntrack_expect_put(exp);
-}
-
static void expectation_timed_out(unsigned long ul_expect)
{
struct ip_conntrack_expect *exp = (void *)ul_expect;
write_lock_bh(&ip_conntrack_lock);
- unlink_expect(exp);
+ ip_ct_unlink_expect(exp);
write_unlock_bh(&ip_conntrack_lock);
ip_conntrack_expect_put(exp);
}
@@ -264,10 +258,14 @@ find_expectation(const struct ip_conntrack_tuple *tuple)
master ct never got confirmed, we'd hold a reference to it
and weird things would happen to future packets). */
if (ip_ct_tuple_mask_cmp(tuple, &i->tuple, &i->mask)
- && is_confirmed(i->master)
- && del_timer(&i->timeout)) {
- unlink_expect(i);
- return i;
+ && is_confirmed(i->master)) {
+ if (i->flags & IP_CT_EXPECT_PERMANENT) {
+ atomic_inc(&i->use);
+ return i;
+ } else if (del_timer(&i->timeout)) {
+ ip_ct_unlink_expect(i);
+ return i;
+ }
}
}
return NULL;
@@ -284,7 +282,7 @@ void ip_ct_remove_expectations(struct ip_conntrack *ct)
list_for_each_entry_safe(i, tmp, &ip_conntrack_expect_list, list) {
if (i->master == ct && del_timer(&i->timeout)) {
- unlink_expect(i);
+ ip_ct_unlink_expect(i);
ip_conntrack_expect_put(i);
}
}
@@ -925,7 +923,7 @@ void ip_conntrack_unexpect_related(struct ip_conntrack_expect *exp)
/* choose the the oldest expectation to evict */
list_for_each_entry_reverse(i, &ip_conntrack_expect_list, list) {
if (expect_matches(i, exp) && del_timer(&i->timeout)) {
- unlink_expect(i);
+ ip_ct_unlink_expect(i);
write_unlock_bh(&ip_conntrack_lock);
ip_conntrack_expect_put(i);
return;
@@ -934,6 +932,9 @@ void ip_conntrack_unexpect_related(struct ip_conntrack_expect *exp)
write_unlock_bh(&ip_conntrack_lock);
}
+/* We don't increase the master conntrack refcount for non-fulfilled
+ * conntracks. During the conntrack destruction, the expectations are
+ * always killed before the conntrack itself */
struct ip_conntrack_expect *ip_conntrack_expect_alloc(struct ip_conntrack *me)
{
struct ip_conntrack_expect *new;
@@ -944,17 +945,14 @@ struct ip_conntrack_expect *ip_conntrack_expect_alloc(struct ip_conntrack *me)
return NULL;
}
new->master = me;
- atomic_inc(&new->master->ct_general.use);
atomic_set(&new->use, 1);
return new;
}
void ip_conntrack_expect_put(struct ip_conntrack_expect *exp)
{
- if (atomic_dec_and_test(&exp->use)) {
- ip_conntrack_put(exp->master);
+ if (atomic_dec_and_test(&exp->use))
kmem_cache_free(ip_conntrack_expect_cachep, exp);
- }
}
static void ip_conntrack_expect_insert(struct ip_conntrack_expect *exp)
@@ -982,7 +980,7 @@ static void evict_oldest_expect(struct ip_conntrack *master)
list_for_each_entry_reverse(i, &ip_conntrack_expect_list, list) {
if (i->master == master) {
if (del_timer(&i->timeout)) {
- unlink_expect(i);
+ ip_ct_unlink_expect(i);
ip_conntrack_expect_put(i);
}
break;
@@ -1099,7 +1097,7 @@ void ip_conntrack_helper_unregister(struct ip_conntrack_helper *me)
/* Get rid of expectations */
list_for_each_entry_safe(exp, tmp, &ip_conntrack_expect_list, list) {
if (exp->master->helper == me && del_timer(&exp->timeout)) {
- unlink_expect(exp);
+ ip_ct_unlink_expect(exp);
ip_conntrack_expect_put(exp);
}
}
diff --git a/net/ipv4/netfilter/ip_conntrack_ftp.c b/net/ipv4/netfilter/ip_conntrack_ftp.c
index 3a2627db172..1b79ec36085 100644
--- a/net/ipv4/netfilter/ip_conntrack_ftp.c
+++ b/net/ipv4/netfilter/ip_conntrack_ftp.c
@@ -421,6 +421,7 @@ static int help(struct sk_buff **pskb,
{ 0xFFFFFFFF, { .tcp = { 0xFFFF } }, 0xFF }});
exp->expectfn = NULL;
+ exp->flags = 0;
/* Now, NAT might want to mangle the packet, and register the
* (possibly changed) expectation itself. */
diff --git a/net/ipv4/netfilter/ip_conntrack_irc.c b/net/ipv4/netfilter/ip_conntrack_irc.c
index 25438eec21a..d7a8a98c05e 100644
--- a/net/ipv4/netfilter/ip_conntrack_irc.c
+++ b/net/ipv4/netfilter/ip_conntrack_irc.c
@@ -221,6 +221,7 @@ static int help(struct sk_buff **pskb,
{ { 0, { 0 } },
{ 0xFFFFFFFF, { .tcp = { 0xFFFF } }, 0xFF }});
exp->expectfn = NULL;
+ exp->flags = 0;
if (ip_nat_irc_hook)
ret = ip_nat_irc_hook(pskb, ctinfo,
addr_beg_p - ib_ptr,
diff --git a/net/ipv4/netfilter/ip_conntrack_netbios_ns.c b/net/ipv4/netfilter/ip_conntrack_netbios_ns.c
new file mode 100644
index 00000000000..2b5cf9c5130
--- /dev/null
+++ b/net/ipv4/netfilter/ip_conntrack_netbios_ns.c
@@ -0,0 +1,131 @@
+/*
+ * NetBIOS name service broadcast connection tracking helper
+ *
+ * (c) 2005 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+/*
+ * This helper tracks locally originating NetBIOS name service
+ * requests by issuing permanent expectations (valid until
+ * timing out) matching all reply connections from the
+ * destination network. The only NetBIOS specific thing is
+ * actually the port number.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <net/route.h>
+
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv4/ip_conntrack.h>
+#include <linux/netfilter_ipv4/ip_conntrack_helper.h>
+
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_DESCRIPTION("NetBIOS name service broadcast connection tracking helper");
+MODULE_LICENSE("GPL");
+
+static unsigned int timeout = 3;
+module_param(timeout, int, 0600);
+MODULE_PARM_DESC(timeout, "timeout for master connection/replies in seconds");
+
+static int help(struct sk_buff **pskb,
+ struct ip_conntrack *ct, enum ip_conntrack_info ctinfo)
+{
+ struct ip_conntrack_expect *exp;
+ struct iphdr *iph = (*pskb)->nh.iph;
+ struct udphdr _uh, *uh;
+ struct rtable *rt = (struct rtable *)(*pskb)->dst;
+ struct in_device *in_dev;
+ u_int32_t mask = 0;
+
+ /* we're only interested in locally generated packets */
+ if ((*pskb)->sk == NULL)
+ goto out;
+ if (rt == NULL || !(rt->rt_flags & RTCF_BROADCAST))
+ goto out;
+ if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
+ goto out;
+
+ rcu_read_lock();
+ in_dev = __in_dev_get(rt->u.dst.dev);
+ if (in_dev != NULL) {
+ for_primary_ifa(in_dev) {
+ if (ifa->ifa_broadcast == iph->daddr) {
+ mask = ifa->ifa_mask;
+ break;
+ }
+ } endfor_ifa(in_dev);
+ }
+ rcu_read_unlock();
+
+ if (mask == 0)
+ goto out;
+
+ uh = skb_header_pointer(*pskb, iph->ihl * 4, sizeof(_uh), &_uh);
+ BUG_ON(uh == NULL);
+
+ exp = ip_conntrack_expect_alloc(ct);
+ if (exp == NULL)
+ goto out;
+ memset(&exp->tuple, 0, sizeof(exp->tuple));
+ exp->tuple.src.ip = iph->daddr & mask;
+ exp->tuple.dst.ip = iph->saddr;
+ exp->tuple.dst.u.udp.port = uh->source;
+ exp->tuple.dst.protonum = IPPROTO_UDP;
+
+ memset(&exp->mask, 0, sizeof(exp->mask));
+ exp->mask.src.ip = mask;
+ exp->mask.dst.ip = 0xFFFFFFFF;
+ exp->mask.dst.u.udp.port = 0xFFFF;
+ exp->mask.dst.protonum = 0xFF;
+
+ exp->expectfn = NULL;
+ exp->flags = IP_CT_EXPECT_PERMANENT;
+
+ ip_conntrack_expect_related(exp);
+ ip_conntrack_expect_put(exp);
+
+ ip_ct_refresh_acct(ct, ctinfo, NULL, timeout * HZ);
+out:
+ return NF_ACCEPT;
+}
+
+static struct ip_conntrack_helper helper = {
+ .name = "netbios-ns",
+ .tuple = {
+ .src.u.udp.port = __constant_htons(137),
+ .dst.protonum = IPPROTO_UDP,
+ },
+ .mask = {
+ .src.u.udp.port = 0xFFFF,
+ .dst.protonum = 0xFF,
+ },
+ .max_expected = 1,
+ .me = THIS_MODULE,
+ .help = help,
+};
+
+static int __init init(void)
+{
+ helper.timeout = timeout;
+ return ip_conntrack_helper_register(&helper);
+}
+
+static void __exit fini(void)
+{
+ ip_conntrack_helper_unregister(&helper);
+}
+
+module_init(init);
+module_exit(fini);
diff --git a/net/ipv4/netfilter/ip_conntrack_netlink.c b/net/ipv4/netfilter/ip_conntrack_netlink.c
index a4e9278db4e..15aef356474 100644
--- a/net/ipv4/netfilter/ip_conntrack_netlink.c
+++ b/net/ipv4/netfilter/ip_conntrack_netlink.c
@@ -1349,8 +1349,10 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb,
list_for_each_entry_safe(exp, tmp, &ip_conntrack_expect_list,
list) {
if (exp->master->helper == h
- && del_timer(&exp->timeout))
- __ip_ct_expect_unlink_destroy(exp);
+ && del_timer(&exp->timeout)) {
+ ip_ct_unlink_expect(exp);
+ ip_conntrack_expect_put(exp);
+ }
}
write_unlock(&ip_conntrack_lock);
} else {
@@ -1358,8 +1360,10 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb,
write_lock_bh(&ip_conntrack_lock);
list_for_each_entry_safe(exp, tmp, &ip_conntrack_expect_list,
list) {
- if (del_timer(&exp->timeout))
- __ip_ct_expect_unlink_destroy(exp);
+ if (del_timer(&exp->timeout)) {
+ ip_ct_unlink_expect(exp);
+ ip_conntrack_expect_put(exp);
+ }
}
write_unlock_bh(&ip_conntrack_lock);
}
@@ -1413,6 +1417,7 @@ ctnetlink_create_expect(struct nfattr *cda[])
}
exp->expectfn = NULL;
+ exp->flags = 0;
exp->master = ct;
memcpy(&exp->tuple, &tuple, sizeof(struct ip_conntrack_tuple));
memcpy(&exp->mask, &mask, sizeof(struct ip_conntrack_tuple));
diff --git a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c
index f23ef1f88c4..1985abc59d2 100644
--- a/net/ipv4/netfilter/ip_conntrack_proto_tcp.c
+++ b/net/ipv4/netfilter/ip_conntrack_proto_tcp.c
@@ -349,6 +349,7 @@ static int tcp_to_nfattr(struct sk_buff *skb, struct nfattr *nfa,
return 0;
nfattr_failure:
+ read_unlock_bh(&tcp_lock);
return -1;
}
#endif
diff --git a/net/ipv4/netfilter/ip_conntrack_standalone.c b/net/ipv4/netfilter/ip_conntrack_standalone.c
index ee5895afd0c..ae3e3e655db 100644
--- a/net/ipv4/netfilter/ip_conntrack_standalone.c
+++ b/net/ipv4/netfilter/ip_conntrack_standalone.c
@@ -998,7 +998,7 @@ EXPORT_SYMBOL(ip_conntrack_expect_related);
EXPORT_SYMBOL(ip_conntrack_unexpect_related);
EXPORT_SYMBOL_GPL(ip_conntrack_expect_list);
EXPORT_SYMBOL_GPL(__ip_conntrack_expect_find);
-EXPORT_SYMBOL_GPL(__ip_ct_expect_unlink_destroy);
+EXPORT_SYMBOL_GPL(ip_ct_unlink_expect);
EXPORT_SYMBOL(ip_conntrack_tuple_taken);
EXPORT_SYMBOL(ip_ct_gather_frags);
diff --git a/net/ipv4/netfilter/ip_conntrack_tftp.c b/net/ipv4/netfilter/ip_conntrack_tftp.c
index f8ff170f390..d2b59053345 100644
--- a/net/ipv4/netfilter/ip_conntrack_tftp.c
+++ b/net/ipv4/netfilter/ip_conntrack_tftp.c
@@ -75,6 +75,7 @@ static int tftp_help(struct sk_buff **pskb,
exp->mask.dst.u.udp.port = 0xffff;
exp->mask.dst.protonum = 0xff;
exp->expectfn = NULL;
+ exp->flags = 0;
DEBUGP("expect: ");
DUMP_TUPLE(&exp->tuple);
diff --git a/net/ipv4/netfilter/ip_nat_rule.c b/net/ipv4/netfilter/ip_nat_rule.c
index 60d70fa41a1..cb66b8bddeb 100644
--- a/net/ipv4/netfilter/ip_nat_rule.c
+++ b/net/ipv4/netfilter/ip_nat_rule.c
@@ -255,6 +255,27 @@ alloc_null_binding(struct ip_conntrack *conntrack,
return ip_nat_setup_info(conntrack, &range, hooknum);
}
+unsigned int
+alloc_null_binding_confirmed(struct ip_conntrack *conntrack,
+ struct ip_nat_info *info,
+ unsigned int hooknum)
+{
+ u_int32_t ip
+ = (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC
+ ? conntrack->tuplehash[IP_CT_DIR_REPLY].tuple.dst.ip
+ : conntrack->tuplehash[IP_CT_DIR_REPLY].tuple.src.ip);
+ u_int16_t all
+ = (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC
+ ? conntrack->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.all
+ : conntrack->tuplehash[IP_CT_DIR_REPLY].tuple.src.u.all);
+ struct ip_nat_range range
+ = { IP_NAT_RANGE_MAP_IPS, ip, ip, { all }, { all } };
+
+ DEBUGP("Allocating NULL binding for confirmed %p (%u.%u.%u.%u)\n",
+ conntrack, NIPQUAD(ip));
+ return ip_nat_setup_info(conntrack, &range, hooknum);
+}
+
int ip_nat_rule_find(struct sk_buff **pskb,
unsigned int hooknum,
const struct net_device *in,
diff --git a/net/ipv4/netfilter/ip_nat_standalone.c b/net/ipv4/netfilter/ip_nat_standalone.c
index 89db052add8..0ff368b131f 100644
--- a/net/ipv4/netfilter/ip_nat_standalone.c
+++ b/net/ipv4/netfilter/ip_nat_standalone.c
@@ -123,8 +123,12 @@ ip_nat_fn(unsigned int hooknum,
if (!ip_nat_initialized(ct, maniptype)) {
unsigned int ret;
- /* LOCAL_IN hook doesn't have a chain! */
- if (hooknum == NF_IP_LOCAL_IN)
+ if (unlikely(is_confirmed(ct)))
+ /* NAT module was loaded late */
+ ret = alloc_null_binding_confirmed(ct, info,
+ hooknum);
+ else if (hooknum == NF_IP_LOCAL_IN)
+ /* LOCAL_IN hook doesn't have a chain! */
ret = alloc_null_binding(ct, info, hooknum);
else
ret = ip_nat_rule_find(pskb, hooknum,
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 2d05cafec22..7d38913754b 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -144,7 +144,7 @@ clusterip_config_init(struct ipt_clusterip_tgt_info *i, u_int32_t ip,
memcpy(&c->clustermac, &i->clustermac, ETH_ALEN);
c->num_total_nodes = i->num_total_nodes;
c->num_local_nodes = i->num_local_nodes;
- memcpy(&c->local_nodes, &i->local_nodes, sizeof(&c->local_nodes));
+ memcpy(&c->local_nodes, &i->local_nodes, sizeof(c->local_nodes));
c->hash_mode = i->hash_mode;
c->hash_initval = i->hash_initval;
atomic_set(&c->refcount, 1);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 02fdda68718..f3f0013a958 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -552,8 +552,7 @@ new_segment:
tcp_mark_push(tp, skb);
goto new_segment;
}
- if (sk->sk_forward_alloc < copy &&
- !sk_stream_mem_schedule(sk, copy, 0))
+ if (!sk_stream_wmem_schedule(sk, copy))
goto wait_for_memory;
if (can_coalesce) {
@@ -770,19 +769,23 @@ new_segment:
if (off == PAGE_SIZE) {
put_page(page);
TCP_PAGE(sk) = page = NULL;
+ off = 0;
}
- }
+ } else
+ off = 0;
+
+ if (copy > PAGE_SIZE - off)
+ copy = PAGE_SIZE - off;
+
+ if (!sk_stream_wmem_schedule(sk, copy))
+ goto wait_for_memory;
if (!page) {
/* Allocate new cache page. */
if (!(page = sk_stream_alloc_page(sk)))
goto wait_for_memory;
- off = 0;
}
- if (copy > PAGE_SIZE - off)
- copy = PAGE_SIZE - off;
-
/* Time to copy data. We are close to
* the end! */
err = skb_copy_to_page(sk, from, skb, page,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 1afb080bdf0..29222b96495 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -923,14 +923,6 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_
int flag = 0;
int i;
- /* So, SACKs for already sent large segments will be lost.
- * Not good, but alternative is to resegment the queue. */
- if (sk->sk_route_caps & NETIF_F_TSO) {
- sk->sk_route_caps &= ~NETIF_F_TSO;
- sock_set_flag(sk, SOCK_NO_LARGESEND);
- tp->mss_cache = tp->mss_cache;
- }
-
if (!tp->sacked_out)
tp->fackets_out = 0;
prior_fackets = tp->fackets_out;
@@ -978,20 +970,40 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_
flag |= FLAG_DATA_LOST;
sk_stream_for_retrans_queue(skb, sk) {
- u8 sacked = TCP_SKB_CB(skb)->sacked;
- int in_sack;
+ int in_sack, pcount;
+ u8 sacked;
/* The retransmission queue is always in order, so
* we can short-circuit the walk early.
*/
- if(!before(TCP_SKB_CB(skb)->seq, end_seq))
+ if (!before(TCP_SKB_CB(skb)->seq, end_seq))
break;
- fack_count += tcp_skb_pcount(skb);
+ pcount = tcp_skb_pcount(skb);
+
+ if (pcount > 1 &&
+ (after(start_seq, TCP_SKB_CB(skb)->seq) ||
+ before(end_seq, TCP_SKB_CB(skb)->end_seq))) {
+ unsigned int pkt_len;
+
+ if (after(start_seq, TCP_SKB_CB(skb)->seq))
+ pkt_len = (start_seq -
+ TCP_SKB_CB(skb)->seq);
+ else
+ pkt_len = (end_seq -
+ TCP_SKB_CB(skb)->seq);
+ if (tcp_fragment(sk, skb, pkt_len, skb_shinfo(skb)->tso_size))
+ break;
+ pcount = tcp_skb_pcount(skb);
+ }
+
+ fack_count += pcount;
in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
!before(end_seq, TCP_SKB_CB(skb)->end_seq);
+ sacked = TCP_SKB_CB(skb)->sacked;
+
/* Account D-SACK for retransmitted packet. */
if ((dup_sack && in_sack) &&
(sacked & TCPCB_RETRANS) &&
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 75b68116682..6094db5e11b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -428,11 +428,11 @@ static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned
* packet to the list. This won't be called frequently, I hope.
* Remember, these are still headerless SKBs at this point.
*/
-static int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss_now)
+int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss_now)
{
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *buff;
- int nsize;
+ int nsize, old_factor;
u16 flags;
nsize = skb_headlen(skb) - len;
@@ -490,18 +490,29 @@ static int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned
tp->left_out -= tcp_skb_pcount(skb);
}
+ old_factor = tcp_skb_pcount(skb);
+
/* Fix up tso_factor for both original and new SKB. */
tcp_set_skb_tso_segs(sk, skb, mss_now);
tcp_set_skb_tso_segs(sk, buff, mss_now);
- if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) {
- tp->lost_out += tcp_skb_pcount(skb);
- tp->left_out += tcp_skb_pcount(skb);
- }
+ /* If this packet has been sent out already, we must
+ * adjust the various packet counters.
+ */
+ if (after(tp->snd_nxt, TCP_SKB_CB(buff)->end_seq)) {
+ int diff = old_factor - tcp_skb_pcount(skb) -
+ tcp_skb_pcount(buff);
- if (TCP_SKB_CB(buff)->sacked&TCPCB_LOST) {
- tp->lost_out += tcp_skb_pcount(buff);
- tp->left_out += tcp_skb_pcount(buff);
+ tp->packets_out -= diff;
+ if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) {
+ tp->lost_out -= diff;
+ tp->left_out -= diff;
+ }
+ if (diff > 0) {
+ tp->fackets_out -= diff;
+ if ((int)tp->fackets_out < 0)
+ tp->fackets_out = 0;
+ }
}
/* Link BUFF into the send queue. */
@@ -1350,12 +1361,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) {
if (before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))
BUG();
-
- if (sk->sk_route_caps & NETIF_F_TSO) {
- sk->sk_route_caps &= ~NETIF_F_TSO;
- sock_set_flag(sk, SOCK_NO_LARGESEND);
- }
-
if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq))
return -ENOMEM;
}
@@ -1370,22 +1375,8 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
return -EAGAIN;
if (skb->len > cur_mss) {
- int old_factor = tcp_skb_pcount(skb);
- int diff;
-
if (tcp_fragment(sk, skb, cur_mss, cur_mss))
return -ENOMEM; /* We'll try again later. */
-
- /* New SKB created, account for it. */
- diff = old_factor - tcp_skb_pcount(skb) -
- tcp_skb_pcount(skb->next);
- tp->packets_out -= diff;
-
- if (diff > 0) {
- tp->fackets_out -= diff;
- if ((int)tp->fackets_out < 0)
- tp->fackets_out = 0;
- }
}
/* Collapse two adjacent packets if worthwhile and we can. */
@@ -1993,12 +1984,6 @@ int tcp_write_wakeup(struct sock *sk)
TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH;
if (tcp_fragment(sk, skb, seg_size, mss))
return -1;
- /* SWS override triggered forced fragmentation.
- * Disable TSO, the connection is too sick. */
- if (sk->sk_route_caps & NETIF_F_TSO) {
- sock_set_flag(sk, SOCK_NO_LARGESEND);
- sk->sk_route_caps &= ~NETIF_F_TSO;
- }
} else if (!tcp_skb_pcount(skb))
tcp_set_skb_tso_segs(sk, skb, mss);
generated by cgit v1.2.3 (git 2.25.1) at 2024-07-17 21:17:54 +0000