summaryrefslogtreecommitdiff
path: root/net/netfilter
diff options
context:
space:
mode:
Diffstat (limited to 'net/netfilter')
-rw-r--r--net/netfilter/Kconfig71
-rw-r--r--net/netfilter/Makefile4
-rw-r--r--net/netfilter/ipvs/Kconfig11
-rw-r--r--net/netfilter/ipvs/ip_vs_app.c43
-rw-r--r--net/netfilter/ipvs/ip_vs_conn.c55
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c57
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c10
-rw-r--r--net/netfilter/ipvs/ip_vs_ftp.c176
-rw-r--r--net/netfilter/ipvs/ip_vs_proto.c1
-rw-r--r--net/netfilter/ipvs/ip_vs_proto_sctp.c55
-rw-r--r--net/netfilter/ipvs/ip_vs_proto_tcp.c50
-rw-r--r--net/netfilter/ipvs/ip_vs_proto_udp.c56
-rw-r--r--net/netfilter/ipvs/ip_vs_xmit.c115
-rw-r--r--net/netfilter/nf_conntrack_acct.c14
-rw-r--r--net/netfilter/nf_conntrack_core.c49
-rw-r--r--net/netfilter/nf_conntrack_extend.c22
-rw-r--r--net/netfilter/nf_conntrack_h323_main.c12
-rw-r--r--net/netfilter/nf_conntrack_netbios_ns.c2
-rw-r--r--net/netfilter/nf_conntrack_netlink.c2
-rw-r--r--net/netfilter/nf_conntrack_proto_tcp.c42
-rw-r--r--net/netfilter/nfnetlink_log.c73
-rw-r--r--net/netfilter/nfnetlink_queue.c39
-rw-r--r--net/netfilter/xt_CHECKSUM.c70
-rw-r--r--net/netfilter/xt_CT.c4
-rw-r--r--net/netfilter/xt_IDLETIMER.c315
-rw-r--r--net/netfilter/xt_NOTRACK.c2
-rw-r--r--net/netfilter/xt_RATEEST.c12
-rw-r--r--net/netfilter/xt_TCPMSS.c8
-rw-r--r--net/netfilter/xt_TEE.c8
-rw-r--r--net/netfilter/xt_TPROXY.c6
-rw-r--r--net/netfilter/xt_cluster.c2
-rw-r--r--net/netfilter/xt_connbytes.c10
-rw-r--r--net/netfilter/xt_conntrack.c11
-rw-r--r--net/netfilter/xt_cpu.c63
-rw-r--r--net/netfilter/xt_ipvs.c189
-rw-r--r--net/netfilter/xt_quota.c12
-rw-r--r--net/netfilter/xt_sctp.c3
-rw-r--r--net/netfilter/xt_socket.c2
-rw-r--r--net/netfilter/xt_state.c14
-rw-r--r--net/netfilter/xt_statistic.c19
40 files changed, 1214 insertions, 495 deletions
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 8593a77cfea9..43288259f4a1 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -40,27 +40,6 @@ config NF_CONNTRACK
if NF_CONNTRACK
-config NF_CT_ACCT
- bool "Connection tracking flow accounting"
- depends on NETFILTER_ADVANCED
- help
- If this option is enabled, the connection tracking code will
- keep per-flow packet and byte counters.
-
- Those counters can be used for flow-based accounting or the
- `connbytes' match.
-
- Please note that currently this option only sets a default state.
- You may change it at boot time with nf_conntrack.acct=0/1 kernel
- parameter or by loading the nf_conntrack module with acct=0/1.
-
- You may also disable/enable it on a running system with:
- sysctl net.netfilter.nf_conntrack_acct=0/1
-
- This option will be removed in 2.6.29.
-
- If unsure, say `N'.
-
config NF_CONNTRACK_MARK
bool 'Connection mark tracking support'
depends on NETFILTER_ADVANCED
@@ -347,6 +326,22 @@ config NETFILTER_XT_CONNMARK
comment "Xtables targets"
+config NETFILTER_XT_TARGET_CHECKSUM
+ tristate "CHECKSUM target support"
+ depends on IP_NF_MANGLE || IP6_NF_MANGLE
+ depends on NETFILTER_ADVANCED
+ ---help---
+ This option adds a `CHECKSUM' target, which can be used in the iptables mangle
+ table.
+
+ You can use this target to compute and fill in the checksum in
+ a packet that lacks a checksum. This is particularly useful,
+ if you need to work around old applications such as dhcp clients,
+ that do not work well with checksum offloads, but don't want to disable
+ checksum offload in your device.
+
+ To compile it as a module, choose M here. If unsure, say N.
+
config NETFILTER_XT_TARGET_CLASSIFY
tristate '"CLASSIFY" target support'
depends on NETFILTER_ADVANCED
@@ -424,6 +419,18 @@ config NETFILTER_XT_TARGET_HL
since you can easily create immortal packets that loop
forever on the network.
+config NETFILTER_XT_TARGET_IDLETIMER
+ tristate "IDLETIMER target support"
+ depends on NETFILTER_ADVANCED
+ help
+
+ This option adds the `IDLETIMER' target. Each matching packet
+ resets the timer associated with label specified when the rule is
+ added. When the timer expires, it triggers a sysfs notification.
+ The remaining time for expiration can be read via sysfs.
+
+ To compile it as a module, choose M here. If unsure, say N.
+
config NETFILTER_XT_TARGET_LED
tristate '"LED" target support'
depends on LEDS_CLASS && LEDS_TRIGGERS
@@ -503,7 +510,7 @@ config NETFILTER_XT_TARGET_RATEEST
To compile it as a module, choose M here. If unsure, say N.
config NETFILTER_XT_TARGET_TEE
- tristate '"TEE" - packet cloning to alternate destiantion'
+ tristate '"TEE" - packet cloning to alternate destination'
depends on NETFILTER_ADVANCED
depends on (IPV6 || IPV6=n)
depends on !NF_CONNTRACK || NF_CONNTRACK
@@ -618,7 +625,6 @@ config NETFILTER_XT_MATCH_CONNBYTES
tristate '"connbytes" per-connection counter match support'
depends on NF_CONNTRACK
depends on NETFILTER_ADVANCED
- select NF_CT_ACCT
help
This option adds a `connbytes' match, which allows you to match the
number of bytes and/or packets for each direction within a connection.
@@ -657,6 +663,15 @@ config NETFILTER_XT_MATCH_CONNTRACK
To compile it as a module, choose M here. If unsure, say N.
+config NETFILTER_XT_MATCH_CPU
+ tristate '"cpu" match support'
+ depends on NETFILTER_ADVANCED
+ help
+ CPU matching allows you to match packets based on the CPU
+ currently handling the packet.
+
+ To compile it as a module, choose M here. If unsure, say N.
+
config NETFILTER_XT_MATCH_DCCP
tristate '"dccp" protocol match support'
depends on NETFILTER_ADVANCED
@@ -736,6 +751,16 @@ config NETFILTER_XT_MATCH_IPRANGE
If unsure, say M.
+config NETFILTER_XT_MATCH_IPVS
+ tristate '"ipvs" match support'
+ depends on IP_VS
+ depends on NETFILTER_ADVANCED
+ depends on NF_CONNTRACK
+ help
+ This option allows you to match against IPVS properties of a packet.
+
+ If unsure, say N.
+
config NETFILTER_XT_MATCH_LENGTH
tristate '"length" match support'
depends on NETFILTER_ADVANCED
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 14e3a8fd8180..441050f31111 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -45,6 +45,7 @@ obj-$(CONFIG_NETFILTER_XT_MARK) += xt_mark.o
obj-$(CONFIG_NETFILTER_XT_CONNMARK) += xt_connmark.o
# targets
+obj-$(CONFIG_NETFILTER_XT_TARGET_CHECKSUM) += xt_CHECKSUM.o
obj-$(CONFIG_NETFILTER_XT_TARGET_CLASSIFY) += xt_CLASSIFY.o
obj-$(CONFIG_NETFILTER_XT_TARGET_CONNSECMARK) += xt_CONNSECMARK.o
obj-$(CONFIG_NETFILTER_XT_TARGET_CT) += xt_CT.o
@@ -61,6 +62,7 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_TCPMSS) += xt_TCPMSS.o
obj-$(CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP) += xt_TCPOPTSTRIP.o
obj-$(CONFIG_NETFILTER_XT_TARGET_TEE) += xt_TEE.o
obj-$(CONFIG_NETFILTER_XT_TARGET_TRACE) += xt_TRACE.o
+obj-$(CONFIG_NETFILTER_XT_TARGET_IDLETIMER) += xt_IDLETIMER.o
# matches
obj-$(CONFIG_NETFILTER_XT_MATCH_CLUSTER) += xt_cluster.o
@@ -68,6 +70,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_COMMENT) += xt_comment.o
obj-$(CONFIG_NETFILTER_XT_MATCH_CONNBYTES) += xt_connbytes.o
obj-$(CONFIG_NETFILTER_XT_MATCH_CONNLIMIT) += xt_connlimit.o
obj-$(CONFIG_NETFILTER_XT_MATCH_CONNTRACK) += xt_conntrack.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_CPU) += xt_cpu.o
obj-$(CONFIG_NETFILTER_XT_MATCH_DCCP) += xt_dccp.o
obj-$(CONFIG_NETFILTER_XT_MATCH_DSCP) += xt_dscp.o
obj-$(CONFIG_NETFILTER_XT_MATCH_ESP) += xt_esp.o
@@ -75,6 +78,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_HASHLIMIT) += xt_hashlimit.o
obj-$(CONFIG_NETFILTER_XT_MATCH_HELPER) += xt_helper.o
obj-$(CONFIG_NETFILTER_XT_MATCH_HL) += xt_hl.o
obj-$(CONFIG_NETFILTER_XT_MATCH_IPRANGE) += xt_iprange.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_IPVS) += xt_ipvs.o
obj-$(CONFIG_NETFILTER_XT_MATCH_LENGTH) += xt_length.o
obj-$(CONFIG_NETFILTER_XT_MATCH_LIMIT) += xt_limit.o
obj-$(CONFIG_NETFILTER_XT_MATCH_MAC) += xt_mac.o
diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index 712ccad13344..46a77d5c3887 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -3,7 +3,7 @@
#
menuconfig IP_VS
tristate "IP virtual server support"
- depends on NET && INET && NETFILTER
+ depends on NET && INET && NETFILTER && NF_CONNTRACK
---help---
IP Virtual Server support will let you build a high-performance
virtual server based on cluster of two or more real servers. This
@@ -26,7 +26,7 @@ if IP_VS
config IP_VS_IPV6
bool "IPv6 support for IPVS"
- depends on EXPERIMENTAL && (IPV6 = y || IP_VS = IPV6)
+ depends on IPV6 = y || IP_VS = IPV6
---help---
Add IPv6 support to IPVS. This is incomplete and might be dangerous.
@@ -87,19 +87,16 @@ config IP_VS_PROTO_UDP
protocol. Say Y if unsure.
config IP_VS_PROTO_AH_ESP
- bool
- depends on UNDEFINED
+ def_bool IP_VS_PROTO_ESP || IP_VS_PROTO_AH
config IP_VS_PROTO_ESP
bool "ESP load balancing support"
- select IP_VS_PROTO_AH_ESP
---help---
This option enables support for load balancing ESP (Encapsulation
Security Payload) transport protocol. Say Y if unsure.
config IP_VS_PROTO_AH
bool "AH load balancing support"
- select IP_VS_PROTO_AH_ESP
---help---
This option enables support for load balancing AH (Authentication
Header) transport protocol. Say Y if unsure.
@@ -238,7 +235,7 @@ comment 'IPVS application helper'
config IP_VS_FTP
tristate "FTP protocol helper"
- depends on IP_VS_PROTO_TCP
+ depends on IP_VS_PROTO_TCP && NF_NAT
---help---
FTP is a protocol that transfers IP address and/or port number in
the payload. In the virtual server via Network Address Translation,
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 1cb0e834f8ff..e76f87f4aca8 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -569,49 +569,6 @@ static const struct file_operations ip_vs_app_fops = {
};
#endif
-
-/*
- * Replace a segment of data with a new segment
- */
-int ip_vs_skb_replace(struct sk_buff *skb, gfp_t pri,
- char *o_buf, int o_len, char *n_buf, int n_len)
-{
- int diff;
- int o_offset;
- int o_left;
-
- EnterFunction(9);
-
- diff = n_len - o_len;
- o_offset = o_buf - (char *)skb->data;
- /* The length of left data after o_buf+o_len in the skb data */
- o_left = skb->len - (o_offset + o_len);
-
- if (diff <= 0) {
- memmove(o_buf + n_len, o_buf + o_len, o_left);
- memcpy(o_buf, n_buf, n_len);
- skb_trim(skb, skb->len + diff);
- } else if (diff <= skb_tailroom(skb)) {
- skb_put(skb, diff);
- memmove(o_buf + n_len, o_buf + o_len, o_left);
- memcpy(o_buf, n_buf, n_len);
- } else {
- if (pskb_expand_head(skb, skb_headroom(skb), diff, pri))
- return -ENOMEM;
- skb_put(skb, diff);
- memmove(skb->data + o_offset + n_len,
- skb->data + o_offset + o_len, o_left);
- skb_copy_to_linear_data_offset(skb, o_offset, n_buf, n_len);
- }
-
- /* must update the iph total length here */
- ip_hdr(skb)->tot_len = htons(skb->len);
-
- LeaveFunction(9);
- return 0;
-}
-
-
int __init ip_vs_app_init(void)
{
/* we will replace it with proc_net_ipvs_create() soon */
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index ff04e9edbed6..b71c69a2db13 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -158,6 +158,9 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp)
unsigned hash;
int ret;
+ if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
+ return 0;
+
/* Hash by protocol, client address and port */
hash = ip_vs_conn_hashkey(cp->af, cp->protocol, &cp->caddr, cp->cport);
@@ -268,6 +271,29 @@ struct ip_vs_conn *ip_vs_conn_in_get
return cp;
}
+struct ip_vs_conn *
+ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb,
+ struct ip_vs_protocol *pp,
+ const struct ip_vs_iphdr *iph,
+ unsigned int proto_off, int inverse)
+{
+ __be16 _ports[2], *pptr;
+
+ pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
+ if (pptr == NULL)
+ return NULL;
+
+ if (likely(!inverse))
+ return ip_vs_conn_in_get(af, iph->protocol,
+ &iph->saddr, pptr[0],
+ &iph->daddr, pptr[1]);
+ else
+ return ip_vs_conn_in_get(af, iph->protocol,
+ &iph->daddr, pptr[1],
+ &iph->saddr, pptr[0]);
+}
+EXPORT_SYMBOL_GPL(ip_vs_conn_in_get_proto);
+
/* Get reference to connection template */
struct ip_vs_conn *ip_vs_ct_in_get
(int af, int protocol, const union nf_inet_addr *s_addr, __be16 s_port,
@@ -353,14 +379,37 @@ struct ip_vs_conn *ip_vs_conn_out_get
return ret;
}
+struct ip_vs_conn *
+ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb,
+ struct ip_vs_protocol *pp,
+ const struct ip_vs_iphdr *iph,
+ unsigned int proto_off, int inverse)
+{
+ __be16 _ports[2], *pptr;
+
+ pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
+ if (pptr == NULL)
+ return NULL;
+
+ if (likely(!inverse))
+ return ip_vs_conn_out_get(af, iph->protocol,
+ &iph->saddr, pptr[0],
+ &iph->daddr, pptr[1]);
+ else
+ return ip_vs_conn_out_get(af, iph->protocol,
+ &iph->daddr, pptr[1],
+ &iph->saddr, pptr[0]);
+}
+EXPORT_SYMBOL_GPL(ip_vs_conn_out_get_proto);
/*
* Put back the conn and restart its timer with its timeout
*/
void ip_vs_conn_put(struct ip_vs_conn *cp)
{
- /* reset it expire in its timeout */
- mod_timer(&cp->timer, jiffies+cp->timeout);
+ unsigned long t = (cp->flags & IP_VS_CONN_F_ONE_PACKET) ?
+ 0 : cp->timeout;
+ mod_timer(&cp->timer, jiffies+t);
__ip_vs_conn_put(cp);
}
@@ -653,7 +702,7 @@ static void ip_vs_conn_expire(unsigned long data)
/*
* unhash it if it is hashed in the conn table
*/
- if (!ip_vs_conn_unhash(cp))
+ if (!ip_vs_conn_unhash(cp) && !(cp->flags & IP_VS_CONN_F_ONE_PACKET))
goto expire_later;
/*
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 1cd6e3fd058b..4f8ddba48011 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -54,7 +54,6 @@
EXPORT_SYMBOL(register_ip_vs_scheduler);
EXPORT_SYMBOL(unregister_ip_vs_scheduler);
-EXPORT_SYMBOL(ip_vs_skb_replace);
EXPORT_SYMBOL(ip_vs_proto_name);
EXPORT_SYMBOL(ip_vs_conn_new);
EXPORT_SYMBOL(ip_vs_conn_in_get);
@@ -194,6 +193,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
struct ip_vs_dest *dest;
struct ip_vs_conn *ct;
__be16 dport; /* destination port to forward */
+ __be16 flags;
union nf_inet_addr snet; /* source network of the client,
after masking */
@@ -340,6 +340,10 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
dport = ports[1];
}
+ flags = (svc->flags & IP_VS_SVC_F_ONEPACKET
+ && iph.protocol == IPPROTO_UDP)?
+ IP_VS_CONN_F_ONE_PACKET : 0;
+
/*
* Create a new connection according to the template
*/
@@ -347,7 +351,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
&iph.saddr, ports[0],
&iph.daddr, ports[1],
&dest->addr, dport,
- 0,
+ flags,
dest);
if (cp == NULL) {
ip_vs_conn_put(ct);
@@ -377,7 +381,7 @@ ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
struct ip_vs_conn *cp = NULL;
struct ip_vs_iphdr iph;
struct ip_vs_dest *dest;
- __be16 _ports[2], *pptr;
+ __be16 _ports[2], *pptr, flags;
ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports);
@@ -407,6 +411,10 @@ ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
return NULL;
}
+ flags = (svc->flags & IP_VS_SVC_F_ONEPACKET
+ && iph.protocol == IPPROTO_UDP)?
+ IP_VS_CONN_F_ONE_PACKET : 0;
+
/*
* Create a connection entry.
*/
@@ -414,7 +422,7 @@ ip_vs_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
&iph.saddr, pptr[0],
&iph.daddr, pptr[1],
&dest->addr, dest->port ? dest->port : pptr[1],
- 0,
+ flags,
dest);
if (cp == NULL)
return NULL;
@@ -464,6 +472,9 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
if (sysctl_ip_vs_cache_bypass && svc->fwmark && unicast) {
int ret, cs;
struct ip_vs_conn *cp;
+ __u16 flags = (svc->flags & IP_VS_SVC_F_ONEPACKET &&
+ iph.protocol == IPPROTO_UDP)?
+ IP_VS_CONN_F_ONE_PACKET : 0;
union nf_inet_addr daddr = { .all = { 0, 0, 0, 0 } };
ip_vs_service_put(svc);
@@ -474,7 +485,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
&iph.saddr, pptr[0],
&iph.daddr, pptr[1],
&daddr, 0,
- IP_VS_CONN_F_BYPASS,
+ IP_VS_CONN_F_BYPASS | flags,
NULL);
if (cp == NULL)
return NF_DROP;
@@ -524,26 +535,6 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
return NF_DROP;
}
-
-/*
- * It is hooked before NF_IP_PRI_NAT_SRC at the NF_INET_POST_ROUTING
- * chain, and is used for VS/NAT.
- * It detects packets for VS/NAT connections and sends the packets
- * immediately. This can avoid that iptable_nat mangles the packets
- * for VS/NAT.
- */
-static unsigned int ip_vs_post_routing(unsigned int hooknum,
- struct sk_buff *skb,
- const struct net_device *in,
- const struct net_device *out,
- int (*okfn)(struct sk_buff *))
-{
- if (!skb->ipvs_property)
- return NF_ACCEPT;
- /* The packet was sent from IPVS, exit this chain */
- return NF_STOP;
-}
-
__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset)
{
return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0));
@@ -1487,14 +1478,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
.hooknum = NF_INET_FORWARD,
.priority = 99,
},
- /* Before the netfilter connection tracking, exit from POST_ROUTING */
- {
- .hook = ip_vs_post_routing,
- .owner = THIS_MODULE,
- .pf = PF_INET,
- .hooknum = NF_INET_POST_ROUTING,
- .priority = NF_IP_PRI_NAT_SRC-1,
- },
#ifdef CONFIG_IP_VS_IPV6
/* After packet filtering, forward packet through VS/DR, VS/TUN,
* or VS/NAT(change destination), so that filtering rules can be
@@ -1523,14 +1506,6 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = {
.hooknum = NF_INET_FORWARD,
.priority = 99,
},
- /* Before the netfilter connection tracking, exit from POST_ROUTING */
- {
- .hook = ip_vs_post_routing,
- .owner = THIS_MODULE,
- .pf = PF_INET6,
- .hooknum = NF_INET_POST_ROUTING,
- .priority = NF_IP6_PRI_NAT_SRC-1,
- },
#endif
};
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 36dc1d88c2fa..0f0c079c422a 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1864,14 +1864,16 @@ static int ip_vs_info_seq_show(struct seq_file *seq, void *v)
svc->scheduler->name);
else
#endif
- seq_printf(seq, "%s %08X:%04X %s ",
+ seq_printf(seq, "%s %08X:%04X %s %s ",
ip_vs_proto_name(svc->protocol),
ntohl(svc->addr.ip),
ntohs(svc->port),
- svc->scheduler->name);
+ svc->scheduler->name,
+ (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
} else {
- seq_printf(seq, "FWM %08X %s ",
- svc->fwmark, svc->scheduler->name);
+ seq_printf(seq, "FWM %08X %s %s",
+ svc->fwmark, svc->scheduler->name,
+ (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
}
if (svc->flags & IP_VS_SVC_F_PERSISTENT)
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 2ae747a376a5..f228a17ec649 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -20,6 +20,17 @@
*
* Author: Wouter Gadeyne
*
+ *
+ * Code for ip_vs_expect_related and ip_vs_expect_callback is taken from
+ * http://www.ssi.bg/~ja/nfct/:
+ *
+ * ip_vs_nfct.c: Netfilter connection tracking support for IPVS
+ *
+ * Portions Copyright (C) 2001-2002
+ * Antefacto Ltd, 181 Parnell St, Dublin 1, Ireland.
+ *
+ * Portions Copyright (C) 2003-2008
+ * Julian Anastasov
*/
#define KMSG_COMPONENT "IPVS"
@@ -32,6 +43,9 @@
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/netfilter.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_expect.h>
+#include <net/netfilter/nf_nat_helper.h>
#include <linux/gfp.h>
#include <net/protocol.h>
#include <net/tcp.h>
@@ -43,6 +57,16 @@
#define SERVER_STRING "227 Entering Passive Mode ("
#define CLIENT_STRING "PORT "
+#define FMT_TUPLE "%pI4:%u->%pI4:%u/%u"
+#define ARG_TUPLE(T) &(T)->src.u3.ip, ntohs((T)->src.u.all), \
+ &(T)->dst.u3.ip, ntohs((T)->dst.u.all), \
+ (T)->dst.protonum
+
+#define FMT_CONN "%pI4:%u->%pI4:%u->%pI4:%u/%u:%u"
+#define ARG_CONN(C) &((C)->caddr.ip), ntohs((C)->cport), \
+ &((C)->vaddr.ip), ntohs((C)->vport), \
+ &((C)->daddr.ip), ntohs((C)->dport), \
+ (C)->protocol, (C)->state
/*
* List of ports (up to IP_VS_APP_MAX_PORTS) to be handled by helper
@@ -123,6 +147,119 @@ static int ip_vs_ftp_get_addrport(char *data, char *data_limit,
return 1;
}
+/*
+ * Called from init_conntrack() as expectfn handler.
+ */
+static void
+ip_vs_expect_callback(struct nf_conn *ct,
+ struct nf_conntrack_expect *exp)
+{
+ struct nf_conntrack_tuple *orig, new_reply;
+ struct ip_vs_conn *cp;
+
+ if (exp->tuple.src.l3num != PF_INET)
+ return;
+
+ /*
+ * We assume that no NF locks are held before this callback.
+ * ip_vs_conn_out_get and ip_vs_conn_in_get should match their
+ * expectations even if they use wildcard values, now we provide the
+ * actual values from the newly created original conntrack direction.
+ * The conntrack is confirmed when packet reaches IPVS hooks.
+ */
+
+ /* RS->CLIENT */
+ orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
+ cp = ip_vs_conn_out_get(exp->tuple.src.l3num, orig->dst.protonum,
+ &orig->src.u3, orig->src.u.tcp.port,
+ &orig->dst.u3, orig->dst.u.tcp.port);
+ if (cp) {
+ /* Change reply CLIENT->RS to CLIENT->VS */
+ new_reply = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
+ IP_VS_DBG(7, "%s(): ct=%p, status=0x%lX, tuples=" FMT_TUPLE ", "
+ FMT_TUPLE ", found inout cp=" FMT_CONN "\n",
+ __func__, ct, ct->status,
+ ARG_TUPLE(orig), ARG_TUPLE(&new_reply),
+ ARG_CONN(cp));
+ new_reply.dst.u3 = cp->vaddr;
+ new_reply.dst.u.tcp.port = cp->vport;
+ IP_VS_DBG(7, "%s(): ct=%p, new tuples=" FMT_TUPLE ", " FMT_TUPLE
+ ", inout cp=" FMT_CONN "\n",
+ __func__, ct,
+ ARG_TUPLE(orig), ARG_TUPLE(&new_reply),
+ ARG_CONN(cp));
+ goto alter;
+ }
+
+ /* CLIENT->VS */
+ cp = ip_vs_conn_in_get(exp->tuple.src.l3num, orig->dst.protonum,
+ &orig->src.u3, orig->src.u.tcp.port,
+ &orig->dst.u3, orig->dst.u.tcp.port);
+ if (cp) {
+ /* Change reply VS->CLIENT to RS->CLIENT */
+ new_reply = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
+ IP_VS_DBG(7, "%s(): ct=%p, status=0x%lX, tuples=" FMT_TUPLE ", "
+ FMT_TUPLE ", found outin cp=" FMT_CONN "\n",
+ __func__, ct, ct->status,
+ ARG_TUPLE(orig), ARG_TUPLE(&new_reply),
+ ARG_CONN(cp));
+ new_reply.src.u3 = cp->daddr;
+ new_reply.src.u.tcp.port = cp->dport;
+ IP_VS_DBG(7, "%s(): ct=%p, new tuples=" FMT_TUPLE ", "
+ FMT_TUPLE ", outin cp=" FMT_CONN "\n",
+ __func__, ct,
+ ARG_TUPLE(orig), ARG_TUPLE(&new_reply),
+ ARG_CONN(cp));
+ goto alter;
+ }
+
+ IP_VS_DBG(7, "%s(): ct=%p, status=0x%lX, tuple=" FMT_TUPLE
+ " - unknown expect\n",
+ __func__, ct, ct->status, ARG_TUPLE(orig));
+ return;
+
+alter:
+ /* Never alter conntrack for non-NAT conns */
+ if (IP_VS_FWD_METHOD(cp) == IP_VS_CONN_F_MASQ)
+ nf_conntrack_alter_reply(ct, &new_reply);
+ ip_vs_conn_put(cp);
+ return;
+}
+
+/*
+ * Create NF conntrack expectation with wildcard (optional) source port.
+ * Then the default callback function will alter the reply and will confirm
+ * the conntrack entry when the first packet comes.
+ */
+static void
+ip_vs_expect_related(struct sk_buff *skb, struct nf_conn *ct,
+ struct ip_vs_conn *cp, u_int8_t proto,
+ const __be16 *port, int from_rs)
+{
+ struct nf_conntrack_expect *exp;
+
+ BUG_ON(!ct || ct == &nf_conntrack_untracked);
+
+ exp = nf_ct_expect_alloc(ct);
+ if (!exp)
+ return;
+
+ if (from_rs)
+ nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT,
+ nf_ct_l3num(ct), &cp->daddr, &cp->caddr,
+ proto, port, &cp->cport);
+ else
+ nf_ct_expect_init(exp, NF_CT_EXPECT_CLASS_DEFAULT,
+ nf_ct_l3num(ct), &cp->caddr, &cp->vaddr,
+ proto, port, &cp->vport);
+
+ exp->expectfn = ip_vs_expect_callback;
+
+ IP_VS_DBG(7, "%s(): ct=%p, expect tuple=" FMT_TUPLE "\n",
+ __func__, ct, ARG_TUPLE(&exp->tuple));
+ nf_ct_expect_related(exp);
+ nf_ct_expect_put(exp);
+}
/*
* Look at outgoing ftp packets to catch the response to a PASV command
@@ -149,7 +286,9 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
struct ip_vs_conn *n_cp;
char buf[24]; /* xxx.xxx.xxx.xxx,ppp,ppp\000 */
unsigned buf_len;
- int ret;
+ int ret = 0;
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct;
#ifdef CONFIG_IP_VS_IPV6
/* This application helper doesn't work with IPv6 yet,
@@ -219,19 +358,26 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
buf_len = strlen(buf);
+ ct = nf_ct_get(skb, &ctinfo);
+ if (ct && !nf_ct_is_untracked(ct)) {
+ /* If mangling fails this function will return 0
+ * which will cause the packet to be dropped.
+ * Mangling can only fail under memory pressure,
+ * hopefully it will succeed on the retransmitted
+ * packet.
+ */
+ ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo,
+ start-data, end-start,
+ buf, buf_len);
+ if (ret)
+ ip_vs_expect_related(skb, ct, n_cp,
+ IPPROTO_TCP, NULL, 0);
+ }
+
/*
- * Calculate required delta-offset to keep TCP happy
+ * Not setting 'diff' is intentional, otherwise the sequence
+ * would be adjusted twice.
*/
- *diff = buf_len - (end-start);
-
- if (*diff == 0) {
- /* simply replace it with new passive address */
- memcpy(start, buf, buf_len);
- ret = 1;
- } else {
- ret = !ip_vs_skb_replace(skb, GFP_ATOMIC, start,
- end-start, buf, buf_len);
- }
cp->app_data = NULL;
ip_vs_tcp_conn_listen(n_cp);
@@ -263,6 +409,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
union nf_inet_addr to;
__be16 port;
struct ip_vs_conn *n_cp;
+ struct nf_conn *ct;
#ifdef CONFIG_IP_VS_IPV6
/* This application helper doesn't work with IPv6 yet,
@@ -349,6 +496,11 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
ip_vs_control_add(n_cp, cp);
}
+ ct = (struct nf_conn *)skb->nfct;
+ if (ct && ct != &nf_conntrack_untracked)
+ ip_vs_expect_related(skb, ct, n_cp,
+ IPPROTO_TCP, &n_cp->dport, 1);
+
/*
* Move tunnel to listen state
*/
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 2d3d5e4b35f8..027f654799fe 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -98,6 +98,7 @@ struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto)
return NULL;
}
+EXPORT_SYMBOL(ip_vs_proto_get);
/*
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index c9a3f7a21d53..4c0855cb006e 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -8,55 +8,6 @@
#include <net/sctp/checksum.h>
#include <net/ip_vs.h>
-
-static struct ip_vs_conn *
-sctp_conn_in_get(int af,
- const struct sk_buff *skb,
- struct ip_vs_protocol *pp,
- const struct ip_vs_iphdr *iph,
- unsigned int proto_off,
- int inverse)
-{
- __be16 _ports[2], *pptr;
-
- pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
- if (pptr == NULL)
- return NULL;
-
- if (likely(!inverse))
- return ip_vs_conn_in_get(af, iph->protocol,
- &iph->saddr, pptr[0],
- &iph->daddr, pptr[1]);
- else
- return ip_vs_conn_in_get(af, iph->protocol,
- &iph->daddr, pptr[1],
- &iph->saddr, pptr[0]);
-}
-
-static struct ip_vs_conn *
-sctp_conn_out_get(int af,
- const struct sk_buff *skb,
- struct ip_vs_protocol *pp,
- const struct ip_vs_iphdr *iph,
- unsigned int proto_off,
- int inverse)
-{
- __be16 _ports[2], *pptr;
-
- pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
- if (pptr == NULL)
- return NULL;
-
- if (likely(!inverse))
- return ip_vs_conn_out_get(af, iph->protocol,
- &iph->saddr, pptr[0],
- &iph->daddr, pptr[1]);
- else
- return ip_vs_conn_out_get(af, iph->protocol,
- &iph->daddr, pptr[1],
- &iph->saddr, pptr[0]);
-}
-
static int
sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
int *verdict, struct ip_vs_conn **cpp)
@@ -173,7 +124,7 @@ sctp_dnat_handler(struct sk_buff *skb,
return 0;
/* Call application helper if needed */
- if (!ip_vs_app_pkt_out(cp, skb))
+ if (!ip_vs_app_pkt_in(cp, skb))
return 0;
}
@@ -1169,8 +1120,8 @@ struct ip_vs_protocol ip_vs_protocol_sctp = {
.register_app = sctp_register_app,
.unregister_app = sctp_unregister_app,
.conn_schedule = sctp_conn_schedule,
- .conn_in_get = sctp_conn_in_get,
- .conn_out_get = sctp_conn_out_get,
+ .conn_in_get = ip_vs_conn_in_get_proto,
+ .conn_out_get = ip_vs_conn_out_get_proto,
.snat_handler = sctp_snat_handler,
.dnat_handler = sctp_dnat_handler,
.csum_check = sctp_csum_check,
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 91d28e073742..282d24de8592 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -27,52 +27,6 @@
#include <net/ip_vs.h>
-
-static struct ip_vs_conn *
-tcp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp,
- const struct ip_vs_iphdr *iph, unsigned int proto_off,
- int inverse)
-{
- __be16 _ports[2], *pptr;
-
- pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
- if (pptr == NULL)
- return NULL;
-
- if (likely(!inverse)) {
- return ip_vs_conn_in_get(af, iph->protocol,
- &iph->saddr, pptr[0],
- &iph->daddr, pptr[1]);
- } else {
- return ip_vs_conn_in_get(af, iph->protocol,
- &iph->daddr, pptr[1],
- &iph->saddr, pptr[0]);
- }
-}
-
-static struct ip_vs_conn *
-tcp_conn_out_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp,
- const struct ip_vs_iphdr *iph, unsigned int proto_off,
- int inverse)
-{
- __be16 _ports[2], *pptr;
-
- pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
- if (pptr == NULL)
- return NULL;
-
- if (likely(!inverse)) {
- return ip_vs_conn_out_get(af, iph->protocol,
- &iph->saddr, pptr[0],
- &iph->daddr, pptr[1]);
- } else {
- return ip_vs_conn_out_get(af, iph->protocol,
- &iph->daddr, pptr[1],
- &iph->saddr, pptr[0]);
- }
-}
-
-
static int
tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
int *verdict, struct ip_vs_conn **cpp)
@@ -721,8 +675,8 @@ struct ip_vs_protocol ip_vs_protocol_tcp = {
.register_app = tcp_register_app,
.unregister_app = tcp_unregister_app,
.conn_schedule = tcp_conn_schedule,
- .conn_in_get = tcp_conn_in_get,
- .conn_out_get = tcp_conn_out_get,
+ .conn_in_get = ip_vs_conn_in_get_proto,
+ .conn_out_get = ip_vs_conn_out_get_proto,
.snat_handler = tcp_snat_handler,
.dnat_handler = tcp_dnat_handler,
.csum_check = tcp_csum_check,
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index e7a6885e0167..8553231b5d41 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -27,58 +27,6 @@
#include <net/ip.h>
#include <net/ip6_checksum.h>
-static struct ip_vs_conn *
-udp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp,
- const struct ip_vs_iphdr *iph, unsigned int proto_off,
- int inverse)
-{
- struct ip_vs_conn *cp;
- __be16 _ports[2], *pptr;
-
- pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
- if (pptr == NULL)
- return NULL;
-
- if (likely(!inverse)) {
- cp = ip_vs_conn_in_get(af, iph->protocol,
- &iph->saddr, pptr[0],
- &iph->daddr, pptr[1]);
- } else {
- cp = ip_vs_conn_in_get(af, iph->protocol,
- &iph->daddr, pptr[1],
- &iph->saddr, pptr[0]);
- }
-
- return cp;
-}
-
-
-static struct ip_vs_conn *
-udp_conn_out_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp,
- const struct ip_vs_iphdr *iph, unsigned int proto_off,
- int inverse)
-{
- struct ip_vs_conn *cp;
- __be16 _ports[2], *pptr;
-
- pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports);
- if (pptr == NULL)
- return NULL;
-
- if (likely(!inverse)) {
- cp = ip_vs_conn_out_get(af, iph->protocol,
- &iph->saddr, pptr[0],
- &iph->daddr, pptr[1]);
- } else {
- cp = ip_vs_conn_out_get(af, iph->protocol,
- &iph->daddr, pptr[1],
- &iph->saddr, pptr[0]);
- }
-
- return cp;
-}
-
-
static int
udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp,
int *verdict, struct ip_vs_conn **cpp)
@@ -520,8 +468,8 @@ struct ip_vs_protocol ip_vs_protocol_udp = {
.init = udp_init,
.exit = udp_exit,
.conn_schedule = udp_conn_schedule,
- .conn_in_get = udp_conn_in_get,
- .conn_out_get = udp_conn_out_get,
+ .conn_in_get = ip_vs_conn_in_get_proto,
+ .conn_out_get = ip_vs_conn_out_get_proto,
.snat_handler = udp_snat_handler,
.dnat_handler = udp_dnat_handler,
.csum_check = udp_csum_check,
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 93c15a107b2c..21e1a5e9b9d3 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -28,6 +28,7 @@
#include <net/ip6_route.h>
#include <linux/icmpv6.h>
#include <linux/netfilter.h>
+#include <net/netfilter/nf_conntrack.h>
#include <linux/netfilter_ipv4.h>
#include <net/ip_vs.h>
@@ -90,10 +91,10 @@ __ip_vs_get_out_rt(struct ip_vs_conn *cp, u32 rtos)
&dest->addr.ip);
return NULL;
}
- __ip_vs_dst_set(dest, rtos, dst_clone(&rt->u.dst));
+ __ip_vs_dst_set(dest, rtos, dst_clone(&rt->dst));
IP_VS_DBG(10, "new dst %pI4, refcnt=%d, rtos=%X\n",
&dest->addr.ip,
- atomic_read(&rt->u.dst.__refcnt), rtos);
+ atomic_read(&rt->dst.__refcnt), rtos);
}
spin_unlock(&dest->dst_lock);
} else {
@@ -148,10 +149,10 @@ __ip_vs_get_out_rt_v6(struct ip_vs_conn *cp)
&dest->addr.in6);
return NULL;
}
- __ip_vs_dst_set(dest, 0, dst_clone(&rt->u.dst));
+ __ip_vs_dst_set(dest, 0, dst_clone(&rt->dst));
IP_VS_DBG(10, "new dst %pI6, refcnt=%d\n",
&dest->addr.in6,
- atomic_read(&rt->u.dst.__refcnt));
+ atomic_read(&rt->dst.__refcnt));
}
spin_unlock(&dest->dst_lock);
} else {
@@ -198,7 +199,7 @@ do { \
(skb)->ipvs_property = 1; \
skb_forward_csum(skb); \
NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \
- (rt)->u.dst.dev, dst_output); \
+ (rt)->dst.dev, dst_output); \
} while (0)
@@ -245,7 +246,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
}
/* MTU checking */
- mtu = dst_mtu(&rt->u.dst);
+ mtu = dst_mtu(&rt->dst);
if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) {
ip_rt_put(rt);
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
@@ -265,7 +266,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
/* drop old route */
skb_dst_drop(skb);
- skb_dst_set(skb, &rt->u.dst);
+ skb_dst_set(skb, &rt->dst);
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
@@ -309,9 +310,9 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
}
/* MTU checking */
- mtu = dst_mtu(&rt->u.dst);
+ mtu = dst_mtu(&rt->dst);
if (skb->len > mtu) {
- dst_release(&rt->u.dst);
+ dst_release(&rt->dst);
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
goto tx_error;
@@ -323,13 +324,13 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
*/
skb = skb_share_check(skb, GFP_ATOMIC);
if (unlikely(skb == NULL)) {
- dst_release(&rt->u.dst);
+ dst_release(&rt->dst);
return NF_STOLEN;
}
/* drop old route */
skb_dst_drop(skb);
- skb_dst_set(skb, &rt->u.dst);
+ skb_dst_set(skb, &rt->dst);
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
@@ -348,6 +349,30 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
}
#endif
+static void
+ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp)
+{
+ struct nf_conn *ct = (struct nf_conn *)skb->nfct;
+ struct nf_conntrack_tuple new_tuple;
+
+ if (ct == NULL || nf_ct_is_untracked(ct) || nf_ct_is_confirmed(ct))
+ return;
+
+ /*
+ * The connection is not yet in the hashtable, so we update it.
+ * CIP->VIP will remain the same, so leave the tuple in
+ * IP_CT_DIR_ORIGINAL untouched. When the reply comes back from the
+ * real-server we will see RIP->DIP.
+ */
+ new_tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple;
+ new_tuple.src.u3 = cp->daddr;
+ /*
+ * This will also take care of UDP and other protocols.
+ */
+ new_tuple.src.u.tcp.port = cp->dport;
+ nf_conntrack_alter_reply(ct, &new_tuple);
+}
+
/*
* NAT transmitter (only for outside-to-inside nat forwarding)
* Not used for related ICMP
@@ -376,7 +401,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
goto tx_error_icmp;
/* MTU checking */
- mtu = dst_mtu(&rt->u.dst);
+ mtu = dst_mtu(&rt->dst);
if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) {
ip_rt_put(rt);
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
@@ -388,12 +413,12 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
if (!skb_make_writable(skb, sizeof(struct iphdr)))
goto tx_error_put;
- if (skb_cow(skb, rt->u.dst.dev->hard_header_len))
+ if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error_put;
/* drop old route */
skb_dst_drop(skb);
- skb_dst_set(skb, &rt->u.dst);
+ skb_dst_set(skb, &rt->dst);
/* mangle the packet */
if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp))
@@ -403,6 +428,8 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT");
+ ip_vs_update_conntrack(skb, cp);
+
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
MTU problem. */
@@ -452,9 +479,9 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
goto tx_error_icmp;
/* MTU checking */
- mtu = dst_mtu(&rt->u.dst);
+ mtu = dst_mtu(&rt->dst);
if (skb->len > mtu) {
- dst_release(&rt->u.dst);
+ dst_release(&rt->dst);
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP_VS_DBG_RL_PKT(0, pp, skb, 0,
"ip_vs_nat_xmit_v6(): frag needed for");
@@ -465,12 +492,12 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
if (!skb_make_writable(skb, sizeof(struct ipv6hdr)))
goto tx_error_put;
- if (skb_cow(skb, rt->u.dst.dev->hard_header_len))
+ if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error_put;
/* drop old route */
skb_dst_drop(skb);
- skb_dst_set(skb, &rt->u.dst);
+ skb_dst_set(skb, &rt->dst);
/* mangle the packet */
if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp))
@@ -479,6 +506,8 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT");
+ ip_vs_update_conntrack(skb, cp);
+
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
MTU problem. */
@@ -498,7 +527,7 @@ tx_error:
kfree_skb(skb);
return NF_STOLEN;
tx_error_put:
- dst_release(&rt->u.dst);
+ dst_release(&rt->dst);
goto tx_error;
}
#endif
@@ -549,9 +578,9 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
if (!(rt = __ip_vs_get_out_rt(cp, RT_TOS(tos))))
goto tx_error_icmp;
- tdev = rt->u.dst.dev;
+ tdev = rt->dst.dev;
- mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr);
+ mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
if (mtu < 68) {
ip_rt_put(rt);
IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
@@ -601,7 +630,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
/* drop old route */
skb_dst_drop(skb);
- skb_dst_set(skb, &rt->u.dst);
+ skb_dst_set(skb, &rt->dst);
/*
* Push down and install the IPIP header.
@@ -615,7 +644,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
iph->daddr = rt->rt_dst;
iph->saddr = rt->rt_src;
iph->ttl = old_iph->ttl;
- ip_select_ident(iph, &rt->u.dst, NULL);
+ ip_select_ident(iph, &rt->dst, NULL);
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
@@ -660,12 +689,12 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
if (!rt)
goto tx_error_icmp;
- tdev = rt->u.dst.dev;
+ tdev = rt->dst.dev;
- mtu = dst_mtu(&rt->u.dst) - sizeof(struct ipv6hdr);
+ mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr);
/* TODO IPv6: do we need this check in IPv6? */
if (mtu < 1280) {
- dst_release(&rt->u.dst);
+ dst_release(&rt->dst);
IP_VS_DBG_RL("%s(): mtu less than 1280\n", __func__);
goto tx_error;
}
@@ -674,7 +703,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr)) {
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
- dst_release(&rt->u.dst);
+ dst_release(&rt->dst);
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
goto tx_error;
}
@@ -689,7 +718,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct sk_buff *new_skb =
skb_realloc_headroom(skb, max_headroom);
if (!new_skb) {
- dst_release(&rt->u.dst);
+ dst_release(&rt->dst);
kfree_skb(skb);
IP_VS_ERR_RL("%s(): no memory\n", __func__);
return NF_STOLEN;
@@ -707,7 +736,7 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
/* drop old route */
skb_dst_drop(skb);
- skb_dst_set(skb, &rt->u.dst);
+ skb_dst_set(skb, &rt->dst);
/*
* Push down and install the IPIP header.
@@ -760,7 +789,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
goto tx_error_icmp;
/* MTU checking */
- mtu = dst_mtu(&rt->u.dst);
+ mtu = dst_mtu(&rt->dst);
if ((iph->frag_off & htons(IP_DF)) && skb->len > mtu) {
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
ip_rt_put(rt);
@@ -780,7 +809,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
/* drop old route */
skb_dst_drop(skb);
- skb_dst_set(skb, &rt->u.dst);
+ skb_dst_set(skb, &rt->dst);
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
@@ -813,10 +842,10 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
goto tx_error_icmp;
/* MTU checking */
- mtu = dst_mtu(&rt->u.dst);
+ mtu = dst_mtu(&rt->dst);
if (skb->len > mtu) {
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
- dst_release(&rt->u.dst);
+ dst_release(&rt->dst);
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
goto tx_error;
}
@@ -827,13 +856,13 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
*/
skb = skb_share_check(skb, GFP_ATOMIC);
if (unlikely(skb == NULL)) {
- dst_release(&rt->u.dst);
+ dst_release(&rt->dst);
return NF_STOLEN;
}
/* drop old route */
skb_dst_drop(skb);
- skb_dst_set(skb, &rt->u.dst);
+ skb_dst_set(skb, &rt->dst);
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
@@ -888,7 +917,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
goto tx_error_icmp;
/* MTU checking */
- mtu = dst_mtu(&rt->u.dst);
+ mtu = dst_mtu(&rt->dst);
if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF))) {
ip_rt_put(rt);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
@@ -900,12 +929,12 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
if (!skb_make_writable(skb, offset))
goto tx_error_put;
- if (skb_cow(skb, rt->u.dst.dev->hard_header_len))
+ if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error_put;
/* drop the old route when skb is not shared */
skb_dst_drop(skb);
- skb_dst_set(skb, &rt->u.dst);
+ skb_dst_set(skb, &rt->dst);
ip_vs_nat_icmp(skb, pp, cp, 0);
@@ -963,9 +992,9 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
goto tx_error_icmp;
/* MTU checking */
- mtu = dst_mtu(&rt->u.dst);
+ mtu = dst_mtu(&rt->dst);
if (skb->len > mtu) {
- dst_release(&rt->u.dst);
+ dst_release(&rt->dst);
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
goto tx_error;
@@ -975,12 +1004,12 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
if (!skb_make_writable(skb, offset))
goto tx_error_put;
- if (skb_cow(skb, rt->u.dst.dev->hard_header_len))
+ if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error_put;
/* drop the old route when skb is not shared */
skb_dst_drop(skb);
- skb_dst_set(skb, &rt->u.dst);
+ skb_dst_set(skb, &rt->dst);
ip_vs_nat_icmp_v6(skb, pp, cp, 0);
@@ -1001,7 +1030,7 @@ out:
LeaveFunction(10);
return rc;
tx_error_put:
- dst_release(&rt->u.dst);
+ dst_release(&rt->dst);
goto tx_error;
}
#endif
diff --git a/net/netfilter/nf_conntrack_acct.c b/net/netfilter/nf_conntrack_acct.c
index ab81b380eae6..5178c691ecbf 100644
--- a/net/netfilter/nf_conntrack_acct.c
+++ b/net/netfilter/nf_conntrack_acct.c
@@ -17,13 +17,7 @@
#include <net/netfilter/nf_conntrack_extend.h>
#include <net/netfilter/nf_conntrack_acct.h>
-#ifdef CONFIG_NF_CT_ACCT
-#define NF_CT_ACCT_DEFAULT 1
-#else
-#define NF_CT_ACCT_DEFAULT 0
-#endif
-
-static int nf_ct_acct __read_mostly = NF_CT_ACCT_DEFAULT;
+static int nf_ct_acct __read_mostly;
module_param_named(acct, nf_ct_acct, bool, 0644);
MODULE_PARM_DESC(acct, "Enable connection tracking flow accounting.");
@@ -114,12 +108,6 @@ int nf_conntrack_acct_init(struct net *net)
net->ct.sysctl_acct = nf_ct_acct;
if (net_eq(net, &init_net)) {
-#ifdef CONFIG_NF_CT_ACCT
- printk(KERN_WARNING "CONFIG_NF_CT_ACCT is deprecated and will be removed soon. Please use\n");
- printk(KERN_WARNING "nf_conntrack.acct=1 kernel parameter, acct=1 nf_conntrack module option or\n");
- printk(KERN_WARNING "sysctl net.netfilter.nf_conntrack_acct=1 to enable it.\n");
-#endif
-
ret = nf_ct_extend_register(&acct_extend);
if (ret < 0) {
printk(KERN_ERR "nf_conntrack_acct: Unable to register extension\n");
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index eeeb8bc73982..df3eedb142ff 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -62,8 +62,8 @@ EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);
unsigned int nf_conntrack_max __read_mostly;
EXPORT_SYMBOL_GPL(nf_conntrack_max);
-struct nf_conn nf_conntrack_untracked __read_mostly;
-EXPORT_SYMBOL_GPL(nf_conntrack_untracked);
+DEFINE_PER_CPU(struct nf_conn, nf_conntrack_untracked);
+EXPORT_PER_CPU_SYMBOL(nf_conntrack_untracked);
static int nf_conntrack_hash_rnd_initted;
static unsigned int nf_conntrack_hash_rnd;
@@ -619,9 +619,7 @@ struct nf_conn *nf_conntrack_alloc(struct net *net, u16 zone,
ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev = NULL;
/* Don't set timer yet: wait for confirmation */
setup_timer(&ct->timeout, death_by_timeout, (unsigned long)ct);
-#ifdef CONFIG_NET_NS
- ct->ct_net = net;
-#endif
+ write_pnet(&ct->ct_net, net);
#ifdef CONFIG_NF_CONNTRACK_ZONES
if (zone) {
struct nf_conntrack_zone *nf_ct_zone;
@@ -968,8 +966,7 @@ acct:
if (acct) {
spin_lock_bh(&ct->lock);
acct[CTINFO2DIR(ctinfo)].packets++;
- acct[CTINFO2DIR(ctinfo)].bytes +=
- skb->len - skb_network_offset(skb);
+ acct[CTINFO2DIR(ctinfo)].bytes += skb->len;
spin_unlock_bh(&ct->lock);
}
}
@@ -1183,10 +1180,21 @@ static void nf_ct_release_dying_list(struct net *net)
spin_unlock_bh(&nf_conntrack_lock);
}
+static int untrack_refs(void)
+{
+ int cnt = 0, cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct nf_conn *ct = &per_cpu(nf_conntrack_untracked, cpu);
+
+ cnt += atomic_read(&ct->ct_general.use) - 1;
+ }
+ return cnt;
+}
+
static void nf_conntrack_cleanup_init_net(void)
{
- /* wait until all references to nf_conntrack_untracked are dropped */
- while (atomic_read(&nf_conntrack_untracked.ct_general.use) > 1)
+ while (untrack_refs() > 0)
schedule();
nf_conntrack_helper_fini();
@@ -1321,10 +1329,19 @@ EXPORT_SYMBOL_GPL(nf_conntrack_set_hashsize);
module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint,
&nf_conntrack_htable_size, 0600);
+void nf_ct_untracked_status_or(unsigned long bits)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ per_cpu(nf_conntrack_untracked, cpu).status |= bits;
+}
+EXPORT_SYMBOL_GPL(nf_ct_untracked_status_or);
+
static int nf_conntrack_init_init_net(void)
{
int max_factor = 8;
- int ret;
+ int ret, cpu;
/* Idea from tcp.c: use 1/16384 of memory. On i386: 32MB
* machine has 512 buckets. >= 1GB machines have 16384 buckets. */
@@ -1363,13 +1380,13 @@ static int nf_conntrack_init_init_net(void)
goto err_extend;
#endif
/* Set up fake conntrack: to never be deleted, not in any hashes */
-#ifdef CONFIG_NET_NS
- nf_conntrack_untracked.ct_net = &init_net;
-#endif
- atomic_set(&nf_conntrack_untracked.ct_general.use, 1);
+ for_each_possible_cpu(cpu) {
+ struct nf_conn *ct = &per_cpu(nf_conntrack_untracked, cpu);
+ write_pnet(&ct->ct_net, &init_net);
+ atomic_set(&ct->ct_general.use, 1);
+ }
/* - and look it like as a confirmed connection */
- set_bit(IPS_CONFIRMED_BIT, &nf_conntrack_untracked.status);
-
+ nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED);
return 0;
#ifdef CONFIG_NF_CONNTRACK_ZONES
diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c
index fdc8fb4ae10f..7dcf7a404190 100644
--- a/net/netfilter/nf_conntrack_extend.c
+++ b/net/netfilter/nf_conntrack_extend.c
@@ -23,9 +23,10 @@ void __nf_ct_ext_destroy(struct nf_conn *ct)
{
unsigned int i;
struct nf_ct_ext_type *t;
+ struct nf_ct_ext *ext = ct->ext;
for (i = 0; i < NF_CT_EXT_NUM; i++) {
- if (!nf_ct_ext_exist(ct, i))
+ if (!__nf_ct_ext_exist(ext, i))
continue;
rcu_read_lock();
@@ -73,44 +74,45 @@ static void __nf_ct_ext_free_rcu(struct rcu_head *head)
void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp)
{
- struct nf_ct_ext *new;
+ struct nf_ct_ext *old, *new;
int i, newlen, newoff;
struct nf_ct_ext_type *t;
/* Conntrack must not be confirmed to avoid races on reallocation. */
NF_CT_ASSERT(!nf_ct_is_confirmed(ct));
- if (!ct->ext)
+ old = ct->ext;
+ if (!old)
return nf_ct_ext_create(&ct->ext, id, gfp);
- if (nf_ct_ext_exist(ct, id))
+ if (__nf_ct_ext_exist(old, id))
return NULL;
rcu_read_lock();
t = rcu_dereference(nf_ct_ext_types[id]);
BUG_ON(t == NULL);
- newoff = ALIGN(ct->ext->len, t->align);
+ newoff = ALIGN(old->len, t->align);
newlen = newoff + t->len;
rcu_read_unlock();
- new = __krealloc(ct->ext, newlen, gfp);
+ new = __krealloc(old, newlen, gfp);
if (!new)
return NULL;
- if (new != ct->ext) {
+ if (new != old) {
for (i = 0; i < NF_CT_EXT_NUM; i++) {
- if (!nf_ct_ext_exist(ct, i))
+ if (!__nf_ct_ext_exist(old, i))
continue;
rcu_read_lock();
t = rcu_dereference(nf_ct_ext_types[i]);
if (t && t->move)
t->move((void *)new + new->offset[i],
- (void *)ct->ext + ct->ext->offset[i]);
+ (void *)old + old->offset[i]);
rcu_read_unlock();
}
- call_rcu(&ct->ext->rcu, __nf_ct_ext_free_rcu);
+ call_rcu(&old->rcu, __nf_ct_ext_free_rcu);
ct->ext = new;
}
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index 6eaee7c8a337..b969025cf82f 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -734,11 +734,11 @@ static int callforward_do_filter(const union nf_inet_addr *src,
if (!afinfo->route((struct dst_entry **)&rt1, &fl1)) {
if (!afinfo->route((struct dst_entry **)&rt2, &fl2)) {
if (rt1->rt_gateway == rt2->rt_gateway &&
- rt1->u.dst.dev == rt2->u.dst.dev)
+ rt1->dst.dev == rt2->dst.dev)
ret = 1;
- dst_release(&rt2->u.dst);
+ dst_release(&rt2->dst);
}
- dst_release(&rt1->u.dst);
+ dst_release(&rt1->dst);
}
break;
}
@@ -753,11 +753,11 @@ static int callforward_do_filter(const union nf_inet_addr *src,
if (!afinfo->route((struct dst_entry **)&rt2, &fl2)) {
if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway,
sizeof(rt1->rt6i_gateway)) &&
- rt1->u.dst.dev == rt2->u.dst.dev)
+ rt1->dst.dev == rt2->dst.dev)
ret = 1;
- dst_release(&rt2->u.dst);
+ dst_release(&rt2->dst);
}
- dst_release(&rt1->u.dst);
+ dst_release(&rt1->dst);
}
break;
}
diff --git a/net/netfilter/nf_conntrack_netbios_ns.c b/net/netfilter/nf_conntrack_netbios_ns.c
index 497b2224536f..aadde018a072 100644
--- a/net/netfilter/nf_conntrack_netbios_ns.c
+++ b/net/netfilter/nf_conntrack_netbios_ns.c
@@ -61,7 +61,7 @@ static int help(struct sk_buff *skb, unsigned int protoff,
goto out;
rcu_read_lock();
- in_dev = __in_dev_get_rcu(rt->u.dst.dev);
+ in_dev = __in_dev_get_rcu(rt->dst.dev);
if (in_dev != NULL) {
for_primary_ifa(in_dev) {
if (ifa->ifa_broadcast == iph->daddr) {
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index c42ff6aa441d..5bae1cd15eea 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -480,7 +480,7 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
int err;
/* ignore our fake conntrack entry */
- if (ct == &nf_conntrack_untracked)
+ if (nf_ct_is_untracked(ct))
return 0;
if (events & (1 << IPCT_DESTROY)) {
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 9dd8cd4fb6e6..c4c885dca3bd 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -585,8 +585,16 @@ static bool tcp_in_window(const struct nf_conn *ct,
* Let's try to use the data from the packet.
*/
sender->td_end = end;
+ win <<= sender->td_scale;
sender->td_maxwin = (win == 0 ? 1 : win);
sender->td_maxend = end + sender->td_maxwin;
+ /*
+ * We haven't seen traffic in the other direction yet
+ * but we have to tweak window tracking to pass III
+ * and IV until that happens.
+ */
+ if (receiver->td_maxwin == 0)
+ receiver->td_end = receiver->td_maxend = sack;
}
} else if (((state->state == TCP_CONNTRACK_SYN_SENT
&& dir == IP_CT_DIR_ORIGINAL)
@@ -680,7 +688,7 @@ static bool tcp_in_window(const struct nf_conn *ct,
/*
* Update receiver data.
*/
- if (after(end, sender->td_maxend))
+ if (receiver->td_maxwin != 0 && after(end, sender->td_maxend))
receiver->td_maxwin += end - sender->td_maxend;
if (after(sack + win, receiver->td_maxend - 1)) {
receiver->td_maxend = sack + win;
@@ -736,27 +744,19 @@ static bool tcp_in_window(const struct nf_conn *ct,
return res;
}
-#define TH_FIN 0x01
-#define TH_SYN 0x02
-#define TH_RST 0x04
-#define TH_PUSH 0x08
-#define TH_ACK 0x10
-#define TH_URG 0x20
-#define TH_ECE 0x40
-#define TH_CWR 0x80
-
/* table of valid flag combinations - PUSH, ECE and CWR are always valid */
-static const u8 tcp_valid_flags[(TH_FIN|TH_SYN|TH_RST|TH_ACK|TH_URG) + 1] =
+static const u8 tcp_valid_flags[(TCPHDR_FIN|TCPHDR_SYN|TCPHDR_RST|TCPHDR_ACK|
+ TCPHDR_URG) + 1] =
{
- [TH_SYN] = 1,
- [TH_SYN|TH_URG] = 1,
- [TH_SYN|TH_ACK] = 1,
- [TH_RST] = 1,
- [TH_RST|TH_ACK] = 1,
- [TH_FIN|TH_ACK] = 1,
- [TH_FIN|TH_ACK|TH_URG] = 1,
- [TH_ACK] = 1,
- [TH_ACK|TH_URG] = 1,
+ [TCPHDR_SYN] = 1,
+ [TCPHDR_SYN|TCPHDR_URG] = 1,
+ [TCPHDR_SYN|TCPHDR_ACK] = 1,
+ [TCPHDR_RST] = 1,
+ [TCPHDR_RST|TCPHDR_ACK] = 1,
+ [TCPHDR_FIN|TCPHDR_ACK] = 1,
+ [TCPHDR_FIN|TCPHDR_ACK|TCPHDR_URG] = 1,
+ [TCPHDR_ACK] = 1,
+ [TCPHDR_ACK|TCPHDR_URG] = 1,
};
/* Protect conntrack agaist broken packets. Code taken from ipt_unclean.c. */
@@ -803,7 +803,7 @@ static int tcp_error(struct net *net, struct nf_conn *tmpl,
}
/* Check TCP flags. */
- tcpflags = (((u_int8_t *)th)[13] & ~(TH_ECE|TH_CWR|TH_PUSH));
+ tcpflags = (tcp_flag_byte(th) & ~(TCPHDR_ECE|TCPHDR_CWR|TCPHDR_PSH));
if (!tcp_valid_flags[tcpflags]) {
if (LOG_INVALID(net, IPPROTO_TCP))
nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index fc9a211e629e..6a1572b0ab41 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -66,9 +66,10 @@ struct nfulnl_instance {
u_int16_t group_num; /* number of this queue */
u_int16_t flags;
u_int8_t copy_mode;
+ struct rcu_head rcu;
};
-static DEFINE_RWLOCK(instances_lock);
+static DEFINE_SPINLOCK(instances_lock);
static atomic_t global_seq;
#define INSTANCE_BUCKETS 16
@@ -88,7 +89,7 @@ __instance_lookup(u_int16_t group_num)
struct nfulnl_instance *inst;
head = &instance_table[instance_hashfn(group_num)];
- hlist_for_each_entry(inst, pos, head, hlist) {
+ hlist_for_each_entry_rcu(inst, pos, head, hlist) {
if (inst->group_num == group_num)
return inst;
}
@@ -106,22 +107,26 @@ instance_lookup_get(u_int16_t group_num)
{
struct nfulnl_instance *inst;
- read_lock_bh(&instances_lock);
+ rcu_read_lock_bh();
inst = __instance_lookup(group_num);
- if (inst)
- instance_get(inst);
- read_unlock_bh(&instances_lock);
+ if (inst && !atomic_inc_not_zero(&inst->use))
+ inst = NULL;
+ rcu_read_unlock_bh();
return inst;
}
+static void nfulnl_instance_free_rcu(struct rcu_head *head)
+{
+ kfree(container_of(head, struct nfulnl_instance, rcu));
+ module_put(THIS_MODULE);
+}
+
static void
instance_put(struct nfulnl_instance *inst)
{
- if (inst && atomic_dec_and_test(&inst->use)) {
- kfree(inst);
- module_put(THIS_MODULE);
- }
+ if (inst && atomic_dec_and_test(&inst->use))
+ call_rcu_bh(&inst->rcu, nfulnl_instance_free_rcu);
}
static void nfulnl_timer(unsigned long data);
@@ -132,7 +137,7 @@ instance_create(u_int16_t group_num, int pid)
struct nfulnl_instance *inst;
int err;
- write_lock_bh(&instances_lock);
+ spin_lock_bh(&instances_lock);
if (__instance_lookup(group_num)) {
err = -EEXIST;
goto out_unlock;
@@ -166,32 +171,37 @@ instance_create(u_int16_t group_num, int pid)
inst->copy_mode = NFULNL_COPY_PACKET;
inst->copy_range = NFULNL_COPY_RANGE_MAX;
- hlist_add_head(&inst->hlist,
+ hlist_add_head_rcu(&inst->hlist,
&instance_table[instance_hashfn(group_num)]);
- write_unlock_bh(&instances_lock);
+ spin_unlock_bh(&instances_lock);
return inst;
out_unlock:
- write_unlock_bh(&instances_lock);
+ spin_unlock_bh(&instances_lock);
return ERR_PTR(err);
}
static void __nfulnl_flush(struct nfulnl_instance *inst);
+/* called with BH disabled */
static void
__instance_destroy(struct nfulnl_instance *inst)
{
/* first pull it out of the global list */
- hlist_del(&inst->hlist);
+ hlist_del_rcu(&inst->hlist);
/* then flush all pending packets from skb */
- spin_lock_bh(&inst->lock);
+ spin_lock(&inst->lock);
+
+ /* lockless readers wont be able to use us */
+ inst->copy_mode = NFULNL_COPY_DISABLED;
+
if (inst->skb)
__nfulnl_flush(inst);
- spin_unlock_bh(&inst->lock);
+ spin_unlock(&inst->lock);
/* and finally put the refcount */
instance_put(inst);
@@ -200,9 +210,9 @@ __instance_destroy(struct nfulnl_instance *inst)
static inline void
instance_destroy(struct nfulnl_instance *inst)
{
- write_lock_bh(&instances_lock);
+ spin_lock_bh(&instances_lock);
__instance_destroy(inst);
- write_unlock_bh(&instances_lock);
+ spin_unlock_bh(&instances_lock);
}
static int
@@ -403,8 +413,9 @@ __build_packet_message(struct nfulnl_instance *inst,
NLA_PUT_BE32(inst->skb, NFULA_IFINDEX_PHYSINDEV,
htonl(indev->ifindex));
/* this is the bridge group "brX" */
+ /* rcu_read_lock()ed by nf_hook_slow or nf_log_packet */
NLA_PUT_BE32(inst->skb, NFULA_IFINDEX_INDEV,
- htonl(indev->br_port->br->dev->ifindex));
+ htonl(br_port_get_rcu(indev)->br->dev->ifindex));
} else {
/* Case 2: indev is bridge group, we need to look for
* physical device (when called from ipv4) */
@@ -430,8 +441,9 @@ __build_packet_message(struct nfulnl_instance *inst,
NLA_PUT_BE32(inst->skb, NFULA_IFINDEX_PHYSOUTDEV,
htonl(outdev->ifindex));
/* this is the bridge group "brX" */
+ /* rcu_read_lock()ed by nf_hook_slow or nf_log_packet */
NLA_PUT_BE32(inst->skb, NFULA_IFINDEX_OUTDEV,
- htonl(outdev->br_port->br->dev->ifindex));
+ htonl(br_port_get_rcu(outdev)->br->dev->ifindex));
} else {
/* Case 2: indev is a bridge group, we need to look
* for physical device (when called from ipv4) */
@@ -619,6 +631,7 @@ nfulnl_log_packet(u_int8_t pf,
size += nla_total_size(data_len);
break;
+ case NFULNL_COPY_DISABLED:
default:
goto unlock_and_release;
}
@@ -672,7 +685,7 @@ nfulnl_rcv_nl_event(struct notifier_block *this,
int i;
/* destroy all instances for this pid */
- write_lock_bh(&instances_lock);
+ spin_lock_bh(&instances_lock);
for (i = 0; i < INSTANCE_BUCKETS; i++) {
struct hlist_node *tmp, *t2;
struct nfulnl_instance *inst;
@@ -684,7 +697,7 @@ nfulnl_rcv_nl_event(struct notifier_block *this,
__instance_destroy(inst);
}
}
- write_unlock_bh(&instances_lock);
+ spin_unlock_bh(&instances_lock);
}
return NOTIFY_DONE;
}
@@ -861,19 +874,19 @@ static struct hlist_node *get_first(struct iter_state *st)
for (st->bucket = 0; st->bucket < INSTANCE_BUCKETS; st->bucket++) {
if (!hlist_empty(&instance_table[st->bucket]))
- return instance_table[st->bucket].first;
+ return rcu_dereference_bh(instance_table[st->bucket].first);
}
return NULL;
}
static struct hlist_node *get_next(struct iter_state *st, struct hlist_node *h)
{
- h = h->next;
+ h = rcu_dereference_bh(h->next);
while (!h) {
if (++st->bucket >= INSTANCE_BUCKETS)
return NULL;
- h = instance_table[st->bucket].first;
+ h = rcu_dereference_bh(instance_table[st->bucket].first);
}
return h;
}
@@ -890,9 +903,9 @@ static struct hlist_node *get_idx(struct iter_state *st, loff_t pos)
}
static void *seq_start(struct seq_file *seq, loff_t *pos)
- __acquires(instances_lock)
+ __acquires(rcu_bh)
{
- read_lock_bh(&instances_lock);
+ rcu_read_lock_bh();
return get_idx(seq->private, *pos);
}
@@ -903,9 +916,9 @@ static void *seq_next(struct seq_file *s, void *v, loff_t *pos)
}
static void seq_stop(struct seq_file *s, void *v)
- __releases(instances_lock)
+ __releases(rcu_bh)
{
- read_unlock_bh(&instances_lock);
+ rcu_read_unlock_bh();
}
static int seq_show(struct seq_file *s, void *v)
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 12e1ab37fcd8..68e67d19724d 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -46,17 +46,19 @@ struct nfqnl_instance {
int peer_pid;
unsigned int queue_maxlen;
unsigned int copy_range;
- unsigned int queue_total;
unsigned int queue_dropped;
unsigned int queue_user_dropped;
- unsigned int id_sequence; /* 'sequence' of pkt ids */
u_int16_t queue_num; /* number of this queue */
u_int8_t copy_mode;
-
- spinlock_t lock;
-
+/*
+ * Following fields are dirtied for each queued packet,
+ * keep them in same cache line if possible.
+ */
+ spinlock_t lock;
+ unsigned int queue_total;
+ atomic_t id_sequence; /* 'sequence' of pkt ids */
struct list_head queue_list; /* packets in queue */
};
@@ -238,32 +240,24 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue,
outdev = entry->outdev;
- spin_lock_bh(&queue->lock);
-
- switch ((enum nfqnl_config_mode)queue->copy_mode) {
+ switch ((enum nfqnl_config_mode)ACCESS_ONCE(queue->copy_mode)) {
case NFQNL_COPY_META:
case NFQNL_COPY_NONE:
break;
case NFQNL_COPY_PACKET:
if (entskb->ip_summed == CHECKSUM_PARTIAL &&
- skb_checksum_help(entskb)) {
- spin_unlock_bh(&queue->lock);
+ skb_checksum_help(entskb))
return NULL;
- }
- if (queue->copy_range == 0
- || queue->copy_range > entskb->len)
+
+ data_len = ACCESS_ONCE(queue->copy_range);
+ if (data_len == 0 || data_len > entskb->len)
data_len = entskb->len;
- else
- data_len = queue->copy_range;
size += nla_total_size(data_len);
break;
}
- entry->id = queue->id_sequence++;
-
- spin_unlock_bh(&queue->lock);
skb = alloc_skb(size, GFP_ATOMIC);
if (!skb)
@@ -278,6 +272,7 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue,
nfmsg->version = NFNETLINK_V0;
nfmsg->res_id = htons(queue->queue_num);
+ entry->id = atomic_inc_return(&queue->id_sequence);
pmsg.packet_id = htonl(entry->id);
pmsg.hw_protocol = entskb->protocol;
pmsg.hook = entry->hook;
@@ -296,8 +291,9 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue,
NLA_PUT_BE32(skb, NFQA_IFINDEX_PHYSINDEV,
htonl(indev->ifindex));
/* this is the bridge group "brX" */
+ /* rcu_read_lock()ed by __nf_queue */
NLA_PUT_BE32(skb, NFQA_IFINDEX_INDEV,
- htonl(indev->br_port->br->dev->ifindex));
+ htonl(br_port_get_rcu(indev)->br->dev->ifindex));
} else {
/* Case 2: indev is bridge group, we need to look for
* physical device (when called from ipv4) */
@@ -321,8 +317,9 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue,
NLA_PUT_BE32(skb, NFQA_IFINDEX_PHYSOUTDEV,
htonl(outdev->ifindex));
/* this is the bridge group "brX" */
+ /* rcu_read_lock()ed by __nf_queue */
NLA_PUT_BE32(skb, NFQA_IFINDEX_OUTDEV,
- htonl(outdev->br_port->br->dev->ifindex));
+ htonl(br_port_get_rcu(outdev)->br->dev->ifindex));
} else {
/* Case 2: outdev is bridge group, we need to look for
* physical output device (when called from ipv4) */
@@ -866,7 +863,7 @@ static int seq_show(struct seq_file *s, void *v)
inst->peer_pid, inst->queue_total,
inst->copy_mode, inst->copy_range,
inst->queue_dropped, inst->queue_user_dropped,
- inst->id_sequence, 1);
+ atomic_read(&inst->id_sequence), 1);
}
static const struct seq_operations nfqnl_seq_ops = {
diff --git a/net/netfilter/xt_CHECKSUM.c b/net/netfilter/xt_CHECKSUM.c
new file mode 100644
index 000000000000..0f642ef8cd26
--- /dev/null
+++ b/net/netfilter/xt_CHECKSUM.c
@@ -0,0 +1,70 @@
+/* iptables module for the packet checksum mangling
+ *
+ * (C) 2002 by Harald Welte <laforge@netfilter.org>
+ * (C) 2010 Red Hat, Inc.
+ *
+ * Author: Michael S. Tsirkin <mst@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.
+*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/skbuff.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_CHECKSUM.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Michael S. Tsirkin <mst@redhat.com>");
+MODULE_DESCRIPTION("Xtables: checksum modification");
+MODULE_ALIAS("ipt_CHECKSUM");
+MODULE_ALIAS("ip6t_CHECKSUM");
+
+static unsigned int
+checksum_tg(struct sk_buff *skb, const struct xt_action_param *par)
+{
+ if (skb->ip_summed == CHECKSUM_PARTIAL)
+ skb_checksum_help(skb);
+
+ return XT_CONTINUE;
+}
+
+static int checksum_tg_check(const struct xt_tgchk_param *par)
+{
+ const struct xt_CHECKSUM_info *einfo = par->targinfo;
+
+ if (einfo->operation & ~XT_CHECKSUM_OP_FILL) {
+ pr_info("unsupported CHECKSUM operation %x\n", einfo->operation);
+ return -EINVAL;
+ }
+ if (!einfo->operation) {
+ pr_info("no CHECKSUM operation enabled\n");
+ return -EINVAL;
+ }
+ return 0;
+}
+
+static struct xt_target checksum_tg_reg __read_mostly = {
+ .name = "CHECKSUM",
+ .family = NFPROTO_UNSPEC,
+ .target = checksum_tg,
+ .targetsize = sizeof(struct xt_CHECKSUM_info),
+ .table = "mangle",
+ .checkentry = checksum_tg_check,
+ .me = THIS_MODULE,
+};
+
+static int __init checksum_tg_init(void)
+{
+ return xt_register_target(&checksum_tg_reg);
+}
+
+static void __exit checksum_tg_exit(void)
+{
+ xt_unregister_target(&checksum_tg_reg);
+}
+
+module_init(checksum_tg_init);
+module_exit(checksum_tg_exit);
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 562bf3266e04..0cb6053f02fd 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -67,7 +67,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par)
return -EINVAL;
if (info->flags & XT_CT_NOTRACK) {
- ct = &nf_conntrack_untracked;
+ ct = nf_ct_untracked_get();
atomic_inc(&ct->ct_general.use);
goto out;
}
@@ -132,7 +132,7 @@ static void xt_ct_tg_destroy(const struct xt_tgdtor_param *par)
struct nf_conn *ct = info->ct;
struct nf_conn_help *help;
- if (ct != &nf_conntrack_untracked) {
+ if (!nf_ct_is_untracked(ct)) {
help = nfct_help(ct);
if (help)
module_put(help->helper->me);
diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
new file mode 100644
index 000000000000..be1f22e13545
--- /dev/null
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -0,0 +1,315 @@
+/*
+ * linux/net/netfilter/xt_IDLETIMER.c
+ *
+ * Netfilter module to trigger a timer when packet matches.
+ * After timer expires a kevent will be sent.
+ *
+ * Copyright (C) 2004, 2010 Nokia Corporation
+ * Written by Timo Teras <ext-timo.teras@nokia.com>
+ *
+ * Converted to x_tables and reworked for upstream inclusion
+ * by Luciano Coelho <luciano.coelho@nokia.com>
+ *
+ * Contact: Luciano Coelho <luciano.coelho@nokia.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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+ * 02110-1301 USA
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/timer.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_IDLETIMER.h>
+#include <linux/kdev_t.h>
+#include <linux/kobject.h>
+#include <linux/workqueue.h>
+#include <linux/sysfs.h>
+
+struct idletimer_tg_attr {
+ struct attribute attr;
+ ssize_t (*show)(struct kobject *kobj,
+ struct attribute *attr, char *buf);
+};
+
+struct idletimer_tg {
+ struct list_head entry;
+ struct timer_list timer;
+ struct work_struct work;
+
+ struct kobject *kobj;
+ struct idletimer_tg_attr attr;
+
+ unsigned int refcnt;
+};
+
+static LIST_HEAD(idletimer_tg_list);
+static DEFINE_MUTEX(list_mutex);
+
+static struct kobject *idletimer_tg_kobj;
+
+static
+struct idletimer_tg *__idletimer_tg_find_by_label(const char *label)
+{
+ struct idletimer_tg *entry;
+
+ BUG_ON(!label);
+
+ list_for_each_entry(entry, &idletimer_tg_list, entry) {
+ if (!strcmp(label, entry->attr.attr.name))
+ return entry;
+ }
+
+ return NULL;
+}
+
+static ssize_t idletimer_tg_show(struct kobject *kobj, struct attribute *attr,
+ char *buf)
+{
+ struct idletimer_tg *timer;
+ unsigned long expires = 0;
+
+ mutex_lock(&list_mutex);
+
+ timer = __idletimer_tg_find_by_label(attr->name);
+ if (timer)
+ expires = timer->timer.expires;
+
+ mutex_unlock(&list_mutex);
+
+ if (time_after(expires, jiffies))
+ return sprintf(buf, "%u\n",
+ jiffies_to_msecs(expires - jiffies) / 1000);
+
+ return sprintf(buf, "0\n");
+}
+
+static void idletimer_tg_work(struct work_struct *work)
+{
+ struct idletimer_tg *timer = container_of(work, struct idletimer_tg,
+ work);
+
+ sysfs_notify(idletimer_tg_kobj, NULL, timer->attr.attr.name);
+}
+
+static void idletimer_tg_expired(unsigned long data)
+{
+ struct idletimer_tg *timer = (struct idletimer_tg *) data;
+
+ pr_debug("timer %s expired\n", timer->attr.attr.name);
+
+ schedule_work(&timer->work);
+}
+
+static int idletimer_tg_create(struct idletimer_tg_info *info)
+{
+ int ret;
+
+ info->timer = kmalloc(sizeof(*info->timer), GFP_KERNEL);
+ if (!info->timer) {
+ pr_debug("couldn't alloc timer\n");
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ info->timer->attr.attr.name = kstrdup(info->label, GFP_KERNEL);
+ if (!info->timer->attr.attr.name) {
+ pr_debug("couldn't alloc attribute name\n");
+ ret = -ENOMEM;
+ goto out_free_timer;
+ }
+ info->timer->attr.attr.mode = S_IRUGO;
+ info->timer->attr.show = idletimer_tg_show;
+
+ ret = sysfs_create_file(idletimer_tg_kobj, &info->timer->attr.attr);
+ if (ret < 0) {
+ pr_debug("couldn't add file to sysfs");
+ goto out_free_attr;
+ }
+
+ list_add(&info->timer->entry, &idletimer_tg_list);
+
+ setup_timer(&info->timer->timer, idletimer_tg_expired,
+ (unsigned long) info->timer);
+ info->timer->refcnt = 1;
+
+ mod_timer(&info->timer->timer,
+ msecs_to_jiffies(info->timeout * 1000) + jiffies);
+
+ INIT_WORK(&info->timer->work, idletimer_tg_work);
+
+ return 0;
+
+out_free_attr:
+ kfree(info->timer->attr.attr.name);
+out_free_timer:
+ kfree(info->timer);
+out:
+ return ret;
+}
+
+/*
+ * The actual xt_tables plugin.
+ */
+static unsigned int idletimer_tg_target(struct sk_buff *skb,
+ const struct xt_action_param *par)
+{
+ const struct idletimer_tg_info *info = par->targinfo;
+
+ pr_debug("resetting timer %s, timeout period %u\n",
+ info->label, info->timeout);
+
+ BUG_ON(!info->timer);
+
+ mod_timer(&info->timer->timer,
+ msecs_to_jiffies(info->timeout * 1000) + jiffies);
+
+ return XT_CONTINUE;
+}
+
+static int idletimer_tg_checkentry(const struct xt_tgchk_param *par)
+{
+ struct idletimer_tg_info *info = par->targinfo;
+ int ret;
+
+ pr_debug("checkentry targinfo%s\n", info->label);
+
+ if (info->timeout == 0) {
+ pr_debug("timeout value is zero\n");
+ return -EINVAL;
+ }
+
+ if (info->label[0] == '\0' ||
+ strnlen(info->label,
+ MAX_IDLETIMER_LABEL_SIZE) == MAX_IDLETIMER_LABEL_SIZE) {
+ pr_debug("label is empty or not nul-terminated\n");
+ return -EINVAL;
+ }
+
+ mutex_lock(&list_mutex);
+
+ info->timer = __idletimer_tg_find_by_label(info->label);
+ if (info->timer) {
+ info->timer->refcnt++;
+ mod_timer(&info->timer->timer,
+ msecs_to_jiffies(info->timeout * 1000) + jiffies);
+
+ pr_debug("increased refcnt of timer %s to %u\n",
+ info->label, info->timer->refcnt);
+ } else {
+ ret = idletimer_tg_create(info);
+ if (ret < 0) {
+ pr_debug("failed to create timer\n");
+ mutex_unlock(&list_mutex);
+ return ret;
+ }
+ }
+
+ mutex_unlock(&list_mutex);
+ return 0;
+}
+
+static void idletimer_tg_destroy(const struct xt_tgdtor_param *par)
+{
+ const struct idletimer_tg_info *info = par->targinfo;
+
+ pr_debug("destroy targinfo %s\n", info->label);
+
+ mutex_lock(&list_mutex);
+
+ if (--info->timer->refcnt == 0) {
+ pr_debug("deleting timer %s\n", info->label);
+
+ list_del(&info->timer->entry);
+ del_timer_sync(&info->timer->timer);
+ sysfs_remove_file(idletimer_tg_kobj, &info->timer->attr.attr);
+ kfree(info->timer->attr.attr.name);
+ kfree(info->timer);
+ } else {
+ pr_debug("decreased refcnt of timer %s to %u\n",
+ info->label, info->timer->refcnt);
+ }
+
+ mutex_unlock(&list_mutex);
+}
+
+static struct xt_target idletimer_tg __read_mostly = {
+ .name = "IDLETIMER",
+ .family = NFPROTO_UNSPEC,
+ .target = idletimer_tg_target,
+ .targetsize = sizeof(struct idletimer_tg_info),
+ .checkentry = idletimer_tg_checkentry,
+ .destroy = idletimer_tg_destroy,
+ .me = THIS_MODULE,
+};
+
+static struct class *idletimer_tg_class;
+
+static struct device *idletimer_tg_device;
+
+static int __init idletimer_tg_init(void)
+{
+ int err;
+
+ idletimer_tg_class = class_create(THIS_MODULE, "xt_idletimer");
+ err = PTR_ERR(idletimer_tg_class);
+ if (IS_ERR(idletimer_tg_class)) {
+ pr_debug("couldn't register device class\n");
+ goto out;
+ }
+
+ idletimer_tg_device = device_create(idletimer_tg_class, NULL,
+ MKDEV(0, 0), NULL, "timers");
+ err = PTR_ERR(idletimer_tg_device);
+ if (IS_ERR(idletimer_tg_device)) {
+ pr_debug("couldn't register system device\n");
+ goto out_class;
+ }
+
+ idletimer_tg_kobj = &idletimer_tg_device->kobj;
+
+ err = xt_register_target(&idletimer_tg);
+ if (err < 0) {
+ pr_debug("couldn't register xt target\n");
+ goto out_dev;
+ }
+
+ return 0;
+out_dev:
+ device_destroy(idletimer_tg_class, MKDEV(0, 0));
+out_class:
+ class_destroy(idletimer_tg_class);
+out:
+ return err;
+}
+
+static void __exit idletimer_tg_exit(void)
+{
+ xt_unregister_target(&idletimer_tg);
+
+ device_destroy(idletimer_tg_class, MKDEV(0, 0));
+ class_destroy(idletimer_tg_class);
+}
+
+module_init(idletimer_tg_init);
+module_exit(idletimer_tg_exit);
+
+MODULE_AUTHOR("Timo Teras <ext-timo.teras@nokia.com>");
+MODULE_AUTHOR("Luciano Coelho <luciano.coelho@nokia.com>");
+MODULE_DESCRIPTION("Xtables: idle time monitor");
+MODULE_LICENSE("GPL v2");
diff --git a/net/netfilter/xt_NOTRACK.c b/net/netfilter/xt_NOTRACK.c
index 512b9123252f..9d782181b6c8 100644
--- a/net/netfilter/xt_NOTRACK.c
+++ b/net/netfilter/xt_NOTRACK.c
@@ -23,7 +23,7 @@ notrack_tg(struct sk_buff *skb, const struct xt_action_param *par)
If there is a real ct entry correspondig to this packet,
it'll hang aroun till timing out. We don't deal with it
for performance reasons. JK */
- skb->nfct = &nf_conntrack_untracked.ct_general;
+ skb->nfct = &nf_ct_untracked_get()->ct_general;
skb->nfctinfo = IP_CT_NEW;
nf_conntrack_get(skb->nfct);
diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
index 69c01e10f8af..de079abd5bc8 100644
--- a/net/netfilter/xt_RATEEST.c
+++ b/net/netfilter/xt_RATEEST.c
@@ -60,13 +60,22 @@ struct xt_rateest *xt_rateest_lookup(const char *name)
}
EXPORT_SYMBOL_GPL(xt_rateest_lookup);
+static void xt_rateest_free_rcu(struct rcu_head *head)
+{
+ kfree(container_of(head, struct xt_rateest, rcu));
+}
+
void xt_rateest_put(struct xt_rateest *est)
{
mutex_lock(&xt_rateest_mutex);
if (--est->refcnt == 0) {
hlist_del(&est->list);
gen_kill_estimator(&est->bstats, &est->rstats);
- kfree(est);
+ /*
+ * gen_estimator est_timer() might access est->lock or bstats,
+ * wait a RCU grace period before freeing 'est'
+ */
+ call_rcu(&est->rcu, xt_rateest_free_rcu);
}
mutex_unlock(&xt_rateest_mutex);
}
@@ -179,6 +188,7 @@ static int __init xt_rateest_tg_init(void)
static void __exit xt_rateest_tg_fini(void)
{
xt_unregister_target(&xt_rateest_tg_reg);
+ rcu_barrier(); /* Wait for completion of call_rcu()'s (xt_rateest_free_rcu) */
}
diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c
index 62ec021fbd50..eb81c380da1b 100644
--- a/net/netfilter/xt_TCPMSS.c
+++ b/net/netfilter/xt_TCPMSS.c
@@ -165,8 +165,8 @@ static u_int32_t tcpmss_reverse_mtu(const struct sk_buff *skb,
rcu_read_unlock();
if (rt != NULL) {
- mtu = dst_mtu(&rt->u.dst);
- dst_release(&rt->u.dst);
+ mtu = dst_mtu(&rt->dst);
+ dst_release(&rt->dst);
}
return mtu;
}
@@ -220,15 +220,13 @@ tcpmss_tg6(struct sk_buff *skb, const struct xt_action_param *par)
}
#endif
-#define TH_SYN 0x02
-
/* Must specify -p tcp --syn */
static inline bool find_syn_match(const struct xt_entry_match *m)
{
const struct xt_tcp *tcpinfo = (const struct xt_tcp *)m->data;
if (strcmp(m->u.kernel.match->name, "tcp") == 0 &&
- tcpinfo->flg_cmp & TH_SYN &&
+ tcpinfo->flg_cmp & TCPHDR_SYN &&
!(tcpinfo->invflags & XT_TCP_INV_FLAGS))
return true;
diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c
index 859d9fd429c8..22a2d421e7eb 100644
--- a/net/netfilter/xt_TEE.c
+++ b/net/netfilter/xt_TEE.c
@@ -77,8 +77,8 @@ tee_tg_route4(struct sk_buff *skb, const struct xt_tee_tginfo *info)
return false;
skb_dst_drop(skb);
- skb_dst_set(skb, &rt->u.dst);
- skb->dev = rt->u.dst.dev;
+ skb_dst_set(skb, &rt->dst);
+ skb->dev = rt->dst.dev;
skb->protocol = htons(ETH_P_IP);
return true;
}
@@ -104,7 +104,7 @@ tee_tg4(struct sk_buff *skb, const struct xt_action_param *par)
#ifdef WITH_CONNTRACK
/* Avoid counting cloned packets towards the original connection. */
nf_conntrack_put(skb->nfct);
- skb->nfct = &nf_conntrack_untracked.ct_general;
+ skb->nfct = &nf_ct_untracked_get()->ct_general;
skb->nfctinfo = IP_CT_NEW;
nf_conntrack_get(skb->nfct);
#endif
@@ -177,7 +177,7 @@ tee_tg6(struct sk_buff *skb, const struct xt_action_param *par)
#ifdef WITH_CONNTRACK
nf_conntrack_put(skb->nfct);
- skb->nfct = &nf_conntrack_untracked.ct_general;
+ skb->nfct = &nf_ct_untracked_get()->ct_general;
skb->nfctinfo = IP_CT_NEW;
nf_conntrack_get(skb->nfct);
#endif
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index e1a0dedac258..c61294d85fda 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -37,8 +37,10 @@ tproxy_tg(struct sk_buff *skb, const struct xt_action_param *par)
return NF_DROP;
sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol,
- iph->saddr, tgi->laddr ? tgi->laddr : iph->daddr,
- hp->source, tgi->lport ? tgi->lport : hp->dest,
+ iph->saddr,
+ tgi->laddr ? tgi->laddr : iph->daddr,
+ hp->source,
+ tgi->lport ? tgi->lport : hp->dest,
par->in, true);
/* NOTE: assign_sock consumes our sk reference */
diff --git a/net/netfilter/xt_cluster.c b/net/netfilter/xt_cluster.c
index 30b95a1c1c89..f4af1bfafb1c 100644
--- a/net/netfilter/xt_cluster.c
+++ b/net/netfilter/xt_cluster.c
@@ -120,7 +120,7 @@ xt_cluster_mt(const struct sk_buff *skb, struct xt_action_param *par)
if (ct == NULL)
return false;
- if (ct == &nf_conntrack_untracked)
+ if (nf_ct_is_untracked(ct))
return false;
if (ct->master)
diff --git a/net/netfilter/xt_connbytes.c b/net/netfilter/xt_connbytes.c
index 73517835303d..5b138506690e 100644
--- a/net/netfilter/xt_connbytes.c
+++ b/net/netfilter/xt_connbytes.c
@@ -112,6 +112,16 @@ static int connbytes_mt_check(const struct xt_mtchk_param *par)
if (ret < 0)
pr_info("cannot load conntrack support for proto=%u\n",
par->family);
+
+ /*
+ * This filter cannot function correctly unless connection tracking
+ * accounting is enabled, so complain in the hope that someone notices.
+ */
+ if (!nf_ct_acct_enabled(par->net)) {
+ pr_warning("Forcing CT accounting to be enabled\n");
+ nf_ct_set_acct(par->net, true);
+ }
+
return ret;
}
diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c
index 39681f10291c..e536710ad916 100644
--- a/net/netfilter/xt_conntrack.c
+++ b/net/netfilter/xt_conntrack.c
@@ -123,11 +123,12 @@ conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par,
ct = nf_ct_get(skb, &ctinfo);
- if (ct == &nf_conntrack_untracked)
- statebit = XT_CONNTRACK_STATE_UNTRACKED;
- else if (ct != NULL)
- statebit = XT_CONNTRACK_STATE_BIT(ctinfo);
- else
+ if (ct) {
+ if (nf_ct_is_untracked(ct))
+ statebit = XT_CONNTRACK_STATE_UNTRACKED;
+ else
+ statebit = XT_CONNTRACK_STATE_BIT(ctinfo);
+ } else
statebit = XT_CONNTRACK_STATE_INVALID;
if (info->match_flags & XT_CONNTRACK_STATE) {
diff --git a/net/netfilter/xt_cpu.c b/net/netfilter/xt_cpu.c
new file mode 100644
index 000000000000..b39db8a5cbae
--- /dev/null
+++ b/net/netfilter/xt_cpu.c
@@ -0,0 +1,63 @@
+/* Kernel module to match running CPU */
+
+/*
+ * Might be used to distribute connections on several daemons, if
+ * RPS (Remote Packet Steering) is enabled or NIC is multiqueue capable,
+ * each RX queue IRQ affined to one CPU (1:1 mapping)
+ *
+ */
+
+/* (C) 2010 Eric Dumazet
+ *
+ * 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/skbuff.h>
+#include <linux/netfilter/xt_cpu.h>
+#include <linux/netfilter/x_tables.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Eric Dumazet <eric.dumazet@gmail.com>");
+MODULE_DESCRIPTION("Xtables: CPU match");
+
+static int cpu_mt_check(const struct xt_mtchk_param *par)
+{
+ const struct xt_cpu_info *info = par->matchinfo;
+
+ if (info->invert & ~1)
+ return -EINVAL;
+ return 0;
+}
+
+static bool cpu_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ const struct xt_cpu_info *info = par->matchinfo;
+
+ return (info->cpu == smp_processor_id()) ^ info->invert;
+}
+
+static struct xt_match cpu_mt_reg __read_mostly = {
+ .name = "cpu",
+ .revision = 0,
+ .family = NFPROTO_UNSPEC,
+ .checkentry = cpu_mt_check,
+ .match = cpu_mt,
+ .matchsize = sizeof(struct xt_cpu_info),
+ .me = THIS_MODULE,
+};
+
+static int __init cpu_mt_init(void)
+{
+ return xt_register_match(&cpu_mt_reg);
+}
+
+static void __exit cpu_mt_exit(void)
+{
+ xt_unregister_match(&cpu_mt_reg);
+}
+
+module_init(cpu_mt_init);
+module_exit(cpu_mt_exit);
diff --git a/net/netfilter/xt_ipvs.c b/net/netfilter/xt_ipvs.c
new file mode 100644
index 000000000000..7a4d66db95ae
--- /dev/null
+++ b/net/netfilter/xt_ipvs.c
@@ -0,0 +1,189 @@
+/*
+ * xt_ipvs - kernel module to match IPVS connection properties
+ *
+ * Author: Hannes Eder <heder@google.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/spinlock.h>
+#include <linux/skbuff.h>
+#ifdef CONFIG_IP_VS_IPV6
+#include <net/ipv6.h>
+#endif
+#include <linux/ip_vs.h>
+#include <linux/types.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter/xt_ipvs.h>
+#include <net/netfilter/nf_conntrack.h>
+
+#include <net/ip_vs.h>
+
+MODULE_AUTHOR("Hannes Eder <heder@google.com>");
+MODULE_DESCRIPTION("Xtables: match IPVS connection properties");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("ipt_ipvs");
+MODULE_ALIAS("ip6t_ipvs");
+
+/* borrowed from xt_conntrack */
+static bool ipvs_mt_addrcmp(const union nf_inet_addr *kaddr,
+ const union nf_inet_addr *uaddr,
+ const union nf_inet_addr *umask,
+ unsigned int l3proto)
+{
+ if (l3proto == NFPROTO_IPV4)
+ return ((kaddr->ip ^ uaddr->ip) & umask->ip) == 0;
+#ifdef CONFIG_IP_VS_IPV6
+ else if (l3proto == NFPROTO_IPV6)
+ return ipv6_masked_addr_cmp(&kaddr->in6, &umask->in6,
+ &uaddr->in6) == 0;
+#endif
+ else
+ return false;
+}
+
+static bool
+ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+ const struct xt_ipvs_mtinfo *data = par->matchinfo;
+ /* ipvs_mt_check ensures that family is only NFPROTO_IPV[46]. */
+ const u_int8_t family = par->family;
+ struct ip_vs_iphdr iph;
+ struct ip_vs_protocol *pp;
+ struct ip_vs_conn *cp;
+ bool match = true;
+
+ if (data->bitmask == XT_IPVS_IPVS_PROPERTY) {
+ match = skb->ipvs_property ^
+ !!(data->invert & XT_IPVS_IPVS_PROPERTY);
+ goto out;
+ }
+
+ /* other flags than XT_IPVS_IPVS_PROPERTY are set */
+ if (!skb->ipvs_property) {
+ match = false;
+ goto out;
+ }
+
+ ip_vs_fill_iphdr(family, skb_network_header(skb), &iph);
+
+ if (data->bitmask & XT_IPVS_PROTO)
+ if ((iph.protocol == data->l4proto) ^
+ !(data->invert & XT_IPVS_PROTO)) {
+ match = false;
+ goto out;
+ }
+
+ pp = ip_vs_proto_get(iph.protocol);
+ if (unlikely(!pp)) {
+ match = false;
+ goto out;
+ }
+
+ /*
+ * Check if the packet belongs to an existing entry
+ */
+ cp = pp->conn_out_get(family, skb, pp, &iph, iph.len, 1 /* inverse */);
+ if (unlikely(cp == NULL)) {
+ match = false;
+ goto out;
+ }
+
+ /*
+ * We found a connection, i.e. ct != 0, make sure to call
+ * __ip_vs_conn_put before returning. In our case jump to out_put_con.
+ */
+
+ if (data->bitmask & XT_IPVS_VPORT)
+ if ((cp->vport == data->vport) ^
+ !(data->invert & XT_IPVS_VPORT)) {
+ match = false;
+ goto out_put_cp;
+ }
+
+ if (data->bitmask & XT_IPVS_VPORTCTL)
+ if ((cp->control != NULL &&
+ cp->control->vport == data->vportctl) ^
+ !(data->invert & XT_IPVS_VPORTCTL)) {
+ match = false;
+ goto out_put_cp;
+ }
+
+ if (data->bitmask & XT_IPVS_DIR) {
+ enum ip_conntrack_info ctinfo;
+ struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
+
+ if (ct == NULL || nf_ct_is_untracked(ct)) {
+ match = false;
+ goto out_put_cp;
+ }
+
+ if ((ctinfo >= IP_CT_IS_REPLY) ^
+ !!(data->invert & XT_IPVS_DIR)) {
+ match = false;
+ goto out_put_cp;
+ }
+ }
+
+ if (data->bitmask & XT_IPVS_METHOD)
+ if (((cp->flags & IP_VS_CONN_F_FWD_MASK) == data->fwd_method) ^
+ !(data->invert & XT_IPVS_METHOD)) {
+ match = false;
+ goto out_put_cp;
+ }
+
+ if (data->bitmask & XT_IPVS_VADDR) {
+ if (ipvs_mt_addrcmp(&cp->vaddr, &data->vaddr,
+ &data->vmask, family) ^
+ !(data->invert & XT_IPVS_VADDR)) {
+ match = false;
+ goto out_put_cp;
+ }
+ }
+
+out_put_cp:
+ __ip_vs_conn_put(cp);
+out:
+ pr_debug("match=%d\n", match);
+ return match;
+}
+
+static int ipvs_mt_check(const struct xt_mtchk_param *par)
+{
+ if (par->family != NFPROTO_IPV4
+#ifdef CONFIG_IP_VS_IPV6
+ && par->family != NFPROTO_IPV6
+#endif
+ ) {
+ pr_info("protocol family %u not supported\n", par->family);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static struct xt_match xt_ipvs_mt_reg __read_mostly = {
+ .name = "ipvs",
+ .revision = 0,
+ .family = NFPROTO_UNSPEC,
+ .match = ipvs_mt,
+ .checkentry = ipvs_mt_check,
+ .matchsize = XT_ALIGN(sizeof(struct xt_ipvs_mtinfo)),
+ .me = THIS_MODULE,
+};
+
+static int __init ipvs_mt_init(void)
+{
+ return xt_register_match(&xt_ipvs_mt_reg);
+}
+
+static void __exit ipvs_mt_exit(void)
+{
+ xt_unregister_match(&xt_ipvs_mt_reg);
+}
+
+module_init(ipvs_mt_init);
+module_exit(ipvs_mt_exit);
diff --git a/net/netfilter/xt_quota.c b/net/netfilter/xt_quota.c
index b4f7dfea5980..70eb2b4984dd 100644
--- a/net/netfilter/xt_quota.c
+++ b/net/netfilter/xt_quota.c
@@ -11,7 +11,8 @@
#include <linux/netfilter/xt_quota.h>
struct xt_quota_priv {
- uint64_t quota;
+ spinlock_t lock;
+ uint64_t quota;
};
MODULE_LICENSE("GPL");
@@ -20,8 +21,6 @@ MODULE_DESCRIPTION("Xtables: countdown quota match");
MODULE_ALIAS("ipt_quota");
MODULE_ALIAS("ip6t_quota");
-static DEFINE_SPINLOCK(quota_lock);
-
static bool
quota_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
@@ -29,7 +28,7 @@ quota_mt(const struct sk_buff *skb, struct xt_action_param *par)
struct xt_quota_priv *priv = q->master;
bool ret = q->flags & XT_QUOTA_INVERT;
- spin_lock_bh(&quota_lock);
+ spin_lock_bh(&priv->lock);
if (priv->quota >= skb->len) {
priv->quota -= skb->len;
ret = !ret;
@@ -37,9 +36,7 @@ quota_mt(const struct sk_buff *skb, struct xt_action_param *par)
/* we do not allow even small packets from now on */
priv->quota = 0;
}
- /* Copy quota back to matchinfo so that iptables can display it */
- q->quota = priv->quota;
- spin_unlock_bh(&quota_lock);
+ spin_unlock_bh(&priv->lock);
return ret;
}
@@ -55,6 +52,7 @@ static int quota_mt_check(const struct xt_mtchk_param *par)
if (q->master == NULL)
return -ENOMEM;
+ spin_lock_init(&q->master->lock);
q->master->quota = q->quota;
return 0;
}
diff --git a/net/netfilter/xt_sctp.c b/net/netfilter/xt_sctp.c
index c04fcf385c59..ef36a56a02c6 100644
--- a/net/netfilter/xt_sctp.c
+++ b/net/netfilter/xt_sctp.c
@@ -3,6 +3,7 @@
#include <linux/skbuff.h>
#include <net/ip.h>
#include <net/ipv6.h>
+#include <net/sctp/sctp.h>
#include <linux/sctp.h>
#include <linux/netfilter/x_tables.h>
@@ -67,7 +68,7 @@ match_packet(const struct sk_buff *skb,
++i, offset, sch->type, htons(sch->length),
sch->flags);
#endif
- offset += (ntohs(sch->length) + 3) & ~3;
+ offset += WORD_ROUND(ntohs(sch->length));
pr_debug("skb->len: %d\toffset: %d\n", skb->len, offset);
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 3d54c236a1ba..1ca89908cbad 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -127,7 +127,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
* reply packet of an established SNAT-ted connection. */
ct = nf_ct_get(skb, &ctinfo);
- if (ct && (ct != &nf_conntrack_untracked) &&
+ if (ct && !nf_ct_is_untracked(ct) &&
((iph->protocol != IPPROTO_ICMP &&
ctinfo == IP_CT_IS_REPLY + IP_CT_ESTABLISHED) ||
(iph->protocol == IPPROTO_ICMP &&
diff --git a/net/netfilter/xt_state.c b/net/netfilter/xt_state.c
index e12e053d3782..a507922d80cd 100644
--- a/net/netfilter/xt_state.c
+++ b/net/netfilter/xt_state.c
@@ -26,14 +26,16 @@ state_mt(const struct sk_buff *skb, struct xt_action_param *par)
const struct xt_state_info *sinfo = par->matchinfo;
enum ip_conntrack_info ctinfo;
unsigned int statebit;
+ struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
- if (nf_ct_is_untracked(skb))
- statebit = XT_STATE_UNTRACKED;
- else if (!nf_ct_get(skb, &ctinfo))
+ if (!ct)
statebit = XT_STATE_INVALID;
- else
- statebit = XT_STATE_BIT(ctinfo);
-
+ else {
+ if (nf_ct_is_untracked(ct))
+ statebit = XT_STATE_UNTRACKED;
+ else
+ statebit = XT_STATE_BIT(ctinfo);
+ }
return (sinfo->statemask & statebit);
}
diff --git a/net/netfilter/xt_statistic.c b/net/netfilter/xt_statistic.c
index 96e62b8fd6b1..42ecb71d445f 100644
--- a/net/netfilter/xt_statistic.c
+++ b/net/netfilter/xt_statistic.c
@@ -18,8 +18,8 @@
#include <linux/netfilter/x_tables.h>
struct xt_statistic_priv {
- uint32_t count;
-};
+ atomic_t count;
+} ____cacheline_aligned_in_smp;
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
@@ -27,13 +27,12 @@ MODULE_DESCRIPTION("Xtables: statistics-based matching (\"Nth\", random)");
MODULE_ALIAS("ipt_statistic");
MODULE_ALIAS("ip6t_statistic");
-static DEFINE_SPINLOCK(nth_lock);
-
static bool
statistic_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct xt_statistic_info *info = par->matchinfo;
bool ret = info->flags & XT_STATISTIC_INVERT;
+ int nval, oval;
switch (info->mode) {
case XT_STATISTIC_MODE_RANDOM:
@@ -41,12 +40,12 @@ statistic_mt(const struct sk_buff *skb, struct xt_action_param *par)
ret = !ret;
break;
case XT_STATISTIC_MODE_NTH:
- spin_lock_bh(&nth_lock);
- if (info->master->count++ == info->u.nth.every) {
- info->master->count = 0;
+ do {
+ oval = atomic_read(&info->master->count);
+ nval = (oval == info->u.nth.every) ? 0 : oval + 1;
+ } while (atomic_cmpxchg(&info->master->count, oval, nval) != oval);
+ if (nval == 0)
ret = !ret;
- }
- spin_unlock_bh(&nth_lock);
break;
}
@@ -64,7 +63,7 @@ static int statistic_mt_check(const struct xt_mtchk_param *par)
info->master = kzalloc(sizeof(*info->master), GFP_KERNEL);
if (info->master == NULL)
return -ENOMEM;
- info->master->count = info->u.nth.count;
+ atomic_set(&info->master->count, info->u.nth.count);
return 0;
}