summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2010-06-15 13:49:24 -0700
committerDavid S. Miller <davem@davemloft.net>2010-06-15 13:49:24 -0700
commit16fb62b6b4d57339a0ec931b3fb8c8d0ca6414e8 (patch)
treea1041342f31a626baf3a08d09d5c81a65dd8ef28
parenta3433f35a55f7604742cae620c6dc6edfc70db6a (diff)
parentf9181f4ffc71d7b7dd1906c9a11d51d6659220ae (diff)
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-next-2.6
-rw-r--r--include/linux/netfilter/Kbuild1
-rw-r--r--include/linux/netfilter/nf_conntrack_common.h4
-rw-r--r--include/linux/netfilter/nfnetlink_log.h1
-rw-r--r--include/linux/netfilter/xt_IDLETIMER.h45
-rw-r--r--include/net/netfilter/nf_conntrack.h11
-rw-r--r--include/net/netfilter/nf_conntrack_core.h2
-rw-r--r--include/net/netfilter/xt_rateest.h10
-rw-r--r--net/bridge/br_netfilter.c6
-rw-r--r--net/ipv4/netfilter.c4
-rw-r--r--net/ipv4/netfilter/arp_tables.c7
-rw-r--r--net/ipv4/netfilter/ip_queue.c57
-rw-r--r--net/ipv4/netfilter/ip_tables.c4
-rw-r--r--net/ipv4/netfilter/ipt_CLUSTERIP.c48
-rw-r--r--net/ipv4/netfilter/nf_nat_core.c2
-rw-r--r--net/ipv4/netfilter/nf_nat_standalone.c2
-rw-r--r--net/ipv6/netfilter.c4
-rw-r--r--net/ipv6/netfilter/ip6_queue.c57
-rw-r--r--net/ipv6/netfilter/ip6_tables.c7
-rw-r--r--net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c2
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c9
-rw-r--r--net/netfilter/Kconfig12
-rw-r--r--net/netfilter/Makefile1
-rw-r--r--net/netfilter/nf_conntrack_core.c40
-rw-r--r--net/netfilter/nf_conntrack_netlink.c2
-rw-r--r--net/netfilter/nfnetlink_log.c67
-rw-r--r--net/netfilter/nfnetlink_queue.c33
-rw-r--r--net/netfilter/xt_CT.c4
-rw-r--r--net/netfilter/xt_IDLETIMER.c314
-rw-r--r--net/netfilter/xt_NOTRACK.c2
-rw-r--r--net/netfilter/xt_TEE.c4
-rw-r--r--net/netfilter/xt_cluster.c2
-rw-r--r--net/netfilter/xt_conntrack.c11
-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
36 files changed, 608 insertions, 205 deletions
diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild
index 48767cd1645..bb103f43afa 100644
--- a/include/linux/netfilter/Kbuild
+++ b/include/linux/netfilter/Kbuild
@@ -8,6 +8,7 @@ header-y += xt_CONNMARK.h
header-y += xt_CONNSECMARK.h
header-y += xt_CT.h
header-y += xt_DSCP.h
+header-y += xt_IDLETIMER.h
header-y += xt_LED.h
header-y += xt_MARK.h
header-y += xt_NFLOG.h
diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h
index 14e6d32002c..1afd18c855e 100644
--- a/include/linux/netfilter/nf_conntrack_common.h
+++ b/include/linux/netfilter/nf_conntrack_common.h
@@ -76,6 +76,10 @@ enum ip_conntrack_status {
/* Conntrack is a template */
IPS_TEMPLATE_BIT = 11,
IPS_TEMPLATE = (1 << IPS_TEMPLATE_BIT),
+
+ /* Conntrack is a fake untracked entry */
+ IPS_UNTRACKED_BIT = 12,
+ IPS_UNTRACKED = (1 << IPS_UNTRACKED_BIT),
};
/* Connection tracking event types */
diff --git a/include/linux/netfilter/nfnetlink_log.h b/include/linux/netfilter/nfnetlink_log.h
index d3bab7a2c9b..1d0b84aa1d4 100644
--- a/include/linux/netfilter/nfnetlink_log.h
+++ b/include/linux/netfilter/nfnetlink_log.h
@@ -89,6 +89,7 @@ enum nfulnl_attr_config {
#define NFULNL_COPY_NONE 0x00
#define NFULNL_COPY_META 0x01
#define NFULNL_COPY_PACKET 0x02
+#define NFULNL_COPY_DISABLED 0x03
#define NFULNL_CFG_F_SEQ 0x0001
#define NFULNL_CFG_F_SEQ_GLOBAL 0x0002
diff --git a/include/linux/netfilter/xt_IDLETIMER.h b/include/linux/netfilter/xt_IDLETIMER.h
new file mode 100644
index 00000000000..3e1aa1be942
--- /dev/null
+++ b/include/linux/netfilter/xt_IDLETIMER.h
@@ -0,0 +1,45 @@
+/*
+ * linux/include/linux/netfilter/xt_IDLETIMER.h
+ *
+ * Header file for Xtables timer target module.
+ *
+ * Copyright (C) 2004, 2010 Nokia Corporation
+ * Written by Timo Teras <ext-timo.teras@nokia.com>
+ *
+ * Converted to x_tables and forward-ported to 2.6.34
+ * 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
+ */
+
+#ifndef _XT_IDLETIMER_H
+#define _XT_IDLETIMER_H
+
+#include <linux/types.h>
+
+#define MAX_IDLETIMER_LABEL_SIZE 28
+
+struct idletimer_tg_info {
+ __u32 timeout;
+
+ char label[MAX_IDLETIMER_LABEL_SIZE];
+
+ /* for kernel module internal use only */
+ struct idletimer_tg *timer __attribute((aligned(8)));
+};
+
+#endif
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index bbfdd945308..e624dae54fa 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -257,7 +257,12 @@ extern s16 (*nf_ct_nat_offset)(const struct nf_conn *ct,
u32 seq);
/* Fake conntrack entry for untracked connections */
-extern struct nf_conn nf_conntrack_untracked;
+DECLARE_PER_CPU(struct nf_conn, nf_conntrack_untracked);
+static inline struct nf_conn *nf_ct_untracked_get(void)
+{
+ return &__raw_get_cpu_var(nf_conntrack_untracked);
+}
+extern void nf_ct_untracked_status_or(unsigned long bits);
/* Iterate over all conntracks: if iter returns true, it's deleted. */
extern void
@@ -285,9 +290,9 @@ static inline int nf_ct_is_dying(struct nf_conn *ct)
return test_bit(IPS_DYING_BIT, &ct->status);
}
-static inline int nf_ct_is_untracked(const struct sk_buff *skb)
+static inline int nf_ct_is_untracked(const struct nf_conn *ct)
{
- return (skb->nfct == &nf_conntrack_untracked.ct_general);
+ return test_bit(IPS_UNTRACKED_BIT, &ct->status);
}
extern int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp);
diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index 3d7524fba19..aced085132e 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -60,7 +60,7 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb)
struct nf_conn *ct = (struct nf_conn *)skb->nfct;
int ret = NF_ACCEPT;
- if (ct && ct != &nf_conntrack_untracked) {
+ if (ct && !nf_ct_is_untracked(ct)) {
if (!nf_ct_is_confirmed(ct))
ret = __nf_conntrack_confirm(skb);
if (likely(ret == NF_ACCEPT))
diff --git a/include/net/netfilter/xt_rateest.h b/include/net/netfilter/xt_rateest.h
index 5e142779592..5a2978d1cb2 100644
--- a/include/net/netfilter/xt_rateest.h
+++ b/include/net/netfilter/xt_rateest.h
@@ -2,13 +2,17 @@
#define _XT_RATEEST_H
struct xt_rateest {
+ /* keep lock and bstats on same cache line to speedup xt_rateest_tg() */
+ struct gnet_stats_basic_packed bstats;
+ spinlock_t lock;
+ /* keep rstats and lock on same cache line to speedup xt_rateest_mt() */
+ struct gnet_stats_rate_est rstats;
+
+ /* following fields not accessed in hot path */
struct hlist_node list;
char name[IFNAMSIZ];
unsigned int refcnt;
- spinlock_t lock;
struct gnet_estimator params;
- struct gnet_stats_rate_est rstats;
- struct gnet_stats_basic_packed bstats;
struct rcu_head rcu;
};
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index f54404ddee5..84060bc48f1 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -245,8 +245,7 @@ static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb)
kfree_skb(skb);
return 0;
}
- dst_hold(&rt->dst);
- skb_dst_set(skb, &rt->dst);
+ skb_dst_set_noref(skb, &rt->dst);
skb->dev = nf_bridge->physindev;
nf_bridge_update_protocol(skb);
@@ -397,8 +396,7 @@ bridged_dnat:
kfree_skb(skb);
return 0;
}
- dst_hold(&rt->dst);
- skb_dst_set(skb, &rt->dst);
+ skb_dst_set_noref(skb, &rt->dst);
}
skb->dev = nf_bridge->physindev;
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index cfbc79af21c..d88a46c54fd 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -212,9 +212,7 @@ static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook,
skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, protocol,
skb->len - dataoff, 0);
skb->ip_summed = CHECKSUM_NONE;
- csum = __skb_checksum_complete_head(skb, dataoff + len);
- if (!csum)
- skb->ip_summed = CHECKSUM_UNNECESSARY;
+ return __skb_checksum_complete_head(skb, dataoff + len);
}
return csum;
}
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 1ac01b12862..16c0ba0a272 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -758,7 +758,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
* about).
*/
countersize = sizeof(struct xt_counters) * private->number;
- counters = vmalloc_node(countersize, numa_node_id());
+ counters = vmalloc(countersize);
if (counters == NULL)
return ERR_PTR(-ENOMEM);
@@ -1005,8 +1005,7 @@ static int __do_replace(struct net *net, const char *name,
struct arpt_entry *iter;
ret = 0;
- counters = vmalloc_node(num_counters * sizeof(struct xt_counters),
- numa_node_id());
+ counters = vmalloc(num_counters * sizeof(struct xt_counters));
if (!counters) {
ret = -ENOMEM;
goto out;
@@ -1159,7 +1158,7 @@ static int do_add_counters(struct net *net, const void __user *user,
if (len != size + num_counters * sizeof(struct xt_counters))
return -EINVAL;
- paddc = vmalloc_node(len - size, numa_node_id());
+ paddc = vmalloc(len - size);
if (!paddc)
return -ENOMEM;
diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c
index a4e5fc5df4b..d2c1311cb28 100644
--- a/net/ipv4/netfilter/ip_queue.c
+++ b/net/ipv4/netfilter/ip_queue.c
@@ -42,7 +42,7 @@ typedef int (*ipq_cmpfn)(struct nf_queue_entry *, unsigned long);
static unsigned char copy_mode __read_mostly = IPQ_COPY_NONE;
static unsigned int queue_maxlen __read_mostly = IPQ_QMAX_DEFAULT;
-static DEFINE_RWLOCK(queue_lock);
+static DEFINE_SPINLOCK(queue_lock);
static int peer_pid __read_mostly;
static unsigned int copy_range __read_mostly;
static unsigned int queue_total;
@@ -72,10 +72,10 @@ __ipq_set_mode(unsigned char mode, unsigned int range)
break;
case IPQ_COPY_PACKET:
- copy_mode = mode;
+ if (range > 0xFFFF)
+ range = 0xFFFF;
copy_range = range;
- if (copy_range > 0xFFFF)
- copy_range = 0xFFFF;
+ copy_mode = mode;
break;
default:
@@ -101,7 +101,7 @@ ipq_find_dequeue_entry(unsigned long id)
{
struct nf_queue_entry *entry = NULL, *i;
- write_lock_bh(&queue_lock);
+ spin_lock_bh(&queue_lock);
list_for_each_entry(i, &queue_list, list) {
if ((unsigned long)i == id) {
@@ -115,7 +115,7 @@ ipq_find_dequeue_entry(unsigned long id)
queue_total--;
}
- write_unlock_bh(&queue_lock);
+ spin_unlock_bh(&queue_lock);
return entry;
}
@@ -136,9 +136,9 @@ __ipq_flush(ipq_cmpfn cmpfn, unsigned long data)
static void
ipq_flush(ipq_cmpfn cmpfn, unsigned long data)
{
- write_lock_bh(&queue_lock);
+ spin_lock_bh(&queue_lock);
__ipq_flush(cmpfn, data);
- write_unlock_bh(&queue_lock);
+ spin_unlock_bh(&queue_lock);
}
static struct sk_buff *
@@ -152,9 +152,7 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp)
struct nlmsghdr *nlh;
struct timeval tv;
- read_lock_bh(&queue_lock);
-
- switch (copy_mode) {
+ switch (ACCESS_ONCE(copy_mode)) {
case IPQ_COPY_META:
case IPQ_COPY_NONE:
size = NLMSG_SPACE(sizeof(*pmsg));
@@ -162,26 +160,21 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp)
case IPQ_COPY_PACKET:
if (entry->skb->ip_summed == CHECKSUM_PARTIAL &&
- (*errp = skb_checksum_help(entry->skb))) {
- read_unlock_bh(&queue_lock);
+ (*errp = skb_checksum_help(entry->skb)))
return NULL;
- }
- if (copy_range == 0 || copy_range > entry->skb->len)
+
+ data_len = ACCESS_ONCE(copy_range);
+ if (data_len == 0 || data_len > entry->skb->len)
data_len = entry->skb->len;
- else
- data_len = copy_range;
size = NLMSG_SPACE(sizeof(*pmsg) + data_len);
break;
default:
*errp = -EINVAL;
- read_unlock_bh(&queue_lock);
return NULL;
}
- read_unlock_bh(&queue_lock);
-
skb = alloc_skb(size, GFP_ATOMIC);
if (!skb)
goto nlmsg_failure;
@@ -242,7 +235,7 @@ ipq_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
if (nskb == NULL)
return status;
- write_lock_bh(&queue_lock);
+ spin_lock_bh(&queue_lock);
if (!peer_pid)
goto err_out_free_nskb;
@@ -266,14 +259,14 @@ ipq_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
__ipq_enqueue_entry(entry);
- write_unlock_bh(&queue_lock);
+ spin_unlock_bh(&queue_lock);
return status;
err_out_free_nskb:
kfree_skb(nskb);
err_out_unlock:
- write_unlock_bh(&queue_lock);
+ spin_unlock_bh(&queue_lock);
return status;
}
@@ -342,9 +335,9 @@ ipq_set_mode(unsigned char mode, unsigned int range)
{
int status;
- write_lock_bh(&queue_lock);
+ spin_lock_bh(&queue_lock);
status = __ipq_set_mode(mode, range);
- write_unlock_bh(&queue_lock);
+ spin_unlock_bh(&queue_lock);
return status;
}
@@ -440,11 +433,11 @@ __ipq_rcv_skb(struct sk_buff *skb)
if (security_netlink_recv(skb, CAP_NET_ADMIN))
RCV_SKB_FAIL(-EPERM);
- write_lock_bh(&queue_lock);
+ spin_lock_bh(&queue_lock);
if (peer_pid) {
if (peer_pid != pid) {
- write_unlock_bh(&queue_lock);
+ spin_unlock_bh(&queue_lock);
RCV_SKB_FAIL(-EBUSY);
}
} else {
@@ -452,7 +445,7 @@ __ipq_rcv_skb(struct sk_buff *skb)
peer_pid = pid;
}
- write_unlock_bh(&queue_lock);
+ spin_unlock_bh(&queue_lock);
status = ipq_receive_peer(NLMSG_DATA(nlh), type,
nlmsglen - NLMSG_LENGTH(0));
@@ -497,10 +490,10 @@ ipq_rcv_nl_event(struct notifier_block *this,
struct netlink_notify *n = ptr;
if (event == NETLINK_URELEASE && n->protocol == NETLINK_FIREWALL) {
- write_lock_bh(&queue_lock);
+ spin_lock_bh(&queue_lock);
if ((net_eq(n->net, &init_net)) && (n->pid == peer_pid))
__ipq_reset();
- write_unlock_bh(&queue_lock);
+ spin_unlock_bh(&queue_lock);
}
return NOTIFY_DONE;
}
@@ -527,7 +520,7 @@ static ctl_table ipq_table[] = {
#ifdef CONFIG_PROC_FS
static int ip_queue_show(struct seq_file *m, void *v)
{
- read_lock_bh(&queue_lock);
+ spin_lock_bh(&queue_lock);
seq_printf(m,
"Peer PID : %d\n"
@@ -545,7 +538,7 @@ static int ip_queue_show(struct seq_file *m, void *v)
queue_dropped,
queue_user_dropped);
- read_unlock_bh(&queue_lock);
+ spin_unlock_bh(&queue_lock);
return 0;
}
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 4b6c5ca610f..b38c11810c6 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -928,7 +928,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
(other than comefrom, which userspace doesn't care
about). */
countersize = sizeof(struct xt_counters) * private->number;
- counters = vmalloc_node(countersize, numa_node_id());
+ counters = vmalloc(countersize);
if (counters == NULL)
return ERR_PTR(-ENOMEM);
@@ -1352,7 +1352,7 @@ do_add_counters(struct net *net, const void __user *user,
if (len != size + num_counters * sizeof(struct xt_counters))
return -EINVAL;
- paddc = vmalloc_node(len - size, numa_node_id());
+ paddc = vmalloc(len - size);
if (!paddc)
return -ENOMEM;
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index f91c94b9a79..64d0875f519 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -53,12 +53,13 @@ struct clusterip_config {
#endif
enum clusterip_hashmode hash_mode; /* which hashing mode */
u_int32_t hash_initval; /* hash initialization */
+ struct rcu_head rcu;
};
static LIST_HEAD(clusterip_configs);
/* clusterip_lock protects the clusterip_configs list */
-static DEFINE_RWLOCK(clusterip_lock);
+static DEFINE_SPINLOCK(clusterip_lock);
#ifdef CONFIG_PROC_FS
static const struct file_operations clusterip_proc_fops;
@@ -71,11 +72,17 @@ clusterip_config_get(struct clusterip_config *c)
atomic_inc(&c->refcount);
}
+
+static void clusterip_config_rcu_free(struct rcu_head *head)
+{
+ kfree(container_of(head, struct clusterip_config, rcu));
+}
+
static inline void
clusterip_config_put(struct clusterip_config *c)
{
if (atomic_dec_and_test(&c->refcount))
- kfree(c);
+ call_rcu_bh(&c->rcu, clusterip_config_rcu_free);
}
/* decrease the count of entries using/referencing this config. If last
@@ -84,10 +91,11 @@ clusterip_config_put(struct clusterip_config *c)
static inline void
clusterip_config_entry_put(struct clusterip_config *c)
{
- write_lock_bh(&clusterip_lock);
- if (atomic_dec_and_test(&c->entries)) {
- list_del(&c->list);
- write_unlock_bh(&clusterip_lock);
+ local_bh_disable();
+ if (atomic_dec_and_lock(&c->entries, &clusterip_lock)) {
+ list_del_rcu(&c->list);
+ spin_unlock(&clusterip_lock);
+ local_bh_enable();
dev_mc_del(c->dev, c->clustermac);
dev_put(c->dev);
@@ -100,7 +108,7 @@ clusterip_config_entry_put(struct clusterip_config *c)
#endif
return;
}
- write_unlock_bh(&clusterip_lock);
+ local_bh_enable();
}
static struct clusterip_config *
@@ -108,7 +116,7 @@ __clusterip_config_find(__be32 clusterip)
{
struct clusterip_config *c;
- list_for_each_entry(c, &clusterip_configs, list) {
+ list_for_each_entry_rcu(c, &clusterip_configs, list) {
if (c->clusterip == clusterip)
return c;
}
@@ -121,16 +129,15 @@ clusterip_config_find_get(__be32 clusterip, int entry)
{
struct clusterip_config *c;
- read_lock_bh(&clusterip_lock);
+ rcu_read_lock_bh();
c = __clusterip_config_find(clusterip);
- if (!c) {
- read_unlock_bh(&clusterip_lock);
- return NULL;
+ if (c) {
+ if (unlikely(!atomic_inc_not_zero(&c->refcount)))
+ c = NULL;
+ else if (entry)
+ atomic_inc(&c->entries);
}
- atomic_inc(&c->refcount);
- if (entry)
- atomic_inc(&c->entries);
- read_unlock_bh(&clusterip_lock);
+ rcu_read_unlock_bh();
return c;
}
@@ -181,9 +188,9 @@ clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip,
}
#endif
- write_lock_bh(&clusterip_lock);
- list_add(&c->list, &clusterip_configs);
- write_unlock_bh(&clusterip_lock);
+ spin_lock_bh(&clusterip_lock);
+ list_add_rcu(&c->list, &clusterip_configs);
+ spin_unlock_bh(&clusterip_lock);
return c;
}
@@ -733,6 +740,9 @@ static void __exit clusterip_tg_exit(void)
#endif
nf_unregister_hook(&cip_arp_ops);
xt_unregister_target(&clusterip_tg_reg);
+
+ /* Wait for completion of call_rcu_bh()'s (clusterip_config_rcu_free) */
+ rcu_barrier_bh();
}
module_init(clusterip_tg_init);
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index 4f8bddb760c..c7719b283ad 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -742,7 +742,7 @@ static int __init nf_nat_init(void)
spin_unlock_bh(&nf_nat_lock);
/* Initialize fake conntrack so that NAT will skip it */
- nf_conntrack_untracked.status |= IPS_NAT_DONE_MASK;
+ nf_ct_untracked_status_or(IPS_NAT_DONE_MASK);
l3proto = nf_ct_l3proto_find_get((u_int16_t)AF_INET);
diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c
index beb25819c9c..6723c682250 100644
--- a/net/ipv4/netfilter/nf_nat_standalone.c
+++ b/net/ipv4/netfilter/nf_nat_standalone.c
@@ -98,7 +98,7 @@ nf_nat_fn(unsigned int hooknum,
return NF_ACCEPT;
/* Don't try to NAT if this packet is not conntracked */
- if (ct == &nf_conntrack_untracked)
+ if (nf_ct_is_untracked(ct))
return NF_ACCEPT;
nat = nfct_nat(ct);
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index a74951c039b..7155b2451d7 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -151,9 +151,7 @@ static __sum16 nf_ip6_checksum_partial(struct sk_buff *skb, unsigned int hook,
protocol,
csum_sub(0, hsum)));
skb->ip_summed = CHECKSUM_NONE;
- csum = __skb_checksum_complete_head(skb, dataoff + len);
- if (!csum)
- skb->ip_summed = CHECKSUM_UNNECESSARY;
+ return __skb_checksum_complete_head(skb, dataoff + len);
}
return csum;
};
diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c
index 8c201743d96..413ab0754e1 100644
--- a/net/ipv6/netfilter/ip6_queue.c
+++ b/net/ipv6/netfilter/ip6_queue.c
@@ -43,7 +43,7 @@ typedef int (*ipq_cmpfn)(struct nf_queue_entry *, unsigned long);
static unsigned char copy_mode __read_mostly = IPQ_COPY_NONE;
static unsigned int queue_maxlen __read_mostly = IPQ_QMAX_DEFAULT;
-static DEFINE_RWLOCK(queue_lock);
+static DEFINE_SPINLOCK(queue_lock);
static int peer_pid __read_mostly;
static unsigned int copy_range __read_mostly;
static unsigned int queue_total;
@@ -73,10 +73,10 @@ __ipq_set_mode(unsigned char mode, unsigned int range)
break;
case IPQ_COPY_PACKET:
- copy_mode = mode;
+ if (range > 0xFFFF)
+ range = 0xFFFF;
copy_range = range;
- if (copy_range > 0xFFFF)
- copy_range = 0xFFFF;
+ copy_mode = mode;
break;
default:
@@ -102,7 +102,7 @@ ipq_find_dequeue_entry(unsigned long id)
{
struct nf_queue_entry *entry = NULL, *i;
- write_lock_bh(&queue_lock);
+ spin_lock_bh(&queue_lock);
list_for_each_entry(i, &queue_list, list) {
if ((unsigned long)i == id) {
@@ -116,7 +116,7 @@ ipq_find_dequeue_entry(unsigned long id)
queue_total--;
}
- write_unlock_bh(&queue_lock);
+ spin_unlock_bh(&queue_lock);
return entry;
}
@@ -137,9 +137,9 @@ __ipq_flush(ipq_cmpfn cmpfn, unsigned long data)
static void
ipq_flush(ipq_cmpfn cmpfn, unsigned long data)
{
- write_lock_bh(&queue_lock);
+ spin_lock_bh(&queue_lock);
__ipq_flush(cmpfn, data);
- write_unlock_bh(&queue_lock);
+ spin_unlock_bh(&queue_lock);
}
static struct sk_buff *
@@ -153,9 +153,7 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp)
struct nlmsghdr *nlh;
struct timeval tv;
- read_lock_bh(&queue_lock);
-
- switch (copy_mode) {
+ switch (ACCESS_ONCE(copy_mode)) {
case IPQ_COPY_META:
case IPQ_COPY_NONE:
size = NLMSG_SPACE(sizeof(*pmsg));
@@ -163,26 +161,21 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp)
case IPQ_COPY_PACKET:
if (entry->skb->ip_summed == CHECKSUM_PARTIAL &&
- (*errp = skb_checksum_help(entry->skb))) {
- read_unlock_bh(&queue_lock);
+ (*errp = skb_checksum_help(entry->skb)))
return NULL;
- }
- if (copy_range == 0 || copy_range > entry->skb->len)
+
+ data_len = ACCESS_ONCE(copy_range);
+ if (data_len == 0 || data_len > entry->skb->len)
data_len = entry->skb->len;
- else
- data_len = copy_range;
size = NLMSG_SPACE(sizeof(*pmsg) + data_len);
break;
default:
*errp = -EINVAL;
- read_unlock_bh(&queue_lock);
return NULL;
}
- read_unlock_bh(&queue_lock);
-
skb = alloc_skb(size, GFP_ATOMIC);
if (!skb)
goto nlmsg_failure;
@@ -242,7 +235,7 @@ ipq_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
if (nskb == NULL)
return status;
- write_lock_bh(&queue_lock);
+ spin_lock_bh(&queue_lock);
if (!peer_pid)
goto err_out_free_nskb;
@@ -266,14 +259,14 @@ ipq_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
__ipq_enqueue_entry(entry);
- write_unlock_bh(&queue_lock);
+ spin_unlock_bh(&queue_lock);
return status;
err_out_free_nskb:
kfree_skb(nskb);
err_out_unlock:
- write_unlock_bh(&queue_lock);
+ spin_unlock_bh(&queue_lock);
return status;
}
@@ -342,9 +335,9 @@ ipq_set_mode(unsigned char mode, unsigned int range)
{
int status;
- write_lock_bh(&queue_lock);
+ spin_lock_bh(&queue_lock);
status = __ipq_set_mode(mode, range);
- write_unlock_bh(&queue_lock);
+ spin_unlock_bh(&queue_lock);
return status;
}
@@ -441,11 +434,11 @@ __ipq_rcv_skb(struct sk_buff *skb)
if (security_netlink_recv(skb, CAP_NET_ADMIN))
RCV_SKB_FAIL(-EPERM);
- write_lock_bh(&queue_lock);
+ spin_lock_bh(&queue_lock);
if (peer_pid) {
if (peer_pid != pid) {
- write_unlock_bh(&queue_lock);
+ spin_unlock_bh(&queue_lock);
RCV_SKB_FAIL(-EBUSY);
}
} else {
@@ -453,7 +446,7 @@ __ipq_rcv_skb(struct sk_buff *skb)
peer_pid = pid;
}
- write_unlock_bh(&queue_lock);
+ spin_unlock_bh(&queue_lock);
status = ipq_receive_peer(NLMSG_DATA(nlh), type,
nlmsglen - NLMSG_LENGTH(0));
@@ -498,10 +491,10 @@ ipq_rcv_nl_event(struct notifier_block *this,
struct netlink_notify *n = ptr;
if (event == NETLINK_URELEASE && n->protocol == NETLINK_IP6_FW) {
- write_lock_bh(&queue_lock);
+ spin_lock_bh(&queue_lock);
if ((net_eq(n->net, &init_net)) && (n->pid == peer_pid))
__ipq_reset();
- write_unlock_bh(&queue_lock);
+ spin_unlock_bh(&queue_lock);
}
return NOTIFY_DONE;
}
@@ -528,7 +521,7 @@ static ctl_table ipq_table[] = {
#ifdef CONFIG_PROC_FS
static int ip6_queue_show(struct seq_file *m, void *v)
{
- read_lock_bh(&queue_lock);
+ spin_lock_bh(&queue_lock);
seq_printf(m,
"Peer PID : %d\n"
@@ -546,7 +539,7 @@ static int ip6_queue_show(struct seq_file *m, void *v)
queue_dropped,
queue_user_dropped);
- read_unlock_bh(&queue_lock);
+ spin_unlock_bh(&queue_lock);
return 0;
}
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 9d2d68f0e60..dc41d6d3c6c 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -943,7 +943,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
(other than comefrom, which userspace doesn't care
about). */
countersize = sizeof(struct xt_counters) * private->number;
- counters = vmalloc_node(countersize, numa_node_id());
+ counters = vmalloc(countersize);
if (counters == NULL)
return ERR_PTR(-ENOMEM);
@@ -1213,8 +1213,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks,
struct ip6t_entry *iter;
ret = 0;
- counters = vmalloc_node(num_counters * sizeof(struct xt_counters),
- numa_node_id());
+ counters = vmalloc(num_counters * sizeof(struct xt_counters));
if (!counters) {
ret = -ENOMEM;
goto out;
@@ -1368,7 +1367,7 @@ do_add_counters(struct net *net, const void __user *user, unsigned int len,
if (len != size + num_counters * sizeof(struct xt_counters))
return -EINVAL;
- paddc = vmalloc_node(len - size, numa_node_id());
+ paddc = vmalloc(len - size);
if (!paddc)
return -ENOMEM;
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index 9be81776415..1df3c8b6bf4 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -208,7 +208,7 @@ icmpv6_error(struct net *net, struct nf_conn *tmpl,
type = icmp6h->icmp6_type - 130;
if (type >= 0 && type < sizeof(noct_valid_new) &&
noct_valid_new[type]) {
- 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);
return NF_ACCEPT;
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 6fb890187de..9254008602d 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -114,10 +114,8 @@ static void nf_skb_free(struct sk_buff *skb)
}
/* Memory Tracking Functions. */
-static inline void frag_kfree_skb(struct sk_buff *skb, unsigned int *work)
+static void frag_kfree_skb(struct sk_buff *skb)
{
- if (work)
- *work -= skb->truesize;
atomic_sub(skb->truesize, &nf_init_frags.mem);
nf_skb_free(skb);
kfree_skb(skb);
@@ -335,7 +333,7 @@ static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb,
fq->q.fragments = next;
fq->q.meat -= free_it->len;
- frag_kfree_skb(free_it, NULL);
+ frag_kfree_skb(free_it);
}
}
@@ -442,7 +440,6 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev)
skb_shinfo(head)->frag_list = head->next;
skb_reset_transport_header(head);
skb_push(head, head->data - skb_network_header(head));
- atomic_sub(head->truesize, &nf_init_frags.mem);
for (fp=head->next; fp; fp = fp->next) {
head->data_len += fp->len;
@@ -452,8 +449,8 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev)
else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
head->truesize += fp->truesize;
- atomic_sub(fp->truesize, &nf_init_frags.mem);
}
+ atomic_sub(head->truesize, &nf_init_frags.mem);
head->next = NULL;
head->dev = dev;
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 8593a77cfea..413ed24a968 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -424,6 +424,18 @@ 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
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 14e3a8fd818..e28420aac5e 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -61,6 +61,7 @@ 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
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 77288980fae..16b41b4e2a3 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;
@@ -1181,10 +1181,21 @@ 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();
@@ -1319,10 +1330,19 @@ 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. */
@@ -1361,11 +1381,13 @@ static int nf_conntrack_init_init_net(void)
goto err_extend;
#endif
/* Set up fake conntrack: to never be deleted, not in any hashes */
- write_pnet(&nf_conntrack_untracked.ct_net, &init_net);
- 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_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index c42ff6aa441..5bae1cd15ee 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/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index e0504e90a0f..6a1572b0ab4 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
@@ -621,6 +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;
}
@@ -674,7 +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;
@@ -686,7 +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;
}
@@ -863,19 +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;
}
@@ -892,9 +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);
}
@@ -905,9 +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 cc3ae861e8f..68e67d19724 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;
@@ -868,7 +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_CT.c b/net/netfilter/xt_CT.c
index 562bf3266e0..0cb6053f02f 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 00000000000..e11090a0675
--- /dev/null
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -0,0 +1,314 @@
+/*
+ * 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/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 512b9123252..9d782181b6c 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_TEE.c b/net/netfilter/xt_TEE.c
index c77a85bbd9e..22a2d421e7e 100644
--- a/net/netfilter/xt_TEE.c
+++ b/net/netfilter/xt_TEE.c
@@ -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_cluster.c b/net/netfilter/xt_cluster.c
index 30b95a1c1c8..f4af1bfafb1 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_conntrack.c b/net/netfilter/xt_conntrack.c
index 39681f10291..e536710ad91 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_sctp.c b/net/netfilter/xt_sctp.c
index c04fcf385c5..ef36a56a02c 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 3d54c236a1b..1ca89908cba 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 e12e053d378..a507922d80c 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 96e62b8fd6b..42ecb71d445 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;
}