summaryrefslogtreecommitdiff
path: root/net/ipv4/netfilter
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/netfilter')
-rw-r--r--net/ipv4/netfilter/arp_tables.c22
-rw-r--r--net/ipv4/netfilter/ip_queue.c57
-rw-r--r--net/ipv4/netfilter/ip_tables.c16
-rw-r--r--net/ipv4/netfilter/ipt_CLUSTERIP.c50
-rw-r--r--net/ipv4/netfilter/ipt_LOG.c54
-rw-r--r--net/ipv4/netfilter/ipt_NETMAP.c6
-rw-r--r--net/ipv4/netfilter/ipt_REJECT.c12
-rw-r--r--net/ipv4/netfilter/nf_defrag_ipv4.c5
-rw-r--r--net/ipv4/netfilter/nf_nat_core.c29
-rw-r--r--net/ipv4/netfilter/nf_nat_proto_common.c12
-rw-r--r--net/ipv4/netfilter/nf_nat_proto_dccp.c6
-rw-r--r--net/ipv4/netfilter/nf_nat_proto_gre.c12
-rw-r--r--net/ipv4/netfilter/nf_nat_proto_icmp.c10
-rw-r--r--net/ipv4/netfilter/nf_nat_proto_sctp.c6
-rw-r--r--net/ipv4/netfilter/nf_nat_proto_tcp.c5
-rw-r--r--net/ipv4/netfilter/nf_nat_proto_udp.c5
-rw-r--r--net/ipv4/netfilter/nf_nat_proto_udplite.c6
-rw-r--r--net/ipv4/netfilter/nf_nat_proto_unknown.c4
-rw-r--r--net/ipv4/netfilter/nf_nat_rule.c10
-rw-r--r--net/ipv4/netfilter/nf_nat_standalone.c10
20 files changed, 179 insertions, 158 deletions
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 1ac01b12862..6bccba31d13 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -283,16 +283,13 @@ unsigned int arpt_do_table(struct sk_buff *skb,
arp = arp_hdr(skb);
do {
const struct arpt_entry_target *t;
- int hdr_len;
if (!arp_packet_match(arp, skb->dev, indev, outdev, &e->arp)) {
e = arpt_next_entry(e);
continue;
}
- hdr_len = sizeof(*arp) + (2 * sizeof(struct in_addr)) +
- (2 * skb->dev->addr_len);
- ADD_COUNTER(e->counters, hdr_len, 1);
+ ADD_COUNTER(e->counters, arp_hdr_len(skb->dev), 1);
t = arpt_get_target_c(e);
@@ -713,7 +710,7 @@ static void get_counters(const struct xt_table_info *t,
struct arpt_entry *iter;
unsigned int cpu;
unsigned int i;
- unsigned int curcpu;
+ unsigned int curcpu = get_cpu();
/* Instead of clearing (by a previous call to memset())
* the counters and using adds, we set the counters
@@ -723,14 +720,16 @@ static void get_counters(const struct xt_table_info *t,
* if new softirq were to run and call ipt_do_table
*/
local_bh_disable();
- curcpu = smp_processor_id();
-
i = 0;
xt_entry_foreach(iter, t->entries[curcpu], t->size) {
SET_COUNTER(counters[i], iter->counters.bcnt,
iter->counters.pcnt);
++i;
}
+ local_bh_enable();
+ /* Processing counters from other cpus, we can let bottom half enabled,
+ * (preemption is disabled)
+ */
for_each_possible_cpu(cpu) {
if (cpu == curcpu)
@@ -744,7 +743,7 @@ static void get_counters(const struct xt_table_info *t,
}
xt_info_wrunlock(cpu);
}
- local_bh_enable();
+ put_cpu();
}
static struct xt_counters *alloc_counters(const struct xt_table *table)
@@ -758,7 +757,7 @@ 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 +1004,7 @@ 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 +1157,7 @@ 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..c439721b165 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -364,7 +364,7 @@ ipt_do_table(struct sk_buff *skb,
goto no_match;
}
- ADD_COUNTER(e->counters, ntohs(ip->tot_len), 1);
+ ADD_COUNTER(e->counters, skb->len, 1);
t = ipt_get_target(e);
IP_NF_ASSERT(t->u.kernel.target);
@@ -884,7 +884,7 @@ get_counters(const struct xt_table_info *t,
struct ipt_entry *iter;
unsigned int cpu;
unsigned int i;
- unsigned int curcpu;
+ unsigned int curcpu = get_cpu();
/* Instead of clearing (by a previous call to memset())
* the counters and using adds, we set the counters
@@ -894,14 +894,16 @@ get_counters(const struct xt_table_info *t,
* if new softirq were to run and call ipt_do_table
*/
local_bh_disable();
- curcpu = smp_processor_id();
-
i = 0;
xt_entry_foreach(iter, t->entries[curcpu], t->size) {
SET_COUNTER(counters[i], iter->counters.bcnt,
iter->counters.pcnt);
++i;
}
+ local_bh_enable();
+ /* Processing counters from other cpus, we can let bottom half enabled,
+ * (preemption is disabled)
+ */
for_each_possible_cpu(cpu) {
if (cpu == curcpu)
@@ -915,7 +917,7 @@ get_counters(const struct xt_table_info *t,
}
xt_info_wrunlock(cpu);
}
- local_bh_enable();
+ put_cpu();
}
static struct xt_counters *alloc_counters(const struct xt_table *table)
@@ -928,7 +930,7 @@ 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 +1354,7 @@ 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..3a43cf36db8 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;
}
@@ -462,7 +469,7 @@ struct arp_payload {
__be32 src_ip;
u_int8_t dst_hw[ETH_ALEN];
__be32 dst_ip;
-} __attribute__ ((packed));
+} __packed;
#ifdef DEBUG
static void arp_print(struct arp_payload *payload)
@@ -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/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c
index 5234f4f3499..915fc17d7ce 100644
--- a/net/ipv4/netfilter/ipt_LOG.c
+++ b/net/ipv4/netfilter/ipt_LOG.c
@@ -13,6 +13,7 @@
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/skbuff.h>
+#include <linux/if_arp.h>
#include <linux/ip.h>
#include <net/icmp.h>
#include <net/udp.h>
@@ -363,6 +364,42 @@ static void dump_packet(const struct nf_loginfo *info,
/* maxlen = 230+ 91 + 230 + 252 = 803 */
}
+static void dump_mac_header(const struct nf_loginfo *info,
+ const struct sk_buff *skb)
+{
+ struct net_device *dev = skb->dev;
+ unsigned int logflags = 0;
+
+ if (info->type == NF_LOG_TYPE_LOG)
+ logflags = info->u.log.logflags;
+
+ if (!(logflags & IPT_LOG_MACDECODE))
+ goto fallback;
+
+ switch (dev->type) {
+ case ARPHRD_ETHER:
+ printk("MACSRC=%pM MACDST=%pM MACPROTO=%04x ",
+ eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest,
+ ntohs(eth_hdr(skb)->h_proto));
+ return;
+ default:
+ break;
+ }
+
+fallback:
+ printk("MAC=");
+ if (dev->hard_header_len &&
+ skb->mac_header != skb->network_header) {
+ const unsigned char *p = skb_mac_header(skb);
+ unsigned int i;
+
+ printk("%02x", *p++);
+ for (i = 1; i < dev->hard_header_len; i++, p++)
+ printk(":%02x", *p);
+ }
+ printk(" ");
+}
+
static struct nf_loginfo default_loginfo = {
.type = NF_LOG_TYPE_LOG,
.u = {
@@ -404,20 +441,9 @@ ipt_log_packet(u_int8_t pf,
}
#endif
- if (in && !out) {
- /* MAC logging for input chain only. */
- printk("MAC=");
- if (skb->dev && skb->dev->hard_header_len &&
- skb->mac_header != skb->network_header) {
- int i;
- const unsigned char *p = skb_mac_header(skb);
- for (i = 0; i < skb->dev->hard_header_len; i++,p++)
- printk("%02x%c", *p,
- i==skb->dev->hard_header_len - 1
- ? ' ':':');
- } else
- printk(" ");
- }
+ /* MAC logging for input path only. */
+ if (in && !out)
+ dump_mac_header(loginfo, skb);
dump_packet(loginfo, skb, 0);
printk("\n");
diff --git a/net/ipv4/netfilter/ipt_NETMAP.c b/net/ipv4/netfilter/ipt_NETMAP.c
index f43867d1697..6cdb298f103 100644
--- a/net/ipv4/netfilter/ipt_NETMAP.c
+++ b/net/ipv4/netfilter/ipt_NETMAP.c
@@ -48,7 +48,8 @@ netmap_tg(struct sk_buff *skb, const struct xt_action_param *par)
NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING ||
par->hooknum == NF_INET_POST_ROUTING ||
- par->hooknum == NF_INET_LOCAL_OUT);
+ par->hooknum == NF_INET_LOCAL_OUT ||
+ par->hooknum == NF_INET_LOCAL_IN);
ct = nf_ct_get(skb, &ctinfo);
netmask = ~(mr->range[0].min_ip ^ mr->range[0].max_ip);
@@ -77,7 +78,8 @@ static struct xt_target netmap_tg_reg __read_mostly = {
.table = "nat",
.hooks = (1 << NF_INET_PRE_ROUTING) |
(1 << NF_INET_POST_ROUTING) |
- (1 << NF_INET_LOCAL_OUT),
+ (1 << NF_INET_LOCAL_OUT) |
+ (1 << NF_INET_LOCAL_IN),
.checkentry = netmap_tg_check,
.me = THIS_MODULE
};
diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c
index f5f4a888e4e..b254dafaf42 100644
--- a/net/ipv4/netfilter/ipt_REJECT.c
+++ b/net/ipv4/netfilter/ipt_REJECT.c
@@ -95,10 +95,11 @@ static void send_reset(struct sk_buff *oldskb, int hook)
}
tcph->rst = 1;
- tcph->check = tcp_v4_check(sizeof(struct tcphdr),
- niph->saddr, niph->daddr,
- csum_partial(tcph,
- sizeof(struct tcphdr), 0));
+ tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr,
+ niph->daddr, 0);
+ nskb->ip_summed = CHECKSUM_PARTIAL;
+ nskb->csum_start = (unsigned char *)tcph - nskb->head;
+ nskb->csum_offset = offsetof(struct tcphdr, check);
addr_type = RTN_UNSPEC;
if (hook != NF_INET_FORWARD
@@ -109,13 +110,12 @@ static void send_reset(struct sk_buff *oldskb, int hook)
addr_type = RTN_LOCAL;
/* ip_route_me_harder expects skb->dst to be set */
- skb_dst_set(nskb, dst_clone(skb_dst(oldskb)));
+ skb_dst_set_noref(nskb, skb_dst(oldskb));
if (ip_route_me_harder(nskb, addr_type))
goto free_nskb;
niph->ttl = dst_metric(skb_dst(nskb), RTAX_HOPLIMIT);
- nskb->ip_summed = CHECKSUM_NONE;
/* "Never happens" */
if (nskb->len > dst_mtu(skb_dst(nskb)))
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index cb763ae9ed9..eab8de32f20 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -66,6 +66,11 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
+ struct inet_sock *inet = inet_sk(skb->sk);
+
+ if (inet && inet->nodefrag)
+ return NF_ACCEPT;
+
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
#if !defined(CONFIG_NF_NAT) && !defined(CONFIG_NF_NAT_MODULE)
/* Previously seen (loopback)? Ignore. Do this before
diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index 4f8bddb760c..8c8632d9b93 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -261,14 +261,9 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple,
rcu_read_lock();
proto = __nf_nat_proto_find(orig_tuple->dst.protonum);
- /* Change protocol info to have some randomization */
- if (range->flags & IP_NAT_RANGE_PROTO_RANDOM) {
- proto->unique_tuple(tuple, range, maniptype, ct);
- goto out;
- }
-
/* Only bother mapping if it's not already in range and unique */
- if ((!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) ||
+ if (!(range->flags & IP_NAT_RANGE_PROTO_RANDOM) &&
+ (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) ||
proto->in_range(tuple, maniptype, &range->min, &range->max)) &&
!nf_nat_used_tuple(tuple, ct))
goto out;
@@ -440,7 +435,7 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct,
if (!skb_make_writable(skb, hdrlen + sizeof(*inside)))
return 0;
- inside = (void *)skb->data + ip_hdrlen(skb);
+ inside = (void *)skb->data + hdrlen;
/* We're actually going to mangle it beyond trivial checksum
adjustment, so make sure the current checksum is correct. */
@@ -470,12 +465,10 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct,
/* rcu_read_lock()ed by nf_hook_slow */
l4proto = __nf_ct_l4proto_find(PF_INET, inside->ip.protocol);
- if (!nf_ct_get_tuple(skb,
- ip_hdrlen(skb) + sizeof(struct icmphdr),
- (ip_hdrlen(skb) +
+ if (!nf_ct_get_tuple(skb, hdrlen + sizeof(struct icmphdr),
+ (hdrlen +
sizeof(struct icmphdr) + inside->ip.ihl * 4),
- (u_int16_t)AF_INET,
- inside->ip.protocol,
+ (u_int16_t)AF_INET, inside->ip.protocol,
&inner, l3proto, l4proto))
return 0;
@@ -484,15 +477,13 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct,
pass all hooks (locally-generated ICMP). Consider incoming
packet: PREROUTING (DST manip), routing produces ICMP, goes
through POSTROUTING (which must correct the DST manip). */
- if (!manip_pkt(inside->ip.protocol, skb,
- ip_hdrlen(skb) + sizeof(inside->icmp),
- &ct->tuplehash[!dir].tuple,
- !manip))
+ if (!manip_pkt(inside->ip.protocol, skb, hdrlen + sizeof(inside->icmp),
+ &ct->tuplehash[!dir].tuple, !manip))
return 0;
if (skb->ip_summed != CHECKSUM_PARTIAL) {
/* Reloading "inside" here since manip_pkt inner. */
- inside = (void *)skb->data + ip_hdrlen(skb);
+ inside = (void *)skb->data + hdrlen;
inside->icmp.checksum = 0;
inside->icmp.checksum =
csum_fold(skb_checksum(skb, hdrlen,
@@ -742,7 +733,7 @@ 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_proto_common.c b/net/ipv4/netfilter/nf_nat_proto_common.c
index 6c4f11f5144..3e61faf23a9 100644
--- a/net/ipv4/netfilter/nf_nat_proto_common.c
+++ b/net/ipv4/netfilter/nf_nat_proto_common.c
@@ -34,7 +34,7 @@ bool nf_nat_proto_in_range(const struct nf_conntrack_tuple *tuple,
}
EXPORT_SYMBOL_GPL(nf_nat_proto_in_range);
-bool nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
+void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
const struct nf_nat_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct,
@@ -53,7 +53,7 @@ bool nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED)) {
/* If it's dst rewrite, can't change port */
if (maniptype == IP_NAT_MANIP_DST)
- return false;
+ return;
if (ntohs(*portptr) < 1024) {
/* Loose convention: >> 512 is credential passing */
@@ -81,15 +81,15 @@ bool nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
else
off = *rover;
- for (i = 0; i < range_size; i++, off++) {
+ for (i = 0; ; ++off) {
*portptr = htons(min + off % range_size);
- if (nf_nat_used_tuple(tuple, ct))
+ if (++i != range_size && nf_nat_used_tuple(tuple, ct))
continue;
if (!(range->flags & IP_NAT_RANGE_PROTO_RANDOM))
*rover = off;
- return true;
+ return;
}
- return false;
+ return;
}
EXPORT_SYMBOL_GPL(nf_nat_proto_unique_tuple);
diff --git a/net/ipv4/netfilter/nf_nat_proto_dccp.c b/net/ipv4/netfilter/nf_nat_proto_dccp.c
index 22485ce306d..570faf2667b 100644
--- a/net/ipv4/netfilter/nf_nat_proto_dccp.c
+++ b/net/ipv4/netfilter/nf_nat_proto_dccp.c
@@ -22,14 +22,14 @@
static u_int16_t dccp_port_rover;
-static bool
+static void
dccp_unique_tuple(struct nf_conntrack_tuple *tuple,
const struct nf_nat_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
- return nf_nat_proto_unique_tuple(tuple, range, maniptype, ct,
- &dccp_port_rover);
+ nf_nat_proto_unique_tuple(tuple, range, maniptype, ct,
+ &dccp_port_rover);
}
static bool
diff --git a/net/ipv4/netfilter/nf_nat_proto_gre.c b/net/ipv4/netfilter/nf_nat_proto_gre.c
index d7e89201351..bc8d83a31c7 100644
--- a/net/ipv4/netfilter/nf_nat_proto_gre.c
+++ b/net/ipv4/netfilter/nf_nat_proto_gre.c
@@ -37,7 +37,7 @@ MODULE_AUTHOR("Harald Welte <laforge@gnumonks.org>");
MODULE_DESCRIPTION("Netfilter NAT protocol helper module for GRE");
/* generate unique tuple ... */
-static bool
+static void
gre_unique_tuple(struct nf_conntrack_tuple *tuple,
const struct nf_nat_range *range,
enum nf_nat_manip_type maniptype,
@@ -50,7 +50,7 @@ gre_unique_tuple(struct nf_conntrack_tuple *tuple,
/* If there is no master conntrack we are not PPTP,
do not change tuples */
if (!ct->master)
- return false;
+ return;
if (maniptype == IP_NAT_MANIP_SRC)
keyptr = &tuple->src.u.gre.key;
@@ -68,14 +68,14 @@ gre_unique_tuple(struct nf_conntrack_tuple *tuple,
pr_debug("min = %u, range_size = %u\n", min, range_size);
- for (i = 0; i < range_size; i++, key++) {
+ for (i = 0; ; ++key) {
*keyptr = htons(min + key % range_size);
- if (!nf_nat_used_tuple(tuple, ct))
- return true;
+ if (++i == range_size || !nf_nat_used_tuple(tuple, ct))
+ return;
}
pr_debug("%p: no NAT mapping\n", ct);
- return false;
+ return;
}
/* manipulate a GRE packet according to maniptype */
diff --git a/net/ipv4/netfilter/nf_nat_proto_icmp.c b/net/ipv4/netfilter/nf_nat_proto_icmp.c
index 19a8b0b07d8..5744c3ec847 100644
--- a/net/ipv4/netfilter/nf_nat_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_nat_proto_icmp.c
@@ -27,7 +27,7 @@ icmp_in_range(const struct nf_conntrack_tuple *tuple,
ntohs(tuple->src.u.icmp.id) <= ntohs(max->icmp.id);
}
-static bool
+static void
icmp_unique_tuple(struct nf_conntrack_tuple *tuple,
const struct nf_nat_range *range,
enum nf_nat_manip_type maniptype,
@@ -42,13 +42,13 @@ icmp_unique_tuple(struct nf_conntrack_tuple *tuple,
if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED))
range_size = 0xFFFF;
- for (i = 0; i < range_size; i++, id++) {
+ for (i = 0; ; ++id) {
tuple->src.u.icmp.id = htons(ntohs(range->min.icmp.id) +
(id % range_size));
- if (!nf_nat_used_tuple(tuple, ct))
- return true;
+ if (++i == range_size || !nf_nat_used_tuple(tuple, ct))
+ return;
}
- return false;
+ return;
}
static bool
diff --git a/net/ipv4/netfilter/nf_nat_proto_sctp.c b/net/ipv4/netfilter/nf_nat_proto_sctp.c
index 3fc598eeeb1..756331d4266 100644
--- a/net/ipv4/netfilter/nf_nat_proto_sctp.c
+++ b/net/ipv4/netfilter/nf_nat_proto_sctp.c
@@ -16,14 +16,14 @@
static u_int16_t nf_sctp_port_rover;
-static bool
+static void
sctp_unique_tuple(struct nf_conntrack_tuple *tuple,
const struct nf_nat_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
- return nf_nat_proto_unique_tuple(tuple, range, maniptype, ct,
- &nf_sctp_port_rover);
+ nf_nat_proto_unique_tuple(tuple, range, maniptype, ct,
+ &nf_sctp_port_rover);
}
static bool
diff --git a/net/ipv4/netfilter/nf_nat_proto_tcp.c b/net/ipv4/netfilter/nf_nat_proto_tcp.c
index 399e2cfa263..aa460a595d5 100644
--- a/net/ipv4/netfilter/nf_nat_proto_tcp.c
+++ b/net/ipv4/netfilter/nf_nat_proto_tcp.c
@@ -20,14 +20,13 @@
static u_int16_t tcp_port_rover;
-static bool
+static void
tcp_unique_tuple(struct nf_conntrack_tuple *tuple,
const struct nf_nat_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
- return nf_nat_proto_unique_tuple(tuple, range, maniptype, ct,
- &tcp_port_rover);
+ nf_nat_proto_unique_tuple(tuple, range, maniptype, ct, &tcp_port_rover);
}
static bool
diff --git a/net/ipv4/netfilter/nf_nat_proto_udp.c b/net/ipv4/netfilter/nf_nat_proto_udp.c
index 9e61c79492e..dfe65c7e292 100644
--- a/net/ipv4/netfilter/nf_nat_proto_udp.c
+++ b/net/ipv4/netfilter/nf_nat_proto_udp.c
@@ -19,14 +19,13 @@
static u_int16_t udp_port_rover;
-static bool
+static void
udp_unique_tuple(struct nf_conntrack_tuple *tuple,
const struct nf_nat_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
- return nf_nat_proto_unique_tuple(tuple, range, maniptype, ct,
- &udp_port_rover);
+ nf_nat_proto_unique_tuple(tuple, range, maniptype, ct, &udp_port_rover);
}
static bool
diff --git a/net/ipv4/netfilter/nf_nat_proto_udplite.c b/net/ipv4/netfilter/nf_nat_proto_udplite.c
index 440a229bbd8..3cc8c8af39e 100644
--- a/net/ipv4/netfilter/nf_nat_proto_udplite.c
+++ b/net/ipv4/netfilter/nf_nat_proto_udplite.c
@@ -18,14 +18,14 @@
static u_int16_t udplite_port_rover;
-static bool
+static void
udplite_unique_tuple(struct nf_conntrack_tuple *tuple,
const struct nf_nat_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
- return nf_nat_proto_unique_tuple(tuple, range, maniptype, ct,
- &udplite_port_rover);
+ nf_nat_proto_unique_tuple(tuple, range, maniptype, ct,
+ &udplite_port_rover);
}
static bool
diff --git a/net/ipv4/netfilter/nf_nat_proto_unknown.c b/net/ipv4/netfilter/nf_nat_proto_unknown.c
index 14381c62ace..a50f2bc1c73 100644
--- a/net/ipv4/netfilter/nf_nat_proto_unknown.c
+++ b/net/ipv4/netfilter/nf_nat_proto_unknown.c
@@ -26,14 +26,14 @@ static bool unknown_in_range(const struct nf_conntrack_tuple *tuple,
return true;
}
-static bool unknown_unique_tuple(struct nf_conntrack_tuple *tuple,
+static void unknown_unique_tuple(struct nf_conntrack_tuple *tuple,
const struct nf_nat_range *range,
enum nf_nat_manip_type maniptype,
const struct nf_conn *ct)
{
/* Sorry: we can't help you; if it's not unique, we can't frob
anything. */
- return false;
+ return;
}
static bool
diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c
index 98ed78281ae..ebbd319f62f 100644
--- a/net/ipv4/netfilter/nf_nat_rule.c
+++ b/net/ipv4/netfilter/nf_nat_rule.c
@@ -28,7 +28,8 @@
#define NAT_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | \
(1 << NF_INET_POST_ROUTING) | \
- (1 << NF_INET_LOCAL_OUT))
+ (1 << NF_INET_LOCAL_OUT) | \
+ (1 << NF_INET_LOCAL_IN))
static const struct xt_table nat_table = {
.name = "nat",
@@ -45,7 +46,8 @@ ipt_snat_target(struct sk_buff *skb, const struct xt_action_param *par)
enum ip_conntrack_info ctinfo;
const struct nf_nat_multi_range_compat *mr = par->targinfo;
- NF_CT_ASSERT(par->hooknum == NF_INET_POST_ROUTING);
+ NF_CT_ASSERT(par->hooknum == NF_INET_POST_ROUTING ||
+ par->hooknum == NF_INET_LOCAL_IN);
ct = nf_ct_get(skb, &ctinfo);
@@ -99,7 +101,7 @@ static int ipt_dnat_checkentry(const struct xt_tgchk_param *par)
return 0;
}
-unsigned int
+static unsigned int
alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
{
/* Force range to this IP; let proto decide mapping for
@@ -141,7 +143,7 @@ static struct xt_target ipt_snat_reg __read_mostly = {
.target = ipt_snat_target,
.targetsize = sizeof(struct nf_nat_multi_range_compat),
.table = "nat",
- .hooks = 1 << NF_INET_POST_ROUTING,
+ .hooks = (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_IN),
.checkentry = ipt_snat_checkentry,
.family = AF_INET,
};
diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c
index beb25819c9c..95481fee8bd 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);
@@ -131,13 +131,7 @@ nf_nat_fn(unsigned int hooknum,
if (!nf_nat_initialized(ct, maniptype)) {
unsigned int ret;
- if (hooknum == NF_INET_LOCAL_IN)
- /* LOCAL_IN hook doesn't have a chain! */
- ret = alloc_null_binding(ct, hooknum);
- else
- ret = nf_nat_rule_find(skb, hooknum, in, out,
- ct);
-
+ ret = nf_nat_rule_find(skb, hooknum, in, out, ct);
if (ret != NF_ACCEPT)
return ret;
} else
generated by cgit v1.2.3 (git 2.39.1) at 2024-04-28 03:39:04 +0000