#include <linux/netdevice.h>
#include <linux/socket.h>
#include <linux/mm.h>
+#include <linux/rculist_nulls.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_l3proto.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_extend.h>
#include <net/netfilter/nf_conntrack_acct.h>
+#include <net/netfilter/nf_conntrack_ecache.h>
#include <net/netfilter/nf_nat.h>
#include <net/netfilter/nf_nat_core.h>
clean_from_lists(struct nf_conn *ct)
{
pr_debug("clean_from_lists(%p)\n", ct);
- hlist_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode);
- hlist_del_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnode);
+ hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
+ hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode);
/* Destroy all pending expectations */
nf_ct_remove_expectations(ct);
/* We overload first tuple to link into unconfirmed list. */
if (!nf_ct_is_confirmed(ct)) {
- BUG_ON(hlist_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode));
- hlist_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode);
+ BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode));
+ hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
}
NF_CT_STAT_INC(net, delete);
{
struct nf_conn *ct = (void *)ul_conntrack;
struct net *net = nf_ct_net(ct);
- struct nf_conn_help *help = nfct_help(ct);
- struct nf_conntrack_helper *helper;
-
- if (help) {
- rcu_read_lock();
- helper = rcu_dereference(help->helper);
- if (helper && helper->destroy)
- helper->destroy(ct);
- rcu_read_unlock();
- }
+ nf_ct_helper_destroy(ct);
spin_lock_bh(&nf_conntrack_lock);
/* Inside lock so preempt is disabled on module removal path.
* Otherwise we can get spurious warnings. */
nf_ct_put(ct);
}
+/*
+ * Warning :
+ * - Caller must take a reference on returned object
+ * and recheck nf_ct_tuple_equal(tuple, &h->tuple)
+ * OR
+ * - Caller must lock nf_conntrack_lock before calling this function
+ */
struct nf_conntrack_tuple_hash *
__nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple)
{
struct nf_conntrack_tuple_hash *h;
- struct hlist_node *n;
+ struct hlist_nulls_node *n;
unsigned int hash = hash_conntrack(tuple);
/* Disable BHs the entire time since we normally need to disable them
* at least once for the stats anyway.
*/
local_bh_disable();
- hlist_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnode) {
+begin:
+ hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) {
if (nf_ct_tuple_equal(tuple, &h->tuple)) {
NF_CT_STAT_INC(net, found);
local_bh_enable();
}
NF_CT_STAT_INC(net, searched);
}
+ /*
+ * if the nulls value we got at the end of this lookup is
+ * not the expected one, we must restart lookup.
+ * We probably met an item that was moved to another chain.
+ */
+ if (get_nulls_value(n) != hash)
+ goto begin;
local_bh_enable();
return NULL;
struct nf_conn *ct;
rcu_read_lock();
+begin:
h = __nf_conntrack_find(net, tuple);
if (h) {
ct = nf_ct_tuplehash_to_ctrack(h);
if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use)))
h = NULL;
+ else {
+ if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple))) {
+ nf_ct_put(ct);
+ goto begin;
+ }
+ }
}
rcu_read_unlock();
{
struct net *net = nf_ct_net(ct);
- hlist_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode,
+ hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
&net->ct.hash[hash]);
- hlist_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnode,
+ hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode,
&net->ct.hash[repl_hash]);
}
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct;
struct nf_conn_help *help;
- struct hlist_node *n;
+ struct hlist_nulls_node *n;
enum ip_conntrack_info ctinfo;
struct net *net;
/* See if there's one in the list already, including reverse:
NAT could have grabbed it without realizing, since we're
not in the hash. If there is, we lost race. */
- hlist_for_each_entry(h, n, &net->ct.hash[hash], hnode)
+ hlist_nulls_for_each_entry(h, n, &net->ct.hash[hash], hnnode)
if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
&h->tuple))
goto out;
- hlist_for_each_entry(h, n, &net->ct.hash[repl_hash], hnode)
+ hlist_nulls_for_each_entry(h, n, &net->ct.hash[repl_hash], hnnode)
if (nf_ct_tuple_equal(&ct->tuplehash[IP_CT_DIR_REPLY].tuple,
&h->tuple))
goto out;
/* Remove from unconfirmed list */
- hlist_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode);
+ hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
__nf_conntrack_hash_insert(ct, hash, repl_hash);
/* Timer relative to confirmation time, not original
help = nfct_help(ct);
if (help && help->helper)
nf_conntrack_event_cache(IPCT_HELPER, ct);
-#ifdef CONFIG_NF_NAT_NEEDED
- if (test_bit(IPS_SRC_NAT_DONE_BIT, &ct->status) ||
- test_bit(IPS_DST_NAT_DONE_BIT, &ct->status))
- nf_conntrack_event_cache(IPCT_NATINFO, ct);
-#endif
+
nf_conntrack_event_cache(master_ct(ct) ?
IPCT_RELATED : IPCT_NEW, ct);
return NF_ACCEPT;
{
struct net *net = nf_ct_net(ignored_conntrack);
struct nf_conntrack_tuple_hash *h;
- struct hlist_node *n;
+ struct hlist_nulls_node *n;
unsigned int hash = hash_conntrack(tuple);
/* Disable BHs the entire time since we need to disable them at
* least once for the stats anyway.
*/
rcu_read_lock_bh();
- hlist_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnode) {
+ hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash], hnnode) {
if (nf_ct_tuplehash_to_ctrack(h) != ignored_conntrack &&
nf_ct_tuple_equal(tuple, &h->tuple)) {
NF_CT_STAT_INC(net, found);
/* Use oldest entry, which is roughly LRU */
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct = NULL, *tmp;
- struct hlist_node *n;
+ struct hlist_nulls_node *n;
unsigned int i, cnt = 0;
int dropped = 0;
rcu_read_lock();
for (i = 0; i < nf_conntrack_htable_size; i++) {
- hlist_for_each_entry_rcu(h, n, &net->ct.hash[hash],
- hnode) {
+ hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[hash],
+ hnnode) {
tmp = nf_ct_tuplehash_to_ctrack(h);
if (!test_bit(IPS_ASSURED_BIT, &tmp->status))
ct = tmp;
return ERR_PTR(-ENOMEM);
}
+ spin_lock_init(&ct->lock);
atomic_set(&ct->ct_general.use, 1);
ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig;
ct->tuplehash[IP_CT_DIR_REPLY].tuple = *repl;
#ifdef CONFIG_NET_NS
ct->ct_net = net;
#endif
- INIT_RCU_HEAD(&ct->rcu);
return ct;
}
EXPORT_SYMBOL_GPL(nf_conntrack_alloc);
-static void nf_conntrack_free_rcu(struct rcu_head *head)
-{
- struct nf_conn *ct = container_of(head, struct nf_conn, rcu);
-
- nf_ct_ext_free(ct);
- kmem_cache_free(nf_conntrack_cachep, ct);
-}
-
void nf_conntrack_free(struct nf_conn *ct)
{
struct net *net = nf_ct_net(ct);
nf_ct_ext_destroy(ct);
atomic_dec(&net->ct.count);
- call_rcu(&ct->rcu, nf_conntrack_free_rcu);
+ nf_ct_ext_free(ct);
+ kmem_cache_free(nf_conntrack_cachep, ct);
}
EXPORT_SYMBOL_GPL(nf_conntrack_free);
}
nf_ct_acct_ext_add(ct, GFP_ATOMIC);
+ nf_ct_ecache_ext_add(ct, GFP_ATOMIC);
spin_lock_bh(&nf_conntrack_lock);
exp = nf_ct_find_expectation(net, tuple);
}
/* Overload tuple linked list to put us in unconfirmed list. */
- hlist_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnode,
+ hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
&net->ct.unconfirmed);
spin_unlock_bh(&nf_conntrack_lock);
unsigned long extra_jiffies,
int do_acct)
{
- int event = 0;
-
NF_CT_ASSERT(ct->timeout.data == (unsigned long)ct);
NF_CT_ASSERT(skb);
- spin_lock_bh(&nf_conntrack_lock);
-
/* Only update if this is not a fixed timeout */
if (test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status))
goto acct;
/* If not in hash table, timer will not be active yet */
if (!nf_ct_is_confirmed(ct)) {
ct->timeout.expires = extra_jiffies;
- event = IPCT_REFRESH;
} else {
unsigned long newtime = jiffies + extra_jiffies;
/* Only update the timeout if the new timeout is at least
HZ jiffies from the old timeout. Need del_timer for race
avoidance (may already be dying). */
- if (newtime - ct->timeout.expires >= HZ
- && del_timer(&ct->timeout)) {
- ct->timeout.expires = newtime;
- add_timer(&ct->timeout);
- event = IPCT_REFRESH;
- }
+ if (newtime - ct->timeout.expires >= HZ)
+ mod_timer_pending(&ct->timeout, newtime);
}
acct:
acct = nf_conn_acct_find(ct);
if (acct) {
+ spin_lock_bh(&ct->lock);
acct[CTINFO2DIR(ctinfo)].packets++;
acct[CTINFO2DIR(ctinfo)].bytes +=
skb->len - skb_network_offset(skb);
+ spin_unlock_bh(&ct->lock);
}
}
-
- spin_unlock_bh(&nf_conntrack_lock);
-
- /* must be unlocked when calling event cache */
- if (event)
- nf_conntrack_event_cache(event, ct);
}
EXPORT_SYMBOL_GPL(__nf_ct_refresh_acct);
if (do_acct) {
struct nf_conn_counter *acct;
- spin_lock_bh(&nf_conntrack_lock);
acct = nf_conn_acct_find(ct);
if (acct) {
+ spin_lock_bh(&ct->lock);
acct[CTINFO2DIR(ctinfo)].packets++;
acct[CTINFO2DIR(ctinfo)].bytes +=
skb->len - skb_network_offset(skb);
+ spin_unlock_bh(&ct->lock);
}
- spin_unlock_bh(&nf_conntrack_lock);
}
if (del_timer(&ct->timeout)) {
return 0;
}
EXPORT_SYMBOL_GPL(nf_ct_port_nlattr_to_tuple);
+
+int nf_ct_port_nlattr_tuple_size(void)
+{
+ return nla_policy_len(nf_ct_port_nla_policy, CTA_PROTO_MAX + 1);
+}
+EXPORT_SYMBOL_GPL(nf_ct_port_nlattr_tuple_size);
#endif
/* Used by ipt_REJECT and ip6t_REJECT. */
{
struct nf_conntrack_tuple_hash *h;
struct nf_conn *ct;
- struct hlist_node *n;
+ struct hlist_nulls_node *n;
spin_lock_bh(&nf_conntrack_lock);
for (; *bucket < nf_conntrack_htable_size; (*bucket)++) {
- hlist_for_each_entry(h, n, &net->ct.hash[*bucket], hnode) {
+ hlist_nulls_for_each_entry(h, n, &net->ct.hash[*bucket], hnnode) {
ct = nf_ct_tuplehash_to_ctrack(h);
if (iter(ct, data))
goto found;
}
}
- hlist_for_each_entry(h, n, &net->ct.unconfirmed, hnode) {
+ hlist_nulls_for_each_entry(h, n, &net->ct.unconfirmed, hnnode) {
ct = nf_ct_tuplehash_to_ctrack(h);
if (iter(ct, data))
set_bit(IPS_DYING_BIT, &ct->status);
int report;
};
-static int kill_all(struct nf_conn *i, void *data)
+static int kill_report(struct nf_conn *i, void *data)
{
struct __nf_ct_flush_report *fr = (struct __nf_ct_flush_report *)data;
return 1;
}
-void nf_ct_free_hashtable(struct hlist_head *hash, int vmalloced, unsigned int size)
+static int kill_all(struct nf_conn *i, void *data)
+{
+ return 1;
+}
+
+void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size)
{
if (vmalloced)
vfree(hash);
}
EXPORT_SYMBOL_GPL(nf_ct_free_hashtable);
-void nf_conntrack_flush(struct net *net, u32 pid, int report)
+void nf_conntrack_flush_report(struct net *net, u32 pid, int report)
{
struct __nf_ct_flush_report fr = {
.pid = pid,
.report = report,
};
- nf_ct_iterate_cleanup(net, kill_all, &fr);
+ nf_ct_iterate_cleanup(net, kill_report, &fr);
}
-EXPORT_SYMBOL_GPL(nf_conntrack_flush);
+EXPORT_SYMBOL_GPL(nf_conntrack_flush_report);
static void nf_conntrack_cleanup_init_net(void)
{
static void nf_conntrack_cleanup_net(struct net *net)
{
- nf_ct_event_cache_flush(net);
- nf_conntrack_ecache_fini(net);
i_see_dead_people:
- nf_conntrack_flush(net, 0, 0);
+ nf_ct_iterate_cleanup(net, kill_all, NULL);
if (atomic_read(&net->ct.count) != 0) {
schedule();
goto i_see_dead_people;
nf_ct_free_hashtable(net->ct.hash, net->ct.hash_vmalloc,
nf_conntrack_htable_size);
+ nf_conntrack_ecache_fini(net);
nf_conntrack_acct_fini(net);
nf_conntrack_expect_fini(net);
free_percpu(net->ct.stat);
}
}
-struct hlist_head *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced)
+void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int nulls)
{
- struct hlist_head *hash;
- unsigned int size, i;
+ struct hlist_nulls_head *hash;
+ unsigned int nr_slots, i;
+ size_t sz;
*vmalloced = 0;
- size = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_head));
- hash = (void*)__get_free_pages(GFP_KERNEL|__GFP_NOWARN,
- get_order(sizeof(struct hlist_head)
- * size));
+ BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head));
+ nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head));
+ sz = nr_slots * sizeof(struct hlist_nulls_head);
+ hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO,
+ get_order(sz));
if (!hash) {
*vmalloced = 1;
printk(KERN_WARNING "nf_conntrack: falling back to vmalloc.\n");
- hash = vmalloc(sizeof(struct hlist_head) * size);
+ hash = __vmalloc(sz, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL);
}
- if (hash)
- for (i = 0; i < size; i++)
- INIT_HLIST_HEAD(&hash[i]);
+ if (hash && nulls)
+ for (i = 0; i < nr_slots; i++)
+ INIT_HLIST_NULLS_HEAD(&hash[i], i);
return hash;
}
int i, bucket, vmalloced, old_vmalloced;
unsigned int hashsize, old_size;
int rnd;
- struct hlist_head *hash, *old_hash;
+ struct hlist_nulls_head *hash, *old_hash;
struct nf_conntrack_tuple_hash *h;
/* On boot, we can set this without any fancy locking. */
if (!hashsize)
return -EINVAL;
- hash = nf_ct_alloc_hashtable(&hashsize, &vmalloced);
+ hash = nf_ct_alloc_hashtable(&hashsize, &vmalloced, 1);
if (!hash)
return -ENOMEM;
*/
spin_lock_bh(&nf_conntrack_lock);
for (i = 0; i < nf_conntrack_htable_size; i++) {
- while (!hlist_empty(&init_net.ct.hash[i])) {
- h = hlist_entry(init_net.ct.hash[i].first,
- struct nf_conntrack_tuple_hash, hnode);
- hlist_del_rcu(&h->hnode);
+ while (!hlist_nulls_empty(&init_net.ct.hash[i])) {
+ h = hlist_nulls_entry(init_net.ct.hash[i].first,
+ struct nf_conntrack_tuple_hash, hnnode);
+ hlist_nulls_del_rcu(&h->hnnode);
bucket = __hash_conntrack(&h->tuple, hashsize, rnd);
- hlist_add_head(&h->hnode, &hash[bucket]);
+ hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]);
}
}
old_size = nf_conntrack_htable_size;
nf_conntrack_cachep = kmem_cache_create("nf_conntrack",
sizeof(struct nf_conn),
- 0, 0, NULL);
+ 0, SLAB_DESTROY_BY_RCU, NULL);
if (!nf_conntrack_cachep) {
printk(KERN_ERR "Unable to create nf_conn slab cache\n");
ret = -ENOMEM;
int ret;
atomic_set(&net->ct.count, 0);
- INIT_HLIST_HEAD(&net->ct.unconfirmed);
+ INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, 0);
net->ct.stat = alloc_percpu(struct ip_conntrack_stat);
if (!net->ct.stat) {
ret = -ENOMEM;
goto err_stat;
}
- ret = nf_conntrack_ecache_init(net);
- if (ret < 0)
- goto err_ecache;
net->ct.hash = nf_ct_alloc_hashtable(&nf_conntrack_htable_size,
- &net->ct.hash_vmalloc);
+ &net->ct.hash_vmalloc, 1);
if (!net->ct.hash) {
ret = -ENOMEM;
printk(KERN_ERR "Unable to create nf_conntrack_hash\n");
ret = nf_conntrack_acct_init(net);
if (ret < 0)
goto err_acct;
+ ret = nf_conntrack_ecache_init(net);
+ if (ret < 0)
+ goto err_ecache;
/* Set up fake conntrack:
- to never be deleted, not in any hashes */
return 0;
+err_ecache:
+ nf_conntrack_acct_fini(net);
err_acct:
nf_conntrack_expect_fini(net);
err_expect:
nf_ct_free_hashtable(net->ct.hash, net->ct.hash_vmalloc,
nf_conntrack_htable_size);
err_hash:
- nf_conntrack_ecache_fini(net);
-err_ecache:
free_percpu(net->ct.stat);
err_stat:
return ret;