#include <linux/types.h>
#include <linux/netfilter.h>
#include <linux/module.h>
+#include <linux/sched.h>
#include <linux/skbuff.h>
#include <linux/proc_fs.h>
#include <linux/vmalloc.h>
#include <linux/netdevice.h>
#include <linux/socket.h>
#include <linux/mm.h>
+#include <linux/nsproxy.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>
int (*nfnetlink_parse_nat_setup_hook)(struct nf_conn *ct,
enum nf_nat_manip_type manip,
- struct nlattr *attr) __read_mostly;
+ const struct nlattr *attr) __read_mostly;
EXPORT_SYMBOL_GPL(nfnetlink_parse_nat_setup_hook);
DEFINE_SPINLOCK(nf_conntrack_lock);
unsigned int nf_conntrack_htable_size __read_mostly;
EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);
-int nf_conntrack_max __read_mostly;
+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);
-static struct kmem_cache *nf_conntrack_cachep __read_mostly;
-
static int nf_conntrack_hash_rnd_initted;
static unsigned int nf_conntrack_hash_rnd;
return ((u64)h * size) >> 32;
}
-static inline u_int32_t hash_conntrack(const struct nf_conntrack_tuple *tuple)
+static inline u_int32_t hash_conntrack(const struct net *net,
+ const struct nf_conntrack_tuple *tuple)
{
- return __hash_conntrack(tuple, nf_conntrack_htable_size,
+ return __hash_conntrack(tuple, net->ct.htable_size,
nf_conntrack_hash_rnd);
}
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);
NF_CT_ASSERT(atomic_read(&nfct->use) == 0);
NF_CT_ASSERT(!timer_pending(&ct->timeout));
- if (!test_bit(IPS_DYING_BIT, &ct->status))
- nf_conntrack_event(IPCT_DESTROY, ct);
- set_bit(IPS_DYING_BIT, &ct->status);
-
/* To make sure we don't get any weird locking issues here:
* destroy_conntrack() MUST NOT be called with a write lock
* to nf_conntrack_lock!!! -HW */
/* 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);
nf_conntrack_free(ct);
}
-static void death_by_timeout(unsigned long ul_conntrack)
+void nf_ct_delete_from_lists(struct nf_conn *ct)
{
- 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_STAT_INC(net, delete_list);
clean_from_lists(ct);
spin_unlock_bh(&nf_conntrack_lock);
+}
+EXPORT_SYMBOL_GPL(nf_ct_delete_from_lists);
+
+static void death_by_event(unsigned long ul_conntrack)
+{
+ struct nf_conn *ct = (void *)ul_conntrack;
+ struct net *net = nf_ct_net(ct);
+
+ if (nf_conntrack_event(IPCT_DESTROY, ct) < 0) {
+ /* bad luck, let's retry again */
+ ct->timeout.expires = jiffies +
+ (random32() % net->ct.sysctl_events_retry_timeout);
+ add_timer(&ct->timeout);
+ return;
+ }
+ /* we've got the event delivered, now it's dying */
+ set_bit(IPS_DYING_BIT, &ct->status);
+ spin_lock(&nf_conntrack_lock);
+ hlist_nulls_del(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
+ spin_unlock(&nf_conntrack_lock);
nf_ct_put(ct);
}
+void nf_ct_insert_dying_list(struct nf_conn *ct)
+{
+ struct net *net = nf_ct_net(ct);
+
+ /* add this conntrack to the dying list */
+ spin_lock_bh(&nf_conntrack_lock);
+ hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
+ &net->ct.dying);
+ spin_unlock_bh(&nf_conntrack_lock);
+ /* set a new timer to retry event delivery */
+ setup_timer(&ct->timeout, death_by_event, (unsigned long)ct);
+ ct->timeout.expires = jiffies +
+ (random32() % net->ct.sysctl_events_retry_timeout);
+ add_timer(&ct->timeout);
+}
+EXPORT_SYMBOL_GPL(nf_ct_insert_dying_list);
+
+static void death_by_timeout(unsigned long ul_conntrack)
+{
+ struct nf_conn *ct = (void *)ul_conntrack;
+
+ if (!test_bit(IPS_DYING_BIT, &ct->status) &&
+ unlikely(nf_conntrack_event(IPCT_DESTROY, ct) < 0)) {
+ /* destroy event was not delivered */
+ nf_ct_delete_from_lists(ct);
+ nf_ct_insert_dying_list(ct);
+ return;
+ }
+ set_bit(IPS_DYING_BIT, &ct->status);
+ nf_ct_delete_from_lists(ct);
+ 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;
- unsigned int hash = hash_conntrack(tuple);
+ struct hlist_nulls_node *n;
+ unsigned int hash = hash_conntrack(net, 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)))
+ if (unlikely(nf_ct_is_dying(ct) ||
+ !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]);
}
void nf_conntrack_hash_insert(struct nf_conn *ct)
{
+ struct net *net = nf_ct_net(ct);
unsigned int hash, repl_hash;
- hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
- repl_hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+ hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+ repl_hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
__nf_conntrack_hash_insert(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;
if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
return NF_ACCEPT;
- hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
- repl_hash = hash_conntrack(&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+ hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+ repl_hash = hash_conntrack(net, &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
/* We're not in hash table, and we refuse to set up related
connections for unconfirmed conns. But packet copies and
/* 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
setting time, otherwise we'd get timer wrap in
weird delay cases. */
add_timer(&ct->timeout);
atomic_inc(&ct->ct_general.use);
set_bit(IPS_CONFIRMED_BIT, &ct->status);
+
+ /* Since the lookup is lockless, hash insertion must be done after
+ * starting the timer and setting the CONFIRMED bit. The RCU barriers
+ * guarantee that no other CPU can find the conntrack before the above
+ * stores are visible.
+ */
+ __nf_conntrack_hash_insert(ct, hash, repl_hash);
NF_CT_STAT_INC(net, insert);
spin_unlock_bh(&nf_conntrack_lock);
+
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;
- unsigned int hash = hash_conntrack(tuple);
+ struct hlist_nulls_node *n;
+ unsigned int hash = hash_conntrack(net, 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) {
+ for (i = 0; i < net->ct.htable_size; i++) {
+ 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;
cnt++;
}
- if (ct && unlikely(!atomic_inc_not_zero(&ct->ct_general.use)))
- ct = NULL;
- if (ct || cnt >= NF_CT_EVICTION_RANGE)
+ if (ct != NULL) {
+ if (likely(!nf_ct_is_dying(ct) &&
+ atomic_inc_not_zero(&ct->ct_general.use)))
+ break;
+ else
+ ct = NULL;
+ }
+
+ if (cnt >= NF_CT_EVICTION_RANGE)
break;
- hash = (hash + 1) % nf_conntrack_htable_size;
+
+ hash = (hash + 1) % net->ct.htable_size;
}
rcu_read_unlock();
struct nf_conn *ct;
if (unlikely(!nf_conntrack_hash_rnd_initted)) {
- get_random_bytes(&nf_conntrack_hash_rnd, 4);
+ get_random_bytes(&nf_conntrack_hash_rnd,
+ sizeof(nf_conntrack_hash_rnd));
nf_conntrack_hash_rnd_initted = 1;
}
if (nf_conntrack_max &&
unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) {
- unsigned int hash = hash_conntrack(orig);
+ unsigned int hash = hash_conntrack(net, orig);
if (!early_drop(net, hash)) {
atomic_dec(&net->ct.count);
if (net_ratelimit())
}
}
- ct = kmem_cache_zalloc(nf_conntrack_cachep, gfp);
+ /*
+ * Do not use kmem_cache_zalloc(), as this cache uses
+ * SLAB_DESTROY_BY_RCU.
+ */
+ ct = kmem_cache_alloc(net->ct.nf_conntrack_cachep, gfp);
if (ct == NULL) {
pr_debug("nf_conntrack_alloc: Can't alloc conntrack.\n");
atomic_dec(&net->ct.count);
return ERR_PTR(-ENOMEM);
}
-
- atomic_set(&ct->ct_general.use, 1);
+ /*
+ * Let ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.next
+ * and ct->tuplehash[IP_CT_DIR_REPLY].hnnode.next unchanged.
+ */
+ memset(&ct->tuplehash[IP_CT_DIR_MAX], 0,
+ sizeof(*ct) - offsetof(struct nf_conn, tuplehash[IP_CT_DIR_MAX]));
+ spin_lock_init(&ct->lock);
ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig;
+ ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.pprev = NULL;
ct->tuplehash[IP_CT_DIR_REPLY].tuple = *repl;
+ ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev = NULL;
/* Don't set timer yet: wait for confirmation */
setup_timer(&ct->timeout, death_by_timeout, (unsigned long)ct);
#ifdef CONFIG_NET_NS
ct->ct_net = net;
#endif
- INIT_RCU_HEAD(&ct->rcu);
+ /*
+ * changes to lookup keys must be done before setting refcnt to 1
+ */
+ smp_wmb();
+ atomic_set(&ct->ct_general.use, 1);
return ct;
}
EXPORT_SYMBOL_GPL(nf_conntrack_alloc);
-static void nf_conntrack_free_rcu(struct rcu_head *head)
+void nf_conntrack_free(struct nf_conn *ct)
{
- struct nf_conn *ct = container_of(head, struct nf_conn, rcu);
struct net *net = nf_ct_net(ct);
- nf_ct_ext_free(ct);
- kmem_cache_free(nf_conntrack_cachep, ct);
- atomic_dec(&net->ct.count);
-}
-
-void nf_conntrack_free(struct nf_conn *ct)
-{
nf_ct_ext_destroy(ct);
- call_rcu(&ct->rcu, nf_conntrack_free_rcu);
+ atomic_dec(&net->ct.count);
+ nf_ct_ext_free(ct);
+ kmem_cache_free(net->ct.nf_conntrack_cachep, ct);
}
EXPORT_SYMBOL_GPL(nf_conntrack_free);
/* Allocate a new conntrack: we return -ENOMEM if classification
failed due to stress. Otherwise it really is unclassifiable. */
static struct nf_conntrack_tuple_hash *
-init_conntrack(struct net *net,
+init_conntrack(struct net *net, struct nf_conn *tmpl,
const struct nf_conntrack_tuple *tuple,
struct nf_conntrack_l3proto *l3proto,
struct nf_conntrack_l4proto *l4proto,
struct nf_conn *ct;
struct nf_conn_help *help;
struct nf_conntrack_tuple repl_tuple;
+ struct nf_conntrack_ecache *ecache;
struct nf_conntrack_expect *exp;
if (!nf_ct_invert_tuple(&repl_tuple, tuple, l3proto, l4proto)) {
nf_ct_acct_ext_add(ct, GFP_ATOMIC);
+ ecache = tmpl ? nf_ct_ecache_find(tmpl) : NULL;
+ nf_ct_ecache_ext_add(ct, ecache ? ecache->ctmask : 0,
+ ecache ? ecache->expmask : 0,
+ GFP_ATOMIC);
+
spin_lock_bh(&nf_conntrack_lock);
exp = nf_ct_find_expectation(net, tuple);
if (exp) {
nf_conntrack_get(&ct->master->ct_general);
NF_CT_STAT_INC(net, expect_new);
} else {
- __nf_ct_try_assign_helper(ct, GFP_ATOMIC);
+ __nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC);
NF_CT_STAT_INC(net, new);
}
/* 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);
/* On success, returns conntrack ptr, sets skb->nfct and ctinfo */
static inline struct nf_conn *
-resolve_normal_ct(struct net *net,
+resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
struct sk_buff *skb,
unsigned int dataoff,
u_int16_t l3num,
/* look for tuple match */
h = nf_conntrack_find_get(net, &tuple);
if (!h) {
- h = init_conntrack(net, &tuple, l3proto, l4proto, skb, dataoff);
+ h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto,
+ skb, dataoff);
if (!h)
return NULL;
if (IS_ERR(h))
nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
struct sk_buff *skb)
{
- struct nf_conn *ct;
+ struct nf_conn *ct, *tmpl = NULL;
enum ip_conntrack_info ctinfo;
struct nf_conntrack_l3proto *l3proto;
struct nf_conntrack_l4proto *l4proto;
int set_reply = 0;
int ret;
- /* Previously seen (loopback or untracked)? Ignore. */
if (skb->nfct) {
- NF_CT_STAT_INC_ATOMIC(net, ignore);
- return NF_ACCEPT;
+ /* Previously seen (loopback or untracked)? Ignore. */
+ tmpl = (struct nf_conn *)skb->nfct;
+ if (!nf_ct_is_template(tmpl)) {
+ NF_CT_STAT_INC_ATOMIC(net, ignore);
+ return NF_ACCEPT;
+ }
+ skb->nfct = NULL;
}
/* rcu_read_lock()ed by nf_hook_slow */
pr_debug("not prepared to track yet or error occured\n");
NF_CT_STAT_INC_ATOMIC(net, error);
NF_CT_STAT_INC_ATOMIC(net, invalid);
- return -ret;
+ ret = -ret;
+ goto out;
}
l4proto = __nf_ct_l4proto_find(pf, protonum);
if (ret <= 0) {
NF_CT_STAT_INC_ATOMIC(net, error);
NF_CT_STAT_INC_ATOMIC(net, invalid);
- return -ret;
+ ret = -ret;
+ goto out;
}
}
- ct = resolve_normal_ct(net, skb, dataoff, pf, protonum,
+ ct = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum,
l3proto, l4proto, &set_reply, &ctinfo);
if (!ct) {
/* Not valid part of a connection */
NF_CT_STAT_INC_ATOMIC(net, invalid);
- return NF_ACCEPT;
+ ret = NF_ACCEPT;
+ goto out;
}
if (IS_ERR(ct)) {
/* Too stressed to deal. */
NF_CT_STAT_INC_ATOMIC(net, drop);
- return NF_DROP;
+ ret = NF_DROP;
+ goto out;
}
NF_CT_ASSERT(skb->nfct);
nf_conntrack_put(skb->nfct);
skb->nfct = NULL;
NF_CT_STAT_INC_ATOMIC(net, invalid);
- return -ret;
+ if (ret == -NF_DROP)
+ NF_CT_STAT_INC_ATOMIC(net, drop);
+ ret = -ret;
+ goto out;
}
if (set_reply && !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status))
- nf_conntrack_event_cache(IPCT_STATUS, ct);
+ nf_conntrack_event_cache(IPCT_REPLY, ct);
+out:
+ if (tmpl)
+ nf_ct_put(tmpl);
return ret;
}
return;
rcu_read_lock();
- __nf_ct_try_assign_helper(ct, GFP_ATOMIC);
+ __nf_ct_try_assign_helper(ct, NULL, GFP_ATOMIC);
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(nf_conntrack_alter_reply);
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) {
+ for (; *bucket < net->ct.htable_size; (*bucket)++) {
+ 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;
- /* get_next_corpse sets the dying bit for us */
- nf_conntrack_event_report(IPCT_DESTROY,
- i,
- fr->pid,
- fr->report);
+ /* If we fail to deliver the event, death_by_timeout() will retry */
+ if (nf_conntrack_event_report(IPCT_DESTROY, i,
+ fr->pid, fr->report) < 0)
+ return 1;
+
+ /* Avoid the delivery of the destroy event in death_by_timeout(). */
+ set_bit(IPS_DYING_BIT, &i->status);
+ return 1;
+}
+
+static int kill_all(struct nf_conn *i, void *data)
+{
return 1;
}
-void nf_ct_free_hashtable(struct hlist_head *hash, int vmalloced, unsigned int size)
+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_report);
+
+static void nf_ct_release_dying_list(struct net *net)
+{
+ struct nf_conntrack_tuple_hash *h;
+ struct nf_conn *ct;
+ struct hlist_nulls_node *n;
+
+ spin_lock_bh(&nf_conntrack_lock);
+ hlist_nulls_for_each_entry(h, n, &net->ct.dying, hnnode) {
+ ct = nf_ct_tuplehash_to_ctrack(h);
+ /* never fails to remove them, no listeners at this point */
+ nf_ct_kill(ct);
+ }
+ spin_unlock_bh(&nf_conntrack_lock);
}
-EXPORT_SYMBOL_GPL(nf_conntrack_flush);
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)
+ schedule();
+
nf_conntrack_helper_fini();
nf_conntrack_proto_fini();
- kmem_cache_destroy(nf_conntrack_cachep);
}
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);
+ nf_ct_release_dying_list(net);
if (atomic_read(&net->ct.count) != 0) {
schedule();
goto i_see_dead_people;
}
- /* wait until all references to nf_conntrack_untracked are dropped */
- while (atomic_read(&nf_conntrack_untracked.ct_general.use) > 1)
- schedule();
nf_ct_free_hashtable(net->ct.hash, net->ct.hash_vmalloc,
- nf_conntrack_htable_size);
+ net->ct.htable_size);
+ nf_conntrack_ecache_fini(net);
nf_conntrack_acct_fini(net);
nf_conntrack_expect_fini(net);
+ kmem_cache_destroy(net->ct.nf_conntrack_cachep);
+ kfree(net->ct.slabname);
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;
+ if (current->nsproxy->net_ns != &init_net)
+ return -EOPNOTSUPP;
+
/* On boot, we can set this without any fancy locking. */
if (!nf_conntrack_htable_size)
return param_set_uint(val, kp);
if (!hashsize)
return -EINVAL;
- hash = nf_ct_alloc_hashtable(&hashsize, &vmalloced);
+ hash = nf_ct_alloc_hashtable(&hashsize, &vmalloced, 1);
if (!hash)
return -ENOMEM;
- /* We have to rehahs for the new table anyway, so we also can
- * use a newrandom seed */
- get_random_bytes(&rnd, 4);
-
/* Lookups in the old hash might happen in parallel, which means we
* might get false negatives during connection lookup. New connections
* created because of a false negative won't make it into the hash
* though since that required taking the lock.
*/
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);
- bucket = __hash_conntrack(&h->tuple, hashsize, rnd);
- hlist_add_head(&h->hnode, &hash[bucket]);
+ for (i = 0; i < init_net.ct.htable_size; i++) {
+ 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,
+ nf_conntrack_hash_rnd);
+ hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]);
}
}
- old_size = nf_conntrack_htable_size;
+ old_size = init_net.ct.htable_size;
old_vmalloced = init_net.ct.hash_vmalloc;
old_hash = init_net.ct.hash;
- nf_conntrack_htable_size = hashsize;
+ init_net.ct.htable_size = nf_conntrack_htable_size = hashsize;
init_net.ct.hash_vmalloc = vmalloced;
init_net.ct.hash = hash;
- nf_conntrack_hash_rnd = rnd;
spin_unlock_bh(&nf_conntrack_lock);
nf_ct_free_hashtable(old_hash, old_vmalloced, old_size);
* machine has 512 buckets. >= 1GB machines have 16384 buckets. */
if (!nf_conntrack_htable_size) {
nf_conntrack_htable_size
- = (((num_physpages << PAGE_SHIFT) / 16384)
+ = (((totalram_pages << PAGE_SHIFT) / 16384)
/ sizeof(struct hlist_head));
- if (num_physpages > (1024 * 1024 * 1024 / PAGE_SIZE))
+ if (totalram_pages > (1024 * 1024 * 1024 / PAGE_SIZE))
nf_conntrack_htable_size = 16384;
if (nf_conntrack_htable_size < 32)
nf_conntrack_htable_size = 32;
NF_CONNTRACK_VERSION, nf_conntrack_htable_size,
nf_conntrack_max);
- nf_conntrack_cachep = kmem_cache_create("nf_conntrack",
- sizeof(struct nf_conn),
- 0, 0, NULL);
- if (!nf_conntrack_cachep) {
- printk(KERN_ERR "Unable to create nf_conn slab cache\n");
- ret = -ENOMEM;
- goto err_cache;
- }
-
ret = nf_conntrack_proto_init();
if (ret < 0)
goto err_proto;
if (ret < 0)
goto err_helper;
+ /* Set up fake conntrack: to never be deleted, not in any hashes */
+#ifdef CONFIG_NET_NS
+ nf_conntrack_untracked.ct_net = &init_net;
+#endif
+ atomic_set(&nf_conntrack_untracked.ct_general.use, 1);
+ /* - and look it like as a confirmed connection */
+ set_bit(IPS_CONFIRMED_BIT, &nf_conntrack_untracked.status);
+
return 0;
err_helper:
nf_conntrack_proto_fini();
err_proto:
- kmem_cache_destroy(nf_conntrack_cachep);
-err_cache:
return ret;
}
+/*
+ * We need to use special "null" values, not used in hash table
+ */
+#define UNCONFIRMED_NULLS_VAL ((1<<30)+0)
+#define DYING_NULLS_VAL ((1<<30)+1)
+
static int nf_conntrack_init_net(struct net *net)
{
int ret;
atomic_set(&net->ct.count, 0);
- INIT_HLIST_HEAD(&net->ct.unconfirmed);
+ INIT_HLIST_NULLS_HEAD(&net->ct.unconfirmed, UNCONFIRMED_NULLS_VAL);
+ INIT_HLIST_NULLS_HEAD(&net->ct.dying, DYING_NULLS_VAL);
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.slabname = kasprintf(GFP_KERNEL, "nf_conntrack_%p", net);
+ if (!net->ct.slabname) {
+ ret = -ENOMEM;
+ goto err_slabname;
+ }
+
+ net->ct.nf_conntrack_cachep = kmem_cache_create(net->ct.slabname,
+ sizeof(struct nf_conn), 0,
+ SLAB_DESTROY_BY_RCU, NULL);
+ if (!net->ct.nf_conntrack_cachep) {
+ printk(KERN_ERR "Unable to create nf_conn slab cache\n");
+ ret = -ENOMEM;
+ goto err_cache;
+ }
+
+ net->ct.htable_size = nf_conntrack_htable_size;
+ net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size,
+ &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;
-
- /* Set up fake conntrack:
- - to never be deleted, not in any hashes */
-#ifdef CONFIG_NET_NS
- nf_conntrack_untracked.ct_net = &init_net;
-#endif
- atomic_set(&nf_conntrack_untracked.ct_general.use, 1);
- /* - and look it like as a confirmed connection */
- set_bit(IPS_CONFIRMED_BIT, &nf_conntrack_untracked.status);
+ ret = nf_conntrack_ecache_init(net);
+ if (ret < 0)
+ goto err_ecache;
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);
+ net->ct.htable_size);
err_hash:
- nf_conntrack_ecache_fini(net);
-err_ecache:
+ kmem_cache_destroy(net->ct.nf_conntrack_cachep);
+err_cache:
+ kfree(net->ct.slabname);
+err_slabname:
free_percpu(net->ct.stat);
err_stat:
return ret;
}
+s16 (*nf_ct_nat_offset)(const struct nf_conn *ct,
+ enum ip_conntrack_dir dir,
+ u32 seq);
+EXPORT_SYMBOL_GPL(nf_ct_nat_offset);
+
int nf_conntrack_init(struct net *net)
{
int ret;
/* For use by REJECT target */
rcu_assign_pointer(ip_ct_attach, nf_conntrack_attach);
rcu_assign_pointer(nf_ct_destroy, destroy_conntrack);
+
+ /* Howto get NAT offsets */
+ rcu_assign_pointer(nf_ct_nat_offset, NULL);
}
return 0;
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff