#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>
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);
}
{
struct nf_conntrack_tuple_hash *h;
struct hlist_nulls_node *n;
- unsigned int hash = hash_conntrack(tuple);
+ 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.
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);
}
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
struct net *net = nf_ct_net(ignored_conntrack);
struct nf_conntrack_tuple_hash *h;
struct hlist_nulls_node *n;
- unsigned int hash = hash_conntrack(tuple);
+ 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.
int dropped = 0;
rcu_read_lock();
- for (i = 0; i < nf_conntrack_htable_size; i++) {
+ 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 (cnt >= NF_CT_EVICTION_RANGE)
break;
- hash = (hash + 1) % nf_conntrack_htable_size;
+ hash = (hash + 1) % net->ct.htable_size;
}
rcu_read_unlock();
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())
* Do not use kmem_cache_zalloc(), as this cache uses
* SLAB_DESTROY_BY_RCU.
*/
- ct = kmem_cache_alloc(nf_conntrack_cachep, gfp);
+ 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);
nf_ct_ext_destroy(ct);
atomic_dec(&net->ct.count);
nf_ct_ext_free(ct);
- kmem_cache_free(nf_conntrack_cachep, 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);
- nf_ct_ecache_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);
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);
}
/* 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_CT_STAT_INC_ATOMIC(net, invalid);
if (ret == -NF_DROP)
NF_CT_STAT_INC_ATOMIC(net, drop);
- return -ret;
+ 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);
struct hlist_nulls_node *n;
spin_lock_bh(&nf_conntrack_lock);
- for (; *bucket < nf_conntrack_htable_size; (*bucket)++) {
+ 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))
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)
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);
}
{
int i, bucket, vmalloced, old_vmalloced;
unsigned int hashsize, old_size;
- int rnd;
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 (!hash)
return -ENOMEM;
- /* We have to rehahs for the new table anyway, so we also can
- * use a newrandom seed */
- get_random_bytes(&rnd, sizeof(rnd));
-
/* 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++) {
+ 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, rnd);
+ 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);
NF_CONNTRACK_VERSION, nf_conntrack_htable_size,
nf_conntrack_max);
- nf_conntrack_cachep = kmem_cache_create("nf_conntrack",
- sizeof(struct nf_conn),
- 0, SLAB_DESTROY_BY_RCU, 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;
}
ret = -ENOMEM;
goto err_stat;
}
- net->ct.hash = nf_ct_alloc_hashtable(&nf_conntrack_htable_size,
+
+ 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;
if (ret < 0)
goto err_ecache;
- /* 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_ecache:
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:
+ 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;