![Gao Feng](/assets/img/avatar_default.png)
When memory is exhausted, nfct_seqadj_ext_add may fail to add the synproxy and seqadj extensions. The function nf_ct_seqadj_init doesn't check if get valid seqadj pointer by the nfct_seqadj. Now drop the packet directly when fail to add seqadj extension to avoid dereference NULL pointer in nf_ct_seqadj_init from init_conntrack(). Signed-off-by: Gao Feng <fgao@ikuai8.com> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
1930 lines
51 KiB
C
1930 lines
51 KiB
C
/* Connection state tracking for netfilter. This is separated from,
|
|
but required by, the NAT layer; it can also be used by an iptables
|
|
extension. */
|
|
|
|
/* (C) 1999-2001 Paul `Rusty' Russell
|
|
* (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
|
|
* (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.org>
|
|
* (C) 2005-2012 Patrick McHardy <kaber@trash.net>
|
|
*
|
|
* 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.
|
|
*/
|
|
|
|
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
|
|
|
|
#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/stddef.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/random.h>
|
|
#include <linux/jhash.h>
|
|
#include <linux/err.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/moduleparam.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/kernel.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_l4proto.h>
|
|
#include <net/netfilter/nf_conntrack_expect.h>
|
|
#include <net/netfilter/nf_conntrack_helper.h>
|
|
#include <net/netfilter/nf_conntrack_seqadj.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_conntrack_zones.h>
|
|
#include <net/netfilter/nf_conntrack_timestamp.h>
|
|
#include <net/netfilter/nf_conntrack_timeout.h>
|
|
#include <net/netfilter/nf_conntrack_labels.h>
|
|
#include <net/netfilter/nf_conntrack_synproxy.h>
|
|
#include <net/netfilter/nf_nat.h>
|
|
#include <net/netfilter/nf_nat_core.h>
|
|
#include <net/netfilter/nf_nat_helper.h>
|
|
#include <net/netns/hash.h>
|
|
|
|
#define NF_CONNTRACK_VERSION "0.5.0"
|
|
|
|
int (*nfnetlink_parse_nat_setup_hook)(struct nf_conn *ct,
|
|
enum nf_nat_manip_type manip,
|
|
const struct nlattr *attr) __read_mostly;
|
|
EXPORT_SYMBOL_GPL(nfnetlink_parse_nat_setup_hook);
|
|
|
|
__cacheline_aligned_in_smp spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS];
|
|
EXPORT_SYMBOL_GPL(nf_conntrack_locks);
|
|
|
|
__cacheline_aligned_in_smp DEFINE_SPINLOCK(nf_conntrack_expect_lock);
|
|
EXPORT_SYMBOL_GPL(nf_conntrack_expect_lock);
|
|
|
|
struct hlist_nulls_head *nf_conntrack_hash __read_mostly;
|
|
EXPORT_SYMBOL_GPL(nf_conntrack_hash);
|
|
|
|
static __read_mostly struct kmem_cache *nf_conntrack_cachep;
|
|
static __read_mostly spinlock_t nf_conntrack_locks_all_lock;
|
|
static __read_mostly seqcount_t nf_conntrack_generation;
|
|
static __read_mostly DEFINE_SPINLOCK(nf_conntrack_locks_all_lock);
|
|
static __read_mostly bool nf_conntrack_locks_all;
|
|
|
|
void nf_conntrack_lock(spinlock_t *lock) __acquires(lock)
|
|
{
|
|
spin_lock(lock);
|
|
while (unlikely(nf_conntrack_locks_all)) {
|
|
spin_unlock(lock);
|
|
|
|
/*
|
|
* Order the 'nf_conntrack_locks_all' load vs. the
|
|
* spin_unlock_wait() loads below, to ensure
|
|
* that 'nf_conntrack_locks_all_lock' is indeed held:
|
|
*/
|
|
smp_rmb(); /* spin_lock(&nf_conntrack_locks_all_lock) */
|
|
spin_unlock_wait(&nf_conntrack_locks_all_lock);
|
|
spin_lock(lock);
|
|
}
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_conntrack_lock);
|
|
|
|
static void nf_conntrack_double_unlock(unsigned int h1, unsigned int h2)
|
|
{
|
|
h1 %= CONNTRACK_LOCKS;
|
|
h2 %= CONNTRACK_LOCKS;
|
|
spin_unlock(&nf_conntrack_locks[h1]);
|
|
if (h1 != h2)
|
|
spin_unlock(&nf_conntrack_locks[h2]);
|
|
}
|
|
|
|
/* return true if we need to recompute hashes (in case hash table was resized) */
|
|
static bool nf_conntrack_double_lock(struct net *net, unsigned int h1,
|
|
unsigned int h2, unsigned int sequence)
|
|
{
|
|
h1 %= CONNTRACK_LOCKS;
|
|
h2 %= CONNTRACK_LOCKS;
|
|
if (h1 <= h2) {
|
|
nf_conntrack_lock(&nf_conntrack_locks[h1]);
|
|
if (h1 != h2)
|
|
spin_lock_nested(&nf_conntrack_locks[h2],
|
|
SINGLE_DEPTH_NESTING);
|
|
} else {
|
|
nf_conntrack_lock(&nf_conntrack_locks[h2]);
|
|
spin_lock_nested(&nf_conntrack_locks[h1],
|
|
SINGLE_DEPTH_NESTING);
|
|
}
|
|
if (read_seqcount_retry(&nf_conntrack_generation, sequence)) {
|
|
nf_conntrack_double_unlock(h1, h2);
|
|
return true;
|
|
}
|
|
return false;
|
|
}
|
|
|
|
static void nf_conntrack_all_lock(void)
|
|
{
|
|
int i;
|
|
|
|
spin_lock(&nf_conntrack_locks_all_lock);
|
|
nf_conntrack_locks_all = true;
|
|
|
|
/*
|
|
* Order the above store of 'nf_conntrack_locks_all' against
|
|
* the spin_unlock_wait() loads below, such that if
|
|
* nf_conntrack_lock() observes 'nf_conntrack_locks_all'
|
|
* we must observe nf_conntrack_locks[] held:
|
|
*/
|
|
smp_mb(); /* spin_lock(&nf_conntrack_locks_all_lock) */
|
|
|
|
for (i = 0; i < CONNTRACK_LOCKS; i++) {
|
|
spin_unlock_wait(&nf_conntrack_locks[i]);
|
|
}
|
|
}
|
|
|
|
static void nf_conntrack_all_unlock(void)
|
|
{
|
|
/*
|
|
* All prior stores must be complete before we clear
|
|
* 'nf_conntrack_locks_all'. Otherwise nf_conntrack_lock()
|
|
* might observe the false value but not the entire
|
|
* critical section:
|
|
*/
|
|
smp_store_release(&nf_conntrack_locks_all, false);
|
|
spin_unlock(&nf_conntrack_locks_all_lock);
|
|
}
|
|
|
|
unsigned int nf_conntrack_htable_size __read_mostly;
|
|
EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);
|
|
|
|
unsigned int nf_conntrack_max __read_mostly;
|
|
EXPORT_SYMBOL_GPL(nf_conntrack_max);
|
|
|
|
DEFINE_PER_CPU(struct nf_conn, nf_conntrack_untracked);
|
|
EXPORT_PER_CPU_SYMBOL(nf_conntrack_untracked);
|
|
|
|
static unsigned int nf_conntrack_hash_rnd __read_mostly;
|
|
|
|
static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple,
|
|
const struct net *net)
|
|
{
|
|
unsigned int n;
|
|
u32 seed;
|
|
|
|
get_random_once(&nf_conntrack_hash_rnd, sizeof(nf_conntrack_hash_rnd));
|
|
|
|
/* The direction must be ignored, so we hash everything up to the
|
|
* destination ports (which is a multiple of 4) and treat the last
|
|
* three bytes manually.
|
|
*/
|
|
seed = nf_conntrack_hash_rnd ^ net_hash_mix(net);
|
|
n = (sizeof(tuple->src) + sizeof(tuple->dst.u3)) / sizeof(u32);
|
|
return jhash2((u32 *)tuple, n, seed ^
|
|
(((__force __u16)tuple->dst.u.all << 16) |
|
|
tuple->dst.protonum));
|
|
}
|
|
|
|
static u32 scale_hash(u32 hash)
|
|
{
|
|
return reciprocal_scale(hash, nf_conntrack_htable_size);
|
|
}
|
|
|
|
static u32 __hash_conntrack(const struct net *net,
|
|
const struct nf_conntrack_tuple *tuple,
|
|
unsigned int size)
|
|
{
|
|
return reciprocal_scale(hash_conntrack_raw(tuple, net), size);
|
|
}
|
|
|
|
static u32 hash_conntrack(const struct net *net,
|
|
const struct nf_conntrack_tuple *tuple)
|
|
{
|
|
return scale_hash(hash_conntrack_raw(tuple, net));
|
|
}
|
|
|
|
bool
|
|
nf_ct_get_tuple(const struct sk_buff *skb,
|
|
unsigned int nhoff,
|
|
unsigned int dataoff,
|
|
u_int16_t l3num,
|
|
u_int8_t protonum,
|
|
struct net *net,
|
|
struct nf_conntrack_tuple *tuple,
|
|
const struct nf_conntrack_l3proto *l3proto,
|
|
const struct nf_conntrack_l4proto *l4proto)
|
|
{
|
|
memset(tuple, 0, sizeof(*tuple));
|
|
|
|
tuple->src.l3num = l3num;
|
|
if (l3proto->pkt_to_tuple(skb, nhoff, tuple) == 0)
|
|
return false;
|
|
|
|
tuple->dst.protonum = protonum;
|
|
tuple->dst.dir = IP_CT_DIR_ORIGINAL;
|
|
|
|
return l4proto->pkt_to_tuple(skb, dataoff, net, tuple);
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_ct_get_tuple);
|
|
|
|
bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff,
|
|
u_int16_t l3num,
|
|
struct net *net, struct nf_conntrack_tuple *tuple)
|
|
{
|
|
struct nf_conntrack_l3proto *l3proto;
|
|
struct nf_conntrack_l4proto *l4proto;
|
|
unsigned int protoff;
|
|
u_int8_t protonum;
|
|
int ret;
|
|
|
|
rcu_read_lock();
|
|
|
|
l3proto = __nf_ct_l3proto_find(l3num);
|
|
ret = l3proto->get_l4proto(skb, nhoff, &protoff, &protonum);
|
|
if (ret != NF_ACCEPT) {
|
|
rcu_read_unlock();
|
|
return false;
|
|
}
|
|
|
|
l4proto = __nf_ct_l4proto_find(l3num, protonum);
|
|
|
|
ret = nf_ct_get_tuple(skb, nhoff, protoff, l3num, protonum, net, tuple,
|
|
l3proto, l4proto);
|
|
|
|
rcu_read_unlock();
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_ct_get_tuplepr);
|
|
|
|
bool
|
|
nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
|
|
const struct nf_conntrack_tuple *orig,
|
|
const struct nf_conntrack_l3proto *l3proto,
|
|
const struct nf_conntrack_l4proto *l4proto)
|
|
{
|
|
memset(inverse, 0, sizeof(*inverse));
|
|
|
|
inverse->src.l3num = orig->src.l3num;
|
|
if (l3proto->invert_tuple(inverse, orig) == 0)
|
|
return false;
|
|
|
|
inverse->dst.dir = !orig->dst.dir;
|
|
|
|
inverse->dst.protonum = orig->dst.protonum;
|
|
return l4proto->invert_tuple(inverse, orig);
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_ct_invert_tuple);
|
|
|
|
static void
|
|
clean_from_lists(struct nf_conn *ct)
|
|
{
|
|
pr_debug("clean_from_lists(%p)\n", ct);
|
|
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);
|
|
}
|
|
|
|
/* must be called with local_bh_disable */
|
|
static void nf_ct_add_to_dying_list(struct nf_conn *ct)
|
|
{
|
|
struct ct_pcpu *pcpu;
|
|
|
|
/* add this conntrack to the (per cpu) dying list */
|
|
ct->cpu = smp_processor_id();
|
|
pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);
|
|
|
|
spin_lock(&pcpu->lock);
|
|
hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
|
|
&pcpu->dying);
|
|
spin_unlock(&pcpu->lock);
|
|
}
|
|
|
|
/* must be called with local_bh_disable */
|
|
static void nf_ct_add_to_unconfirmed_list(struct nf_conn *ct)
|
|
{
|
|
struct ct_pcpu *pcpu;
|
|
|
|
/* add this conntrack to the (per cpu) unconfirmed list */
|
|
ct->cpu = smp_processor_id();
|
|
pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);
|
|
|
|
spin_lock(&pcpu->lock);
|
|
hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
|
|
&pcpu->unconfirmed);
|
|
spin_unlock(&pcpu->lock);
|
|
}
|
|
|
|
/* must be called with local_bh_disable */
|
|
static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct)
|
|
{
|
|
struct ct_pcpu *pcpu;
|
|
|
|
/* We overload first tuple to link into unconfirmed or dying list.*/
|
|
pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);
|
|
|
|
spin_lock(&pcpu->lock);
|
|
BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode));
|
|
hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
|
|
spin_unlock(&pcpu->lock);
|
|
}
|
|
|
|
/* Released via destroy_conntrack() */
|
|
struct nf_conn *nf_ct_tmpl_alloc(struct net *net,
|
|
const struct nf_conntrack_zone *zone,
|
|
gfp_t flags)
|
|
{
|
|
struct nf_conn *tmpl;
|
|
|
|
tmpl = kzalloc(sizeof(*tmpl), flags);
|
|
if (tmpl == NULL)
|
|
return NULL;
|
|
|
|
tmpl->status = IPS_TEMPLATE;
|
|
write_pnet(&tmpl->ct_net, net);
|
|
nf_ct_zone_add(tmpl, zone);
|
|
atomic_set(&tmpl->ct_general.use, 0);
|
|
|
|
return tmpl;
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_ct_tmpl_alloc);
|
|
|
|
void nf_ct_tmpl_free(struct nf_conn *tmpl)
|
|
{
|
|
nf_ct_ext_destroy(tmpl);
|
|
nf_ct_ext_free(tmpl);
|
|
kfree(tmpl);
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_ct_tmpl_free);
|
|
|
|
static void
|
|
destroy_conntrack(struct nf_conntrack *nfct)
|
|
{
|
|
struct nf_conn *ct = (struct nf_conn *)nfct;
|
|
struct net *net = nf_ct_net(ct);
|
|
struct nf_conntrack_l4proto *l4proto;
|
|
|
|
pr_debug("destroy_conntrack(%p)\n", ct);
|
|
NF_CT_ASSERT(atomic_read(&nfct->use) == 0);
|
|
NF_CT_ASSERT(!timer_pending(&ct->timeout));
|
|
|
|
if (unlikely(nf_ct_is_template(ct))) {
|
|
nf_ct_tmpl_free(ct);
|
|
return;
|
|
}
|
|
rcu_read_lock();
|
|
l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
|
|
if (l4proto->destroy)
|
|
l4proto->destroy(ct);
|
|
|
|
rcu_read_unlock();
|
|
|
|
local_bh_disable();
|
|
/* Expectations will have been removed in clean_from_lists,
|
|
* except TFTP can create an expectation on the first packet,
|
|
* before connection is in the list, so we need to clean here,
|
|
* too.
|
|
*/
|
|
nf_ct_remove_expectations(ct);
|
|
|
|
nf_ct_del_from_dying_or_unconfirmed_list(ct);
|
|
|
|
NF_CT_STAT_INC(net, delete);
|
|
local_bh_enable();
|
|
|
|
if (ct->master)
|
|
nf_ct_put(ct->master);
|
|
|
|
pr_debug("destroy_conntrack: returning ct=%p to slab\n", ct);
|
|
nf_conntrack_free(ct);
|
|
}
|
|
|
|
static void nf_ct_delete_from_lists(struct nf_conn *ct)
|
|
{
|
|
struct net *net = nf_ct_net(ct);
|
|
unsigned int hash, reply_hash;
|
|
unsigned int sequence;
|
|
|
|
nf_ct_helper_destroy(ct);
|
|
|
|
local_bh_disable();
|
|
do {
|
|
sequence = read_seqcount_begin(&nf_conntrack_generation);
|
|
hash = hash_conntrack(net,
|
|
&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
|
|
reply_hash = hash_conntrack(net,
|
|
&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
|
|
} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
|
|
|
|
clean_from_lists(ct);
|
|
nf_conntrack_double_unlock(hash, reply_hash);
|
|
|
|
nf_ct_add_to_dying_list(ct);
|
|
|
|
NF_CT_STAT_INC(net, delete_list);
|
|
local_bh_enable();
|
|
}
|
|
|
|
bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report)
|
|
{
|
|
struct nf_conn_tstamp *tstamp;
|
|
|
|
tstamp = nf_conn_tstamp_find(ct);
|
|
if (tstamp && tstamp->stop == 0)
|
|
tstamp->stop = ktime_get_real_ns();
|
|
|
|
if (nf_ct_is_dying(ct))
|
|
goto delete;
|
|
|
|
if (nf_conntrack_event_report(IPCT_DESTROY, ct,
|
|
portid, report) < 0) {
|
|
/* destroy event was not delivered */
|
|
nf_ct_delete_from_lists(ct);
|
|
nf_conntrack_ecache_delayed_work(nf_ct_net(ct));
|
|
return false;
|
|
}
|
|
|
|
nf_conntrack_ecache_work(nf_ct_net(ct));
|
|
set_bit(IPS_DYING_BIT, &ct->status);
|
|
delete:
|
|
nf_ct_delete_from_lists(ct);
|
|
nf_ct_put(ct);
|
|
return true;
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_ct_delete);
|
|
|
|
static void death_by_timeout(unsigned long ul_conntrack)
|
|
{
|
|
nf_ct_delete((struct nf_conn *)ul_conntrack, 0, 0);
|
|
}
|
|
|
|
static inline bool
|
|
nf_ct_key_equal(struct nf_conntrack_tuple_hash *h,
|
|
const struct nf_conntrack_tuple *tuple,
|
|
const struct nf_conntrack_zone *zone,
|
|
const struct net *net)
|
|
{
|
|
struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
|
|
|
|
/* A conntrack can be recreated with the equal tuple,
|
|
* so we need to check that the conntrack is confirmed
|
|
*/
|
|
return nf_ct_tuple_equal(tuple, &h->tuple) &&
|
|
nf_ct_zone_equal(ct, zone, NF_CT_DIRECTION(h)) &&
|
|
nf_ct_is_confirmed(ct) &&
|
|
net_eq(net, nf_ct_net(ct));
|
|
}
|
|
|
|
/* must be called with rcu read lock held */
|
|
void nf_conntrack_get_ht(struct hlist_nulls_head **hash, unsigned int *hsize)
|
|
{
|
|
struct hlist_nulls_head *hptr;
|
|
unsigned int sequence, hsz;
|
|
|
|
do {
|
|
sequence = read_seqcount_begin(&nf_conntrack_generation);
|
|
hsz = nf_conntrack_htable_size;
|
|
hptr = nf_conntrack_hash;
|
|
} while (read_seqcount_retry(&nf_conntrack_generation, sequence));
|
|
|
|
*hash = hptr;
|
|
*hsize = hsz;
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_conntrack_get_ht);
|
|
|
|
/*
|
|
* Warning :
|
|
* - Caller must take a reference on returned object
|
|
* and recheck nf_ct_tuple_equal(tuple, &h->tuple)
|
|
*/
|
|
static struct nf_conntrack_tuple_hash *
|
|
____nf_conntrack_find(struct net *net, const struct nf_conntrack_zone *zone,
|
|
const struct nf_conntrack_tuple *tuple, u32 hash)
|
|
{
|
|
struct nf_conntrack_tuple_hash *h;
|
|
struct hlist_nulls_head *ct_hash;
|
|
struct hlist_nulls_node *n;
|
|
unsigned int bucket, sequence;
|
|
|
|
begin:
|
|
do {
|
|
sequence = read_seqcount_begin(&nf_conntrack_generation);
|
|
bucket = scale_hash(hash);
|
|
ct_hash = nf_conntrack_hash;
|
|
} while (read_seqcount_retry(&nf_conntrack_generation, sequence));
|
|
|
|
hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[bucket], hnnode) {
|
|
if (nf_ct_key_equal(h, tuple, zone, net)) {
|
|
NF_CT_STAT_INC_ATOMIC(net, found);
|
|
return h;
|
|
}
|
|
NF_CT_STAT_INC_ATOMIC(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) != bucket) {
|
|
NF_CT_STAT_INC_ATOMIC(net, search_restart);
|
|
goto begin;
|
|
}
|
|
|
|
return NULL;
|
|
}
|
|
|
|
/* Find a connection corresponding to a tuple. */
|
|
static struct nf_conntrack_tuple_hash *
|
|
__nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone,
|
|
const struct nf_conntrack_tuple *tuple, u32 hash)
|
|
{
|
|
struct nf_conntrack_tuple_hash *h;
|
|
struct nf_conn *ct;
|
|
|
|
rcu_read_lock();
|
|
begin:
|
|
h = ____nf_conntrack_find(net, zone, tuple, hash);
|
|
if (h) {
|
|
ct = nf_ct_tuplehash_to_ctrack(h);
|
|
if (unlikely(nf_ct_is_dying(ct) ||
|
|
!atomic_inc_not_zero(&ct->ct_general.use)))
|
|
h = NULL;
|
|
else {
|
|
if (unlikely(!nf_ct_key_equal(h, tuple, zone, net))) {
|
|
nf_ct_put(ct);
|
|
goto begin;
|
|
}
|
|
}
|
|
}
|
|
rcu_read_unlock();
|
|
|
|
return h;
|
|
}
|
|
|
|
struct nf_conntrack_tuple_hash *
|
|
nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone,
|
|
const struct nf_conntrack_tuple *tuple)
|
|
{
|
|
return __nf_conntrack_find_get(net, zone, tuple,
|
|
hash_conntrack_raw(tuple, net));
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_conntrack_find_get);
|
|
|
|
static void __nf_conntrack_hash_insert(struct nf_conn *ct,
|
|
unsigned int hash,
|
|
unsigned int reply_hash)
|
|
{
|
|
hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
|
|
&nf_conntrack_hash[hash]);
|
|
hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode,
|
|
&nf_conntrack_hash[reply_hash]);
|
|
}
|
|
|
|
int
|
|
nf_conntrack_hash_check_insert(struct nf_conn *ct)
|
|
{
|
|
const struct nf_conntrack_zone *zone;
|
|
struct net *net = nf_ct_net(ct);
|
|
unsigned int hash, reply_hash;
|
|
struct nf_conntrack_tuple_hash *h;
|
|
struct hlist_nulls_node *n;
|
|
unsigned int sequence;
|
|
|
|
zone = nf_ct_zone(ct);
|
|
|
|
local_bh_disable();
|
|
do {
|
|
sequence = read_seqcount_begin(&nf_conntrack_generation);
|
|
hash = hash_conntrack(net,
|
|
&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
|
|
reply_hash = hash_conntrack(net,
|
|
&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
|
|
} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
|
|
|
|
/* See if there's one in the list already, including reverse */
|
|
hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode)
|
|
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
|
|
zone, net))
|
|
goto out;
|
|
|
|
hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode)
|
|
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
|
|
zone, net))
|
|
goto out;
|
|
|
|
add_timer(&ct->timeout);
|
|
smp_wmb();
|
|
/* The caller holds a reference to this object */
|
|
atomic_set(&ct->ct_general.use, 2);
|
|
__nf_conntrack_hash_insert(ct, hash, reply_hash);
|
|
nf_conntrack_double_unlock(hash, reply_hash);
|
|
NF_CT_STAT_INC(net, insert);
|
|
local_bh_enable();
|
|
return 0;
|
|
|
|
out:
|
|
nf_conntrack_double_unlock(hash, reply_hash);
|
|
NF_CT_STAT_INC(net, insert_failed);
|
|
local_bh_enable();
|
|
return -EEXIST;
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert);
|
|
|
|
static inline void nf_ct_acct_update(struct nf_conn *ct,
|
|
enum ip_conntrack_info ctinfo,
|
|
unsigned int len)
|
|
{
|
|
struct nf_conn_acct *acct;
|
|
|
|
acct = nf_conn_acct_find(ct);
|
|
if (acct) {
|
|
struct nf_conn_counter *counter = acct->counter;
|
|
|
|
atomic64_inc(&counter[CTINFO2DIR(ctinfo)].packets);
|
|
atomic64_add(len, &counter[CTINFO2DIR(ctinfo)].bytes);
|
|
}
|
|
}
|
|
|
|
static void nf_ct_acct_merge(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
|
|
const struct nf_conn *loser_ct)
|
|
{
|
|
struct nf_conn_acct *acct;
|
|
|
|
acct = nf_conn_acct_find(loser_ct);
|
|
if (acct) {
|
|
struct nf_conn_counter *counter = acct->counter;
|
|
unsigned int bytes;
|
|
|
|
/* u32 should be fine since we must have seen one packet. */
|
|
bytes = atomic64_read(&counter[CTINFO2DIR(ctinfo)].bytes);
|
|
nf_ct_acct_update(ct, ctinfo, bytes);
|
|
}
|
|
}
|
|
|
|
/* Resolve race on insertion if this protocol allows this. */
|
|
static int nf_ct_resolve_clash(struct net *net, struct sk_buff *skb,
|
|
enum ip_conntrack_info ctinfo,
|
|
struct nf_conntrack_tuple_hash *h)
|
|
{
|
|
/* This is the conntrack entry already in hashes that won race. */
|
|
struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
|
|
struct nf_conntrack_l4proto *l4proto;
|
|
|
|
l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
|
|
if (l4proto->allow_clash &&
|
|
!nfct_nat(ct) &&
|
|
!nf_ct_is_dying(ct) &&
|
|
atomic_inc_not_zero(&ct->ct_general.use)) {
|
|
nf_ct_acct_merge(ct, ctinfo, (struct nf_conn *)skb->nfct);
|
|
nf_conntrack_put(skb->nfct);
|
|
/* Assign conntrack already in hashes to this skbuff. Don't
|
|
* modify skb->nfctinfo to ensure consistent stateful filtering.
|
|
*/
|
|
skb->nfct = &ct->ct_general;
|
|
return NF_ACCEPT;
|
|
}
|
|
NF_CT_STAT_INC(net, drop);
|
|
return NF_DROP;
|
|
}
|
|
|
|
/* Confirm a connection given skb; places it in hash table */
|
|
int
|
|
__nf_conntrack_confirm(struct sk_buff *skb)
|
|
{
|
|
const struct nf_conntrack_zone *zone;
|
|
unsigned int hash, reply_hash;
|
|
struct nf_conntrack_tuple_hash *h;
|
|
struct nf_conn *ct;
|
|
struct nf_conn_help *help;
|
|
struct nf_conn_tstamp *tstamp;
|
|
struct hlist_nulls_node *n;
|
|
enum ip_conntrack_info ctinfo;
|
|
struct net *net;
|
|
unsigned int sequence;
|
|
int ret = NF_DROP;
|
|
|
|
ct = nf_ct_get(skb, &ctinfo);
|
|
net = nf_ct_net(ct);
|
|
|
|
/* ipt_REJECT uses nf_conntrack_attach to attach related
|
|
ICMP/TCP RST packets in other direction. Actual packet
|
|
which created connection will be IP_CT_NEW or for an
|
|
expected connection, IP_CT_RELATED. */
|
|
if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
|
|
return NF_ACCEPT;
|
|
|
|
zone = nf_ct_zone(ct);
|
|
local_bh_disable();
|
|
|
|
do {
|
|
sequence = read_seqcount_begin(&nf_conntrack_generation);
|
|
/* reuse the hash saved before */
|
|
hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev;
|
|
hash = scale_hash(hash);
|
|
reply_hash = hash_conntrack(net,
|
|
&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
|
|
|
|
} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));
|
|
|
|
/* We're not in hash table, and we refuse to set up related
|
|
* connections for unconfirmed conns. But packet copies and
|
|
* REJECT will give spurious warnings here.
|
|
*/
|
|
/* NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 1); */
|
|
|
|
/* No external references means no one else could have
|
|
* confirmed us.
|
|
*/
|
|
NF_CT_ASSERT(!nf_ct_is_confirmed(ct));
|
|
pr_debug("Confirming conntrack %p\n", ct);
|
|
/* We have to check the DYING flag after unlink to prevent
|
|
* a race against nf_ct_get_next_corpse() possibly called from
|
|
* user context, else we insert an already 'dead' hash, blocking
|
|
* further use of that particular connection -JM.
|
|
*/
|
|
nf_ct_del_from_dying_or_unconfirmed_list(ct);
|
|
|
|
if (unlikely(nf_ct_is_dying(ct))) {
|
|
nf_ct_add_to_dying_list(ct);
|
|
goto dying;
|
|
}
|
|
|
|
/* 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_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode)
|
|
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
|
|
zone, net))
|
|
goto out;
|
|
|
|
hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode)
|
|
if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
|
|
zone, net))
|
|
goto out;
|
|
|
|
/* Timer relative to confirmation time, not original
|
|
setting time, otherwise we'd get timer wrap in
|
|
weird delay cases. */
|
|
ct->timeout.expires += jiffies;
|
|
add_timer(&ct->timeout);
|
|
atomic_inc(&ct->ct_general.use);
|
|
ct->status |= IPS_CONFIRMED;
|
|
|
|
/* set conntrack timestamp, if enabled. */
|
|
tstamp = nf_conn_tstamp_find(ct);
|
|
if (tstamp) {
|
|
if (skb->tstamp.tv64 == 0)
|
|
__net_timestamp(skb);
|
|
|
|
tstamp->start = ktime_to_ns(skb->tstamp);
|
|
}
|
|
/* 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, reply_hash);
|
|
nf_conntrack_double_unlock(hash, reply_hash);
|
|
NF_CT_STAT_INC(net, insert);
|
|
local_bh_enable();
|
|
|
|
help = nfct_help(ct);
|
|
if (help && help->helper)
|
|
nf_conntrack_event_cache(IPCT_HELPER, ct);
|
|
|
|
nf_conntrack_event_cache(master_ct(ct) ?
|
|
IPCT_RELATED : IPCT_NEW, ct);
|
|
return NF_ACCEPT;
|
|
|
|
out:
|
|
nf_ct_add_to_dying_list(ct);
|
|
ret = nf_ct_resolve_clash(net, skb, ctinfo, h);
|
|
dying:
|
|
nf_conntrack_double_unlock(hash, reply_hash);
|
|
NF_CT_STAT_INC(net, insert_failed);
|
|
local_bh_enable();
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__nf_conntrack_confirm);
|
|
|
|
/* Returns true if a connection correspondings to the tuple (required
|
|
for NAT). */
|
|
int
|
|
nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
|
|
const struct nf_conn *ignored_conntrack)
|
|
{
|
|
struct net *net = nf_ct_net(ignored_conntrack);
|
|
const struct nf_conntrack_zone *zone;
|
|
struct nf_conntrack_tuple_hash *h;
|
|
struct hlist_nulls_head *ct_hash;
|
|
unsigned int hash, sequence;
|
|
struct hlist_nulls_node *n;
|
|
struct nf_conn *ct;
|
|
|
|
zone = nf_ct_zone(ignored_conntrack);
|
|
|
|
rcu_read_lock();
|
|
do {
|
|
sequence = read_seqcount_begin(&nf_conntrack_generation);
|
|
hash = hash_conntrack(net, tuple);
|
|
ct_hash = nf_conntrack_hash;
|
|
} while (read_seqcount_retry(&nf_conntrack_generation, sequence));
|
|
|
|
hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[hash], hnnode) {
|
|
ct = nf_ct_tuplehash_to_ctrack(h);
|
|
if (ct != ignored_conntrack &&
|
|
nf_ct_key_equal(h, tuple, zone, net)) {
|
|
NF_CT_STAT_INC_ATOMIC(net, found);
|
|
rcu_read_unlock();
|
|
return 1;
|
|
}
|
|
NF_CT_STAT_INC_ATOMIC(net, searched);
|
|
}
|
|
rcu_read_unlock();
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_conntrack_tuple_taken);
|
|
|
|
#define NF_CT_EVICTION_RANGE 8
|
|
|
|
/* There's a small race here where we may free a just-assured
|
|
connection. Too bad: we're in trouble anyway. */
|
|
static unsigned int early_drop_list(struct net *net,
|
|
struct hlist_nulls_head *head)
|
|
{
|
|
struct nf_conntrack_tuple_hash *h;
|
|
struct hlist_nulls_node *n;
|
|
unsigned int drops = 0;
|
|
struct nf_conn *tmp;
|
|
|
|
hlist_nulls_for_each_entry_rcu(h, n, head, hnnode) {
|
|
tmp = nf_ct_tuplehash_to_ctrack(h);
|
|
|
|
if (test_bit(IPS_ASSURED_BIT, &tmp->status) ||
|
|
!net_eq(nf_ct_net(tmp), net) ||
|
|
nf_ct_is_dying(tmp))
|
|
continue;
|
|
|
|
if (!atomic_inc_not_zero(&tmp->ct_general.use))
|
|
continue;
|
|
|
|
/* kill only if still in same netns -- might have moved due to
|
|
* SLAB_DESTROY_BY_RCU rules.
|
|
*
|
|
* We steal the timer reference. If that fails timer has
|
|
* already fired or someone else deleted it. Just drop ref
|
|
* and move to next entry.
|
|
*/
|
|
if (net_eq(nf_ct_net(tmp), net) &&
|
|
nf_ct_is_confirmed(tmp) &&
|
|
del_timer(&tmp->timeout) &&
|
|
nf_ct_delete(tmp, 0, 0))
|
|
drops++;
|
|
|
|
nf_ct_put(tmp);
|
|
}
|
|
|
|
return drops;
|
|
}
|
|
|
|
static noinline int early_drop(struct net *net, unsigned int _hash)
|
|
{
|
|
unsigned int i;
|
|
|
|
for (i = 0; i < NF_CT_EVICTION_RANGE; i++) {
|
|
struct hlist_nulls_head *ct_hash;
|
|
unsigned hash, sequence, drops;
|
|
|
|
rcu_read_lock();
|
|
do {
|
|
sequence = read_seqcount_begin(&nf_conntrack_generation);
|
|
hash = scale_hash(_hash++);
|
|
ct_hash = nf_conntrack_hash;
|
|
} while (read_seqcount_retry(&nf_conntrack_generation, sequence));
|
|
|
|
drops = early_drop_list(net, &ct_hash[hash]);
|
|
rcu_read_unlock();
|
|
|
|
if (drops) {
|
|
NF_CT_STAT_ADD_ATOMIC(net, early_drop, drops);
|
|
return true;
|
|
}
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
static struct nf_conn *
|
|
__nf_conntrack_alloc(struct net *net,
|
|
const struct nf_conntrack_zone *zone,
|
|
const struct nf_conntrack_tuple *orig,
|
|
const struct nf_conntrack_tuple *repl,
|
|
gfp_t gfp, u32 hash)
|
|
{
|
|
struct nf_conn *ct;
|
|
|
|
/* We don't want any race condition at early drop stage */
|
|
atomic_inc(&net->ct.count);
|
|
|
|
if (nf_conntrack_max &&
|
|
unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) {
|
|
if (!early_drop(net, hash)) {
|
|
atomic_dec(&net->ct.count);
|
|
net_warn_ratelimited("nf_conntrack: table full, dropping packet\n");
|
|
return ERR_PTR(-ENOMEM);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Do not use kmem_cache_zalloc(), as this cache uses
|
|
* SLAB_DESTROY_BY_RCU.
|
|
*/
|
|
ct = kmem_cache_alloc(nf_conntrack_cachep, gfp);
|
|
if (ct == NULL)
|
|
goto out;
|
|
|
|
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;
|
|
/* save hash for reusing when confirming */
|
|
*(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash;
|
|
ct->status = 0;
|
|
/* Don't set timer yet: wait for confirmation */
|
|
setup_timer(&ct->timeout, death_by_timeout, (unsigned long)ct);
|
|
write_pnet(&ct->ct_net, net);
|
|
memset(&ct->__nfct_init_offset[0], 0,
|
|
offsetof(struct nf_conn, proto) -
|
|
offsetof(struct nf_conn, __nfct_init_offset[0]));
|
|
|
|
nf_ct_zone_add(ct, zone);
|
|
|
|
/* Because we use RCU lookups, we set ct_general.use to zero before
|
|
* this is inserted in any list.
|
|
*/
|
|
atomic_set(&ct->ct_general.use, 0);
|
|
return ct;
|
|
out:
|
|
atomic_dec(&net->ct.count);
|
|
return ERR_PTR(-ENOMEM);
|
|
}
|
|
|
|
struct nf_conn *nf_conntrack_alloc(struct net *net,
|
|
const struct nf_conntrack_zone *zone,
|
|
const struct nf_conntrack_tuple *orig,
|
|
const struct nf_conntrack_tuple *repl,
|
|
gfp_t gfp)
|
|
{
|
|
return __nf_conntrack_alloc(net, zone, orig, repl, gfp, 0);
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_conntrack_alloc);
|
|
|
|
void nf_conntrack_free(struct nf_conn *ct)
|
|
{
|
|
struct net *net = nf_ct_net(ct);
|
|
|
|
/* A freed object has refcnt == 0, that's
|
|
* the golden rule for SLAB_DESTROY_BY_RCU
|
|
*/
|
|
NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 0);
|
|
|
|
nf_ct_ext_destroy(ct);
|
|
nf_ct_ext_free(ct);
|
|
kmem_cache_free(nf_conntrack_cachep, ct);
|
|
smp_mb__before_atomic();
|
|
atomic_dec(&net->ct.count);
|
|
}
|
|
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, struct nf_conn *tmpl,
|
|
const struct nf_conntrack_tuple *tuple,
|
|
struct nf_conntrack_l3proto *l3proto,
|
|
struct nf_conntrack_l4proto *l4proto,
|
|
struct sk_buff *skb,
|
|
unsigned int dataoff, u32 hash)
|
|
{
|
|
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 = NULL;
|
|
const struct nf_conntrack_zone *zone;
|
|
struct nf_conn_timeout *timeout_ext;
|
|
struct nf_conntrack_zone tmp;
|
|
unsigned int *timeouts;
|
|
|
|
if (!nf_ct_invert_tuple(&repl_tuple, tuple, l3proto, l4proto)) {
|
|
pr_debug("Can't invert tuple.\n");
|
|
return NULL;
|
|
}
|
|
|
|
zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
|
|
ct = __nf_conntrack_alloc(net, zone, tuple, &repl_tuple, GFP_ATOMIC,
|
|
hash);
|
|
if (IS_ERR(ct))
|
|
return (struct nf_conntrack_tuple_hash *)ct;
|
|
|
|
if (!nf_ct_add_synproxy(ct, tmpl)) {
|
|
nf_conntrack_free(ct);
|
|
return ERR_PTR(-ENOMEM);
|
|
}
|
|
|
|
timeout_ext = tmpl ? nf_ct_timeout_find(tmpl) : NULL;
|
|
if (timeout_ext) {
|
|
timeouts = nf_ct_timeout_data(timeout_ext);
|
|
if (unlikely(!timeouts))
|
|
timeouts = l4proto->get_timeouts(net);
|
|
} else {
|
|
timeouts = l4proto->get_timeouts(net);
|
|
}
|
|
|
|
if (!l4proto->new(ct, skb, dataoff, timeouts)) {
|
|
nf_conntrack_free(ct);
|
|
pr_debug("can't track with proto module\n");
|
|
return NULL;
|
|
}
|
|
|
|
if (timeout_ext)
|
|
nf_ct_timeout_ext_add(ct, rcu_dereference(timeout_ext->timeout),
|
|
GFP_ATOMIC);
|
|
|
|
nf_ct_acct_ext_add(ct, GFP_ATOMIC);
|
|
nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);
|
|
nf_ct_labels_ext_add(ct);
|
|
|
|
ecache = tmpl ? nf_ct_ecache_find(tmpl) : NULL;
|
|
nf_ct_ecache_ext_add(ct, ecache ? ecache->ctmask : 0,
|
|
ecache ? ecache->expmask : 0,
|
|
GFP_ATOMIC);
|
|
|
|
local_bh_disable();
|
|
if (net->ct.expect_count) {
|
|
spin_lock(&nf_conntrack_expect_lock);
|
|
exp = nf_ct_find_expectation(net, zone, tuple);
|
|
if (exp) {
|
|
pr_debug("expectation arrives ct=%p exp=%p\n",
|
|
ct, exp);
|
|
/* Welcome, Mr. Bond. We've been expecting you... */
|
|
__set_bit(IPS_EXPECTED_BIT, &ct->status);
|
|
/* exp->master safe, refcnt bumped in nf_ct_find_expectation */
|
|
ct->master = exp->master;
|
|
if (exp->helper) {
|
|
help = nf_ct_helper_ext_add(ct, exp->helper,
|
|
GFP_ATOMIC);
|
|
if (help)
|
|
rcu_assign_pointer(help->helper, exp->helper);
|
|
}
|
|
|
|
#ifdef CONFIG_NF_CONNTRACK_MARK
|
|
ct->mark = exp->master->mark;
|
|
#endif
|
|
#ifdef CONFIG_NF_CONNTRACK_SECMARK
|
|
ct->secmark = exp->master->secmark;
|
|
#endif
|
|
NF_CT_STAT_INC(net, expect_new);
|
|
}
|
|
spin_unlock(&nf_conntrack_expect_lock);
|
|
}
|
|
if (!exp) {
|
|
__nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC);
|
|
NF_CT_STAT_INC(net, new);
|
|
}
|
|
|
|
/* Now it is inserted into the unconfirmed list, bump refcount */
|
|
nf_conntrack_get(&ct->ct_general);
|
|
nf_ct_add_to_unconfirmed_list(ct);
|
|
|
|
local_bh_enable();
|
|
|
|
if (exp) {
|
|
if (exp->expectfn)
|
|
exp->expectfn(ct, exp);
|
|
nf_ct_expect_put(exp);
|
|
}
|
|
|
|
return &ct->tuplehash[IP_CT_DIR_ORIGINAL];
|
|
}
|
|
|
|
/* On success, returns conntrack ptr, sets skb->nfct and ctinfo */
|
|
static inline struct nf_conn *
|
|
resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
|
|
struct sk_buff *skb,
|
|
unsigned int dataoff,
|
|
u_int16_t l3num,
|
|
u_int8_t protonum,
|
|
struct nf_conntrack_l3proto *l3proto,
|
|
struct nf_conntrack_l4proto *l4proto,
|
|
int *set_reply,
|
|
enum ip_conntrack_info *ctinfo)
|
|
{
|
|
const struct nf_conntrack_zone *zone;
|
|
struct nf_conntrack_tuple tuple;
|
|
struct nf_conntrack_tuple_hash *h;
|
|
struct nf_conntrack_zone tmp;
|
|
struct nf_conn *ct;
|
|
u32 hash;
|
|
|
|
if (!nf_ct_get_tuple(skb, skb_network_offset(skb),
|
|
dataoff, l3num, protonum, net, &tuple, l3proto,
|
|
l4proto)) {
|
|
pr_debug("Can't get tuple\n");
|
|
return NULL;
|
|
}
|
|
|
|
/* look for tuple match */
|
|
zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
|
|
hash = hash_conntrack_raw(&tuple, net);
|
|
h = __nf_conntrack_find_get(net, zone, &tuple, hash);
|
|
if (!h) {
|
|
h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto,
|
|
skb, dataoff, hash);
|
|
if (!h)
|
|
return NULL;
|
|
if (IS_ERR(h))
|
|
return (void *)h;
|
|
}
|
|
ct = nf_ct_tuplehash_to_ctrack(h);
|
|
|
|
/* It exists; we have (non-exclusive) reference. */
|
|
if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) {
|
|
*ctinfo = IP_CT_ESTABLISHED_REPLY;
|
|
/* Please set reply bit if this packet OK */
|
|
*set_reply = 1;
|
|
} else {
|
|
/* Once we've had two way comms, always ESTABLISHED. */
|
|
if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
|
|
pr_debug("normal packet for %p\n", ct);
|
|
*ctinfo = IP_CT_ESTABLISHED;
|
|
} else if (test_bit(IPS_EXPECTED_BIT, &ct->status)) {
|
|
pr_debug("related packet for %p\n", ct);
|
|
*ctinfo = IP_CT_RELATED;
|
|
} else {
|
|
pr_debug("new packet for %p\n", ct);
|
|
*ctinfo = IP_CT_NEW;
|
|
}
|
|
*set_reply = 0;
|
|
}
|
|
skb->nfct = &ct->ct_general;
|
|
skb->nfctinfo = *ctinfo;
|
|
return ct;
|
|
}
|
|
|
|
unsigned int
|
|
nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
|
|
struct sk_buff *skb)
|
|
{
|
|
struct nf_conn *ct, *tmpl = NULL;
|
|
enum ip_conntrack_info ctinfo;
|
|
struct nf_conntrack_l3proto *l3proto;
|
|
struct nf_conntrack_l4proto *l4proto;
|
|
unsigned int *timeouts;
|
|
unsigned int dataoff;
|
|
u_int8_t protonum;
|
|
int set_reply = 0;
|
|
int ret;
|
|
|
|
if (skb->nfct) {
|
|
/* 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 */
|
|
l3proto = __nf_ct_l3proto_find(pf);
|
|
ret = l3proto->get_l4proto(skb, skb_network_offset(skb),
|
|
&dataoff, &protonum);
|
|
if (ret <= 0) {
|
|
pr_debug("not prepared to track yet or error occurred\n");
|
|
NF_CT_STAT_INC_ATOMIC(net, error);
|
|
NF_CT_STAT_INC_ATOMIC(net, invalid);
|
|
ret = -ret;
|
|
goto out;
|
|
}
|
|
|
|
l4proto = __nf_ct_l4proto_find(pf, protonum);
|
|
|
|
/* It may be an special packet, error, unclean...
|
|
* inverse of the return code tells to the netfilter
|
|
* core what to do with the packet. */
|
|
if (l4proto->error != NULL) {
|
|
ret = l4proto->error(net, tmpl, skb, dataoff, &ctinfo,
|
|
pf, hooknum);
|
|
if (ret <= 0) {
|
|
NF_CT_STAT_INC_ATOMIC(net, error);
|
|
NF_CT_STAT_INC_ATOMIC(net, invalid);
|
|
ret = -ret;
|
|
goto out;
|
|
}
|
|
/* ICMP[v6] protocol trackers may assign one conntrack. */
|
|
if (skb->nfct)
|
|
goto out;
|
|
}
|
|
|
|
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);
|
|
ret = NF_ACCEPT;
|
|
goto out;
|
|
}
|
|
|
|
if (IS_ERR(ct)) {
|
|
/* Too stressed to deal. */
|
|
NF_CT_STAT_INC_ATOMIC(net, drop);
|
|
ret = NF_DROP;
|
|
goto out;
|
|
}
|
|
|
|
NF_CT_ASSERT(skb->nfct);
|
|
|
|
/* Decide what timeout policy we want to apply to this flow. */
|
|
timeouts = nf_ct_timeout_lookup(net, ct, l4proto);
|
|
|
|
ret = l4proto->packet(ct, skb, dataoff, ctinfo, pf, hooknum, timeouts);
|
|
if (ret <= 0) {
|
|
/* Invalid: inverse of the return code tells
|
|
* the netfilter core what to do */
|
|
pr_debug("nf_conntrack_in: Can't track with proto module\n");
|
|
nf_conntrack_put(skb->nfct);
|
|
skb->nfct = NULL;
|
|
NF_CT_STAT_INC_ATOMIC(net, invalid);
|
|
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_REPLY, ct);
|
|
out:
|
|
if (tmpl) {
|
|
/* Special case: we have to repeat this hook, assign the
|
|
* template again to this packet. We assume that this packet
|
|
* has no conntrack assigned. This is used by nf_ct_tcp. */
|
|
if (ret == NF_REPEAT)
|
|
skb->nfct = (struct nf_conntrack *)tmpl;
|
|
else
|
|
nf_ct_put(tmpl);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_conntrack_in);
|
|
|
|
bool nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse,
|
|
const struct nf_conntrack_tuple *orig)
|
|
{
|
|
bool ret;
|
|
|
|
rcu_read_lock();
|
|
ret = nf_ct_invert_tuple(inverse, orig,
|
|
__nf_ct_l3proto_find(orig->src.l3num),
|
|
__nf_ct_l4proto_find(orig->src.l3num,
|
|
orig->dst.protonum));
|
|
rcu_read_unlock();
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_ct_invert_tuplepr);
|
|
|
|
/* Alter reply tuple (maybe alter helper). This is for NAT, and is
|
|
implicitly racy: see __nf_conntrack_confirm */
|
|
void nf_conntrack_alter_reply(struct nf_conn *ct,
|
|
const struct nf_conntrack_tuple *newreply)
|
|
{
|
|
struct nf_conn_help *help = nfct_help(ct);
|
|
|
|
/* Should be unconfirmed, so not in hash table yet */
|
|
NF_CT_ASSERT(!nf_ct_is_confirmed(ct));
|
|
|
|
pr_debug("Altering reply tuple of %p to ", ct);
|
|
nf_ct_dump_tuple(newreply);
|
|
|
|
ct->tuplehash[IP_CT_DIR_REPLY].tuple = *newreply;
|
|
if (ct->master || (help && !hlist_empty(&help->expectations)))
|
|
return;
|
|
|
|
rcu_read_lock();
|
|
__nf_ct_try_assign_helper(ct, NULL, GFP_ATOMIC);
|
|
rcu_read_unlock();
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_conntrack_alter_reply);
|
|
|
|
/* Refresh conntrack for this many jiffies and do accounting if do_acct is 1 */
|
|
void __nf_ct_refresh_acct(struct nf_conn *ct,
|
|
enum ip_conntrack_info ctinfo,
|
|
const struct sk_buff *skb,
|
|
unsigned long extra_jiffies,
|
|
int do_acct)
|
|
{
|
|
NF_CT_ASSERT(ct->timeout.data == (unsigned long)ct);
|
|
NF_CT_ASSERT(skb);
|
|
|
|
/* 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;
|
|
} 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)
|
|
mod_timer_pending(&ct->timeout, newtime);
|
|
}
|
|
|
|
acct:
|
|
if (do_acct)
|
|
nf_ct_acct_update(ct, ctinfo, skb->len);
|
|
}
|
|
EXPORT_SYMBOL_GPL(__nf_ct_refresh_acct);
|
|
|
|
bool __nf_ct_kill_acct(struct nf_conn *ct,
|
|
enum ip_conntrack_info ctinfo,
|
|
const struct sk_buff *skb,
|
|
int do_acct)
|
|
{
|
|
if (do_acct)
|
|
nf_ct_acct_update(ct, ctinfo, skb->len);
|
|
|
|
if (del_timer(&ct->timeout)) {
|
|
ct->timeout.function((unsigned long)ct);
|
|
return true;
|
|
}
|
|
return false;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__nf_ct_kill_acct);
|
|
|
|
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
|
|
|
|
#include <linux/netfilter/nfnetlink.h>
|
|
#include <linux/netfilter/nfnetlink_conntrack.h>
|
|
#include <linux/mutex.h>
|
|
|
|
/* Generic function for tcp/udp/sctp/dccp and alike. This needs to be
|
|
* in ip_conntrack_core, since we don't want the protocols to autoload
|
|
* or depend on ctnetlink */
|
|
int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb,
|
|
const struct nf_conntrack_tuple *tuple)
|
|
{
|
|
if (nla_put_be16(skb, CTA_PROTO_SRC_PORT, tuple->src.u.tcp.port) ||
|
|
nla_put_be16(skb, CTA_PROTO_DST_PORT, tuple->dst.u.tcp.port))
|
|
goto nla_put_failure;
|
|
return 0;
|
|
|
|
nla_put_failure:
|
|
return -1;
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_ct_port_tuple_to_nlattr);
|
|
|
|
const struct nla_policy nf_ct_port_nla_policy[CTA_PROTO_MAX+1] = {
|
|
[CTA_PROTO_SRC_PORT] = { .type = NLA_U16 },
|
|
[CTA_PROTO_DST_PORT] = { .type = NLA_U16 },
|
|
};
|
|
EXPORT_SYMBOL_GPL(nf_ct_port_nla_policy);
|
|
|
|
int nf_ct_port_nlattr_to_tuple(struct nlattr *tb[],
|
|
struct nf_conntrack_tuple *t)
|
|
{
|
|
if (!tb[CTA_PROTO_SRC_PORT] || !tb[CTA_PROTO_DST_PORT])
|
|
return -EINVAL;
|
|
|
|
t->src.u.tcp.port = nla_get_be16(tb[CTA_PROTO_SRC_PORT]);
|
|
t->dst.u.tcp.port = nla_get_be16(tb[CTA_PROTO_DST_PORT]);
|
|
|
|
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. */
|
|
static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb)
|
|
{
|
|
struct nf_conn *ct;
|
|
enum ip_conntrack_info ctinfo;
|
|
|
|
/* This ICMP is in reverse direction to the packet which caused it */
|
|
ct = nf_ct_get(skb, &ctinfo);
|
|
if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL)
|
|
ctinfo = IP_CT_RELATED_REPLY;
|
|
else
|
|
ctinfo = IP_CT_RELATED;
|
|
|
|
/* Attach to new skbuff, and increment count */
|
|
nskb->nfct = &ct->ct_general;
|
|
nskb->nfctinfo = ctinfo;
|
|
nf_conntrack_get(nskb->nfct);
|
|
}
|
|
|
|
/* Bring out ya dead! */
|
|
static struct nf_conn *
|
|
get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data),
|
|
void *data, unsigned int *bucket)
|
|
{
|
|
struct nf_conntrack_tuple_hash *h;
|
|
struct nf_conn *ct;
|
|
struct hlist_nulls_node *n;
|
|
int cpu;
|
|
spinlock_t *lockp;
|
|
|
|
for (; *bucket < nf_conntrack_htable_size; (*bucket)++) {
|
|
lockp = &nf_conntrack_locks[*bucket % CONNTRACK_LOCKS];
|
|
local_bh_disable();
|
|
nf_conntrack_lock(lockp);
|
|
if (*bucket < nf_conntrack_htable_size) {
|
|
hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[*bucket], hnnode) {
|
|
if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
|
|
continue;
|
|
ct = nf_ct_tuplehash_to_ctrack(h);
|
|
if (net_eq(nf_ct_net(ct), net) &&
|
|
iter(ct, data))
|
|
goto found;
|
|
}
|
|
}
|
|
spin_unlock(lockp);
|
|
local_bh_enable();
|
|
cond_resched();
|
|
}
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
|
|
|
|
spin_lock_bh(&pcpu->lock);
|
|
hlist_nulls_for_each_entry(h, n, &pcpu->unconfirmed, hnnode) {
|
|
ct = nf_ct_tuplehash_to_ctrack(h);
|
|
if (iter(ct, data))
|
|
set_bit(IPS_DYING_BIT, &ct->status);
|
|
}
|
|
spin_unlock_bh(&pcpu->lock);
|
|
cond_resched();
|
|
}
|
|
return NULL;
|
|
found:
|
|
atomic_inc(&ct->ct_general.use);
|
|
spin_unlock(lockp);
|
|
local_bh_enable();
|
|
return ct;
|
|
}
|
|
|
|
void nf_ct_iterate_cleanup(struct net *net,
|
|
int (*iter)(struct nf_conn *i, void *data),
|
|
void *data, u32 portid, int report)
|
|
{
|
|
struct nf_conn *ct;
|
|
unsigned int bucket = 0;
|
|
|
|
might_sleep();
|
|
|
|
if (atomic_read(&net->ct.count) == 0)
|
|
return;
|
|
|
|
while ((ct = get_next_corpse(net, iter, data, &bucket)) != NULL) {
|
|
/* Time to push up daises... */
|
|
if (del_timer(&ct->timeout))
|
|
nf_ct_delete(ct, portid, report);
|
|
|
|
/* ... else the timer will get him soon. */
|
|
|
|
nf_ct_put(ct);
|
|
cond_resched();
|
|
}
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup);
|
|
|
|
static int kill_all(struct nf_conn *i, void *data)
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
void nf_ct_free_hashtable(void *hash, unsigned int size)
|
|
{
|
|
if (is_vmalloc_addr(hash))
|
|
vfree(hash);
|
|
else
|
|
free_pages((unsigned long)hash,
|
|
get_order(sizeof(struct hlist_head) * size));
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_ct_free_hashtable);
|
|
|
|
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;
|
|
}
|
|
|
|
void nf_conntrack_cleanup_start(void)
|
|
{
|
|
RCU_INIT_POINTER(ip_ct_attach, NULL);
|
|
}
|
|
|
|
void nf_conntrack_cleanup_end(void)
|
|
{
|
|
RCU_INIT_POINTER(nf_ct_destroy, NULL);
|
|
while (untrack_refs() > 0)
|
|
schedule();
|
|
|
|
nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size);
|
|
|
|
nf_conntrack_proto_fini();
|
|
nf_conntrack_seqadj_fini();
|
|
nf_conntrack_labels_fini();
|
|
nf_conntrack_helper_fini();
|
|
nf_conntrack_timeout_fini();
|
|
nf_conntrack_ecache_fini();
|
|
nf_conntrack_tstamp_fini();
|
|
nf_conntrack_acct_fini();
|
|
nf_conntrack_expect_fini();
|
|
|
|
kmem_cache_destroy(nf_conntrack_cachep);
|
|
}
|
|
|
|
/*
|
|
* Mishearing the voices in his head, our hero wonders how he's
|
|
* supposed to kill the mall.
|
|
*/
|
|
void nf_conntrack_cleanup_net(struct net *net)
|
|
{
|
|
LIST_HEAD(single);
|
|
|
|
list_add(&net->exit_list, &single);
|
|
nf_conntrack_cleanup_net_list(&single);
|
|
}
|
|
|
|
void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list)
|
|
{
|
|
int busy;
|
|
struct net *net;
|
|
|
|
/*
|
|
* This makes sure all current packets have passed through
|
|
* netfilter framework. Roll on, two-stage module
|
|
* delete...
|
|
*/
|
|
synchronize_net();
|
|
i_see_dead_people:
|
|
busy = 0;
|
|
list_for_each_entry(net, net_exit_list, exit_list) {
|
|
nf_ct_iterate_cleanup(net, kill_all, NULL, 0, 0);
|
|
if (atomic_read(&net->ct.count) != 0)
|
|
busy = 1;
|
|
}
|
|
if (busy) {
|
|
schedule();
|
|
goto i_see_dead_people;
|
|
}
|
|
|
|
list_for_each_entry(net, net_exit_list, exit_list) {
|
|
nf_conntrack_proto_pernet_fini(net);
|
|
nf_conntrack_helper_pernet_fini(net);
|
|
nf_conntrack_ecache_pernet_fini(net);
|
|
nf_conntrack_tstamp_pernet_fini(net);
|
|
nf_conntrack_acct_pernet_fini(net);
|
|
nf_conntrack_expect_pernet_fini(net);
|
|
free_percpu(net->ct.stat);
|
|
free_percpu(net->ct.pcpu_lists);
|
|
}
|
|
}
|
|
|
|
void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls)
|
|
{
|
|
struct hlist_nulls_head *hash;
|
|
unsigned int nr_slots, i;
|
|
size_t sz;
|
|
|
|
if (*sizep > (UINT_MAX / sizeof(struct hlist_nulls_head)))
|
|
return NULL;
|
|
|
|
BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head));
|
|
nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head));
|
|
|
|
if (nr_slots > (UINT_MAX / sizeof(struct hlist_nulls_head)))
|
|
return NULL;
|
|
|
|
sz = nr_slots * sizeof(struct hlist_nulls_head);
|
|
hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO,
|
|
get_order(sz));
|
|
if (!hash)
|
|
hash = vzalloc(sz);
|
|
|
|
if (hash && nulls)
|
|
for (i = 0; i < nr_slots; i++)
|
|
INIT_HLIST_NULLS_HEAD(&hash[i], i);
|
|
|
|
return hash;
|
|
}
|
|
EXPORT_SYMBOL_GPL(nf_ct_alloc_hashtable);
|
|
|
|
int nf_conntrack_hash_resize(unsigned int hashsize)
|
|
{
|
|
int i, bucket;
|
|
unsigned int old_size;
|
|
struct hlist_nulls_head *hash, *old_hash;
|
|
struct nf_conntrack_tuple_hash *h;
|
|
struct nf_conn *ct;
|
|
|
|
if (!hashsize)
|
|
return -EINVAL;
|
|
|
|
hash = nf_ct_alloc_hashtable(&hashsize, 1);
|
|
if (!hash)
|
|
return -ENOMEM;
|
|
|
|
old_size = nf_conntrack_htable_size;
|
|
if (old_size == hashsize) {
|
|
nf_ct_free_hashtable(hash, hashsize);
|
|
return 0;
|
|
}
|
|
|
|
local_bh_disable();
|
|
nf_conntrack_all_lock();
|
|
write_seqcount_begin(&nf_conntrack_generation);
|
|
|
|
/* 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 locks.
|
|
*/
|
|
|
|
for (i = 0; i < nf_conntrack_htable_size; i++) {
|
|
while (!hlist_nulls_empty(&nf_conntrack_hash[i])) {
|
|
h = hlist_nulls_entry(nf_conntrack_hash[i].first,
|
|
struct nf_conntrack_tuple_hash, hnnode);
|
|
ct = nf_ct_tuplehash_to_ctrack(h);
|
|
hlist_nulls_del_rcu(&h->hnnode);
|
|
bucket = __hash_conntrack(nf_ct_net(ct),
|
|
&h->tuple, hashsize);
|
|
hlist_nulls_add_head_rcu(&h->hnnode, &hash[bucket]);
|
|
}
|
|
}
|
|
old_size = nf_conntrack_htable_size;
|
|
old_hash = nf_conntrack_hash;
|
|
|
|
nf_conntrack_hash = hash;
|
|
nf_conntrack_htable_size = hashsize;
|
|
|
|
write_seqcount_end(&nf_conntrack_generation);
|
|
nf_conntrack_all_unlock();
|
|
local_bh_enable();
|
|
|
|
synchronize_net();
|
|
nf_ct_free_hashtable(old_hash, old_size);
|
|
return 0;
|
|
}
|
|
|
|
int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
|
|
{
|
|
unsigned int hashsize;
|
|
int rc;
|
|
|
|
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);
|
|
|
|
rc = kstrtouint(val, 0, &hashsize);
|
|
if (rc)
|
|
return rc;
|
|
|
|
return nf_conntrack_hash_resize(hashsize);
|
|
}
|
|
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);
|
|
|
|
int nf_conntrack_init_start(void)
|
|
{
|
|
int max_factor = 8;
|
|
int ret = -ENOMEM;
|
|
int i, cpu;
|
|
|
|
seqcount_init(&nf_conntrack_generation);
|
|
|
|
for (i = 0; i < CONNTRACK_LOCKS; i++)
|
|
spin_lock_init(&nf_conntrack_locks[i]);
|
|
|
|
if (!nf_conntrack_htable_size) {
|
|
/* Idea from tcp.c: use 1/16384 of memory.
|
|
* On i386: 32MB machine has 512 buckets.
|
|
* >= 1GB machines have 16384 buckets.
|
|
* >= 4GB machines have 65536 buckets.
|
|
*/
|
|
nf_conntrack_htable_size
|
|
= (((totalram_pages << PAGE_SHIFT) / 16384)
|
|
/ sizeof(struct hlist_head));
|
|
if (totalram_pages > (4 * (1024 * 1024 * 1024 / PAGE_SIZE)))
|
|
nf_conntrack_htable_size = 65536;
|
|
else if (totalram_pages > (1024 * 1024 * 1024 / PAGE_SIZE))
|
|
nf_conntrack_htable_size = 16384;
|
|
if (nf_conntrack_htable_size < 32)
|
|
nf_conntrack_htable_size = 32;
|
|
|
|
/* Use a max. factor of four by default to get the same max as
|
|
* with the old struct list_heads. When a table size is given
|
|
* we use the old value of 8 to avoid reducing the max.
|
|
* entries. */
|
|
max_factor = 4;
|
|
}
|
|
|
|
nf_conntrack_hash = nf_ct_alloc_hashtable(&nf_conntrack_htable_size, 1);
|
|
if (!nf_conntrack_hash)
|
|
return -ENOMEM;
|
|
|
|
nf_conntrack_max = max_factor * nf_conntrack_htable_size;
|
|
|
|
nf_conntrack_cachep = kmem_cache_create("nf_conntrack",
|
|
sizeof(struct nf_conn), 0,
|
|
SLAB_DESTROY_BY_RCU | SLAB_HWCACHE_ALIGN, NULL);
|
|
if (!nf_conntrack_cachep)
|
|
goto err_cachep;
|
|
|
|
printk(KERN_INFO "nf_conntrack version %s (%u buckets, %d max)\n",
|
|
NF_CONNTRACK_VERSION, nf_conntrack_htable_size,
|
|
nf_conntrack_max);
|
|
|
|
ret = nf_conntrack_expect_init();
|
|
if (ret < 0)
|
|
goto err_expect;
|
|
|
|
ret = nf_conntrack_acct_init();
|
|
if (ret < 0)
|
|
goto err_acct;
|
|
|
|
ret = nf_conntrack_tstamp_init();
|
|
if (ret < 0)
|
|
goto err_tstamp;
|
|
|
|
ret = nf_conntrack_ecache_init();
|
|
if (ret < 0)
|
|
goto err_ecache;
|
|
|
|
ret = nf_conntrack_timeout_init();
|
|
if (ret < 0)
|
|
goto err_timeout;
|
|
|
|
ret = nf_conntrack_helper_init();
|
|
if (ret < 0)
|
|
goto err_helper;
|
|
|
|
ret = nf_conntrack_labels_init();
|
|
if (ret < 0)
|
|
goto err_labels;
|
|
|
|
ret = nf_conntrack_seqadj_init();
|
|
if (ret < 0)
|
|
goto err_seqadj;
|
|
|
|
ret = nf_conntrack_proto_init();
|
|
if (ret < 0)
|
|
goto err_proto;
|
|
|
|
/* Set up fake conntrack: to never be deleted, not in any hashes */
|
|
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 */
|
|
nf_ct_untracked_status_or(IPS_CONFIRMED | IPS_UNTRACKED);
|
|
return 0;
|
|
|
|
err_proto:
|
|
nf_conntrack_seqadj_fini();
|
|
err_seqadj:
|
|
nf_conntrack_labels_fini();
|
|
err_labels:
|
|
nf_conntrack_helper_fini();
|
|
err_helper:
|
|
nf_conntrack_timeout_fini();
|
|
err_timeout:
|
|
nf_conntrack_ecache_fini();
|
|
err_ecache:
|
|
nf_conntrack_tstamp_fini();
|
|
err_tstamp:
|
|
nf_conntrack_acct_fini();
|
|
err_acct:
|
|
nf_conntrack_expect_fini();
|
|
err_expect:
|
|
kmem_cache_destroy(nf_conntrack_cachep);
|
|
err_cachep:
|
|
nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size);
|
|
return ret;
|
|
}
|
|
|
|
void nf_conntrack_init_end(void)
|
|
{
|
|
/* For use by REJECT target */
|
|
RCU_INIT_POINTER(ip_ct_attach, nf_conntrack_attach);
|
|
RCU_INIT_POINTER(nf_ct_destroy, destroy_conntrack);
|
|
}
|
|
|
|
/*
|
|
* 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)
|
|
#define TEMPLATE_NULLS_VAL ((1<<30)+2)
|
|
|
|
int nf_conntrack_init_net(struct net *net)
|
|
{
|
|
int ret = -ENOMEM;
|
|
int cpu;
|
|
|
|
atomic_set(&net->ct.count, 0);
|
|
|
|
net->ct.pcpu_lists = alloc_percpu(struct ct_pcpu);
|
|
if (!net->ct.pcpu_lists)
|
|
goto err_stat;
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
|
|
|
|
spin_lock_init(&pcpu->lock);
|
|
INIT_HLIST_NULLS_HEAD(&pcpu->unconfirmed, UNCONFIRMED_NULLS_VAL);
|
|
INIT_HLIST_NULLS_HEAD(&pcpu->dying, DYING_NULLS_VAL);
|
|
}
|
|
|
|
net->ct.stat = alloc_percpu(struct ip_conntrack_stat);
|
|
if (!net->ct.stat)
|
|
goto err_pcpu_lists;
|
|
|
|
ret = nf_conntrack_expect_pernet_init(net);
|
|
if (ret < 0)
|
|
goto err_expect;
|
|
ret = nf_conntrack_acct_pernet_init(net);
|
|
if (ret < 0)
|
|
goto err_acct;
|
|
ret = nf_conntrack_tstamp_pernet_init(net);
|
|
if (ret < 0)
|
|
goto err_tstamp;
|
|
ret = nf_conntrack_ecache_pernet_init(net);
|
|
if (ret < 0)
|
|
goto err_ecache;
|
|
ret = nf_conntrack_helper_pernet_init(net);
|
|
if (ret < 0)
|
|
goto err_helper;
|
|
ret = nf_conntrack_proto_pernet_init(net);
|
|
if (ret < 0)
|
|
goto err_proto;
|
|
return 0;
|
|
|
|
err_proto:
|
|
nf_conntrack_helper_pernet_fini(net);
|
|
err_helper:
|
|
nf_conntrack_ecache_pernet_fini(net);
|
|
err_ecache:
|
|
nf_conntrack_tstamp_pernet_fini(net);
|
|
err_tstamp:
|
|
nf_conntrack_acct_pernet_fini(net);
|
|
err_acct:
|
|
nf_conntrack_expect_pernet_fini(net);
|
|
err_expect:
|
|
free_percpu(net->ct.stat);
|
|
err_pcpu_lists:
|
|
free_percpu(net->ct.pcpu_lists);
|
|
err_stat:
|
|
return ret;
|
|
}
|