Release 4.11 net/netfilter/nf_conntrack_core.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);


struct conntrack_gc_work {
	
struct delayed_work	dwork;
	
u32			last_bucket;
	
bool			exiting;
	
long			next_gc_run;
};


static __read_mostly struct kmem_cache *nf_conntrack_cachep;

static __read_mostly spinlock_t nf_conntrack_locks_all_lock;
static __read_mostly DEFINE_SPINLOCK(nf_conntrack_locks_all_lock);

static __read_mostly bool nf_conntrack_locks_all;

/* every gc cycle scans at most 1/GC_MAX_BUCKETS_DIV part of table */

#define GC_MAX_BUCKETS_DIV	128u
/* upper bound of full table scan */

#define GC_MAX_SCAN_JIFFIES	(16u * HZ)
/* desired ratio of entries found to be expired */

#define GC_EVICT_RATIO	50u


static struct conntrack_gc_work conntrack_gc_work;



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);
	}
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Sasha Levin
42
87.50%
1
33.33%
Peter Zijlstra
5
10.42%
1
33.33%
Nicholas Mc Guire
1
2.08%
1
33.33%
Total
48
100.00%
3
100.00%


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]);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jesper Dangaard Brouer
46
100.00%
1
100.00%
Total
46
100.00%
1
100.00%

/* 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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jesper Dangaard Brouer
110
97.35%
1
33.33%
Sasha Levin
2
1.77%
1
33.33%
Florian Westphal
1
0.88%
1
33.33%
Total
113
100.00%
3
100.00%



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]);
	}
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jesper Dangaard Brouer
27
54.00%
1
25.00%
Sasha Levin
17
34.00%
1
25.00%
Peter Zijlstra
5
10.00%
1
25.00%
Nicholas Mc Guire
1
2.00%
1
25.00%
Total
50
100.00%
4
100.00%



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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jesper Dangaard Brouer
13
56.52%
1
33.33%
Peter Zijlstra
6
26.09%
1
33.33%
Sasha Levin
4
17.39%
1
33.33%
Total
23
100.00%
3
100.00%


unsigned int nf_conntrack_htable_size __read_mostly;

EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);


unsigned int nf_conntrack_max __read_mostly;

seqcount_t nf_conntrack_generation __read_mostly;

/* nf_conn must be 8 bytes aligned, as the 3 LSB bits are used
 * for the nfctinfo. We cheat by (ab)using the PER CPU cache line
 * alignment to enforce this.
 */
DEFINE_PER_CPU_ALIGNED(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));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Yasuyuki Kozakai
46
42.20%
1
14.29%
Florian Westphal
30
27.52%
2
28.57%
Patrick McHardy
23
21.10%
1
14.29%
Changli Gao
5
4.59%
1
14.29%
Al Viro
4
3.67%
1
14.29%
Sami Farin
1
0.92%
1
14.29%
Total
109
100.00%
7
100.00%



static u32 scale_hash(u32 hash)
{
	return reciprocal_scale(hash, nf_conntrack_htable_size);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Changli Gao
14
82.35%
1
33.33%
Florian Westphal
3
17.65%
2
66.67%
Total
17
100.00%
3
100.00%



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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Changli Gao
25
71.43%
1
50.00%
Florian Westphal
10
28.57%
1
50.00%
Total
35
100.00%
2
100.00%



static u32 hash_conntrack(const struct net *net,
			  const struct nf_conntrack_tuple *tuple)
{
	return scale_hash(hash_conntrack_raw(tuple, net));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Yasuyuki Kozakai
17
58.62%
1
20.00%
Florian Westphal
5
17.24%
2
40.00%
Patrick McHardy
5
17.24%
1
20.00%
Daniel Borkmann
2
6.90%
1
20.00%
Total
29
100.00%
5
100.00%


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);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Yasuyuki Kozakai
95
81.90%
1
20.00%
Philip Craig
9
7.76%
1
20.00%
Eric W. Biedermann
7
6.03%
1
20.00%
Martin Josefsson
3
2.59%
1
20.00%
Jan Engelhardt
2
1.72%
1
20.00%
Total
116
100.00%
5
100.00%


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;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Yasuyuki Kozakai
118
92.91%
1
33.33%
Eric W. Biedermann
7
5.51%
1
33.33%
Jan Engelhardt
2
1.57%
1
33.33%
Total
127
100.00%
3
100.00%


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);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Yasuyuki Kozakai
90
86.54%
1
25.00%
Philip Craig
9
8.65%
1
25.00%
Martin Josefsson
3
2.88%
1
25.00%
Jan Engelhardt
2
1.92%
1
25.00%
Total
104
100.00%
4
100.00%


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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Martin Josefsson
22
44.00%
1
16.67%
Yasuyuki Kozakai
19
38.00%
1
16.67%
Eric Dumazet
4
8.00%
1
16.67%
Harald Welte
3
6.00%
1
16.67%
Patrick McHardy
2
4.00%
2
33.33%
Total
50
100.00%
6
100.00%

/* 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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jesper Dangaard Brouer
76
100.00%
1
100.00%
Total
76
100.00%
1
100.00%

/* 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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jesper Dangaard Brouer
76
100.00%
1
100.00%
Total
76
100.00%
1
100.00%

/* 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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jesper Dangaard Brouer
80
100.00%
1
100.00%
Total
80
100.00%
1
100.00%


#define NFCT_ALIGN(len)	(((len) + NFCT_INFOMASK) & ~NFCT_INFOMASK)

/* 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, *p;

	if (ARCH_KMALLOC_MINALIGN <= NFCT_INFOMASK) {
		tmpl = kzalloc(sizeof(*tmpl) + NFCT_INFOMASK, flags);
		if (!tmpl)
			return NULL;

		p = tmpl;
		tmpl = (struct nf_conn *)NFCT_ALIGN((unsigned long)p);
		if (tmpl != p) {
			tmpl = (struct nf_conn *)NFCT_ALIGN((unsigned long)p);
			tmpl->proto.tmpl_padto = (char *)tmpl - (char *)p;
		}
	} else {
		tmpl = kzalloc(sizeof(*tmpl), flags);
		if (!tmpl)
			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;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Florian Westphal
100
54.35%
2
33.33%
Pablo Neira Ayuso
75
40.76%
1
16.67%
Daniel Borkmann
6
3.26%
2
33.33%
Joe Stringer
3
1.63%
1
16.67%
Total
184
100.00%
6
100.00%


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);

	if (ARCH_KMALLOC_MINALIGN <= NFCT_INFOMASK)
		kfree((char *)tmpl - tmpl->proto.tmpl_padto);
	else
		kfree(tmpl);
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Pablo Neira Ayuso
25
53.19%
1
50.00%
Florian Westphal
22
46.81%
1
50.00%
Total
47
100.00%
2
100.00%


EXPORT_SYMBOL_GPL(nf_ct_tmpl_free);


static void

destroy_conntrack(struct nf_conntrack *nfct)
{
	struct nf_conn *ct = (struct nf_conn *)nfct;
	struct nf_conntrack_l4proto *l4proto;

	pr_debug("destroy_conntrack(%p)\n", ct);
	NF_CT_ASSERT(atomic_read(&nfct->use) == 0);

	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);

	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);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Martin Josefsson
60
42.25%
2
16.67%
Yasuyuki Kozakai
40
28.17%
1
8.33%
Pablo Neira Ayuso
19
13.38%
2
16.67%
Patrick McHardy
14
9.86%
4
33.33%
Jesper Dangaard Brouer
6
4.23%
2
16.67%
Harald Welte
3
2.11%
1
8.33%
Total
142
100.00%
12
100.00%



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);

	local_bh_enable();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jesper Dangaard Brouer
69
58.47%
2
28.57%
Pablo Neira Ayuso
43
36.44%
2
28.57%
Daniel Borkmann
4
3.39%
1
14.29%
Florian Westphal
2
1.69%
2
28.57%
Total
118
100.00%
7
100.00%



bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report)
{
	struct nf_conn_tstamp *tstamp;

	if (test_and_set_bit(IPS_DYING_BIT, &ct->status))
		return false;

	tstamp = nf_conn_tstamp_find(ct);
	if (tstamp && tstamp->stop == 0)
		tstamp->stop = ktime_get_real_ns();

	if (nf_conntrack_event_report(IPCT_DESTROY, ct,
				    portid, report) < 0) {
		/* destroy event was not delivered. nf_ct_put will
                 * be done by event cache worker on redelivery.
                 */
		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));
	nf_ct_delete_from_lists(ct);
	nf_ct_put(ct);
	return true;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Pablo Neira Ayuso
59
51.30%
2
28.57%
Florian Westphal
50
43.48%
3
42.86%
Yasuyuki Kozakai
5
4.35%
1
14.29%
Eric Dumazet
1
0.87%
1
14.29%
Total
115
100.00%
7
100.00%


EXPORT_SYMBOL_GPL(nf_ct_delete);


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));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Andrey Vagin
51
64.56%
1
25.00%
Florian Westphal
16
20.25%
1
25.00%
Daniel Borkmann
12
15.19%
2
50.00%
Total
79
100.00%
4
100.00%

/* caller must hold rcu readlock and none of the nf_conntrack_locks */


static void nf_ct_gc_expired(struct nf_conn *ct)
{
	if (!atomic_inc_not_zero(&ct->ct_general.use))
		return;

	if (nf_ct_should_gc(ct))
		nf_ct_kill(ct);

	nf_ct_put(ct);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Florian Westphal
42
100.00%
1
100.00%
Total
42
100.00%
1
100.00%

/*
 * 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, hsize;

begin:
	nf_conntrack_get_ht(&ct_hash, &hsize);
	bucket = reciprocal_scale(hash, hsize);

	hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[bucket], hnnode) {
		struct nf_conn *ct;

		ct = nf_ct_tuplehash_to_ctrack(h);
		if (nf_ct_is_expired(ct)) {
			nf_ct_gc_expired(ct);
			continue;
		}

		if (nf_ct_is_dying(ct))
			continue;

		if (nf_ct_key_equal(h, tuple, zone, net))
			return h;
	}
	/*
         * 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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Florian Westphal
56
35.67%
4
26.67%
Yasuyuki Kozakai
36
22.93%
1
6.67%
Eric Dumazet
15
9.55%
1
6.67%
Patrick McHardy
12
7.64%
3
20.00%
Liping Zhang
9
5.73%
1
6.67%
Jesper Dangaard Brouer
8
5.10%
1
6.67%
Changli Gao
8
5.10%
1
6.67%
Alexey Dobriyan
5
3.18%
1
6.67%
Daniel Borkmann
4
2.55%
1
6.67%
Andrey Vagin
4
2.55%
1
6.67%
Total
157
100.00%
15
100.00%

/* 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;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Yasuyuki Kozakai
42
32.31%
1
10.00%
Patrick McHardy
38
29.23%
3
30.00%
Eric Dumazet
25
19.23%
1
10.00%
Changli Gao
8
6.15%
1
10.00%
Alexey Dobriyan
7
5.38%
1
10.00%
Andrey Vagin
4
3.08%
1
10.00%
Daniel Borkmann
4
3.08%
1
10.00%
Florian Westphal
2
1.54%
1
10.00%
Total
130
100.00%
10
100.00%


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));
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Changli Gao
35
85.37%
1
33.33%
Daniel Borkmann
4
9.76%
1
33.33%
Florian Westphal
2
4.88%
1
33.33%
Total
41
100.00%
3
100.00%


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]);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Pablo Neira Ayuso
38
66.67%
1
16.67%
Patrick McHardy
9
15.79%
1
16.67%
Eric Dumazet
4
7.02%
1
16.67%
Jesper Dangaard Brouer
2
3.51%
1
16.67%
Florian Westphal
2
3.51%
1
16.67%
Yasuyuki Kozakai
2
3.51%
1
16.67%
Total
57
100.00%
6
100.00%


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;

	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 -