summaryrefslogtreecommitdiffstats
path: root/net/netfilter/xt_connlimit.c
blob: e029c4807404f3a4c5644cff7e9f8ef2618d1e7f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
/*
 * netfilter module to limit the number of parallel tcp
 * connections per IP address.
 *   (c) 2000 Gerd Knorr <kraxel@bytesex.org>
 *   Nov 2002: Martin Bene <martin.bene@icomedias.com>:
 *		only ignore TIME_WAIT or gone connections
 *   (C) CC Computer Consultants GmbH, 2007
 *
 * based on ...
 *
 * Kernel module to match connection tracking information.
 * GPL (C) 1999  Rusty Russell (rusty@rustcorp.com.au).
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/jhash.h>
#include <linux/slab.h>
#include <linux/list.h>
#include <linux/module.h>
#include <linux/random.h>
#include <linux/skbuff.h>
#include <linux/spinlock.h>
#include <linux/netfilter/nf_conntrack_tcp.h>
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter/xt_connlimit.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_tuple.h>
#include <net/netfilter/nf_conntrack_zones.h>

/* we will save the tuples of all connections we care about */
struct xt_connlimit_conn {
	struct list_head list;
	struct nf_conntrack_tuple tuple;
};

struct xt_connlimit_data {
	struct list_head iphash[256];
	spinlock_t lock;
};

static u_int32_t connlimit_rnd __read_mostly;
static bool connlimit_rnd_inited __read_mostly;

static inline unsigned int connlimit_iphash(__be32 addr)
{
	return jhash_1word((__force __u32)addr, connlimit_rnd) & 0xFF;
}

static inline unsigned int
connlimit_iphash6(const union nf_inet_addr *addr,
                  const union nf_inet_addr *mask)
{
	union nf_inet_addr res;
	unsigned int i;

	for (i = 0; i < ARRAY_SIZE(addr->ip6); ++i)
		res.ip6[i] = addr->ip6[i] & mask->ip6[i];

	return jhash2((u32 *)res.ip6, ARRAY_SIZE(res.ip6), connlimit_rnd) & 0xFF;
}

static inline bool already_closed(const struct nf_conn *conn)
{
	if (nf_ct_protonum(conn) == IPPROTO_TCP)
		return conn->proto.tcp.state == TCP_CONNTRACK_TIME_WAIT ||
		       conn->proto.tcp.state == TCP_CONNTRACK_CLOSE;
	else
		return 0;
}

static inline unsigned int
same_source_net(const union nf_inet_addr *addr,
		const union nf_inet_addr *mask,
		const union nf_inet_addr *u3, u_int8_t family)
{
	if (family == NFPROTO_IPV4) {
		return (addr->ip & mask->ip) == (u3->ip & mask->ip);
	} else {
		union nf_inet_addr lh, rh;
		unsigned int i;

		for (i = 0; i < ARRAY_SIZE(addr->ip6); ++i) {
			lh.ip6[i] = addr->ip6[i] & mask->ip6[i];
			rh.ip6[i] = u3->ip6[i] & mask->ip6[i];
		}

		return memcmp(&lh.ip6, &rh.ip6, sizeof(lh.ip6)) == 0;
	}
}

static int count_them(struct net *net,
		      struct xt_connlimit_data *data,
		      const struct nf_conntrack_tuple *tuple,
		      const union nf_inet_addr *addr,
		      const union nf_inet_addr *mask,
		      u_int8_t family)
{
	const struct nf_conntrack_tuple_hash *found;
	struct xt_connlimit_conn *conn;
	struct xt_connlimit_conn *tmp;
	struct nf_conn *found_ct;
	struct list_head *hash;
	bool addit = true;
	int matches = 0;

	if (family == NFPROTO_IPV6)
		hash = &data->iphash[connlimit_iphash6(addr, mask)];
	else
		hash = &data->iphash[connlimit_iphash(addr->ip & mask->ip)];

	rcu_read_lock();

	/* check the saved connections */
	list_for_each_entry_safe(conn, tmp, hash, list) {
		found    = nf_conntrack_find_get(net, NF_CT_DEFAULT_ZONE,
						 &conn->tuple);
		found_ct = NULL;

		if (found != NULL)
			found_ct = nf_ct_tuplehash_to_ctrack(found);

		if (found_ct != NULL &&
		    nf_ct_tuple_equal(&conn->tuple, tuple) &&
		    !already_closed(found_ct))
			/*
			 * Just to be sure we have it only once in the list.
			 * We should not see tuples twice unless someone hooks
			 * this into a table without "-p tcp --syn".
			 */
			addit = false;

		if (found == NULL) {
			/* this one is gone */
			list_del(&conn->list);
			kfree(conn);
			continue;
		}

		if (already_closed(found_ct)) {
			/*
			 * we do not care about connections which are
			 * closed already -> ditch it
			 */
			nf_ct_put(found_ct);
			list_del(&conn->list);
			kfree(conn);
			continue;
		}

		if (same_source_net(addr, mask, &conn->tuple.src.u3, family))
			/* same source network -> be counted! */
			++matches;
		nf_ct_put(found_ct);
	}

	rcu_read_unlock();

	if (addit) {
		/* save the new connection in our list */
		conn = kzalloc(sizeof(*conn), GFP_ATOMIC);
		if (conn == NULL)
			return -ENOMEM;
		conn->tuple = *tuple;
		list_add(&conn->list, hash);
		++matches;
	}

	return matches;
}

static bool
connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
	struct net *net = dev_net(par->in ? par->in : par->out);
	const struct xt_connlimit_info *info = par->matchinfo;
	union nf_inet_addr addr;
	struct nf_conntrack_tuple tuple;
	const struct nf_conntrack_tuple *tuple_ptr = &tuple;
	enum ip_conntrack_info ctinfo;
	const struct nf_conn *ct;
	int connections;

	ct = nf_ct_get(skb, &ctinfo);
	if (ct != NULL) {
		if (info->flags & XT_CONNLIMIT_DADDR)
			tuple_ptr = &ct->tuplehash[IP_CT_DIR_REPLY].tuple;
		else
			tuple_ptr = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
	} else if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb),
				    par->family, &tuple)) {
		goto hotdrop;
	}

	if (par->family == NFPROTO_IPV6) {
		const struct ipv6hdr *iph = ipv6_hdr(skb);
		memcpy(&addr.ip6, (info->flags & XT_CONNLIMIT_DADDR) ?
		       &iph->daddr : &iph->saddr, sizeof(addr.ip6));
	} else {
		const struct iphdr *iph = ip_hdr(skb);
		addr.ip = (info->flags & XT_CONNLIMIT_DADDR) ?
			  iph->daddr : iph->saddr;
	}

	spin_lock_bh(&info->data->lock);
	connections = count_them(net, info->data, tuple_ptr, &addr,
	                         &info->mask, par->family);
	spin_unlock_bh(&info->data->lock);

	if (connections < 0)
		/* kmalloc failed, drop it entirely */
		goto hotdrop;

	return (connections > info->limit) ^
	       !!(info->flags & XT_CONNLIMIT_INVERT);

 hotdrop:
	par->hotdrop = true;
	return false;
}

static int connlimit_mt_check(const struct xt_mtchk_param *par)
{
	struct xt_connlimit_info *info = par->matchinfo;
	unsigned int i;
	int ret;

	if (unlikely(!connlimit_rnd_inited)) {
		get_random_bytes(&connlimit_rnd, sizeof(connlimit_rnd));
		connlimit_rnd_inited = true;
	}
	ret = nf_ct_l3proto_try_module_get(par->family);
	if (ret < 0) {
		pr_info("cannot load conntrack support for "
			"address family %u\n", par->family);
		return ret;
	}

	/* init private data */
	info->data = kmalloc(sizeof(struct xt_connlimit_data), GFP_KERNEL);
	if (info->data == NULL) {
		nf_ct_l3proto_module_put(par->family);
		return -ENOMEM;
	}

	spin_lock_init(&info->data->lock);
	for (i = 0; i < ARRAY_SIZE(info->data->iphash); ++i)
		INIT_LIST_HEAD(&info->data->iphash[i]);

	return 0;
}

static void connlimit_mt_destroy(const struct xt_mtdtor_param *par)
{
	const struct xt_connlimit_info *info = par->matchinfo;
	struct xt_connlimit_conn *conn;
	struct xt_connlimit_conn *tmp;
	struct list_head *hash = info->data->iphash;
	unsigned int i;

	nf_ct_l3proto_module_put(par->family);

	for (i = 0; i < ARRAY_SIZE(info->data->iphash); ++i) {
		list_for_each_entry_safe(conn, tmp, &hash[i], list) {
			list_del(&conn->list);
			kfree(conn);
		}
	}

	kfree(info->data);
}

static struct xt_match connlimit_mt_reg[] __read_mostly = {
	{
		.name       = "connlimit",
		.revision   = 0,
		.family     = NFPROTO_UNSPEC,
		.checkentry = connlimit_mt_check,
		.match      = connlimit_mt,
		.matchsize  = sizeof(struct xt_connlimit_info),
		.destroy    = connlimit_mt_destroy,
		.me         = THIS_MODULE,
	},
	{
		.name       = "connlimit",
		.revision   = 1,
		.family     = NFPROTO_UNSPEC,
		.checkentry = connlimit_mt_check,
		.match      = connlimit_mt,
		.matchsize  = sizeof(struct xt_connlimit_info),
		.destroy    = connlimit_mt_destroy,
		.me         = THIS_MODULE,
	},
};

static int __init connlimit_mt_init(void)
{
	return xt_register_matches(connlimit_mt_reg,
	       ARRAY_SIZE(connlimit_mt_reg));
}

static void __exit connlimit_mt_exit(void)
{
	xt_unregister_matches(connlimit_mt_reg, ARRAY_SIZE(connlimit_mt_reg));
}

module_init(connlimit_mt_init);
module_exit(connlimit_mt_exit);
MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>");
MODULE_DESCRIPTION("Xtables: Number of connections matching");
MODULE_LICENSE("GPL");
MODULE_ALIAS("ipt_connlimit");
MODULE_ALIAS("ip6t_connlimit");