summaryrefslogtreecommitdiff
path: root/net/netfilter/xt_connlimit.c
blob: a6214f2353335c20fabdc2a60078ac6be918a22d (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
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
/*
 * 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/rbtree.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>

#define CONNLIMIT_SLOTS		256U

#ifdef CONFIG_LOCKDEP
#define CONNLIMIT_LOCK_SLOTS	8U
#else
#define CONNLIMIT_LOCK_SLOTS	256U
#endif

#define CONNLIMIT_GC_MAX_NODES	8

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

struct xt_connlimit_rb {
	struct rb_node node;
	struct hlist_head hhead; /* connections/hosts in same subnet */
	union nf_inet_addr addr; /* search key */
};

static spinlock_t xt_connlimit_locks[CONNLIMIT_LOCK_SLOTS] __cacheline_aligned_in_smp;

struct xt_connlimit_data {
	struct rb_root climit_root[CONNLIMIT_SLOTS];
};

static u_int32_t connlimit_rnd __read_mostly;
static struct kmem_cache *connlimit_rb_cachep __read_mostly;
static struct kmem_cache *connlimit_conn_cachep __read_mostly;

static inline unsigned int connlimit_iphash(__be32 addr)
{
	return jhash_1word((__force __u32)addr,
			    connlimit_rnd) % CONNLIMIT_SLOTS;
}

static inline unsigned int
connlimit_iphash6(const union nf_inet_addr *addr)
{
	return jhash2((u32 *)addr->ip6, ARRAY_SIZE(addr->ip6),
		       connlimit_rnd) % CONNLIMIT_SLOTS;
}

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 int
same_source(const union nf_inet_addr *addr,
	    const union nf_inet_addr *u3, u_int8_t family)
{
	if (family == NFPROTO_IPV4)
		return ntohl(addr->ip) - ntohl(u3->ip);

	return memcmp(addr->ip6, u3->ip6, sizeof(addr->ip6));
}

static bool add_hlist(struct hlist_head *head,
		      const struct nf_conntrack_tuple *tuple,
		      const union nf_inet_addr *addr)
{
	struct xt_connlimit_conn *conn;

	conn = kmem_cache_alloc(connlimit_conn_cachep, GFP_ATOMIC);
	if (conn == NULL)
		return false;
	conn->tuple = *tuple;
	hlist_add_head(&conn->node, head);
	return true;
}

static unsigned int check_hlist(struct net *net,
				struct hlist_head *head,
				const struct nf_conntrack_tuple *tuple,
				const struct nf_conntrack_zone *zone,
				bool *addit)
{
	const struct nf_conntrack_tuple_hash *found;
	struct xt_connlimit_conn *conn;
	struct hlist_node *n;
	struct nf_conn *found_ct;
	unsigned int length = 0;

	*addit = true;

	/* check the saved connections */
	hlist_for_each_entry_safe(conn, n, head, node) {
		found = nf_conntrack_find_get(net, zone, &conn->tuple);
		if (found == NULL) {
			hlist_del(&conn->node);
			kmem_cache_free(connlimit_conn_cachep, conn);
			continue;
		}

		found_ct = nf_ct_tuplehash_to_ctrack(found);

		if (nf_ct_tuple_equal(&conn->tuple, tuple)) {
			/*
			 * 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;
		} else if (already_closed(found_ct)) {
			/*
			 * we do not care about connections which are
			 * closed already -> ditch it
			 */
			nf_ct_put(found_ct);
			hlist_del(&conn->node);
			kmem_cache_free(connlimit_conn_cachep, conn);
			continue;
		}

		nf_ct_put(found_ct);
		length++;
	}

	return length;
}

static void tree_nodes_free(struct rb_root *root,
			    struct xt_connlimit_rb *gc_nodes[],
			    unsigned int gc_count)
{
	struct xt_connlimit_rb *rbconn;

	while (gc_count) {
		rbconn = gc_nodes[--gc_count];
		rb_erase(&rbconn->node, root);
		kmem_cache_free(connlimit_rb_cachep, rbconn);
	}
}

static unsigned int
count_tree(struct net *net, struct rb_root *root,
	   const struct nf_conntrack_tuple *tuple,
	   const union nf_inet_addr *addr,
	   u8 family, const struct nf_conntrack_zone *zone)
{
	struct xt_connlimit_rb *gc_nodes[CONNLIMIT_GC_MAX_NODES];
	struct rb_node **rbnode, *parent;
	struct xt_connlimit_rb *rbconn;
	struct xt_connlimit_conn *conn;
	unsigned int gc_count;
	bool no_gc = false;

 restart:
	gc_count = 0;
	parent = NULL;
	rbnode = &(root->rb_node);
	while (*rbnode) {
		int diff;
		bool addit;

		rbconn = rb_entry(*rbnode, struct xt_connlimit_rb, node);

		parent = *rbnode;
		diff = same_source(addr, &rbconn->addr, family);
		if (diff < 0) {
			rbnode = &((*rbnode)->rb_left);
		} else if (diff > 0) {
			rbnode = &((*rbnode)->rb_right);
		} else {
			/* same source network -> be counted! */
			unsigned int count;
			count = check_hlist(net, &rbconn->hhead, tuple, zone, &addit);

			tree_nodes_free(root, gc_nodes, gc_count);
			if (!addit)
				return count;

			if (!add_hlist(&rbconn->hhead, tuple, addr))
				return 0; /* hotdrop */

			return count + 1;
		}

		if (no_gc || gc_count >= ARRAY_SIZE(gc_nodes))
			continue;

		/* only used for GC on hhead, retval and 'addit' ignored */
		check_hlist(net, &rbconn->hhead, tuple, zone, &addit);
		if (hlist_empty(&rbconn->hhead))
			gc_nodes[gc_count++] = rbconn;
	}

	if (gc_count) {
		no_gc = true;
		tree_nodes_free(root, gc_nodes, gc_count);
		/* tree_node_free before new allocation permits
		 * allocator to re-use newly free'd object.
		 *
		 * This is a rare event; in most cases we will find
		 * existing node to re-use. (or gc_count is 0).
		 */
		goto restart;
	}

	/* no match, need to insert new node */
	rbconn = kmem_cache_alloc(connlimit_rb_cachep, GFP_ATOMIC);
	if (rbconn == NULL)
		return 0;

	conn = kmem_cache_alloc(connlimit_conn_cachep, GFP_ATOMIC);
	if (conn == NULL) {
		kmem_cache_free(connlimit_rb_cachep, rbconn);
		return 0;
	}

	conn->tuple = *tuple;
	rbconn->addr = *addr;

	INIT_HLIST_HEAD(&rbconn->hhead);
	hlist_add_head(&conn->node, &rbconn->hhead);

	rb_link_node(&rbconn->node, parent, rbnode);
	rb_insert_color(&rbconn->node, root);
	return 1;
}

static int count_them(struct net *net,
		      struct xt_connlimit_data *data,
		      const struct nf_conntrack_tuple *tuple,
		      const union nf_inet_addr *addr,
		      u_int8_t family,
		      const struct nf_conntrack_zone *zone)
{
	struct rb_root *root;
	int count;
	u32 hash;

	if (family == NFPROTO_IPV6)
		hash = connlimit_iphash6(addr);
	else
		hash = connlimit_iphash(addr->ip);
	root = &data->climit_root[hash];

	spin_lock_bh(&xt_connlimit_locks[hash % CONNLIMIT_LOCK_SLOTS]);

	count = count_tree(net, root, tuple, addr, family, zone);

	spin_unlock_bh(&xt_connlimit_locks[hash % CONNLIMIT_LOCK_SLOTS]);

	return count;
}

static bool
connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
	struct net *net = xt_net(par);
	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;
	const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt;
	enum ip_conntrack_info ctinfo;
	const struct nf_conn *ct;
	unsigned int connections;

	ct = nf_ct_get(skb, &ctinfo);
	if (ct != NULL) {
		tuple_ptr = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
		zone = nf_ct_zone(ct);
	} else if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb),
				      xt_family(par), net, &tuple)) {
		goto hotdrop;
	}

	if (xt_family(par) == NFPROTO_IPV6) {
		const struct ipv6hdr *iph = ipv6_hdr(skb);
		unsigned int i;

		memcpy(&addr.ip6, (info->flags & XT_CONNLIMIT_DADDR) ?
		       &iph->daddr : &iph->saddr, sizeof(addr.ip6));

		for (i = 0; i < ARRAY_SIZE(addr.ip6); ++i)
			addr.ip6[i] &= info->mask.ip6[i];
	} else {
		const struct iphdr *iph = ip_hdr(skb);
		addr.ip = (info->flags & XT_CONNLIMIT_DADDR) ?
			  iph->daddr : iph->saddr;

		addr.ip &= info->mask.ip;
	}

	connections = count_them(net, info->data, tuple_ptr, &addr,
				 xt_family(par), zone);
	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;

	net_get_random_once(&connlimit_rnd, sizeof(connlimit_rnd));

	ret = nf_ct_netns_get(par->net, 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_netns_put(par->net, par->family);
		return -ENOMEM;
	}

	for (i = 0; i < ARRAY_SIZE(info->data->climit_root); ++i)
		info->data->climit_root[i] = RB_ROOT;

	return 0;
}

static void destroy_tree(struct rb_root *r)
{
	struct xt_connlimit_conn *conn;
	struct xt_connlimit_rb *rbconn;
	struct hlist_node *n;
	struct rb_node *node;

	while ((node = rb_first(r)) != NULL) {
		rbconn = rb_entry(node, struct xt_connlimit_rb, node);

		rb_erase(node, r);

		hlist_for_each_entry_safe(conn, n, &rbconn->hhead, node)
			kmem_cache_free(connlimit_conn_cachep, conn);

		kmem_cache_free(connlimit_rb_cachep, rbconn);
	}
}

static void connlimit_mt_destroy(const struct xt_mtdtor_param *par)
{
	const struct xt_connlimit_info *info = par->matchinfo;
	unsigned int i;

	nf_ct_netns_put(par->net, par->family);

	for (i = 0; i < ARRAY_SIZE(info->data->climit_root); ++i)
		destroy_tree(&info->data->climit_root[i]);

	kfree(info->data);
}

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

static int __init connlimit_mt_init(void)
{
	int ret, i;

	BUILD_BUG_ON(CONNLIMIT_LOCK_SLOTS > CONNLIMIT_SLOTS);
	BUILD_BUG_ON((CONNLIMIT_SLOTS % CONNLIMIT_LOCK_SLOTS) != 0);

	for (i = 0; i < CONNLIMIT_LOCK_SLOTS; ++i)
		spin_lock_init(&xt_connlimit_locks[i]);

	connlimit_conn_cachep = kmem_cache_create("xt_connlimit_conn",
					   sizeof(struct xt_connlimit_conn),
					   0, 0, NULL);
	if (!connlimit_conn_cachep)
		return -ENOMEM;

	connlimit_rb_cachep = kmem_cache_create("xt_connlimit_rb",
					   sizeof(struct xt_connlimit_rb),
					   0, 0, NULL);
	if (!connlimit_rb_cachep) {
		kmem_cache_destroy(connlimit_conn_cachep);
		return -ENOMEM;
	}
	ret = xt_register_match(&connlimit_mt_reg);
	if (ret != 0) {
		kmem_cache_destroy(connlimit_conn_cachep);
		kmem_cache_destroy(connlimit_rb_cachep);
	}
	return ret;
}

static void __exit connlimit_mt_exit(void)
{
	xt_unregister_match(&connlimit_mt_reg);
	kmem_cache_destroy(connlimit_conn_cachep);
	kmem_cache_destroy(connlimit_rb_cachep);
}

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");