summaryrefslogtreecommitdiff
path: root/net/netfilter/nf_conncount.c
blob: 510039862aa93c99904d2dbd3a7969327d0d896a (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
/*
 * count the number of connections matching an arbitrary key.
 *
 * (C) 2017 Red Hat GmbH
 * Author: Florian Westphal <fw@strlen.de>
 *
 * split from xt_connlimit.c:
 *   (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
 */
#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 <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_count.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_tuple.h>
#include <net/netfilter/nf_conntrack_zones.h>

#define CONNCOUNT_SLOTS		256U

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

#define CONNCOUNT_GC_MAX_NODES	8
#define MAX_KEYLEN		5

/* we will save the tuples of all connections we care about */
struct nf_conncount_tuple {
	struct hlist_node		node;
	struct nf_conntrack_tuple	tuple;
	struct nf_conntrack_zone	zone;
	int				cpu;
	u32				jiffies32;
};

struct nf_conncount_rb {
	struct rb_node node;
	struct hlist_head hhead; /* connections/hosts in same subnet */
	u32 key[MAX_KEYLEN];
};

static spinlock_t nf_conncount_locks[CONNCOUNT_LOCK_SLOTS] __cacheline_aligned_in_smp;

struct nf_conncount_data {
	unsigned int keylen;
	struct rb_root root[CONNCOUNT_SLOTS];
};

static u_int32_t conncount_rnd __read_mostly;
static struct kmem_cache *conncount_rb_cachep __read_mostly;
static struct kmem_cache *conncount_conn_cachep __read_mostly;

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 false;
}

static int key_diff(const u32 *a, const u32 *b, unsigned int klen)
{
	return memcmp(a, b, klen * sizeof(u32));
}

bool nf_conncount_add(struct hlist_head *head,
		      const struct nf_conntrack_tuple *tuple,
		      const struct nf_conntrack_zone *zone)
{
	struct nf_conncount_tuple *conn;

	conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC);
	if (conn == NULL)
		return false;
	conn->tuple = *tuple;
	conn->zone = *zone;
	conn->cpu = raw_smp_processor_id();
	conn->jiffies32 = (u32)jiffies;
	hlist_add_head(&conn->node, head);
	return true;
}
EXPORT_SYMBOL_GPL(nf_conncount_add);

static const struct nf_conntrack_tuple_hash *
find_or_evict(struct net *net, struct nf_conncount_tuple *conn)
{
	const struct nf_conntrack_tuple_hash *found;
	unsigned long a, b;
	int cpu = raw_smp_processor_id();
	__s32 age;

	found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple);
	if (found)
		return found;
	b = conn->jiffies32;
	a = (u32)jiffies;

	/* conn might have been added just before by another cpu and
	 * might still be unconfirmed.  In this case, nf_conntrack_find()
	 * returns no result.  Thus only evict if this cpu added the
	 * stale entry or if the entry is older than two jiffies.
	 */
	age = a - b;
	if (conn->cpu == cpu || age >= 2) {
		hlist_del(&conn->node);
		kmem_cache_free(conncount_conn_cachep, conn);
		return ERR_PTR(-ENOENT);
	}

	return ERR_PTR(-EAGAIN);
}

unsigned int nf_conncount_lookup(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 nf_conncount_tuple *conn;
	struct nf_conn *found_ct;
	struct hlist_node *n;
	unsigned int length = 0;

	*addit = tuple ? true : false;

	/* check the saved connections */
	hlist_for_each_entry_safe(conn, n, head, node) {
		found = find_or_evict(net, conn);
		if (IS_ERR(found)) {
			/* Not found, but might be about to be confirmed */
			if (PTR_ERR(found) == -EAGAIN) {
				length++;
				if (!tuple)
					continue;

				if (nf_ct_tuple_equal(&conn->tuple, tuple) &&
				    nf_ct_zone_id(&conn->zone, conn->zone.dir) ==
				    nf_ct_zone_id(zone, zone->dir))
					*addit = false;
			}
			continue;
		}

		found_ct = nf_ct_tuplehash_to_ctrack(found);

		if (tuple && nf_ct_tuple_equal(&conn->tuple, tuple) &&
		    nf_ct_zone_equal(found_ct, zone, zone->dir)) {
			/*
			 * 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(conncount_conn_cachep, conn);
			continue;
		}

		nf_ct_put(found_ct);
		length++;
	}

	return length;
}
EXPORT_SYMBOL_GPL(nf_conncount_lookup);

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

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

static unsigned int
count_tree(struct net *net, struct rb_root *root,
	   const u32 *key, u8 keylen,
	   const struct nf_conntrack_tuple *tuple,
	   const struct nf_conntrack_zone *zone)
{
	struct nf_conncount_rb *gc_nodes[CONNCOUNT_GC_MAX_NODES];
	struct rb_node **rbnode, *parent;
	struct nf_conncount_rb *rbconn;
	struct nf_conncount_tuple *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 nf_conncount_rb, node);

		parent = *rbnode;
		diff = key_diff(key, rbconn->key, keylen);
		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 = nf_conncount_lookup(net, &rbconn->hhead, tuple,
						    zone, &addit);

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

			if (!nf_conncount_add(&rbconn->hhead, tuple, zone))
				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 */
		nf_conncount_lookup(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;
	}

	if (!tuple)
		return 0;

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

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

	conn->tuple = *tuple;
	conn->zone = *zone;
	memcpy(rbconn->key, key, sizeof(u32) * keylen);

	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;
}

/* Count and return number of conntrack entries in 'net' with particular 'key'.
 * If 'tuple' is not null, insert it into the accounting data structure.
 */
unsigned int nf_conncount_count(struct net *net,
				struct nf_conncount_data *data,
				const u32 *key,
				const struct nf_conntrack_tuple *tuple,
				const struct nf_conntrack_zone *zone)
{
	struct rb_root *root;
	int count;
	u32 hash;

	hash = jhash2(key, data->keylen, conncount_rnd) % CONNCOUNT_SLOTS;
	root = &data->root[hash];

	spin_lock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);

	count = count_tree(net, root, key, data->keylen, tuple, zone);

	spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);

	return count;
}
EXPORT_SYMBOL_GPL(nf_conncount_count);

struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family,
					    unsigned int keylen)
{
	struct nf_conncount_data *data;
	int ret, i;

	if (keylen % sizeof(u32) ||
	    keylen / sizeof(u32) > MAX_KEYLEN ||
	    keylen == 0)
		return ERR_PTR(-EINVAL);

	net_get_random_once(&conncount_rnd, sizeof(conncount_rnd));

	data = kmalloc(sizeof(*data), GFP_KERNEL);
	if (!data)
		return ERR_PTR(-ENOMEM);

	ret = nf_ct_netns_get(net, family);
	if (ret < 0) {
		kfree(data);
		return ERR_PTR(ret);
	}

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

	data->keylen = keylen / sizeof(u32);

	return data;
}
EXPORT_SYMBOL_GPL(nf_conncount_init);

void nf_conncount_cache_free(struct hlist_head *hhead)
{
	struct nf_conncount_tuple *conn;
	struct hlist_node *n;

	hlist_for_each_entry_safe(conn, n, hhead, node)
		kmem_cache_free(conncount_conn_cachep, conn);
}
EXPORT_SYMBOL_GPL(nf_conncount_cache_free);

static void destroy_tree(struct rb_root *r)
{
	struct nf_conncount_rb *rbconn;
	struct rb_node *node;

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

		rb_erase(node, r);

		nf_conncount_cache_free(&rbconn->hhead);

		kmem_cache_free(conncount_rb_cachep, rbconn);
	}
}

void nf_conncount_destroy(struct net *net, unsigned int family,
			  struct nf_conncount_data *data)
{
	unsigned int i;

	nf_ct_netns_put(net, family);

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

	kfree(data);
}
EXPORT_SYMBOL_GPL(nf_conncount_destroy);

static int __init nf_conncount_modinit(void)
{
	int i;

	BUILD_BUG_ON(CONNCOUNT_LOCK_SLOTS > CONNCOUNT_SLOTS);
	BUILD_BUG_ON((CONNCOUNT_SLOTS % CONNCOUNT_LOCK_SLOTS) != 0);

	for (i = 0; i < CONNCOUNT_LOCK_SLOTS; ++i)
		spin_lock_init(&nf_conncount_locks[i]);

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

	conncount_rb_cachep = kmem_cache_create("nf_conncount_rb",
					   sizeof(struct nf_conncount_rb),
					   0, 0, NULL);
	if (!conncount_rb_cachep) {
		kmem_cache_destroy(conncount_conn_cachep);
		return -ENOMEM;
	}

	return 0;
}

static void __exit nf_conncount_modexit(void)
{
	kmem_cache_destroy(conncount_conn_cachep);
	kmem_cache_destroy(conncount_rb_cachep);
}

module_init(nf_conncount_modinit);
module_exit(nf_conncount_modexit);
MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>");
MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
MODULE_DESCRIPTION("netfilter: count number of connections matching a key");
MODULE_LICENSE("GPL");