aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4/fib_rules.c
blob: 768e8f5d7daa37e95863195d0418d0d77e6e0684 (plain) (blame)
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
459
460
461
462
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		IPv4 Forwarding Information Base: policy rules.
 *
 * Version:	$Id: fib_rules.c,v 1.17 2001/10/31 21:55:54 davem Exp $
 *
 * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
 *
 *		This program is free software; you can redistribute it and/or
 *		modify it under the terms of the GNU General Public License
 *		as published by the Free Software Foundation; either version
 *		2 of the License, or (at your option) any later version.
 *
 * Fixes:
 * 		Rani Assaf	:	local_rule cannot be deleted
 *		Marc Boucher	:	routing by fwmark
 */

#include <linux/config.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <linux/bitops.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/errno.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/inetdevice.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/proc_fs.h>
#include <linux/skbuff.h>
#include <linux/netlink.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/rcupdate.h>

#include <net/ip.h>
#include <net/protocol.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/sock.h>
#include <net/ip_fib.h>

#define FRprintk(a...)

struct fib_rule
{
	struct hlist_node hlist;
	atomic_t	r_clntref;
	u32		r_preference;
	unsigned char	r_table;
	unsigned char	r_action;
	unsigned char	r_dst_len;
	unsigned char	r_src_len;
	u32		r_src;
	u32		r_srcmask;
	u32		r_dst;
	u32		r_dstmask;
	u32		r_srcmap;
	u8		r_flags;
	u8		r_tos;
#ifdef CONFIG_IP_ROUTE_FWMARK
	u32		r_fwmark;
#endif
	int		r_ifindex;
#ifdef CONFIG_NET_CLS_ROUTE
	__u32		r_tclassid;
#endif
	char		r_ifname[IFNAMSIZ];
	int		r_dead;
	struct		rcu_head rcu;
};

static struct fib_rule default_rule = {
	.r_clntref =	ATOMIC_INIT(2),
	.r_preference =	0x7FFF,
	.r_table =	RT_TABLE_DEFAULT,
	.r_action =	RTN_UNICAST,
};

static struct fib_rule main_rule = {
	.r_clntref =	ATOMIC_INIT(2),
	.r_preference =	0x7FFE,
	.r_table =	RT_TABLE_MAIN,
	.r_action =	RTN_UNICAST,
};

static struct fib_rule local_rule = {
	.r_clntref =	ATOMIC_INIT(2),
	.r_table =	RT_TABLE_LOCAL,
	.r_action =	RTN_UNICAST,
};

static struct hlist_head fib_rules;

/* writer func called from netlink -- rtnl_sem hold*/

int inet_rtm_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
	struct rtattr **rta = arg;
	struct rtmsg *rtm = NLMSG_DATA(nlh);
	struct fib_rule *r;
	struct hlist_node *node;
	int err = -ESRCH;

	hlist_for_each_entry(r, node, &fib_rules, hlist) {
		if ((!rta[RTA_SRC-1] || memcmp(RTA_DATA(rta[RTA_SRC-1]), &r->r_src, 4) == 0) &&
		    rtm->rtm_src_len == r->r_src_len &&
		    rtm->rtm_dst_len == r->r_dst_len &&
		    (!rta[RTA_DST-1] || memcmp(RTA_DATA(rta[RTA_DST-1]), &r->r_dst, 4) == 0) &&
		    rtm->rtm_tos == r->r_tos &&
#ifdef CONFIG_IP_ROUTE_FWMARK
		    (!rta[RTA_PROTOINFO-1] || memcmp(RTA_DATA(rta[RTA_PROTOINFO-1]), &r->r_fwmark, 4) == 0) &&
#endif
		    (!rtm->rtm_type || rtm->rtm_type == r->r_action) &&
		    (!rta[RTA_PRIORITY-1] || memcmp(RTA_DATA(rta[RTA_PRIORITY-1]), &r->r_preference, 4) == 0) &&
		    (!rta[RTA_IIF-1] || rtattr_strcmp(rta[RTA_IIF-1], r->r_ifname) == 0) &&
		    (!rtm->rtm_table || (r && rtm->rtm_table == r->r_table))) {
			err = -EPERM;
			if (r == &local_rule)
				break;

			hlist_del_rcu(&r->hlist);
			r->r_dead = 1;
			fib_rule_put(r);
			err = 0;
			break;
		}
	}
	return err;
}

/* Allocate new unique table id */

static struct fib_table *fib_empty_table(void)
{
	int id;

	for (id = 1; id <= RT_TABLE_MAX; id++)
		if (fib_tables[id] == NULL)
			return __fib_new_table(id);
	return NULL;
}

static inline void fib_rule_put_rcu(struct rcu_head *head)
{
	struct fib_rule *r = container_of(head, struct fib_rule, rcu);
	kfree(r);
}

void fib_rule_put(struct fib_rule *r)
{
	if (atomic_dec_and_test(&r->r_clntref)) {
		if (r->r_dead)
			call_rcu(&r->rcu, fib_rule_put_rcu);
		else
			printk("Freeing alive rule %p\n", r);
	}
}

/* writer func called from netlink -- rtnl_sem hold*/

int inet_rtm_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
	struct rtattr **rta = arg;
	struct rtmsg *rtm = NLMSG_DATA(nlh);
	struct fib_rule *r, *new_r, *last = NULL;
	struct hlist_node *node = NULL;
	unsigned char table_id;

	if (rtm->rtm_src_len > 32 || rtm->rtm_dst_len > 32 ||
	    (rtm->rtm_tos & ~IPTOS_TOS_MASK))
		return -EINVAL;

	if (rta[RTA_IIF-1] && RTA_PAYLOAD(rta[RTA_IIF-1]) > IFNAMSIZ)
		return -EINVAL;

	table_id = rtm->rtm_table;
	if (table_id == RT_TABLE_UNSPEC) {
		struct fib_table *table;
		if (rtm->rtm_type == RTN_UNICAST) {
			if ((table = fib_empty_table()) == NULL)
				return -ENOBUFS;
			table_id = table->tb_id;
		}
	}

	new_r = kmalloc(sizeof(*new_r), GFP_KERNEL);
	if (!new_r)
		return -ENOMEM;
	memset(new_r, 0, sizeof(*new_r));

	if (rta[RTA_SRC-1])
		memcpy(&new_r->r_src, RTA_DATA(rta[RTA_SRC-1]), 4);
	if (rta[RTA_DST-1])
		memcpy(&new_r->r_dst, RTA_DATA(rta[RTA_DST-1]), 4);
	if (rta[RTA_GATEWAY-1])
		memcpy(&new_r->r_srcmap, RTA_DATA(rta[RTA_GATEWAY-1]), 4);
	new_r->r_src_len = rtm->rtm_src_len;
	new_r->r_dst_len = rtm->rtm_dst_len;
	new_r->r_srcmask = inet_make_mask(rtm->rtm_src_len);
	new_r->r_dstmask = inet_make_mask(rtm->rtm_dst_len);
	new_r->r_tos = rtm->rtm_tos;
#ifdef CONFIG_IP_ROUTE_FWMARK
	if (rta[RTA_PROTOINFO-1])
		memcpy(&new_r->r_fwmark, RTA_DATA(rta[RTA_PROTOINFO-1]), 4);
#endif
	new_r->r_action = rtm->rtm_type;
	new_r->r_flags = rtm->rtm_flags;
	if (rta[RTA_PRIORITY-1])
		memcpy(&new_r->r_preference, RTA_DATA(rta[RTA_PRIORITY-1]), 4);
	new_r->r_table = table_id;
	if (rta[RTA_IIF-1]) {
		struct net_device *dev;
		rtattr_strlcpy(new_r->r_ifname, rta[RTA_IIF-1], IFNAMSIZ);
		new_r->r_ifindex = -1;
		dev = __dev_get_by_name(new_r->r_ifname);
		if (dev)
			new_r->r_ifindex = dev->ifindex;
	}
#ifdef CONFIG_NET_CLS_ROUTE
	if (rta[RTA_FLOW-1])
		memcpy(&new_r->r_tclassid, RTA_DATA(rta[RTA_FLOW-1]), 4);
#endif
	r = container_of(fib_rules.first, struct fib_rule, hlist);

	if (!new_r->r_preference) {
		if (r && r->hlist.next != NULL) {
			r = container_of(r->hlist.next, struct fib_rule, hlist);
			if (r->r_preference)
				new_r->r_preference = r->r_preference - 1;
		}
	}

	hlist_for_each_entry(r, node, &fib_rules, hlist) {
		if (r->r_preference > new_r->r_preference)
			break;
		last = r;
	}
	atomic_inc(&new_r->r_clntref);

	if (last)
		hlist_add_after_rcu(&last->hlist, &new_r->hlist);
	else
		hlist_add_before_rcu(&new_r->hlist, &r->hlist);

	return 0;
}

#ifdef CONFIG_NET_CLS_ROUTE
u32 fib_rules_tclass(struct fib_result *res)
{
	if (res->r)
		return res->r->r_tclassid;
	return 0;
}
#endif

/* callers should hold rtnl semaphore */

static void fib_rules_detach(struct net_device *dev)
{
	struct hlist_node *node;
	struct fib_rule *r;

	hlist_for_each_entry(r, node, &fib_rules, hlist) {
		if (r->r_ifindex == dev->ifindex)
			r->r_ifindex = -1;

	}
}

/* callers should hold rtnl semaphore */

static void fib_rules_attach(struct net_device *dev)
{
	struct hlist_node *node;
	struct fib_rule *r;

	hlist_for_each_entry(r, node, &fib_rules, hlist) {
		if (r->r_ifindex == -1 && strcmp(dev->name, r->r_ifname) == 0)
			r->r_ifindex = dev->ifindex;
	}
}

int fib_lookup(const struct flowi *flp, struct fib_result *res)
{
	int err;
	struct fib_rule *r, *policy;
	struct fib_table *tb;
	struct hlist_node *node;

	u32 daddr = flp->fl4_dst;
	u32 saddr = flp->fl4_src;

FRprintk("Lookup: %u.%u.%u.%u <- %u.%u.%u.%u ",
	NIPQUAD(flp->fl4_dst), NIPQUAD(flp->fl4_src));

	rcu_read_lock();

	hlist_for_each_entry_rcu(r, node, &fib_rules, hlist) {
		if (((saddr^r->r_src) & r->r_srcmask) ||
		    ((daddr^r->r_dst) & r->r_dstmask) ||
		    (r->r_tos && r->r_tos != flp->fl4_tos) ||
#ifdef CONFIG_IP_ROUTE_FWMARK
		    (r->r_fwmark && r->r_fwmark != flp->fl4_fwmark) ||
#endif
		    (r->r_ifindex && r->r_ifindex != flp->iif))
			continue;

FRprintk("tb %d r %d ", r->r_table, r->r_action);
		switch (r->r_action) {
		case RTN_UNICAST:
			policy = r;
			break;
		case RTN_UNREACHABLE:
			rcu_read_unlock();
			return -ENETUNREACH;
		default:
		case RTN_BLACKHOLE:
			rcu_read_unlock();
			return -EINVAL;
		case RTN_PROHIBIT:
			rcu_read_unlock();
			return -EACCES;
		}

		if ((tb = fib_get_table(r->r_table)) == NULL)
			continue;
		err = tb->tb_lookup(tb, flp, res);
		if (err == 0) {
			res->r = policy;
			if (policy)
				atomic_inc(&policy->r_clntref);
			rcu_read_unlock();
			return 0;
		}
		if (err < 0 && err != -EAGAIN) {
			rcu_read_unlock();
			return err;
		}
	}
FRprintk("FAILURE\n");
	rcu_read_unlock();
	return -ENETUNREACH;
}

void fib_select_default(const struct flowi *flp, struct fib_result *res)
{
	if (res->r && res->r->r_action == RTN_UNICAST &&
	    FIB_RES_GW(*res) && FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) {
		struct fib_table *tb;
		if ((tb = fib_get_table(res->r->r_table)) != NULL)
			tb->tb_select_default(tb, flp, res);
	}
}

static int fib_rules_event(struct notifier_block *this, unsigned long event, void *ptr)
{
	struct net_device *dev = ptr;

	if (event == NETDEV_UNREGISTER)
		fib_rules_detach(dev);
	else if (event == NETDEV_REGISTER)
		fib_rules_attach(dev);
	return NOTIFY_DONE;
}


static struct notifier_block fib_rules_notifier = {
	.notifier_call =fib_rules_event,
};

static __inline__ int inet_fill_rule(struct sk_buff *skb,
				     struct fib_rule *r,
				     struct netlink_callback *cb,
				     unsigned int flags)
{
	struct rtmsg *rtm;
	struct nlmsghdr  *nlh;
	unsigned char	 *b = skb->tail;

	nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWRULE, sizeof(*rtm), flags);
	rtm = NLMSG_DATA(nlh);
	rtm->rtm_family = AF_INET;
	rtm->rtm_dst_len = r->r_dst_len;
	rtm->rtm_src_len = r->r_src_len;
	rtm->rtm_tos = r->r_tos;
#ifdef CONFIG_IP_ROUTE_FWMARK
	if (r->r_fwmark)
		RTA_PUT(skb, RTA_PROTOINFO, 4, &r->r_fwmark);
#endif
	rtm->rtm_table = r->r_table;
	rtm->rtm_protocol = 0;
	rtm->rtm_scope = 0;
	rtm->rtm_type = r->r_action;
	rtm->rtm_flags = r->r_flags;

	if (r->r_dst_len)
		RTA_PUT(skb, RTA_DST, 4, &r->r_dst);
	if (r->r_src_len)
		RTA_PUT(skb, RTA_SRC, 4, &r->r_src);
	if (r->r_ifname[0])
		RTA_PUT(skb, RTA_IIF, IFNAMSIZ, &r->r_ifname);
	if (r->r_preference)
		RTA_PUT(skb, RTA_PRIORITY, 4, &r->r_preference);
	if (r->r_srcmap)
		RTA_PUT(skb, RTA_GATEWAY, 4, &r->r_srcmap);
#ifdef CONFIG_NET_CLS_ROUTE
	if (r->r_tclassid)
		RTA_PUT(skb, RTA_FLOW, 4, &r->r_tclassid);
#endif
	nlh->nlmsg_len = skb->tail - b;
	return skb->len;

nlmsg_failure:
rtattr_failure:
	skb_trim(skb, b - skb->data);
	return -1;
}

/* callers should hold rtnl semaphore */

int inet_dump_rules(struct sk_buff *skb, struct netlink_callback *cb)
{
	int idx = 0;
	int s_idx = cb->args[0];
	struct fib_rule *r;
	struct hlist_node *node;

	rcu_read_lock();
	hlist_for_each_entry(r, node, &fib_rules, hlist) {

		if (idx < s_idx)
			continue;
		if (inet_fill_rule(skb, r, cb, NLM_F_MULTI) < 0)
			break;
		idx++;
	}
	rcu_read_unlock();
	cb->args[0] = idx;

	return skb->len;
}

void __init fib_rules_init(void)
{
	INIT_HLIST_HEAD(&fib_rules);
	hlist_add_head(&local_rule.hlist, &fib_rules);
	hlist_add_after(&local_rule.hlist, &main_rule.hlist);
	hlist_add_after(&main_rule.hlist, &default_rule.hlist);
	register_netdevice_notifier(&fib_rules_notifier);
}