aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4/ipmr_base.c
blob: 3e614cc824f77948493a7867009591b3b09a0179 (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
/* Linux multicast routing support
 * Common logic shared by IPv4 [ipmr] and IPv6 [ip6mr] implementation
 */

#include <linux/rhashtable.h>
#include <linux/mroute_base.h>

/* Sets everything common except 'dev', since that is done under locking */
void vif_device_init(struct vif_device *v,
		     struct net_device *dev,
		     unsigned long rate_limit,
		     unsigned char threshold,
		     unsigned short flags,
		     unsigned short get_iflink_mask)
{
	v->dev = NULL;
	v->bytes_in = 0;
	v->bytes_out = 0;
	v->pkt_in = 0;
	v->pkt_out = 0;
	v->rate_limit = rate_limit;
	v->flags = flags;
	v->threshold = threshold;
	if (v->flags & get_iflink_mask)
		v->link = dev_get_iflink(dev);
	else
		v->link = dev->ifindex;
}
EXPORT_SYMBOL(vif_device_init);

struct mr_table *
mr_table_alloc(struct net *net, u32 id,
	       struct mr_table_ops *ops,
	       void (*expire_func)(struct timer_list *t),
	       void (*table_set)(struct mr_table *mrt,
				 struct net *net))
{
	struct mr_table *mrt;
	int err;

	mrt = kzalloc(sizeof(*mrt), GFP_KERNEL);
	if (!mrt)
		return ERR_PTR(-ENOMEM);
	mrt->id = id;
	write_pnet(&mrt->net, net);

	mrt->ops = *ops;
	err = rhltable_init(&mrt->mfc_hash, mrt->ops.rht_params);
	if (err) {
		kfree(mrt);
		return ERR_PTR(err);
	}
	INIT_LIST_HEAD(&mrt->mfc_cache_list);
	INIT_LIST_HEAD(&mrt->mfc_unres_queue);

	timer_setup(&mrt->ipmr_expire_timer, expire_func, 0);

	mrt->mroute_reg_vif_num = -1;
	table_set(mrt, net);
	return mrt;
}
EXPORT_SYMBOL(mr_table_alloc);

void *mr_mfc_find_parent(struct mr_table *mrt, void *hasharg, int parent)
{
	struct rhlist_head *tmp, *list;
	struct mr_mfc *c;

	list = rhltable_lookup(&mrt->mfc_hash, hasharg, *mrt->ops.rht_params);
	rhl_for_each_entry_rcu(c, tmp, list, mnode)
		if (parent == -1 || parent == c->mfc_parent)
			return c;

	return NULL;
}
EXPORT_SYMBOL(mr_mfc_find_parent);

void *mr_mfc_find_any_parent(struct mr_table *mrt, int vifi)
{
	struct rhlist_head *tmp, *list;
	struct mr_mfc *c;

	list = rhltable_lookup(&mrt->mfc_hash, mrt->ops.cmparg_any,
			       *mrt->ops.rht_params);
	rhl_for_each_entry_rcu(c, tmp, list, mnode)
		if (c->mfc_un.res.ttls[vifi] < 255)
			return c;

	return NULL;
}
EXPORT_SYMBOL(mr_mfc_find_any_parent);

void *mr_mfc_find_any(struct mr_table *mrt, int vifi, void *hasharg)
{
	struct rhlist_head *tmp, *list;
	struct mr_mfc *c, *proxy;

	list = rhltable_lookup(&mrt->mfc_hash, hasharg, *mrt->ops.rht_params);
	rhl_for_each_entry_rcu(c, tmp, list, mnode) {
		if (c->mfc_un.res.ttls[vifi] < 255)
			return c;

		/* It's ok if the vifi is part of the static tree */
		proxy = mr_mfc_find_any_parent(mrt, c->mfc_parent);
		if (proxy && proxy->mfc_un.res.ttls[vifi] < 255)
			return c;
	}

	return mr_mfc_find_any_parent(mrt, vifi);
}
EXPORT_SYMBOL(mr_mfc_find_any);

#ifdef CONFIG_PROC_FS
void *mr_vif_seq_idx(struct net *net, struct mr_vif_iter *iter, loff_t pos)
{
	struct mr_table *mrt = iter->mrt;

	for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) {
		if (!VIF_EXISTS(mrt, iter->ct))
			continue;
		if (pos-- == 0)
			return &mrt->vif_table[iter->ct];
	}
	return NULL;
}
EXPORT_SYMBOL(mr_vif_seq_idx);

void *mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct mr_vif_iter *iter = seq->private;
	struct net *net = seq_file_net(seq);
	struct mr_table *mrt = iter->mrt;

	++*pos;
	if (v == SEQ_START_TOKEN)
		return mr_vif_seq_idx(net, iter, 0);

	while (++iter->ct < mrt->maxvif) {
		if (!VIF_EXISTS(mrt, iter->ct))
			continue;
		return &mrt->vif_table[iter->ct];
	}
	return NULL;
}
EXPORT_SYMBOL(mr_vif_seq_next);

void *mr_mfc_seq_idx(struct net *net,
		     struct mr_mfc_iter *it, loff_t pos)
{
	struct mr_table *mrt = it->mrt;
	struct mr_mfc *mfc;

	rcu_read_lock();
	it->cache = &mrt->mfc_cache_list;
	list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list)
		if (pos-- == 0)
			return mfc;
	rcu_read_unlock();

	spin_lock_bh(it->lock);
	it->cache = &mrt->mfc_unres_queue;
	list_for_each_entry(mfc, it->cache, list)
		if (pos-- == 0)
			return mfc;
	spin_unlock_bh(it->lock);

	it->cache = NULL;
	return NULL;
}
EXPORT_SYMBOL(mr_mfc_seq_idx);

void *mr_mfc_seq_next(struct seq_file *seq, void *v,
		      loff_t *pos)
{
	struct mr_mfc_iter *it = seq->private;
	struct net *net = seq_file_net(seq);
	struct mr_table *mrt = it->mrt;
	struct mr_mfc *c = v;

	++*pos;

	if (v == SEQ_START_TOKEN)
		return mr_mfc_seq_idx(net, seq->private, 0);

	if (c->list.next != it->cache)
		return list_entry(c->list.next, struct mr_mfc, list);

	if (it->cache == &mrt->mfc_unres_queue)
		goto end_of_list;

	/* exhausted cache_array, show unresolved */
	rcu_read_unlock();
	it->cache = &mrt->mfc_unres_queue;

	spin_lock_bh(it->lock);
	if (!list_empty(it->cache))
		return list_first_entry(it->cache, struct mr_mfc, list);

end_of_list:
	spin_unlock_bh(it->lock);
	it->cache = NULL;

	return NULL;
}
EXPORT_SYMBOL(mr_mfc_seq_next);
#endif

int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
		   struct mr_mfc *c, struct rtmsg *rtm)
{
	struct rta_mfc_stats mfcs;
	struct nlattr *mp_attr;
	struct rtnexthop *nhp;
	unsigned long lastuse;
	int ct;

	/* If cache is unresolved, don't try to parse IIF and OIF */
	if (c->mfc_parent >= MAXVIFS) {
		rtm->rtm_flags |= RTNH_F_UNRESOLVED;
		return -ENOENT;
	}

	if (VIF_EXISTS(mrt, c->mfc_parent) &&
	    nla_put_u32(skb, RTA_IIF,
			mrt->vif_table[c->mfc_parent].dev->ifindex) < 0)
		return -EMSGSIZE;

	if (c->mfc_flags & MFC_OFFLOAD)
		rtm->rtm_flags |= RTNH_F_OFFLOAD;

	mp_attr = nla_nest_start(skb, RTA_MULTIPATH);
	if (!mp_attr)
		return -EMSGSIZE;

	for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) {
		if (VIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) {
			struct vif_device *vif;

			nhp = nla_reserve_nohdr(skb, sizeof(*nhp));
			if (!nhp) {
				nla_nest_cancel(skb, mp_attr);
				return -EMSGSIZE;
			}

			nhp->rtnh_flags = 0;
			nhp->rtnh_hops = c->mfc_un.res.ttls[ct];
			vif = &mrt->vif_table[ct];
			nhp->rtnh_ifindex = vif->dev->ifindex;
			nhp->rtnh_len = sizeof(*nhp);
		}
	}

	nla_nest_end(skb, mp_attr);

	lastuse = READ_ONCE(c->mfc_un.res.lastuse);
	lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0;

	mfcs.mfcs_packets = c->mfc_un.res.pkt;
	mfcs.mfcs_bytes = c->mfc_un.res.bytes;
	mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if;
	if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) ||
	    nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse),
			      RTA_PAD))
		return -EMSGSIZE;

	rtm->rtm_type = RTN_MULTICAST;
	return 1;
}
EXPORT_SYMBOL(mr_fill_mroute);

static bool mr_mfc_uses_dev(const struct mr_table *mrt,
			    const struct mr_mfc *c,
			    const struct net_device *dev)
{
	int ct;

	for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) {
		if (VIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) {
			const struct vif_device *vif;

			vif = &mrt->vif_table[ct];
			if (vif->dev == dev)
				return true;
		}
	}
	return false;
}

int mr_table_dump(struct mr_table *mrt, struct sk_buff *skb,
		  struct netlink_callback *cb,
		  int (*fill)(struct mr_table *mrt, struct sk_buff *skb,
			      u32 portid, u32 seq, struct mr_mfc *c,
			      int cmd, int flags),
		  spinlock_t *lock, struct fib_dump_filter *filter)
{
	unsigned int e = 0, s_e = cb->args[1];
	unsigned int flags = NLM_F_MULTI;
	struct mr_mfc *mfc;
	int err;

	if (filter->filter_set)
		flags |= NLM_F_DUMP_FILTERED;

	list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) {
		if (e < s_e)
			goto next_entry;
		if (filter->dev &&
		    !mr_mfc_uses_dev(mrt, mfc, filter->dev))
			goto next_entry;

		err = fill(mrt, skb, NETLINK_CB(cb->skb).portid,
			   cb->nlh->nlmsg_seq, mfc, RTM_NEWROUTE, flags);
		if (err < 0)
			goto out;
next_entry:
		e++;
	}

	spin_lock_bh(lock);
	list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) {
		if (e < s_e)
			goto next_entry2;
		if (filter->dev &&
		    !mr_mfc_uses_dev(mrt, mfc, filter->dev))
			goto next_entry2;

		err = fill(mrt, skb, NETLINK_CB(cb->skb).portid,
			   cb->nlh->nlmsg_seq, mfc, RTM_NEWROUTE, flags);
		if (err < 0) {
			spin_unlock_bh(lock);
			goto out;
		}
next_entry2:
		e++;
	}
	spin_unlock_bh(lock);
	err = 0;
	e = 0;

out:
	cb->args[1] = e;
	return err;
}
EXPORT_SYMBOL(mr_table_dump);

int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb,
		     struct mr_table *(*iter)(struct net *net,
					      struct mr_table *mrt),
		     int (*fill)(struct mr_table *mrt,
				 struct sk_buff *skb,
				 u32 portid, u32 seq, struct mr_mfc *c,
				 int cmd, int flags),
		     spinlock_t *lock, struct fib_dump_filter *filter)
{
	unsigned int t = 0, s_t = cb->args[0];
	struct net *net = sock_net(skb->sk);
	struct mr_table *mrt;
	int err;

	/* multicast does not track protocol or have route type other
	 * than RTN_MULTICAST
	 */
	if (filter->filter_set) {
		if (filter->protocol || filter->flags ||
		    (filter->rt_type && filter->rt_type != RTN_MULTICAST))
			return skb->len;
	}

	rcu_read_lock();
	for (mrt = iter(net, NULL); mrt; mrt = iter(net, mrt)) {
		if (t < s_t)
			goto next_table;

		err = mr_table_dump(mrt, skb, cb, fill, lock, filter);
		if (err < 0)
			break;
next_table:
		t++;
	}
	rcu_read_unlock();

	cb->args[0] = t;

	return skb->len;
}
EXPORT_SYMBOL(mr_rtm_dumproute);

int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family,
	    int (*rules_dump)(struct net *net,
			      struct notifier_block *nb),
	    struct mr_table *(*mr_iter)(struct net *net,
					struct mr_table *mrt),
	    rwlock_t *mrt_lock)
{
	struct mr_table *mrt;
	int err;

	err = rules_dump(net, nb);
	if (err)
		return err;

	for (mrt = mr_iter(net, NULL); mrt; mrt = mr_iter(net, mrt)) {
		struct vif_device *v = &mrt->vif_table[0];
		struct mr_mfc *mfc;
		int vifi;

		/* Notifiy on table VIF entries */
		read_lock(mrt_lock);
		for (vifi = 0; vifi < mrt->maxvif; vifi++, v++) {
			if (!v->dev)
				continue;

			mr_call_vif_notifier(nb, net, family,
					     FIB_EVENT_VIF_ADD,
					     v, vifi, mrt->id);
		}
		read_unlock(mrt_lock);

		/* Notify on table MFC entries */
		list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list)
			mr_call_mfc_notifier(nb, net, family,
					     FIB_EVENT_ENTRY_ADD,
					     mfc, mrt->id);
	}

	return 0;
}
EXPORT_SYMBOL(mr_dump);