summaryrefslogtreecommitdiffstats
path: root/net/mctp/device.c
blob: 3827d62f52c9bf92472541c17aed6c4072c3f30e (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Management Component Transport Protocol (MCTP) - device implementation.
 *
 * Copyright (c) 2021 Code Construct
 * Copyright (c) 2021 Google
 */

#include <linux/if_link.h>
#include <linux/mctp.h>
#include <linux/netdevice.h>
#include <linux/rcupdate.h>
#include <linux/rtnetlink.h>

#include <net/addrconf.h>
#include <net/netlink.h>
#include <net/mctp.h>
#include <net/mctpdevice.h>
#include <net/sock.h>

struct mctp_dump_cb {
	int h;
	int idx;
	size_t a_idx;
};

/* unlocked: caller must hold rcu_read_lock */
struct mctp_dev *__mctp_dev_get(const struct net_device *dev)
{
	return rcu_dereference(dev->mctp_ptr);
}

struct mctp_dev *mctp_dev_get_rtnl(const struct net_device *dev)
{
	return rtnl_dereference(dev->mctp_ptr);
}

static int mctp_fill_addrinfo(struct sk_buff *skb, struct netlink_callback *cb,
			      struct mctp_dev *mdev, mctp_eid_t eid)
{
	struct ifaddrmsg *hdr;
	struct nlmsghdr *nlh;

	nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
			RTM_NEWADDR, sizeof(*hdr), NLM_F_MULTI);
	if (!nlh)
		return -EMSGSIZE;

	hdr = nlmsg_data(nlh);
	hdr->ifa_family = AF_MCTP;
	hdr->ifa_prefixlen = 0;
	hdr->ifa_flags = 0;
	hdr->ifa_scope = 0;
	hdr->ifa_index = mdev->dev->ifindex;

	if (nla_put_u8(skb, IFA_LOCAL, eid))
		goto cancel;

	if (nla_put_u8(skb, IFA_ADDRESS, eid))
		goto cancel;

	nlmsg_end(skb, nlh);

	return 0;

cancel:
	nlmsg_cancel(skb, nlh);
	return -EMSGSIZE;
}

static int mctp_dump_dev_addrinfo(struct mctp_dev *mdev, struct sk_buff *skb,
				  struct netlink_callback *cb)
{
	struct mctp_dump_cb *mcb = (void *)cb->ctx;
	int rc = 0;

	for (; mcb->a_idx < mdev->num_addrs; mcb->a_idx++) {
		rc = mctp_fill_addrinfo(skb, cb, mdev, mdev->addrs[mcb->a_idx]);
		if (rc < 0)
			break;
	}

	return rc;
}

static int mctp_dump_addrinfo(struct sk_buff *skb, struct netlink_callback *cb)
{
	struct mctp_dump_cb *mcb = (void *)cb->ctx;
	struct net *net = sock_net(skb->sk);
	struct hlist_head *head;
	struct net_device *dev;
	struct ifaddrmsg *hdr;
	struct mctp_dev *mdev;
	int ifindex;
	int idx, rc;

	hdr = nlmsg_data(cb->nlh);
	// filter by ifindex if requested
	ifindex = hdr->ifa_index;

	rcu_read_lock();
	for (; mcb->h < NETDEV_HASHENTRIES; mcb->h++, mcb->idx = 0) {
		idx = 0;
		head = &net->dev_index_head[mcb->h];
		hlist_for_each_entry_rcu(dev, head, index_hlist) {
			if (idx >= mcb->idx &&
			    (ifindex == 0 || ifindex == dev->ifindex)) {
				mdev = __mctp_dev_get(dev);
				if (mdev) {
					rc = mctp_dump_dev_addrinfo(mdev,
								    skb, cb);
					// Error indicates full buffer, this
					// callback will get retried.
					if (rc < 0)
						goto out;
				}
			}
			idx++;
			// reset for next iteration
			mcb->a_idx = 0;
		}
	}
out:
	rcu_read_unlock();
	mcb->idx = idx;

	return skb->len;
}

static const struct nla_policy ifa_mctp_policy[IFA_MAX + 1] = {
	[IFA_ADDRESS]		= { .type = NLA_U8 },
	[IFA_LOCAL]		= { .type = NLA_U8 },
};

static int mctp_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
			    struct netlink_ext_ack *extack)
{
	struct net *net = sock_net(skb->sk);
	struct nlattr *tb[IFA_MAX + 1];
	struct net_device *dev;
	struct mctp_addr *addr;
	struct mctp_dev *mdev;
	struct ifaddrmsg *ifm;
	unsigned long flags;
	u8 *tmp_addrs;
	int rc;

	rc = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_mctp_policy,
			 extack);
	if (rc < 0)
		return rc;

	ifm = nlmsg_data(nlh);

	if (tb[IFA_LOCAL])
		addr = nla_data(tb[IFA_LOCAL]);
	else if (tb[IFA_ADDRESS])
		addr = nla_data(tb[IFA_ADDRESS]);
	else
		return -EINVAL;

	/* find device */
	dev = __dev_get_by_index(net, ifm->ifa_index);
	if (!dev)
		return -ENODEV;

	mdev = mctp_dev_get_rtnl(dev);
	if (!mdev)
		return -ENODEV;

	if (!mctp_address_ok(addr->s_addr))
		return -EINVAL;

	/* Prevent duplicates. Under RTNL so don't need to lock for reading */
	if (memchr(mdev->addrs, addr->s_addr, mdev->num_addrs))
		return -EEXIST;

	tmp_addrs = kmalloc(mdev->num_addrs + 1, GFP_KERNEL);
	if (!tmp_addrs)
		return -ENOMEM;
	memcpy(tmp_addrs, mdev->addrs, mdev->num_addrs);
	tmp_addrs[mdev->num_addrs] = addr->s_addr;

	/* Lock to write */
	spin_lock_irqsave(&mdev->addrs_lock, flags);
	mdev->num_addrs++;
	swap(mdev->addrs, tmp_addrs);
	spin_unlock_irqrestore(&mdev->addrs_lock, flags);

	kfree(tmp_addrs);

	mctp_route_add_local(mdev, addr->s_addr);

	return 0;
}

static int mctp_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
			    struct netlink_ext_ack *extack)
{
	struct net *net = sock_net(skb->sk);
	struct nlattr *tb[IFA_MAX + 1];
	struct net_device *dev;
	struct mctp_addr *addr;
	struct mctp_dev *mdev;
	struct ifaddrmsg *ifm;
	unsigned long flags;
	u8 *pos;
	int rc;

	rc = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_mctp_policy,
			 extack);
	if (rc < 0)
		return rc;

	ifm = nlmsg_data(nlh);

	if (tb[IFA_LOCAL])
		addr = nla_data(tb[IFA_LOCAL]);
	else if (tb[IFA_ADDRESS])
		addr = nla_data(tb[IFA_ADDRESS]);
	else
		return -EINVAL;

	/* find device */
	dev = __dev_get_by_index(net, ifm->ifa_index);
	if (!dev)
		return -ENODEV;

	mdev = mctp_dev_get_rtnl(dev);
	if (!mdev)
		return -ENODEV;

	pos = memchr(mdev->addrs, addr->s_addr, mdev->num_addrs);
	if (!pos)
		return -ENOENT;

	rc = mctp_route_remove_local(mdev, addr->s_addr);
	// we can ignore -ENOENT in the case a route was already removed
	if (rc < 0 && rc != -ENOENT)
		return rc;

	spin_lock_irqsave(&mdev->addrs_lock, flags);
	memmove(pos, pos + 1, mdev->num_addrs - 1 - (pos - mdev->addrs));
	mdev->num_addrs--;
	spin_unlock_irqrestore(&mdev->addrs_lock, flags);

	return 0;
}

void mctp_dev_hold(struct mctp_dev *mdev)
{
	refcount_inc(&mdev->refs);
}

void mctp_dev_put(struct mctp_dev *mdev)
{
	if (refcount_dec_and_test(&mdev->refs)) {
		dev_put(mdev->dev);
		kfree_rcu(mdev, rcu);
	}
}

static struct mctp_dev *mctp_add_dev(struct net_device *dev)
{
	struct mctp_dev *mdev;

	ASSERT_RTNL();

	mdev = kzalloc(sizeof(*mdev), GFP_KERNEL);
	if (!mdev)
		return ERR_PTR(-ENOMEM);

	spin_lock_init(&mdev->addrs_lock);

	mdev->net = mctp_default_net(dev_net(dev));

	/* associate to net_device */
	refcount_set(&mdev->refs, 1);
	rcu_assign_pointer(dev->mctp_ptr, mdev);

	dev_hold(dev);
	mdev->dev = dev;

	return mdev;
}

static int mctp_fill_link_af(struct sk_buff *skb,
			     const struct net_device *dev, u32 ext_filter_mask)
{
	struct mctp_dev *mdev;

	mdev = mctp_dev_get_rtnl(dev);
	if (!mdev)
		return -ENODATA;
	if (nla_put_u32(skb, IFLA_MCTP_NET, mdev->net))
		return -EMSGSIZE;
	return 0;
}

static size_t mctp_get_link_af_size(const struct net_device *dev,
				    u32 ext_filter_mask)
{
	struct mctp_dev *mdev;
	unsigned int ret;

	/* caller holds RCU */
	mdev = __mctp_dev_get(dev);
	if (!mdev)
		return 0;
	ret = nla_total_size(4); /* IFLA_MCTP_NET */
	return ret;
}

static const struct nla_policy ifla_af_mctp_policy[IFLA_MCTP_MAX + 1] = {
	[IFLA_MCTP_NET]		= { .type = NLA_U32 },
};

static int mctp_set_link_af(struct net_device *dev, const struct nlattr *attr,
			    struct netlink_ext_ack *extack)
{
	struct nlattr *tb[IFLA_MCTP_MAX + 1];
	struct mctp_dev *mdev;
	int rc;

	rc = nla_parse_nested(tb, IFLA_MCTP_MAX, attr, ifla_af_mctp_policy,
			      NULL);
	if (rc)
		return rc;

	mdev = mctp_dev_get_rtnl(dev);
	if (!mdev)
		return 0;

	if (tb[IFLA_MCTP_NET])
		WRITE_ONCE(mdev->net, nla_get_u32(tb[IFLA_MCTP_NET]));

	return 0;
}

/* Matches netdev types that should have MCTP handling */
static bool mctp_known(struct net_device *dev)
{
	/* only register specific types (inc. NONE for TUN devices) */
	return dev->type == ARPHRD_MCTP ||
		   dev->type == ARPHRD_LOOPBACK ||
		   dev->type == ARPHRD_NONE;
}

static void mctp_unregister(struct net_device *dev)
{
	struct mctp_dev *mdev;

	mdev = mctp_dev_get_rtnl(dev);
	if (mctp_known(dev) != (bool)mdev) {
		// Sanity check, should match what was set in mctp_register
		netdev_warn(dev, "%s: mdev pointer %d but type (%d) match is %d",
			    __func__, (bool)mdev, mctp_known(dev), dev->type);
		return;
	}
	if (!mdev)
		return;

	RCU_INIT_POINTER(mdev->dev->mctp_ptr, NULL);

	mctp_route_remove_dev(mdev);
	mctp_neigh_remove_dev(mdev);
	kfree(mdev->addrs);

	mctp_dev_put(mdev);
}

static int mctp_register(struct net_device *dev)
{
	struct mctp_dev *mdev;

	/* Already registered? */
	mdev = rtnl_dereference(dev->mctp_ptr);

	if (mdev) {
		if (!mctp_known(dev))
			netdev_warn(dev, "%s: mctp_dev set for unknown type %d",
				    __func__, dev->type);
		return 0;
	}

	/* only register specific types */
	if (!mctp_known(dev))
		return 0;

	mdev = mctp_add_dev(dev);
	if (IS_ERR(mdev))
		return PTR_ERR(mdev);

	return 0;
}

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

	switch (event) {
	case NETDEV_REGISTER:
		rc = mctp_register(dev);
		if (rc)
			return notifier_from_errno(rc);
		break;
	case NETDEV_UNREGISTER:
		mctp_unregister(dev);
		break;
	}

	return NOTIFY_OK;
}

static struct rtnl_af_ops mctp_af_ops = {
	.family = AF_MCTP,
	.fill_link_af = mctp_fill_link_af,
	.get_link_af_size = mctp_get_link_af_size,
	.set_link_af = mctp_set_link_af,
};

static struct notifier_block mctp_dev_nb = {
	.notifier_call = mctp_dev_notify,
	.priority = ADDRCONF_NOTIFY_PRIORITY,
};

void __init mctp_device_init(void)
{
	register_netdevice_notifier(&mctp_dev_nb);

	rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_GETADDR,
			     NULL, mctp_dump_addrinfo, 0);
	rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_NEWADDR,
			     mctp_rtm_newaddr, NULL, 0);
	rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_DELADDR,
			     mctp_rtm_deladdr, NULL, 0);
	rtnl_af_register(&mctp_af_ops);
}

void __exit mctp_device_exit(void)
{
	rtnl_af_unregister(&mctp_af_ops);
	rtnl_unregister(PF_MCTP, RTM_DELADDR);
	rtnl_unregister(PF_MCTP, RTM_NEWADDR);
	rtnl_unregister(PF_MCTP, RTM_GETADDR);

	unregister_netdevice_notifier(&mctp_dev_nb);
}