summaryrefslogtreecommitdiffstats
path: root/net/tipc/node.c
blob: 86152de8248da7164cde4b932ac7be1b6b6b2245 (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
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
/*
 * net/tipc/node.c: TIPC node management routines
 *
 * Copyright (c) 2000-2006, 2012-2014, Ericsson AB
 * Copyright (c) 2005-2006, 2010-2014, Wind River Systems
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. Neither the names of the copyright holders nor the names of its
 *    contributors may be used to endorse or promote products derived from
 *    this software without specific prior written permission.
 *
 * Alternatively, this software may be distributed under the terms of the
 * GNU General Public License ("GPL") version 2 as published by the Free
 * Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
 * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 * POSSIBILITY OF SUCH DAMAGE.
 */

#include "core.h"
#include "link.h"
#include "node.h"
#include "name_distr.h"
#include "socket.h"

static void node_lost_contact(struct tipc_node *n_ptr);
static void node_established_contact(struct tipc_node *n_ptr);

struct tipc_sock_conn {
	u32 port;
	u32 peer_port;
	u32 peer_node;
	struct list_head list;
};

static const struct nla_policy tipc_nl_node_policy[TIPC_NLA_NODE_MAX + 1] = {
	[TIPC_NLA_NODE_UNSPEC]		= { .type = NLA_UNSPEC },
	[TIPC_NLA_NODE_ADDR]		= { .type = NLA_U32 },
	[TIPC_NLA_NODE_UP]		= { .type = NLA_FLAG }
};

/*
 * A trivial power-of-two bitmask technique is used for speed, since this
 * operation is done for every incoming TIPC packet. The number of hash table
 * entries has been chosen so that no hash chain exceeds 8 nodes and will
 * usually be much smaller (typically only a single node).
 */
static unsigned int tipc_hashfn(u32 addr)
{
	return addr & (NODE_HTABLE_SIZE - 1);
}

/*
 * tipc_node_find - locate specified node object, if it exists
 */
struct tipc_node *tipc_node_find(struct net *net, u32 addr)
{
	struct tipc_net *tn = net_generic(net, tipc_net_id);
	struct tipc_node *node;

	if (unlikely(!in_own_cluster_exact(net, addr)))
		return NULL;

	rcu_read_lock();
	hlist_for_each_entry_rcu(node, &tn->node_htable[tipc_hashfn(addr)],
				 hash) {
		if (node->addr == addr) {
			rcu_read_unlock();
			return node;
		}
	}
	rcu_read_unlock();
	return NULL;
}

struct tipc_node *tipc_node_create(struct net *net, u32 addr)
{
	struct tipc_net *tn = net_generic(net, tipc_net_id);
	struct tipc_node *n_ptr, *temp_node;

	spin_lock_bh(&tn->node_list_lock);
	n_ptr = tipc_node_find(net, addr);
	if (n_ptr)
		goto exit;
	n_ptr = kzalloc(sizeof(*n_ptr), GFP_ATOMIC);
	if (!n_ptr) {
		pr_warn("Node creation failed, no memory\n");
		goto exit;
	}
	n_ptr->addr = addr;
	n_ptr->net = net;
	spin_lock_init(&n_ptr->lock);
	INIT_HLIST_NODE(&n_ptr->hash);
	INIT_LIST_HEAD(&n_ptr->list);
	INIT_LIST_HEAD(&n_ptr->publ_list);
	INIT_LIST_HEAD(&n_ptr->conn_sks);
	__skb_queue_head_init(&n_ptr->bclink.deferred_queue);
	hlist_add_head_rcu(&n_ptr->hash, &tn->node_htable[tipc_hashfn(addr)]);
	list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
		if (n_ptr->addr < temp_node->addr)
			break;
	}
	list_add_tail_rcu(&n_ptr->list, &temp_node->list);
	n_ptr->action_flags = TIPC_WAIT_PEER_LINKS_DOWN;
	n_ptr->signature = INVALID_NODE_SIG;
exit:
	spin_unlock_bh(&tn->node_list_lock);
	return n_ptr;
}

static void tipc_node_delete(struct tipc_net *tn, struct tipc_node *n_ptr)
{
	list_del_rcu(&n_ptr->list);
	hlist_del_rcu(&n_ptr->hash);
	kfree_rcu(n_ptr, rcu);
}

void tipc_node_stop(struct net *net)
{
	struct tipc_net *tn = net_generic(net, tipc_net_id);
	struct tipc_node *node, *t_node;

	spin_lock_bh(&tn->node_list_lock);
	list_for_each_entry_safe(node, t_node, &tn->node_list, list)
		tipc_node_delete(tn, node);
	spin_unlock_bh(&tn->node_list_lock);
}

int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port)
{
	struct tipc_node *node;
	struct tipc_sock_conn *conn;

	if (in_own_node(net, dnode))
		return 0;

	node = tipc_node_find(net, dnode);
	if (!node) {
		pr_warn("Connecting sock to node 0x%x failed\n", dnode);
		return -EHOSTUNREACH;
	}
	conn = kmalloc(sizeof(*conn), GFP_ATOMIC);
	if (!conn)
		return -EHOSTUNREACH;
	conn->peer_node = dnode;
	conn->port = port;
	conn->peer_port = peer_port;

	tipc_node_lock(node);
	list_add_tail(&conn->list, &node->conn_sks);
	tipc_node_unlock(node);
	return 0;
}

void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port)
{
	struct tipc_node *node;
	struct tipc_sock_conn *conn, *safe;

	if (in_own_node(net, dnode))
		return;

	node = tipc_node_find(net, dnode);
	if (!node)
		return;

	tipc_node_lock(node);
	list_for_each_entry_safe(conn, safe, &node->conn_sks, list) {
		if (port != conn->port)
			continue;
		list_del(&conn->list);
		kfree(conn);
	}
	tipc_node_unlock(node);
}

/**
 * tipc_node_link_up - handle addition of link
 *
 * Link becomes active (alone or shared) or standby, depending on its priority.
 */
void tipc_node_link_up(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
{
	struct tipc_link **active = &n_ptr->active_links[0];

	n_ptr->working_links++;
	n_ptr->action_flags |= TIPC_NOTIFY_LINK_UP;
	n_ptr->link_id = l_ptr->peer_bearer_id << 16 | l_ptr->bearer_id;

	pr_debug("Established link <%s> on network plane %c\n",
		 l_ptr->name, l_ptr->net_plane);

	if (!active[0]) {
		active[0] = active[1] = l_ptr;
		node_established_contact(n_ptr);
		goto exit;
	}
	if (l_ptr->priority < active[0]->priority) {
		pr_debug("New link <%s> becomes standby\n", l_ptr->name);
		goto exit;
	}
	tipc_link_dup_queue_xmit(active[0], l_ptr);
	if (l_ptr->priority == active[0]->priority) {
		active[0] = l_ptr;
		goto exit;
	}
	pr_debug("Old link <%s> becomes standby\n", active[0]->name);
	if (active[1] != active[0])
		pr_debug("Old link <%s> becomes standby\n", active[1]->name);
	active[0] = active[1] = l_ptr;
exit:
	/* Leave room for changeover header when returning 'mtu' to users: */
	n_ptr->act_mtus[0] = active[0]->max_pkt - INT_H_SIZE;
	n_ptr->act_mtus[1] = active[1]->max_pkt - INT_H_SIZE;
}

/**
 * node_select_active_links - select active link
 */
static void node_select_active_links(struct tipc_node *n_ptr)
{
	struct tipc_link **active = &n_ptr->active_links[0];
	u32 i;
	u32 highest_prio = 0;

	active[0] = active[1] = NULL;

	for (i = 0; i < MAX_BEARERS; i++) {
		struct tipc_link *l_ptr = n_ptr->links[i];

		if (!l_ptr || !tipc_link_is_up(l_ptr) ||
		    (l_ptr->priority < highest_prio))
			continue;

		if (l_ptr->priority > highest_prio) {
			highest_prio = l_ptr->priority;
			active[0] = active[1] = l_ptr;
		} else {
			active[1] = l_ptr;
		}
	}
}

/**
 * tipc_node_link_down - handle loss of link
 */
void tipc_node_link_down(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
{
	struct tipc_net *tn = net_generic(n_ptr->net, tipc_net_id);
	struct tipc_link **active;

	n_ptr->working_links--;
	n_ptr->action_flags |= TIPC_NOTIFY_LINK_DOWN;
	n_ptr->link_id = l_ptr->peer_bearer_id << 16 | l_ptr->bearer_id;

	if (!tipc_link_is_active(l_ptr)) {
		pr_debug("Lost standby link <%s> on network plane %c\n",
			 l_ptr->name, l_ptr->net_plane);
		return;
	}
	pr_debug("Lost link <%s> on network plane %c\n",
		 l_ptr->name, l_ptr->net_plane);

	active = &n_ptr->active_links[0];
	if (active[0] == l_ptr)
		active[0] = active[1];
	if (active[1] == l_ptr)
		active[1] = active[0];
	if (active[0] == l_ptr)
		node_select_active_links(n_ptr);
	if (tipc_node_is_up(n_ptr))
		tipc_link_failover_send_queue(l_ptr);
	else
		node_lost_contact(n_ptr);

	/* Leave room for changeover header when returning 'mtu' to users: */
	if (active[0]) {
		n_ptr->act_mtus[0] = active[0]->max_pkt - INT_H_SIZE;
		n_ptr->act_mtus[1] = active[1]->max_pkt - INT_H_SIZE;
		return;
	}

	/* Loopback link went down? No fragmentation needed from now on. */
	if (n_ptr->addr == tn->own_addr) {
		n_ptr->act_mtus[0] = MAX_MSG_SIZE;
		n_ptr->act_mtus[1] = MAX_MSG_SIZE;
	}
}

int tipc_node_active_links(struct tipc_node *n_ptr)
{
	return n_ptr->active_links[0] != NULL;
}

int tipc_node_is_up(struct tipc_node *n_ptr)
{
	return tipc_node_active_links(n_ptr);
}

void tipc_node_attach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
{
	n_ptr->links[l_ptr->bearer_id] = l_ptr;
	n_ptr->link_cnt++;
}

void tipc_node_detach_link(struct tipc_node *n_ptr, struct tipc_link *l_ptr)
{
	int i;

	for (i = 0; i < MAX_BEARERS; i++) {
		if (l_ptr != n_ptr->links[i])
			continue;
		n_ptr->links[i] = NULL;
		n_ptr->link_cnt--;
	}
}

static void node_established_contact(struct tipc_node *n_ptr)
{
	n_ptr->action_flags |= TIPC_NOTIFY_NODE_UP;
	n_ptr->bclink.oos_state = 0;
	n_ptr->bclink.acked = tipc_bclink_get_last_sent(n_ptr->net);
	tipc_bclink_add_node(n_ptr->net, n_ptr->addr);
}

static void node_lost_contact(struct tipc_node *n_ptr)
{
	char addr_string[16];
	struct tipc_sock_conn *conn, *safe;
	struct list_head *conns = &n_ptr->conn_sks;
	struct sk_buff *skb;
	struct tipc_net *tn = net_generic(n_ptr->net, tipc_net_id);
	uint i;

	pr_debug("Lost contact with %s\n",
		 tipc_addr_string_fill(addr_string, n_ptr->addr));

	/* Flush broadcast link info associated with lost node */
	if (n_ptr->bclink.recv_permitted) {
		__skb_queue_purge(&n_ptr->bclink.deferred_queue);

		if (n_ptr->bclink.reasm_buf) {
			kfree_skb(n_ptr->bclink.reasm_buf);
			n_ptr->bclink.reasm_buf = NULL;
		}

		tipc_bclink_remove_node(n_ptr->net, n_ptr->addr);
		tipc_bclink_acknowledge(n_ptr, INVALID_LINK_SEQ);

		n_ptr->bclink.recv_permitted = false;
	}

	/* Abort link changeover */
	for (i = 0; i < MAX_BEARERS; i++) {
		struct tipc_link *l_ptr = n_ptr->links[i];
		if (!l_ptr)
			continue;
		l_ptr->reset_checkpoint = l_ptr->next_in_no;
		l_ptr->exp_msg_count = 0;
		tipc_link_reset_fragments(l_ptr);

		/* Link marked for deletion after failover? => do it now */
		if (l_ptr->flags & LINK_STOPPED)
			tipc_link_delete(l_ptr);
	}

	n_ptr->action_flags &= ~TIPC_WAIT_OWN_LINKS_DOWN;

	/* Prevent re-contact with node until cleanup is done */
	n_ptr->action_flags |= TIPC_WAIT_PEER_LINKS_DOWN;

	/* Notify publications from this node */
	n_ptr->action_flags |= TIPC_NOTIFY_NODE_DOWN;

	/* Notify sockets connected to node */
	list_for_each_entry_safe(conn, safe, conns, list) {
		skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG,
				      SHORT_H_SIZE, 0, tn->own_addr,
				      conn->peer_node, conn->port,
				      conn->peer_port, TIPC_ERR_NO_NODE);
		if (likely(skb)) {
			skb_queue_tail(n_ptr->inputq, skb);
			n_ptr->action_flags |= TIPC_MSG_EVT;
		}
		list_del(&conn->list);
		kfree(conn);
	}
}

/**
 * tipc_node_get_linkname - get the name of a link
 *
 * @bearer_id: id of the bearer
 * @node: peer node address
 * @linkname: link name output buffer
 *
 * Returns 0 on success
 */
int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 addr,
			   char *linkname, size_t len)
{
	struct tipc_link *link;
	struct tipc_node *node = tipc_node_find(net, addr);

	if ((bearer_id >= MAX_BEARERS) || !node)
		return -EINVAL;
	tipc_node_lock(node);
	link = node->links[bearer_id];
	if (link) {
		strncpy(linkname, link->name, len);
		tipc_node_unlock(node);
		return 0;
	}
	tipc_node_unlock(node);
	return -EINVAL;
}

void tipc_node_unlock(struct tipc_node *node)
{
	struct net *net = node->net;
	u32 addr = 0;
	u32 flags = node->action_flags;
	u32 link_id = 0;
	struct list_head *publ_list;
	struct sk_buff_head *inputq = node->inputq;
	struct sk_buff_head *namedq;

	if (likely(!flags || (flags == TIPC_MSG_EVT))) {
		node->action_flags = 0;
		spin_unlock_bh(&node->lock);
		if (flags == TIPC_MSG_EVT)
			tipc_sk_rcv(net, inputq);
		return;
	}

	addr = node->addr;
	link_id = node->link_id;
	namedq = node->namedq;
	publ_list = &node->publ_list;

	node->action_flags &= ~(TIPC_MSG_EVT |
				TIPC_NOTIFY_NODE_DOWN | TIPC_NOTIFY_NODE_UP |
				TIPC_NOTIFY_LINK_DOWN | TIPC_NOTIFY_LINK_UP |
				TIPC_WAKEUP_BCAST_USERS | TIPC_BCAST_MSG_EVT |
				TIPC_NAMED_MSG_EVT);

	spin_unlock_bh(&node->lock);

	if (flags & TIPC_NOTIFY_NODE_DOWN)
		tipc_publ_notify(net, publ_list, addr);

	if (flags & TIPC_WAKEUP_BCAST_USERS)
		tipc_bclink_wakeup_users(net);

	if (flags & TIPC_NOTIFY_NODE_UP)
		tipc_named_node_up(net, addr);

	if (flags & TIPC_NOTIFY_LINK_UP)
		tipc_nametbl_publish(net, TIPC_LINK_STATE, addr, addr,
				     TIPC_NODE_SCOPE, link_id, addr);

	if (flags & TIPC_NOTIFY_LINK_DOWN)
		tipc_nametbl_withdraw(net, TIPC_LINK_STATE, addr,
				      link_id, addr);

	if (flags & TIPC_MSG_EVT)
		tipc_sk_rcv(net, inputq);

	if (flags & TIPC_NAMED_MSG_EVT)
		tipc_named_rcv(net, namedq);

	if (flags & TIPC_BCAST_MSG_EVT)
		tipc_bclink_input(net);
}

/* Caller should hold node lock for the passed node */
static int __tipc_nl_add_node(struct tipc_nl_msg *msg, struct tipc_node *node)
{
	void *hdr;
	struct nlattr *attrs;

	hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family,
			  NLM_F_MULTI, TIPC_NL_NODE_GET);
	if (!hdr)
		return -EMSGSIZE;

	attrs = nla_nest_start(msg->skb, TIPC_NLA_NODE);
	if (!attrs)
		goto msg_full;

	if (nla_put_u32(msg->skb, TIPC_NLA_NODE_ADDR, node->addr))
		goto attr_msg_full;
	if (tipc_node_is_up(node))
		if (nla_put_flag(msg->skb, TIPC_NLA_NODE_UP))
			goto attr_msg_full;

	nla_nest_end(msg->skb, attrs);
	genlmsg_end(msg->skb, hdr);

	return 0;

attr_msg_full:
	nla_nest_cancel(msg->skb, attrs);
msg_full:
	genlmsg_cancel(msg->skb, hdr);

	return -EMSGSIZE;
}

int tipc_nl_node_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
	int err;
	struct net *net = sock_net(skb->sk);
	struct tipc_net *tn = net_generic(net, tipc_net_id);
	int done = cb->args[0];
	int last_addr = cb->args[1];
	struct tipc_node *node;
	struct tipc_nl_msg msg;

	if (done)
		return 0;

	msg.skb = skb;
	msg.portid = NETLINK_CB(cb->skb).portid;
	msg.seq = cb->nlh->nlmsg_seq;

	rcu_read_lock();

	if (last_addr && !tipc_node_find(net, last_addr)) {
		rcu_read_unlock();
		/* We never set seq or call nl_dump_check_consistent() this
		 * means that setting prev_seq here will cause the consistence
		 * check to fail in the netlink callback handler. Resulting in
		 * the NLMSG_DONE message having the NLM_F_DUMP_INTR flag set if
		 * the node state changed while we released the lock.
		 */
		cb->prev_seq = 1;
		return -EPIPE;
	}

	list_for_each_entry_rcu(node, &tn->node_list, list) {
		if (last_addr) {
			if (node->addr == last_addr)
				last_addr = 0;
			else
				continue;
		}

		tipc_node_lock(node);
		err = __tipc_nl_add_node(&msg, node);
		if (err) {
			last_addr = node->addr;
			tipc_node_unlock(node);
			goto out;
		}

		tipc_node_unlock(node);
	}
	done = 1;
out:
	cb->args[0] = done;
	cb->args[1] = last_addr;
	rcu_read_unlock();

	return skb->len;
}
OpenPOWER on IntegriCloud