summaryrefslogtreecommitdiffstats
path: root/net/tipc/group.c
blob: b8ed70abba01470742de2f7a43995be45cd155fe (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
/*
 * net/tipc/group.c: TIPC group messaging code
 *
 * Copyright (c) 2017, Ericsson AB
 * 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 "addr.h"
#include "group.h"
#include "bcast.h"
#include "server.h"
#include "msg.h"
#include "socket.h"
#include "node.h"
#include "name_table.h"
#include "subscr.h"

#define ADV_UNIT (((MAX_MSG_SIZE + MAX_H_SIZE) / FLOWCTL_BLK_SZ) + 1)
#define ADV_IDLE ADV_UNIT
#define ADV_ACTIVE (ADV_UNIT * 12)

enum mbr_state {
	MBR_QUARANTINED,
	MBR_DISCOVERED,
	MBR_JOINING,
	MBR_PUBLISHED,
	MBR_JOINED,
	MBR_LEAVING
};

struct tipc_member {
	struct rb_node tree_node;
	struct list_head list;
	struct list_head congested;
	struct sk_buff *event_msg;
	struct tipc_group *group;
	u32 node;
	u32 port;
	u32 instance;
	enum mbr_state state;
	u16 advertised;
	u16 window;
	u16 bc_rcv_nxt;
	bool usr_pending;
};

struct tipc_group {
	struct rb_root members;
	struct list_head congested;
	struct tipc_nlist dests;
	struct net *net;
	int subid;
	u32 type;
	u32 instance;
	u32 domain;
	u32 scope;
	u32 portid;
	u16 member_cnt;
	u16 bc_snd_nxt;
	bool loopback;
	bool events;
};

static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m,
				  int mtyp, struct sk_buff_head *xmitq);

static int tipc_group_rcvbuf_limit(struct tipc_group *grp)
{
	int mcnt = grp->member_cnt + 1;

	/* Scale to bytes, considering worst-case truesize/msgsize ratio */
	return mcnt * ADV_ACTIVE * FLOWCTL_BLK_SZ * 4;
}

u16 tipc_group_bc_snd_nxt(struct tipc_group *grp)
{
	return grp->bc_snd_nxt;
}

static bool tipc_group_is_enabled(struct tipc_member *m)
{
	return m->state != MBR_QUARANTINED && m->state != MBR_LEAVING;
}

static bool tipc_group_is_receiver(struct tipc_member *m)
{
	return m && m->state >= MBR_JOINED;
}

int tipc_group_size(struct tipc_group *grp)
{
	return grp->member_cnt;
}

struct tipc_group *tipc_group_create(struct net *net, u32 portid,
				     struct tipc_group_req *mreq)
{
	struct tipc_group *grp;
	u32 type = mreq->type;

	grp = kzalloc(sizeof(*grp), GFP_ATOMIC);
	if (!grp)
		return NULL;
	tipc_nlist_init(&grp->dests, tipc_own_addr(net));
	INIT_LIST_HEAD(&grp->congested);
	grp->members = RB_ROOT;
	grp->net = net;
	grp->portid = portid;
	grp->domain = addr_domain(net, mreq->scope);
	grp->type = type;
	grp->instance = mreq->instance;
	grp->scope = mreq->scope;
	grp->loopback = mreq->flags & TIPC_GROUP_LOOPBACK;
	grp->events = mreq->flags & TIPC_GROUP_MEMBER_EVTS;
	if (tipc_topsrv_kern_subscr(net, portid, type, 0, ~0, &grp->subid))
		return grp;
	kfree(grp);
	return NULL;
}

void tipc_group_delete(struct net *net, struct tipc_group *grp)
{
	struct rb_root *tree = &grp->members;
	struct tipc_member *m, *tmp;
	struct sk_buff_head xmitq;

	__skb_queue_head_init(&xmitq);

	rbtree_postorder_for_each_entry_safe(m, tmp, tree, tree_node) {
		tipc_group_proto_xmit(grp, m, GRP_LEAVE_MSG, &xmitq);
		list_del(&m->list);
		kfree(m);
	}
	tipc_node_distr_xmit(net, &xmitq);
	tipc_nlist_purge(&grp->dests);
	tipc_topsrv_kern_unsubscr(net, grp->subid);
	kfree(grp);
}

struct tipc_member *tipc_group_find_member(struct tipc_group *grp,
					   u32 node, u32 port)
{
	struct rb_node *n = grp->members.rb_node;
	u64 nkey, key = (u64)node << 32 | port;
	struct tipc_member *m;

	while (n) {
		m = container_of(n, struct tipc_member, tree_node);
		nkey = (u64)m->node << 32 | m->port;
		if (key < nkey)
			n = n->rb_left;
		else if (key > nkey)
			n = n->rb_right;
		else
			return m;
	}
	return NULL;
}

static struct tipc_member *tipc_group_find_node(struct tipc_group *grp,
						u32 node)
{
	struct tipc_member *m;
	struct rb_node *n;

	for (n = rb_first(&grp->members); n; n = rb_next(n)) {
		m = container_of(n, struct tipc_member, tree_node);
		if (m->node == node)
			return m;
	}
	return NULL;
}

static void tipc_group_add_to_tree(struct tipc_group *grp,
				   struct tipc_member *m)
{
	u64 nkey, key = (u64)m->node << 32 | m->port;
	struct rb_node **n, *parent = NULL;
	struct tipc_member *tmp;

	n = &grp->members.rb_node;
	while (*n) {
		tmp = container_of(*n, struct tipc_member, tree_node);
		parent = *n;
		tmp = container_of(parent, struct tipc_member, tree_node);
		nkey = (u64)tmp->node << 32 | tmp->port;
		if (key < nkey)
			n = &(*n)->rb_left;
		else if (key > nkey)
			n = &(*n)->rb_right;
		else
			return;
	}
	rb_link_node(&m->tree_node, parent, n);
	rb_insert_color(&m->tree_node, &grp->members);
}

static struct tipc_member *tipc_group_create_member(struct tipc_group *grp,
						    u32 node, u32 port,
						    int state)
{
	struct tipc_member *m;

	m = kzalloc(sizeof(*m), GFP_ATOMIC);
	if (!m)
		return NULL;
	INIT_LIST_HEAD(&m->list);
	INIT_LIST_HEAD(&m->congested);
	m->group = grp;
	m->node = node;
	m->port = port;
	grp->member_cnt++;
	tipc_group_add_to_tree(grp, m);
	tipc_nlist_add(&grp->dests, m->node);
	m->state = state;
	return m;
}

void tipc_group_add_member(struct tipc_group *grp, u32 node, u32 port)
{
	tipc_group_create_member(grp, node, port, MBR_DISCOVERED);
}

static void tipc_group_delete_member(struct tipc_group *grp,
				     struct tipc_member *m)
{
	rb_erase(&m->tree_node, &grp->members);
	grp->member_cnt--;
	list_del_init(&m->list);
	list_del_init(&m->congested);

	/* If last member on a node, remove node from dest list */
	if (!tipc_group_find_node(grp, m->node))
		tipc_nlist_del(&grp->dests, m->node);

	kfree(m);
}

struct tipc_nlist *tipc_group_dests(struct tipc_group *grp)
{
	return &grp->dests;
}

void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq,
		     int *scope)
{
	seq->type = grp->type;
	seq->lower = grp->instance;
	seq->upper = grp->instance;
	*scope = grp->scope;
}

void tipc_group_update_member(struct tipc_member *m, int len)
{
	struct tipc_group *grp = m->group;
	struct tipc_member *_m, *tmp;

	if (!tipc_group_is_enabled(m))
		return;

	m->window -= len;

	if (m->window >= ADV_IDLE)
		return;

	if (!list_empty(&m->congested))
		return;

	/* Sort member into congested members' list */
	list_for_each_entry_safe(_m, tmp, &grp->congested, congested) {
		if (m->window > _m->window)
			continue;
		list_add_tail(&m->congested, &_m->congested);
		return;
	}
	list_add_tail(&m->congested, &grp->congested);
}

void tipc_group_update_bc_members(struct tipc_group *grp, int len)
{
	struct tipc_member *m;
	struct rb_node *n;

	for (n = rb_first(&grp->members); n; n = rb_next(n)) {
		m = container_of(n, struct tipc_member, tree_node);
		if (tipc_group_is_enabled(m))
			tipc_group_update_member(m, len);
	}
	grp->bc_snd_nxt++;
}

bool tipc_group_bc_cong(struct tipc_group *grp, int len)
{
	struct tipc_member *m;

	if (list_empty(&grp->congested))
		return false;

	m = list_first_entry(&grp->congested, struct tipc_member, congested);
	if (m->window >= len)
		return false;

	return true;
}

/* tipc_group_filter_msg() - determine if we should accept arriving message
 */
void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq,
			   struct sk_buff_head *xmitq)
{
	struct sk_buff *skb = __skb_dequeue(inputq);
	struct tipc_member *m;
	struct tipc_msg *hdr;
	u32 node, port;
	int mtyp;

	if (!skb)
		return;

	hdr = buf_msg(skb);
	mtyp = msg_type(hdr);
	node =  msg_orignode(hdr);
	port = msg_origport(hdr);

	if (!msg_in_group(hdr))
		goto drop;

	if (mtyp == TIPC_GRP_MEMBER_EVT) {
		if (!grp->events)
			goto drop;
		__skb_queue_tail(inputq, skb);
		return;
	}

	m = tipc_group_find_member(grp, node, port);
	if (!tipc_group_is_receiver(m))
		goto drop;

	TIPC_SKB_CB(skb)->orig_member = m->instance;
	__skb_queue_tail(inputq, skb);

	m->bc_rcv_nxt = msg_grp_bc_seqno(hdr) + 1;
	return;
drop:
	kfree_skb(skb);
}

void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node,
			       u32 port, struct sk_buff_head *xmitq)
{
	struct tipc_member *m;

	m = tipc_group_find_member(grp, node, port);
	if (!m)
		return;

	m->advertised -= blks;

	switch (m->state) {
	case MBR_JOINED:
		if (m->advertised <= (ADV_ACTIVE - ADV_UNIT))
			tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq);
		break;
	case MBR_DISCOVERED:
	case MBR_JOINING:
	case MBR_LEAVING:
	default:
		break;
	}
}

static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m,
				  int mtyp, struct sk_buff_head *xmitq)
{
	struct tipc_msg *hdr;
	struct sk_buff *skb;
	int adv = 0;

	skb = tipc_msg_create(GROUP_PROTOCOL, mtyp, INT_H_SIZE, 0,
			      m->node, tipc_own_addr(grp->net),
			      m->port, grp->portid, 0);
	if (!skb)
		return;

	if (m->state == MBR_JOINED)
		adv = ADV_ACTIVE - m->advertised;

	hdr = buf_msg(skb);

	if (mtyp == GRP_JOIN_MSG) {
		msg_set_grp_bc_syncpt(hdr, grp->bc_snd_nxt);
		msg_set_adv_win(hdr, adv);
		m->advertised += adv;
	} else if (mtyp == GRP_ADV_MSG) {
		msg_set_adv_win(hdr, adv);
		m->advertised += adv;
	}
	__skb_queue_tail(xmitq, skb);
}

void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup,
			  struct tipc_msg *hdr, struct sk_buff_head *inputq,
			  struct sk_buff_head *xmitq)
{
	u32 node = msg_orignode(hdr);
	u32 port = msg_origport(hdr);
	struct tipc_member *m;

	if (!grp)
		return;

	m = tipc_group_find_member(grp, node, port);

	switch (msg_type(hdr)) {
	case GRP_JOIN_MSG:
		if (!m)
			m = tipc_group_create_member(grp, node, port,
						     MBR_QUARANTINED);
		if (!m)
			return;
		m->bc_rcv_nxt = msg_grp_bc_syncpt(hdr);
		m->window += msg_adv_win(hdr);

		/* Wait until PUBLISH event is received */
		if (m->state == MBR_DISCOVERED) {
			m->state = MBR_JOINING;
		} else if (m->state == MBR_PUBLISHED) {
			m->state = MBR_JOINED;
			*usr_wakeup = true;
			m->usr_pending = false;
			tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq);
			__skb_queue_tail(inputq, m->event_msg);
		}
		if (m->window < ADV_IDLE)
			tipc_group_update_member(m, 0);
		else
			list_del_init(&m->congested);
		return;
	case GRP_LEAVE_MSG:
		if (!m)
			return;

		/* Wait until WITHDRAW event is received */
		if (m->state != MBR_LEAVING) {
			m->state = MBR_LEAVING;
			return;
		}
		/* Otherwise deliver already received WITHDRAW event */
		__skb_queue_tail(inputq, m->event_msg);
		*usr_wakeup = m->usr_pending;
		tipc_group_delete_member(grp, m);
		list_del_init(&m->congested);
		return;
	case GRP_ADV_MSG:
		if (!m)
			return;
		m->window += msg_adv_win(hdr);
		*usr_wakeup = m->usr_pending;
		m->usr_pending = false;
		list_del_init(&m->congested);
		return;
	default:
		pr_warn("Received unknown GROUP_PROTO message\n");
	}
}

/* tipc_group_member_evt() - receive and handle a member up/down event
 */
void tipc_group_member_evt(struct tipc_group *grp,
			   bool *usr_wakeup,
			   int *sk_rcvbuf,
			   struct sk_buff *skb,
			   struct sk_buff_head *inputq,
			   struct sk_buff_head *xmitq)
{
	struct tipc_msg *hdr = buf_msg(skb);
	struct tipc_event *evt = (void *)msg_data(hdr);
	u32 instance = evt->found_lower;
	u32 node = evt->port.node;
	u32 port = evt->port.ref;
	int event = evt->event;
	struct tipc_member *m;
	struct net *net;
	u32 self;

	if (!grp)
		goto drop;

	net = grp->net;
	self = tipc_own_addr(net);
	if (!grp->loopback && node == self && port == grp->portid)
		goto drop;

	/* Convert message before delivery to user */
	msg_set_hdr_sz(hdr, GROUP_H_SIZE);
	msg_set_user(hdr, TIPC_CRITICAL_IMPORTANCE);
	msg_set_type(hdr, TIPC_GRP_MEMBER_EVT);
	msg_set_origport(hdr, port);
	msg_set_orignode(hdr, node);
	msg_set_nametype(hdr, grp->type);
	msg_set_grp_evt(hdr, event);

	m = tipc_group_find_member(grp, node, port);

	if (event == TIPC_PUBLISHED) {
		if (!m)
			m = tipc_group_create_member(grp, node, port,
						     MBR_DISCOVERED);
		if (!m)
			goto drop;

		/* Hold back event if JOIN message not yet received */
		if (m->state == MBR_DISCOVERED) {
			m->event_msg = skb;
			m->state = MBR_PUBLISHED;
		} else {
			__skb_queue_tail(inputq, skb);
			m->state = MBR_JOINED;
			*usr_wakeup = true;
			m->usr_pending = false;
		}
		m->instance = instance;
		TIPC_SKB_CB(skb)->orig_member = m->instance;
		tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq);
		if (m->window < ADV_IDLE)
			tipc_group_update_member(m, 0);
		else
			list_del_init(&m->congested);
	} else if (event == TIPC_WITHDRAWN) {
		if (!m)
			goto drop;

		TIPC_SKB_CB(skb)->orig_member = m->instance;

		*usr_wakeup = m->usr_pending;
		m->usr_pending = false;

		/* Hold back event if more messages might be expected */
		if (m->state != MBR_LEAVING && tipc_node_is_up(net, node)) {
			m->event_msg = skb;
			m->state = MBR_LEAVING;
		} else {
			__skb_queue_tail(inputq, skb);
			tipc_group_delete_member(grp, m);
		}
		list_del_init(&m->congested);
	}
	*sk_rcvbuf = tipc_group_rcvbuf_limit(grp);
	return;
drop:
	kfree_skb(skb);
}