aboutsummaryrefslogtreecommitdiffstats
path: root/fs/ocfs2/cluster/nodemanager.c
blob: af2070da308b87904c468988ba94cae0ee7cf8ae (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
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
/* -*- mode: c; c-basic-offset: 8; -*-
 * vim: noexpandtab sw=8 ts=8 sts=0:
 *
 * Copyright (C) 2004, 2005 Oracle.  All rights reserved.
 *
 * 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.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sysctl.h>
#include <linux/configfs.h>

#include "endian.h"
#include "tcp.h"
#include "nodemanager.h"
#include "heartbeat.h"
#include "masklog.h"
#include "sys.h"
#include "ver.h"

/* for now we operate under the assertion that there can be only one
 * cluster active at a time.  Changing this will require trickling
 * cluster references throughout where nodes are looked up */
struct o2nm_cluster *o2nm_single_cluster = NULL;

#define OCFS2_MAX_HB_CTL_PATH 256
static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl";

static ctl_table ocfs2_nm_table[] = {
	{
		.ctl_name	= 1,
		.procname	= "hb_ctl_path",
		.data		= ocfs2_hb_ctl_path,
		.maxlen		= OCFS2_MAX_HB_CTL_PATH,
		.mode		= 0644,
		.proc_handler	= &proc_dostring,
		.strategy	= &sysctl_string,
	},
	{ .ctl_name = 0 }
};

static ctl_table ocfs2_mod_table[] = {
	{
		.ctl_name	= FS_OCFS2_NM,
		.procname	= "nm",
		.data		= NULL,
		.maxlen		= 0,
		.mode		= 0555,
		.child		= ocfs2_nm_table
	},
	{ .ctl_name = 0}
};

static ctl_table ocfs2_kern_table[] = {
	{
		.ctl_name	= FS_OCFS2,
		.procname	= "ocfs2",
		.data		= NULL,
		.maxlen		= 0,
		.mode		= 0555,
		.child		= ocfs2_mod_table
	},
	{ .ctl_name = 0}
};

static ctl_table ocfs2_root_table[] = {
	{
		.ctl_name	= CTL_FS,
		.procname	= "fs",
		.data		= NULL,
		.maxlen		= 0,
		.mode		= 0555,
		.child		= ocfs2_kern_table
	},
	{ .ctl_name = 0 }
};

static struct ctl_table_header *ocfs2_table_header = NULL;

const char *o2nm_get_hb_ctl_path(void)
{
	return ocfs2_hb_ctl_path;
}
EXPORT_SYMBOL_GPL(o2nm_get_hb_ctl_path);

struct o2nm_node *o2nm_get_node_by_num(u8 node_num)
{
	struct o2nm_node *node = NULL;

	if (node_num >= O2NM_MAX_NODES || o2nm_single_cluster == NULL)
		goto out;

	read_lock(&o2nm_single_cluster->cl_nodes_lock);
	node = o2nm_single_cluster->cl_nodes[node_num];
	if (node)
		config_item_get(&node->nd_item);
	read_unlock(&o2nm_single_cluster->cl_nodes_lock);
out:
	return node;
}
EXPORT_SYMBOL_GPL(o2nm_get_node_by_num);

int o2nm_configured_node_map(unsigned long *map, unsigned bytes)
{
	struct o2nm_cluster *cluster = o2nm_single_cluster;

	BUG_ON(bytes < (sizeof(cluster->cl_nodes_bitmap)));

	if (cluster == NULL)
		return -EINVAL;

	read_lock(&cluster->cl_nodes_lock);
	memcpy(map, cluster->cl_nodes_bitmap, sizeof(cluster->cl_nodes_bitmap));
	read_unlock(&cluster->cl_nodes_lock);

	return 0;
}
EXPORT_SYMBOL_GPL(o2nm_configured_node_map);

static struct o2nm_node *o2nm_node_ip_tree_lookup(struct o2nm_cluster *cluster,
						  __be32 ip_needle,
						  struct rb_node ***ret_p,
						  struct rb_node **ret_parent)
{
	struct rb_node **p = &cluster->cl_node_ip_tree.rb_node;
	struct rb_node *parent = NULL;
	struct o2nm_node *node, *ret = NULL;

	while (*p) {
		int cmp;

		parent = *p;
		node = rb_entry(parent, struct o2nm_node, nd_ip_node);

		cmp = memcmp(&ip_needle, &node->nd_ipv4_address,
				sizeof(ip_needle));
		if (cmp < 0)
			p = &(*p)->rb_left;
		else if (cmp > 0)
			p = &(*p)->rb_right;
		else {
			ret = node;
			break;
		}
	}

	if (ret_p != NULL)
		*ret_p = p;
	if (ret_parent != NULL)
		*ret_parent = parent;

	return ret;
}

struct o2nm_node *o2nm_get_node_by_ip(__be32 addr)
{
	struct o2nm_node *node = NULL;
	struct o2nm_cluster *cluster = o2nm_single_cluster;

	if (cluster == NULL)
		goto out;

	read_lock(&cluster->cl_nodes_lock);
	node = o2nm_node_ip_tree_lookup(cluster, addr, NULL, NULL);
	if (node)
		config_item_get(&node->nd_item);
	read_unlock(&cluster->cl_nodes_lock);

out:
	return node;
}
EXPORT_SYMBOL_GPL(o2nm_get_node_by_ip);

void o2nm_node_put(struct o2nm_node *node)
{
	config_item_put(&node->nd_item);
}
EXPORT_SYMBOL_GPL(o2nm_node_put);

void o2nm_node_get(struct o2nm_node *node)
{
	config_item_get(&node->nd_item);
}
EXPORT_SYMBOL_GPL(o2nm_node_get);

u8 o2nm_this_node(void)
{
	u8 node_num = O2NM_MAX_NODES;

	if (o2nm_single_cluster && o2nm_single_cluster->cl_has_local)
		node_num = o2nm_single_cluster->cl_local_node;

	return node_num;
}
EXPORT_SYMBOL_GPL(o2nm_this_node);

/* node configfs bits */

static struct o2nm_cluster *to_o2nm_cluster(struct config_item *item)
{
	return item ?
		container_of(to_config_group(item), struct o2nm_cluster,
			     cl_group)
		: NULL;
}

static struct o2nm_node *to_o2nm_node(struct config_item *item)
{
	return item ? container_of(item, struct o2nm_node, nd_item) : NULL;
}

static void o2nm_node_release(struct config_item *item)
{
	struct o2nm_node *node = to_o2nm_node(item);
	kfree(node);
}

static ssize_t o2nm_node_num_read(struct o2nm_node *node, char *page)
{
	return sprintf(page, "%d\n", node->nd_num);
}

static struct o2nm_cluster *to_o2nm_cluster_from_node(struct o2nm_node *node)
{
	/* through the first node_set .parent
	 * mycluster/nodes/mynode == o2nm_cluster->o2nm_node_group->o2nm_node */
	return to_o2nm_cluster(node->nd_item.ci_parent->ci_parent);
}

enum {
	O2NM_NODE_ATTR_NUM = 0,
	O2NM_NODE_ATTR_PORT,
	O2NM_NODE_ATTR_ADDRESS,
	O2NM_NODE_ATTR_LOCAL,
};

static ssize_t o2nm_node_num_write(struct o2nm_node *node, const char *page,
				   size_t count)
{
	struct o2nm_cluster *cluster = to_o2nm_cluster_from_node(node);
	unsigned long tmp;
	char *p = (char *)page;

	tmp = simple_strtoul(p, &p, 0);
	if (!p || (*p && (*p != '\n')))
		return -EINVAL;

	if (tmp >= O2NM_MAX_NODES)
		return -ERANGE;

	/* once we're in the cl_nodes tree networking can look us up by
	 * node number and try to use our address and port attributes
	 * to connect to this node.. make sure that they've been set
	 * before writing the node attribute? */
	if (!test_bit(O2NM_NODE_ATTR_ADDRESS, &node->nd_set_attributes) ||
	    !test_bit(O2NM_NODE_ATTR_PORT, &node->nd_set_attributes))
		return -EINVAL; /* XXX */

	write_lock(&cluster->cl_nodes_lock);
	if (cluster->cl_nodes[tmp])
		p = NULL;
	else  {
		cluster->cl_nodes[tmp] = node;
		node->nd_num = tmp;
		set_bit(tmp, cluster->cl_nodes_bitmap);
	}
	write_unlock(&cluster->cl_nodes_lock);
	if (p == NULL)
		return -EEXIST;

	return count;
}
static ssize_t o2nm_node_ipv4_port_read(struct o2nm_node *node, char *page)
{
	return sprintf(page, "%u\n", ntohs(node->nd_ipv4_port));
}

static ssize_t o2nm_node_ipv4_port_write(struct o2nm_node *node,
					 const char *page, size_t count)
{
	unsigned long tmp;
	char *p = (char *)page;

	tmp = simple_strtoul(p, &p, 0);
	if (!p || (*p && (*p != '\n')))
		return -EINVAL;

	if (tmp == 0)
		return -EINVAL;
	if (tmp >= (u16)-1)
		return -ERANGE;

	node->nd_ipv4_port = htons(tmp);

	return count;
}

static ssize_t o2nm_node_ipv4_address_read(struct o2nm_node *node, char *page)
{
	return sprintf(page, "%u.%u.%u.%u\n", NIPQUAD(node->nd_ipv4_address));
}

static ssize_t o2nm_node_ipv4_address_write(struct o2nm_node *node,
					    const char *page,
					    size_t count)
{
	struct o2nm_cluster *cluster = to_o2nm_cluster_from_node(node);
	int ret, i;
	struct rb_node **p, *parent;
	unsigned int octets[4];
	__be32 ipv4_addr = 0;

	ret = sscanf(page, "%3u.%3u.%3u.%3u", &octets[3], &octets[2],
		     &octets[1], &octets[0]);
	if (ret != 4)
		return -EINVAL;

	for (i = 0; i < ARRAY_SIZE(octets); i++) {
		if (octets[i] > 255)
			return -ERANGE;
		be32_add_cpu(&ipv4_addr, octets[i] << (i * 8));
	}

	ret = 0;
	write_lock(&cluster->cl_nodes_lock);
	if (o2nm_node_ip_tree_lookup(cluster, ipv4_addr, &p, &parent))
		ret = -EEXIST;
	else {
		rb_link_node(&node->nd_ip_node, parent, p);
		rb_insert_color(&node->nd_ip_node, &cluster->cl_node_ip_tree);
	}
	write_unlock(&cluster->cl_nodes_lock);
	if (ret)
		return ret;

	memcpy(&node->nd_ipv4_address, &ipv4_addr, sizeof(ipv4_addr));

	return count;
}

static ssize_t o2nm_node_local_read(struct o2nm_node *node, char *page)
{
	return sprintf(page, "%d\n", node->nd_local);
}

static ssize_t o2nm_node_local_write(struct o2nm_node *node, const char *page,
				     size_t count)
{
	struct o2nm_cluster *cluster = to_o2nm_cluster_from_node(node);
	unsigned long tmp;
	char *p = (char *)page;
	ssize_t ret;

	tmp = simple_strtoul(p, &p, 0);
	if (!p || (*p && (*p != '\n')))
		return -EINVAL;

	tmp = !!tmp; /* boolean of whether this node wants to be local */

	/* setting local turns on networking rx for now so we require having
	 * set everything else first */
	if (!test_bit(O2NM_NODE_ATTR_ADDRESS, &node->nd_set_attributes) ||
	    !test_bit(O2NM_NODE_ATTR_NUM, &node->nd_set_attributes) ||
	    !test_bit(O2NM_NODE_ATTR_PORT, &node->nd_set_attributes))
		return -EINVAL; /* XXX */

	/* the only failure case is trying to set a new local node
	 * when a different one is already set */
	if (tmp && tmp == cluster->cl_has_local &&
	    cluster->cl_local_node != node->nd_num)
		return -EBUSY;

	/* bring up the rx thread if we're setting the new local node. */
	if (tmp && !cluster->cl_has_local) {
		ret = o2net_start_listening(node);
		if (ret)
			return ret;
	}

	if (!tmp && cluster->cl_has_local &&
	    cluster->cl_local_node == node->nd_num) {
		o2net_stop_listening(node);
		cluster->cl_local_node = O2NM_INVALID_NODE_NUM;
	}

	node->nd_local = tmp;
	if (node->nd_local) {
		cluster->cl_has_local = tmp;
		cluster->cl_local_node = node->nd_num;
	}

	return count;
}

struct o2nm_node_attribute {
	struct configfs_attribute attr;
	ssize_t (*show)(struct o2nm_node *, char *);
	ssize_t (*store)(struct o2nm_node *, const char *, size_t);
};

static struct o2nm_node_attribute o2nm_node_attr_num = {
	.attr	= { .ca_owner = THIS_MODULE,
		    .ca_name = "num",
		    .ca_mode = S_IRUGO | S_IWUSR },
	.show	= o2nm_node_num_read,
	.store	= o2nm_node_num_write,
};

static struct o2nm_node_attribute o2nm_node_attr_ipv4_port = {
	.attr	= { .ca_owner = THIS_MODULE,
		    .ca_name = "ipv4_port",
		    .ca_mode = S_IRUGO | S_IWUSR },
	.show	= o2nm_node_ipv4_port_read,
	.store	= o2nm_node_ipv4_port_write,
};

static struct o2nm_node_attribute o2nm_node_attr_ipv4_address = {
	.attr	= { .ca_owner = THIS_MODULE,
		    .ca_name = "ipv4_address",
		    .ca_mode = S_IRUGO | S_IWUSR },
	.show	= o2nm_node_ipv4_address_read,
	.store	= o2nm_node_ipv4_address_write,
};

static struct o2nm_node_attribute o2nm_node_attr_local = {
	.attr	= { .ca_owner = THIS_MODULE,
		    .ca_name = "local",
		    .ca_mode = S_IRUGO | S_IWUSR },
	.show	= o2nm_node_local_read,
	.store	= o2nm_node_local_write,
};

static struct configfs_attribute *o2nm_node_attrs[] = {
	[O2NM_NODE_ATTR_NUM] = &o2nm_node_attr_num.attr,
	[O2NM_NODE_ATTR_PORT] = &o2nm_node_attr_ipv4_port.attr,
	[O2NM_NODE_ATTR_ADDRESS] = &o2nm_node_attr_ipv4_address.attr,
	[O2NM_NODE_ATTR_LOCAL] = &o2nm_node_attr_local.attr,
	NULL,
};

static int o2nm_attr_index(struct configfs_attribute *attr)
{
	int i;
	for (i = 0; i < ARRAY_SIZE(o2nm_node_attrs); i++) {
		if (attr == o2nm_node_attrs[i])
			return i;
	}
	BUG();
	return 0;
}

static ssize_t o2nm_node_show(struct config_item *item,
			      struct configfs_attribute *attr,
			      char *page)
{
	struct o2nm_node *node = to_o2nm_node(item);
	struct o2nm_node_attribute *o2nm_node_attr =
		container_of(attr, struct o2nm_node_attribute, attr);
	ssize_t ret = 0;

	if (o2nm_node_attr->show)
		ret = o2nm_node_attr->show(node, page);
	return ret;
}

static ssize_t o2nm_node_store(struct config_item *item,
			       struct configfs_attribute *attr,
			       const char *page, size_t count)
{
	struct o2nm_node *node = to_o2nm_node(item);
	struct o2nm_node_attribute *o2nm_node_attr =
		container_of(attr, struct o2nm_node_attribute, attr);
	ssize_t ret;
	int attr_index = o2nm_attr_index(attr);

	if (o2nm_node_attr->store == NULL) {
		ret = -EINVAL;
		goto out;
	}

	if (test_bit(attr_index, &node->nd_set_attributes))
		return -EBUSY;

	ret = o2nm_node_attr->store(node, page, count);
	if (ret < count)
		goto out;

	set_bit(attr_index, &node->nd_set_attributes);
out:
	return ret;
}

static struct configfs_item_operations o2nm_node_item_ops = {
	.release		= o2nm_node_release,
	.show_attribute		= o2nm_node_show,
	.store_attribute	= o2nm_node_store,
};

static struct config_item_type o2nm_node_type = {
	.ct_item_ops	= &o2nm_node_item_ops,
	.ct_attrs	= o2nm_node_attrs,
	.ct_owner	= THIS_MODULE,
};

/* node set */

struct o2nm_node_group {
	struct config_group ns_group;
	/* some stuff? */
};

#if 0
static struct o2nm_node_group *to_o2nm_node_group(struct config_group *group)
{
	return group ?
		container_of(group, struct o2nm_node_group, ns_group)
		: NULL;
}
#endif

struct o2nm_cluster_attribute {
	struct configfs_attribute attr;
	ssize_t (*show)(struct o2nm_cluster *, char *);
	ssize_t (*store)(struct o2nm_cluster *, const char *, size_t);
};

static ssize_t o2nm_cluster_attr_write(const char *page, ssize_t count,
                                       unsigned int *val)
{
	unsigned long tmp;
	char *p = (char *)page;

	tmp = simple_strtoul(p, &p, 0);
	if (!p || (*p && (*p != '\n')))
		return -EINVAL;

	if (tmp == 0)
		return -EINVAL;
	if (tmp >= (u32)-1)
		return -ERANGE;

	*val = tmp;

	return count;
}

static ssize_t o2nm_cluster_attr_idle_timeout_ms_read(
	struct o2nm_cluster *cluster, char *page)
{
	return sprintf(page, "%u\n", cluster->cl_idle_timeout_ms);
}

static ssize_t o2nm_cluster_attr_idle_timeout_ms_write(
	struct o2nm_cluster *cluster, const char *page, size_t count)
{
	ssize_t ret;
	unsigned int val;

	ret =  o2nm_cluster_attr_write(page, count, &val);

	if (ret > 0) {
		if (cluster->cl_idle_timeout_ms != val
			&& o2net_num_connected_peers()) {
			mlog(ML_NOTICE,
			     "o2net: cannot change idle timeout after "
			     "the first peer has agreed to it."
			     "  %d connected peers\n",
			     o2net_num_connected_peers());
			ret = -EINVAL;
		} else if (val <= cluster->cl_keepalive_delay_ms) {
			mlog(ML_NOTICE, "o2net: idle timeout must be larger "
			     "than keepalive delay\n");
			ret = -EINVAL;
		} else {
			cluster->cl_idle_timeout_ms = val;
		}
	}

	return ret;
}

static ssize_t o2nm_cluster_attr_keepalive_delay_ms_read(
	struct o2nm_cluster *cluster, char *page)
{
	return sprintf(page, "%u\n", cluster->cl_keepalive_delay_ms);
}

static ssize_t o2nm_cluster_attr_keepalive_delay_ms_write(
	struct o2nm_cluster *cluster, const char *page, size_t count)
{
	ssize_t ret;
	unsigned int val;

	ret =  o2nm_cluster_attr_write(page, count, &val);

	if (ret > 0) {
		if (cluster->cl_keepalive_delay_ms != val
		    && o2net_num_connected_peers()) {
			mlog(ML_NOTICE,
			     "o2net: cannot change keepalive delay after"
			     " the first peer has agreed to it."
			     "  %d connected peers\n",
			     o2net_num_connected_peers());
			ret = -EINVAL;
		} else if (val >= cluster->cl_idle_timeout_ms) {
			mlog(ML_NOTICE, "o2net: keepalive delay must be "
			     "smaller than idle timeout\n");
			ret = -EINVAL;
		} else {
			cluster->cl_keepalive_delay_ms = val;
		}
	}

	return ret;
}

static ssize_t o2nm_cluster_attr_reconnect_delay_ms_read(
	struct o2nm_cluster *cluster, char *page)
{
	return sprintf(page, "%u\n", cluster->cl_reconnect_delay_ms);
}

static ssize_t o2nm_cluster_attr_reconnect_delay_ms_write(
	struct o2nm_cluster *cluster, const char *page, size_t count)
{
	return o2nm_cluster_attr_write(page, count,
	                               &cluster->cl_reconnect_delay_ms);
}
static struct o2nm_cluster_attribute o2nm_cluster_attr_idle_timeout_ms = {
	.attr	= { .ca_owner = THIS_MODULE,
		    .ca_name = "idle_timeout_ms",
		    .ca_mode = S_IRUGO | S_IWUSR },
	.show	= o2nm_cluster_attr_idle_timeout_ms_read,
	.store	= o2nm_cluster_attr_idle_timeout_ms_write,
};

static struct o2nm_cluster_attribute o2nm_cluster_attr_keepalive_delay_ms = {
	.attr	= { .ca_owner = THIS_MODULE,
		    .ca_name = "keepalive_delay_ms",
		    .ca_mode = S_IRUGO | S_IWUSR },
	.show	= o2nm_cluster_attr_keepalive_delay_ms_read,
	.store	= o2nm_cluster_attr_keepalive_delay_ms_write,
};

static struct o2nm_cluster_attribute o2nm_cluster_attr_reconnect_delay_ms = {
	.attr	= { .ca_owner = THIS_MODULE,
		    .ca_name = "reconnect_delay_ms",
		    .ca_mode = S_IRUGO | S_IWUSR },
	.show	= o2nm_cluster_attr_reconnect_delay_ms_read,
	.store	= o2nm_cluster_attr_reconnect_delay_ms_write,
};

static struct configfs_attribute *o2nm_cluster_attrs[] = {
	&o2nm_cluster_attr_idle_timeout_ms.attr,
	&o2nm_cluster_attr_keepalive_delay_ms.attr,
	&o2nm_cluster_attr_reconnect_delay_ms.attr,
	NULL,
};
static ssize_t o2nm_cluster_show(struct config_item *item,
                                 struct configfs_attribute *attr,
                                 char *page)
{
	struct o2nm_cluster *cluster = to_o2nm_cluster(item);
	struct o2nm_cluster_attribute *o2nm_cluster_attr =
		container_of(attr, struct o2nm_cluster_attribute, attr);
	ssize_t ret = 0;

	if (o2nm_cluster_attr->show)
		ret = o2nm_cluster_attr->show(cluster, page);
	return ret;
}

static ssize_t o2nm_cluster_store(struct config_item *item,
                                  struct configfs_attribute *attr,
                                  const char *page, size_t count)
{
	struct o2nm_cluster *cluster = to_o2nm_cluster(item);
	struct o2nm_cluster_attribute *o2nm_cluster_attr =
		container_of(attr, struct o2nm_cluster_attribute, attr);
	ssize_t ret;

	if (o2nm_cluster_attr->store == NULL) {
		ret = -EINVAL;
		goto out;
	}

	ret = o2nm_cluster_attr->store(cluster, page, count);
	if (ret < count)
		goto out;
out:
	return ret;
}

static struct config_item *o2nm_node_group_make_item(struct config_group *group,
						     const char *name)
{
	struct o2nm_node *node = NULL;
	struct config_item *ret = NULL;

	if (strlen(name) > O2NM_MAX_NAME_LEN)
		goto out; /* ENAMETOOLONG */

	node = kzalloc(sizeof(struct o2nm_node), GFP_KERNEL);
	if (node == NULL)
		goto out; /* ENOMEM */

	strcpy(node->nd_name, name); /* use item.ci_namebuf instead? */
	config_item_init_type_name(&node->nd_item, name, &o2nm_node_type);
	spin_lock_init(&node->nd_lock);

	ret = &node->nd_item;

out:
	if (ret == NULL)
		kfree(node);

	return ret;
}

static void o2nm_node_group_drop_item(struct config_group *group,
				      struct config_item *item)
{
	struct o2nm_node *node = to_o2nm_node(item);
	struct o2nm_cluster *cluster = to_o2nm_cluster(group->cg_item.ci_parent);

	o2net_disconnect_node(node);

	if (cluster->cl_has_local &&
	    (cluster->cl_local_node == node->nd_num)) {
		cluster->cl_has_local = 0;
		cluster->cl_local_node = O2NM_INVALID_NODE_NUM;
		o2net_stop_listening(node);
	}

	/* XXX call into net to stop this node from trading messages */

	write_lock(&cluster->cl_nodes_lock);

	/* XXX sloppy */
	if (node->nd_ipv4_address)
		rb_erase(&node->nd_ip_node, &cluster->cl_node_ip_tree);

	/* nd_num might be 0 if the node number hasn't been set.. */
	if (cluster->cl_nodes[node->nd_num] == node) {
		cluster->cl_nodes[node->nd_num] = NULL;
		clear_bit(node->nd_num, cluster->cl_nodes_bitmap);
	}
	write_unlock(&cluster->cl_nodes_lock);

	config_item_put(item);
}

static struct configfs_group_operations o2nm_node_group_group_ops = {
	.make_item	= o2nm_node_group_make_item,
	.drop_item	= o2nm_node_group_drop_item,
};

static struct config_item_type o2nm_node_group_type = {
	.ct_group_ops	= &o2nm_node_group_group_ops,
	.ct_owner	= THIS_MODULE,
};

/* cluster */

static void o2nm_cluster_release(struct config_item *item)
{
	struct o2nm_cluster *cluster = to_o2nm_cluster(item);

	kfree(cluster->cl_group.default_groups);
	kfree(cluster);
}

static struct configfs_item_operations o2nm_cluster_item_ops = {
	.release	= o2nm_cluster_release,
	.show_attribute		= o2nm_cluster_show,
	.store_attribute	= o2nm_cluster_store,
};

static struct config_item_type o2nm_cluster_type = {
	.ct_item_ops	= &o2nm_cluster_item_ops,
	.ct_attrs	= o2nm_cluster_attrs,
	.ct_owner	= THIS_MODULE,
};

/* cluster set */

struct o2nm_cluster_group {
	struct configfs_subsystem cs_subsys;
	/* some stuff? */
};

#if 0
static struct o2nm_cluster_group *to_o2nm_cluster_group(struct config_group *group)
{
	return group ?
		container_of(to_configfs_subsystem(group), struct o2nm_cluster_group, cs_subsys)
	       : NULL;
}
#endif

static struct config_group *o2nm_cluster_group_make_group(struct config_group *group,
							  const char *name)
{
	struct o2nm_cluster *cluster = NULL;
	struct o2nm_node_group *ns = NULL;
	struct config_group *o2hb_group = NULL, *ret = NULL;
	void *defs = NULL;

	/* this runs under the parent dir's i_mutex; there can be only
	 * one caller in here at a time */
	if (o2nm_single_cluster)
		goto out; /* ENOSPC */

	cluster = kzalloc(sizeof(struct o2nm_cluster), GFP_KERNEL);
	ns = kzalloc(sizeof(struct o2nm_node_group), GFP_KERNEL);
	defs = kcalloc(3, sizeof(struct config_group *), GFP_KERNEL);
	o2hb_group = o2hb_alloc_hb_set();
	if (cluster == NULL || ns == NULL || o2hb_group == NULL || defs == NULL)
		goto out;

	config_group_init_type_name(&cluster->cl_group, name,
				    &o2nm_cluster_type);
	config_group_init_type_name(&ns->ns_group, "node",
				    &o2nm_node_group_type);

	cluster->cl_group.default_groups = defs;
	cluster->cl_group.default_groups[0] = &ns->ns_group;
	cluster->cl_group.default_groups[1] = o2hb_group;
	cluster->cl_group.default_groups[2] = NULL;
	rwlock_init(&cluster->cl_nodes_lock);
	cluster->cl_node_ip_tree = RB_ROOT;
	cluster->cl_reconnect_delay_ms = O2NET_RECONNECT_DELAY_MS_DEFAULT;
	cluster->cl_idle_timeout_ms    = O2NET_IDLE_TIMEOUT_MS_DEFAULT;
	cluster->cl_keepalive_delay_ms = O2NET_KEEPALIVE_DELAY_MS_DEFAULT;

	ret = &cluster->cl_group;
	o2nm_single_cluster = cluster;

out:
	if (ret == NULL) {
		kfree(cluster);
		kfree(ns);
		o2hb_free_hb_set(o2hb_group);
		kfree(defs);
	}

	return ret;
}

static void o2nm_cluster_group_drop_item(struct config_group *group, struct config_item *item)
{
	struct o2nm_cluster *cluster = to_o2nm_cluster(item);
	int i;
	struct config_item *killme;

	BUG_ON(o2nm_single_cluster != cluster);
	o2nm_single_cluster = NULL;

	for (i = 0; cluster->cl_group.default_groups[i]; i++) {
		killme = &cluster->cl_group.default_groups[i]->cg_item;
		cluster->cl_group.default_groups[i] = NULL;
		config_item_put(killme);
	}

	config_item_put(item);
}

static struct configfs_group_operations o2nm_cluster_group_group_ops = {
	.make_group	= o2nm_cluster_group_make_group,
	.drop_item	= o2nm_cluster_group_drop_item,
};

static struct config_item_type o2nm_cluster_group_type = {
	.ct_group_ops	= &o2nm_cluster_group_group_ops,
	.ct_owner	= THIS_MODULE,
};

static struct o2nm_cluster_group o2nm_cluster_group = {
	.cs_subsys = {
		.su_group = {
			.cg_item = {
				.ci_namebuf = "cluster",
				.ci_type = &o2nm_cluster_group_type,
			},
		},
	},
};

int o2nm_depend_item(struct config_item *item)
{
	return configfs_depend_item(&o2nm_cluster_group.cs_subsys, item);
}

void o2nm_undepend_item(struct config_item *item)
{
	configfs_undepend_item(&o2nm_cluster_group.cs_subsys, item);
}

int o2nm_depend_this_node(void)
{
	int ret = 0;
	struct o2nm_node *local_node;

	local_node = o2nm_get_node_by_num(o2nm_this_node());
	if (!local_node) {
		ret = -EINVAL;
		goto out;
	}

	ret = o2nm_depend_item(&local_node->nd_item);
	o2nm_node_put(local_node);

out:
	return ret;
}

void o2nm_undepend_this_node(void)
{
	struct o2nm_node *local_node;

	local_node = o2nm_get_node_by_num(o2nm_this_node());
	BUG_ON(!local_node);

	o2nm_undepend_item(&local_node->nd_item);
	o2nm_node_put(local_node);
}


static void __exit exit_o2nm(void)
{
	if (ocfs2_table_header)
		unregister_sysctl_table(ocfs2_table_header);

	/* XXX sync with hb callbacks and shut down hb? */
	o2net_unregister_hb_callbacks();
	configfs_unregister_subsystem(&o2nm_cluster_group.cs_subsys);
	o2cb_sys_shutdown();

	o2net_exit();
}

static int __init init_o2nm(void)
{
	int ret = -1;

	cluster_print_version();

	o2hb_init();
	o2net_init();

	ocfs2_table_header = register_sysctl_table(ocfs2_root_table);
	if (!ocfs2_table_header) {
		printk(KERN_ERR "nodemanager: unable to register sysctl\n");
		ret = -ENOMEM; /* or something. */
		goto out_o2net;
	}

	ret = o2net_register_hb_callbacks();
	if (ret)
		goto out_sysctl;

	config_group_init(&o2nm_cluster_group.cs_subsys.su_group);
	mutex_init(&o2nm_cluster_group.cs_subsys.su_mutex);
	ret = configfs_register_subsystem(&o2nm_cluster_group.cs_subsys);
	if (ret) {
		printk(KERN_ERR "nodemanager: Registration returned %d\n", ret);
		goto out_callbacks;
	}

	ret = o2cb_sys_init();
	if (!ret)
		goto out;

	configfs_unregister_subsystem(&o2nm_cluster_group.cs_subsys);
out_callbacks:
	o2net_unregister_hb_callbacks();
out_sysctl:
	unregister_sysctl_table(ocfs2_table_header);
out_o2net:
	o2net_exit();
out:
	return ret;
}

MODULE_AUTHOR("Oracle");
MODULE_LICENSE("GPL");

module_init(init_o2nm)
module_exit(exit_o2nm)