summaryrefslogtreecommitdiffstats
path: root/fs/dlm/lockspace.c
blob: 3ca79d3253b9b195e698084f76cc23e686b5a0a7 (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
/******************************************************************************
*******************************************************************************
**
**  Copyright (C) Sistina Software, Inc.  1997-2003  All rights reserved.
**  Copyright (C) 2004-2011 Red Hat, Inc.  All rights reserved.
**
**  This copyrighted material is made available to anyone wishing to use,
**  modify, copy, or redistribute it subject to the terms and conditions
**  of the GNU General Public License v.2.
**
*******************************************************************************
******************************************************************************/

#include "dlm_internal.h"
#include "lockspace.h"
#include "member.h"
#include "recoverd.h"
#include "dir.h"
#include "lowcomms.h"
#include "config.h"
#include "memory.h"
#include "lock.h"
#include "recover.h"
#include "requestqueue.h"
#include "user.h"
#include "ast.h"

static int			ls_count;
static struct mutex		ls_lock;
static struct list_head		lslist;
static spinlock_t		lslist_lock;
static struct task_struct *	scand_task;


static ssize_t dlm_control_store(struct dlm_ls *ls, const char *buf, size_t len)
{
	ssize_t ret = len;
	int n = simple_strtol(buf, NULL, 0);

	ls = dlm_find_lockspace_local(ls->ls_local_handle);
	if (!ls)
		return -EINVAL;

	switch (n) {
	case 0:
		dlm_ls_stop(ls);
		break;
	case 1:
		dlm_ls_start(ls);
		break;
	default:
		ret = -EINVAL;
	}
	dlm_put_lockspace(ls);
	return ret;
}

static ssize_t dlm_event_store(struct dlm_ls *ls, const char *buf, size_t len)
{
	ls->ls_uevent_result = simple_strtol(buf, NULL, 0);
	set_bit(LSFL_UEVENT_WAIT, &ls->ls_flags);
	wake_up(&ls->ls_uevent_wait);
	return len;
}

static ssize_t dlm_id_show(struct dlm_ls *ls, char *buf)
{
	return snprintf(buf, PAGE_SIZE, "%u\n", ls->ls_global_id);
}

static ssize_t dlm_id_store(struct dlm_ls *ls, const char *buf, size_t len)
{
	ls->ls_global_id = simple_strtoul(buf, NULL, 0);
	return len;
}

static ssize_t dlm_nodir_show(struct dlm_ls *ls, char *buf)
{
	return snprintf(buf, PAGE_SIZE, "%u\n", dlm_no_directory(ls));
}

static ssize_t dlm_nodir_store(struct dlm_ls *ls, const char *buf, size_t len)
{
	int val = simple_strtoul(buf, NULL, 0);
	if (val == 1)
		set_bit(LSFL_NODIR, &ls->ls_flags);
	return len;
}

static ssize_t dlm_recover_status_show(struct dlm_ls *ls, char *buf)
{
	uint32_t status = dlm_recover_status(ls);
	return snprintf(buf, PAGE_SIZE, "%x\n", status);
}

static ssize_t dlm_recover_nodeid_show(struct dlm_ls *ls, char *buf)
{
	return snprintf(buf, PAGE_SIZE, "%d\n", ls->ls_recover_nodeid);
}

struct dlm_attr {
	struct attribute attr;
	ssize_t (*show)(struct dlm_ls *, char *);
	ssize_t (*store)(struct dlm_ls *, const char *, size_t);
};

static struct dlm_attr dlm_attr_control = {
	.attr  = {.name = "control", .mode = S_IWUSR},
	.store = dlm_control_store
};

static struct dlm_attr dlm_attr_event = {
	.attr  = {.name = "event_done", .mode = S_IWUSR},
	.store = dlm_event_store
};

static struct dlm_attr dlm_attr_id = {
	.attr  = {.name = "id", .mode = S_IRUGO | S_IWUSR},
	.show  = dlm_id_show,
	.store = dlm_id_store
};

static struct dlm_attr dlm_attr_nodir = {
	.attr  = {.name = "nodir", .mode = S_IRUGO | S_IWUSR},
	.show  = dlm_nodir_show,
	.store = dlm_nodir_store
};

static struct dlm_attr dlm_attr_recover_status = {
	.attr  = {.name = "recover_status", .mode = S_IRUGO},
	.show  = dlm_recover_status_show
};

static struct dlm_attr dlm_attr_recover_nodeid = {
	.attr  = {.name = "recover_nodeid", .mode = S_IRUGO},
	.show  = dlm_recover_nodeid_show
};

static struct attribute *dlm_attrs[] = {
	&dlm_attr_control.attr,
	&dlm_attr_event.attr,
	&dlm_attr_id.attr,
	&dlm_attr_nodir.attr,
	&dlm_attr_recover_status.attr,
	&dlm_attr_recover_nodeid.attr,
	NULL,
};

static ssize_t dlm_attr_show(struct kobject *kobj, struct attribute *attr,
			     char *buf)
{
	struct dlm_ls *ls  = container_of(kobj, struct dlm_ls, ls_kobj);
	struct dlm_attr *a = container_of(attr, struct dlm_attr, attr);
	return a->show ? a->show(ls, buf) : 0;
}

static ssize_t dlm_attr_store(struct kobject *kobj, struct attribute *attr,
			      const char *buf, size_t len)
{
	struct dlm_ls *ls  = container_of(kobj, struct dlm_ls, ls_kobj);
	struct dlm_attr *a = container_of(attr, struct dlm_attr, attr);
	return a->store ? a->store(ls, buf, len) : len;
}

static void lockspace_kobj_release(struct kobject *k)
{
	struct dlm_ls *ls  = container_of(k, struct dlm_ls, ls_kobj);
	kfree(ls);
}

static const struct sysfs_ops dlm_attr_ops = {
	.show  = dlm_attr_show,
	.store = dlm_attr_store,
};

static struct kobj_type dlm_ktype = {
	.default_attrs = dlm_attrs,
	.sysfs_ops     = &dlm_attr_ops,
	.release       = lockspace_kobj_release,
};

static struct kset *dlm_kset;

static int do_uevent(struct dlm_ls *ls, int in)
{
	int error;

	if (in)
		kobject_uevent(&ls->ls_kobj, KOBJ_ONLINE);
	else
		kobject_uevent(&ls->ls_kobj, KOBJ_OFFLINE);

	log_debug(ls, "%s the lockspace group...", in ? "joining" : "leaving");

	/* dlm_controld will see the uevent, do the necessary group management
	   and then write to sysfs to wake us */

	error = wait_event_interruptible(ls->ls_uevent_wait,
			test_and_clear_bit(LSFL_UEVENT_WAIT, &ls->ls_flags));

	log_debug(ls, "group event done %d %d", error, ls->ls_uevent_result);

	if (error)
		goto out;

	error = ls->ls_uevent_result;
 out:
	if (error)
		log_error(ls, "group %s failed %d %d", in ? "join" : "leave",
			  error, ls->ls_uevent_result);
	return error;
}

static int dlm_uevent(struct kset *kset, struct kobject *kobj,
		      struct kobj_uevent_env *env)
{
	struct dlm_ls *ls = container_of(kobj, struct dlm_ls, ls_kobj);

	add_uevent_var(env, "LOCKSPACE=%s", ls->ls_name);
	return 0;
}

static struct kset_uevent_ops dlm_uevent_ops = {
	.uevent = dlm_uevent,
};

int __init dlm_lockspace_init(void)
{
	ls_count = 0;
	mutex_init(&ls_lock);
	INIT_LIST_HEAD(&lslist);
	spin_lock_init(&lslist_lock);

	dlm_kset = kset_create_and_add("dlm", &dlm_uevent_ops, kernel_kobj);
	if (!dlm_kset) {
		printk(KERN_WARNING "%s: can not create kset\n", __func__);
		return -ENOMEM;
	}
	return 0;
}

void dlm_lockspace_exit(void)
{
	kset_unregister(dlm_kset);
}

static struct dlm_ls *find_ls_to_scan(void)
{
	struct dlm_ls *ls;

	spin_lock(&lslist_lock);
	list_for_each_entry(ls, &lslist, ls_list) {
		if (time_after_eq(jiffies, ls->ls_scan_time +
					    dlm_config.ci_scan_secs * HZ)) {
			spin_unlock(&lslist_lock);
			return ls;
		}
	}
	spin_unlock(&lslist_lock);
	return NULL;
}

static int dlm_scand(void *data)
{
	struct dlm_ls *ls;

	while (!kthread_should_stop()) {
		ls = find_ls_to_scan();
		if (ls) {
			if (dlm_lock_recovery_try(ls)) {
				ls->ls_scan_time = jiffies;
				dlm_scan_rsbs(ls);
				dlm_scan_timeout(ls);
				dlm_scan_waiters(ls);
				dlm_unlock_recovery(ls);
			} else {
				ls->ls_scan_time += HZ;
			}
			continue;
		}
		schedule_timeout_interruptible(dlm_config.ci_scan_secs * HZ);
	}
	return 0;
}

static int dlm_scand_start(void)
{
	struct task_struct *p;
	int error = 0;

	p = kthread_run(dlm_scand, NULL, "dlm_scand");
	if (IS_ERR(p))
		error = PTR_ERR(p);
	else
		scand_task = p;
	return error;
}

static void dlm_scand_stop(void)
{
	kthread_stop(scand_task);
}

struct dlm_ls *dlm_find_lockspace_global(uint32_t id)
{
	struct dlm_ls *ls;

	spin_lock(&lslist_lock);

	list_for_each_entry(ls, &lslist, ls_list) {
		if (ls->ls_global_id == id) {
			ls->ls_count++;
			goto out;
		}
	}
	ls = NULL;
 out:
	spin_unlock(&lslist_lock);
	return ls;
}

struct dlm_ls *dlm_find_lockspace_local(dlm_lockspace_t *lockspace)
{
	struct dlm_ls *ls;

	spin_lock(&lslist_lock);
	list_for_each_entry(ls, &lslist, ls_list) {
		if (ls->ls_local_handle == lockspace) {
			ls->ls_count++;
			goto out;
		}
	}
	ls = NULL;
 out:
	spin_unlock(&lslist_lock);
	return ls;
}

struct dlm_ls *dlm_find_lockspace_device(int minor)
{
	struct dlm_ls *ls;

	spin_lock(&lslist_lock);
	list_for_each_entry(ls, &lslist, ls_list) {
		if (ls->ls_device.minor == minor) {
			ls->ls_count++;
			goto out;
		}
	}
	ls = NULL;
 out:
	spin_unlock(&lslist_lock);
	return ls;
}

void dlm_put_lockspace(struct dlm_ls *ls)
{
	spin_lock(&lslist_lock);
	ls->ls_count--;
	spin_unlock(&lslist_lock);
}

static void remove_lockspace(struct dlm_ls *ls)
{
	for (;;) {
		spin_lock(&lslist_lock);
		if (ls->ls_count == 0) {
			WARN_ON(ls->ls_create_count != 0);
			list_del(&ls->ls_list);
			spin_unlock(&lslist_lock);
			return;
		}
		spin_unlock(&lslist_lock);
		ssleep(1);
	}
}

static int threads_start(void)
{
	int error;

	error = dlm_scand_start();
	if (error) {
		log_print("cannot start dlm_scand thread %d", error);
		goto fail;
	}

	/* Thread for sending/receiving messages for all lockspace's */
	error = dlm_lowcomms_start();
	if (error) {
		log_print("cannot start dlm lowcomms %d", error);
		goto scand_fail;
	}

	return 0;

 scand_fail:
	dlm_scand_stop();
 fail:
	return error;
}

static void threads_stop(void)
{
	dlm_scand_stop();
	dlm_lowcomms_stop();
}

static int new_lockspace(const char *name, const char *cluster,
			 uint32_t flags, int lvblen,
			 const struct dlm_lockspace_ops *ops, void *ops_arg,
			 int *ops_result, dlm_lockspace_t **lockspace)
{
	struct dlm_ls *ls;
	int i, size, error;
	int do_unreg = 0;
	int namelen = strlen(name);

	if (namelen > DLM_LOCKSPACE_LEN)
		return -EINVAL;

	if (!lvblen || (lvblen % 8))
		return -EINVAL;

	if (!try_module_get(THIS_MODULE))
		return -EINVAL;

	if (!dlm_user_daemon_available()) {
		log_print("dlm user daemon not available");
		error = -EUNATCH;
		goto out;
	}

	if (ops && ops_result) {
	       	if (!dlm_config.ci_recover_callbacks)
			*ops_result = -EOPNOTSUPP;
		else
			*ops_result = 0;
	}

	if (dlm_config.ci_recover_callbacks && cluster &&
	    strncmp(cluster, dlm_config.ci_cluster_name, DLM_LOCKSPACE_LEN)) {
		log_print("dlm cluster name %s mismatch %s",
			  dlm_config.ci_cluster_name, cluster);
		error = -EBADR;
		goto out;
	}

	error = 0;

	spin_lock(&lslist_lock);
	list_for_each_entry(ls, &lslist, ls_list) {
		WARN_ON(ls->ls_create_count <= 0);
		if (ls->ls_namelen != namelen)
			continue;
		if (memcmp(ls->ls_name, name, namelen))
			continue;
		if (flags & DLM_LSFL_NEWEXCL) {
			error = -EEXIST;
			break;
		}
		ls->ls_create_count++;
		*lockspace = ls;
		error = 1;
		break;
	}
	spin_unlock(&lslist_lock);

	if (error)
		goto out;

	error = -ENOMEM;

	ls = kzalloc(sizeof(struct dlm_ls) + namelen, GFP_NOFS);
	if (!ls)
		goto out;
	memcpy(ls->ls_name, name, namelen);
	ls->ls_namelen = namelen;
	ls->ls_lvblen = lvblen;
	ls->ls_count = 0;
	ls->ls_flags = 0;
	ls->ls_scan_time = jiffies;

	if (ops && dlm_config.ci_recover_callbacks) {
		ls->ls_ops = ops;
		ls->ls_ops_arg = ops_arg;
	}

	if (flags & DLM_LSFL_TIMEWARN)
		set_bit(LSFL_TIMEWARN, &ls->ls_flags);

	/* ls_exflags are forced to match among nodes, and we don't
	   need to require all nodes to have some flags set */
	ls->ls_exflags = (flags & ~(DLM_LSFL_TIMEWARN | DLM_LSFL_FS |
				    DLM_LSFL_NEWEXCL));

	size = dlm_config.ci_rsbtbl_size;
	ls->ls_rsbtbl_size = size;

	ls->ls_rsbtbl = vmalloc(sizeof(struct dlm_rsbtable) * size);
	if (!ls->ls_rsbtbl)
		goto out_lsfree;
	for (i = 0; i < size; i++) {
		ls->ls_rsbtbl[i].keep.rb_node = NULL;
		ls->ls_rsbtbl[i].toss.rb_node = NULL;
		spin_lock_init(&ls->ls_rsbtbl[i].lock);
	}

	spin_lock_init(&ls->ls_remove_spin);

	for (i = 0; i < DLM_REMOVE_NAMES_MAX; i++) {
		ls->ls_remove_names[i] = kzalloc(DLM_RESNAME_MAXLEN+1,
						 GFP_KERNEL);
		if (!ls->ls_remove_names[i])
			goto out_rsbtbl;
	}

	idr_init(&ls->ls_lkbidr);
	spin_lock_init(&ls->ls_lkbidr_spin);

	INIT_LIST_HEAD(&ls->ls_waiters);
	mutex_init(&ls->ls_waiters_mutex);
	INIT_LIST_HEAD(&ls->ls_orphans);
	mutex_init(&ls->ls_orphans_mutex);
	INIT_LIST_HEAD(&ls->ls_timeout);
	mutex_init(&ls->ls_timeout_mutex);

	INIT_LIST_HEAD(&ls->ls_new_rsb);
	spin_lock_init(&ls->ls_new_rsb_spin);

	INIT_LIST_HEAD(&ls->ls_nodes);
	INIT_LIST_HEAD(&ls->ls_nodes_gone);
	ls->ls_num_nodes = 0;
	ls->ls_low_nodeid = 0;
	ls->ls_total_weight = 0;
	ls->ls_node_array = NULL;

	memset(&ls->ls_stub_rsb, 0, sizeof(struct dlm_rsb));
	ls->ls_stub_rsb.res_ls = ls;

	ls->ls_debug_rsb_dentry = NULL;
	ls->ls_debug_waiters_dentry = NULL;

	init_waitqueue_head(&ls->ls_uevent_wait);
	ls->ls_uevent_result = 0;
	init_completion(&ls->ls_members_done);
	ls->ls_members_result = -1;

	mutex_init(&ls->ls_cb_mutex);
	INIT_LIST_HEAD(&ls->ls_cb_delay);

	ls->ls_recoverd_task = NULL;
	mutex_init(&ls->ls_recoverd_active);
	spin_lock_init(&ls->ls_recover_lock);
	spin_lock_init(&ls->ls_rcom_spin);
	get_random_bytes(&ls->ls_rcom_seq, sizeof(uint64_t));
	ls->ls_recover_status = 0;
	ls->ls_recover_seq = 0;
	ls->ls_recover_args = NULL;
	init_rwsem(&ls->ls_in_recovery);
	init_rwsem(&ls->ls_recv_active);
	INIT_LIST_HEAD(&ls->ls_requestqueue);
	mutex_init(&ls->ls_requestqueue_mutex);
	mutex_init(&ls->ls_clear_proc_locks);

	ls->ls_recover_buf = kmalloc(dlm_config.ci_buffer_size, GFP_NOFS);
	if (!ls->ls_recover_buf)
		goto out_lkbidr;

	ls->ls_slot = 0;
	ls->ls_num_slots = 0;
	ls->ls_slots_size = 0;
	ls->ls_slots = NULL;

	INIT_LIST_HEAD(&ls->ls_recover_list);
	spin_lock_init(&ls->ls_recover_list_lock);
	idr_init(&ls->ls_recover_idr);
	spin_lock_init(&ls->ls_recover_idr_lock);
	ls->ls_recover_list_count = 0;
	ls->ls_local_handle = ls;
	init_waitqueue_head(&ls->ls_wait_general);
	INIT_LIST_HEAD(&ls->ls_root_list);
	init_rwsem(&ls->ls_root_sem);

	spin_lock(&lslist_lock);
	ls->ls_create_count = 1;
	list_add(&ls->ls_list, &lslist);
	spin_unlock(&lslist_lock);

	if (flags & DLM_LSFL_FS) {
		error = dlm_callback_start(ls);
		if (error) {
			log_error(ls, "can't start dlm_callback %d", error);
			goto out_delist;
		}
	}

	init_waitqueue_head(&ls->ls_recover_lock_wait);

	/*
	 * Once started, dlm_recoverd first looks for ls in lslist, then
	 * initializes ls_in_recovery as locked in "down" mode.  We need
	 * to wait for the wakeup from dlm_recoverd because in_recovery
	 * has to start out in down mode.
	 */

	error = dlm_recoverd_start(ls);
	if (error) {
		log_error(ls, "can't start dlm_recoverd %d", error);
		goto out_callback;
	}

	wait_event(ls->ls_recover_lock_wait,
		   test_bit(LSFL_RECOVER_LOCK, &ls->ls_flags));

	ls->ls_kobj.kset = dlm_kset;
	error = kobject_init_and_add(&ls->ls_kobj, &dlm_ktype, NULL,
				     "%s", ls->ls_name);
	if (error)
		goto out_recoverd;
	kobject_uevent(&ls->ls_kobj, KOBJ_ADD);

	/* let kobject handle freeing of ls if there's an error */
	do_unreg = 1;

	/* This uevent triggers dlm_controld in userspace to add us to the
	   group of nodes that are members of this lockspace (managed by the
	   cluster infrastructure.)  Once it's done that, it tells us who the
	   current lockspace members are (via configfs) and then tells the
	   lockspace to start running (via sysfs) in dlm_ls_start(). */

	error = do_uevent(ls, 1);
	if (error)
		goto out_recoverd;

	wait_for_completion(&ls->ls_members_done);
	error = ls->ls_members_result;
	if (error)
		goto out_members;

	dlm_create_debug_file(ls);

	log_debug(ls, "join complete");
	*lockspace = ls;
	return 0;

 out_members:
	do_uevent(ls, 0);
	dlm_clear_members(ls);
	kfree(ls->ls_node_array);
 out_recoverd:
	dlm_recoverd_stop(ls);
 out_callback:
	dlm_callback_stop(ls);
 out_delist:
	spin_lock(&lslist_lock);
	list_del(&ls->ls_list);
	spin_unlock(&lslist_lock);
	idr_destroy(&ls->ls_recover_idr);
	kfree(ls->ls_recover_buf);
 out_lkbidr:
	idr_destroy(&ls->ls_lkbidr);
	for (i = 0; i < DLM_REMOVE_NAMES_MAX; i++) {
		if (ls->ls_remove_names[i])
			kfree(ls->ls_remove_names[i]);
	}
 out_rsbtbl:
	vfree(ls->ls_rsbtbl);
 out_lsfree:
	if (do_unreg)
		kobject_put(&ls->ls_kobj);
	else
		kfree(ls);
 out:
	module_put(THIS_MODULE);
	return error;
}

int dlm_new_lockspace(const char *name, const char *cluster,
		      uint32_t flags, int lvblen,
		      const struct dlm_lockspace_ops *ops, void *ops_arg,
		      int *ops_result, dlm_lockspace_t **lockspace)
{
	int error = 0;

	mutex_lock(&ls_lock);
	if (!ls_count)
		error = threads_start();
	if (error)
		goto out;

	error = new_lockspace(name, cluster, flags, lvblen, ops, ops_arg,
			      ops_result, lockspace);
	if (!error)
		ls_count++;
	if (error > 0)
		error = 0;
	if (!ls_count)
		threads_stop();
 out:
	mutex_unlock(&ls_lock);
	return error;
}

static int lkb_idr_is_local(int id, void *p, void *data)
{
	struct dlm_lkb *lkb = p;

	if (!lkb->lkb_nodeid)
		return 1;
	return 0;
}

static int lkb_idr_is_any(int id, void *p, void *data)
{
	return 1;
}

static int lkb_idr_free(int id, void *p, void *data)
{
	struct dlm_lkb *lkb = p;

	if (lkb->lkb_lvbptr && lkb->lkb_flags & DLM_IFL_MSTCPY)
		dlm_free_lvb(lkb->lkb_lvbptr);

	dlm_free_lkb(lkb);
	return 0;
}

/* NOTE: We check the lkbidr here rather than the resource table.
   This is because there may be LKBs queued as ASTs that have been unlinked
   from their RSBs and are pending deletion once the AST has been delivered */

static int lockspace_busy(struct dlm_ls *ls, int force)
{
	int rv;

	spin_lock(&ls->ls_lkbidr_spin);
	if (force == 0) {
		rv = idr_for_each(&ls->ls_lkbidr, lkb_idr_is_any, ls);
	} else if (force == 1) {
		rv = idr_for_each(&ls->ls_lkbidr, lkb_idr_is_local, ls);
	} else {
		rv = 0;
	}
	spin_unlock(&ls->ls_lkbidr_spin);
	return rv;
}

static int release_lockspace(struct dlm_ls *ls, int force)
{
	struct dlm_rsb *rsb;
	struct rb_node *n;
	int i, busy, rv;

	busy = lockspace_busy(ls, force);

	spin_lock(&lslist_lock);
	if (ls->ls_create_count == 1) {
		if (busy) {
			rv = -EBUSY;
		} else {
			/* remove_lockspace takes ls off lslist */
			ls->ls_create_count = 0;
			rv = 0;
		}
	} else if (ls->ls_create_count > 1) {
		rv = --ls->ls_create_count;
	} else {
		rv = -EINVAL;
	}
	spin_unlock(&lslist_lock);

	if (rv) {
		log_debug(ls, "release_lockspace no remove %d", rv);
		return rv;
	}

	dlm_device_deregister(ls);

	if (force < 3 && dlm_user_daemon_available())
		do_uevent(ls, 0);

	dlm_recoverd_stop(ls);

	dlm_callback_stop(ls);

	remove_lockspace(ls);

	dlm_delete_debug_file(ls);

	kfree(ls->ls_recover_buf);

	/*
	 * Free all lkb's in idr
	 */

	idr_for_each(&ls->ls_lkbidr, lkb_idr_free, ls);
	idr_destroy(&ls->ls_lkbidr);

	/*
	 * Free all rsb's on rsbtbl[] lists
	 */

	for (i = 0; i < ls->ls_rsbtbl_size; i++) {
		while ((n = rb_first(&ls->ls_rsbtbl[i].keep))) {
			rsb = rb_entry(n, struct dlm_rsb, res_hashnode);
			rb_erase(n, &ls->ls_rsbtbl[i].keep);
			dlm_free_rsb(rsb);
		}

		while ((n = rb_first(&ls->ls_rsbtbl[i].toss))) {
			rsb = rb_entry(n, struct dlm_rsb, res_hashnode);
			rb_erase(n, &ls->ls_rsbtbl[i].toss);
			dlm_free_rsb(rsb);
		}
	}

	vfree(ls->ls_rsbtbl);

	for (i = 0; i < DLM_REMOVE_NAMES_MAX; i++)
		kfree(ls->ls_remove_names[i]);

	while (!list_empty(&ls->ls_new_rsb)) {
		rsb = list_first_entry(&ls->ls_new_rsb, struct dlm_rsb,
				       res_hashchain);
		list_del(&rsb->res_hashchain);
		dlm_free_rsb(rsb);
	}

	/*
	 * Free structures on any other lists
	 */

	dlm_purge_requestqueue(ls);
	kfree(ls->ls_recover_args);
	dlm_clear_members(ls);
	dlm_clear_members_gone(ls);
	kfree(ls->ls_node_array);
	log_debug(ls, "release_lockspace final free");
	kobject_put(&ls->ls_kobj);
	/* The ls structure will be freed when the kobject is done with */

	module_put(THIS_MODULE);
	return 0;
}

/*
 * Called when a system has released all its locks and is not going to use the
 * lockspace any longer.  We free everything we're managing for this lockspace.
 * Remaining nodes will go through the recovery process as if we'd died.  The
 * lockspace must continue to function as usual, participating in recoveries,
 * until this returns.
 *
 * Force has 4 possible values:
 * 0 - don't destroy locksapce if it has any LKBs
 * 1 - destroy lockspace if it has remote LKBs but not if it has local LKBs
 * 2 - destroy lockspace regardless of LKBs
 * 3 - destroy lockspace as part of a forced shutdown
 */

int dlm_release_lockspace(void *lockspace, int force)
{
	struct dlm_ls *ls;
	int error;

	ls = dlm_find_lockspace_local(lockspace);
	if (!ls)
		return -EINVAL;
	dlm_put_lockspace(ls);

	mutex_lock(&ls_lock);
	error = release_lockspace(ls, force);
	if (!error)
		ls_count--;
	if (!ls_count)
		threads_stop();
	mutex_unlock(&ls_lock);

	return error;
}

void dlm_stop_lockspaces(void)
{
	struct dlm_ls *ls;

 restart:
	spin_lock(&lslist_lock);
	list_for_each_entry(ls, &lslist, ls_list) {
		if (!test_bit(LSFL_RUNNING, &ls->ls_flags))
			continue;
		spin_unlock(&lslist_lock);
		log_error(ls, "no userland control daemon, stopping lockspace");
		dlm_ls_stop(ls);
		goto restart;
	}
	spin_unlock(&lslist_lock);
}

OpenPOWER on IntegriCloud