summaryrefslogtreecommitdiffstats
path: root/fs/ocfs2/stack_user.c
blob: 31276bac78f5e813e34c4453efad7ebb3565356b (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
/* -*- mode: c; c-basic-offset: 8; -*-
 * vim: noexpandtab sw=8 ts=8 sts=0:
 *
 * stack_user.c
 *
 * Code which interfaces ocfs2 with fs/dlm and a userspace stack.
 *
 * Copyright (C) 2007 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, version 2.
 *
 * 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.
 */

#include <linux/module.h>
#include <linux/fs.h>
#include <linux/miscdevice.h>
#include <linux/mutex.h>
#include <linux/smp_lock.h>
#include <linux/reboot.h>
#include <asm/uaccess.h>

#include "stackglue.h"

#include <linux/dlm_plock.h>

/*
 * The control protocol starts with a handshake.  Until the handshake
 * is complete, the control device will fail all write(2)s.
 *
 * The handshake is simple.  First, the client reads until EOF.  Each line
 * of output is a supported protocol tag.  All protocol tags are a single
 * character followed by a two hex digit version number.  Currently the
 * only things supported is T01, for "Text-base version 0x01".  Next, the
 * client writes the version they would like to use, including the newline.
 * Thus, the protocol tag is 'T01\n'.  If the version tag written is
 * unknown, -EINVAL is returned.  Once the negotiation is complete, the
 * client can start sending messages.
 *
 * The T01 protocol has three messages.  First is the "SETN" message.
 * It has the following syntax:
 *
 *  SETN<space><8-char-hex-nodenum><newline>
 *
 * This is 14 characters.
 *
 * The "SETN" message must be the first message following the protocol.
 * It tells ocfs2_control the local node number.
 *
 * Next comes the "SETV" message.  It has the following syntax:
 *
 *  SETV<space><2-char-hex-major><space><2-char-hex-minor><newline>
 *
 * This is 11 characters.
 *
 * The "SETV" message sets the filesystem locking protocol version as
 * negotiated by the client.  The client negotiates based on the maximum
 * version advertised in /sys/fs/ocfs2/max_locking_protocol.  The major
 * number from the "SETV" message must match
 * ocfs2_user_plugin.sp_proto->lp_max_version.pv_major, and the minor number
 * must be less than or equal to ...->lp_max_version.pv_minor.
 *
 * Once this information has been set, mounts will be allowed.  From this
 * point on, the "DOWN" message can be sent for node down notification.
 * It has the following syntax:
 *
 *  DOWN<space><32-char-cap-hex-uuid><space><8-char-hex-nodenum><newline>
 *
 * eg:
 *
 *  DOWN 632A924FDD844190BDA93C0DF6B94899 00000001\n
 *
 * This is 47 characters.
 */

/*
 * Whether or not the client has done the handshake.
 * For now, we have just one protocol version.
 */
#define OCFS2_CONTROL_PROTO			"T01\n"
#define OCFS2_CONTROL_PROTO_LEN			4

/* Handshake states */
#define OCFS2_CONTROL_HANDSHAKE_INVALID		(0)
#define OCFS2_CONTROL_HANDSHAKE_READ		(1)
#define OCFS2_CONTROL_HANDSHAKE_PROTOCOL	(2)
#define OCFS2_CONTROL_HANDSHAKE_VALID		(3)

/* Messages */
#define OCFS2_CONTROL_MESSAGE_OP_LEN		4
#define OCFS2_CONTROL_MESSAGE_SETNODE_OP	"SETN"
#define OCFS2_CONTROL_MESSAGE_SETNODE_TOTAL_LEN	14
#define OCFS2_CONTROL_MESSAGE_SETVERSION_OP	"SETV"
#define OCFS2_CONTROL_MESSAGE_SETVERSION_TOTAL_LEN	11
#define OCFS2_CONTROL_MESSAGE_DOWN_OP		"DOWN"
#define OCFS2_CONTROL_MESSAGE_DOWN_TOTAL_LEN	47
#define OCFS2_TEXT_UUID_LEN			32
#define OCFS2_CONTROL_MESSAGE_VERNUM_LEN	2
#define OCFS2_CONTROL_MESSAGE_NODENUM_LEN	8

/*
 * ocfs2_live_connection is refcounted because the filesystem and
 * miscdevice sides can detach in different order.  Let's just be safe.
 */
struct ocfs2_live_connection {
	struct list_head		oc_list;
	struct ocfs2_cluster_connection	*oc_conn;
};

struct ocfs2_control_private {
	struct list_head op_list;
	int op_state;
	int op_this_node;
	struct ocfs2_protocol_version op_proto;
};

/* SETN<space><8-char-hex-nodenum><newline> */
struct ocfs2_control_message_setn {
	char	tag[OCFS2_CONTROL_MESSAGE_OP_LEN];
	char	space;
	char	nodestr[OCFS2_CONTROL_MESSAGE_NODENUM_LEN];
	char	newline;
};

/* SETV<space><2-char-hex-major><space><2-char-hex-minor><newline> */
struct ocfs2_control_message_setv {
	char	tag[OCFS2_CONTROL_MESSAGE_OP_LEN];
	char	space1;
	char	major[OCFS2_CONTROL_MESSAGE_VERNUM_LEN];
	char	space2;
	char	minor[OCFS2_CONTROL_MESSAGE_VERNUM_LEN];
	char	newline;
};

/* DOWN<space><32-char-cap-hex-uuid><space><8-char-hex-nodenum><newline> */
struct ocfs2_control_message_down {
	char	tag[OCFS2_CONTROL_MESSAGE_OP_LEN];
	char	space1;
	char	uuid[OCFS2_TEXT_UUID_LEN];
	char	space2;
	char	nodestr[OCFS2_CONTROL_MESSAGE_NODENUM_LEN];
	char	newline;
};

union ocfs2_control_message {
	char					tag[OCFS2_CONTROL_MESSAGE_OP_LEN];
	struct ocfs2_control_message_setn	u_setn;
	struct ocfs2_control_message_setv	u_setv;
	struct ocfs2_control_message_down	u_down;
};

static struct ocfs2_stack_plugin ocfs2_user_plugin;

static atomic_t ocfs2_control_opened;
static int ocfs2_control_this_node = -1;
static struct ocfs2_protocol_version running_proto;

static LIST_HEAD(ocfs2_live_connection_list);
static LIST_HEAD(ocfs2_control_private_list);
static DEFINE_MUTEX(ocfs2_control_lock);

static inline void ocfs2_control_set_handshake_state(struct file *file,
						     int state)
{
	struct ocfs2_control_private *p = file->private_data;
	p->op_state = state;
}

static inline int ocfs2_control_get_handshake_state(struct file *file)
{
	struct ocfs2_control_private *p = file->private_data;
	return p->op_state;
}

static struct ocfs2_live_connection *ocfs2_connection_find(const char *name)
{
	size_t len = strlen(name);
	struct ocfs2_live_connection *c;

	BUG_ON(!mutex_is_locked(&ocfs2_control_lock));

	list_for_each_entry(c, &ocfs2_live_connection_list, oc_list) {
		if ((c->oc_conn->cc_namelen == len) &&
		    !strncmp(c->oc_conn->cc_name, name, len))
			return c;
	}

	return c;
}

/*
 * ocfs2_live_connection structures are created underneath the ocfs2
 * mount path.  Since the VFS prevents multiple calls to
 * fill_super(), we can't get dupes here.
 */
static int ocfs2_live_connection_new(struct ocfs2_cluster_connection *conn,
				     struct ocfs2_live_connection **c_ret)
{
	int rc = 0;
	struct ocfs2_live_connection *c;

	c = kzalloc(sizeof(struct ocfs2_live_connection), GFP_KERNEL);
	if (!c)
		return -ENOMEM;

	mutex_lock(&ocfs2_control_lock);
	c->oc_conn = conn;

	if (atomic_read(&ocfs2_control_opened))
		list_add(&c->oc_list, &ocfs2_live_connection_list);
	else {
		printk(KERN_ERR
		       "ocfs2: Userspace control daemon is not present\n");
		rc = -ESRCH;
	}

	mutex_unlock(&ocfs2_control_lock);

	if (!rc)
		*c_ret = c;
	else
		kfree(c);

	return rc;
}

/*
 * This function disconnects the cluster connection from ocfs2_control.
 * Afterwards, userspace can't affect the cluster connection.
 */
static void ocfs2_live_connection_drop(struct ocfs2_live_connection *c)
{
	mutex_lock(&ocfs2_control_lock);
	list_del_init(&c->oc_list);
	c->oc_conn = NULL;
	mutex_unlock(&ocfs2_control_lock);

	kfree(c);
}

static int ocfs2_control_cfu(void *target, size_t target_len,
			     const char __user *buf, size_t count)
{
	/* The T01 expects write(2) calls to have exactly one command */
	if ((count != target_len) ||
	    (count > sizeof(union ocfs2_control_message)))
		return -EINVAL;

	if (copy_from_user(target, buf, target_len))
		return -EFAULT;

	return 0;
}

static ssize_t ocfs2_control_validate_protocol(struct file *file,
					       const char __user *buf,
					       size_t count)
{
	ssize_t ret;
	char kbuf[OCFS2_CONTROL_PROTO_LEN];

	ret = ocfs2_control_cfu(kbuf, OCFS2_CONTROL_PROTO_LEN,
				buf, count);
	if (ret)
		return ret;

	if (strncmp(kbuf, OCFS2_CONTROL_PROTO, OCFS2_CONTROL_PROTO_LEN))
		return -EINVAL;

	ocfs2_control_set_handshake_state(file,
					  OCFS2_CONTROL_HANDSHAKE_PROTOCOL);

	return count;
}

static void ocfs2_control_send_down(const char *uuid,
				    int nodenum)
{
	struct ocfs2_live_connection *c;

	mutex_lock(&ocfs2_control_lock);

	c = ocfs2_connection_find(uuid);
	if (c) {
		BUG_ON(c->oc_conn == NULL);
		c->oc_conn->cc_recovery_handler(nodenum,
						c->oc_conn->cc_recovery_data);
	}

	mutex_unlock(&ocfs2_control_lock);
}

/*
 * Called whenever configuration elements are sent to /dev/ocfs2_control.
 * If all configuration elements are present, try to set the global
 * values.  If there is a problem, return an error.  Skip any missing
 * elements, and only bump ocfs2_control_opened when we have all elements
 * and are successful.
 */
static int ocfs2_control_install_private(struct file *file)
{
	int rc = 0;
	int set_p = 1;
	struct ocfs2_control_private *p = file->private_data;

	BUG_ON(p->op_state != OCFS2_CONTROL_HANDSHAKE_PROTOCOL);

	mutex_lock(&ocfs2_control_lock);

	if (p->op_this_node < 0) {
		set_p = 0;
	} else if ((ocfs2_control_this_node >= 0) &&
		   (ocfs2_control_this_node != p->op_this_node)) {
		rc = -EINVAL;
		goto out_unlock;
	}

	if (!p->op_proto.pv_major) {
		set_p = 0;
	} else if (!list_empty(&ocfs2_live_connection_list) &&
		   ((running_proto.pv_major != p->op_proto.pv_major) ||
		    (running_proto.pv_minor != p->op_proto.pv_minor))) {
		rc = -EINVAL;
		goto out_unlock;
	}

	if (set_p) {
		ocfs2_control_this_node = p->op_this_node;
		running_proto.pv_major = p->op_proto.pv_major;
		running_proto.pv_minor = p->op_proto.pv_minor;
	}

out_unlock:
	mutex_unlock(&ocfs2_control_lock);

	if (!rc && set_p) {
		/* We set the global values successfully */
		atomic_inc(&ocfs2_control_opened);
		ocfs2_control_set_handshake_state(file,
					OCFS2_CONTROL_HANDSHAKE_VALID);
	}

	return rc;
}

static int ocfs2_control_get_this_node(void)
{
	int rc;

	mutex_lock(&ocfs2_control_lock);
	if (ocfs2_control_this_node < 0)
		rc = -EINVAL;
	else
		rc = ocfs2_control_this_node;
	mutex_unlock(&ocfs2_control_lock);

	return rc;
}

static int ocfs2_control_do_setnode_msg(struct file *file,
					struct ocfs2_control_message_setn *msg)
{
	long nodenum;
	char *ptr = NULL;
	struct ocfs2_control_private *p = file->private_data;

	if (ocfs2_control_get_handshake_state(file) !=
	    OCFS2_CONTROL_HANDSHAKE_PROTOCOL)
		return -EINVAL;

	if (strncmp(msg->tag, OCFS2_CONTROL_MESSAGE_SETNODE_OP,
		    OCFS2_CONTROL_MESSAGE_OP_LEN))
		return -EINVAL;

	if ((msg->space != ' ') || (msg->newline != '\n'))
		return -EINVAL;
	msg->space = msg->newline = '\0';

	nodenum = simple_strtol(msg->nodestr, &ptr, 16);
	if (!ptr || *ptr)
		return -EINVAL;

	if ((nodenum == LONG_MIN) || (nodenum == LONG_MAX) ||
	    (nodenum > INT_MAX) || (nodenum < 0))
		return -ERANGE;
	p->op_this_node = nodenum;

	return ocfs2_control_install_private(file);
}

static int ocfs2_control_do_setversion_msg(struct file *file,
					   struct ocfs2_control_message_setv *msg)
 {
	long major, minor;
	char *ptr = NULL;
	struct ocfs2_control_private *p = file->private_data;
	struct ocfs2_protocol_version *max =
		&ocfs2_user_plugin.sp_proto->lp_max_version;

	if (ocfs2_control_get_handshake_state(file) !=
	    OCFS2_CONTROL_HANDSHAKE_PROTOCOL)
		return -EINVAL;

	if (strncmp(msg->tag, OCFS2_CONTROL_MESSAGE_SETVERSION_OP,
		    OCFS2_CONTROL_MESSAGE_OP_LEN))
		return -EINVAL;

	if ((msg->space1 != ' ') || (msg->space2 != ' ') ||
	    (msg->newline != '\n'))
		return -EINVAL;
	msg->space1 = msg->space2 = msg->newline = '\0';

	major = simple_strtol(msg->major, &ptr, 16);
	if (!ptr || *ptr)
		return -EINVAL;
	minor = simple_strtol(msg->minor, &ptr, 16);
	if (!ptr || *ptr)
		return -EINVAL;

	/*
	 * The major must be between 1 and 255, inclusive.  The minor
	 * must be between 0 and 255, inclusive.  The version passed in
	 * must be within the maximum version supported by the filesystem.
	 */
	if ((major == LONG_MIN) || (major == LONG_MAX) ||
	    (major > (u8)-1) || (major < 1))
		return -ERANGE;
	if ((minor == LONG_MIN) || (minor == LONG_MAX) ||
	    (minor > (u8)-1) || (minor < 0))
		return -ERANGE;
	if ((major != max->pv_major) ||
	    (minor > max->pv_minor))
		return -EINVAL;

	p->op_proto.pv_major = major;
	p->op_proto.pv_minor = minor;

	return ocfs2_control_install_private(file);
}

static int ocfs2_control_do_down_msg(struct file *file,
				     struct ocfs2_control_message_down *msg)
{
	long nodenum;
	char *p = NULL;

	if (ocfs2_control_get_handshake_state(file) !=
	    OCFS2_CONTROL_HANDSHAKE_VALID)
		return -EINVAL;

	if (strncmp(msg->tag, OCFS2_CONTROL_MESSAGE_DOWN_OP,
		    OCFS2_CONTROL_MESSAGE_OP_LEN))
		return -EINVAL;

	if ((msg->space1 != ' ') || (msg->space2 != ' ') ||
	    (msg->newline != '\n'))
		return -EINVAL;
	msg->space1 = msg->space2 = msg->newline = '\0';

	nodenum = simple_strtol(msg->nodestr, &p, 16);
	if (!p || *p)
		return -EINVAL;

	if ((nodenum == LONG_MIN) || (nodenum == LONG_MAX) ||
	    (nodenum > INT_MAX) || (nodenum < 0))
		return -ERANGE;

	ocfs2_control_send_down(msg->uuid, nodenum);

	return 0;
}

static ssize_t ocfs2_control_message(struct file *file,
				     const char __user *buf,
				     size_t count)
{
	ssize_t ret;
	union ocfs2_control_message msg;

	/* Try to catch padding issues */
	WARN_ON(offsetof(struct ocfs2_control_message_down, uuid) !=
		(sizeof(msg.u_down.tag) + sizeof(msg.u_down.space1)));

	memset(&msg, 0, sizeof(union ocfs2_control_message));
	ret = ocfs2_control_cfu(&msg, count, buf, count);
	if (ret)
		goto out;

	if ((count == OCFS2_CONTROL_MESSAGE_SETNODE_TOTAL_LEN) &&
	    !strncmp(msg.tag, OCFS2_CONTROL_MESSAGE_SETNODE_OP,
		     OCFS2_CONTROL_MESSAGE_OP_LEN))
		ret = ocfs2_control_do_setnode_msg(file, &msg.u_setn);
	else if ((count == OCFS2_CONTROL_MESSAGE_SETVERSION_TOTAL_LEN) &&
		 !strncmp(msg.tag, OCFS2_CONTROL_MESSAGE_SETVERSION_OP,
			  OCFS2_CONTROL_MESSAGE_OP_LEN))
		ret = ocfs2_control_do_setversion_msg(file, &msg.u_setv);
	else if ((count == OCFS2_CONTROL_MESSAGE_DOWN_TOTAL_LEN) &&
		 !strncmp(msg.tag, OCFS2_CONTROL_MESSAGE_DOWN_OP,
			  OCFS2_CONTROL_MESSAGE_OP_LEN))
		ret = ocfs2_control_do_down_msg(file, &msg.u_down);
	else
		ret = -EINVAL;

out:
	return ret ? ret : count;
}

static ssize_t ocfs2_control_write(struct file *file,
				   const char __user *buf,
				   size_t count,
				   loff_t *ppos)
{
	ssize_t ret;

	switch (ocfs2_control_get_handshake_state(file)) {
		case OCFS2_CONTROL_HANDSHAKE_INVALID:
			ret = -EINVAL;
			break;

		case OCFS2_CONTROL_HANDSHAKE_READ:
			ret = ocfs2_control_validate_protocol(file, buf,
							      count);
			break;

		case OCFS2_CONTROL_HANDSHAKE_PROTOCOL:
		case OCFS2_CONTROL_HANDSHAKE_VALID:
			ret = ocfs2_control_message(file, buf, count);
			break;

		default:
			BUG();
			ret = -EIO;
			break;
	}

	return ret;
}

/*
 * This is a naive version.  If we ever have a new protocol, we'll expand
 * it.  Probably using seq_file.
 */
static ssize_t ocfs2_control_read(struct file *file,
				  char __user *buf,
				  size_t count,
				  loff_t *ppos)
{
	ssize_t ret;

	ret = simple_read_from_buffer(buf, count, ppos,
			OCFS2_CONTROL_PROTO, OCFS2_CONTROL_PROTO_LEN);

	/* Have we read the whole protocol list? */
	if (ret > 0 && *ppos >= OCFS2_CONTROL_PROTO_LEN)
		ocfs2_control_set_handshake_state(file,
						  OCFS2_CONTROL_HANDSHAKE_READ);

	return ret;
}

static int ocfs2_control_release(struct inode *inode, struct file *file)
{
	struct ocfs2_control_private *p = file->private_data;

	mutex_lock(&ocfs2_control_lock);

	if (ocfs2_control_get_handshake_state(file) !=
	    OCFS2_CONTROL_HANDSHAKE_VALID)
		goto out;

	if (atomic_dec_and_test(&ocfs2_control_opened)) {
		if (!list_empty(&ocfs2_live_connection_list)) {
			/* XXX: Do bad things! */
			printk(KERN_ERR
			       "ocfs2: Unexpected release of ocfs2_control!\n"
			       "       Loss of cluster connection requires "
			       "an emergency restart!\n");
			emergency_restart();
		}
		/*
		 * Last valid close clears the node number and resets
		 * the locking protocol version
		 */
		ocfs2_control_this_node = -1;
		running_proto.pv_major = 0;
		running_proto.pv_major = 0;
	}

out:
	list_del_init(&p->op_list);
	file->private_data = NULL;

	mutex_unlock(&ocfs2_control_lock);

	kfree(p);

	return 0;
}

static int ocfs2_control_open(struct inode *inode, struct file *file)
{
	struct ocfs2_control_private *p;

	p = kzalloc(sizeof(struct ocfs2_control_private), GFP_KERNEL);
	if (!p)
		return -ENOMEM;
	p->op_this_node = -1;

	lock_kernel();
	mutex_lock(&ocfs2_control_lock);
	file->private_data = p;
	list_add(&p->op_list, &ocfs2_control_private_list);
	mutex_unlock(&ocfs2_control_lock);
	unlock_kernel();

	return 0;
}

static const struct file_operations ocfs2_control_fops = {
	.open    = ocfs2_control_open,
	.release = ocfs2_control_release,
	.read    = ocfs2_control_read,
	.write   = ocfs2_control_write,
	.owner   = THIS_MODULE,
};

static struct miscdevice ocfs2_control_device = {
	.minor		= MISC_DYNAMIC_MINOR,
	.name		= "ocfs2_control",
	.fops		= &ocfs2_control_fops,
};

static int ocfs2_control_init(void)
{
	int rc;

	atomic_set(&ocfs2_control_opened, 0);

	rc = misc_register(&ocfs2_control_device);
	if (rc)
		printk(KERN_ERR
		       "ocfs2: Unable to register ocfs2_control device "
		       "(errno %d)\n",
		       -rc);

	return rc;
}

static void ocfs2_control_exit(void)
{
	int rc;

	rc = misc_deregister(&ocfs2_control_device);
	if (rc)
		printk(KERN_ERR
		       "ocfs2: Unable to deregister ocfs2_control device "
		       "(errno %d)\n",
		       -rc);
}

static void fsdlm_lock_ast_wrapper(void *astarg)
{
	struct ocfs2_dlm_lksb *lksb = astarg;
	int status = lksb->lksb_fsdlm.sb_status;

	BUG_ON(ocfs2_user_plugin.sp_proto == NULL);

	/*
	 * For now we're punting on the issue of other non-standard errors
	 * where we can't tell if the unlock_ast or lock_ast should be called.
	 * The main "other error" that's possible is EINVAL which means the
	 * function was called with invalid args, which shouldn't be possible
	 * since the caller here is under our control.  Other non-standard
	 * errors probably fall into the same category, or otherwise are fatal
	 * which means we can't carry on anyway.
	 */

	if (status == -DLM_EUNLOCK || status == -DLM_ECANCEL)
		ocfs2_user_plugin.sp_proto->lp_unlock_ast(lksb, 0);
	else
		ocfs2_user_plugin.sp_proto->lp_lock_ast(lksb);
}

static void fsdlm_blocking_ast_wrapper(void *astarg, int level)
{
	struct ocfs2_dlm_lksb *lksb = astarg;

	BUG_ON(ocfs2_user_plugin.sp_proto == NULL);

	ocfs2_user_plugin.sp_proto->lp_blocking_ast(lksb, level);
}

static int user_dlm_lock(struct ocfs2_cluster_connection *conn,
			 int mode,
			 struct ocfs2_dlm_lksb *lksb,
			 u32 flags,
			 void *name,
			 unsigned int namelen)
{
	int ret;

	if (!lksb->lksb_fsdlm.sb_lvbptr)
		lksb->lksb_fsdlm.sb_lvbptr = (char *)lksb +
					     sizeof(struct dlm_lksb);

	ret = dlm_lock(conn->cc_lockspace, mode, &lksb->lksb_fsdlm,
		       flags|DLM_LKF_NODLCKWT, name, namelen, 0,
		       fsdlm_lock_ast_wrapper, lksb,
		       fsdlm_blocking_ast_wrapper);
	return ret;
}

static int user_dlm_unlock(struct ocfs2_cluster_connection *conn,
			   struct ocfs2_dlm_lksb *lksb,
			   u32 flags)
{
	int ret;

	ret = dlm_unlock(conn->cc_lockspace, lksb->lksb_fsdlm.sb_lkid,
			 flags, &lksb->lksb_fsdlm, lksb);
	return ret;
}

static int user_dlm_lock_status(struct ocfs2_dlm_lksb *lksb)
{
	return lksb->lksb_fsdlm.sb_status;
}

static int user_dlm_lvb_valid(struct ocfs2_dlm_lksb *lksb)
{
	int invalid = lksb->lksb_fsdlm.sb_flags & DLM_SBF_VALNOTVALID;

	return !invalid;
}

static void *user_dlm_lvb(struct ocfs2_dlm_lksb *lksb)
{
	if (!lksb->lksb_fsdlm.sb_lvbptr)
		lksb->lksb_fsdlm.sb_lvbptr = (char *)lksb +
					     sizeof(struct dlm_lksb);
	return (void *)(lksb->lksb_fsdlm.sb_lvbptr);
}

static void user_dlm_dump_lksb(struct ocfs2_dlm_lksb *lksb)
{
}

static int user_plock(struct ocfs2_cluster_connection *conn,
		      u64 ino,
		      struct file *file,
		      int cmd,
		      struct file_lock *fl)
{
	/*
	 * This more or less just demuxes the plock request into any
	 * one of three dlm calls.
	 *
	 * Internally, fs/dlm will pass these to a misc device, which
	 * a userspace daemon will read and write to.
	 *
	 * For now, cancel requests (which happen internally only),
	 * are turned into unlocks. Most of this function taken from
	 * gfs2_lock.
	 */

	if (cmd == F_CANCELLK) {
		cmd = F_SETLK;
		fl->fl_type = F_UNLCK;
	}

	if (IS_GETLK(cmd))
		return dlm_posix_get(conn->cc_lockspace, ino, file, fl);
	else if (fl->fl_type == F_UNLCK)
		return dlm_posix_unlock(conn->cc_lockspace, ino, file, fl);
	else
		return dlm_posix_lock(conn->cc_lockspace, ino, file, cmd, fl);
}

/*
 * Compare a requested locking protocol version against the current one.
 *
 * If the major numbers are different, they are incompatible.
 * If the current minor is greater than the request, they are incompatible.
 * If the current minor is less than or equal to the request, they are
 * compatible, and the requester should run at the current minor version.
 */
static int fs_protocol_compare(struct ocfs2_protocol_version *existing,
			       struct ocfs2_protocol_version *request)
{
	if (existing->pv_major != request->pv_major)
		return 1;

	if (existing->pv_minor > request->pv_minor)
		return 1;

	if (existing->pv_minor < request->pv_minor)
		request->pv_minor = existing->pv_minor;

	return 0;
}

static int user_cluster_connect(struct ocfs2_cluster_connection *conn)
{
	dlm_lockspace_t *fsdlm;
	struct ocfs2_live_connection *uninitialized_var(control);
	int rc = 0;

	BUG_ON(conn == NULL);

	rc = ocfs2_live_connection_new(conn, &control);
	if (rc)
		goto out;

	/*
	 * running_proto must have been set before we allowed any mounts
	 * to proceed.
	 */
	if (fs_protocol_compare(&running_proto, &conn->cc_version)) {
		printk(KERN_ERR
		       "Unable to mount with fs locking protocol version "
		       "%u.%u because the userspace control daemon has "
		       "negotiated %u.%u\n",
		       conn->cc_version.pv_major, conn->cc_version.pv_minor,
		       running_proto.pv_major, running_proto.pv_minor);
		rc = -EPROTO;
		ocfs2_live_connection_drop(control);
		goto out;
	}

	rc = dlm_new_lockspace(conn->cc_name, strlen(conn->cc_name),
			       &fsdlm, DLM_LSFL_FS, DLM_LVB_LEN);
	if (rc) {
		ocfs2_live_connection_drop(control);
		goto out;
	}

	conn->cc_private = control;
	conn->cc_lockspace = fsdlm;
out:
	return rc;
}

static int user_cluster_disconnect(struct ocfs2_cluster_connection *conn)
{
	dlm_release_lockspace(conn->cc_lockspace, 2);
	conn->cc_lockspace = NULL;
	ocfs2_live_connection_drop(conn->cc_private);
	conn->cc_private = NULL;
	return 0;
}

static int user_cluster_this_node(unsigned int *this_node)
{
	int rc;

	rc = ocfs2_control_get_this_node();
	if (rc < 0)
		return rc;

	*this_node = rc;
	return 0;
}

static struct ocfs2_stack_operations ocfs2_user_plugin_ops = {
	.connect	= user_cluster_connect,
	.disconnect	= user_cluster_disconnect,
	.this_node	= user_cluster_this_node,
	.dlm_lock	= user_dlm_lock,
	.dlm_unlock	= user_dlm_unlock,
	.lock_status	= user_dlm_lock_status,
	.lvb_valid	= user_dlm_lvb_valid,
	.lock_lvb	= user_dlm_lvb,
	.plock		= user_plock,
	.dump_lksb	= user_dlm_dump_lksb,
};

static struct ocfs2_stack_plugin ocfs2_user_plugin = {
	.sp_name	= "user",
	.sp_ops		= &ocfs2_user_plugin_ops,
	.sp_owner	= THIS_MODULE,
};


static int __init ocfs2_user_plugin_init(void)
{
	int rc;

	rc = ocfs2_control_init();
	if (!rc) {
		rc = ocfs2_stack_glue_register(&ocfs2_user_plugin);
		if (rc)
			ocfs2_control_exit();
	}

	return rc;
}

static void __exit ocfs2_user_plugin_exit(void)
{
	ocfs2_stack_glue_unregister(&ocfs2_user_plugin);
	ocfs2_control_exit();
}

MODULE_AUTHOR("Oracle");
MODULE_DESCRIPTION("ocfs2 driver for userspace cluster stacks");
MODULE_LICENSE("GPL");
module_init(ocfs2_user_plugin_init);
module_exit(ocfs2_user_plugin_exit);