tems journal paper
aboutsummaryrefslogtreecommitdiffstats
path: root/fs/gfs2/sys.c
blob: 529d9a9eb89765093969837fba6cf44fb374f38e (plain) (blame)
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
/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2006 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 version 2.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/sched.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/module.h>
#include <linux/kobject.h>
#include <asm/uaccess.h>
#include <linux/gfs2_ondisk.h>
#include <linux/genhd.h>

#include "gfs2.h"
#include "incore.h"
#include "sys.h"
#include "super.h"
#include "glock.h"
#include "quota.h"
#include "util.h"
#include "glops.h"
#include "recovery.h"

struct gfs2_attr {
	struct attribute attr;
	ssize_t (*show)(struct gfs2_sbd *, char *);
	ssize_t (*store)(struct gfs2_sbd *, const char *, size_t);
};

static ssize_t gfs2_attr_show(struct kobject *kobj, struct attribute *attr,
			      char *buf)
{
	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
	struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr);
	return a->show ? a->show(sdp, buf) : 0;
}

static ssize_t gfs2_attr_store(struct kobject *kobj, struct attribute *attr,
			       const char *buf, size_t len)
{
	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
	struct gfs2_attr *a = container_of(attr, struct gfs2_attr, attr);
	return a->store ? a->store(sdp, buf, len) : len;
}

static const struct sysfs_ops gfs2_attr_ops = {
	.show  = gfs2_attr_show,
	.store = gfs2_attr_store,
};


static struct kset *gfs2_kset;

static ssize_t id_show(struct gfs2_sbd *sdp, char *buf)
{
	return snprintf(buf, PAGE_SIZE, "%u:%u\n",
			MAJOR(sdp->sd_vfs->s_dev), MINOR(sdp->sd_vfs->s_dev));
}

static ssize_t fsname_show(struct gfs2_sbd *sdp, char *buf)
{
	return snprintf(buf, PAGE_SIZE, "%s\n", sdp->sd_fsname);
}

static int gfs2_uuid_valid(const u8 *uuid)
{
	int i;

	for (i = 0; i < 16; i++) {
		if (uuid[i])
			return 1;
	}
	return 0;
}

static ssize_t uuid_show(struct gfs2_sbd *sdp, char *buf)
{
	struct super_block *s = sdp->sd_vfs;
	const u8 *uuid = s->s_uuid;
	buf[0] = '\0';
	if (!gfs2_uuid_valid(uuid))
		return 0;
	return snprintf(buf, PAGE_SIZE, "%pUB\n", uuid);
}

static ssize_t freeze_show(struct gfs2_sbd *sdp, char *buf)
{
	struct super_block *sb = sdp->sd_vfs;
	int frozen = (sb->s_writers.frozen == SB_UNFROZEN) ? 0 : 1;

	return snprintf(buf, PAGE_SIZE, "%u\n", frozen);
}

static ssize_t freeze_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
{
	int error;
	int n = simple_strtol(buf, NULL, 0);

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	switch (n) {
	case 0:
		error = thaw_super(sdp->sd_vfs);
		break;
	case 1:
		error = freeze_super(sdp->sd_vfs);
		break;
	default:
		return -EINVAL;
	}

	if (error) {
		fs_warn(sdp, "freeze %d error %d", n, error);
		return error;
	}

	return len;
}

static ssize_t withdraw_show(struct gfs2_sbd *sdp, char *buf)
{
	unsigned int b = test_bit(SDF_SHUTDOWN, &sdp->sd_flags);
	return snprintf(buf, PAGE_SIZE, "%u\n", b);
}

static ssize_t withdraw_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
{
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (simple_strtol(buf, NULL, 0) != 1)
		return -EINVAL;

	gfs2_lm_withdraw(sdp, "withdrawing from cluster at user's request\n");

	return len;
}

static ssize_t statfs_sync_store(struct gfs2_sbd *sdp, const char *buf,
				 size_t len)
{
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (simple_strtol(buf, NULL, 0) != 1)
		return -EINVAL;

	gfs2_statfs_sync(sdp->sd_vfs, 0);
	return len;
}

static ssize_t quota_sync_store(struct gfs2_sbd *sdp, const char *buf,
				size_t len)
{
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (simple_strtol(buf, NULL, 0) != 1)
		return -EINVAL;

	gfs2_quota_sync(sdp->sd_vfs, 0);
	return len;
}

static ssize_t quota_refresh_user_store(struct gfs2_sbd *sdp, const char *buf,
					size_t len)
{
	struct kqid qid;
	int error;
	u32 id;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	id = simple_strtoul(buf, NULL, 0);

	qid = make_kqid(current_user_ns(), USRQUOTA, id);
	if (!qid_valid(qid))
		return -EINVAL;

	error = gfs2_quota_refresh(sdp, qid);
	return error ? error : len;
}

static ssize_t quota_refresh_group_store(struct gfs2_sbd *sdp, const char *buf,
					 size_t len)
{
	struct kqid qid;
	int error;
	u32 id;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	id = simple_strtoul(buf, NULL, 0);

	qid = make_kqid(current_user_ns(), GRPQUOTA, id);
	if (!qid_valid(qid))
		return -EINVAL;

	error = gfs2_quota_refresh(sdp, qid);
	return error ? error : len;
}

static ssize_t demote_rq_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
{
	struct gfs2_glock *gl;
	const struct gfs2_glock_operations *glops;
	unsigned int glmode;
	unsigned int gltype;
	unsigned long long glnum;
	char mode[16];
	int rv;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	rv = sscanf(buf, "%u:%llu %15s", &gltype, &glnum,
		    mode);
	if (rv != 3)
		return -EINVAL;

	if (strcmp(mode, "EX") == 0)
		glmode = LM_ST_UNLOCKED;
	else if ((strcmp(mode, "CW") == 0) || (strcmp(mode, "DF") == 0))
		glmode = LM_ST_DEFERRED;
	else if ((strcmp(mode, "PR") == 0) || (strcmp(mode, "SH") == 0))
		glmode = LM_ST_SHARED;
	else
		return -EINVAL;

	if (gltype > LM_TYPE_JOURNAL)
		return -EINVAL;
	if (gltype == LM_TYPE_NONDISK && glnum == GFS2_TRANS_LOCK)
		glops = &gfs2_trans_glops;
	else
		glops = gfs2_glops_list[gltype];
	if (glops == NULL)
		return -EINVAL;
	if (!test_and_set_bit(SDF_DEMOTE, &sdp->sd_flags))
		fs_info(sdp, "demote interface used\n");
	rv = gfs2_glock_get(sdp, glnum, glops, 0, &gl);
	if (rv)
		return rv;
	gfs2_glock_cb(gl, glmode);
	gfs2_glock_put(gl);
	return len;
}


#define GFS2_ATTR(name, mode, show, store) \
static struct gfs2_attr gfs2_attr_##name = __ATTR(name, mode, show, store)

GFS2_ATTR(id,                  0444, id_show,       NULL);
GFS2_ATTR(fsname,              0444, fsname_show,   NULL);
GFS2_ATTR(uuid,                0444, uuid_show,     NULL);
GFS2_ATTR(freeze,              0644, freeze_show,   freeze_store);
GFS2_ATTR(withdraw,            0644, withdraw_show, withdraw_store);
GFS2_ATTR(statfs_sync,         0200, NULL,          statfs_sync_store);
GFS2_ATTR(quota_sync,          0200, NULL,          quota_sync_store);
GFS2_ATTR(quota_refresh_user,  0200, NULL,          quota_refresh_user_store);
GFS2_ATTR(quota_refresh_group, 0200, NULL,          quota_refresh_group_store);
GFS2_ATTR(demote_rq,           0200, NULL,	    demote_rq_store);

static struct attribute *gfs2_attrs[] = {
	&gfs2_attr_id.attr,
	&gfs2_attr_fsname.attr,
	&gfs2_attr_uuid.attr,
	&gfs2_attr_freeze.attr,
	&gfs2_attr_withdraw.attr,
	&gfs2_attr_statfs_sync.attr,
	&gfs2_attr_quota_sync.attr,
	&gfs2_attr_quota_refresh_user.attr,
	&gfs2_attr_quota_refresh_group.attr,
	&gfs2_attr_demote_rq.attr,
	NULL,
};

static void gfs2_sbd_release(struct kobject *kobj)
{
	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);

	kfree(sdp);
}

static struct kobj_type gfs2_ktype = {
	.release = gfs2_sbd_release,
	.default_attrs = gfs2_attrs,
	.sysfs_ops     = &gfs2_attr_ops,
};


/*
 * lock_module. Originally from lock_dlm
 */

static ssize_t proto_name_show(struct gfs2_sbd *sdp, char *buf)
{
	const struct lm_lockops *ops = sdp->sd_lockstruct.ls_ops;
	return sprintf(buf, "%s\n", ops->lm_proto_name);
}

static ssize_t block_show(struct gfs2_sbd *sdp, char *buf)
{
	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
	ssize_t ret;
	int val = 0;

	if (test_bit(DFL_BLOCK_LOCKS, &ls->ls_recover_flags))
		val = 1;
	ret = sprintf(buf, "%d\n", val);
	return ret;
}

static ssize_t block_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
{
	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
	ssize_t ret = len;
	int val;

	val = simple_strtol(buf, NULL, 0);

	if (val == 1)
		set_bit(DFL_BLOCK_LOCKS, &ls->ls_recover_flags);
	else if (val == 0) {
		clear_bit(DFL_BLOCK_LOCKS, &ls->ls_recover_flags);
		smp_mb__after_atomic();
		gfs2_glock_thaw(sdp);
	} else {
		ret = -EINVAL;
	}
	return ret;
}

static ssize_t wdack_show(struct gfs2_sbd *sdp, char *buf)
{
	int val = completion_done(&sdp->sd_wdack) ? 1 : 0;

	return sprintf(buf, "%d\n", val);
}

static ssize_t wdack_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
{
	ssize_t ret = len;
	int val;

	val = simple_strtol(buf, NULL, 0);

	if ((val == 1) &&
	    !strcmp(sdp->sd_lockstruct.ls_ops->lm_proto_name, "lock_dlm"))
		complete(&sdp->sd_wdack);
	else
		ret = -EINVAL;
	return ret;
}

static ssize_t lkfirst_show(struct gfs2_sbd *sdp, char *buf)
{
	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
	return sprintf(buf, "%d\n", ls->ls_first);
}

static ssize_t lkfirst_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
{
	unsigned first;
	int rv;

	rv = sscanf(buf, "%u", &first);
	if (rv != 1 || first > 1)
		return -EINVAL;
	rv = wait_for_completion_killable(&sdp->sd_locking_init);
	if (rv)
		return rv;
	spin_lock(&sdp->sd_jindex_spin);
	rv = -EBUSY;
	if (test_bit(SDF_NOJOURNALID, &sdp->sd_flags) == 0)
		goto out;
	rv = -EINVAL;
	if (sdp->sd_args.ar_spectator)
		goto out;
	if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
		goto out;
	sdp->sd_lockstruct.ls_first = first;
	rv = 0;
out:
        spin_unlock(&sdp->sd_jindex_spin);
        return rv ? rv : len;
}

static ssize_t first_done_show(struct gfs2_sbd *sdp, char *buf)
{
	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
	return sprintf(buf, "%d\n", !!test_bit(DFL_FIRST_MOUNT_DONE, &ls->ls_recover_flags));
}

int gfs2_recover_set(struct gfs2_sbd *sdp, unsigned jid)
{
	struct gfs2_jdesc *jd;
	int rv;

	spin_lock(&sdp->sd_jindex_spin);
	rv = -EBUSY;
	if (sdp->sd_jdesc->jd_jid == jid)
		goto out;
	rv = -ENOENT;
	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
		if (jd->jd_jid != jid)
			continue;
		rv = gfs2_recover_journal(jd, false);
		break;
	}
out:
	spin_unlock(&sdp->sd_jindex_spin);
	return rv;
}

static ssize_t recover_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
{
	unsigned jid;
	int rv;

	rv = sscanf(buf, "%u", &jid);
	if (rv != 1)
		return -EINVAL;

	if (test_bit(SDF_NORECOVERY, &sdp->sd_flags)) {
		rv = -ESHUTDOWN;
		goto out;
	}

	rv = gfs2_recover_set(sdp, jid);
out:
	return rv ? rv : len;
}

static ssize_t recover_done_show(struct gfs2_sbd *sdp, char *buf)
{
	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
	return sprintf(buf, "%d\n", ls->ls_recover_jid_done);
}

static ssize_t recover_status_show(struct gfs2_sbd *sdp, char *buf)
{
	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
	return sprintf(buf, "%d\n", ls->ls_recover_jid_status);
}

static ssize_t jid_show(struct gfs2_sbd *sdp, char *buf)
{
	return sprintf(buf, "%d\n", sdp->sd_lockstruct.ls_jid);
}

static ssize_t jid_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
{
        int jid;
	int rv;

	rv = sscanf(buf, "%d", &jid);
	if (rv != 1)
		return -EINVAL;
	rv = wait_for_completion_killable(&sdp->sd_locking_init);
	if (rv)
		return rv;
	spin_lock(&sdp->sd_jindex_spin);
	rv = -EINVAL;
	if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
		goto out;
	rv = -EBUSY;
	if (test_bit(SDF_NOJOURNALID, &sdp->sd_flags) == 0)
		goto out;
	rv = 0;
	if (sdp->sd_args.ar_spectator && jid > 0)
		rv = jid = -EINVAL;
	sdp->sd_lockstruct.ls_jid = jid;
	clear_bit(SDF_NOJOURNALID, &sdp->sd_flags);
	smp_mb__after_atomic();
	wake_up_bit(&sdp->sd_flags, SDF_NOJOURNALID);
out:
	spin_unlock(&sdp->sd_jindex_spin);
	return rv ? rv : len;
}

#define GDLM_ATTR(_name,_mode,_show,_store) \
static struct gfs2_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store)

GDLM_ATTR(proto_name,		0444, proto_name_show,		NULL);
GDLM_ATTR(block,		0644, block_show,		block_store);
GDLM_ATTR(withdraw,		0644, wdack_show,		wdack_store);
GDLM_ATTR(jid,			0644, jid_show,			jid_store);
GDLM_ATTR(first,		0644, lkfirst_show,		lkfirst_store);
GDLM_ATTR(first_done,		0444, first_done_show,		NULL);
GDLM_ATTR(recover,		0600, NULL,			recover_store);
GDLM_ATTR(recover_done,		0444, recover_done_show,	NULL);
GDLM_ATTR(recover_status,	0444, recover_status_show,	NULL);

static struct attribute *lock_module_attrs[] = {
	&gdlm_attr_proto_name.attr,
	&gdlm_attr_block.attr,
	&gdlm_attr_withdraw.attr,
	&gdlm_attr_jid.attr,
	&gdlm_attr_first.attr,
	&gdlm_attr_first_done.attr,
	&gdlm_attr_recover.attr,
	&gdlm_attr_recover_done.attr,
	&gdlm_attr_recover_status.attr,
	NULL,
};

/*
 * get and set struct gfs2_tune fields
 */

static ssize_t quota_scale_show(struct gfs2_sbd *sdp, char *buf)
{
	return snprintf(buf, PAGE_SIZE, "%u %u\n",
			sdp->sd_tune.gt_quota_scale_num,
			sdp->sd_tune.gt_quota_scale_den);
}

static ssize_t quota_scale_store(struct gfs2_sbd *sdp, const char *buf,
				 size_t len)
{
	struct gfs2_tune *gt = &sdp->sd_tune;
	unsigned int x, y;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (sscanf(buf, "%u %u", &x, &y) != 2 || !y)
		return -EINVAL;

	spin_lock(&gt->gt_spin);
	gt->gt_quota_scale_num = x;
	gt->gt_quota_scale_den = y;
	spin_unlock(&gt->gt_spin);
	return len;
}

static ssize_t tune_set(struct gfs2_sbd *sdp, unsigned int *field,
			int check_zero, const char *buf, size_t len)
{
	struct gfs2_tune *gt = &sdp->sd_tune;
	unsigned int x;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	x = simple_strtoul(buf, NULL, 0);

	if (check_zero && !x)
		return -EINVAL;

	spin_lock(&gt->gt_spin);
	*field = x;
	spin_unlock(&gt->gt_spin);
	return len;
}

#define TUNE_ATTR_3(name, show, store)                                        \
static struct gfs2_attr tune_attr_##name = __ATTR(name, 0644, show, store)

#define TUNE_ATTR_2(name, store)                                              \
static ssize_t name##_show(struct gfs2_sbd *sdp, char *buf)                   \
{                                                                             \
	return snprintf(buf, PAGE_SIZE, "%u\n", sdp->sd_tune.gt_##name);      \
}                                                                             \
TUNE_ATTR_3(name, name##_show, store)

#define TUNE_ATTR(name, check_zero)                                           \
static ssize_t name##_store(struct gfs2_sbd *sdp, const char *buf, size_t len)\
{                                                                             \
	return tune_set(sdp, &sdp->sd_tune.gt_##name, check_zero, buf, len);  \
}                                                                             \
TUNE_ATTR_2(name, name##_store)

TUNE_ATTR(quota_warn_period, 0);
TUNE_ATTR(quota_quantum, 0);
TUNE_ATTR(max_readahead, 0);
TUNE_ATTR(complain_secs, 0);
TUNE_ATTR(statfs_slow, 0);
TUNE_ATTR(new_files_jdata, 0);
TUNE_ATTR(statfs_quantum, 1);
TUNE_ATTR_3(quota_scale, quota_scale_show, quota_scale_store);

static struct attribute *tune_attrs[] = {
	&tune_attr_quota_warn_period.attr,
	&tune_attr_quota_quantum.attr,
	&tune_attr_max_readahead.attr,
	&tune_attr_complain_secs.attr,
	&tune_attr_statfs_slow.attr,
	&tune_attr_statfs_quantum.attr,
	&tune_attr_quota_scale.attr,
	&tune_attr_new_files_jdata.attr,
	NULL,
};

static struct attribute_group tune_group = {
	.name = "tune",
	.attrs = tune_attrs,
};

static struct attribute_group lock_module_group = {
	.name = "lock_module",
	.attrs = lock_module_attrs,
};

int gfs2_sys_fs_add(struct gfs2_sbd *sdp)
{
	struct super_block *sb = sdp->sd_vfs;
	int error;
	char ro[20];
	char spectator[20];
	char *envp[] = { ro, spectator, NULL };
	int sysfs_frees_sdp = 0;

	sprintf(ro, "RDONLY=%d", (sb->s_flags & MS_RDONLY) ? 1 : 0);
	sprintf(spectator, "SPECTATOR=%d", sdp->sd_args.ar_spectator ? 1 : 0);

	sdp->sd_kobj.kset = gfs2_kset;
	error = kobject_init_and_add(&sdp->sd_kobj, &gfs2_ktype, NULL,
				     "%s", sdp->sd_table_name);
	if (error)
		goto fail_reg;

	sysfs_frees_sdp = 1; /* Freeing sdp is now done by sysfs calling
				function gfs2_sbd_release. */
	error = sysfs_create_group(&sdp->sd_kobj, &tune_group);
	if (error)
		goto fail_reg;

	error = sysfs_create_group(&sdp->sd_kobj, &lock_module_group);
	if (error)
		goto fail_tune;

	error = sysfs_create_link(&sdp->sd_kobj,
				  &disk_to_dev(sb->s_bdev->bd_disk)->kobj,
				  "device");
	if (error)
		goto fail_lock_module;

	kobject_uevent_env(&sdp->sd_kobj, KOBJ_ADD, envp);
	return 0;

fail_lock_module:
	sysfs_remove_group(&sdp->sd_kobj, &lock_module_group);
fail_tune:
	sysfs_remove_group(&sdp->sd_kobj, &tune_group);
fail_reg:
	free_percpu(sdp->sd_lkstats);
	fs_err(sdp, "error %d adding sysfs files", error);
	if (sysfs_frees_sdp)
		kobject_put(&sdp->sd_kobj);
	else
		kfree(sdp);
	sb->s_fs_info = NULL;
	return error;
}

void gfs2_sys_fs_del(struct gfs2_sbd *sdp)
{
	sysfs_remove_link(&sdp->sd_kobj, "device");
	sysfs_remove_group(&sdp->sd_kobj, &tune_group);
	sysfs_remove_group(&sdp->sd_kobj, &lock_module_group);
	kobject_put(&sdp->sd_kobj);
}

static int gfs2_uevent(struct kset *kset, struct kobject *kobj,
		       struct kobj_uevent_env *env)
{
	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
	struct super_block *s = sdp->sd_vfs;
	const u8 *uuid = s->s_uuid;

	add_uevent_var(env, "LOCKTABLE=%s", sdp->sd_table_name);
	add_uevent_var(env, "LOCKPROTO=%s", sdp->sd_proto_name);
	if (!test_bit(SDF_NOJOURNALID, &sdp->sd_flags))
		add_uevent_var(env, "JOURNALID=%d", sdp->sd_lockstruct.ls_jid);
	if (gfs2_uuid_valid(uuid))
		add_uevent_var(env, "UUID=%pUB", uuid);
	return 0;
}

static const struct kset_uevent_ops gfs2_uevent_ops = {
	.uevent = gfs2_uevent,
};

int gfs2_sys_init(void)
{
	gfs2_kset = kset_create_and_add("gfs2", &gfs2_uevent_ops, fs_kobj);
	if (!gfs2_kset)
		return -ENOMEM;
	return 0;
}

void gfs2_sys_uninit(void)
{
	kset_unregister(gfs2_kset);
}

="hl opt">) { vunmap_page_range(va->va_start, va->va_end); } static void vmap_debug_free_range(unsigned long start, unsigned long end) { /* * Unmap page tables and force a TLB flush immediately if * CONFIG_DEBUG_PAGEALLOC is set. This catches use after free * bugs similarly to those in linear kernel virtual address * space after a page has been freed. * * All the lazy freeing logic is still retained, in order to * minimise intrusiveness of this debugging feature. * * This is going to be *slow* (linear kernel virtual address * debugging doesn't do a broadcast TLB flush so it is a lot * faster). */ #ifdef CONFIG_DEBUG_PAGEALLOC vunmap_page_range(start, end); flush_tlb_kernel_range(start, end); #endif } /* * lazy_max_pages is the maximum amount of virtual address space we gather up * before attempting to purge with a TLB flush. * * There is a tradeoff here: a larger number will cover more kernel page tables * and take slightly longer to purge, but it will linearly reduce the number of * global TLB flushes that must be performed. It would seem natural to scale * this number up linearly with the number of CPUs (because vmapping activity * could also scale linearly with the number of CPUs), however it is likely * that in practice, workloads might be constrained in other ways that mean * vmap activity will not scale linearly with CPUs. Also, I want to be * conservative and not introduce a big latency on huge systems, so go with * a less aggressive log scale. It will still be an improvement over the old * code, and it will be simple to change the scale factor if we find that it * becomes a problem on bigger systems. */ static unsigned long lazy_max_pages(void) { unsigned int log; log = fls(num_online_cpus()); return log * (32UL * 1024 * 1024 / PAGE_SIZE); } static atomic_t vmap_lazy_nr = ATOMIC_INIT(0); /* * Purges all lazily-freed vmap areas. * * If sync is 0 then don't purge if there is already a purge in progress. * If force_flush is 1, then flush kernel TLBs between *start and *end even * if we found no lazy vmap areas to unmap (callers can use this to optimise * their own TLB flushing). * Returns with *start = min(*start, lowest purged address) * *end = max(*end, highest purged address) */ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end, int sync, int force_flush) { static DEFINE_SPINLOCK(purge_lock); LIST_HEAD(valist); struct vmap_area *va; int nr = 0; /* * If sync is 0 but force_flush is 1, we'll go sync anyway but callers * should not expect such behaviour. This just simplifies locking for * the case that isn't actually used at the moment anyway. */ if (!sync && !force_flush) { if (!spin_trylock(&purge_lock)) return; } else spin_lock(&purge_lock); rcu_read_lock(); list_for_each_entry_rcu(va, &vmap_area_list, list) { if (va->flags & VM_LAZY_FREE) { if (va->va_start < *start) *start = va->va_start; if (va->va_end > *end) *end = va->va_end; nr += (va->va_end - va->va_start) >> PAGE_SHIFT; unmap_vmap_area(va); list_add_tail(&va->purge_list, &valist); va->flags |= VM_LAZY_FREEING; va->flags &= ~VM_LAZY_FREE; } } rcu_read_unlock(); if (nr) { BUG_ON(nr > atomic_read(&vmap_lazy_nr)); atomic_sub(nr, &vmap_lazy_nr); } if (nr || force_flush) flush_tlb_kernel_range(*start, *end); if (nr) { spin_lock(&vmap_area_lock); list_for_each_entry(va, &valist, purge_list) __free_vmap_area(va); spin_unlock(&vmap_area_lock); } spin_unlock(&purge_lock); } /* * Kick off a purge of the outstanding lazy areas. Don't bother if somebody * is already purging. */ static void try_purge_vmap_area_lazy(void) { unsigned long start = ULONG_MAX, end = 0; __purge_vmap_area_lazy(&start, &end, 0, 0); } /* * Kick off a purge of the outstanding lazy areas. */ static void purge_vmap_area_lazy(void) { unsigned long start = ULONG_MAX, end = 0; __purge_vmap_area_lazy(&start, &end, 1, 0); } /* * Free and unmap a vmap area, caller ensuring flush_cache_vunmap had been * called for the correct range previously. */ static void free_unmap_vmap_area_noflush(struct vmap_area *va) { va->flags |= VM_LAZY_FREE; atomic_add((va->va_end - va->va_start) >> PAGE_SHIFT, &vmap_lazy_nr); if (unlikely(atomic_read(&vmap_lazy_nr) > lazy_max_pages())) try_purge_vmap_area_lazy(); } /* * Free and unmap a vmap area */ static void free_unmap_vmap_area(struct vmap_area *va) { flush_cache_vunmap(va->va_start, va->va_end); free_unmap_vmap_area_noflush(va); } static struct vmap_area *find_vmap_area(unsigned long addr) { struct vmap_area *va; spin_lock(&vmap_area_lock); va = __find_vmap_area(addr); spin_unlock(&vmap_area_lock); return va; } static void free_unmap_vmap_area_addr(unsigned long addr) { struct vmap_area *va; va = find_vmap_area(addr); BUG_ON(!va); free_unmap_vmap_area(va); } /*** Per cpu kva allocator ***/ /* * vmap space is limited especially on 32 bit architectures. Ensure there is * room for at least 16 percpu vmap blocks per CPU. */ /* * If we had a constant VMALLOC_START and VMALLOC_END, we'd like to be able * to #define VMALLOC_SPACE (VMALLOC_END-VMALLOC_START). Guess * instead (we just need a rough idea) */ #if BITS_PER_LONG == 32 #define VMALLOC_SPACE (128UL*1024*1024) #else #define VMALLOC_SPACE (128UL*1024*1024*1024) #endif #define VMALLOC_PAGES (VMALLOC_SPACE / PAGE_SIZE) #define VMAP_MAX_ALLOC BITS_PER_LONG /* 256K with 4K pages */ #define VMAP_BBMAP_BITS_MAX 1024 /* 4MB with 4K pages */ #define VMAP_BBMAP_BITS_MIN (VMAP_MAX_ALLOC*2) #define VMAP_MIN(x, y) ((x) < (y) ? (x) : (y)) /* can't use min() */ #define VMAP_MAX(x, y) ((x) > (y) ? (x) : (y)) /* can't use max() */ #define VMAP_BBMAP_BITS VMAP_MIN(VMAP_BBMAP_BITS_MAX, \ VMAP_MAX(VMAP_BBMAP_BITS_MIN, \ VMALLOC_PAGES / NR_CPUS / 16)) #define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE) static bool vmap_initialized __read_mostly = false; struct vmap_block_queue { spinlock_t lock; struct list_head free; struct list_head dirty; unsigned int nr_dirty; }; struct vmap_block { spinlock_t lock; struct vmap_area *va; struct vmap_block_queue *vbq; unsigned long free, dirty; DECLARE_BITMAP(alloc_map, VMAP_BBMAP_BITS); DECLARE_BITMAP(dirty_map, VMAP_BBMAP_BITS); union { struct { struct list_head free_list; struct list_head dirty_list; }; struct rcu_head rcu_head; }; }; /* Queue of free and dirty vmap blocks, for allocation and flushing purposes */ static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue); /* * Radix tree of vmap blocks, indexed by address, to quickly find a vmap block * in the free path. Could get rid of this if we change the API to return a * "cookie" from alloc, to be passed to free. But no big deal yet. */ static DEFINE_SPINLOCK(vmap_block_tree_lock); static RADIX_TREE(vmap_block_tree, GFP_ATOMIC); /* * We should probably have a fallback mechanism to allocate virtual memory * out of partially filled vmap blocks. However vmap block sizing should be * fairly reasonable according to the vmalloc size, so it shouldn't be a * big problem. */ static unsigned long addr_to_vb_idx(unsigned long addr) { addr -= VMALLOC_START & ~(VMAP_BLOCK_SIZE-1); addr /= VMAP_BLOCK_SIZE; return addr; } static struct vmap_block *new_vmap_block(gfp_t gfp_mask) { struct vmap_block_queue *vbq; struct vmap_block *vb; struct vmap_area *va; unsigned long vb_idx; int node, err; node = numa_node_id(); vb = kmalloc_node(sizeof(struct vmap_block), gfp_mask & GFP_RECLAIM_MASK, node); if (unlikely(!vb)) return ERR_PTR(-ENOMEM); va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE, VMALLOC_START, VMALLOC_END, node, gfp_mask); if (unlikely(IS_ERR(va))) { kfree(vb); return ERR_PTR(PTR_ERR(va)); } err = radix_tree_preload(gfp_mask); if (unlikely(err)) { kfree(vb); free_vmap_area(va); return ERR_PTR(err); } spin_lock_init(&vb->lock); vb->va = va; vb->free = VMAP_BBMAP_BITS; vb->dirty = 0; bitmap_zero(vb->alloc_map, VMAP_BBMAP_BITS); bitmap_zero(vb->dirty_map, VMAP_BBMAP_BITS); INIT_LIST_HEAD(&vb->free_list); INIT_LIST_HEAD(&vb->dirty_list); vb_idx = addr_to_vb_idx(va->va_start); spin_lock(&vmap_block_tree_lock); err = radix_tree_insert(&vmap_block_tree, vb_idx, vb); spin_unlock(&vmap_block_tree_lock); BUG_ON(err); radix_tree_preload_end(); vbq = &get_cpu_var(vmap_block_queue); vb->vbq = vbq; spin_lock(&vbq->lock); list_add(&vb->free_list, &vbq->free);