summaryrefslogtreecommitdiffstats
path: root/fs/gfs2/ops_super.c
blob: bd08a0a8d9bfb708b8c4084c732847d04944d488 (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
/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2008 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.
 */

#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/statfs.h>
#include <linux/seq_file.h>
#include <linux/mount.h>
#include <linux/kthread.h>
#include <linux/delay.h>
#include <linux/gfs2_ondisk.h>
#include <linux/crc32.h>
#include <linux/lm_interface.h>
#include <linux/time.h>

#include "gfs2.h"
#include "incore.h"
#include "glock.h"
#include "inode.h"
#include "log.h"
#include "mount.h"
#include "quota.h"
#include "recovery.h"
#include "rgrp.h"
#include "super.h"
#include "sys.h"
#include "util.h"
#include "trans.h"
#include "dir.h"
#include "eattr.h"
#include "bmap.h"
#include "meta_io.h"

/**
 * gfs2_write_inode - Make sure the inode is stable on the disk
 * @inode: The inode
 * @sync: synchronous write flag
 *
 * Returns: errno
 */

static int gfs2_write_inode(struct inode *inode, int sync)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	struct gfs2_holder gh;
	struct buffer_head *bh;
	struct timespec atime;
	struct gfs2_dinode *di;
	int ret = 0;

	/* Check this is a "normal" inode, etc */
	if (!test_bit(GIF_USER, &ip->i_flags) ||
	    (current->flags & PF_MEMALLOC))
		return 0;
	ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
	if (ret)
		goto do_flush;
	ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
	if (ret)
		goto do_unlock;
	ret = gfs2_meta_inode_buffer(ip, &bh);
	if (ret == 0) {
		di = (struct gfs2_dinode *)bh->b_data;
		atime.tv_sec = be64_to_cpu(di->di_atime);
		atime.tv_nsec = be32_to_cpu(di->di_atime_nsec);
		if (timespec_compare(&inode->i_atime, &atime) > 0) {
			gfs2_trans_add_bh(ip->i_gl, bh, 1);
			gfs2_dinode_out(ip, bh->b_data);
		}
		brelse(bh);
	}
	gfs2_trans_end(sdp);
do_unlock:
	gfs2_glock_dq_uninit(&gh);
do_flush:
	if (sync != 0)
		gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
	return ret;
}

/**
 * gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one
 * @sdp: the filesystem
 *
 * Returns: errno
 */

int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
{
	struct gfs2_holder t_gh;
	int error;

	gfs2_quota_sync(sdp);
	gfs2_statfs_sync(sdp);

	error = gfs2_glock_nq_init(sdp->sd_trans_gl, LM_ST_SHARED, GL_NOCACHE,
				   &t_gh);
	if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
		return error;

	gfs2_meta_syncfs(sdp);
	gfs2_log_shutdown(sdp);

	clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);

	if (t_gh.gh_gl)
		gfs2_glock_dq_uninit(&t_gh);

	gfs2_quota_cleanup(sdp);

	return error;
}

/**
 * gfs2_write_super
 * @sb: the superblock
 *
 */

static void gfs2_write_super(struct super_block *sb)
{
	sb->s_dirt = 0;
}

/**
 * gfs2_sync_fs - sync the filesystem
 * @sb: the superblock
 *
 * Flushes the log to disk.
 */

static int gfs2_sync_fs(struct super_block *sb, int wait)
{
	sb->s_dirt = 0;
	if (wait && sb->s_fs_info)
		gfs2_log_flush(sb->s_fs_info, NULL);
	return 0;
}

/**
 * gfs2_write_super_lockfs - prevent further writes to the filesystem
 * @sb: the VFS structure for the filesystem
 *
 */

static void gfs2_write_super_lockfs(struct super_block *sb)
{
	struct gfs2_sbd *sdp = sb->s_fs_info;
	int error;

	if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
		return;

	for (;;) {
		error = gfs2_freeze_fs(sdp);
		if (!error)
			break;

		switch (error) {
		case -EBUSY:
			fs_err(sdp, "waiting for recovery before freeze\n");
			break;

		default:
			fs_err(sdp, "error freezing FS: %d\n", error);
			break;
		}

		fs_err(sdp, "retrying...\n");
		msleep(1000);
	}
}

/**
 * gfs2_unlockfs - reallow writes to the filesystem
 * @sb: the VFS structure for the filesystem
 *
 */

static void gfs2_unlockfs(struct super_block *sb)
{
	gfs2_unfreeze_fs(sb->s_fs_info);
}

/**
 * statfs_fill - fill in the sg for a given RG
 * @rgd: the RG
 * @sc: the sc structure
 *
 * Returns: 0 on success, -ESTALE if the LVB is invalid
 */

static int statfs_slow_fill(struct gfs2_rgrpd *rgd,
			    struct gfs2_statfs_change_host *sc)
{
	gfs2_rgrp_verify(rgd);
	sc->sc_total += rgd->rd_data;
	sc->sc_free += rgd->rd_free;
	sc->sc_dinodes += rgd->rd_dinodes;
	return 0;
}

/**
 * gfs2_statfs_slow - Stat a filesystem using asynchronous locking
 * @sdp: the filesystem
 * @sc: the sc info that will be returned
 *
 * Any error (other than a signal) will cause this routine to fall back
 * to the synchronous version.
 *
 * FIXME: This really shouldn't busy wait like this.
 *
 * Returns: errno
 */

static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
{
	struct gfs2_holder ri_gh;
	struct gfs2_rgrpd *rgd_next;
	struct gfs2_holder *gha, *gh;
	unsigned int slots = 64;
	unsigned int x;
	int done;
	int error = 0, err;

	memset(sc, 0, sizeof(struct gfs2_statfs_change_host));
	gha = kcalloc(slots, sizeof(struct gfs2_holder), GFP_KERNEL);
	if (!gha)
		return -ENOMEM;

	error = gfs2_rindex_hold(sdp, &ri_gh);
	if (error)
		goto out;

	rgd_next = gfs2_rgrpd_get_first(sdp);

	for (;;) {
		done = 1;

		for (x = 0; x < slots; x++) {
			gh = gha + x;

			if (gh->gh_gl && gfs2_glock_poll(gh)) {
				err = gfs2_glock_wait(gh);
				if (err) {
					gfs2_holder_uninit(gh);
					error = err;
				} else {
					if (!error)
						error = statfs_slow_fill(
							gh->gh_gl->gl_object, sc);
					gfs2_glock_dq_uninit(gh);
				}
			}

			if (gh->gh_gl)
				done = 0;
			else if (rgd_next && !error) {
				error = gfs2_glock_nq_init(rgd_next->rd_gl,
							   LM_ST_SHARED,
							   GL_ASYNC,
							   gh);
				rgd_next = gfs2_rgrpd_get_next(rgd_next);
				done = 0;
			}

			if (signal_pending(current))
				error = -ERESTARTSYS;
		}

		if (done)
			break;

		yield();
	}

	gfs2_glock_dq_uninit(&ri_gh);

out:
	kfree(gha);
	return error;
}

/**
 * gfs2_statfs_i - Do a statfs
 * @sdp: the filesystem
 * @sg: the sg structure
 *
 * Returns: errno
 */

static int gfs2_statfs_i(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
{
	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;

	spin_lock(&sdp->sd_statfs_spin);

	*sc = *m_sc;
	sc->sc_total += l_sc->sc_total;
	sc->sc_free += l_sc->sc_free;
	sc->sc_dinodes += l_sc->sc_dinodes;

	spin_unlock(&sdp->sd_statfs_spin);

	if (sc->sc_free < 0)
		sc->sc_free = 0;
	if (sc->sc_free > sc->sc_total)
		sc->sc_free = sc->sc_total;
	if (sc->sc_dinodes < 0)
		sc->sc_dinodes = 0;

	return 0;
}

/**
 * gfs2_statfs - Gather and return stats about the filesystem
 * @sb: The superblock
 * @statfsbuf: The buffer
 *
 * Returns: 0 on success or error code
 */

static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct super_block *sb = dentry->d_inode->i_sb;
	struct gfs2_sbd *sdp = sb->s_fs_info;
	struct gfs2_statfs_change_host sc;
	int error;

	if (gfs2_tune_get(sdp, gt_statfs_slow))
		error = gfs2_statfs_slow(sdp, &sc);
	else
		error = gfs2_statfs_i(sdp, &sc);

	if (error)
		return error;

	buf->f_type = GFS2_MAGIC;
	buf->f_bsize = sdp->sd_sb.sb_bsize;
	buf->f_blocks = sc.sc_total;
	buf->f_bfree = sc.sc_free;
	buf->f_bavail = sc.sc_free;
	buf->f_files = sc.sc_dinodes + sc.sc_free;
	buf->f_ffree = sc.sc_free;
	buf->f_namelen = GFS2_FNAMESIZE;

	return 0;
}

/**
 * gfs2_remount_fs - called when the FS is remounted
 * @sb:  the filesystem
 * @flags:  the remount flags
 * @data:  extra data passed in (not used right now)
 *
 * Returns: errno
 */

static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
{
	struct gfs2_sbd *sdp = sb->s_fs_info;
	int error;

	error = gfs2_mount_args(sdp, data, 1);
	if (error)
		return error;

	if (sdp->sd_args.ar_spectator)
		*flags |= MS_RDONLY;
	else {
		if (*flags & MS_RDONLY) {
			if (!(sb->s_flags & MS_RDONLY))
				error = gfs2_make_fs_ro(sdp);
		} else if (!(*flags & MS_RDONLY) &&
			   (sb->s_flags & MS_RDONLY)) {
			error = gfs2_make_fs_rw(sdp);
		}
	}

	return error;
}

/**
 * gfs2_drop_inode - Drop an inode (test for remote unlink)
 * @inode: The inode to drop
 *
 * If we've received a callback on an iopen lock then its because a
 * remote node tried to deallocate the inode but failed due to this node
 * still having the inode open. Here we mark the link count zero
 * since we know that it must have reached zero if the GLF_DEMOTE flag
 * is set on the iopen glock. If we didn't do a disk read since the
 * remote node removed the final link then we might otherwise miss
 * this event. This check ensures that this node will deallocate the
 * inode's blocks, or alternatively pass the baton on to another
 * node for later deallocation.
 */

static void gfs2_drop_inode(struct inode *inode)
{
	struct gfs2_inode *ip = GFS2_I(inode);

	if (test_bit(GIF_USER, &ip->i_flags) && inode->i_nlink) {
		struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
		if (gl && test_bit(GLF_DEMOTE, &gl->gl_flags))
			clear_nlink(inode);
	}
	generic_drop_inode(inode);
}

/**
 * gfs2_clear_inode - Deallocate an inode when VFS is done with it
 * @inode: The VFS inode
 *
 */

static void gfs2_clear_inode(struct inode *inode)
{
	struct gfs2_inode *ip = GFS2_I(inode);

	/* This tells us its a "real" inode and not one which only
	 * serves to contain an address space (see rgrp.c, meta_io.c)
	 * which therefore doesn't have its own glocks.
	 */
	if (test_bit(GIF_USER, &ip->i_flags)) {
		ip->i_gl->gl_object = NULL;
		gfs2_glock_put(ip->i_gl);
		ip->i_gl = NULL;
		if (ip->i_iopen_gh.gh_gl) {
			ip->i_iopen_gh.gh_gl->gl_object = NULL;
			gfs2_glock_dq_uninit(&ip->i_iopen_gh);
		}
	}
}

static int is_ancestor(const struct dentry *d1, const struct dentry *d2)
{
	do {
		if (d1 == d2)
			return 1;
		d1 = d1->d_parent;
	} while (!IS_ROOT(d1));
	return 0;
}

/**
 * gfs2_show_options - Show mount options for /proc/mounts
 * @s: seq_file structure
 * @mnt: vfsmount
 *
 * Returns: 0 on success or error code
 */

static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
{
	struct gfs2_sbd *sdp = mnt->mnt_sb->s_fs_info;
	struct gfs2_args *args = &sdp->sd_args;

	if (is_ancestor(mnt->mnt_root, sdp->sd_master_dir))
		seq_printf(s, ",meta");
	if (args->ar_lockproto[0])
		seq_printf(s, ",lockproto=%s", args->ar_lockproto);
	if (args->ar_locktable[0])
		seq_printf(s, ",locktable=%s", args->ar_locktable);
	if (args->ar_hostdata[0])
		seq_printf(s, ",hostdata=%s", args->ar_hostdata);
	if (args->ar_spectator)
		seq_printf(s, ",spectator");
	if (args->ar_ignore_local_fs)
		seq_printf(s, ",ignore_local_fs");
	if (args->ar_localflocks)
		seq_printf(s, ",localflocks");
	if (args->ar_localcaching)
		seq_printf(s, ",localcaching");
	if (args->ar_debug)
		seq_printf(s, ",debug");
	if (args->ar_upgrade)
		seq_printf(s, ",upgrade");
	if (args->ar_posix_acl)
		seq_printf(s, ",acl");
	if (args->ar_quota != GFS2_QUOTA_DEFAULT) {
		char *state;
		switch (args->ar_quota) {
		case GFS2_QUOTA_OFF:
			state = "off";
			break;
		case GFS2_QUOTA_ACCOUNT:
			state = "account";
			break;
		case GFS2_QUOTA_ON:
			state = "on";
			break;
		default:
			state = "unknown";
			break;
		}
		seq_printf(s, ",quota=%s", state);
	}
	if (args->ar_suiddir)
		seq_printf(s, ",suiddir");
	if (args->ar_data != GFS2_DATA_DEFAULT) {
		char *state;
		switch (args->ar_data) {
		case GFS2_DATA_WRITEBACK:
			state = "writeback";
			break;
		case GFS2_DATA_ORDERED:
			state = "ordered";
			break;
		default:
			state = "unknown";
			break;
		}
		seq_printf(s, ",data=%s", state);
	}

	return 0;
}

/*
 * We have to (at the moment) hold the inodes main lock to cover
 * the gap between unlocking the shared lock on the iopen lock and
 * taking the exclusive lock. I'd rather do a shared -> exclusive
 * conversion on the iopen lock, but we can change that later. This
 * is safe, just less efficient.
 */

static void gfs2_delete_inode(struct inode *inode)
{
	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_holder gh;
	int error;

	if (!test_bit(GIF_USER, &ip->i_flags))
		goto out;

	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
	if (unlikely(error)) {
		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
		goto out;
	}

	gfs2_glock_dq_wait(&ip->i_iopen_gh);
	gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh);
	error = gfs2_glock_nq(&ip->i_iopen_gh);
	if (error)
		goto out_truncate;

	if (S_ISDIR(inode->i_mode) &&
	    (ip->i_diskflags & GFS2_DIF_EXHASH)) {
		error = gfs2_dir_exhash_dealloc(ip);
		if (error)
			goto out_unlock;
	}

	if (ip->i_eattr) {
		error = gfs2_ea_dealloc(ip);
		if (error)
			goto out_unlock;
	}

	if (!gfs2_is_stuffed(ip)) {
		error = gfs2_file_dealloc(ip);
		if (error)
			goto out_unlock;
	}

	error = gfs2_dinode_dealloc(ip);
	if (error)
		goto out_unlock;

out_truncate:
	error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
	if (error)
		goto out_unlock;
	/* Needs to be done before glock release & also in a transaction */
	truncate_inode_pages(&inode->i_data, 0);
	gfs2_trans_end(sdp);

out_unlock:
	if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags))
		gfs2_glock_dq(&ip->i_iopen_gh);
	gfs2_holder_uninit(&ip->i_iopen_gh);
	gfs2_glock_dq_uninit(&gh);
	if (error && error != GLR_TRYFAILED)
		fs_warn(sdp, "gfs2_delete_inode: %d\n", error);
out:
	truncate_inode_pages(&inode->i_data, 0);
	clear_inode(inode);
}

static struct inode *gfs2_alloc_inode(struct super_block *sb)
{
	struct gfs2_inode *ip;

	ip = kmem_cache_alloc(gfs2_inode_cachep, GFP_KERNEL);
	if (ip) {
		ip->i_flags = 0;
		ip->i_gl = NULL;
	}
	return &ip->i_inode;
}

static void gfs2_destroy_inode(struct inode *inode)
{
	kmem_cache_free(gfs2_inode_cachep, inode);
}

const struct super_operations gfs2_super_ops = {
	.alloc_inode		= gfs2_alloc_inode,
	.destroy_inode		= gfs2_destroy_inode,
	.write_inode		= gfs2_write_inode,
	.delete_inode		= gfs2_delete_inode,
	.put_super		= gfs2_gl_hash_clear,
	.write_super		= gfs2_write_super,
	.sync_fs		= gfs2_sync_fs,
	.write_super_lockfs 	= gfs2_write_super_lockfs,
	.unlockfs		= gfs2_unlockfs,
	.statfs			= gfs2_statfs,
	.remount_fs		= gfs2_remount_fs,
	.clear_inode		= gfs2_clear_inode,
	.drop_inode		= gfs2_drop_inode,
	.show_options		= gfs2_show_options,
};

OpenPOWER on IntegriCloud