summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_fsops.c
blob: 33e26690a8c4fc1d3722b2eabe51245cd87d6aa5 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_trans.h"
#include "xfs_error.h"
#include "xfs_alloc.h"
#include "xfs_fsops.h"
#include "xfs_trans_space.h"
#include "xfs_log.h"
#include "xfs_ag.h"
#include "xfs_ag_resv.h"
#include "xfs_trace.h"

/*
 * Write new AG headers to disk. Non-transactional, but need to be
 * written and completed prior to the growfs transaction being logged.
 * To do this, we use a delayed write buffer list and wait for
 * submission and IO completion of the list as a whole. This allows the
 * IO subsystem to merge all the AG headers in a single AG into a single
 * IO and hide most of the latency of the IO from us.
 *
 * This also means that if we get an error whilst building the buffer
 * list to write, we can cancel the entire list without having written
 * anything.
 */
static int
xfs_resizefs_init_new_ags(
	struct xfs_trans	*tp,
	struct aghdr_init_data	*id,
	xfs_agnumber_t		oagcount,
	xfs_agnumber_t		nagcount,
	xfs_rfsblock_t		delta,
	bool			*lastag_extended)
{
	struct xfs_mount	*mp = tp->t_mountp;
	xfs_rfsblock_t		nb = mp->m_sb.sb_dblocks + delta;
	int			error;

	*lastag_extended = false;

	INIT_LIST_HEAD(&id->buffer_list);
	for (id->agno = nagcount - 1;
	     id->agno >= oagcount;
	     id->agno--, delta -= id->agsize) {

		if (id->agno == nagcount - 1)
			id->agsize = nb - (id->agno *
					(xfs_rfsblock_t)mp->m_sb.sb_agblocks);
		else
			id->agsize = mp->m_sb.sb_agblocks;

		error = xfs_ag_init_headers(mp, id);
		if (error) {
			xfs_buf_delwri_cancel(&id->buffer_list);
			return error;
		}
	}

	error = xfs_buf_delwri_submit(&id->buffer_list);
	if (error)
		return error;

	if (delta) {
		*lastag_extended = true;
		error = xfs_ag_extend_space(mp, tp, id, delta);
	}
	return error;
}

/*
 * growfs operations
 */
static int
xfs_growfs_data_private(
	struct xfs_mount	*mp,		/* mount point for filesystem */
	struct xfs_growfs_data	*in)		/* growfs data input struct */
{
	struct xfs_buf		*bp;
	int			error;
	xfs_agnumber_t		nagcount;
	xfs_agnumber_t		nagimax = 0;
	xfs_rfsblock_t		nb, nb_div, nb_mod;
	int64_t			delta;
	bool			lastag_extended;
	xfs_agnumber_t		oagcount;
	struct xfs_trans	*tp;
	struct aghdr_init_data	id = {};

	nb = in->newblocks;
	error = xfs_sb_validate_fsb_count(&mp->m_sb, nb);
	if (error)
		return error;

	if (nb > mp->m_sb.sb_dblocks) {
		error = xfs_buf_read_uncached(mp->m_ddev_targp,
				XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1),
				XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
		if (error)
			return error;
		xfs_buf_relse(bp);
	}

	nb_div = nb;
	nb_mod = do_div(nb_div, mp->m_sb.sb_agblocks);
	nagcount = nb_div + (nb_mod != 0);
	if (nb_mod && nb_mod < XFS_MIN_AG_BLOCKS) {
		nagcount--;
		nb = (xfs_rfsblock_t)nagcount * mp->m_sb.sb_agblocks;
	}
	delta = nb - mp->m_sb.sb_dblocks;
	/*
	 * Reject filesystems with a single AG because they are not
	 * supported, and reject a shrink operation that would cause a
	 * filesystem to become unsupported.
	 */
	if (delta < 0 && nagcount < 2)
		return -EINVAL;

	oagcount = mp->m_sb.sb_agcount;

	/* allocate the new per-ag structures */
	if (nagcount > oagcount) {
		error = xfs_initialize_perag(mp, nagcount, &nagimax);
		if (error)
			return error;
	} else if (nagcount < oagcount) {
		/* TODO: shrinking the entire AGs hasn't yet completed */
		return -EINVAL;
	}

	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growdata,
			(delta > 0 ? XFS_GROWFS_SPACE_RES(mp) : -delta), 0,
			XFS_TRANS_RESERVE, &tp);
	if (error)
		return error;

	if (delta > 0) {
		error = xfs_resizefs_init_new_ags(tp, &id, oagcount, nagcount,
						  delta, &lastag_extended);
	} else {
		static struct ratelimit_state shrink_warning = \
			RATELIMIT_STATE_INIT("shrink_warning", 86400 * HZ, 1);
		ratelimit_set_flags(&shrink_warning, RATELIMIT_MSG_ON_RELEASE);

		if (__ratelimit(&shrink_warning))
			xfs_alert(mp,
	"EXPERIMENTAL online shrink feature in use. Use at your own risk!");

		error = xfs_ag_shrink_space(mp, &tp, nagcount - 1, -delta);
	}
	if (error)
		goto out_trans_cancel;

	/*
	 * Update changed superblock fields transactionally. These are not
	 * seen by the rest of the world until the transaction commit applies
	 * them atomically to the superblock.
	 */
	if (nagcount > oagcount)
		xfs_trans_mod_sb(tp, XFS_TRANS_SB_AGCOUNT, nagcount - oagcount);
	if (delta)
		xfs_trans_mod_sb(tp, XFS_TRANS_SB_DBLOCKS, delta);
	if (id.nfree)
		xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, id.nfree);

	/*
	 * Sync sb counters now to reflect the updated values. This is
	 * particularly important for shrink because the write verifier
	 * will fail if sb_fdblocks is ever larger than sb_dblocks.
	 */
	if (xfs_has_lazysbcount(mp))
		xfs_log_sb(tp);

	xfs_trans_set_sync(tp);
	error = xfs_trans_commit(tp);
	if (error)
		return error;

	/* New allocation groups fully initialized, so update mount struct */
	if (nagimax)
		mp->m_maxagi = nagimax;
	xfs_set_low_space_thresholds(mp);
	mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);

	if (delta > 0) {
		/*
		 * If we expanded the last AG, free the per-AG reservation
		 * so we can reinitialize it with the new size.
		 */
		if (lastag_extended) {
			struct xfs_perag	*pag;

			pag = xfs_perag_get(mp, id.agno);
			error = xfs_ag_resv_free(pag);
			xfs_perag_put(pag);
			if (error)
				return error;
		}
		/*
		 * Reserve AG metadata blocks. ENOSPC here does not mean there
		 * was a growfs failure, just that there still isn't space for
		 * new user data after the grow has been run.
		 */
		error = xfs_fs_reserve_ag_blocks(mp);
		if (error == -ENOSPC)
			error = 0;
	}
	return error;

out_trans_cancel:
	xfs_trans_cancel(tp);
	return error;
}

static int
xfs_growfs_log_private(
	struct xfs_mount	*mp,	/* mount point for filesystem */
	struct xfs_growfs_log	*in)	/* growfs log input struct */
{
	xfs_extlen_t		nb;

	nb = in->newblocks;
	if (nb < XFS_MIN_LOG_BLOCKS || nb < XFS_B_TO_FSB(mp, XFS_MIN_LOG_BYTES))
		return -EINVAL;
	if (nb == mp->m_sb.sb_logblocks &&
	    in->isint == (mp->m_sb.sb_logstart != 0))
		return -EINVAL;
	/*
	 * Moving the log is hard, need new interfaces to sync
	 * the log first, hold off all activity while moving it.
	 * Can have shorter or longer log in the same space,
	 * or transform internal to external log or vice versa.
	 */
	return -ENOSYS;
}

static int
xfs_growfs_imaxpct(
	struct xfs_mount	*mp,
	__u32			imaxpct)
{
	struct xfs_trans	*tp;
	int			dpct;
	int			error;

	if (imaxpct > 100)
		return -EINVAL;

	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growdata,
			XFS_GROWFS_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp);
	if (error)
		return error;

	dpct = imaxpct - mp->m_sb.sb_imax_pct;
	xfs_trans_mod_sb(tp, XFS_TRANS_SB_IMAXPCT, dpct);
	xfs_trans_set_sync(tp);
	return xfs_trans_commit(tp);
}

/*
 * protected versions of growfs function acquire and release locks on the mount
 * point - exported through ioctls: XFS_IOC_FSGROWFSDATA, XFS_IOC_FSGROWFSLOG,
 * XFS_IOC_FSGROWFSRT
 */
int
xfs_growfs_data(
	struct xfs_mount	*mp,
	struct xfs_growfs_data	*in)
{
	int			error = 0;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (!mutex_trylock(&mp->m_growlock))
		return -EWOULDBLOCK;

	/* update imaxpct separately to the physical grow of the filesystem */
	if (in->imaxpct != mp->m_sb.sb_imax_pct) {
		error = xfs_growfs_imaxpct(mp, in->imaxpct);
		if (error)
			goto out_error;
	}

	if (in->newblocks != mp->m_sb.sb_dblocks) {
		error = xfs_growfs_data_private(mp, in);
		if (error)
			goto out_error;
	}

	/* Post growfs calculations needed to reflect new state in operations */
	if (mp->m_sb.sb_imax_pct) {
		uint64_t icount = mp->m_sb.sb_dblocks * mp->m_sb.sb_imax_pct;
		do_div(icount, 100);
		M_IGEO(mp)->maxicount = XFS_FSB_TO_INO(mp, icount);
	} else
		M_IGEO(mp)->maxicount = 0;

	/* Update secondary superblocks now the physical grow has completed */
	error = xfs_update_secondary_sbs(mp);

out_error:
	/*
	 * Increment the generation unconditionally, the error could be from
	 * updating the secondary superblocks, in which case the new size
	 * is live already.
	 */
	mp->m_generation++;
	mutex_unlock(&mp->m_growlock);
	return error;
}

int
xfs_growfs_log(
	xfs_mount_t		*mp,
	struct xfs_growfs_log	*in)
{
	int error;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (!mutex_trylock(&mp->m_growlock))
		return -EWOULDBLOCK;
	error = xfs_growfs_log_private(mp, in);
	mutex_unlock(&mp->m_growlock);
	return error;
}

/*
 * exported through ioctl XFS_IOC_FSCOUNTS
 */

void
xfs_fs_counts(
	xfs_mount_t		*mp,
	xfs_fsop_counts_t	*cnt)
{
	cnt->allocino = percpu_counter_read_positive(&mp->m_icount);
	cnt->freeino = percpu_counter_read_positive(&mp->m_ifree);
	cnt->freedata = percpu_counter_read_positive(&mp->m_fdblocks) -
						mp->m_alloc_set_aside;

	spin_lock(&mp->m_sb_lock);
	cnt->freertx = mp->m_sb.sb_frextents;
	spin_unlock(&mp->m_sb_lock);
}

/*
 * exported through ioctl XFS_IOC_SET_RESBLKS & XFS_IOC_GET_RESBLKS
 *
 * xfs_reserve_blocks is called to set m_resblks
 * in the in-core mount table. The number of unused reserved blocks
 * is kept in m_resblks_avail.
 *
 * Reserve the requested number of blocks if available. Otherwise return
 * as many as possible to satisfy the request. The actual number
 * reserved are returned in outval
 *
 * A null inval pointer indicates that only the current reserved blocks
 * available  should  be returned no settings are changed.
 */

int
xfs_reserve_blocks(
	xfs_mount_t             *mp,
	uint64_t              *inval,
	xfs_fsop_resblks_t      *outval)
{
	int64_t			lcounter, delta;
	int64_t			fdblks_delta = 0;
	uint64_t		request;
	int64_t			free;
	int			error = 0;

	/* If inval is null, report current values and return */
	if (inval == (uint64_t *)NULL) {
		if (!outval)
			return -EINVAL;
		outval->resblks = mp->m_resblks;
		outval->resblks_avail = mp->m_resblks_avail;
		return 0;
	}

	request = *inval;

	/*
	 * With per-cpu counters, this becomes an interesting problem. we need
	 * to work out if we are freeing or allocation blocks first, then we can
	 * do the modification as necessary.
	 *
	 * We do this under the m_sb_lock so that if we are near ENOSPC, we will
	 * hold out any changes while we work out what to do. This means that
	 * the amount of free space can change while we do this, so we need to
	 * retry if we end up trying to reserve more space than is available.
	 */
	spin_lock(&mp->m_sb_lock);

	/*
	 * If our previous reservation was larger than the current value,
	 * then move any unused blocks back to the free pool. Modify the resblks
	 * counters directly since we shouldn't have any problems unreserving
	 * space.
	 */
	if (mp->m_resblks > request) {
		lcounter = mp->m_resblks_avail - request;
		if (lcounter  > 0) {		/* release unused blocks */
			fdblks_delta = lcounter;
			mp->m_resblks_avail -= lcounter;
		}
		mp->m_resblks = request;
		if (fdblks_delta) {
			spin_unlock(&mp->m_sb_lock);
			error = xfs_mod_fdblocks(mp, fdblks_delta, 0);
			spin_lock(&mp->m_sb_lock);
		}

		goto out;
	}

	/*
	 * If the request is larger than the current reservation, reserve the
	 * blocks before we update the reserve counters. Sample m_fdblocks and
	 * perform a partial reservation if the request exceeds free space.
	 */
	error = -ENOSPC;
	do {
		free = percpu_counter_sum(&mp->m_fdblocks) -
						mp->m_alloc_set_aside;
		if (free <= 0)
			break;

		delta = request - mp->m_resblks;
		lcounter = free - delta;
		if (lcounter < 0)
			/* We can't satisfy the request, just get what we can */
			fdblks_delta = free;
		else
			fdblks_delta = delta;

		/*
		 * We'll either succeed in getting space from the free block
		 * count or we'll get an ENOSPC. If we get a ENOSPC, it means
		 * things changed while we were calculating fdblks_delta and so
		 * we should try again to see if there is anything left to
		 * reserve.
		 *
		 * Don't set the reserved flag here - we don't want to reserve
		 * the extra reserve blocks from the reserve.....
		 */
		spin_unlock(&mp->m_sb_lock);
		error = xfs_mod_fdblocks(mp, -fdblks_delta, 0);
		spin_lock(&mp->m_sb_lock);
	} while (error == -ENOSPC);

	/*
	 * Update the reserve counters if blocks have been successfully
	 * allocated.
	 */
	if (!error && fdblks_delta) {
		mp->m_resblks += fdblks_delta;
		mp->m_resblks_avail += fdblks_delta;
	}

out:
	if (outval) {
		outval->resblks = mp->m_resblks;
		outval->resblks_avail = mp->m_resblks_avail;
	}

	spin_unlock(&mp->m_sb_lock);
	return error;
}

int
xfs_fs_goingdown(
	xfs_mount_t	*mp,
	uint32_t	inflags)
{
	switch (inflags) {
	case XFS_FSOP_GOING_FLAGS_DEFAULT: {
		if (!freeze_bdev(mp->m_super->s_bdev)) {
			xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT);
			thaw_bdev(mp->m_super->s_bdev);
		}
		break;
	}
	case XFS_FSOP_GOING_FLAGS_LOGFLUSH:
		xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT);
		break;
	case XFS_FSOP_GOING_FLAGS_NOLOGFLUSH:
		xfs_force_shutdown(mp,
				SHUTDOWN_FORCE_UMOUNT | SHUTDOWN_LOG_IO_ERROR);
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

/*
 * Force a shutdown of the filesystem instantly while keeping the filesystem
 * consistent. We don't do an unmount here; just shutdown the shop, make sure
 * that absolutely nothing persistent happens to this filesystem after this
 * point.
 *
 * The shutdown state change is atomic, resulting in the first and only the
 * first shutdown call processing the shutdown. This means we only shutdown the
 * log once as it requires, and we don't spam the logs when multiple concurrent
 * shutdowns race to set the shutdown flags.
 */
void
xfs_do_force_shutdown(
	struct xfs_mount *mp,
	int		flags,
	char		*fname,
	int		lnnum)
{
	int		tag;
	const char	*why;

	if (test_and_set_bit(XFS_OPSTATE_SHUTDOWN, &mp->m_opstate))
		return;
	if (mp->m_sb_bp)
		mp->m_sb_bp->b_flags |= XBF_DONE;

	if (flags & SHUTDOWN_FORCE_UMOUNT)
		xfs_alert(mp, "User initiated shutdown received.");

	if (xlog_force_shutdown(mp->m_log, flags)) {
		tag = XFS_PTAG_SHUTDOWN_LOGERROR;
		why = "Log I/O Error";
	} else if (flags & SHUTDOWN_CORRUPT_INCORE) {
		tag = XFS_PTAG_SHUTDOWN_CORRUPT;
		why = "Corruption of in-memory data";
	} else {
		tag = XFS_PTAG_SHUTDOWN_IOERROR;
		why = "Metadata I/O Error";
	}

	trace_xfs_force_shutdown(mp, tag, flags, fname, lnnum);

	xfs_alert_tag(mp, tag,
"%s (0x%x) detected at %pS (%s:%d).  Shutting down filesystem.",
			why, flags, __return_address, fname, lnnum);
	xfs_alert(mp,
		"Please unmount the filesystem and rectify the problem(s)");
	if (xfs_error_level >= XFS_ERRLEVEL_HIGH)
		xfs_stack_trace();
}

/*
 * Reserve free space for per-AG metadata.
 */
int
xfs_fs_reserve_ag_blocks(
	struct xfs_mount	*mp)
{
	xfs_agnumber_t		agno;
	struct xfs_perag	*pag;
	int			error = 0;
	int			err2;

	mp->m_finobt_nores = false;
	for_each_perag(mp, agno, pag) {
		err2 = xfs_ag_resv_init(pag, NULL);
		if (err2 && !error)
			error = err2;
	}

	if (error && error != -ENOSPC) {
		xfs_warn(mp,
	"Error %d reserving per-AG metadata reserve pool.", error);
		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
	}

	return error;
}

/*
 * Free space reserved for per-AG metadata.
 */
int
xfs_fs_unreserve_ag_blocks(
	struct xfs_mount	*mp)
{
	xfs_agnumber_t		agno;
	struct xfs_perag	*pag;
	int			error = 0;
	int			err2;

	for_each_perag(mp, agno, pag) {
		err2 = xfs_ag_resv_free(pag);
		if (err2 && !error)
			error = err2;
	}

	if (error)
		xfs_warn(mp,
	"Error %d freeing per-AG metadata reserve pool.", error);

	return error;
}