summaryrefslogtreecommitdiffstats
path: root/fs/gfs2/glops.c
blob: 5406b193227cc19759f7b6771a10523b31b44e5c (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
/*
 * 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.
 */

#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/gfs2_ondisk.h>
#include <linux/lm_interface.h>

#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
#include "glock.h"
#include "glops.h"
#include "inode.h"
#include "log.h"
#include "meta_io.h"
#include "recovery.h"
#include "rgrp.h"
#include "util.h"
#include "trans.h"

/**
 * ail_empty_gl - remove all buffers for a given lock from the AIL
 * @gl: the glock
 *
 * None of the buffers should be dirty, locked, or pinned.
 */

static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
{
	struct gfs2_sbd *sdp = gl->gl_sbd;
	unsigned int blocks;
	struct list_head *head = &gl->gl_ail_list;
	struct gfs2_bufdata *bd;
	struct buffer_head *bh;
	u64 blkno;
	int error;

	blocks = atomic_read(&gl->gl_ail_count);
	if (!blocks)
		return;

	error = gfs2_trans_begin(sdp, 0, blocks);
	if (gfs2_assert_withdraw(sdp, !error))
		return;

	gfs2_log_lock(sdp);
	while (!list_empty(head)) {
		bd = list_entry(head->next, struct gfs2_bufdata,
				bd_ail_gl_list);
		bh = bd->bd_bh;
		blkno = bh->b_blocknr;
		gfs2_assert_withdraw(sdp, !buffer_busy(bh));

		bd->bd_ail = NULL;
		list_del(&bd->bd_ail_st_list);
		list_del(&bd->bd_ail_gl_list);
		atomic_dec(&gl->gl_ail_count);
		brelse(bh);
		gfs2_log_unlock(sdp);

		gfs2_trans_add_revoke(sdp, blkno);

		gfs2_log_lock(sdp);
	}
	gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
	gfs2_log_unlock(sdp);

	gfs2_trans_end(sdp);
	gfs2_log_flush(sdp, NULL);
}

/**
 * gfs2_pte_inval - Sync and invalidate all PTEs associated with a glock
 * @gl: the glock
 *
 */

static void gfs2_pte_inval(struct gfs2_glock *gl)
{
	struct gfs2_inode *ip;
	struct inode *inode;

	ip = gl->gl_object;
	inode = &ip->i_inode;
	if (!ip || !S_ISREG(ip->i_di.di_mode))
		return;

	if (!test_bit(GIF_PAGED, &ip->i_flags))
		return;

	unmap_shared_mapping_range(inode->i_mapping, 0, 0);

	if (test_bit(GIF_SW_PAGED, &ip->i_flags))
		set_bit(GLF_DIRTY, &gl->gl_flags);

	clear_bit(GIF_SW_PAGED, &ip->i_flags);
}

/**
 * gfs2_page_inval - Invalidate all pages associated with a glock
 * @gl: the glock
 *
 */

static void gfs2_page_inval(struct gfs2_glock *gl)
{
	struct gfs2_inode *ip;
	struct inode *inode;

	ip = gl->gl_object;
	inode = &ip->i_inode;
	if (!ip || !S_ISREG(ip->i_di.di_mode))
		return;

	truncate_inode_pages(inode->i_mapping, 0);
	gfs2_assert_withdraw(GFS2_SB(&ip->i_inode), !inode->i_mapping->nrpages);
	clear_bit(GIF_PAGED, &ip->i_flags);
}

/**
 * gfs2_page_wait - Wait for writeback of data
 * @gl: the glock
 *
 * Syncs data (not metadata) for a regular file.
 * No-op for all other types.
 */

static void gfs2_page_wait(struct gfs2_glock *gl)
{
	struct gfs2_inode *ip = gl->gl_object;
	struct inode *inode = &ip->i_inode;
	struct address_space *mapping = inode->i_mapping;
	int error;

	if (!S_ISREG(ip->i_di.di_mode))
		return;

	error = filemap_fdatawait(mapping);

	/* Put back any errors cleared by filemap_fdatawait()
	   so they can be caught by someone who can pass them
	   up to user space. */

	if (error == -ENOSPC)
		set_bit(AS_ENOSPC, &mapping->flags);
	else if (error)
		set_bit(AS_EIO, &mapping->flags);

}

static void gfs2_page_writeback(struct gfs2_glock *gl)
{
	struct gfs2_inode *ip = gl->gl_object;
	struct inode *inode = &ip->i_inode;
	struct address_space *mapping = inode->i_mapping;

	if (!S_ISREG(ip->i_di.di_mode))
		return;

	filemap_fdatawrite(mapping);
}

/**
 * meta_go_sync - sync out the metadata for this glock
 * @gl: the glock
 * @flags: DIO_*
 *
 * Called when demoting or unlocking an EX glock.  We must flush
 * to disk all dirty buffers/pages relating to this glock, and must not
 * not return to caller to demote/unlock the glock until I/O is complete.
 */

static void meta_go_sync(struct gfs2_glock *gl, int flags)
{
	if (!(flags & DIO_METADATA))
		return;

	if (test_and_clear_bit(GLF_DIRTY, &gl->gl_flags)) {
		gfs2_log_flush(gl->gl_sbd, gl);
		gfs2_meta_sync(gl);
		if (flags & DIO_RELEASE)
			gfs2_ail_empty_gl(gl);
	}

}

/**
 * meta_go_inval - invalidate the metadata for this glock
 * @gl: the glock
 * @flags:
 *
 */

static void meta_go_inval(struct gfs2_glock *gl, int flags)
{
	if (!(flags & DIO_METADATA))
		return;

	gfs2_meta_inval(gl);
	gl->gl_vn++;
}

/**
 * inode_go_xmote_th - promote/demote a glock
 * @gl: the glock
 * @state: the requested state
 * @flags:
 *
 */

static void inode_go_xmote_th(struct gfs2_glock *gl, unsigned int state,
			      int flags)
{
	if (gl->gl_state != LM_ST_UNLOCKED)
		gfs2_pte_inval(gl);
	gfs2_glock_xmote_th(gl, state, flags);
}

/**
 * inode_go_xmote_bh - After promoting/demoting a glock
 * @gl: the glock
 *
 */

static void inode_go_xmote_bh(struct gfs2_glock *gl)
{
	struct gfs2_holder *gh = gl->gl_req_gh;
	struct buffer_head *bh;
	int error;

	if (gl->gl_state != LM_ST_UNLOCKED &&
	    (!gh || !(gh->gh_flags & GL_SKIP))) {
		error = gfs2_meta_read(gl, gl->gl_name.ln_number, 0, &bh);
		if (!error)
			brelse(bh);
	}
}

/**
 * inode_go_drop_th - unlock a glock
 * @gl: the glock
 *
 * Invoked from rq_demote().
 * Another node needs the lock in EXCLUSIVE mode, or lock (unused for too long)
 * is being purged from our node's glock cache; we're dropping lock.
 */

static void inode_go_drop_th(struct gfs2_glock *gl)
{
	gfs2_pte_inval(gl);
	gfs2_glock_drop_th(gl);
}

/**
 * inode_go_sync - Sync the dirty data and/or metadata for an inode glock
 * @gl: the glock protecting the inode
 * @flags:
 *
 */

static void inode_go_sync(struct gfs2_glock *gl, int flags)
{
	int meta = (flags & DIO_METADATA);
	int data = (flags & DIO_DATA);

	if (test_bit(GLF_DIRTY, &gl->gl_flags)) {
		if (meta && data) {
			gfs2_page_writeback(gl);
			gfs2_log_flush(gl->gl_sbd, gl);
			gfs2_meta_sync(gl);
			gfs2_page_wait(gl);
			clear_bit(GLF_DIRTY, &gl->gl_flags);
		} else if (meta) {
			gfs2_log_flush(gl->gl_sbd, gl);
			gfs2_meta_sync(gl);
		} else if (data) {
			gfs2_page_writeback(gl);
			gfs2_page_wait(gl);
		}
		if (flags & DIO_RELEASE)
			gfs2_ail_empty_gl(gl);
	}
}

/**
 * inode_go_inval - prepare a inode glock to be released
 * @gl: the glock
 * @flags:
 *
 */

static void inode_go_inval(struct gfs2_glock *gl, int flags)
{
	int meta = (flags & DIO_METADATA);
	int data = (flags & DIO_DATA);

	if (meta) {
		gfs2_meta_inval(gl);
		gl->gl_vn++;
	}
	if (data)
		gfs2_page_inval(gl);
}

/**
 * inode_go_demote_ok - Check to see if it's ok to unlock an inode glock
 * @gl: the glock
 *
 * Returns: 1 if it's ok
 */

static int inode_go_demote_ok(struct gfs2_glock *gl)
{
	struct gfs2_sbd *sdp = gl->gl_sbd;
	int demote = 0;

	if (!gl->gl_object && !gl->gl_aspace->i_mapping->nrpages)
		demote = 1;
	else if (!sdp->sd_args.ar_localcaching &&
		 time_after_eq(jiffies, gl->gl_stamp +
			       gfs2_tune_get(sdp, gt_demote_secs) * HZ))
		demote = 1;

	return demote;
}

/**
 * inode_go_lock - operation done after an inode lock is locked by a process
 * @gl: the glock
 * @flags:
 *
 * Returns: errno
 */

static int inode_go_lock(struct gfs2_holder *gh)
{
	struct gfs2_glock *gl = gh->gh_gl;
	struct gfs2_inode *ip = gl->gl_object;
	int error = 0;

	if (!ip)
		return 0;

	if (ip->i_vn != gl->gl_vn) {
		error = gfs2_inode_refresh(ip);
		if (error)
			return error;
		gfs2_inode_attr_in(ip);
	}

	if ((ip->i_di.di_flags & GFS2_DIF_TRUNC_IN_PROG) &&
	    (gl->gl_state == LM_ST_EXCLUSIVE) &&
	    (gh->gh_flags & GL_LOCAL_EXCL))
		error = gfs2_truncatei_resume(ip);

	return error;
}

/**
 * inode_go_unlock - operation done before an inode lock is unlocked by a
 *		     process
 * @gl: the glock
 * @flags:
 *
 */

static void inode_go_unlock(struct gfs2_holder *gh)
{
	struct gfs2_glock *gl = gh->gh_gl;
	struct gfs2_inode *ip = gl->gl_object;

	if (ip == NULL)
		return;
	if (test_bit(GLF_DIRTY, &gl->gl_flags))
		gfs2_inode_attr_in(ip);
	gfs2_meta_cache_flush(ip);
}

/**
 * inode_greedy -
 * @gl: the glock
 *
 */

static void inode_greedy(struct gfs2_glock *gl)
{
	struct gfs2_sbd *sdp = gl->gl_sbd;
	struct gfs2_inode *ip = gl->gl_object;
	unsigned int quantum = gfs2_tune_get(sdp, gt_greedy_quantum);
	unsigned int max = gfs2_tune_get(sdp, gt_greedy_max);
	unsigned int new_time;

	spin_lock(&ip->i_spin);

	if (time_after(ip->i_last_pfault + quantum, jiffies)) {
		new_time = ip->i_greedy + quantum;
		if (new_time > max)
			new_time = max;
	} else {
		new_time = ip->i_greedy - quantum;
		if (!new_time || new_time > max)
			new_time = 1;
	}

	ip->i_greedy = new_time;

	spin_unlock(&ip->i_spin);

	iput(&ip->i_inode);
}

/**
 * rgrp_go_demote_ok - Check to see if it's ok to unlock a RG's glock
 * @gl: the glock
 *
 * Returns: 1 if it's ok
 */

static int rgrp_go_demote_ok(struct gfs2_glock *gl)
{
	return !gl->gl_aspace->i_mapping->nrpages;
}

/**
 * rgrp_go_lock - operation done after an rgrp lock is locked by
 *    a first holder on this node.
 * @gl: the glock
 * @flags:
 *
 * Returns: errno
 */

static int rgrp_go_lock(struct gfs2_holder *gh)
{
	return gfs2_rgrp_bh_get(gh->gh_gl->gl_object);
}

/**
 * rgrp_go_unlock - operation done before an rgrp lock is unlocked by
 *    a last holder on this node.
 * @gl: the glock
 * @flags:
 *
 */

static void rgrp_go_unlock(struct gfs2_holder *gh)
{
	gfs2_rgrp_bh_put(gh->gh_gl->gl_object);
}

/**
 * trans_go_xmote_th - promote/demote the transaction glock
 * @gl: the glock
 * @state: the requested state
 * @flags:
 *
 */

static void trans_go_xmote_th(struct gfs2_glock *gl, unsigned int state,
			      int flags)
{
	struct gfs2_sbd *sdp = gl->gl_sbd;

	if (gl->gl_state != LM_ST_UNLOCKED &&
	    test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
		gfs2_meta_syncfs(sdp);
		gfs2_log_shutdown(sdp);
	}

	gfs2_glock_xmote_th(gl, state, flags);
}

/**
 * trans_go_xmote_bh - After promoting/demoting the transaction glock
 * @gl: the glock
 *
 */

static void trans_go_xmote_bh(struct gfs2_glock *gl)
{
	struct gfs2_sbd *sdp = gl->gl_sbd;
	struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
	struct gfs2_glock *j_gl = ip->i_gl;
	struct gfs2_log_header_host head;
	int error;

	if (gl->gl_state != LM_ST_UNLOCKED &&
	    test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
		gfs2_meta_cache_flush(GFS2_I(sdp->sd_jdesc->jd_inode));
		j_gl->gl_ops->go_inval(j_gl, DIO_METADATA | DIO_DATA);

		error = gfs2_find_jhead(sdp->sd_jdesc, &head);
		if (error)
			gfs2_consist(sdp);
		if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT))
			gfs2_consist(sdp);

		/*  Initialize some head of the log stuff  */
		if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) {
			sdp->sd_log_sequence = head.lh_sequence + 1;
			gfs2_log_pointers_init(sdp, head.lh_blkno);
		}
	}
}

/**
 * trans_go_drop_th - unlock the transaction glock
 * @gl: the glock
 *
 * We want to sync the device even with localcaching.  Remember
 * that localcaching journal replay only marks buffers dirty.
 */

static void trans_go_drop_th(struct gfs2_glock *gl)
{
	struct gfs2_sbd *sdp = gl->gl_sbd;

	if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
		gfs2_meta_syncfs(sdp);
		gfs2_log_shutdown(sdp);
	}

	gfs2_glock_drop_th(gl);
}

/**
 * quota_go_demote_ok - Check to see if it's ok to unlock a quota glock
 * @gl: the glock
 *
 * Returns: 1 if it's ok
 */

static int quota_go_demote_ok(struct gfs2_glock *gl)
{
	return !atomic_read(&gl->gl_lvb_count);
}

const struct gfs2_glock_operations gfs2_meta_glops = {
	.go_xmote_th = gfs2_glock_xmote_th,
	.go_drop_th = gfs2_glock_drop_th,
	.go_type = LM_TYPE_META,
};

const struct gfs2_glock_operations gfs2_inode_glops = {
	.go_xmote_th = inode_go_xmote_th,
	.go_xmote_bh = inode_go_xmote_bh,
	.go_drop_th = inode_go_drop_th,
	.go_sync = inode_go_sync,
	.go_inval = inode_go_inval,
	.go_demote_ok = inode_go_demote_ok,
	.go_lock = inode_go_lock,
	.go_unlock = inode_go_unlock,
	.go_greedy = inode_greedy,
	.go_type = LM_TYPE_INODE,
};

const struct gfs2_glock_operations gfs2_rgrp_glops = {
	.go_xmote_th = gfs2_glock_xmote_th,
	.go_drop_th = gfs2_glock_drop_th,
	.go_sync = meta_go_sync,
	.go_inval = meta_go_inval,
	.go_demote_ok = rgrp_go_demote_ok,
	.go_lock = rgrp_go_lock,
	.go_unlock = rgrp_go_unlock,
	.go_type = LM_TYPE_RGRP,
};

const struct gfs2_glock_operations gfs2_trans_glops = {
	.go_xmote_th = trans_go_xmote_th,
	.go_xmote_bh = trans_go_xmote_bh,
	.go_drop_th = trans_go_drop_th,
	.go_type = LM_TYPE_NONDISK,
};

const struct gfs2_glock_operations gfs2_iopen_glops = {
	.go_xmote_th = gfs2_glock_xmote_th,
	.go_drop_th = gfs2_glock_drop_th,
	.go_type = LM_TYPE_IOPEN,
};

const struct gfs2_glock_operations gfs2_flock_glops = {
	.go_xmote_th = gfs2_glock_xmote_th,
	.go_drop_th = gfs2_glock_drop_th,
	.go_type = LM_TYPE_FLOCK,
};

const struct gfs2_glock_operations gfs2_nondisk_glops = {
	.go_xmote_th = gfs2_glock_xmote_th,
	.go_drop_th = gfs2_glock_drop_th,
	.go_type = LM_TYPE_NONDISK,
};

const struct gfs2_glock_operations gfs2_quota_glops = {
	.go_xmote_th = gfs2_glock_xmote_th,
	.go_drop_th = gfs2_glock_drop_th,
	.go_demote_ok = quota_go_demote_ok,
	.go_type = LM_TYPE_QUOTA,
};

const struct gfs2_glock_operations gfs2_journal_glops = {
	.go_xmote_th = gfs2_glock_xmote_th,
	.go_drop_th = gfs2_glock_drop_th,
	.go_type = LM_TYPE_JOURNAL,
};