summaryrefslogtreecommitdiff
path: root/fs/gfs2/meta_io.c
blob: 924361fa510b1f37b669e831e749c986ca36263a (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
 */

#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/swap.h>
#include <linux/delay.h>
#include <linux/bio.h>
#include <linux/gfs2_ondisk.h>

#include "gfs2.h"
#include "incore.h"
#include "glock.h"
#include "glops.h"
#include "inode.h"
#include "log.h"
#include "lops.h"
#include "meta_io.h"
#include "rgrp.h"
#include "trans.h"
#include "util.h"
#include "trace_gfs2.h"

static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wbc)
{
	struct buffer_head *bh, *head;
	int nr_underway = 0;
	blk_opf_t write_flags = REQ_META | REQ_PRIO | wbc_to_write_flags(wbc);

	BUG_ON(!PageLocked(page));
	BUG_ON(!page_has_buffers(page));

	head = page_buffers(page);
	bh = head;

	do {
		if (!buffer_mapped(bh))
			continue;
		/*
		 * If it's a fully non-blocking write attempt and we cannot
		 * lock the buffer then redirty the page.  Note that this can
		 * potentially cause a busy-wait loop from flusher thread and kswapd
		 * activity, but those code paths have their own higher-level
		 * throttling.
		 */
		if (wbc->sync_mode != WB_SYNC_NONE) {
			lock_buffer(bh);
		} else if (!trylock_buffer(bh)) {
			redirty_page_for_writepage(wbc, page);
			continue;
		}
		if (test_clear_buffer_dirty(bh)) {
			mark_buffer_async_write(bh);
		} else {
			unlock_buffer(bh);
		}
	} while ((bh = bh->b_this_page) != head);

	/*
	 * The page and its buffers are protected by PageWriteback(), so we can
	 * drop the bh refcounts early.
	 */
	BUG_ON(PageWriteback(page));
	set_page_writeback(page);

	do {
		struct buffer_head *next = bh->b_this_page;
		if (buffer_async_write(bh)) {
			submit_bh(REQ_OP_WRITE | write_flags, bh);
			nr_underway++;
		}
		bh = next;
	} while (bh != head);
	unlock_page(page);

	if (nr_underway == 0)
		end_page_writeback(page);

	return 0;
}

const struct address_space_operations gfs2_meta_aops = {
	.dirty_folio	= block_dirty_folio,
	.invalidate_folio = block_invalidate_folio,
	.writepage = gfs2_aspace_writepage,
	.release_folio = gfs2_release_folio,
};

const struct address_space_operations gfs2_rgrp_aops = {
	.dirty_folio	= block_dirty_folio,
	.invalidate_folio = block_invalidate_folio,
	.writepage = gfs2_aspace_writepage,
	.release_folio = gfs2_release_folio,
};

/**
 * gfs2_getbuf - Get a buffer with a given address space
 * @gl: the glock
 * @blkno: the block number (filesystem scope)
 * @create: 1 if the buffer should be created
 *
 * Returns: the buffer
 */

struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create)
{
	struct address_space *mapping = gfs2_glock2aspace(gl);
	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
	struct page *page;
	struct buffer_head *bh;
	unsigned int shift;
	unsigned long index;
	unsigned int bufnum;

	if (mapping == NULL)
		mapping = &sdp->sd_aspace;

	shift = PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift;
	index = blkno >> shift;             /* convert block to page */
	bufnum = blkno - (index << shift);  /* block buf index within page */

	if (create) {
		for (;;) {
			page = grab_cache_page(mapping, index);
			if (page)
				break;
			yield();
		}
		if (!page_has_buffers(page))
			create_empty_buffers(page, sdp->sd_sb.sb_bsize, 0);
	} else {
		page = find_get_page_flags(mapping, index,
						FGP_LOCK|FGP_ACCESSED);
		if (!page)
			return NULL;
		if (!page_has_buffers(page)) {
			bh = NULL;
			goto out_unlock;
		}
	}

	/* Locate header for our buffer within our page */
	for (bh = page_buffers(page); bufnum--; bh = bh->b_this_page)
		/* Do nothing */;
	get_bh(bh);

	if (!buffer_mapped(bh))
		map_bh(bh, sdp->sd_vfs, blkno);

out_unlock:
	unlock_page(page);
	put_page(page);

	return bh;
}

static void meta_prep_new(struct buffer_head *bh)
{
	struct gfs2_meta_header *mh = (struct gfs2_meta_header *)bh->b_data;

	lock_buffer(bh);
	clear_buffer_dirty(bh);
	set_buffer_uptodate(bh);
	unlock_buffer(bh);

	mh->mh_magic = cpu_to_be32(GFS2_MAGIC);
}

/**
 * gfs2_meta_new - Get a block
 * @gl: The glock associated with this block
 * @blkno: The block number
 *
 * Returns: The buffer
 */

struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
{
	struct buffer_head *bh;
	bh = gfs2_getbuf(gl, blkno, CREATE);
	meta_prep_new(bh);
	return bh;
}

static void gfs2_meta_read_endio(struct bio *bio)
{
	struct bio_vec *bvec;
	struct bvec_iter_all iter_all;

	bio_for_each_segment_all(bvec, bio, iter_all) {
		struct page *page = bvec->bv_page;
		struct buffer_head *bh = page_buffers(page);
		unsigned int len = bvec->bv_len;

		while (bh_offset(bh) < bvec->bv_offset)
			bh = bh->b_this_page;
		do {
			struct buffer_head *next = bh->b_this_page;
			len -= bh->b_size;
			bh->b_end_io(bh, !bio->bi_status);
			bh = next;
		} while (bh && len);
	}
	bio_put(bio);
}

/*
 * Submit several consecutive buffer head I/O requests as a single bio I/O
 * request.  (See submit_bh_wbc.)
 */
static void gfs2_submit_bhs(blk_opf_t opf, struct buffer_head *bhs[], int num)
{
	while (num > 0) {
		struct buffer_head *bh = *bhs;
		struct bio *bio;

		bio = bio_alloc(bh->b_bdev, num, opf, GFP_NOIO);
		bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
		while (num > 0) {
			bh = *bhs;
			if (!bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh))) {
				BUG_ON(bio->bi_iter.bi_size == 0);
				break;
			}
			bhs++;
			num--;
		}
		bio->bi_end_io = gfs2_meta_read_endio;
		submit_bio(bio);
	}
}

/**
 * gfs2_meta_read - Read a block from disk
 * @gl: The glock covering the block
 * @blkno: The block number
 * @flags: flags
 * @rahead: Do read-ahead
 * @bhp: the place where the buffer is returned (NULL on failure)
 *
 * Returns: errno
 */

int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
		   int rahead, struct buffer_head **bhp)
{
	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
	struct buffer_head *bh, *bhs[2];
	int num = 0;

	if (unlikely(gfs2_withdrawn(sdp)) && !gfs2_withdraw_in_prog(sdp)) {
		*bhp = NULL;
		return -EIO;
	}

	*bhp = bh = gfs2_getbuf(gl, blkno, CREATE);

	lock_buffer(bh);
	if (buffer_uptodate(bh)) {
		unlock_buffer(bh);
		flags &= ~DIO_WAIT;
	} else {
		bh->b_end_io = end_buffer_read_sync;
		get_bh(bh);
		bhs[num++] = bh;
	}

	if (rahead) {
		bh = gfs2_getbuf(gl, blkno + 1, CREATE);

		lock_buffer(bh);
		if (buffer_uptodate(bh)) {
			unlock_buffer(bh);
			brelse(bh);
		} else {
			bh->b_end_io = end_buffer_read_sync;
			bhs[num++] = bh;
		}
	}

	gfs2_submit_bhs(REQ_OP_READ | REQ_META | REQ_PRIO, bhs, num);
	if (!(flags & DIO_WAIT))
		return 0;

	bh = *bhp;
	wait_on_buffer(bh);
	if (unlikely(!buffer_uptodate(bh))) {
		struct gfs2_trans *tr = current->journal_info;
		if (tr && test_bit(TR_TOUCHED, &tr->tr_flags))
			gfs2_io_error_bh_wd(sdp, bh);
		brelse(bh);
		*bhp = NULL;
		return -EIO;
	}

	return 0;
}

/**
 * gfs2_meta_wait - Reread a block from disk
 * @sdp: the filesystem
 * @bh: The block to wait for
 *
 * Returns: errno
 */

int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh)
{
	if (unlikely(gfs2_withdrawn(sdp)) && !gfs2_withdraw_in_prog(sdp))
		return -EIO;

	wait_on_buffer(bh);

	if (!buffer_uptodate(bh)) {
		struct gfs2_trans *tr = current->journal_info;
		if (tr && test_bit(TR_TOUCHED, &tr->tr_flags))
			gfs2_io_error_bh_wd(sdp, bh);
		return -EIO;
	}
	if (unlikely(gfs2_withdrawn(sdp)) && !gfs2_withdraw_in_prog(sdp))
		return -EIO;

	return 0;
}

void gfs2_remove_from_journal(struct buffer_head *bh, int meta)
{
	struct address_space *mapping = bh->b_folio->mapping;
	struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping);
	struct gfs2_bufdata *bd = bh->b_private;
	struct gfs2_trans *tr = current->journal_info;
	int was_pinned = 0;

	if (test_clear_buffer_pinned(bh)) {
		trace_gfs2_pin(bd, 0);
		atomic_dec(&sdp->sd_log_pinned);
		list_del_init(&bd->bd_list);
		if (meta == REMOVE_META)
			tr->tr_num_buf_rm++;
		else
			tr->tr_num_databuf_rm++;
		set_bit(TR_TOUCHED, &tr->tr_flags);
		was_pinned = 1;
		brelse(bh);
	}
	if (bd) {
		if (bd->bd_tr) {
			gfs2_trans_add_revoke(sdp, bd);
		} else if (was_pinned) {
			bh->b_private = NULL;
			kmem_cache_free(gfs2_bufdata_cachep, bd);
		} else if (!list_empty(&bd->bd_ail_st_list) &&
					!list_empty(&bd->bd_ail_gl_list)) {
			gfs2_remove_from_ail(bd);
		}
	}
	clear_buffer_dirty(bh);
	clear_buffer_uptodate(bh);
}

/**
 * gfs2_ail1_wipe - remove deleted/freed buffers from the ail1 list
 * @sdp: superblock
 * @bstart: starting block address of buffers to remove
 * @blen: length of buffers to be removed
 *
 * This function is called from gfs2_journal wipe, whose job is to remove
 * buffers, corresponding to deleted blocks, from the journal. If we find any
 * bufdata elements on the system ail1 list, they haven't been written to
 * the journal yet. So we remove them.
 */
static void gfs2_ail1_wipe(struct gfs2_sbd *sdp, u64 bstart, u32 blen)
{
	struct gfs2_trans *tr, *s;
	struct gfs2_bufdata *bd, *bs;
	struct buffer_head *bh;
	u64 end = bstart + blen;

	gfs2_log_lock(sdp);
	spin_lock(&sdp->sd_ail_lock);
	list_for_each_entry_safe(tr, s, &sdp->sd_ail1_list, tr_list) {
		list_for_each_entry_safe(bd, bs, &tr->tr_ail1_list,
					 bd_ail_st_list) {
			bh = bd->bd_bh;
			if (bh->b_blocknr < bstart || bh->b_blocknr >= end)
				continue;

			gfs2_remove_from_journal(bh, REMOVE_JDATA);
		}
	}
	spin_unlock(&sdp->sd_ail_lock);
	gfs2_log_unlock(sdp);
}

static struct buffer_head *gfs2_getjdatabuf(struct gfs2_inode *ip, u64 blkno)
{
	struct address_space *mapping = ip->i_inode.i_mapping;
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	struct page *page;
	struct buffer_head *bh;
	unsigned int shift = PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift;
	unsigned long index = blkno >> shift; /* convert block to page */
	unsigned int bufnum = blkno - (index << shift);

	page = find_get_page_flags(mapping, index, FGP_LOCK|FGP_ACCESSED);
	if (!page)
		return NULL;
	if (!page_has_buffers(page)) {
		unlock_page(page);
		put_page(page);
		return NULL;
	}
	/* Locate header for our buffer within our page */
	for (bh = page_buffers(page); bufnum--; bh = bh->b_this_page)
		/* Do nothing */;
	get_bh(bh);
	unlock_page(page);
	put_page(page);
	return bh;
}

/**
 * gfs2_journal_wipe - make inode's buffers so they aren't dirty/pinned anymore
 * @ip: the inode who owns the buffers
 * @bstart: the first buffer in the run
 * @blen: the number of buffers in the run
 *
 */

void gfs2_journal_wipe(struct gfs2_inode *ip, u64 bstart, u32 blen)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	struct buffer_head *bh;
	int ty;

	if (!ip->i_gl) {
		/* This can only happen during incomplete inode creation. */
		BUG_ON(!test_bit(GIF_ALLOC_FAILED, &ip->i_flags));
		return;
	}

	gfs2_ail1_wipe(sdp, bstart, blen);
	while (blen) {
		ty = REMOVE_META;
		bh = gfs2_getbuf(ip->i_gl, bstart, NO_CREATE);
		if (!bh && gfs2_is_jdata(ip)) {
			bh = gfs2_getjdatabuf(ip, bstart);
			ty = REMOVE_JDATA;
		}
		if (bh) {
			lock_buffer(bh);
			gfs2_log_lock(sdp);
			spin_lock(&sdp->sd_ail_lock);
			gfs2_remove_from_journal(bh, ty);
			spin_unlock(&sdp->sd_ail_lock);
			gfs2_log_unlock(sdp);
			unlock_buffer(bh);
			brelse(bh);
		}

		bstart++;
		blen--;
	}
}

/**
 * gfs2_meta_buffer - Get a metadata buffer
 * @ip: The GFS2 inode
 * @mtype: The block type (GFS2_METATYPE_*)
 * @num: The block number (device relative) of the buffer
 * @bhp: the buffer is returned here
 *
 * Returns: errno
 */

int gfs2_meta_buffer(struct gfs2_inode *ip, u32 mtype, u64 num,
		     struct buffer_head **bhp)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	struct gfs2_glock *gl = ip->i_gl;
	struct buffer_head *bh;
	int ret = 0;
	int rahead = 0;

	if (num == ip->i_no_addr)
		rahead = ip->i_rahead;

	ret = gfs2_meta_read(gl, num, DIO_WAIT, rahead, &bh);
	if (ret == 0 && gfs2_metatype_check(sdp, bh, mtype)) {
		brelse(bh);
		ret = -EIO;
	} else {
		*bhp = bh;
	}
	return ret;
}

/**
 * gfs2_meta_ra - start readahead on an extent of a file
 * @gl: the glock the blocks belong to
 * @dblock: the starting disk block
 * @extlen: the number of blocks in the extent
 *
 * returns: the first buffer in the extent
 */

struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
{
	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
	struct buffer_head *first_bh, *bh;
	u32 max_ra = gfs2_tune_get(sdp, gt_max_readahead) >>
			  sdp->sd_sb.sb_bsize_shift;

	BUG_ON(!extlen);

	if (max_ra < 1)
		max_ra = 1;
	if (extlen > max_ra)
		extlen = max_ra;

	first_bh = gfs2_getbuf(gl, dblock, CREATE);

	if (buffer_uptodate(first_bh))
		goto out;
	bh_read_nowait(first_bh, REQ_META | REQ_PRIO);

	dblock++;
	extlen--;

	while (extlen) {
		bh = gfs2_getbuf(gl, dblock, CREATE);

		bh_readahead(bh, REQ_RAHEAD | REQ_META | REQ_PRIO);
		brelse(bh);
		dblock++;
		extlen--;
		if (!buffer_locked(first_bh) && buffer_uptodate(first_bh))
			goto out;
	}

	wait_on_buffer(first_bh);
out:
	return first_bh;
}