summaryrefslogtreecommitdiff
path: root/fs/ocfs2/move_extents.c
blob: e928a88f2db19110a945d279ef8927cd914ae7ec (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
/* -*- mode: c; c-basic-offset: 8; -*-
 * vim: noexpandtab sw=8 ts=8 sts=0:
 *
 * move_extents.c
 *
 * Copyright (C) 2011 Oracle.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License version 2 as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 */
#include <linux/fs.h>
#include <linux/types.h>
#include <linux/mount.h>
#include <linux/swap.h>

#include <cluster/masklog.h>

#include "ocfs2.h"
#include "ocfs2_ioctl.h"

#include "alloc.h"
#include "aops.h"
#include "dlmglue.h"
#include "extent_map.h"
#include "inode.h"
#include "journal.h"
#include "suballoc.h"
#include "uptodate.h"
#include "super.h"
#include "dir.h"
#include "buffer_head_io.h"
#include "sysfile.h"
#include "suballoc.h"
#include "refcounttree.h"
#include "move_extents.h"

struct ocfs2_move_extents_context {
	struct inode *inode;
	struct file *file;
	int auto_defrag;
	int credits;
	u32 new_phys_cpos;
	u32 clusters_moved;
	u64 refcount_loc;
	struct ocfs2_move_extents *range;
	struct ocfs2_extent_tree et;
	struct ocfs2_alloc_context *meta_ac;
	struct ocfs2_alloc_context *data_ac;
	struct ocfs2_cached_dealloc_ctxt dealloc;
};

static int __ocfs2_move_extent(handle_t *handle,
			       struct ocfs2_move_extents_context *context,
			       u32 cpos, u32 len, u32 p_cpos, u32 new_p_cpos,
			       int ext_flags)
{
	int ret = 0, index;
	struct inode *inode = context->inode;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	struct ocfs2_extent_rec *rec, replace_rec;
	struct ocfs2_path *path = NULL;
	struct ocfs2_extent_list *el;
	u64 ino = ocfs2_metadata_cache_owner(context->et.et_ci);
	u64 old_blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cpos);

	ret = ocfs2_duplicate_clusters_by_page(handle, context->file, cpos,
					       p_cpos, new_p_cpos, len);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	memset(&replace_rec, 0, sizeof(replace_rec));
	replace_rec.e_cpos = cpu_to_le32(cpos);
	replace_rec.e_leaf_clusters = cpu_to_le16(len);
	replace_rec.e_blkno = cpu_to_le64(ocfs2_clusters_to_blocks(inode->i_sb,
								   new_p_cpos));

	path = ocfs2_new_path_from_et(&context->et);
	if (!path) {
		ret = -ENOMEM;
		mlog_errno(ret);
		goto out;
	}

	ret = ocfs2_find_path(INODE_CACHE(inode), path, cpos);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	el = path_leaf_el(path);

	index = ocfs2_search_extent_list(el, cpos);
	if (index == -1 || index >= le16_to_cpu(el->l_next_free_rec)) {
		ocfs2_error(inode->i_sb,
			    "Inode %llu has an extent at cpos %u which can no "
			    "longer be found.\n",
			    (unsigned long long)ino, cpos);
		ret = -EROFS;
		goto out;
	}

	rec = &el->l_recs[index];

	BUG_ON(ext_flags != rec->e_flags);
	/*
	 * after moving/defraging to new location, the extent is not going
	 * to be refcounted anymore.
	 */
	replace_rec.e_flags = ext_flags & ~OCFS2_EXT_REFCOUNTED;

	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode),
				      context->et.et_root_bh,
				      OCFS2_JOURNAL_ACCESS_WRITE);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	ret = ocfs2_split_extent(handle, &context->et, path, index,
				 &replace_rec, context->meta_ac,
				 &context->dealloc);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	ocfs2_journal_dirty(handle, context->et.et_root_bh);

	context->new_phys_cpos = new_p_cpos;

	/*
	 * need I to append truncate log for old clusters?
	 */
	if (old_blkno) {
		if (ext_flags & OCFS2_EXT_REFCOUNTED)
			ret = ocfs2_decrease_refcount(inode, handle,
					ocfs2_blocks_to_clusters(osb->sb,
								 old_blkno),
					len, context->meta_ac,
					&context->dealloc, 1);
		else
			ret = ocfs2_truncate_log_append(osb, handle,
							old_blkno, len);
	}

out:
	return ret;
}

/*
 * lock allocators, and reserving appropriate number of bits for
 * meta blocks and data clusters.
 *
 * in some cases, we don't need to reserve clusters, just let data_ac
 * be NULL.
 */
static int ocfs2_lock_allocators_move_extents(struct inode *inode,
					struct ocfs2_extent_tree *et,
					u32 clusters_to_move,
					u32 extents_to_split,
					struct ocfs2_alloc_context **meta_ac,
					struct ocfs2_alloc_context **data_ac,
					int extra_blocks,
					int *credits)
{
	int ret, num_free_extents;
	unsigned int max_recs_needed = 2 * extents_to_split + clusters_to_move;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);

	num_free_extents = ocfs2_num_free_extents(osb, et);
	if (num_free_extents < 0) {
		ret = num_free_extents;
		mlog_errno(ret);
		goto out;
	}

	if (!num_free_extents ||
	    (ocfs2_sparse_alloc(osb) && num_free_extents < max_recs_needed))
		extra_blocks += ocfs2_extend_meta_needed(et->et_root_el);

	ret = ocfs2_reserve_new_metadata_blocks(osb, extra_blocks, meta_ac);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	if (data_ac) {
		ret = ocfs2_reserve_clusters(osb, clusters_to_move, data_ac);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}
	}

	*credits += ocfs2_calc_extend_credits(osb->sb, et->et_root_el,
					      clusters_to_move + 2);

	mlog(0, "reserve metadata_blocks: %d, data_clusters: %u, credits: %d\n",
	     extra_blocks, clusters_to_move, *credits);
out:
	if (ret) {
		if (*meta_ac) {
			ocfs2_free_alloc_context(*meta_ac);
			*meta_ac = NULL;
		}
	}

	return ret;
}

/*
 * Using one journal handle to guarantee the data consistency in case
 * crash happens anywhere.
 */
static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context,
			       u32 cpos, u32 phys_cpos, u32 len, int ext_flags)
{
	int ret, credits = 0, extra_blocks = 0;
	handle_t *handle;
	struct inode *inode = context->inode;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	struct inode *tl_inode = osb->osb_tl_inode;
	struct ocfs2_refcount_tree *ref_tree = NULL;
	u32 new_phys_cpos, new_len;
	u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos);

	if ((ext_flags & OCFS2_EXT_REFCOUNTED) && len) {

		BUG_ON(!(OCFS2_I(inode)->ip_dyn_features &
			 OCFS2_HAS_REFCOUNT_FL));

		BUG_ON(!context->refcount_loc);

		ret = ocfs2_lock_refcount_tree(osb, context->refcount_loc, 1,
					       &ref_tree, NULL);
		if (ret) {
			mlog_errno(ret);
			return ret;
		}

		ret = ocfs2_prepare_refcount_change_for_del(inode,
							context->refcount_loc,
							phys_blkno,
							len,
							&credits,
							&extra_blocks);
		if (ret) {
			mlog_errno(ret);
			goto out;
		}
	}

	ret = ocfs2_lock_allocators_move_extents(inode, &context->et, len, 1,
						 &context->meta_ac,
						 &context->data_ac,
						 extra_blocks, &credits);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	/*
	 * should be using allocation reservation strategy there?
	 *
	 * if (context->data_ac)
	 *	context->data_ac->ac_resv = &OCFS2_I(inode)->ip_la_data_resv;
	 */

	mutex_lock(&tl_inode->i_mutex);

	if (ocfs2_truncate_log_needs_flush(osb)) {
		ret = __ocfs2_flush_truncate_log(osb);
		if (ret < 0) {
			mlog_errno(ret);
			goto out_unlock_mutex;
		}
	}

	handle = ocfs2_start_trans(osb, credits);
	if (IS_ERR(handle)) {
		ret = PTR_ERR(handle);
		mlog_errno(ret);
		goto out_unlock_mutex;
	}

	ret = __ocfs2_claim_clusters(handle, context->data_ac, 1, len,
				     &new_phys_cpos, &new_len);
	if (ret) {
		mlog_errno(ret);
		goto out_commit;
	}

	/*
	 * we're not quite patient here to make multiple attempts for claiming
	 * enough clusters, failure to claim clusters per-requested is not a
	 * disaster though, it can only mean partial range of defragmentation
	 * or extent movements gets gone, users anyway is able to have another
	 * try as they wish anytime, since they're going to be returned a
	 * '-ENOSPC' and completed length of this movement.
	 */
	if (new_len != len) {
		mlog(0, "len_claimed: %u, len: %u\n", new_len, len);
		context->range->me_flags &= ~OCFS2_MOVE_EXT_FL_COMPLETE;
		ret = -ENOSPC;
		goto out_commit;
	}

	mlog(0, "cpos: %u, phys_cpos: %u, new_phys_cpos: %u\n", cpos,
	     phys_cpos, new_phys_cpos);

	ret = __ocfs2_move_extent(handle, context, cpos, len, phys_cpos,
				  new_phys_cpos, ext_flags);
	if (ret)
		mlog_errno(ret);

	/*
	 * Here we should write the new page out first if we are
	 * in write-back mode.
	 */
	ret = ocfs2_cow_sync_writeback(inode->i_sb, context->inode, cpos, len);
	if (ret)
		mlog_errno(ret);

out_commit:
	ocfs2_commit_trans(osb, handle);

out_unlock_mutex:
	mutex_unlock(&tl_inode->i_mutex);

	if (context->data_ac) {
		ocfs2_free_alloc_context(context->data_ac);
		context->data_ac = NULL;
	}

	if (context->meta_ac) {
		ocfs2_free_alloc_context(context->meta_ac);
		context->meta_ac = NULL;
	}

out:
	if (ref_tree)
		ocfs2_unlock_refcount_tree(osb, ref_tree, 1);

	return ret;
}

/*
 * find the victim alloc group, where #blkno fits.
 */
static int ocfs2_find_victim_alloc_group(struct inode *inode,
					 u64 vict_blkno,
					 int type, int slot,
					 int *vict_bit,
					 struct buffer_head **ret_bh)
{
	int ret, i, blocks_per_unit = 1;
	u64 blkno;
	char namebuf[40];

	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	struct buffer_head *ac_bh = NULL, *gd_bh = NULL;
	struct ocfs2_chain_list *cl;
	struct ocfs2_chain_rec *rec;
	struct ocfs2_dinode *ac_dinode;
	struct ocfs2_group_desc *bg;

	ocfs2_sprintf_system_inode_name(namebuf, sizeof(namebuf), type, slot);
	ret = ocfs2_lookup_ino_from_name(osb->sys_root_inode, namebuf,
					 strlen(namebuf), &blkno);
	if (ret) {
		ret = -ENOENT;
		goto out;
	}

	ret = ocfs2_read_blocks_sync(osb, blkno, 1, &ac_bh);
	if (ret) {
		mlog_errno(ret);
		goto out;
	}

	ac_dinode = (struct ocfs2_dinode *)ac_bh->b_data;
	cl = &(ac_dinode->id2.i_chain);
	rec = &(cl->cl_recs[0]);

	if (type == GLOBAL_BITMAP_SYSTEM_INODE)
		blocks_per_unit <<= (osb->s_clustersize_bits -
						inode->i_sb->s_blocksize_bits);
	/*
	 * 'vict_blkno' was out of the valid range.
	 */
	if ((vict_blkno < le64_to_cpu(rec->c_blkno)) ||
	    (vict_blkno >= (le32_to_cpu(ac_dinode->id1.bitmap1.i_total) *
				blocks_per_unit))) {
		ret = -EINVAL;
		goto out;
	}

	for (i = 0; i < le16_to_cpu(cl->cl_next_free_rec); i++) {

		rec = &(cl->cl_recs[i]);
		if (!rec)
			continue;

		bg = NULL;

		do {
			if (!bg)
				blkno = le64_to_cpu(rec->c_blkno);
			else
				blkno = le64_to_cpu(bg->bg_next_group);

			if (gd_bh) {
				brelse(gd_bh);
				gd_bh = NULL;
			}

			ret = ocfs2_read_blocks_sync(osb, blkno, 1, &gd_bh);
			if (ret) {
				mlog_errno(ret);
				goto out;
			}

			bg = (struct ocfs2_group_desc *)gd_bh->b_data;

			if (vict_blkno < (le64_to_cpu(bg->bg_blkno) +
						le16_to_cpu(bg->bg_bits))) {

				*ret_bh = gd_bh;
				*vict_bit = (vict_blkno - blkno) /
							blocks_per_unit;
				mlog(0, "find the victim group: #%llu, "
				     "total_bits: %u, vict_bit: %u\n",
				     blkno, le16_to_cpu(bg->bg_bits),
				     *vict_bit);
				goto out;
			}

		} while (le64_to_cpu(bg->bg_next_group));
	}

	ret = -EINVAL;
out:
	brelse(ac_bh);

	/*
	 * caller has to release the gd_bh properly.
	 */
	return ret;
}

/*
 * XXX: helper to validate and adjust moving goal.
 */
static int ocfs2_validate_and_adjust_move_goal(struct inode *inode,
					       struct ocfs2_move_extents *range)
{
	int ret, goal_bit = 0;

	struct buffer_head *gd_bh = NULL;
	struct ocfs2_group_desc *bg;
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
	int c_to_b = 1 << (osb->s_clustersize_bits -
					inode->i_sb->s_blocksize_bits);

	/*
	 * validate goal sits within global_bitmap, and return the victim
	 * group desc
	 */
	ret = ocfs2_find_victim_alloc_group(inode, range->me_goal,
					    GLOBAL_BITMAP_SYSTEM_INODE,
					    OCFS2_INVALID_SLOT,
					    &goal_bit, &gd_bh);
	if (ret)
		goto out;

	bg = (struct ocfs2_group_desc *)gd_bh->b_data;

	/*
	 * make goal become cluster aligned.
	 */
	if (range->me_goal % c_to_b)
		range->me_goal = range->me_goal / c_to_b * c_to_b;

	/*
	 * moving goal is not allowd to start with a group desc blok(#0 blk)
	 * let's compromise to the latter cluster.
	 */
	if (range->me_goal == le64_to_cpu(bg->bg_blkno))
		range->me_goal += c_to_b;

	/*
	 * movement is not gonna cross two groups.
	 */
	if ((le16_to_cpu(bg->bg_bits) - goal_bit) * osb->s_clustersize <
								range->me_len) {
		ret = -EINVAL;
		goto out;
	}
	/*
	 * more exact validations/adjustments will be performed later during
	 * moving operation for each extent range.
	 */
	mlog(0, "extents get ready to be moved to #%llu block\n",
	     range->me_goal);

out:
	brelse(gd_bh);

	return ret;
}