summaryrefslogtreecommitdiff
path: root/fs/ocfs2/slot_map.c
blob: bdda2d8f85080a5a883c1b01b4cc1fbe68d83d18 (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
/* -*- mode: c; c-basic-offset: 8; -*-
 * vim: noexpandtab sw=8 ts=8 sts=0:
 *
 * slot_map.c
 *
 *
 *
 * Copyright (C) 2002, 2004 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 as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * 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.
 *
 * You should have received a copy of the GNU General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */

#include <linux/types.h>
#include <linux/slab.h>
#include <linux/highmem.h>

#define MLOG_MASK_PREFIX ML_SUPER
#include <cluster/masklog.h>

#include "ocfs2.h"

#include "dlmglue.h"
#include "extent_map.h"
#include "heartbeat.h"
#include "inode.h"
#include "slot_map.h"
#include "super.h"
#include "sysfile.h"

#include "buffer_head_io.h"


struct ocfs2_slot {
	int sl_valid;
	unsigned int sl_node_num;
};

struct ocfs2_slot_info {
	int si_extended;
	int si_slots_per_block;
	struct inode *si_inode;
	unsigned int si_blocks;
	struct buffer_head **si_bh;
	unsigned int si_num_slots;
	struct ocfs2_slot *si_slots;
};


static int __ocfs2_node_num_to_slot(struct ocfs2_slot_info *si,
				    unsigned int node_num);

static void ocfs2_invalidate_slot(struct ocfs2_slot_info *si,
				  int slot_num)
{
	BUG_ON((slot_num < 0) || (slot_num >= si->si_num_slots));
	si->si_slots[slot_num].sl_valid = 0;
}

static void ocfs2_set_slot(struct ocfs2_slot_info *si,
			   int slot_num, unsigned int node_num)
{
	BUG_ON((slot_num < 0) || (slot_num >= si->si_num_slots));

	si->si_slots[slot_num].sl_valid = 1;
	si->si_slots[slot_num].sl_node_num = node_num;
}

/* This version is for the extended slot map */
static void ocfs2_update_slot_info_extended(struct ocfs2_slot_info *si)
{
	int b, i, slotno;
	struct ocfs2_slot_map_extended *se;

	slotno = 0;
	for (b = 0; b < si->si_blocks; b++) {
		se = (struct ocfs2_slot_map_extended *)si->si_bh[b]->b_data;
		for (i = 0;
		     (i < si->si_slots_per_block) &&
		     (slotno < si->si_num_slots);
		     i++, slotno++) {
			if (se->se_slots[i].es_valid)
				ocfs2_set_slot(si, slotno,
					       le32_to_cpu(se->se_slots[i].es_node_num));
			else
				ocfs2_invalidate_slot(si, slotno);
		}
	}
}

/*
 * Post the slot information on disk into our slot_info struct.
 * Must be protected by osb_lock.
 */
static void ocfs2_update_slot_info_old(struct ocfs2_slot_info *si)
{
	int i;
	struct ocfs2_slot_map *sm;

	sm = (struct ocfs2_slot_map *)si->si_bh[0]->b_data;

	for (i = 0; i < si->si_num_slots; i++) {
		if (le16_to_cpu(sm->sm_slots[i]) == (u16)OCFS2_INVALID_SLOT)
			ocfs2_invalidate_slot(si, i);
		else
			ocfs2_set_slot(si, i, le16_to_cpu(sm->sm_slots[i]));
	}
}

static void ocfs2_update_slot_info(struct ocfs2_slot_info *si)
{
	/*
	 * The slot data will have been refreshed when ocfs2_super_lock
	 * was taken.
	 */
	if (si->si_extended)
		ocfs2_update_slot_info_extended(si);
	else
		ocfs2_update_slot_info_old(si);
}

int ocfs2_refresh_slot_info(struct ocfs2_super *osb)
{
	int ret;
	struct ocfs2_slot_info *si = osb->slot_info;

	if (si == NULL)
		return 0;

	BUG_ON(si->si_blocks == 0);
	BUG_ON(si->si_bh == NULL);

	mlog(0, "Refreshing slot map, reading %u block(s)\n",
	     si->si_blocks);

	/*
	 * We pass -1 as blocknr because we expect all of si->si_bh to
	 * be !NULL.  Thus, ocfs2_read_blocks() will ignore blocknr.  If
	 * this is not true, the read of -1 (UINT64_MAX) will fail.
	 */
	ret = ocfs2_read_blocks(si->si_inode, -1, si->si_blocks, si->si_bh,
				OCFS2_BH_IGNORE_CACHE);
	if (ret == 0) {
		spin_lock(&osb->osb_lock);
		ocfs2_update_slot_info(si);
		spin_unlock(&osb->osb_lock);
	}

	return ret;
}

/* post the our slot info stuff into it's destination bh and write it
 * out. */
static void ocfs2_update_disk_slot_extended(struct ocfs2_slot_info *si,
					    int slot_num,
					    struct buffer_head **bh)
{
	int blkind = slot_num / si->si_slots_per_block;
	int slotno = slot_num % si->si_slots_per_block;
	struct ocfs2_slot_map_extended *se;

	BUG_ON(blkind >= si->si_blocks);

	se = (struct ocfs2_slot_map_extended *)si->si_bh[blkind]->b_data;
	se->se_slots[slotno].es_valid = si->si_slots[slot_num].sl_valid;
	if (si->si_slots[slot_num].sl_valid)
		se->se_slots[slotno].es_node_num =
			cpu_to_le32(si->si_slots[slot_num].sl_node_num);
	*bh = si->si_bh[blkind];
}

static void ocfs2_update_disk_slot_old(struct ocfs2_slot_info *si,
				       int slot_num,
				       struct buffer_head **bh)
{
	int i;
	struct ocfs2_slot_map *sm;

	sm = (struct ocfs2_slot_map *)si->si_bh[0]->b_data;
	for (i = 0; i < si->si_num_slots; i++) {
		if (si->si_slots[i].sl_valid)
			sm->sm_slots[i] =
				cpu_to_le16(si->si_slots[i].sl_node_num);
		else
			sm->sm_slots[i] = cpu_to_le16(OCFS2_INVALID_SLOT);
	}
	*bh = si->si_bh[0];
}

static int ocfs2_update_disk_slot(struct ocfs2_super *osb,
				  struct ocfs2_slot_info *si,
				  int slot_num)
{
	int status;
	struct buffer_head *bh;

	spin_lock(&osb->osb_lock);
	if (si->si_extended)
		ocfs2_update_disk_slot_extended(si, slot_num, &bh);
	else
		ocfs2_update_disk_slot_old(si, slot_num, &bh);
	spin_unlock(&osb->osb_lock);

	status = ocfs2_write_block(osb, bh, si->si_inode);
	if (status < 0)
		mlog_errno(status);

	return status;
}

/*
 * Calculate how many bytes are needed by the slot map.  Returns
 * an error if the slot map file is too small.
 */
static int ocfs2_slot_map_physical_size(struct ocfs2_super *osb,
					struct inode *inode,
					unsigned long long *bytes)
{
	unsigned long long bytes_needed;

	if (ocfs2_uses_extended_slot_map(osb)) {
		bytes_needed = osb->max_slots *
			sizeof(struct ocfs2_extended_slot);
	} else {
		bytes_needed = osb->max_slots * sizeof(__le16);
	}
	if (bytes_needed > i_size_read(inode)) {
		mlog(ML_ERROR,
		     "Slot map file is too small!  (size %llu, needed %llu)\n",
		     i_size_read(inode), bytes_needed);
		return -ENOSPC;
	}

	*bytes = bytes_needed;
	return 0;
}

/* try to find global node in the slot info. Returns -ENOENT
 * if nothing is found. */
static int __ocfs2_node_num_to_slot(struct ocfs2_slot_info *si,
				    unsigned int node_num)
{
	int i, ret = -ENOENT;

	for(i = 0; i < si->si_num_slots; i++) {
		if (si->si_slots[i].sl_valid &&
		    (node_num == si->si_slots[i].sl_node_num)) {
			ret = i;
			break;
		}
	}

	return ret;
}

static int __ocfs2_find_empty_slot(struct ocfs2_slot_info *si,
				   int preferred)
{
	int i, ret = -ENOSPC;

	if ((preferred >= 0) && (preferred < si->si_num_slots)) {
		if (!si->si_slots[preferred].sl_valid) {
			ret = preferred;
			goto out;
		}
	}

	for(i = 0; i < si->si_num_slots; i++) {
		if (!si->si_slots[i].sl_valid) {
			ret = i;
			break;
		}
	}
out:
	return ret;
}

int ocfs2_node_num_to_slot(struct ocfs2_super *osb, unsigned int node_num)
{
	int slot;
	struct ocfs2_slot_info *si = osb->slot_info;

	spin_lock(&osb->osb_lock);
	slot = __ocfs2_node_num_to_slot(si, node_num);
	spin_unlock(&osb->osb_lock);

	return slot;
}

int ocfs2_slot_to_node_num_locked(struct ocfs2_super *osb, int slot_num,
				  unsigned int *node_num)
{
	struct ocfs2_slot_info *si = osb->slot_info;

	assert_spin_locked(&osb->osb_lock);

	BUG_ON(slot_num < 0);
	BUG_ON(slot_num > osb->max_slots);

	if (!si->si_slots[slot_num].sl_valid)
		return -ENOENT;

	*node_num = si->si_slots[slot_num].sl_node_num;
	return 0;
}

static void __ocfs2_free_slot_info(struct ocfs2_slot_info *si)
{
	unsigned int i;

	if (si == NULL)
		return;

	if (si->si_inode)
		iput(si->si_inode);
	if (si->si_bh) {
		for (i = 0; i < si->si_blocks; i++) {
			if (si->si_bh[i]) {
				brelse(si->si_bh[i]);
				si->si_bh[i] = NULL;
			}
		}
		kfree(si->si_bh);
	}

	kfree(si);
}

int ocfs2_clear_slot(struct ocfs2_super *osb, int slot_num)
{
	struct ocfs2_slot_info *si = osb->slot_info;

	if (si == NULL)
		return 0;

	spin_lock(&osb->osb_lock);
	ocfs2_invalidate_slot(si, slot_num);
	spin_unlock(&osb->osb_lock);

	return ocfs2_update_disk_slot(osb, osb->slot_info, slot_num);
}

static int ocfs2_map_slot_buffers(struct ocfs2_super *osb,
				  struct ocfs2_slot_info *si)
{
	int status = 0;
	u64 blkno;
	unsigned long long blocks, bytes;
	unsigned int i;
	struct buffer_head *bh;

	status = ocfs2_slot_map_physical_size(osb, si->si_inode, &bytes);
	if (status)
		goto bail;

	blocks = ocfs2_blocks_for_bytes(si->si_inode->i_sb, bytes);
	BUG_ON(blocks > UINT_MAX);
	si->si_blocks = blocks;
	if (!si->si_blocks)
		goto bail;

	if (si->si_extended)
		si->si_slots_per_block =
			(osb->sb->s_blocksize /
			 sizeof(struct ocfs2_extended_slot));
	else
		si->si_slots_per_block = osb->sb->s_blocksize / sizeof(__le16);

	/* The size checks above should ensure this */
	BUG_ON((osb->max_slots / si->si_slots_per_block) > blocks);

	mlog(0, "Slot map needs %u buffers for %llu bytes\n",
	     si->si_blocks, bytes);

	si->si_bh = kzalloc(sizeof(struct buffer_head *) * si->si_blocks,
			    GFP_KERNEL);
	if (!si->si_bh) {
		status = -ENOMEM;
		mlog_errno(status);
		goto bail;
	}

	for (i = 0; i < si->si_blocks; i++) {
		status = ocfs2_extent_map_get_blocks(si->si_inode, i,
						     &blkno, NULL, NULL);
		if (status < 0) {
			mlog_errno(status);
			goto bail;
		}

		mlog(0, "Reading slot map block %u at %llu\n", i,
		     (unsigned long long)blkno);

		bh = NULL;  /* Acquire a fresh bh */
		status = ocfs2_read_blocks(si->si_inode, blkno, 1, &bh,
					   OCFS2_BH_IGNORE_CACHE);
		if (status < 0) {
			mlog_errno(status);
			goto bail;
		}

		si->si_bh[i] = bh;
	}

bail:
	return status;
}

int ocfs2_init_slot_info(struct ocfs2_super *osb)
{
	int status;
	struct inode *inode = NULL;
	struct ocfs2_slot_info *si;

	si = kzalloc(sizeof(struct ocfs2_slot_info) +
		     (sizeof(struct ocfs2_slot) * osb->max_slots),
		     GFP_KERNEL);
	if (!si) {
		status = -ENOMEM;
		mlog_errno(status);
		goto bail;
	}

	si->si_extended = ocfs2_uses_extended_slot_map(osb);
	si->si_num_slots = osb->max_slots;
	si->si_slots = (struct ocfs2_slot *)((char *)si +
					     sizeof(struct ocfs2_slot_info));

	inode = ocfs2_get_system_file_inode(osb, SLOT_MAP_SYSTEM_INODE,
					    OCFS2_INVALID_SLOT);
	if (!inode) {
		status = -EINVAL;
		mlog_errno(status);
		goto bail;
	}

	si->si_inode = inode;
	status = ocfs2_map_slot_buffers(osb, si);
	if (status < 0) {
		mlog_errno(status);
		goto bail;
	}

	osb->slot_info = (struct ocfs2_slot_info *)si;
bail:
	if (status < 0 && si)
		__ocfs2_free_slot_info(si);

	return status;
}

void ocfs2_free_slot_info(struct ocfs2_super *osb)
{
	struct ocfs2_slot_info *si = osb->slot_info;

	osb->slot_info = NULL;
	__ocfs2_free_slot_info(si);
}

int ocfs2_find_slot(struct ocfs2_super *osb)
{
	int status;
	int slot;
	struct ocfs2_slot_info *si;

	mlog_entry_void();

	si = osb->slot_info;

	spin_lock(&osb->osb_lock);
	ocfs2_update_slot_info(si);

	/* search for ourselves first and take the slot if it already
	 * exists. Perhaps we need to mark this in a variable for our
	 * own journal recovery? Possibly not, though we certainly
	 * need to warn to the user */
	slot = __ocfs2_node_num_to_slot(si, osb->node_num);
	if (slot < 0) {
		/* if no slot yet, then just take 1st available
		 * one. */
		slot = __ocfs2_find_empty_slot(si, osb->preferred_slot);
		if (slot < 0) {
			spin_unlock(&osb->osb_lock);
			mlog(ML_ERROR, "no free slots available!\n");
			status = -EINVAL;
			goto bail;
		}
	} else
		mlog(ML_NOTICE, "slot %d is already allocated to this node!\n",
		     slot);

	ocfs2_set_slot(si, slot, osb->node_num);
	osb->slot_num = slot;
	spin_unlock(&osb->osb_lock);

	mlog(0, "taking node slot %d\n", osb->slot_num);

	status = ocfs2_update_disk_slot(osb, si, osb->slot_num);
	if (status < 0)
		mlog_errno(status);

bail:
	mlog_exit(status);
	return status;
}

void ocfs2_put_slot(struct ocfs2_super *osb)
{
	int status, slot_num;
	struct ocfs2_slot_info *si = osb->slot_info;

	if (!si)
		return;

	spin_lock(&osb->osb_lock);
	ocfs2_update_slot_info(si);

	slot_num = osb->slot_num;
	ocfs2_invalidate_slot(si, osb->slot_num);
	osb->slot_num = OCFS2_INVALID_SLOT;
	spin_unlock(&osb->osb_lock);

	status = ocfs2_update_disk_slot(osb, si, slot_num);
	if (status < 0) {
		mlog_errno(status);
		goto bail;
	}

bail:
	ocfs2_free_slot_info(osb);
}