summaryrefslogtreecommitdiffstats
path: root/fs/hfsplus/btree.c
blob: 3345c7553edc131302b5a2202418f3c47a0e4f03 (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
/*
 *  linux/fs/hfsplus/btree.c
 *
 * Copyright (C) 2001
 * Brad Boyer (flar@allandria.com)
 * (C) 2003 Ardis Technologies <roman@ardistech.com>
 *
 * Handle opening/closing btree
 */

#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/log2.h>

#include "hfsplus_fs.h"
#include "hfsplus_raw.h"

/*
 * Initial source code of clump size calculation is gotten
 * from http://opensource.apple.com/tarballs/diskdev_cmds/
 */
#define CLUMP_ENTRIES	15

static short clumptbl[CLUMP_ENTRIES * 3] = {
/*
 *	    Volume	Attributes	 Catalog	 Extents
 *	     Size	Clump (MB)	Clump (MB)	Clump (MB)
 */
	/*   1GB */	  4,		  4,		 4,
	/*   2GB */	  6,		  6,		 4,
	/*   4GB */	  8,		  8,		 4,
	/*   8GB */	 11,		 11,		 5,
	/*
	 * For volumes 16GB and larger, we want to make sure that a full OS
	 * install won't require fragmentation of the Catalog or Attributes
	 * B-trees.  We do this by making the clump sizes sufficiently large,
	 * and by leaving a gap after the B-trees for them to grow into.
	 *
	 * For SnowLeopard 10A298, a FullNetInstall with all packages selected
	 * results in:
	 * Catalog B-tree Header
	 *	nodeSize:          8192
	 *	totalNodes:       31616
	 *	freeNodes:         1978
	 * (used = 231.55 MB)
	 * Attributes B-tree Header
	 *	nodeSize:          8192
	 *	totalNodes:       63232
	 *	freeNodes:          958
	 * (used = 486.52 MB)
	 *
	 * We also want Time Machine backup volumes to have a sufficiently
	 * large clump size to reduce fragmentation.
	 *
	 * The series of numbers for Catalog and Attribute form a geometric
	 * series. For Catalog (16GB to 512GB), each term is 8**(1/5) times
	 * the previous term.  For Attributes (16GB to 512GB), each term is
	 * 4**(1/5) times the previous term.  For 1TB to 16TB, each term is
	 * 2**(1/5) times the previous term.
	 */
	/*  16GB */	 64,		 32,		 5,
	/*  32GB */	 84,		 49,		 6,
	/*  64GB */	111,		 74,		 7,
	/* 128GB */	147,		111,		 8,
	/* 256GB */	194,		169,		 9,
	/* 512GB */	256,		256,		11,
	/*   1TB */	294,		294,		14,
	/*   2TB */	338,		338,		16,
	/*   4TB */	388,		388,		20,
	/*   8TB */	446,		446,		25,
	/*  16TB */	512,		512,		32
};

u32 hfsplus_calc_btree_clump_size(u32 block_size, u32 node_size,
					u64 sectors, int file_id)
{
	u32 mod = max(node_size, block_size);
	u32 clump_size;
	int column;
	int i;

	/* Figure out which column of the above table to use for this file. */
	switch (file_id) {
	case HFSPLUS_ATTR_CNID:
		column = 0;
		break;
	case HFSPLUS_CAT_CNID:
		column = 1;
		break;
	default:
		column = 2;
		break;
	}

	/*
	 * The default clump size is 0.8% of the volume size. And
	 * it must also be a multiple of the node and block size.
	 */
	if (sectors < 0x200000) {
		clump_size = sectors << 2;	/*  0.8 %  */
		if (clump_size < (8 * node_size))
			clump_size = 8 * node_size;
	} else {
		/* turn exponent into table index... */
		for (i = 0, sectors = sectors >> 22;
		     sectors && (i < CLUMP_ENTRIES - 1);
		     ++i, sectors = sectors >> 1) {
			/* empty body */
		}

		clump_size = clumptbl[column + (i) * 3] * 1024 * 1024;
	}

	/*
	 * Round the clump size to a multiple of node and block size.
	 * NOTE: This rounds down.
	 */
	clump_size /= mod;
	clump_size *= mod;

	/*
	 * Rounding down could have rounded down to 0 if the block size was
	 * greater than the clump size.  If so, just use one block or node.
	 */
	if (clump_size == 0)
		clump_size = mod;

	return clump_size;
}

/* Get a reference to a B*Tree and do some initial checks */
struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id)
{
	struct hfs_btree *tree;
	struct hfs_btree_header_rec *head;
	struct address_space *mapping;
	struct inode *inode;
	struct page *page;
	unsigned int size;

	tree = kzalloc(sizeof(*tree), GFP_KERNEL);
	if (!tree)
		return NULL;

	mutex_init(&tree->tree_lock);
	spin_lock_init(&tree->hash_lock);
	tree->sb = sb;
	tree->cnid = id;
	inode = hfsplus_iget(sb, id);
	if (IS_ERR(inode))
		goto free_tree;
	tree->inode = inode;

	if (!HFSPLUS_I(tree->inode)->first_blocks) {
		pr_err("invalid btree extent records (0 size)\n");
		goto free_inode;
	}

	mapping = tree->inode->i_mapping;
	page = read_mapping_page(mapping, 0, NULL);
	if (IS_ERR(page))
		goto free_inode;

	/* Load the header */
	head = (struct hfs_btree_header_rec *)(kmap(page) +
		sizeof(struct hfs_bnode_desc));
	tree->root = be32_to_cpu(head->root);
	tree->leaf_count = be32_to_cpu(head->leaf_count);
	tree->leaf_head = be32_to_cpu(head->leaf_head);
	tree->leaf_tail = be32_to_cpu(head->leaf_tail);
	tree->node_count = be32_to_cpu(head->node_count);
	tree->free_nodes = be32_to_cpu(head->free_nodes);
	tree->attributes = be32_to_cpu(head->attributes);
	tree->node_size = be16_to_cpu(head->node_size);
	tree->max_key_len = be16_to_cpu(head->max_key_len);
	tree->depth = be16_to_cpu(head->depth);

	/* Verify the tree and set the correct compare function */
	switch (id) {
	case HFSPLUS_EXT_CNID:
		if (tree->max_key_len != HFSPLUS_EXT_KEYLEN - sizeof(u16)) {
			pr_err("invalid extent max_key_len %d\n",
				tree->max_key_len);
			goto fail_page;
		}
		if (tree->attributes & HFS_TREE_VARIDXKEYS) {
			pr_err("invalid extent btree flag\n");
			goto fail_page;
		}

		tree->keycmp = hfsplus_ext_cmp_key;
		break;
	case HFSPLUS_CAT_CNID:
		if (tree->max_key_len != HFSPLUS_CAT_KEYLEN - sizeof(u16)) {
			pr_err("invalid catalog max_key_len %d\n",
				tree->max_key_len);
			goto fail_page;
		}
		if (!(tree->attributes & HFS_TREE_VARIDXKEYS)) {
			pr_err("invalid catalog btree flag\n");
			goto fail_page;
		}

		if (test_bit(HFSPLUS_SB_HFSX, &HFSPLUS_SB(sb)->flags) &&
		    (head->key_type == HFSPLUS_KEY_BINARY))
			tree->keycmp = hfsplus_cat_bin_cmp_key;
		else {
			tree->keycmp = hfsplus_cat_case_cmp_key;
			set_bit(HFSPLUS_SB_CASEFOLD, &HFSPLUS_SB(sb)->flags);
		}
		break;
	case HFSPLUS_ATTR_CNID:
		if (tree->max_key_len != HFSPLUS_ATTR_KEYLEN - sizeof(u16)) {
			pr_err("invalid attributes max_key_len %d\n",
				tree->max_key_len);
			goto fail_page;
		}
		tree->keycmp = hfsplus_attr_bin_cmp_key;
		break;
	default:
		pr_err("unknown B*Tree requested\n");
		goto fail_page;
	}

	if (!(tree->attributes & HFS_TREE_BIGKEYS)) {
		pr_err("invalid btree flag\n");
		goto fail_page;
	}

	size = tree->node_size;
	if (!is_power_of_2(size))
		goto fail_page;
	if (!tree->node_count)
		goto fail_page;

	tree->node_size_shift = ffs(size) - 1;

	tree->pages_per_bnode =
		(tree->node_size + PAGE_CACHE_SIZE - 1) >>
		PAGE_CACHE_SHIFT;

	kunmap(page);
	page_cache_release(page);
	return tree;

 fail_page:
	page_cache_release(page);
 free_inode:
	tree->inode->i_mapping->a_ops = &hfsplus_aops;
	iput(tree->inode);
 free_tree:
	kfree(tree);
	return NULL;
}

/* Release resources used by a btree */
void hfs_btree_close(struct hfs_btree *tree)
{
	struct hfs_bnode *node;
	int i;

	if (!tree)
		return;

	for (i = 0; i < NODE_HASH_SIZE; i++) {
		while ((node = tree->node_hash[i])) {
			tree->node_hash[i] = node->next_hash;
			if (atomic_read(&node->refcnt))
				pr_crit("node %d:%d "
						"still has %d user(s)!\n",
					node->tree->cnid, node->this,
					atomic_read(&node->refcnt));
			hfs_bnode_free(node);
			tree->node_hash_cnt--;
		}
	}
	iput(tree->inode);
	kfree(tree);
}

int hfs_btree_write(struct hfs_btree *tree)
{
	struct hfs_btree_header_rec *head;
	struct hfs_bnode *node;
	struct page *page;

	node = hfs_bnode_find(tree, 0);
	if (IS_ERR(node))
		/* panic? */
		return -EIO;
	/* Load the header */
	page = node->page[0];
	head = (struct hfs_btree_header_rec *)(kmap(page) +
		sizeof(struct hfs_bnode_desc));

	head->root = cpu_to_be32(tree->root);
	head->leaf_count = cpu_to_be32(tree->leaf_count);
	head->leaf_head = cpu_to_be32(tree->leaf_head);
	head->leaf_tail = cpu_to_be32(tree->leaf_tail);
	head->node_count = cpu_to_be32(tree->node_count);
	head->free_nodes = cpu_to_be32(tree->free_nodes);
	head->attributes = cpu_to_be32(tree->attributes);
	head->depth = cpu_to_be16(tree->depth);

	kunmap(page);
	set_page_dirty(page);
	hfs_bnode_put(node);
	return 0;
}

static struct hfs_bnode *hfs_bmap_new_bmap(struct hfs_bnode *prev, u32 idx)
{
	struct hfs_btree *tree = prev->tree;
	struct hfs_bnode *node;
	struct hfs_bnode_desc desc;
	__be32 cnid;

	node = hfs_bnode_create(tree, idx);
	if (IS_ERR(node))
		return node;

	tree->free_nodes--;
	prev->next = idx;
	cnid = cpu_to_be32(idx);
	hfs_bnode_write(prev, &cnid, offsetof(struct hfs_bnode_desc, next), 4);

	node->type = HFS_NODE_MAP;
	node->num_recs = 1;
	hfs_bnode_clear(node, 0, tree->node_size);
	desc.next = 0;
	desc.prev = 0;
	desc.type = HFS_NODE_MAP;
	desc.height = 0;
	desc.num_recs = cpu_to_be16(1);
	desc.reserved = 0;
	hfs_bnode_write(node, &desc, 0, sizeof(desc));
	hfs_bnode_write_u16(node, 14, 0x8000);
	hfs_bnode_write_u16(node, tree->node_size - 2, 14);
	hfs_bnode_write_u16(node, tree->node_size - 4, tree->node_size - 6);

	return node;
}

struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree)
{
	struct hfs_bnode *node, *next_node;
	struct page **pagep;
	u32 nidx, idx;
	unsigned off;
	u16 off16;
	u16 len;
	u8 *data, byte, m;
	int i;

	while (!tree->free_nodes) {
		struct inode *inode = tree->inode;
		struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
		u32 count;
		int res;

		res = hfsplus_file_extend(inode, hfs_bnode_need_zeroout(tree));
		if (res)
			return ERR_PTR(res);
		hip->phys_size = inode->i_size =
			(loff_t)hip->alloc_blocks <<
				HFSPLUS_SB(tree->sb)->alloc_blksz_shift;
		hip->fs_blocks =
			hip->alloc_blocks << HFSPLUS_SB(tree->sb)->fs_shift;
		inode_set_bytes(inode, inode->i_size);
		count = inode->i_size >> tree->node_size_shift;
		tree->free_nodes = count - tree->node_count;
		tree->node_count = count;
	}

	nidx = 0;
	node = hfs_bnode_find(tree, nidx);
	if (IS_ERR(node))
		return node;
	len = hfs_brec_lenoff(node, 2, &off16);
	off = off16;

	off += node->page_offset;
	pagep = node->page + (off >> PAGE_CACHE_SHIFT);
	data = kmap(*pagep);
	off &= ~PAGE_CACHE_MASK;
	idx = 0;

	for (;;) {
		while (len) {
			byte = data[off];
			if (byte != 0xff) {
				for (m = 0x80, i = 0; i < 8; m >>= 1, i++) {
					if (!(byte & m)) {
						idx += i;
						data[off] |= m;
						set_page_dirty(*pagep);
						kunmap(*pagep);
						tree->free_nodes--;
						mark_inode_dirty(tree->inode);
						hfs_bnode_put(node);
						return hfs_bnode_create(tree,
							idx);
					}
				}
			}
			if (++off >= PAGE_CACHE_SIZE) {
				kunmap(*pagep);
				data = kmap(*++pagep);
				off = 0;
			}
			idx += 8;
			len--;
		}
		kunmap(*pagep);
		nidx = node->next;
		if (!nidx) {
			hfs_dbg(BNODE_MOD, "create new bmap node\n");
			next_node = hfs_bmap_new_bmap(node, idx);
		} else
			next_node = hfs_bnode_find(tree, nidx);
		hfs_bnode_put(node);
		if (IS_ERR(next_node))
			return next_node;
		node = next_node;

		len = hfs_brec_lenoff(node, 0, &off16);
		off = off16;
		off += node->page_offset;
		pagep = node->page + (off >> PAGE_CACHE_SHIFT);
		data = kmap(*pagep);
		off &= ~PAGE_CACHE_MASK;
	}
}

void hfs_bmap_free(struct hfs_bnode *node)
{
	struct hfs_btree *tree;
	struct page *page;
	u16 off, len;
	u32 nidx;
	u8 *data, byte, m;

	hfs_dbg(BNODE_MOD, "btree_free_node: %u\n", node->this);
	BUG_ON(!node->this);
	tree = node->tree;
	nidx = node->this;
	node = hfs_bnode_find(tree, 0);
	if (IS_ERR(node))
		return;
	len = hfs_brec_lenoff(node, 2, &off);
	while (nidx >= len * 8) {
		u32 i;

		nidx -= len * 8;
		i = node->next;
		hfs_bnode_put(node);
		if (!i) {
			/* panic */;
			pr_crit("unable to free bnode %u. "
					"bmap not found!\n",
				node->this);
			return;
		}
		node = hfs_bnode_find(tree, i);
		if (IS_ERR(node))
			return;
		if (node->type != HFS_NODE_MAP) {
			/* panic */;
			pr_crit("invalid bmap found! "
					"(%u,%d)\n",
				node->this, node->type);
			hfs_bnode_put(node);
			return;
		}
		len = hfs_brec_lenoff(node, 0, &off);
	}
	off += node->page_offset + nidx / 8;
	page = node->page[off >> PAGE_CACHE_SHIFT];
	data = kmap(page);
	off &= ~PAGE_CACHE_MASK;
	m = 1 << (~nidx & 7);
	byte = data[off];
	if (!(byte & m)) {
		pr_crit("trying to free free bnode "
				"%u(%d)\n",
			node->this, node->type);
		kunmap(page);
		hfs_bnode_put(node);
		return;
	}
	data[off] = byte & ~m;
	set_page_dirty(page);
	kunmap(page);
	hfs_bnode_put(node);
	tree->free_nodes++;
	mark_inode_dirty(tree->inode);
}