Home Home > GIT Browse
summaryrefslogtreecommitdiff
blob: bcb67b0cabe7e5b99561610106fe383066925d9e (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
// SPDX-License-Identifier: GPL-2.0
/*
 *  linux/fs/sysv/itree.c
 *
 *  Handling of indirect blocks' trees.
 *  AV, Sep--Dec 2000
 */

#include <linux/buffer_head.h>
#include <linux/mount.h>
#include <linux/string.h>
#include "sysv.h"

enum {DIRECT = 10, DEPTH = 4};	/* Have triple indirect */

static inline void dirty_indirect(struct buffer_head *bh, struct inode *inode)
{
	mark_buffer_dirty_inode(bh, inode);
	if (IS_SYNC(inode))
		sync_dirty_buffer(bh);
}

static int block_to_path(struct inode *inode, long block, int offsets[DEPTH])
{
	struct super_block *sb = inode->i_sb;
	struct sysv_sb_info *sbi = SYSV_SB(sb);
	int ptrs_bits = sbi->s_ind_per_block_bits;
	unsigned long	indirect_blocks = sbi->s_ind_per_block,
			double_blocks = sbi->s_ind_per_block_2;
	int n = 0;

	if (block < 0) {
		printk("sysv_block_map: block < 0\n");
	} else if (block < DIRECT) {
		offsets[n++] = block;
	} else if ( (block -= DIRECT) < indirect_blocks) {
		offsets[n++] = DIRECT;
		offsets[n++] = block;
	} else if ((block -= indirect_blocks) < double_blocks) {
		offsets[n++] = DIRECT+1;
		offsets[n++] = block >> ptrs_bits;
		offsets[n++] = block & (indirect_blocks - 1);
	} else if (((block -= double_blocks) >> (ptrs_bits * 2)) < indirect_blocks) {
		offsets[n++] = DIRECT+2;
		offsets[n++] = block >> (ptrs_bits * 2);
		offsets[n++] = (block >> ptrs_bits) & (indirect_blocks - 1);
		offsets[n++] = block & (indirect_blocks - 1);
	} else {
		/* nothing */;
	}
	return n;
}

static inline int block_to_cpu(struct sysv_sb_info *sbi, sysv_zone_t nr)
{
	return sbi->s_block_base + fs32_to_cpu(sbi, nr);
}

typedef struct {
	sysv_zone_t     *p;
	sysv_zone_t     key;
	struct buffer_head *bh;
} Indirect;

static DEFINE_RWLOCK(pointers_lock);

static inline void add_chain(Indirect *p, struct buffer_head *bh, sysv_zone_t *v)
{
	p->key = *(p->p = v);
	p->bh = bh;
}

static inline int verify_chain(Indirect *from, Indirect *to)
{
	while (from <= to && from->key == *from->p)
		from++;
	return (from > to);
}

static inline sysv_zone_t *block_end(struct buffer_head *bh)
{
	return (sysv_zone_t*)((char*)bh->b_data + bh->b_size);
}

/*
 * Requires read_lock(&pointers_lock) or write_lock(&pointers_lock)
 */
static Indirect *get_branch(struct inode *inode,
			    int depth,
			    int offsets[],
			    Indirect chain[],
			    int *err)
{
	struct super_block *sb = inode->i_sb;
	Indirect *p = chain;
	struct buffer_head *bh;

	*err = 0;
	add_chain(chain, NULL, SYSV_I(inode)->i_data + *offsets);
	if (!p->key)
		goto no_block;
	while (--depth) {
		int block = block_to_cpu(SYSV_SB(sb), p->key);
		bh = sb_bread(sb, block);
		if (!bh)
			goto failure;
		if (!verify_chain(chain, p))
			goto changed;
		add_chain(++p, bh, (sysv_zone_t*)bh->b_data + *++offsets);
		if (!p->key)
			goto no_block;
	}
	return NULL;

changed:
	brelse(bh);
	*err = -EAGAIN;
	goto no_block;
failure:
	*err = -EIO;
no_block:
	return p;
}

static int alloc_branch(struct inode *inode,
			int num,
			int *offsets,
			Indirect *branch)
{
	int blocksize = inode->i_sb->s_blocksize;
	int n = 0;
	int i;

	branch[0].key = sysv_new_block(inode->i_sb);
	if (branch[0].key) for (n = 1; n < num; n++) {
		struct buffer_head *bh;
		int parent;
		/* Allocate the next block */
		branch[n].key = sysv_new_block(inode->i_sb);
		if (!branch[n].key)
			break;
		/*
		 * Get buffer_head for parent block, zero it out and set 
		 * the pointer to new one, then send parent to disk.
		 */
		parent = block_to_cpu(SYSV_SB(inode->i_sb), branch[n-1].key);
		bh = sb_getblk(inode->i_sb, parent);
		lock_buffer(bh);
		memset(bh->b_data, 0, blocksize);
		branch[n].bh = bh;
		branch[n].p = (sysv_zone_t*) bh->b_data + offsets[n];
		*branch[n].p = branch[n].key;
		set_buffer_uptodate(bh);
		unlock_buffer(bh);
		dirty_indirect(bh, inode);
	}
	if (n == num)
		return 0;

	/* Allocation failed, free what we already allocated */
	for (i = 1; i < n; i++)
		bforget(branch[i].bh);
	for (i = 0; i < n; i++)
		sysv_free_block(inode->i_sb, branch[i].key);
	return -ENOSPC;
}

static inline int splice_branch(struct inode *inode,
				Indirect chain[],
				Indirect *where,
				int num)
{
	int i;

	/* Verify that place we are splicing to is still there and vacant */
	write_lock(&pointers_lock);
	if (!verify_chain(chain, where-1) || *where->p)
		goto changed;
	*where->p = where->key;
	write_unlock(&pointers_lock);

	inode->i_ctime = current_time(inode);

	/* had we spliced it onto indirect block? */
	if (where->bh)
		dirty_indirect(where->bh, inode);

	if (IS_SYNC(inode))
		sysv_sync_inode(inode);
	else
		mark_inode_dirty(inode);
	return 0;

changed:
	write_unlock(&pointers_lock);
	for (i = 1; i < num; i++)
		bforget(where[i].bh);
	for (i = 0; i < num; i++)
		sysv_free_block(inode->i_sb, where[i].key);
	return -EAGAIN;
}

static int get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create)
{
	int err = -EIO;
	int offsets[DEPTH];
	Indirect chain[DEPTH];
	struct super_block *sb = inode->i_sb;
	Indirect *partial;
	int left;
	int depth = block_to_path(inode, iblock, offsets);

	if (depth == 0)
		goto out;

reread:
	read_lock(&pointers_lock);
	partial = get_branch(inode, depth, offsets, chain, &err);
	read_unlock(&pointers_lock);

	/* Simplest case - block found, no allocation needed */
	if (!partial) {
got_it:
		map_bh(bh_result, sb, block_to_cpu(SYSV_SB(sb),
					chain[depth-1].key));
		/* Clean up and exit */
		partial = chain+depth-1; /* the whole chain */
		goto cleanup;
	}

	/* Next simple case - plain lookup or failed read of indirect block */
	if (!create || err == -EIO) {
cleanup:
		while (partial > chain) {
			brelse(partial->bh);
			partial--;
		}
out:
		return err;
	}

	/*
	 * Indirect block might be removed by truncate while we were
	 * reading it. Handling of that case (forget what we've got and
	 * reread) is taken out of the main path.
	 */
	if (err == -EAGAIN)
		goto changed;

	left = (chain + depth) - partial;
	err = alloc_branch(inode, left, offsets+(partial-chain), partial);
	if (err)
		goto cleanup;

	if (splice_branch(inode, chain, partial, left) < 0)
		goto changed;

	set_buffer_new(bh_result);
	goto got_it;

changed:
	while (partial > chain) {
		brelse(partial->bh);
		partial--;
	}
	goto reread;
}

static inline int all_zeroes(sysv_zone_t *p, sysv_zone_t *q)
{
	while (p < q)
		if (*p++)
			return 0;
	return 1;
}

static Indirect *find_shared(struct inode *inode,
				int depth,
				int offsets[],
				Indirect chain[],
				sysv_zone_t *top)
{
	Indirect *partial, *p;
	int k, err;

	*top = 0;
	for (k = depth; k > 1 && !offsets[k-1]; k--)
		;

	write_lock(&pointers_lock);
	partial = get_branch(inode, k, offsets, chain, &err);
	if (!partial)
		partial = chain + k-1;
	/*
	 * If the branch acquired continuation since we've looked at it -
	 * fine, it should all survive and (new) top doesn't belong to us.
	 */
	if (!partial->key && *partial->p) {
		write_unlock(&pointers_lock);
		goto no_top;
	}
	for (p=partial; p>chain && all_zeroes((sysv_zone_t*)p->bh->b_data,p->p); p--)
		;
	/*
	 * OK, we've found the last block that must survive. The rest of our
	 * branch should be detached before unlocking. However, if that rest
	 * of branch is all ours and does not grow immediately from the inode
	 * it's easier to cheat and just decrement partial->p.
	 */
	if (p == chain + k - 1 && p > chain) {
		p->p--;
	} else {
		*top = *p->p;
		*p->p = 0;
	}
	write_unlock(&pointers_lock);

	while (partial > p) {
		brelse(partial->bh);
		partial--;
	}
no_top:
	return partial;
}

static inline void free_data(struct inode *inode, sysv_zone_t *p, sysv_zone_t *q)
{
	for ( ; p < q ; p++) {
		sysv_zone_t nr = *p;
		if (nr) {
			*p = 0;
			sysv_free_block(inode->i_sb, nr);
			mark_inode_dirty(inode);
		}
	}
}

static void free_branches(struct inode *inode, sysv_zone_t *p, sysv_zone_t *q, int depth)
{
	struct buffer_head * bh;
	struct super_block *sb = inode->i_sb;

	if (depth--) {
		for ( ; p < q ; p++) {
			int block;
			sysv_zone_t nr = *p;
			if (!nr)
				continue;
			*p = 0;
			block = block_to_cpu(SYSV_SB(sb), nr);
			bh = sb_bread(sb, block);
			if (!bh)
				continue;
			free_branches(inode, (sysv_zone_t*)bh->b_data,
					block_end(bh), depth);
			bforget(bh);
			sysv_free_block(sb, nr);
			mark_inode_dirty(inode);
		}
	} else
		free_data(inode, p, q);
}

void sysv_truncate (struct inode * inode)
{
	sysv_zone_t *i_data = SYSV_I(inode)->i_data;
	int offsets[DEPTH];
	Indirect chain[DEPTH];
	Indirect *partial;
	sysv_zone_t nr = 0;
	int n;
	long iblock;
	unsigned blocksize;

	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
	    S_ISLNK(inode->i_mode)))
		return;

	blocksize = inode->i_sb->s_blocksize;
	iblock = (inode->i_size + blocksize-1)
					>> inode->i_sb->s_blocksize_bits;

	block_truncate_page(inode->i_mapping, inode->i_size, get_block);

	n = block_to_path(inode, iblock, offsets);
	if (n == 0)
		return;

	if (n == 1) {
		free_data(inode, i_data+offsets[0], i_data + DIRECT);
		goto do_indirects;
	}

	partial = find_shared(inode, n, offsets, chain, &nr);
	/* Kill the top of shared branch (already detached) */
	if (nr) {
		if (partial == chain)
			mark_inode_dirty(inode);
		else
			dirty_indirect(partial->bh, inode);
		free_branches(inode, &nr, &nr+1, (chain+n-1) - partial);
	}
	/* Clear the ends of indirect blocks on the shared branch */
	while (partial > chain) {
		free_branches(inode, partial->p + 1, block_end(partial->bh),
				(chain+n-1) - partial);
		dirty_indirect(partial->bh, inode);
		brelse (partial->bh);
		partial--;
	}
do_indirects:
	/* Kill the remaining (whole) subtrees (== subtrees deeper than...) */
	while (n < DEPTH) {
		nr = i_data[DIRECT + n - 1];
		if (nr) {
			i_data[DIRECT + n - 1] = 0;
			mark_inode_dirty(inode);
			free_branches(inode, &nr, &nr+1, n);
		}
		n++;
	}
	inode->i_mtime = inode->i_ctime = current_time(inode);
	if (IS_SYNC(inode))
		sysv_sync_inode (inode);
	else
		mark_inode_dirty(inode);
}

static unsigned sysv_nblocks(struct super_block *s, loff_t size)
{
	struct sysv_sb_info *sbi = SYSV_SB(s);
	int ptrs_bits = sbi->s_ind_per_block_bits;
	unsigned blocks, res, direct = DIRECT, i = DEPTH;
	blocks = (size + s->s_blocksize - 1) >> s->s_blocksize_bits;
	res = blocks;
	while (--i && blocks > direct) {
		blocks = ((blocks - direct - 1) >> ptrs_bits) + 1;
		res += blocks;
		direct = 1;
	}
	return blocks;
}

int sysv_getattr(const struct path *path, struct kstat *stat,
		 u32 request_mask, unsigned int flags)
{
	struct super_block *s = path->dentry->d_sb;
	generic_fillattr(d_inode(path->dentry), stat);
	stat->blocks = (s->s_blocksize / 512) * sysv_nblocks(s, stat->size);
	stat->blksize = s->s_blocksize;
	return 0;
}

static int sysv_writepage(struct page *page, struct writeback_control *wbc)
{
	return block_write_full_page(page,get_block,wbc);
}

static int sysv_readpage(struct file *file, struct page *page)
{
	return block_read_full_page(page,get_block);
}

int sysv_prepare_chunk(struct page *page, loff_t pos, unsigned len)
{
	return __block_write_begin(page, pos, len, get_block);
}

static void sysv_write_failed(struct address_space *mapping, loff_t to)
{
	struct inode *inode = mapping->host;

	if (to > inode->i_size) {
		truncate_pagecache(inode, inode->i_size);
		sysv_truncate(inode);
	}
}

static int sysv_write_begin(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned flags,
			struct page **pagep, void **fsdata)
{
	int ret;

	ret = block_write_begin(mapping, pos, len, flags, pagep, get_block);
	if (unlikely(ret))
		sysv_write_failed(mapping, pos + len);

	return ret;
}

static sector_t sysv_bmap(struct address_space *mapping, sector_t block)
{
	return generic_block_bmap(mapping,block,get_block);
}

const struct address_space_operations sysv_aops = {
	.readpage = sysv_readpage,
	.writepage = sysv_writepage,
	.write_begin = sysv_write_begin,
	.write_end = generic_write_end,
	.bmap = sysv_bmap
};