summaryrefslogtreecommitdiff
path: root/fs/jfs/inode.c
blob: 41aa3ca6a6a4995104d12f38cc5945ebb63a0f7d (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
/*
 *   Copyright (C) International Business Machines Corp., 2000-2004
 *   Portions Copyright (C) Christoph Hellwig, 2001-2002
 *
 *   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 02111-1307 USA
 */

#include <linux/fs.h>
#include <linux/mpage.h>
#include <linux/buffer_head.h>
#include <linux/pagemap.h>
#include <linux/quotaops.h>
#include <linux/uio.h>
#include <linux/writeback.h>
#include "jfs_incore.h"
#include "jfs_inode.h"
#include "jfs_filsys.h"
#include "jfs_imap.h"
#include "jfs_extent.h"
#include "jfs_unicode.h"
#include "jfs_debug.h"


struct inode *jfs_iget(struct super_block *sb, unsigned long ino)
{
	struct inode *inode;
	int ret;

	inode = iget_locked(sb, ino);
	if (!inode)
		return ERR_PTR(-ENOMEM);
	if (!(inode->i_state & I_NEW))
		return inode;

	ret = diRead(inode);
	if (ret < 0) {
		iget_failed(inode);
		return ERR_PTR(ret);
	}

	if (S_ISREG(inode->i_mode)) {
		inode->i_op = &jfs_file_inode_operations;
		inode->i_fop = &jfs_file_operations;
		inode->i_mapping->a_ops = &jfs_aops;
	} else if (S_ISDIR(inode->i_mode)) {
		inode->i_op = &jfs_dir_inode_operations;
		inode->i_fop = &jfs_dir_operations;
	} else if (S_ISLNK(inode->i_mode)) {
		if (inode->i_size >= IDATASIZE) {
			inode->i_op = &page_symlink_inode_operations;
			inode->i_mapping->a_ops = &jfs_aops;
		} else {
			inode->i_op = &jfs_fast_symlink_inode_operations;
			inode->i_link = JFS_IP(inode)->i_inline;
			/*
			 * The inline data should be null-terminated, but
			 * don't let on-disk corruption crash the kernel
			 */
			inode->i_link[inode->i_size] = '\0';
		}
	} else {
		inode->i_op = &jfs_file_inode_operations;
		init_special_inode(inode, inode->i_mode, inode->i_rdev);
	}
	unlock_new_inode(inode);
	return inode;
}

/*
 * Workhorse of both fsync & write_inode
 */
int jfs_commit_inode(struct inode *inode, int wait)
{
	int rc = 0;
	tid_t tid;
	static int noisy = 5;

	jfs_info("In jfs_commit_inode, inode = 0x%p", inode);

	/*
	 * Don't commit if inode has been committed since last being
	 * marked dirty, or if it has been deleted.
	 */
	if (inode->i_nlink == 0 || !test_cflag(COMMIT_Dirty, inode))
		return 0;

	if (isReadOnly(inode)) {
		/* kernel allows writes to devices on read-only
		 * partitions and may think inode is dirty
		 */
		if (!special_file(inode->i_mode) && noisy) {
			jfs_err("jfs_commit_inode(0x%p) called on "
				   "read-only volume", inode);
			jfs_err("Is remount racy?");
			noisy--;
		}
		return 0;
	}

	tid = txBegin(inode->i_sb, COMMIT_INODE);
	mutex_lock(&JFS_IP(inode)->commit_mutex);

	/*
	 * Retest inode state after taking commit_mutex
	 */
	if (inode->i_nlink && test_cflag(COMMIT_Dirty, inode))
		rc = txCommit(tid, 1, &inode, wait ? COMMIT_SYNC : 0);

	txEnd(tid);
	mutex_unlock(&JFS_IP(inode)->commit_mutex);
	return rc;
}

int jfs_write_inode(struct inode *inode, struct writeback_control *wbc)
{
	int wait = wbc->sync_mode == WB_SYNC_ALL;

	if (inode->i_nlink == 0)
		return 0;
	/*
	 * If COMMIT_DIRTY is not set, the inode isn't really dirty.
	 * It has been committed since the last change, but was still
	 * on the dirty inode list.
	 */
	if (!test_cflag(COMMIT_Dirty, inode)) {
		/* Make sure committed changes hit the disk */
		jfs_flush_journal(JFS_SBI(inode->i_sb)->log, wait);
		return 0;
	}

	if (jfs_commit_inode(inode, wait)) {
		jfs_err("jfs_write_inode: jfs_commit_inode failed!");
		return -EIO;
	} else
		return 0;
}

void jfs_evict_inode(struct inode *inode)
{
	jfs_info("In jfs_evict_inode, inode = 0x%p", inode);

	if (!inode->i_nlink && !is_bad_inode(inode)) {
		dquot_initialize(inode);

		if (JFS_IP(inode)->fileset == FILESYSTEM_I) {
			truncate_inode_pages_final(&inode->i_data);

			if (test_cflag(COMMIT_Freewmap, inode))
				jfs_free_zero_link(inode);

			diFree(inode);

			/*
			 * Free the inode from the quota allocation.
			 */
			dquot_initialize(inode);
			dquot_free_inode(inode);
		}
	} else {
		truncate_inode_pages_final(&inode->i_data);
	}
	clear_inode(inode);
	dquot_drop(inode);
}

void jfs_dirty_inode(struct inode *inode, int flags)
{
	static int noisy = 5;

	if (isReadOnly(inode)) {
		if (!special_file(inode->i_mode) && noisy) {
			/* kernel allows writes to devices on read-only
			 * partitions and may try to mark inode dirty
			 */
			jfs_err("jfs_dirty_inode called on read-only volume");
			jfs_err("Is remount racy?");
			noisy--;
		}
		return;
	}

	set_cflag(COMMIT_Dirty, inode);
}

int jfs_get_block(struct inode *ip, sector_t lblock,
		  struct buffer_head *bh_result, int create)
{
	s64 lblock64 = lblock;
	int rc = 0;
	xad_t xad;
	s64 xaddr;
	int xflag;
	s32 xlen = bh_result->b_size >> ip->i_blkbits;

	/*
	 * Take appropriate lock on inode
	 */
	if (create)
		IWRITE_LOCK(ip, RDWRLOCK_NORMAL);
	else
		IREAD_LOCK(ip, RDWRLOCK_NORMAL);

	if (((lblock64 << ip->i_sb->s_blocksize_bits) < ip->i_size) &&
	    (!xtLookup(ip, lblock64, xlen, &xflag, &xaddr, &xlen, 0)) &&
	    xaddr) {
		if (xflag & XAD_NOTRECORDED) {
			if (!create)
				/*
				 * Allocated but not recorded, read treats
				 * this as a hole
				 */
				goto unlock;
#ifdef _JFS_4K
			XADoffset(&xad, lblock64);
			XADlength(&xad, xlen);
			XADaddress(&xad, xaddr);
#else				/* _JFS_4K */
			/*
			 * As long as block size = 4K, this isn't a problem.
			 * We should mark the whole page not ABNR, but how
			 * will we know to mark the other blocks BH_New?
			 */
			BUG();
#endif				/* _JFS_4K */
			rc = extRecord(ip, &xad);
			if (rc)
				goto unlock;
			set_buffer_new(bh_result);
		}

		map_bh(bh_result, ip->i_sb, xaddr);
		bh_result->b_size = xlen << ip->i_blkbits;
		goto unlock;
	}
	if (!create)
		goto unlock;

	/*
	 * Allocate a new block
	 */
#ifdef _JFS_4K
	if ((rc = extHint(ip, lblock64 << ip->i_sb->s_blocksize_bits, &xad)))
		goto unlock;
	rc = extAlloc(ip, xlen, lblock64, &xad, false);
	if (rc)
		goto unlock;

	set_buffer_new(bh_result);
	map_bh(bh_result, ip->i_sb, addressXAD(&xad));
	bh_result->b_size = lengthXAD(&xad) << ip->i_blkbits;

#else				/* _JFS_4K */
	/*
	 * We need to do whatever it takes to keep all but the last buffers
	 * in 4K pages - see jfs_write.c
	 */
	BUG();
#endif				/* _JFS_4K */

      unlock:
	/*
	 * Release lock on inode
	 */
	if (create)
		IWRITE_UNLOCK(ip);
	else
		IREAD_UNLOCK(ip);
	return rc;
}

static int jfs_writepage(struct page *page, struct writeback_control *wbc)
{
	return block_write_full_page(page, jfs_get_block, wbc);
}

static int jfs_writepages(struct address_space *mapping,
			struct writeback_control *wbc)
{
	return mpage_writepages(mapping, wbc, jfs_get_block);
}

static int jfs_readpage(struct file *file, struct page *page)
{
	return mpage_readpage(page, jfs_get_block);
}

static int jfs_readpages(struct file *file, struct address_space *mapping,
		struct list_head *pages, unsigned nr_pages)
{
	return mpage_readpages(mapping, pages, nr_pages, jfs_get_block);
}

static void jfs_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);
		jfs_truncate(inode);
	}
}

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

	ret = nobh_write_begin(mapping, pos, len, flags, pagep, fsdata,
				jfs_get_block);
	if (unlikely(ret))
		jfs_write_failed(mapping, pos + len);

	return ret;
}

static sector_t jfs_bmap(struct address_space *mapping, sector_t block)
{
	return generic_block_bmap(mapping, block, jfs_get_block);
}

static ssize_t jfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
			     loff_t offset)
{
	struct file *file = iocb->ki_filp;
	struct address_space *mapping = file->f_mapping;
	struct inode *inode = file->f_mapping->host;
	size_t count = iov_iter_count(iter);
	ssize_t ret;

	ret = blockdev_direct_IO(iocb, inode, iter, offset, jfs_get_block);

	/*
	 * In case of error extending write may have instantiated a few
	 * blocks outside i_size. Trim these off again.
	 */
	if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
		loff_t isize = i_size_read(inode);
		loff_t end = offset + count;

		if (end > isize)
			jfs_write_failed(mapping, end);
	}

	return ret;
}

const struct address_space_operations jfs_aops = {
	.readpage	= jfs_readpage,
	.readpages	= jfs_readpages,
	.writepage	= jfs_writepage,
	.writepages	= jfs_writepages,
	.write_begin	= jfs_write_begin,
	.write_end	= nobh_write_end,
	.bmap		= jfs_bmap,
	.direct_IO	= jfs_direct_IO,
};

/*
 * Guts of jfs_truncate.  Called with locks already held.  Can be called
 * with directory for truncating directory index table.
 */
void jfs_truncate_nolock(struct inode *ip, loff_t length)
{
	loff_t newsize;
	tid_t tid;

	ASSERT(length >= 0);

	if (test_cflag(COMMIT_Nolink, ip)) {
		xtTruncate(0, ip, length, COMMIT_WMAP);
		return;
	}

	do {
		tid = txBegin(ip->i_sb, 0);

		/*
		 * The commit_mutex cannot be taken before txBegin.
		 * txBegin may block and there is a chance the inode
		 * could be marked dirty and need to be committed
		 * before txBegin unblocks
		 */
		mutex_lock(&JFS_IP(ip)->commit_mutex);

		newsize = xtTruncate(tid, ip, length,
				     COMMIT_TRUNCATE | COMMIT_PWMAP);
		if (newsize < 0) {
			txEnd(tid);
			mutex_unlock(&JFS_IP(ip)->commit_mutex);
			break;
		}

		ip->i_mtime = ip->i_ctime = CURRENT_TIME;
		mark_inode_dirty(ip);

		txCommit(tid, 1, &ip, 0);
		txEnd(tid);
		mutex_unlock(&JFS_IP(ip)->commit_mutex);
	} while (newsize > length);	/* Truncate isn't always atomic */
}

void jfs_truncate(struct inode *ip)
{
	jfs_info("jfs_truncate: size = 0x%lx", (ulong) ip->i_size);

	nobh_truncate_page(ip->i_mapping, ip->i_size, jfs_get_block);

	IWRITE_LOCK(ip, RDWRLOCK_NORMAL);
	jfs_truncate_nolock(ip, ip->i_size);
	IWRITE_UNLOCK(ip);
}