summaryrefslogtreecommitdiffstats
path: root/fs/ext4/ext4_jbd2.c
blob: 77f318ec8abb78f712fb95c1b71e6c0e86ef3cbe (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Interface between ext4 and JBD
 */

#include "ext4_jbd2.h"

#include <trace/events/ext4.h>

int ext4_inode_journal_mode(struct inode *inode)
{
	if (EXT4_JOURNAL(inode) == NULL)
		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
	/* We do not support data journalling with delayed allocation */
	if (!S_ISREG(inode->i_mode) ||
	    ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) ||
	    test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
	    (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
	    !test_opt(inode->i_sb, DELALLOC))) {
		/* We do not support data journalling for encrypted data */
		if (S_ISREG(inode->i_mode) && IS_ENCRYPTED(inode))
			return EXT4_INODE_ORDERED_DATA_MODE;  /* ordered */
		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
	}
	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
		return EXT4_INODE_ORDERED_DATA_MODE;	/* ordered */
	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
	BUG();
}

/* Just increment the non-pointer handle value */
static handle_t *ext4_get_nojournal(void)
{
	handle_t *handle = current->journal_info;
	unsigned long ref_cnt = (unsigned long)handle;

	BUG_ON(ref_cnt >= EXT4_NOJOURNAL_MAX_REF_COUNT);

	ref_cnt++;
	handle = (handle_t *)ref_cnt;

	current->journal_info = handle;
	return handle;
}


/* Decrement the non-pointer handle value */
static void ext4_put_nojournal(handle_t *handle)
{
	unsigned long ref_cnt = (unsigned long)handle;

	BUG_ON(ref_cnt == 0);

	ref_cnt--;
	handle = (handle_t *)ref_cnt;

	current->journal_info = handle;
}

/*
 * Wrappers for jbd2_journal_start/end.
 */
static int ext4_journal_check_start(struct super_block *sb)
{
	journal_t *journal;

	might_sleep();

	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
		return -EIO;

	if (sb_rdonly(sb))
		return -EROFS;
	WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE);
	journal = EXT4_SB(sb)->s_journal;
	/*
	 * Special case here: if the journal has aborted behind our
	 * backs (eg. EIO in the commit thread), then we still need to
	 * take the FS itself readonly cleanly.
	 */
	if (journal && is_journal_aborted(journal)) {
		ext4_abort(sb, -journal->j_errno, "Detected aborted journal");
		return -EROFS;
	}
	return 0;
}

handle_t *__ext4_journal_start_sb(struct inode *inode,
				  struct super_block *sb, unsigned int line,
				  int type, int blocks, int rsv_blocks,
				  int revoke_creds)
{
	journal_t *journal;
	int err;
	if (inode)
		trace_ext4_journal_start_inode(inode, blocks, rsv_blocks,
					revoke_creds, type,
					_RET_IP_);
	else
		trace_ext4_journal_start_sb(sb, blocks, rsv_blocks,
					revoke_creds, type,
					_RET_IP_);
	err = ext4_journal_check_start(sb);
	if (err < 0)
		return ERR_PTR(err);

	journal = EXT4_SB(sb)->s_journal;
	if (!journal || (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
		return ext4_get_nojournal();
	return jbd2__journal_start(journal, blocks, rsv_blocks, revoke_creds,
				   GFP_NOFS, type, line);
}

int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)
{
	struct super_block *sb;
	int err;
	int rc;

	if (!ext4_handle_valid(handle)) {
		ext4_put_nojournal(handle);
		return 0;
	}

	err = handle->h_err;
	if (!handle->h_transaction) {
		rc = jbd2_journal_stop(handle);
		return err ? err : rc;
	}

	sb = handle->h_transaction->t_journal->j_private;
	rc = jbd2_journal_stop(handle);

	if (!err)
		err = rc;
	if (err)
		__ext4_std_error(sb, where, line, err);
	return err;
}

handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line,
					int type)
{
	struct super_block *sb;
	int err;

	if (!ext4_handle_valid(handle))
		return ext4_get_nojournal();

	sb = handle->h_journal->j_private;
	trace_ext4_journal_start_reserved(sb,
				jbd2_handle_buffer_credits(handle), _RET_IP_);
	err = ext4_journal_check_start(sb);
	if (err < 0) {
		jbd2_journal_free_reserved(handle);
		return ERR_PTR(err);
	}

	err = jbd2_journal_start_reserved(handle, type, line);
	if (err < 0)
		return ERR_PTR(err);
	return handle;
}

int __ext4_journal_ensure_credits(handle_t *handle, int check_cred,
				  int extend_cred, int revoke_cred)
{
	if (!ext4_handle_valid(handle))
		return 0;
	if (is_handle_aborted(handle))
		return -EROFS;
	if (jbd2_handle_buffer_credits(handle) >= check_cred &&
	    handle->h_revoke_credits >= revoke_cred)
		return 0;
	extend_cred = max(0, extend_cred - jbd2_handle_buffer_credits(handle));
	revoke_cred = max(0, revoke_cred - handle->h_revoke_credits);
	return ext4_journal_extend(handle, extend_cred, revoke_cred);
}

static void ext4_journal_abort_handle(const char *caller, unsigned int line,
				      const char *err_fn,
				      struct buffer_head *bh,
				      handle_t *handle, int err)
{
	char nbuf[16];
	const char *errstr = ext4_decode_error(NULL, err, nbuf);

	BUG_ON(!ext4_handle_valid(handle));

	if (bh)
		BUFFER_TRACE(bh, "abort");

	if (!handle->h_err)
		handle->h_err = err;

	if (is_handle_aborted(handle))
		return;

	printk(KERN_ERR "EXT4-fs: %s:%d: aborting transaction: %s in %s\n",
	       caller, line, errstr, err_fn);

	jbd2_journal_abort_handle(handle);
}

static void ext4_check_bdev_write_error(struct super_block *sb)
{
	struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	int err;

	/*
	 * If the block device has write error flag, it may have failed to
	 * async write out metadata buffers in the background. In this case,
	 * we could read old data from disk and write it out again, which
	 * may lead to on-disk filesystem inconsistency.
	 */
	if (errseq_check(&mapping->wb_err, READ_ONCE(sbi->s_bdev_wb_err))) {
		spin_lock(&sbi->s_bdev_wb_lock);
		err = errseq_check_and_advance(&mapping->wb_err, &sbi->s_bdev_wb_err);
		spin_unlock(&sbi->s_bdev_wb_lock);
		if (err)
			ext4_error_err(sb, -err,
				       "Error while async write back metadata");
	}
}

int __ext4_journal_get_write_access(const char *where, unsigned int line,
				    handle_t *handle, struct super_block *sb,
				    struct buffer_head *bh,
				    enum ext4_journal_trigger_type trigger_type)
{
	int err;

	might_sleep();

	if (bh->b_bdev->bd_super)
		ext4_check_bdev_write_error(bh->b_bdev->bd_super);

	if (ext4_handle_valid(handle)) {
		err = jbd2_journal_get_write_access(handle, bh);
		if (err) {
			ext4_journal_abort_handle(where, line, __func__, bh,
						  handle, err);
			return err;
		}
	}
	if (trigger_type == EXT4_JTR_NONE || !ext4_has_metadata_csum(sb))
		return 0;
	BUG_ON(trigger_type >= EXT4_JOURNAL_TRIGGER_COUNT);
	jbd2_journal_set_triggers(bh,
		&EXT4_SB(sb)->s_journal_triggers[trigger_type].tr_triggers);
	return 0;
}

/*
 * The ext4 forget function must perform a revoke if we are freeing data
 * which has been journaled.  Metadata (eg. indirect blocks) must be
 * revoked in all cases.
 *
 * "bh" may be NULL: a metadata block may have been freed from memory
 * but there may still be a record of it in the journal, and that record
 * still needs to be revoked.
 */
int __ext4_forget(const char *where, unsigned int line, handle_t *handle,
		  int is_metadata, struct inode *inode,
		  struct buffer_head *bh, ext4_fsblk_t blocknr)
{
	int err;

	might_sleep();

	trace_ext4_forget(inode, is_metadata, blocknr);
	BUFFER_TRACE(bh, "enter");

	ext4_debug("forgetting bh %p: is_metadata=%d, mode %o, data mode %x\n",
		  bh, is_metadata, inode->i_mode,
		  test_opt(inode->i_sb, DATA_FLAGS));

	/* In the no journal case, we can just do a bforget and return */
	if (!ext4_handle_valid(handle)) {
		bforget(bh);
		return 0;
	}

	/* Never use the revoke function if we are doing full data
	 * journaling: there is no need to, and a V1 superblock won't
	 * support it.  Otherwise, only skip the revoke on un-journaled
	 * data blocks. */

	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
	    (!is_metadata && !ext4_should_journal_data(inode))) {
		if (bh) {
			BUFFER_TRACE(bh, "call jbd2_journal_forget");
			err = jbd2_journal_forget(handle, bh);
			if (err)
				ext4_journal_abort_handle(where, line, __func__,
							  bh, handle, err);
			return err;
		}
		return 0;
	}

	/*
	 * data!=journal && (is_metadata || should_journal_data(inode))
	 */
	BUFFER_TRACE(bh, "call jbd2_journal_revoke");
	err = jbd2_journal_revoke(handle, blocknr, bh);
	if (err) {
		ext4_journal_abort_handle(where, line, __func__,
					  bh, handle, err);
		__ext4_error(inode->i_sb, where, line, true, -err, 0,
			     "error %d when attempting revoke", err);
	}
	BUFFER_TRACE(bh, "exit");
	return err;
}

int __ext4_journal_get_create_access(const char *where, unsigned int line,
				handle_t *handle, struct super_block *sb,
				struct buffer_head *bh,
				enum ext4_journal_trigger_type trigger_type)
{
	int err;

	if (!ext4_handle_valid(handle))
		return 0;

	err = jbd2_journal_get_create_access(handle, bh);
	if (err) {
		ext4_journal_abort_handle(where, line, __func__, bh, handle,
					  err);
		return err;
	}
	if (trigger_type == EXT4_JTR_NONE || !ext4_has_metadata_csum(sb))
		return 0;
	BUG_ON(trigger_type >= EXT4_JOURNAL_TRIGGER_COUNT);
	jbd2_journal_set_triggers(bh,
		&EXT4_SB(sb)->s_journal_triggers[trigger_type].tr_triggers);
	return 0;
}

int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
				 handle_t *handle, struct inode *inode,
				 struct buffer_head *bh)
{
	int err = 0;

	might_sleep();

	set_buffer_meta(bh);
	set_buffer_prio(bh);
	set_buffer_uptodate(bh);
	if (ext4_handle_valid(handle)) {
		err = jbd2_journal_dirty_metadata(handle, bh);
		/* Errors can only happen due to aborted journal or a nasty bug */
		if (!is_handle_aborted(handle) && WARN_ON_ONCE(err)) {
			ext4_journal_abort_handle(where, line, __func__, bh,
						  handle, err);
			if (inode == NULL) {
				pr_err("EXT4: jbd2_journal_dirty_metadata "
				       "failed: handle type %u started at "
				       "line %u, credits %u/%u, errcode %d",
				       handle->h_type,
				       handle->h_line_no,
				       handle->h_requested_credits,
				       jbd2_handle_buffer_credits(handle), err);
				return err;
			}
			ext4_error_inode(inode, where, line,
					 bh->b_blocknr,
					 "journal_dirty_metadata failed: "
					 "handle type %u started at line %u, "
					 "credits %u/%u, errcode %d",
					 handle->h_type,
					 handle->h_line_no,
					 handle->h_requested_credits,
					 jbd2_handle_buffer_credits(handle),
					 err);
		}
	} else {
		if (inode)
			mark_buffer_dirty_inode(bh, inode);
		else
			mark_buffer_dirty(bh);
		if (inode && inode_needs_sync(inode)) {
			sync_dirty_buffer(bh);
			if (buffer_req(bh) && !buffer_uptodate(bh)) {
				ext4_error_inode_err(inode, where, line,
						     bh->b_blocknr, EIO,
					"IO error syncing itable block");
				err = -EIO;
			}
		}
	}
	return err;
}