summaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_attr_inactive.c
blob: 83af4c14963579b3a8377e43c54e4cd0825ca236 (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
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * Copyright (c) 2013 Red Hat, Inc.
 * 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.
 *
 * This program is distributed in the hope that it would 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 the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_mount.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_inode.h"
#include "xfs_alloc.h"
#include "xfs_attr_remote.h"
#include "xfs_trans.h"
#include "xfs_inode_item.h"
#include "xfs_bmap.h"
#include "xfs_attr.h"
#include "xfs_attr_leaf.h"
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_trace.h"
#include "xfs_dir2.h"

/*
 * Look at all the extents for this logical region,
 * invalidate any buffers that are incore/in transactions.
 */
STATIC int
xfs_attr3_leaf_freextent(
	struct xfs_trans	**trans,
	struct xfs_inode	*dp,
	xfs_dablk_t		blkno,
	int			blkcnt)
{
	struct xfs_bmbt_irec	map;
	struct xfs_buf		*bp;
	xfs_dablk_t		tblkno;
	xfs_daddr_t		dblkno;
	int			tblkcnt;
	int			dblkcnt;
	int			nmap;
	int			error;

	/*
	 * Roll through the "value", invalidating the attribute value's
	 * blocks.
	 */
	tblkno = blkno;
	tblkcnt = blkcnt;
	while (tblkcnt > 0) {
		/*
		 * Try to remember where we decided to put the value.
		 */
		nmap = 1;
		error = xfs_bmapi_read(dp, (xfs_fileoff_t)tblkno, tblkcnt,
				       &map, &nmap, XFS_BMAPI_ATTRFORK);
		if (error) {
			return error;
		}
		ASSERT(nmap == 1);
		ASSERT(map.br_startblock != DELAYSTARTBLOCK);

		/*
		 * If it's a hole, these are already unmapped
		 * so there's nothing to invalidate.
		 */
		if (map.br_startblock != HOLESTARTBLOCK) {

			dblkno = XFS_FSB_TO_DADDR(dp->i_mount,
						  map.br_startblock);
			dblkcnt = XFS_FSB_TO_BB(dp->i_mount,
						map.br_blockcount);
			bp = xfs_trans_get_buf(*trans,
					dp->i_mount->m_ddev_targp,
					dblkno, dblkcnt, 0);
			if (!bp)
				return -ENOMEM;
			xfs_trans_binval(*trans, bp);
			/*
			 * Roll to next transaction.
			 */
			error = xfs_trans_roll(trans, dp);
			if (error)
				return error;
		}

		tblkno += map.br_blockcount;
		tblkcnt -= map.br_blockcount;
	}

	return 0;
}

/*
 * Invalidate all of the "remote" value regions pointed to by a particular
 * leaf block.
 * Note that we must release the lock on the buffer so that we are not
 * caught holding something that the logging code wants to flush to disk.
 */
STATIC int
xfs_attr3_leaf_inactive(
	struct xfs_trans	**trans,
	struct xfs_inode	*dp,
	struct xfs_buf		*bp)
{
	struct xfs_attr_leafblock *leaf;
	struct xfs_attr3_icleaf_hdr ichdr;
	struct xfs_attr_leaf_entry *entry;
	struct xfs_attr_leaf_name_remote *name_rmt;
	struct xfs_attr_inactive_list *list;
	struct xfs_attr_inactive_list *lp;
	int			error;
	int			count;
	int			size;
	int			tmp;
	int			i;

	leaf = bp->b_addr;
	xfs_attr3_leaf_hdr_from_disk(&ichdr, leaf);

	/*
	 * Count the number of "remote" value extents.
	 */
	count = 0;
	entry = xfs_attr3_leaf_entryp(leaf);
	for (i = 0; i < ichdr.count; entry++, i++) {
		if (be16_to_cpu(entry->nameidx) &&
		    ((entry->flags & XFS_ATTR_LOCAL) == 0)) {
			name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
			if (name_rmt->valueblk)
				count++;
		}
	}

	/*
	 * If there are no "remote" values, we're done.
	 */
	if (count == 0) {
		xfs_trans_brelse(*trans, bp);
		return 0;
	}

	/*
	 * Allocate storage for a list of all the "remote" value extents.
	 */
	size = count * sizeof(xfs_attr_inactive_list_t);
	list = kmem_alloc(size, KM_SLEEP);

	/*
	 * Identify each of the "remote" value extents.
	 */
	lp = list;
	entry = xfs_attr3_leaf_entryp(leaf);
	for (i = 0; i < ichdr.count; entry++, i++) {
		if (be16_to_cpu(entry->nameidx) &&
		    ((entry->flags & XFS_ATTR_LOCAL) == 0)) {
			name_rmt = xfs_attr3_leaf_name_remote(leaf, i);
			if (name_rmt->valueblk) {
				lp->valueblk = be32_to_cpu(name_rmt->valueblk);
				lp->valuelen = xfs_attr3_rmt_blocks(dp->i_mount,
						    be32_to_cpu(name_rmt->valuelen));
				lp++;
			}
		}
	}
	xfs_trans_brelse(*trans, bp);	/* unlock for trans. in freextent() */

	/*
	 * Invalidate each of the "remote" value extents.
	 */
	error = 0;
	for (lp = list, i = 0; i < count; i++, lp++) {
		tmp = xfs_attr3_leaf_freextent(trans, dp,
				lp->valueblk, lp->valuelen);

		if (error == 0)
			error = tmp;	/* save only the 1st errno */
	}

	kmem_free(list);
	return error;
}

/*
 * Recurse (gasp!) through the attribute nodes until we find leaves.
 * We're doing a depth-first traversal in order to invalidate everything.
 */
STATIC int
xfs_attr3_node_inactive(
	struct xfs_trans **trans,
	struct xfs_inode *dp,
	struct xfs_buf	*bp,
	int		level)
{
	xfs_da_blkinfo_t *info;
	xfs_da_intnode_t *node;
	xfs_dablk_t child_fsb;
	xfs_daddr_t parent_blkno, child_blkno;
	int error, i;
	struct xfs_buf *child_bp;
	struct xfs_da_node_entry *btree;
	struct xfs_da3_icnode_hdr ichdr;

	/*
	 * Since this code is recursive (gasp!) we must protect ourselves.
	 */
	if (level > XFS_DA_NODE_MAXDEPTH) {
		xfs_trans_brelse(*trans, bp);	/* no locks for later trans */
		return -EIO;
	}

	node = bp->b_addr;
	dp->d_ops->node_hdr_from_disk(&ichdr, node);
	parent_blkno = bp->b_bn;
	if (!ichdr.count) {
		xfs_trans_brelse(*trans, bp);
		return 0;
	}
	btree = dp->d_ops->node_tree_p(node);
	child_fsb = be32_to_cpu(btree[0].before);
	xfs_trans_brelse(*trans, bp);	/* no locks for later trans */

	/*
	 * If this is the node level just above the leaves, simply loop
	 * over the leaves removing all of them.  If this is higher up
	 * in the tree, recurse downward.
	 */
	for (i = 0; i < ichdr.count; i++) {
		/*
		 * Read the subsidiary block to see what we have to work with.
		 * Don't do this in a transaction.  This is a depth-first
		 * traversal of the tree so we may deal with many blocks
		 * before we come back to this one.
		 */
		error = xfs_da3_node_read(*trans, dp, child_fsb, -2, &child_bp,
						XFS_ATTR_FORK);
		if (error)
			return error;
		if (child_bp) {
						/* save for re-read later */
			child_blkno = XFS_BUF_ADDR(child_bp);

			/*
			 * Invalidate the subtree, however we have to.
			 */
			info = child_bp->b_addr;
			switch (info->magic) {
			case cpu_to_be16(XFS_DA_NODE_MAGIC):
			case cpu_to_be16(XFS_DA3_NODE_MAGIC):
				error = xfs_attr3_node_inactive(trans, dp,
							child_bp, level + 1);
				break;
			case cpu_to_be16(XFS_ATTR_LEAF_MAGIC):
			case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
				error = xfs_attr3_leaf_inactive(trans, dp,
							child_bp);
				break;
			default:
				error = -EIO;
				xfs_trans_brelse(*trans, child_bp);
				break;
			}
			if (error)
				return error;

			/*
			 * Remove the subsidiary block from the cache
			 * and from the log.
			 */
			error = xfs_da_get_buf(*trans, dp, 0, child_blkno,
				&child_bp, XFS_ATTR_FORK);
			if (error)
				return error;
			xfs_trans_binval(*trans, child_bp);
		}

		/*
		 * If we're not done, re-read the parent to get the next
		 * child block number.
		 */
		if (i + 1 < ichdr.count) {
			error = xfs_da3_node_read(*trans, dp, 0, parent_blkno,
						 &bp, XFS_ATTR_FORK);
			if (error)
				return error;
			child_fsb = be32_to_cpu(btree[i + 1].before);
			xfs_trans_brelse(*trans, bp);
		}
		/*
		 * Atomically commit the whole invalidate stuff.
		 */
		error = xfs_trans_roll(trans, dp);
		if (error)
			return  error;
	}

	return 0;
}

/*
 * Indiscriminately delete the entire attribute fork
 *
 * Recurse (gasp!) through the attribute nodes until we find leaves.
 * We're doing a depth-first traversal in order to invalidate everything.
 */
int
xfs_attr3_root_inactive(
	struct xfs_trans	**trans,
	struct xfs_inode	*dp)
{
	struct xfs_da_blkinfo	*info;
	struct xfs_buf		*bp;
	xfs_daddr_t		blkno;
	int			error;

	/*
	 * Read block 0 to see what we have to work with.
	 * We only get here if we have extents, since we remove
	 * the extents in reverse order the extent containing
	 * block 0 must still be there.
	 */
	error = xfs_da3_node_read(*trans, dp, 0, -1, &bp, XFS_ATTR_FORK);
	if (error)
		return error;
	blkno = bp->b_bn;

	/*
	 * Invalidate the tree, even if the "tree" is only a single leaf block.
	 * This is a depth-first traversal!
	 */
	info = bp->b_addr;
	switch (info->magic) {
	case cpu_to_be16(XFS_DA_NODE_MAGIC):
	case cpu_to_be16(XFS_DA3_NODE_MAGIC):
		error = xfs_attr3_node_inactive(trans, dp, bp, 1);
		break;
	case cpu_to_be16(XFS_ATTR_LEAF_MAGIC):
	case cpu_to_be16(XFS_ATTR3_LEAF_MAGIC):
		error = xfs_attr3_leaf_inactive(trans, dp, bp);
		break;
	default:
		error = -EIO;
		xfs_trans_brelse(*trans, bp);
		break;
	}
	if (error)
		return error;

	/*
	 * Invalidate the incore copy of the root block.
	 */
	error = xfs_da_get_buf(*trans, dp, 0, blkno, &bp, XFS_ATTR_FORK);
	if (error)
		return error;
	xfs_trans_binval(*trans, bp);	/* remove from cache */
	/*
	 * Commit the invalidate and start the next transaction.
	 */
	error = xfs_trans_roll(trans, dp);

	return error;
}

int
xfs_attr_inactive(xfs_inode_t *dp)
{
	xfs_trans_t *trans;
	xfs_mount_t *mp;
	int error;

	mp = dp->i_mount;
	ASSERT(! XFS_NOT_DQATTACHED(mp, dp));

	xfs_ilock(dp, XFS_ILOCK_SHARED);
	if (!xfs_inode_hasattr(dp) ||
	    dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
		xfs_iunlock(dp, XFS_ILOCK_SHARED);
		return 0;
	}
	xfs_iunlock(dp, XFS_ILOCK_SHARED);

	/*
	 * Start our first transaction of the day.
	 *
	 * All future transactions during this code must be "chained" off
	 * this one via the trans_dup() call.  All transactions will contain
	 * the inode, and the inode will always be marked with trans_ihold().
	 * Since the inode will be locked in all transactions, we must log
	 * the inode in every transaction to let it float upward through
	 * the log.
	 */
	trans = xfs_trans_alloc(mp, XFS_TRANS_ATTRINVAL);
	error = xfs_trans_reserve(trans, &M_RES(mp)->tr_attrinval, 0, 0);
	if (error) {
		xfs_trans_cancel(trans, 0);
		return error;
	}
	xfs_ilock(dp, XFS_ILOCK_EXCL);

	/*
	 * No need to make quota reservations here. We expect to release some
	 * blocks, not allocate, in the common case.
	 */
	xfs_trans_ijoin(trans, dp, 0);

	/*
	 * Decide on what work routines to call based on the inode size.
	 */
	if (!xfs_inode_hasattr(dp) ||
	    dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
		error = 0;
		goto out;
	}
	error = xfs_attr3_root_inactive(&trans, dp);
	if (error)
		goto out;

	error = xfs_itruncate_extents(&trans, dp, XFS_ATTR_FORK, 0);
	if (error)
		goto out;

	error = xfs_trans_commit(trans, XFS_TRANS_RELEASE_LOG_RES);
	xfs_iunlock(dp, XFS_ILOCK_EXCL);

	return error;

out:
	xfs_trans_cancel(trans, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
	xfs_iunlock(dp, XFS_ILOCK_EXCL);
	return error;
}