summaryrefslogtreecommitdiffstats
path: root/fs/erofs/inode.c
blob: 31ac3a73b390ce9e1072b27a6d1917717a4eec08 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2017-2018 HUAWEI, Inc.
 *             https://www.huawei.com/
 * Copyright (C) 2021, Alibaba Cloud
 */
#include "xattr.h"

#include <trace/events/erofs.h>

/*
 * if inode is successfully read, return its inode page (or sometimes
 * the inode payload page if it's an extended inode) in order to fill
 * inline data if possible.
 */
static struct page *erofs_read_inode(struct inode *inode,
				     unsigned int *ofs)
{
	struct super_block *sb = inode->i_sb;
	struct erofs_sb_info *sbi = EROFS_SB(sb);
	struct erofs_inode *vi = EROFS_I(inode);
	const erofs_off_t inode_loc = iloc(sbi, vi->nid);

	erofs_blk_t blkaddr, nblks = 0;
	struct page *page;
	struct erofs_inode_compact *dic;
	struct erofs_inode_extended *die, *copied = NULL;
	unsigned int ifmt;
	int err;

	blkaddr = erofs_blknr(inode_loc);
	*ofs = erofs_blkoff(inode_loc);

	erofs_dbg("%s, reading inode nid %llu at %u of blkaddr %u",
		  __func__, vi->nid, *ofs, blkaddr);

	page = erofs_get_meta_page(sb, blkaddr);
	if (IS_ERR(page)) {
		erofs_err(sb, "failed to get inode (nid: %llu) page, err %ld",
			  vi->nid, PTR_ERR(page));
		return page;
	}

	dic = page_address(page) + *ofs;
	ifmt = le16_to_cpu(dic->i_format);

	if (ifmt & ~EROFS_I_ALL) {
		erofs_err(inode->i_sb, "unsupported i_format %u of nid %llu",
			  ifmt, vi->nid);
		err = -EOPNOTSUPP;
		goto err_out;
	}

	vi->datalayout = erofs_inode_datalayout(ifmt);
	if (vi->datalayout >= EROFS_INODE_DATALAYOUT_MAX) {
		erofs_err(inode->i_sb, "unsupported datalayout %u of nid %llu",
			  vi->datalayout, vi->nid);
		err = -EOPNOTSUPP;
		goto err_out;
	}

	switch (erofs_inode_version(ifmt)) {
	case EROFS_INODE_LAYOUT_EXTENDED:
		vi->inode_isize = sizeof(struct erofs_inode_extended);
		/* check if the inode acrosses page boundary */
		if (*ofs + vi->inode_isize <= PAGE_SIZE) {
			*ofs += vi->inode_isize;
			die = (struct erofs_inode_extended *)dic;
		} else {
			const unsigned int gotten = PAGE_SIZE - *ofs;

			copied = kmalloc(vi->inode_isize, GFP_NOFS);
			if (!copied) {
				err = -ENOMEM;
				goto err_out;
			}
			memcpy(copied, dic, gotten);
			unlock_page(page);
			put_page(page);

			page = erofs_get_meta_page(sb, blkaddr + 1);
			if (IS_ERR(page)) {
				erofs_err(sb, "failed to get inode payload page (nid: %llu), err %ld",
					  vi->nid, PTR_ERR(page));
				kfree(copied);
				return page;
			}
			*ofs = vi->inode_isize - gotten;
			memcpy((u8 *)copied + gotten, page_address(page), *ofs);
			die = copied;
		}
		vi->xattr_isize = erofs_xattr_ibody_size(die->i_xattr_icount);

		inode->i_mode = le16_to_cpu(die->i_mode);
		switch (inode->i_mode & S_IFMT) {
		case S_IFREG:
		case S_IFDIR:
		case S_IFLNK:
			vi->raw_blkaddr = le32_to_cpu(die->i_u.raw_blkaddr);
			break;
		case S_IFCHR:
		case S_IFBLK:
			inode->i_rdev =
				new_decode_dev(le32_to_cpu(die->i_u.rdev));
			break;
		case S_IFIFO:
		case S_IFSOCK:
			inode->i_rdev = 0;
			break;
		default:
			goto bogusimode;
		}
		i_uid_write(inode, le32_to_cpu(die->i_uid));
		i_gid_write(inode, le32_to_cpu(die->i_gid));
		set_nlink(inode, le32_to_cpu(die->i_nlink));

		/* extended inode has its own timestamp */
		inode->i_ctime.tv_sec = le64_to_cpu(die->i_ctime);
		inode->i_ctime.tv_nsec = le32_to_cpu(die->i_ctime_nsec);

		inode->i_size = le64_to_cpu(die->i_size);

		/* total blocks for compressed files */
		if (erofs_inode_is_data_compressed(vi->datalayout))
			nblks = le32_to_cpu(die->i_u.compressed_blocks);
		else if (vi->datalayout == EROFS_INODE_CHUNK_BASED)
			/* fill chunked inode summary info */
			vi->chunkformat = le16_to_cpu(die->i_u.c.format);
		kfree(copied);
		copied = NULL;
		break;
	case EROFS_INODE_LAYOUT_COMPACT:
		vi->inode_isize = sizeof(struct erofs_inode_compact);
		*ofs += vi->inode_isize;
		vi->xattr_isize = erofs_xattr_ibody_size(dic->i_xattr_icount);

		inode->i_mode = le16_to_cpu(dic->i_mode);
		switch (inode->i_mode & S_IFMT) {
		case S_IFREG:
		case S_IFDIR:
		case S_IFLNK:
			vi->raw_blkaddr = le32_to_cpu(dic->i_u.raw_blkaddr);
			break;
		case S_IFCHR:
		case S_IFBLK:
			inode->i_rdev =
				new_decode_dev(le32_to_cpu(dic->i_u.rdev));
			break;
		case S_IFIFO:
		case S_IFSOCK:
			inode->i_rdev = 0;
			break;
		default:
			goto bogusimode;
		}
		i_uid_write(inode, le16_to_cpu(dic->i_uid));
		i_gid_write(inode, le16_to_cpu(dic->i_gid));
		set_nlink(inode, le16_to_cpu(dic->i_nlink));

		/* use build time for compact inodes */
		inode->i_ctime.tv_sec = sbi->build_time;
		inode->i_ctime.tv_nsec = sbi->build_time_nsec;

		inode->i_size = le32_to_cpu(dic->i_size);
		if (erofs_inode_is_data_compressed(vi->datalayout))
			nblks = le32_to_cpu(dic->i_u.compressed_blocks);
		else if (vi->datalayout == EROFS_INODE_CHUNK_BASED)
			vi->chunkformat = le16_to_cpu(dic->i_u.c.format);
		break;
	default:
		erofs_err(inode->i_sb,
			  "unsupported on-disk inode version %u of nid %llu",
			  erofs_inode_version(ifmt), vi->nid);
		err = -EOPNOTSUPP;
		goto err_out;
	}

	if (vi->datalayout == EROFS_INODE_CHUNK_BASED) {
		if (!(vi->chunkformat & EROFS_CHUNK_FORMAT_ALL)) {
			erofs_err(inode->i_sb,
				  "unsupported chunk format %x of nid %llu",
				  vi->chunkformat, vi->nid);
			err = -EOPNOTSUPP;
			goto err_out;
		}
		vi->chunkbits = LOG_BLOCK_SIZE +
			(vi->chunkformat & EROFS_CHUNK_FORMAT_BLKBITS_MASK);
	}
	inode->i_mtime.tv_sec = inode->i_ctime.tv_sec;
	inode->i_atime.tv_sec = inode->i_ctime.tv_sec;
	inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec;
	inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec;

	inode->i_flags &= ~S_DAX;
	if (test_opt(&sbi->ctx, DAX_ALWAYS) && S_ISREG(inode->i_mode) &&
	    vi->datalayout == EROFS_INODE_FLAT_PLAIN)
		inode->i_flags |= S_DAX;
	if (!nblks)
		/* measure inode.i_blocks as generic filesystems */
		inode->i_blocks = roundup(inode->i_size, EROFS_BLKSIZ) >> 9;
	else
		inode->i_blocks = nblks << LOG_SECTORS_PER_BLOCK;
	return page;

bogusimode:
	erofs_err(inode->i_sb, "bogus i_mode (%o) @ nid %llu",
		  inode->i_mode, vi->nid);
	err = -EFSCORRUPTED;
err_out:
	DBG_BUGON(1);
	kfree(copied);
	unlock_page(page);
	put_page(page);
	return ERR_PTR(err);
}

static int erofs_fill_symlink(struct inode *inode, void *data,
			      unsigned int m_pofs)
{
	struct erofs_inode *vi = EROFS_I(inode);
	char *lnk;

	/* if it cannot be handled with fast symlink scheme */
	if (vi->datalayout != EROFS_INODE_FLAT_INLINE ||
	    inode->i_size >= PAGE_SIZE) {
		inode->i_op = &erofs_symlink_iops;
		return 0;
	}

	lnk = kmalloc(inode->i_size + 1, GFP_KERNEL);
	if (!lnk)
		return -ENOMEM;

	m_pofs += vi->xattr_isize;
	/* inline symlink data shouldn't cross page boundary as well */
	if (m_pofs + inode->i_size > PAGE_SIZE) {
		kfree(lnk);
		erofs_err(inode->i_sb,
			  "inline data cross block boundary @ nid %llu",
			  vi->nid);
		DBG_BUGON(1);
		return -EFSCORRUPTED;
	}

	memcpy(lnk, data + m_pofs, inode->i_size);
	lnk[inode->i_size] = '\0';

	inode->i_link = lnk;
	inode->i_op = &erofs_fast_symlink_iops;
	return 0;
}

static int erofs_fill_inode(struct inode *inode, int isdir)
{
	struct erofs_inode *vi = EROFS_I(inode);
	struct page *page;
	unsigned int ofs;
	int err = 0;

	trace_erofs_fill_inode(inode, isdir);

	/* read inode base data from disk */
	page = erofs_read_inode(inode, &ofs);
	if (IS_ERR(page))
		return PTR_ERR(page);

	/* setup the new inode */
	switch (inode->i_mode & S_IFMT) {
	case S_IFREG:
		inode->i_op = &erofs_generic_iops;
		if (erofs_inode_is_data_compressed(vi->datalayout))
			inode->i_fop = &generic_ro_fops;
		else
			inode->i_fop = &erofs_file_fops;
		break;
	case S_IFDIR:
		inode->i_op = &erofs_dir_iops;
		inode->i_fop = &erofs_dir_fops;
		break;
	case S_IFLNK:
		err = erofs_fill_symlink(inode, page_address(page), ofs);
		if (err)
			goto out_unlock;
		inode_nohighmem(inode);
		break;
	case S_IFCHR:
	case S_IFBLK:
	case S_IFIFO:
	case S_IFSOCK:
		inode->i_op = &erofs_generic_iops;
		init_special_inode(inode, inode->i_mode, inode->i_rdev);
		goto out_unlock;
	default:
		err = -EFSCORRUPTED;
		goto out_unlock;
	}

	if (erofs_inode_is_data_compressed(vi->datalayout)) {
		err = z_erofs_fill_inode(inode);
		goto out_unlock;
	}
	inode->i_mapping->a_ops = &erofs_raw_access_aops;

out_unlock:
	unlock_page(page);
	put_page(page);
	return err;
}

/*
 * erofs nid is 64bits, but i_ino is 'unsigned long', therefore
 * we should do more for 32-bit platform to find the right inode.
 */
static int erofs_ilookup_test_actor(struct inode *inode, void *opaque)
{
	const erofs_nid_t nid = *(erofs_nid_t *)opaque;

	return EROFS_I(inode)->nid == nid;
}

static int erofs_iget_set_actor(struct inode *inode, void *opaque)
{
	const erofs_nid_t nid = *(erofs_nid_t *)opaque;

	inode->i_ino = erofs_inode_hash(nid);
	return 0;
}

static inline struct inode *erofs_iget_locked(struct super_block *sb,
					      erofs_nid_t nid)
{
	const unsigned long hashval = erofs_inode_hash(nid);

	return iget5_locked(sb, hashval, erofs_ilookup_test_actor,
		erofs_iget_set_actor, &nid);
}

struct inode *erofs_iget(struct super_block *sb,
			 erofs_nid_t nid,
			 bool isdir)
{
	struct inode *inode = erofs_iget_locked(sb, nid);

	if (!inode)
		return ERR_PTR(-ENOMEM);

	if (inode->i_state & I_NEW) {
		int err;
		struct erofs_inode *vi = EROFS_I(inode);

		vi->nid = nid;

		err = erofs_fill_inode(inode, isdir);
		if (!err)
			unlock_new_inode(inode);
		else {
			iget_failed(inode);
			inode = ERR_PTR(err);
		}
	}
	return inode;
}

int erofs_getattr(struct user_namespace *mnt_userns, const struct path *path,
		  struct kstat *stat, u32 request_mask,
		  unsigned int query_flags)
{
	struct inode *const inode = d_inode(path->dentry);

	if (erofs_inode_is_data_compressed(EROFS_I(inode)->datalayout))
		stat->attributes |= STATX_ATTR_COMPRESSED;

	stat->attributes |= STATX_ATTR_IMMUTABLE;
	stat->attributes_mask |= (STATX_ATTR_COMPRESSED |
				  STATX_ATTR_IMMUTABLE);

	generic_fillattr(&init_user_ns, inode, stat);
	return 0;
}

const struct inode_operations erofs_generic_iops = {
	.getattr = erofs_getattr,
	.listxattr = erofs_listxattr,
	.get_acl = erofs_get_acl,
	.fiemap = erofs_fiemap,
};

const struct inode_operations erofs_symlink_iops = {
	.get_link = page_get_link,
	.getattr = erofs_getattr,
	.listxattr = erofs_listxattr,
	.get_acl = erofs_get_acl,
};

const struct inode_operations erofs_fast_symlink_iops = {
	.get_link = simple_get_link,
	.getattr = erofs_getattr,
	.listxattr = erofs_listxattr,
	.get_acl = erofs_get_acl,
};