summaryrefslogtreecommitdiffstats
path: root/fs/erofs/inode.c
blob: 80f4fe919ee74d0efb286b54ff4d18a3c48daa9b (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2017-2018 HUAWEI, Inc.
 *             http://www.huawei.com/
 * Created by Gao Xiang <gaoxiang25@huawei.com>
 */
#include "xattr.h"

#include <trace/events/erofs.h>

/* no locking */
static int read_inode(struct inode *inode, void *data)
{
	struct erofs_vnode *vi = EROFS_V(inode);
	struct erofs_inode_v1 *v1 = data;
	const unsigned int advise = le16_to_cpu(v1->i_advise);
	erofs_blk_t nblks = 0;

	vi->datamode = __inode_data_mapping(advise);

	if (unlikely(vi->datamode >= EROFS_INODE_LAYOUT_MAX)) {
		errln("unsupported data mapping %u of nid %llu",
		      vi->datamode, vi->nid);
		DBG_BUGON(1);
		return -EOPNOTSUPP;
	}

	if (__inode_version(advise) == EROFS_INODE_LAYOUT_V2) {
		struct erofs_inode_v2 *v2 = data;

		vi->inode_isize = sizeof(struct erofs_inode_v2);
		vi->xattr_isize = ondisk_xattr_ibody_size(v2->i_xattr_icount);

		inode->i_mode = le16_to_cpu(v2->i_mode);
		if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
		    S_ISLNK(inode->i_mode))
			vi->raw_blkaddr = le32_to_cpu(v2->i_u.raw_blkaddr);
		else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
			inode->i_rdev =
				new_decode_dev(le32_to_cpu(v2->i_u.rdev));
		else if (S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode))
			inode->i_rdev = 0;
		else
			goto bogusimode;

		i_uid_write(inode, le32_to_cpu(v2->i_uid));
		i_gid_write(inode, le32_to_cpu(v2->i_gid));
		set_nlink(inode, le32_to_cpu(v2->i_nlink));

		/* ns timestamp */
		inode->i_mtime.tv_sec = inode->i_ctime.tv_sec =
			le64_to_cpu(v2->i_ctime);
		inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec =
			le32_to_cpu(v2->i_ctime_nsec);

		inode->i_size = le64_to_cpu(v2->i_size);

		/* total blocks for compressed files */
		if (is_inode_layout_compression(inode))
			nblks = le32_to_cpu(v2->i_u.compressed_blocks);
	} else if (__inode_version(advise) == EROFS_INODE_LAYOUT_V1) {
		struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb);

		vi->inode_isize = sizeof(struct erofs_inode_v1);
		vi->xattr_isize = ondisk_xattr_ibody_size(v1->i_xattr_icount);

		inode->i_mode = le16_to_cpu(v1->i_mode);
		if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
		    S_ISLNK(inode->i_mode))
			vi->raw_blkaddr = le32_to_cpu(v1->i_u.raw_blkaddr);
		else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
			inode->i_rdev =
				new_decode_dev(le32_to_cpu(v1->i_u.rdev));
		else if (S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode))
			inode->i_rdev = 0;
		else
			goto bogusimode;

		i_uid_write(inode, le16_to_cpu(v1->i_uid));
		i_gid_write(inode, le16_to_cpu(v1->i_gid));
		set_nlink(inode, le16_to_cpu(v1->i_nlink));

		/* use build time to derive all file time */
		inode->i_mtime.tv_sec = inode->i_ctime.tv_sec =
			sbi->build_time;
		inode->i_mtime.tv_nsec = inode->i_ctime.tv_nsec =
			sbi->build_time_nsec;

		inode->i_size = le32_to_cpu(v1->i_size);
		if (is_inode_layout_compression(inode))
			nblks = le32_to_cpu(v1->i_u.compressed_blocks);
	} else {
		errln("unsupported on-disk inode version %u of nid %llu",
		      __inode_version(advise), vi->nid);
		DBG_BUGON(1);
		return -EOPNOTSUPP;
	}

	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 0;

bogusimode:
	errln("bogus i_mode (%o) @ nid %llu", inode->i_mode, vi->nid);
	DBG_BUGON(1);
	return -EFSCORRUPTED;
}

/*
 * try_lock can be required since locking order is:
 *   file data(fs_inode)
 *        meta(bd_inode)
 * but the majority of the callers is "iget",
 * in that case we are pretty sure no deadlock since
 * no data operations exist. However I tend to
 * try_lock since it takes no much overhead and
 * will success immediately.
 */
static int fill_inline_data(struct inode *inode, void *data,
			    unsigned int m_pofs)
{
	struct erofs_vnode *vi = EROFS_V(inode);
	struct erofs_sb_info *sbi = EROFS_I_SB(inode);

	/* should be inode inline C */
	if (!is_inode_flat_inline(inode))
		return 0;

	/* fast symlink (following ext4) */
	if (S_ISLNK(inode->i_mode) && inode->i_size < PAGE_SIZE) {
		char *lnk = erofs_kmalloc(sbi, inode->i_size + 1, GFP_KERNEL);

		if (unlikely(!lnk))
			return -ENOMEM;

		m_pofs += vi->inode_isize + vi->xattr_isize;

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

		/* get in-page inline data */
		memcpy(lnk, data + m_pofs, inode->i_size);
		lnk[inode->i_size] = '\0';

		inode->i_link = lnk;
		set_inode_fast_symlink(inode);
	}
	return 0;
}

static int fill_inode(struct inode *inode, int isdir)
{
	struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb);
	struct erofs_vnode *vi = EROFS_V(inode);
	struct page *page;
	void *data;
	int err;
	erofs_blk_t blkaddr;
	unsigned int ofs;
	erofs_off_t inode_loc;

	trace_erofs_fill_inode(inode, isdir);
	inode_loc = iloc(sbi, vi->nid);
	blkaddr = erofs_blknr(inode_loc);
	ofs = erofs_blkoff(inode_loc);

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

	page = erofs_get_meta_page(inode->i_sb, blkaddr, isdir);

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

	DBG_BUGON(!PageUptodate(page));
	data = page_address(page);

	err = read_inode(inode, data + ofs);
	if (!err) {
		/* setup the new inode */
		if (S_ISREG(inode->i_mode)) {
			inode->i_op = &erofs_generic_iops;
			inode->i_fop = &generic_ro_fops;
		} else if (S_ISDIR(inode->i_mode)) {
			inode->i_op = &erofs_dir_iops;
			inode->i_fop = &erofs_dir_fops;
		} else if (S_ISLNK(inode->i_mode)) {
			/* by default, page_get_link is used for symlink */
			inode->i_op = &erofs_symlink_iops;
			inode_nohighmem(inode);
		} else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
			S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
			inode->i_op = &erofs_generic_iops;
			init_special_inode(inode, inode->i_mode, inode->i_rdev);
			goto out_unlock;
		} else {
			err = -EFSCORRUPTED;
			goto out_unlock;
		}

		if (is_inode_layout_compression(inode)) {
			err = z_erofs_fill_inode(inode);
			goto out_unlock;
		}

		inode->i_mapping->a_ops = &erofs_raw_access_aops;

		/* fill last page if inline data is available */
		err = fill_inline_data(inode, data, ofs);
	}

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.
 */
#if BITS_PER_LONG == 32
static int erofs_ilookup_test_actor(struct inode *inode, void *opaque)
{
	const erofs_nid_t nid = *(erofs_nid_t *)opaque;

	return EROFS_V(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;
}
#endif

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

#if BITS_PER_LONG >= 64
	/* it is safe to use iget_locked for >= 64-bit platform */
	return iget_locked(sb, hashval);
#else
	return iget5_locked(sb, hashval, erofs_ilookup_test_actor,
		erofs_iget_set_actor, &nid);
#endif
}

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

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

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

		vi->nid = nid;

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

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

	if (is_inode_layout_compression(inode))
		stat->attributes |= STATX_ATTR_COMPRESSED;

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

	generic_fillattr(inode, stat);
	return 0;
}

const struct inode_operations erofs_generic_iops = {
	.getattr = erofs_getattr,
#ifdef CONFIG_EROFS_FS_XATTR
	.listxattr = erofs_listxattr,
#endif
	.get_acl = erofs_get_acl,
};

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

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