summaryrefslogtreecommitdiff
path: root/fs/fuse/readdir.c
blob: e38ac983435a69c91297417f7536dc91ef825674 (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
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
/*
  FUSE: Filesystem in Userspace
  Copyright (C) 2001-2018  Miklos Szeredi <miklos@szeredi.hu>

  This program can be distributed under the terms of the GNU GPL.
  See the file COPYING.
*/


#include "fuse_i.h"
#include <linux/iversion.h>
#include <linux/posix_acl.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>

static bool fuse_use_readdirplus(struct inode *dir, struct dir_context *ctx)
{
	struct fuse_conn *fc = get_fuse_conn(dir);
	struct fuse_inode *fi = get_fuse_inode(dir);

	if (!fc->do_readdirplus)
		return false;
	if (!fc->readdirplus_auto)
		return true;
	if (test_and_clear_bit(FUSE_I_ADVISE_RDPLUS, &fi->state))
		return true;
	if (ctx->pos == 0)
		return true;
	return false;
}

static void fuse_add_dirent_to_cache(struct file *file,
				     struct fuse_dirent *dirent, loff_t pos)
{
	struct fuse_inode *fi = get_fuse_inode(file_inode(file));
	size_t reclen = FUSE_DIRENT_SIZE(dirent);
	pgoff_t index;
	struct page *page;
	loff_t size;
	u64 version;
	unsigned int offset;
	void *addr;

	spin_lock(&fi->rdc.lock);
	/*
	 * Is cache already completed?  Or this entry does not go at the end of
	 * cache?
	 */
	if (fi->rdc.cached || pos != fi->rdc.pos) {
		spin_unlock(&fi->rdc.lock);
		return;
	}
	version = fi->rdc.version;
	size = fi->rdc.size;
	offset = size & ~PAGE_MASK;
	index = size >> PAGE_SHIFT;
	/* Dirent doesn't fit in current page?  Jump to next page. */
	if (offset + reclen > PAGE_SIZE) {
		index++;
		offset = 0;
	}
	spin_unlock(&fi->rdc.lock);

	if (offset) {
		page = find_lock_page(file->f_mapping, index);
	} else {
		page = find_or_create_page(file->f_mapping, index,
					   mapping_gfp_mask(file->f_mapping));
	}
	if (!page)
		return;

	spin_lock(&fi->rdc.lock);
	/* Raced with another readdir */
	if (fi->rdc.version != version || fi->rdc.size != size ||
	    WARN_ON(fi->rdc.pos != pos))
		goto unlock;

	addr = kmap_local_page(page);
	if (!offset)
		clear_page(addr);
	memcpy(addr + offset, dirent, reclen);
	kunmap_local(addr);
	fi->rdc.size = (index << PAGE_SHIFT) + offset + reclen;
	fi->rdc.pos = dirent->off;
unlock:
	spin_unlock(&fi->rdc.lock);
	unlock_page(page);
	put_page(page);
}

static void fuse_readdir_cache_end(struct file *file, loff_t pos)
{
	struct fuse_inode *fi = get_fuse_inode(file_inode(file));
	loff_t end;

	spin_lock(&fi->rdc.lock);
	/* does cache end position match current position? */
	if (fi->rdc.pos != pos) {
		spin_unlock(&fi->rdc.lock);
		return;
	}

	fi->rdc.cached = true;
	end = ALIGN(fi->rdc.size, PAGE_SIZE);
	spin_unlock(&fi->rdc.lock);

	/* truncate unused tail of cache */
	truncate_inode_pages(file->f_mapping, end);
}

static bool fuse_emit(struct file *file, struct dir_context *ctx,
		      struct fuse_dirent *dirent)
{
	struct fuse_file *ff = file->private_data;

	if (ff->open_flags & FOPEN_CACHE_DIR)
		fuse_add_dirent_to_cache(file, dirent, ctx->pos);

	return dir_emit(ctx, dirent->name, dirent->namelen, dirent->ino,
			dirent->type);
}

static int parse_dirfile(char *buf, size_t nbytes, struct file *file,
			 struct dir_context *ctx)
{
	while (nbytes >= FUSE_NAME_OFFSET) {
		struct fuse_dirent *dirent = (struct fuse_dirent *) buf;
		size_t reclen = FUSE_DIRENT_SIZE(dirent);
		if (!dirent->namelen || dirent->namelen > FUSE_NAME_MAX)
			return -EIO;
		if (reclen > nbytes)
			break;
		if (memchr(dirent->name, '/', dirent->namelen) != NULL)
			return -EIO;

		if (!fuse_emit(file, ctx, dirent))
			break;

		buf += reclen;
		nbytes -= reclen;
		ctx->pos = dirent->off;
	}

	return 0;
}

static int fuse_direntplus_link(struct file *file,
				struct fuse_direntplus *direntplus,
				u64 attr_version)
{
	struct fuse_entry_out *o = &direntplus->entry_out;
	struct fuse_dirent *dirent = &direntplus->dirent;
	struct dentry *parent = file->f_path.dentry;
	struct qstr name = QSTR_INIT(dirent->name, dirent->namelen);
	struct dentry *dentry;
	struct dentry *alias;
	struct inode *dir = d_inode(parent);
	struct fuse_conn *fc;
	struct inode *inode;
	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);

	if (!o->nodeid) {
		/*
		 * Unlike in the case of fuse_lookup, zero nodeid does not mean
		 * ENOENT. Instead, it only means the userspace filesystem did
		 * not want to return attributes/handle for this entry.
		 *
		 * So do nothing.
		 */
		return 0;
	}

	if (name.name[0] == '.') {
		/*
		 * We could potentially refresh the attributes of the directory
		 * and its parent?
		 */
		if (name.len == 1)
			return 0;
		if (name.name[1] == '.' && name.len == 2)
			return 0;
	}

	if (invalid_nodeid(o->nodeid))
		return -EIO;
	if (fuse_invalid_attr(&o->attr))
		return -EIO;

	fc = get_fuse_conn(dir);

	name.hash = full_name_hash(parent, name.name, name.len);
	dentry = d_lookup(parent, &name);
	if (!dentry) {
retry:
		dentry = d_alloc_parallel(parent, &name, &wq);
		if (IS_ERR(dentry))
			return PTR_ERR(dentry);
	}
	if (!d_in_lookup(dentry)) {
		struct fuse_inode *fi;
		inode = d_inode(dentry);
		if (inode && get_node_id(inode) != o->nodeid)
			inode = NULL;
		if (!inode ||
		    fuse_stale_inode(inode, o->generation, &o->attr)) {
			if (inode)
				fuse_make_bad(inode);
			d_invalidate(dentry);
			dput(dentry);
			goto retry;
		}
		if (fuse_is_bad(inode)) {
			dput(dentry);
			return -EIO;
		}

		fi = get_fuse_inode(inode);
		spin_lock(&fi->lock);
		fi->nlookup++;
		spin_unlock(&fi->lock);

		forget_all_cached_acls(inode);
		fuse_change_attributes(inode, &o->attr,
				       entry_attr_timeout(o),
				       attr_version);
		/*
		 * The other branch comes via fuse_iget()
		 * which bumps nlookup inside
		 */
	} else {
		inode = fuse_iget(dir->i_sb, o->nodeid, o->generation,
				  &o->attr, entry_attr_timeout(o),
				  attr_version);
		if (!inode)
			inode = ERR_PTR(-ENOMEM);

		alias = d_splice_alias(inode, dentry);
		d_lookup_done(dentry);
		if (alias) {
			dput(dentry);
			dentry = alias;
		}
		if (IS_ERR(dentry))
			return PTR_ERR(dentry);
	}
	if (fc->readdirplus_auto)
		set_bit(FUSE_I_INIT_RDPLUS, &get_fuse_inode(inode)->state);
	fuse_change_entry_timeout(dentry, o);

	dput(dentry);
	return 0;
}

static void fuse_force_forget(struct file *file, u64 nodeid)
{
	struct inode *inode = file_inode(file);
	struct fuse_mount *fm = get_fuse_mount(inode);
	struct fuse_forget_in inarg;
	FUSE_ARGS(args);

	memset(&inarg, 0, sizeof(inarg));
	inarg.nlookup = 1;
	args.opcode = FUSE_FORGET;
	args.nodeid = nodeid;
	args.in_numargs = 1;
	args.in_args[0].size = sizeof(inarg);
	args.in_args[0].value = &inarg;
	args.force = true;
	args.noreply = true;

	fuse_simple_request(fm, &args);
	/* ignore errors */
}

static int parse_dirplusfile(char *buf, size_t nbytes, struct file *file,
			     struct dir_context *ctx, u64 attr_version)
{
	struct fuse_direntplus *direntplus;
	struct fuse_dirent *dirent;
	size_t reclen;
	int over = 0;
	int ret;

	while (nbytes >= FUSE_NAME_OFFSET_DIRENTPLUS) {
		direntplus = (struct fuse_direntplus *) buf;
		dirent = &direntplus->dirent;
		reclen = FUSE_DIRENTPLUS_SIZE(direntplus);

		if (!dirent->namelen || dirent->namelen > FUSE_NAME_MAX)
			return -EIO;
		if (reclen > nbytes)
			break;
		if (memchr(dirent->name, '/', dirent->namelen) != NULL)
			return -EIO;

		if (!over) {
			/* We fill entries into dstbuf only as much as
			   it can hold. But we still continue iterating
			   over remaining entries to link them. If not,
			   we need to send a FORGET for each of those
			   which we did not link.
			*/
			over = !fuse_emit(file, ctx, dirent);
			if (!over)
				ctx->pos = dirent->off;
		}

		buf += reclen;
		nbytes -= reclen;

		ret = fuse_direntplus_link(file, direntplus, attr_version);
		if (ret)
			fuse_force_forget(file, direntplus->entry_out.nodeid);
	}

	return 0;
}

static int fuse_readdir_uncached(struct file *file, struct dir_context *ctx)
{
	int plus;
	ssize_t res;
	struct page *page;
	struct inode *inode = file_inode(file);
	struct fuse_mount *fm = get_fuse_mount(inode);
	struct fuse_io_args ia = {};
	struct fuse_args_pages *ap = &ia.ap;
	struct fuse_page_desc desc = { .length = PAGE_SIZE };
	u64 attr_version = 0;
	bool locked;

	page = alloc_page(GFP_KERNEL);
	if (!page)
		return -ENOMEM;

	plus = fuse_use_readdirplus(inode, ctx);
	ap->args.out_pages = true;
	ap->num_pages = 1;
	ap->pages = &page;
	ap->descs = &desc;
	if (plus) {
		attr_version = fuse_get_attr_version(fm->fc);
		fuse_read_args_fill(&ia, file, ctx->pos, PAGE_SIZE,
				    FUSE_READDIRPLUS);
	} else {
		fuse_read_args_fill(&ia, file, ctx->pos, PAGE_SIZE,
				    FUSE_READDIR);
	}
	locked = fuse_lock_inode(inode);
	res = fuse_simple_request(fm, &ap->args);
	fuse_unlock_inode(inode, locked);
	if (res >= 0) {
		if (!res) {
			struct fuse_file *ff = file->private_data;

			if (ff->open_flags & FOPEN_CACHE_DIR)
				fuse_readdir_cache_end(file, ctx->pos);
		} else if (plus) {
			res = parse_dirplusfile(page_address(page), res,
						file, ctx, attr_version);
		} else {
			res = parse_dirfile(page_address(page), res, file,
					    ctx);
		}
	}

	__free_page(page);
	fuse_invalidate_atime(inode);
	return res;
}

enum fuse_parse_result {
	FOUND_ERR = -1,
	FOUND_NONE = 0,
	FOUND_SOME,
	FOUND_ALL,
};

static enum fuse_parse_result fuse_parse_cache(struct fuse_file *ff,
					       void *addr, unsigned int size,
					       struct dir_context *ctx)
{
	unsigned int offset = ff->readdir.cache_off & ~PAGE_MASK;
	enum fuse_parse_result res = FOUND_NONE;

	WARN_ON(offset >= size);

	for (;;) {
		struct fuse_dirent *dirent = addr + offset;
		unsigned int nbytes = size - offset;
		size_t reclen;

		if (nbytes < FUSE_NAME_OFFSET || !dirent->namelen)
			break;

		reclen = FUSE_DIRENT_SIZE(dirent); /* derefs ->namelen */

		if (WARN_ON(dirent->namelen > FUSE_NAME_MAX))
			return FOUND_ERR;
		if (WARN_ON(reclen > nbytes))
			return FOUND_ERR;
		if (WARN_ON(memchr(dirent->name, '/', dirent->namelen) != NULL))
			return FOUND_ERR;

		if (ff->readdir.pos == ctx->pos) {
			res = FOUND_SOME;
			if (!dir_emit(ctx, dirent->name, dirent->namelen,
				      dirent->ino, dirent->type))
				return FOUND_ALL;
			ctx->pos = dirent->off;
		}
		ff->readdir.pos = dirent->off;
		ff->readdir.cache_off += reclen;

		offset += reclen;
	}

	return res;
}

static void fuse_rdc_reset(struct inode *inode)
{
	struct fuse_inode *fi = get_fuse_inode(inode);

	fi->rdc.cached = false;
	fi->rdc.version++;
	fi->rdc.size = 0;
	fi->rdc.pos = 0;
}

#define UNCACHED 1

static int fuse_readdir_cached(struct file *file, struct dir_context *ctx)
{
	struct fuse_file *ff = file->private_data;
	struct inode *inode = file_inode(file);
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct fuse_inode *fi = get_fuse_inode(inode);
	enum fuse_parse_result res;
	pgoff_t index;
	unsigned int size;
	struct page *page;
	void *addr;

	/* Seeked?  If so, reset the cache stream */
	if (ff->readdir.pos != ctx->pos) {
		ff->readdir.pos = 0;
		ff->readdir.cache_off = 0;
	}

	/*
	 * We're just about to start reading into the cache or reading the
	 * cache; both cases require an up-to-date mtime value.
	 */
	if (!ctx->pos && fc->auto_inval_data) {
		int err = fuse_update_attributes(inode, file);

		if (err)
			return err;
	}

retry:
	spin_lock(&fi->rdc.lock);
retry_locked:
	if (!fi->rdc.cached) {
		/* Starting cache? Set cache mtime. */
		if (!ctx->pos && !fi->rdc.size) {
			fi->rdc.mtime = inode->i_mtime;
			fi->rdc.iversion = inode_query_iversion(inode);
		}
		spin_unlock(&fi->rdc.lock);
		return UNCACHED;
	}
	/*
	 * When at the beginning of the directory (i.e. just after opendir(3) or
	 * rewinddir(3)), then need to check whether directory contents have
	 * changed, and reset the cache if so.
	 */
	if (!ctx->pos) {
		if (inode_peek_iversion(inode) != fi->rdc.iversion ||
		    !timespec64_equal(&fi->rdc.mtime, &inode->i_mtime)) {
			fuse_rdc_reset(inode);
			goto retry_locked;
		}
	}

	/*
	 * If cache version changed since the last getdents() call, then reset
	 * the cache stream.
	 */
	if (ff->readdir.version != fi->rdc.version) {
		ff->readdir.pos = 0;
		ff->readdir.cache_off = 0;
	}
	/*
	 * If at the beginning of the cache, than reset version to
	 * current.
	 */
	if (ff->readdir.pos == 0)
		ff->readdir.version = fi->rdc.version;

	WARN_ON(fi->rdc.size < ff->readdir.cache_off);

	index = ff->readdir.cache_off >> PAGE_SHIFT;

	if (index == (fi->rdc.size >> PAGE_SHIFT))
		size = fi->rdc.size & ~PAGE_MASK;
	else
		size = PAGE_SIZE;
	spin_unlock(&fi->rdc.lock);

	/* EOF? */
	if ((ff->readdir.cache_off & ~PAGE_MASK) == size)
		return 0;

	page = find_get_page_flags(file->f_mapping, index,
				   FGP_ACCESSED | FGP_LOCK);
	spin_lock(&fi->rdc.lock);
	if (!page) {
		/*
		 * Uh-oh: page gone missing, cache is useless
		 */
		if (fi->rdc.version == ff->readdir.version)
			fuse_rdc_reset(inode);
		goto retry_locked;
	}

	/* Make sure it's still the same version after getting the page. */
	if (ff->readdir.version != fi->rdc.version) {
		spin_unlock(&fi->rdc.lock);
		unlock_page(page);
		put_page(page);
		goto retry;
	}
	spin_unlock(&fi->rdc.lock);

	/*
	 * Contents of the page are now protected against changing by holding
	 * the page lock.
	 */
	addr = kmap(page);
	res = fuse_parse_cache(ff, addr, size, ctx);
	kunmap(page);
	unlock_page(page);
	put_page(page);

	if (res == FOUND_ERR)
		return -EIO;

	if (res == FOUND_ALL)
		return 0;

	if (size == PAGE_SIZE) {
		/* We hit end of page: skip to next page. */
		ff->readdir.cache_off = ALIGN(ff->readdir.cache_off, PAGE_SIZE);
		goto retry;
	}

	/*
	 * End of cache reached.  If found position, then we are done, otherwise
	 * need to fall back to uncached, since the position we were looking for
	 * wasn't in the cache.
	 */
	return res == FOUND_SOME ? 0 : UNCACHED;
}

int fuse_readdir(struct file *file, struct dir_context *ctx)
{
	struct fuse_file *ff = file->private_data;
	struct inode *inode = file_inode(file);
	int err;

	if (fuse_is_bad(inode))
		return -EIO;

	mutex_lock(&ff->readdir.lock);

	err = UNCACHED;
	if (ff->open_flags & FOPEN_CACHE_DIR)
		err = fuse_readdir_cached(file, ctx);
	if (err == UNCACHED)
		err = fuse_readdir_uncached(file, ctx);

	mutex_unlock(&ff->readdir.lock);

	return err;
}