f_op.c 19.2 KB
Newer Older
J. R. Okajima's avatar
J. R. Okajima committed
1
2
3
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2005-2019 Junjiro R. Okajima
4
5
6
7
8
9
10
11
12
13
14
15
16
 *
 * This program, aufs 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; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will 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, see <http://www.gnu.org/licenses/>.
J. R. Okajima's avatar
J. R. Okajima committed
17
18
19
20
21
22
 */

/*
 * file and vm operations
 */

J. R. Okajima's avatar
J. R. Okajima committed
23
#include <linux/aio.h>
J. R. Okajima's avatar
J. R. Okajima committed
24
25
#include <linux/fs_stack.h>
#include <linux/mman.h>
J. R. Okajima's avatar
J. R. Okajima committed
26
#include <linux/security.h>
J. R. Okajima's avatar
J. R. Okajima committed
27
28
#include "aufs.h"

29
int au_do_open_nondir(struct file *file, int flags, struct file *h_file)
J. R. Okajima's avatar
J. R. Okajima committed
30
31
32
{
	int err;
	aufs_bindex_t bindex;
33
	struct dentry *dentry, *h_dentry;
J. R. Okajima's avatar
J. R. Okajima committed
34
35
36
37
38
39
40
	struct au_finfo *finfo;
	struct inode *h_inode;

	FiMustWriteLock(file);

	err = 0;
	dentry = file->f_path.dentry;
41
	AuDebugOn(IS_ERR_OR_NULL(dentry));
J. R. Okajima's avatar
J. R. Okajima committed
42
43
	finfo = au_fi(file);
	memset(&finfo->fi_htop, 0, sizeof(finfo->fi_htop));
J. R. Okajima's avatar
J. R. Okajima committed
44
	atomic_set(&finfo->fi_mmapped, 0);
J. R. Okajima's avatar
J. R. Okajima committed
45
	bindex = au_dbtop(dentry);
46
47
48
49
50
	if (!h_file) {
		h_dentry = au_h_dptr(dentry, bindex);
		err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb);
		if (unlikely(err))
			goto out;
51
		h_file = au_h_open(dentry, bindex, flags, file, /*force_wr*/0);
52
53
54
		if (IS_ERR(h_file)) {
			err = PTR_ERR(h_file);
			goto out;
J. R. Okajima's avatar
J. R. Okajima committed
55
		}
56
57
58
59
60
61
62
63
64
65
66
67
68
69
	} else {
		h_dentry = h_file->f_path.dentry;
		err = vfsub_test_mntns(file->f_path.mnt, h_dentry->d_sb);
		if (unlikely(err))
			goto out;
		/* br ref is already inc-ed */
	}

	if ((flags & __O_TMPFILE)
	    && !(flags & O_EXCL)) {
		h_inode = file_inode(h_file);
		spin_lock(&h_inode->i_lock);
		h_inode->i_state |= I_LINKABLE;
		spin_unlock(&h_inode->i_lock);
J. R. Okajima's avatar
J. R. Okajima committed
70
	}
71
72
73
74
75
	au_set_fbtop(file, bindex);
	au_set_h_fptr(file, bindex, h_file);
	au_update_figen(file);
	/* todo: necessary? */
	/* file->f_ra = h_file->f_ra; */
J. R. Okajima's avatar
J. R. Okajima committed
76

77
out:
J. R. Okajima's avatar
J. R. Okajima committed
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
	return err;
}

static int aufs_open_nondir(struct inode *inode __maybe_unused,
			    struct file *file)
{
	int err;
	struct super_block *sb;
	struct au_do_open_args args = {
		.open	= au_do_open_nondir
	};

	AuDbg("%pD, f_flags 0x%x, f_mode 0x%x\n",
	      file, vfsub_file_flags(file), file->f_mode);

	sb = file->f_path.dentry->d_sb;
	si_read_lock(sb, AuLock_FLUSH);
	err = au_do_open(file, &args);
	si_read_unlock(sb);
	return err;
}

int aufs_release_nondir(struct inode *inode __maybe_unused, struct file *file)
{
	struct au_finfo *finfo;
	aufs_bindex_t bindex;

	finfo = au_fi(file);
106
107
	au_hbl_del(&finfo->fi_hlist,
		   &au_sbi(file->f_path.dentry->d_sb)->si_files);
J. R. Okajima's avatar
J. R. Okajima committed
108
109
110
111
112
113
114
115
116
117
	bindex = finfo->fi_btop;
	if (bindex >= 0)
		au_set_h_fptr(file, bindex, NULL);

	au_finfo_fin(file);
	return 0;
}

/* ---------------------------------------------------------------------- */

J. R. Okajima's avatar
J. R. Okajima committed
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
static int au_do_flush_nondir(struct file *file, fl_owner_t id)
{
	int err;
	struct file *h_file;

	err = 0;
	h_file = au_hf_top(file);
	if (h_file)
		err = vfsub_flush(h_file, id);
	return err;
}

static int aufs_flush_nondir(struct file *file, fl_owner_t id)
{
	return au_do_flush(file, id, au_do_flush_nondir);
}

/* ---------------------------------------------------------------------- */
/*
 * read and write functions acquire [fdi]_rwsem once, but release before
 * mmap_sem. This is because to stop a race condition between mmap(2).
 * Releasing these aufs-rwsem should be safe, no branch-management (by keeping
 * si_rwsem), no harmful copy-up should happen. Actually copy-up may happen in
 * read functions after [fdi]_rwsem are released, but it should be harmless.
 */

/* Callers should call au_read_post() or fput() in the end */
struct file *au_read_pre(struct file *file, int keep_fi, unsigned int lsc)
{
	struct file *h_file;
	int err;

	err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/0, lsc);
	if (!err) {
		di_read_unlock(file->f_path.dentry, AuLock_IR);
		h_file = au_hf_top(file);
		get_file(h_file);
		if (!keep_fi)
			fi_read_unlock(file);
	} else
		h_file = ERR_PTR(err);

	return h_file;
}

static void au_read_post(struct inode *inode, struct file *h_file)
{
	/* update without lock, I don't think it a problem */
	fsstack_copy_attr_atime(inode, file_inode(h_file));
	fput(h_file);
}

J. R. Okajima's avatar
J. R. Okajima committed
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
struct au_write_pre {
	/* input */
	unsigned int lsc;

	/* output */
	blkcnt_t blks;
	aufs_bindex_t btop;
};

/*
 * return with iinfo is write-locked
 * callers should call au_write_post() or iinfo_write_unlock() + fput() in the
 * end
 */
static struct file *au_write_pre(struct file *file, int do_ready,
				 struct au_write_pre *wpre)
{
	struct file *h_file;
	struct dentry *dentry;
	int err;
	unsigned int lsc;
	struct au_pin pin;

	lsc = 0;
	if (wpre)
		lsc = wpre->lsc;
	err = au_reval_and_lock_fdi(file, au_reopen_nondir, /*wlock*/1, lsc);
	h_file = ERR_PTR(err);
	if (unlikely(err))
		goto out;

	dentry = file->f_path.dentry;
	if (do_ready) {
		err = au_ready_to_write(file, -1, &pin);
		if (unlikely(err)) {
			h_file = ERR_PTR(err);
			di_write_unlock(dentry);
			goto out_fi;
		}
	}

	di_downgrade_lock(dentry, /*flags*/0);
	if (wpre)
		wpre->btop = au_fbtop(file);
	h_file = au_hf_top(file);
	get_file(h_file);
	if (wpre)
		wpre->blks = file_inode(h_file)->i_blocks;
	if (do_ready)
		au_unpin(&pin);
	di_read_unlock(dentry, /*flags*/0);

out_fi:
	fi_write_unlock(file);
out:
	return h_file;
}

J. R. Okajima's avatar
J. R. Okajima committed
228
static void au_write_post(struct inode *inode, struct file *h_file,
229
			  struct au_write_pre *wpre, ssize_t written)
J. R. Okajima's avatar
J. R. Okajima committed
230
231
232
233
234
235
236
237
{
	struct inode *h_inode;

	au_cpup_attr_timesizes(inode);
	AuDebugOn(au_ibtop(inode) != wpre->btop);
	h_inode = file_inode(h_file);
	inode->i_mode = h_inode->i_mode;
	ii_write_unlock(inode);
238
239
240
241
	/* AuDbg("blks %llu, %llu\n", (u64)blks, (u64)h_inode->i_blocks); */
	if (written > 0)
		au_fhsm_wrote(inode->i_sb, wpre->btop,
			      /*force*/h_inode->i_blocks > wpre->blks);
J. R. Okajima's avatar
J. R. Okajima committed
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
	fput(h_file);
}

static ssize_t aufs_read(struct file *file, char __user *buf, size_t count,
			 loff_t *ppos)
{
	ssize_t err;
	struct inode *inode;
	struct file *h_file;
	struct super_block *sb;

	inode = file_inode(file);
	sb = inode->i_sb;
	si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);

	h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
	err = PTR_ERR(h_file);
	if (IS_ERR(h_file))
		goto out;

	/* filedata may be obsoleted by concurrent copyup, but no problem */
	err = vfsub_read_u(h_file, buf, count, ppos);
	/* todo: necessary? */
	/* file->f_ra = h_file->f_ra; */
	au_read_post(inode, h_file);

out:
	si_read_unlock(sb);
	return err;
}

/*
 * todo: very ugly
 * it locks both of i_mutex and si_rwsem for read in safe.
 * if the plink maintenance mode continues forever (that is the problem),
 * may loop forever.
 */
static void au_mtx_and_read_lock(struct inode *inode)
{
	int err;
	struct super_block *sb = inode->i_sb;

	while (1) {
		inode_lock(inode);
		err = si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLM);
		if (!err)
			break;
		inode_unlock(inode);
		si_read_lock(sb, AuLock_NOPLMW);
		si_read_unlock(sb);
	}
}

static ssize_t aufs_write(struct file *file, const char __user *ubuf,
			  size_t count, loff_t *ppos)
{
	ssize_t err;
	struct au_write_pre wpre;
	struct inode *inode;
	struct file *h_file;
	char __user *buf = (char __user *)ubuf;

	inode = file_inode(file);
	au_mtx_and_read_lock(inode);

	wpre.lsc = 0;
	h_file = au_write_pre(file, /*do_ready*/1, &wpre);
	err = PTR_ERR(h_file);
	if (IS_ERR(h_file))
		goto out;

	err = vfsub_write_u(h_file, buf, count, ppos);
314
	au_write_post(inode, h_file, &wpre, err);
J. R. Okajima's avatar
J. R. Okajima committed
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332

out:
	si_read_unlock(inode->i_sb);
	inode_unlock(inode);
	return err;
}

static ssize_t au_do_iter(struct file *h_file, int rw, struct kiocb *kio,
			  struct iov_iter *iov_iter)
{
	ssize_t err;
	struct file *file;
	ssize_t (*iter)(struct kiocb *, struct iov_iter *);

	err = security_file_permission(h_file, rw);
	if (unlikely(err))
		goto out;

333
	err = -ENOSYS;	/* the branch doesn't have its ->(read|write)_iter() */
J. R. Okajima's avatar
J. R. Okajima committed
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
	iter = NULL;
	if (rw == MAY_READ)
		iter = h_file->f_op->read_iter;
	else if (rw == MAY_WRITE)
		iter = h_file->f_op->write_iter;

	file = kio->ki_filp;
	kio->ki_filp = h_file;
	if (iter) {
		lockdep_off();
		err = iter(kio, iov_iter);
		lockdep_on();
	} else
		/* currently there is no such fs */
		WARN_ON_ONCE(1);
	kio->ki_filp = file;

out:
	return err;
}

static ssize_t aufs_read_iter(struct kiocb *kio, struct iov_iter *iov_iter)
{
	ssize_t err;
	struct file *file, *h_file;
	struct inode *inode;
	struct super_block *sb;

	file = kio->ki_filp;
	inode = file_inode(file);
	sb = inode->i_sb;
	si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);

	h_file = au_read_pre(file, /*keep_fi*/1, /*lsc*/0);
	err = PTR_ERR(h_file);
	if (IS_ERR(h_file))
		goto out;

J. R. Okajima's avatar
J. R. Okajima committed
372
373
374
375
376
377
378
	if (au_test_loopback_kthread()) {
		au_warn_loopback(h_file->f_path.dentry->d_sb);
		if (file->f_mapping != h_file->f_mapping) {
			file->f_mapping = h_file->f_mapping;
			smp_mb(); /* unnecessary? */
		}
	}
J. R. Okajima's avatar
J. R. Okajima committed
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
	fi_read_unlock(file);

	err = au_do_iter(h_file, MAY_READ, kio, iov_iter);
	/* todo: necessary? */
	/* file->f_ra = h_file->f_ra; */
	au_read_post(inode, h_file);

out:
	si_read_unlock(sb);
	return err;
}

static ssize_t aufs_write_iter(struct kiocb *kio, struct iov_iter *iov_iter)
{
	ssize_t err;
	struct au_write_pre wpre;
	struct inode *inode;
	struct file *file, *h_file;

	file = kio->ki_filp;
	inode = file_inode(file);
	au_mtx_and_read_lock(inode);

	wpre.lsc = 0;
	h_file = au_write_pre(file, /*do_ready*/1, &wpre);
	err = PTR_ERR(h_file);
	if (IS_ERR(h_file))
		goto out;

	err = au_do_iter(h_file, MAY_WRITE, kio, iov_iter);
409
	au_write_post(inode, h_file, &wpre, err);
J. R. Okajima's avatar
J. R. Okajima committed
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

out:
	si_read_unlock(inode->i_sb);
	inode_unlock(inode);
	return err;
}

static ssize_t aufs_splice_read(struct file *file, loff_t *ppos,
				struct pipe_inode_info *pipe, size_t len,
				unsigned int flags)
{
	ssize_t err;
	struct file *h_file;
	struct inode *inode;
	struct super_block *sb;

	inode = file_inode(file);
	sb = inode->i_sb;
	si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);

	h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
	err = PTR_ERR(h_file);
	if (IS_ERR(h_file))
		goto out;

	err = vfsub_splice_to(h_file, ppos, pipe, len, flags);
	/* todo: necessary? */
	/* file->f_ra = h_file->f_ra; */
	au_read_post(inode, h_file);

out:
	si_read_unlock(sb);
	return err;
}

static ssize_t
aufs_splice_write(struct pipe_inode_info *pipe, struct file *file, loff_t *ppos,
		  size_t len, unsigned int flags)
{
	ssize_t err;
	struct au_write_pre wpre;
	struct inode *inode;
	struct file *h_file;

	inode = file_inode(file);
	au_mtx_and_read_lock(inode);

	wpre.lsc = 0;
	h_file = au_write_pre(file, /*do_ready*/1, &wpre);
	err = PTR_ERR(h_file);
	if (IS_ERR(h_file))
		goto out;

	err = vfsub_splice_from(pipe, h_file, ppos, len, flags);
464
	au_write_post(inode, h_file, &wpre, err);
J. R. Okajima's avatar
J. R. Okajima committed
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

out:
	si_read_unlock(inode->i_sb);
	inode_unlock(inode);
	return err;
}

static long aufs_fallocate(struct file *file, int mode, loff_t offset,
			   loff_t len)
{
	long err;
	struct au_write_pre wpre;
	struct inode *inode;
	struct file *h_file;

	inode = file_inode(file);
	au_mtx_and_read_lock(inode);

	wpre.lsc = 0;
	h_file = au_write_pre(file, /*do_ready*/1, &wpre);
	err = PTR_ERR(h_file);
	if (IS_ERR(h_file))
		goto out;

	lockdep_off();
	err = vfs_fallocate(h_file, mode, offset, len);
	lockdep_on();
492
	au_write_post(inode, h_file, &wpre, /*written*/1);
J. R. Okajima's avatar
J. R. Okajima committed
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

out:
	si_read_unlock(inode->i_sb);
	inode_unlock(inode);
	return err;
}

static ssize_t aufs_copy_file_range(struct file *src, loff_t src_pos,
				    struct file *dst, loff_t dst_pos,
				    size_t len, unsigned int flags)
{
	ssize_t err;
	struct au_write_pre wpre;
	enum { SRC, DST };
	struct {
		struct inode *inode;
		struct file *h_file;
		struct super_block *h_sb;
	} a[2];
#define a_src	a[SRC]
#define a_dst	a[DST]

	err = -EINVAL;
	a_src.inode = file_inode(src);
	if (unlikely(!S_ISREG(a_src.inode->i_mode)))
		goto out;
	a_dst.inode = file_inode(dst);
	if (unlikely(!S_ISREG(a_dst.inode->i_mode)))
		goto out;

	au_mtx_and_read_lock(a_dst.inode);
	/*
	 * in order to match the order in di_write_lock2_{child,parent}(),
	 * use f_path.dentry for this comparison.
	 */
	if (src->f_path.dentry < dst->f_path.dentry) {
		a_src.h_file = au_read_pre(src, /*keep_fi*/1, AuLsc_FI_1);
		err = PTR_ERR(a_src.h_file);
		if (IS_ERR(a_src.h_file))
			goto out_si;

		wpre.lsc = AuLsc_FI_2;
		a_dst.h_file = au_write_pre(dst, /*do_ready*/1, &wpre);
		err = PTR_ERR(a_dst.h_file);
		if (IS_ERR(a_dst.h_file)) {
			au_read_post(a_src.inode, a_src.h_file);
			goto out_si;
		}
	} else {
		wpre.lsc = AuLsc_FI_1;
		a_dst.h_file = au_write_pre(dst, /*do_ready*/1, &wpre);
		err = PTR_ERR(a_dst.h_file);
		if (IS_ERR(a_dst.h_file))
			goto out_si;

		a_src.h_file = au_read_pre(src, /*keep_fi*/1, AuLsc_FI_2);
		err = PTR_ERR(a_src.h_file);
		if (IS_ERR(a_src.h_file)) {
551
552
			au_write_post(a_dst.inode, a_dst.h_file, &wpre,
				      /*written*/0);
J. R. Okajima's avatar
J. R. Okajima committed
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
			goto out_si;
		}
	}

	err = -EXDEV;
	a_src.h_sb = file_inode(a_src.h_file)->i_sb;
	a_dst.h_sb = file_inode(a_dst.h_file)->i_sb;
	if (unlikely(a_src.h_sb != a_dst.h_sb)) {
		AuDbgFile(src);
		AuDbgFile(dst);
		goto out_file;
	}

	err = vfsub_copy_file_range(a_src.h_file, src_pos, a_dst.h_file,
				    dst_pos, len, flags);

out_file:
570
	au_write_post(a_dst.inode, a_dst.h_file, &wpre, err);
J. R. Okajima's avatar
J. R. Okajima committed
571
572
573
574
575
576
577
578
579
580
581
582
583
	fi_read_unlock(src);
	au_read_post(a_src.inode, a_src.h_file);
out_si:
	si_read_unlock(a_dst.inode->i_sb);
	inode_unlock(a_dst.inode);
out:
	return err;
#undef a_src
#undef a_dst
}

/* ---------------------------------------------------------------------- */

J. R. Okajima's avatar
J. R. Okajima committed
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
/*
 * The locking order around current->mmap_sem.
 * - in most and regular cases
 *   file I/O syscall -- aufs_read() or something
 *	-- si_rwsem for read -- mmap_sem
 *	(Note that [fdi]i_rwsem are released before mmap_sem).
 * - in mmap case
 *   mmap(2) -- mmap_sem -- aufs_mmap() -- si_rwsem for read -- [fdi]i_rwsem
 * This AB-BA order is definitely bad, but is not a problem since "si_rwsem for
 * read" allows multiple processes to acquire it and [fdi]i_rwsem are not held
 * in file I/O. Aufs needs to stop lockdep in aufs_mmap() though.
 * It means that when aufs acquires si_rwsem for write, the process should never
 * acquire mmap_sem.
 *
 * Actually aufs_iterate() holds [fdi]i_rwsem before mmap_sem, but this is not a
 * problem either since any directory is not able to be mmap-ed.
 * The similar scenario is applied to aufs_readlink() too.
 */

#if 0 /* stop calling security_file_mmap() */
/* cf. linux/include/linux/mman.h: calc_vm_prot_bits() */
#define AuConv_VM_PROT(f, b)	_calc_vm_trans(f, VM_##b, PROT_##b)

static unsigned long au_arch_prot_conv(unsigned long flags)
{
	/* currently ppc64 only */
#ifdef CONFIG_PPC64
	/* cf. linux/arch/powerpc/include/asm/mman.h */
	AuDebugOn(arch_calc_vm_prot_bits(-1) != VM_SAO);
	return AuConv_VM_PROT(flags, SAO);
#else
	AuDebugOn(arch_calc_vm_prot_bits(-1));
	return 0;
#endif
}

static unsigned long au_prot_conv(unsigned long flags)
{
	return AuConv_VM_PROT(flags, READ)
		| AuConv_VM_PROT(flags, WRITE)
		| AuConv_VM_PROT(flags, EXEC)
		| au_arch_prot_conv(flags);
}

/* cf. linux/include/linux/mman.h: calc_vm_flag_bits() */
#define AuConv_VM_MAP(f, b)	_calc_vm_trans(f, VM_##b, MAP_##b)

static unsigned long au_flag_conv(unsigned long flags)
{
	return AuConv_VM_MAP(flags, GROWSDOWN)
		| AuConv_VM_MAP(flags, DENYWRITE)
		| AuConv_VM_MAP(flags, LOCKED);
}
#endif

static int aufs_mmap(struct file *file, struct vm_area_struct *vma)
{
	int err;
	const unsigned char wlock
		= (file->f_mode & FMODE_WRITE) && (vma->vm_flags & VM_SHARED);
	struct super_block *sb;
	struct file *h_file;
	struct inode *inode;

	AuDbgVmRegion(file, vma);

	inode = file_inode(file);
	sb = inode->i_sb;
	lockdep_off();
	si_read_lock(sb, AuLock_NOPLMW);

	h_file = au_write_pre(file, wlock, /*wpre*/NULL);
	lockdep_on();
	err = PTR_ERR(h_file);
	if (IS_ERR(h_file))
		goto out;

	err = 0;
	au_set_mmapped(file);
	au_vm_file_reset(vma, h_file);
	/*
	 * we cannot call security_mmap_file() here since it may acquire
	 * mmap_sem or i_mutex.
	 *
	 * err = security_mmap_file(h_file, au_prot_conv(vma->vm_flags),
	 *			 au_flag_conv(vma->vm_flags));
	 */
	if (!err)
		err = call_mmap(h_file, vma);
	if (!err) {
		au_vm_prfile_set(vma, file);
		fsstack_copy_attr_atime(inode, file_inode(h_file));
		goto out_fput; /* success */
	}
	au_unset_mmapped(file);
	au_vm_file_reset(vma, file);

out_fput:
	lockdep_off();
	ii_write_unlock(inode);
	lockdep_on();
	fput(h_file);
out:
	lockdep_off();
	si_read_unlock(sb);
	lockdep_on();
	AuTraceErr(err);
	return err;
}

/* ---------------------------------------------------------------------- */

J. R. Okajima's avatar
J. R. Okajima committed
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
static int aufs_fsync_nondir(struct file *file, loff_t start, loff_t end,
			     int datasync)
{
	int err;
	struct au_write_pre wpre;
	struct inode *inode;
	struct file *h_file;

	err = 0; /* -EBADF; */ /* posix? */
	if (unlikely(!(file->f_mode & FMODE_WRITE)))
		goto out;

	inode = file_inode(file);
	au_mtx_and_read_lock(inode);

	wpre.lsc = 0;
	h_file = au_write_pre(file, /*do_ready*/1, &wpre);
	err = PTR_ERR(h_file);
	if (IS_ERR(h_file))
		goto out_unlock;

	err = vfsub_fsync(h_file, &h_file->f_path, datasync);
718
	au_write_post(inode, h_file, &wpre, /*written*/0);
J. R. Okajima's avatar
J. R. Okajima committed
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776

out_unlock:
	si_read_unlock(inode->i_sb);
	inode_unlock(inode);
out:
	return err;
}

static int aufs_fasync(int fd, struct file *file, int flag)
{
	int err;
	struct file *h_file;
	struct super_block *sb;

	sb = file->f_path.dentry->d_sb;
	si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);

	h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
	err = PTR_ERR(h_file);
	if (IS_ERR(h_file))
		goto out;

	if (h_file->f_op->fasync)
		err = h_file->f_op->fasync(fd, h_file, flag);
	fput(h_file); /* instead of au_read_post() */

out:
	si_read_unlock(sb);
	return err;
}

static int aufs_setfl(struct file *file, unsigned long arg)
{
	int err;
	struct file *h_file;
	struct super_block *sb;

	sb = file->f_path.dentry->d_sb;
	si_read_lock(sb, AuLock_FLUSH | AuLock_NOPLMW);

	h_file = au_read_pre(file, /*keep_fi*/0, /*lsc*/0);
	err = PTR_ERR(h_file);
	if (IS_ERR(h_file))
		goto out;

	/* stop calling h_file->fasync */
	arg |= vfsub_file_flags(file) & FASYNC;
	err = setfl(/*unused fd*/-1, h_file, arg);
	fput(h_file); /* instead of au_read_post() */

out:
	si_read_unlock(sb);
	return err;
}

/* ---------------------------------------------------------------------- */

/* no one supports this operation, currently */
777
#if 0 /* reserved for future use */
J. R. Okajima's avatar
J. R. Okajima committed
778
779
780
781
782
783
784
785
static ssize_t aufs_sendpage(struct file *file, struct page *page, int offset,
			     size_t len, loff_t *pos, int more)
{
}
#endif

/* ---------------------------------------------------------------------- */

J. R. Okajima's avatar
J. R. Okajima committed
786
787
788
const struct file_operations aufs_file_fop = {
	.owner		= THIS_MODULE,

J. R. Okajima's avatar
J. R. Okajima committed
789
790
791
792
793
794
795
	.llseek		= default_llseek,

	.read		= aufs_read,
	.write		= aufs_write,
	.read_iter	= aufs_read_iter,
	.write_iter	= aufs_write_iter,

796
797
798
#ifdef CONFIG_AUFS_POLL
	.poll		= aufs_poll,
#endif
J. R. Okajima's avatar
J. R. Okajima committed
799
800
801
802
	.unlocked_ioctl	= aufs_ioctl_nondir,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= aufs_compat_ioctl_nondir,
#endif
J. R. Okajima's avatar
J. R. Okajima committed
803
	.mmap		= aufs_mmap,
J. R. Okajima's avatar
J. R. Okajima committed
804
	.open		= aufs_open_nondir,
J. R. Okajima's avatar
J. R. Okajima committed
805
806
807
808
809
810
811
812
	.flush		= aufs_flush_nondir,
	.release	= aufs_release_nondir,
	.fsync		= aufs_fsync_nondir,
	.fasync		= aufs_fasync,
	/* .sendpage	= aufs_sendpage, */
	.setfl		= aufs_setfl,
	.splice_write	= aufs_splice_write,
	.splice_read	= aufs_splice_read,
813
#if 0 /* reserved for future use */
J. R. Okajima's avatar
J. R. Okajima committed
814
815
816
817
818
	.aio_splice_write = aufs_aio_splice_write,
	.aio_splice_read  = aufs_aio_splice_read,
#endif
	.fallocate	= aufs_fallocate,
	.copy_file_range = aufs_copy_file_range
J. R. Okajima's avatar
J. R. Okajima committed
819
};