summaryrefslogtreecommitdiff
path: root/fs/xfs/linux-2.6/xfs_file.c
blob: e1fcef2eb9285a6f8f449b72deb1e925c540671d (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
/*
 * Copyright (c) 2000-2005 Silicon Graphics, 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_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
#include "xfs_trans.h"
#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_alloc.h"
#include "xfs_btree.h"
#include "xfs_attr_sf.h"
#include "xfs_dir2_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_error.h"
#include "xfs_rw.h"
#include "xfs_ioctl32.h"
#include "xfs_vnodeops.h"

#include <linux/dcache.h>
#include <linux/smp_lock.h>

static struct vm_operations_struct xfs_file_vm_ops;
#ifdef CONFIG_XFS_DMAPI
static struct vm_operations_struct xfs_dmapi_file_vm_ops;
#endif

STATIC_INLINE ssize_t
__xfs_file_read(
	struct kiocb		*iocb,
	const struct iovec	*iov,
	unsigned long		nr_segs,
	int			ioflags,
	loff_t			pos)
{
	struct file		*file = iocb->ki_filp;

	BUG_ON(iocb->ki_pos != pos);
	if (unlikely(file->f_flags & O_DIRECT))
		ioflags |= IO_ISDIRECT;
	return xfs_read(XFS_I(file->f_path.dentry->d_inode), iocb, iov,
				nr_segs, &iocb->ki_pos, ioflags);
}

STATIC ssize_t
xfs_file_aio_read(
	struct kiocb		*iocb,
	const struct iovec	*iov,
	unsigned long		nr_segs,
	loff_t			pos)
{
	return __xfs_file_read(iocb, iov, nr_segs, IO_ISAIO, pos);
}

STATIC ssize_t
xfs_file_aio_read_invis(
	struct kiocb		*iocb,
	const struct iovec	*iov,
	unsigned long		nr_segs,
	loff_t			pos)
{
	return __xfs_file_read(iocb, iov, nr_segs, IO_ISAIO|IO_INVIS, pos);
}

STATIC_INLINE ssize_t
__xfs_file_write(
	struct kiocb		*iocb,
	const struct iovec	*iov,
	unsigned long		nr_segs,
	int			ioflags,
	loff_t			pos)
{
	struct file	*file = iocb->ki_filp;

	BUG_ON(iocb->ki_pos != pos);
	if (unlikely(file->f_flags & O_DIRECT))
		ioflags |= IO_ISDIRECT;
	return xfs_write(XFS_I(file->f_mapping->host), iocb, iov, nr_segs,
				&iocb->ki_pos, ioflags);
}

STATIC ssize_t
xfs_file_aio_write(
	struct kiocb		*iocb,
	const struct iovec	*iov,
	unsigned long		nr_segs,
	loff_t			pos)
{
	return __xfs_file_write(iocb, iov, nr_segs, IO_ISAIO, pos);
}

STATIC ssize_t
xfs_file_aio_write_invis(
	struct kiocb		*iocb,
	const struct iovec	*iov,
	unsigned long		nr_segs,
	loff_t			pos)
{
	return __xfs_file_write(iocb, iov, nr_segs, IO_ISAIO|IO_INVIS, pos);
}

STATIC ssize_t
xfs_file_splice_read(
	struct file		*infilp,
	loff_t			*ppos,
	struct pipe_inode_info	*pipe,
	size_t			len,
	unsigned int		flags)
{
	return xfs_splice_read(XFS_I(infilp->f_path.dentry->d_inode),
				   infilp, ppos, pipe, len, flags, 0);
}

STATIC ssize_t
xfs_file_splice_read_invis(
	struct file		*infilp,
	loff_t			*ppos,
	struct pipe_inode_info	*pipe,
	size_t			len,
	unsigned int		flags)
{
	return xfs_splice_read(XFS_I(infilp->f_path.dentry->d_inode),
				   infilp, ppos, pipe, len, flags, IO_INVIS);
}

STATIC ssize_t
xfs_file_splice_write(
	struct pipe_inode_info	*pipe,
	struct file		*outfilp,
	loff_t			*ppos,
	size_t			len,
	unsigned int		flags)
{
	return xfs_splice_write(XFS_I(outfilp->f_path.dentry->d_inode),
				    pipe, outfilp, ppos, len, flags, 0);
}

STATIC ssize_t
xfs_file_splice_write_invis(
	struct pipe_inode_info	*pipe,
	struct file		*outfilp,
	loff_t			*ppos,
	size_t			len,
	unsigned int		flags)
{
	return xfs_splice_write(XFS_I(outfilp->f_path.dentry->d_inode),
				    pipe, outfilp, ppos, len, flags, IO_INVIS);
}

STATIC int
xfs_file_open(
	struct inode	*inode,
	struct file	*filp)
{
	if (!(filp->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
		return -EFBIG;
	return -xfs_open(XFS_I(inode));
}

STATIC int
xfs_file_release(
	struct inode	*inode,
	struct file	*filp)
{
	return -xfs_release(XFS_I(inode));
}

STATIC int
xfs_file_fsync(
	struct file	*filp,
	struct dentry	*dentry,
	int		datasync)
{
	int		flags = FSYNC_WAIT;

	if (datasync)
		flags |= FSYNC_DATA;
	xfs_iflags_clear(XFS_I(dentry->d_inode), XFS_ITRUNCATED);
	return -xfs_fsync(XFS_I(dentry->d_inode), flags,
			(xfs_off_t)0, (xfs_off_t)-1);
}

#ifdef CONFIG_XFS_DMAPI
STATIC int
xfs_vm_fault(
	struct vm_area_struct	*vma,
	struct vm_fault	*vmf)
{
	struct inode	*inode = vma->vm_file->f_path.dentry->d_inode;
	bhv_vnode_t	*vp = vn_from_inode(inode);

	ASSERT_ALWAYS(vp->v_vfsp->vfs_flag & VFS_DMI);
	if (XFS_SEND_MMAP(XFS_VFSTOM(vp->v_vfsp), vma, 0))
		return VM_FAULT_SIGBUS;
	return filemap_fault(vma, vmf);
}
#endif /* CONFIG_XFS_DMAPI */

/*
 * Unfortunately we can't just use the clean and simple readdir implementation
 * below, because nfs might call back into ->lookup from the filldir callback
 * and that will deadlock the low-level btree code.
 *
 * Hopefully we'll find a better workaround that allows to use the optimal
 * version at least for local readdirs for 2.6.25.
 */
#if 0
STATIC int
xfs_file_readdir(
	struct file	*filp,
	void		*dirent,
	filldir_t	filldir)
{
	struct inode	*inode = filp->f_path.dentry->d_inode;
	xfs_inode_t	*ip = XFS_I(inode);
	int		error;
	size_t		bufsize;

	/*
	 * The Linux API doesn't pass down the total size of the buffer
	 * we read into down to the filesystem.  With the filldir concept
	 * it's not needed for correct information, but the XFS dir2 leaf
	 * code wants an estimate of the buffer size to calculate it's
	 * readahead window and size the buffers used for mapping to
	 * physical blocks.
	 *
	 * Try to give it an estimate that's good enough, maybe at some
	 * point we can change the ->readdir prototype to include the
	 * buffer size.
	 */
	bufsize = (size_t)min_t(loff_t, PAGE_SIZE, inode->i_size);

	error = xfs_readdir(ip, dirent, bufsize,
				(xfs_off_t *)&filp->f_pos, filldir);
	if (error)
		return -error;
	return 0;
}
#else

struct hack_dirent {
	int		namlen;
	loff_t		offset;
	u64		ino;
	unsigned int	d_type;
	char		name[];
};

struct hack_callback {
	char		*dirent;
	size_t		len;
	size_t		used;
};

STATIC int
xfs_hack_filldir(
	void		*__buf,
	const char	*name,
	int		namlen,
	loff_t		offset,
	u64		ino,
	unsigned int	d_type)
{
	struct hack_callback *buf = __buf;
	struct hack_dirent *de = (struct hack_dirent *)(buf->dirent + buf->used);

	if (buf->used + sizeof(struct hack_dirent) + namlen > buf->len)
		return -EINVAL;

	de->namlen = namlen;
	de->offset = offset;
	de->ino = ino;
	de->d_type = d_type;
	memcpy(de->name, name, namlen);
	buf->used += sizeof(struct hack_dirent) + namlen;
	return 0;
}

STATIC int
xfs_file_readdir(
	struct file	*filp,
	void		*dirent,
	filldir_t	filldir)
{
	struct inode	*inode = filp->f_path.dentry->d_inode;
	xfs_inode_t	*ip = XFS_I(inode);
	struct hack_callback buf;
	struct hack_dirent *de;
	int		error;
	loff_t		size;
	int		eof = 0;
	xfs_off_t       start_offset, curr_offset, offset;

	/*
	 * Try fairly hard to get memory
	 */
	buf.len = PAGE_CACHE_SIZE;
	do {
		buf.dirent = kmalloc(buf.len, GFP_KERNEL);
		if (buf.dirent)
			break;
		buf.len >>= 1;
	} while (buf.len >= 1024);

	if (!buf.dirent)
		return -ENOMEM;

	curr_offset = filp->f_pos;
	if (curr_offset == 0x7fffffff)
		offset = 0xffffffff;
	else
		offset = filp->f_pos;

	while (!eof) {
		int reclen;
		start_offset = offset;

		buf.used = 0;
		error = -xfs_readdir(ip, &buf, buf.len, &offset,
				     xfs_hack_filldir);
		if (error || offset == start_offset) {
			size = 0;
			break;
		}

		size = buf.used;
		de = (struct hack_dirent *)buf.dirent;
		while (size > 0) {
			if (filldir(dirent, de->name, de->namlen,
					curr_offset & 0x7fffffff,
					de->ino, de->d_type)) {
				goto done;
			}

			reclen = sizeof(struct hack_dirent) + de->namlen;
			size -= reclen;
			de = (struct hack_dirent *)((char *)de + reclen);
			curr_offset = de->offset /* & 0x7fffffff */;
		}
	}

 done:
	if (!error) {
		if (size == 0)
			filp->f_pos = offset & 0x7fffffff;
		else if (de)
			filp->f_pos = curr_offset;
	}

	kfree(buf.dirent);
	return error;
}
#endif

STATIC int
xfs_file_mmap(
	struct file	*filp,
	struct vm_area_struct *vma)
{
	vma->vm_ops = &xfs_file_vm_ops;
	vma->vm_flags |= VM_CAN_NONLINEAR;

#ifdef CONFIG_XFS_DMAPI
	if (XFS_M(filp->f_path.dentry->d_inode->i_sb)->m_flags & XFS_MOUNT_DMAPI)
		vma->vm_ops = &xfs_dmapi_file_vm_ops;
#endif /* CONFIG_XFS_DMAPI */

	file_accessed(filp);
	return 0;
}

STATIC long
xfs_file_ioctl(
	struct file	*filp,
	unsigned int	cmd,
	unsigned long	p)
{
	int		error;
	struct inode	*inode = filp->f_path.dentry->d_inode;

	error = xfs_ioctl(XFS_I(inode), filp, 0, cmd, (void __user *)p);
	xfs_iflags_set(XFS_I(inode), XFS_IMODIFIED);

	/* NOTE:  some of the ioctl's return positive #'s as a
	 *	  byte count indicating success, such as
	 *	  readlink_by_handle.  So we don't "sign flip"
	 *	  like most other routines.  This means true
	 *	  errors need to be returned as a negative value.
	 */
	return error;
}

STATIC long
xfs_file_ioctl_invis(
	struct file	*filp,
	unsigned int	cmd,
	unsigned long	p)
{
	int		error;
	struct inode	*inode = filp->f_path.dentry->d_inode;

	error = xfs_ioctl(XFS_I(inode), filp, IO_INVIS, cmd, (void __user *)p);
	xfs_iflags_set(XFS_I(inode), XFS_IMODIFIED);

	/* NOTE:  some of the ioctl's return positive #'s as a
	 *	  byte count indicating success, such as
	 *	  readlink_by_handle.  So we don't "sign flip"
	 *	  like most other routines.  This means true
	 *	  errors need to be returned as a negative value.
	 */
	return error;
}

#ifdef CONFIG_XFS_DMAPI
#ifdef HAVE_VMOP_MPROTECT
STATIC int
xfs_vm_mprotect(
	struct vm_area_struct *vma,
	unsigned int	newflags)
{
	struct inode	*inode = vma->vm_file->f_path.dentry->d_inode;
	struct xfs_mount *mp = XFS_M(inode->i_sb);
	int		error = 0;

	if (mp->m_flags & XFS_MOUNT_DMAPI) {
		if ((vma->vm_flags & VM_MAYSHARE) &&
		    (newflags & VM_WRITE) && !(vma->vm_flags & VM_WRITE))
			error = XFS_SEND_MMAP(mp, vma, VM_WRITE);
	}
	return error;
}
#endif /* HAVE_VMOP_MPROTECT */
#endif /* CONFIG_XFS_DMAPI */

#ifdef HAVE_FOP_OPEN_EXEC
/* If the user is attempting to execute a file that is offline then
 * we have to trigger a DMAPI READ event before the file is marked as busy
 * otherwise the invisible I/O will not be able to write to the file to bring
 * it back online.
 */
STATIC int
xfs_file_open_exec(
	struct inode	*inode)
{
	struct xfs_mount *mp = XFS_M(inode->i_sb);

	if (unlikely(mp->m_flags & XFS_MOUNT_DMAPI)) {
		if (DM_EVENT_ENABLED(XFS_I(inode), DM_EVENT_READ)) {
			bhv_vnode_t *vp = vn_from_inode(inode);

			return -XFS_SEND_DATA(mp, DM_EVENT_READ,
						vp, 0, 0, 0, NULL);
		}
	}

	return 0;
}
#endif /* HAVE_FOP_OPEN_EXEC */

/*
 * mmap()d file has taken write protection fault and is being made
 * writable. We can set the page state up correctly for a writable
 * page, which means we can do correct delalloc accounting (ENOSPC
 * checking!) and unwritten extent mapping.
 */
STATIC int
xfs_vm_page_mkwrite(
	struct vm_area_struct	*vma,
	struct page		*page)
{
	return block_page_mkwrite(vma, page, xfs_get_blocks);
}

const struct file_operations xfs_file_operations = {
	.llseek		= generic_file_llseek,
	.read		= do_sync_read,
	.write		= do_sync_write,
	.aio_read	= xfs_file_aio_read,
	.aio_write	= xfs_file_aio_write,
	.splice_read	= xfs_file_splice_read,
	.splice_write	= xfs_file_splice_write,
	.unlocked_ioctl	= xfs_file_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= xfs_file_compat_ioctl,
#endif
	.mmap		= xfs_file_mmap,
	.open		= xfs_file_open,
	.release	= xfs_file_release,
	.fsync		= xfs_file_fsync,
#ifdef HAVE_FOP_OPEN_EXEC
	.open_exec	= xfs_file_open_exec,
#endif
};

const struct file_operations xfs_invis_file_operations = {
	.llseek		= generic_file_llseek,
	.read		= do_sync_read,
	.write		= do_sync_write,
	.aio_read	= xfs_file_aio_read_invis,
	.aio_write	= xfs_file_aio_write_invis,
	.splice_read	= xfs_file_splice_read_invis,
	.splice_write	= xfs_file_splice_write_invis,
	.unlocked_ioctl	= xfs_file_ioctl_invis,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= xfs_file_compat_invis_ioctl,
#endif
	.mmap		= xfs_file_mmap,
	.open		= xfs_file_open,
	.release	= xfs_file_release,
	.fsync		= xfs_file_fsync,
};


const struct file_operations xfs_dir_file_operations = {
	.read		= generic_read_dir,
	.readdir	= xfs_file_readdir,
	.unlocked_ioctl	= xfs_file_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= xfs_file_compat_ioctl,
#endif
	.fsync		= xfs_file_fsync,
};

static struct vm_operations_struct xfs_file_vm_ops = {
	.fault		= filemap_fault,
	.page_mkwrite	= xfs_vm_page_mkwrite,
};

#ifdef CONFIG_XFS_DMAPI
static struct vm_operations_struct xfs_dmapi_file_vm_ops = {
	.fault		= xfs_vm_fault,
	.page_mkwrite	= xfs_vm_page_mkwrite,
#ifdef HAVE_VMOP_MPROTECT
	.mprotect	= xfs_vm_mprotect,
#endif
};
#endif /* CONFIG_XFS_DMAPI */