aboutsummaryrefslogtreecommitdiff
path: root/fs/xfs/linux-2.6/xfs_file.c
blob: d0d412afd2617e7d1799bfa86d313833194e3c9b (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
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
/*
 * 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 version 2 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.
 *
 * Further, this software is distributed without any warranty that it is
 * free of the rightful claim of any third person regarding infringement
 * or the like.  Any license provided herein, whether implied or
 * otherwise, applies only to this software file.  Patent licenses, if
 * any, provided herein do not apply to combinations of this program with
 * other software, or any other product whatsoever.
 *
 * You should have received a copy of the GNU General Public License along
 * with this program; if not, write the Free Software Foundation, Inc., 59
 * Temple Place - Suite 330, Boston MA 02111-1307, USA.
 *
 * Contact information: Silicon Graphics, Inc., 1600 Amphitheatre Pkwy,
 * Mountain View, CA  94043, or:
 *
 * http://www.sgi.com
 *
 * For further information regarding this notice, see:
 *
 * http://oss.sgi.com/projects/GenInfo/SGIGPLNoticeExplan/
 */

#include "xfs.h"
#include "xfs_inum.h"
#include "xfs_log.h"
#include "xfs_sb.h"
#include "xfs_dir.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_dir_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 <linux/dcache.h>
#include <linux/smp_lock.h>

static struct vm_operations_struct linvfs_file_vm_ops;


STATIC inline ssize_t
__linvfs_read(
	struct kiocb		*iocb,
	char			__user *buf,
	int			ioflags,
	size_t			count,
	loff_t			pos)
{
	struct iovec		iov = {buf, count};
	struct file		*file = iocb->ki_filp;
	vnode_t			*vp = LINVFS_GET_VP(file->f_dentry->d_inode);
	ssize_t			rval;

	BUG_ON(iocb->ki_pos != pos);

	if (unlikely(file->f_flags & O_DIRECT))
		ioflags |= IO_ISDIRECT;
	VOP_READ(vp, iocb, &iov, 1, &iocb->ki_pos, ioflags, NULL, rval);
	return rval;
}


STATIC ssize_t
linvfs_aio_read(
	struct kiocb		*iocb,
	char			__user *buf,
	size_t			count,
	loff_t			pos)
{
	return __linvfs_read(iocb, buf, IO_ISAIO, count, pos);
}

STATIC ssize_t
linvfs_aio_read_invis(
	struct kiocb		*iocb,
	char			__user *buf,
	size_t			count,
	loff_t			pos)
{
	return __linvfs_read(iocb, buf, IO_ISAIO|IO_INVIS, count, pos);
}


STATIC inline ssize_t
__linvfs_write(
	struct kiocb	*iocb,
	const char	__user *buf,
	int		ioflags,
	size_t		count,
	loff_t		pos)
{
	struct iovec	iov = {(void __user *)buf, count};
	struct file	*file = iocb->ki_filp;
	struct inode	*inode = file->f_mapping->host;
	vnode_t		*vp = LINVFS_GET_VP(inode);
	ssize_t		rval;

	BUG_ON(iocb->ki_pos != pos);
	if (unlikely(file->f_flags & O_DIRECT))
		ioflags |= IO_ISDIRECT;

	VOP_WRITE(vp, iocb, &iov, 1, &iocb->ki_pos, ioflags, NULL, rval);
	return rval;
}


STATIC ssize_t
linvfs_aio_write(
	struct kiocb		*iocb,
	const char		__user *buf,
	size_t			count,
	loff_t			pos)
{
	return __linvfs_write(iocb, buf, IO_ISAIO, count, pos);
}

STATIC ssize_t
linvfs_aio_write_invis(
	struct kiocb		*iocb,
	const char		__user *buf,
	size_t			count,
	loff_t			pos)
{
	return __linvfs_write(iocb, buf, IO_ISAIO|IO_INVIS, count, pos);
}


STATIC inline ssize_t
__linvfs_readv(
	struct file		*file,
	const struct iovec 	*iov,
	int			ioflags,
	unsigned long		nr_segs,
	loff_t			*ppos)
{
	struct inode	*inode = file->f_mapping->host;
	vnode_t		*vp = LINVFS_GET_VP(inode);
	struct		kiocb kiocb;
	ssize_t		rval;

	init_sync_kiocb(&kiocb, file);
	kiocb.ki_pos = *ppos;

	if (unlikely(file->f_flags & O_DIRECT))
		ioflags |= IO_ISDIRECT;
	VOP_READ(vp, &kiocb, iov, nr_segs, &kiocb.ki_pos, ioflags, NULL, rval);

	*ppos = kiocb.ki_pos;
	return rval;
}

STATIC ssize_t
linvfs_readv(
	struct file		*file,
	const struct iovec 	*iov,
	unsigned long		nr_segs,
	loff_t			*ppos)
{
	return __linvfs_readv(file, iov, 0, nr_segs, ppos);
}

STATIC ssize_t
linvfs_readv_invis(
	struct file		*file,
	const struct iovec 	*iov,
	unsigned long		nr_segs,
	loff_t			*ppos)
{
	return __linvfs_readv(file, iov, IO_INVIS, nr_segs, ppos);
}


STATIC inline ssize_t
__linvfs_writev(
	struct file		*file,
	const struct iovec 	*iov,
	int			ioflags,
	unsigned long		nr_segs,
	loff_t			*ppos)
{
	struct inode	*inode = file->f_mapping->host;
	vnode_t		*vp = LINVFS_GET_VP(inode);
	struct		kiocb kiocb;
	ssize_t		rval;

	init_sync_kiocb(&kiocb, file);
	kiocb.ki_pos = *ppos;
	if (unlikely(file->f_flags & O_DIRECT))
		ioflags |= IO_ISDIRECT;

	VOP_WRITE(vp, &kiocb, iov, nr_segs, &kiocb.ki_pos, ioflags, NULL, rval);

	*ppos = kiocb.ki_pos;
	return rval;
}


STATIC ssize_t
linvfs_writev(
	struct file		*file,
	const struct iovec 	*iov,
	unsigned long		nr_segs,
	loff_t			*ppos)
{
	return __linvfs_writev(file, iov, 0, nr_segs, ppos);
}

STATIC ssize_t
linvfs_writev_invis(
	struct file		*file,
	const struct iovec 	*iov,
	unsigned long		nr_segs,
	loff_t			*ppos)
{
	return __linvfs_writev(file, iov, IO_INVIS, nr_segs, ppos);
}

STATIC ssize_t
linvfs_sendfile(
	struct file		*filp,
	loff_t			*ppos,
	size_t			count,
	read_actor_t		actor,
	void			*target)
{
	vnode_t			*vp = LINVFS_GET_VP(filp->f_dentry->d_inode);
	ssize_t			rval;

	VOP_SENDFILE(vp, filp, ppos, 0, count, actor, target, NULL, rval);
	return rval;
}


STATIC int
linvfs_open(
	struct inode	*inode,
	struct file	*filp)
{
	vnode_t		*vp = LINVFS_GET_VP(inode);
	int		error;

	if (!(filp->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
		return -EFBIG;

	ASSERT(vp);
	VOP_OPEN(vp, NULL, error);
	return -error;
}


STATIC int
linvfs_release(
	struct inode	*inode,
	struct file	*filp)
{
	vnode_t		*vp = LINVFS_GET_VP(inode);
	int		error = 0;

	if (vp)
		VOP_RELEASE(vp, error);
	return -error;
}


STATIC int
linvfs_fsync(
	struct file	*filp,
	struct dentry	*dentry,
	int		datasync)
{
	struct inode	*inode = dentry->d_inode;
	vnode_t		*vp = LINVFS_GET_VP(inode);
	int		error;
	int		flags = FSYNC_WAIT;

	if (datasync)
		flags |= FSYNC_DATA;

	ASSERT(vp);
	VOP_FSYNC(vp, flags, NULL, (xfs_off_t)0, (xfs_off_t)-1, error);
	return -error;
}

/*
 * linvfs_readdir maps to VOP_READDIR().
 * We need to build a uio, cred, ...
 */

#define nextdp(dp)      ((struct xfs_dirent *)((char *)(dp) + (dp)->d_reclen))

STATIC int
linvfs_readdir(
	struct file	*filp,
	void		*dirent,
	filldir_t	filldir)
{
	int		error = 0;
	vnode_t		*vp;
	uio_t		uio;
	iovec_t		iov;
	int		eof = 0;
	caddr_t		read_buf;
	int		namelen, size = 0;
	size_t		rlen = PAGE_CACHE_SIZE;
	xfs_off_t	start_offset, curr_offset;
	xfs_dirent_t	*dbp = NULL;

	vp = LINVFS_GET_VP(filp->f_dentry->d_inode);
	ASSERT(vp);

	/* Try fairly hard to get memory */
	do {
		if ((read_buf = (caddr_t)kmalloc(rlen, GFP_KERNEL)))
			break;
		rlen >>= 1;
	} while (rlen >= 1024);

	if (read_buf == NULL)
		return -ENOMEM;

	uio.uio_iov = &iov;
	uio.uio_segflg = UIO_SYSSPACE;
	curr_offset = filp->f_pos;
	if (filp->f_pos != 0x7fffffff)
		uio.uio_offset = filp->f_pos;
	else
		uio.uio_offset = 0xffffffff;

	while (!eof) {
		uio.uio_resid = iov.iov_len = rlen;
		iov.iov_base = read_buf;
		uio.uio_iovcnt = 1;

		start_offset = uio.uio_offset;

		VOP_READDIR(vp, &uio, NULL, &eof, error);
		if ((uio.uio_offset == start_offset) || error) {
			size = 0;
			break;
		}

		size = rlen - uio.uio_resid;
		dbp = (xfs_dirent_t *)read_buf;
		while (size > 0) {
			namelen = strlen(dbp->d_name);

			if (filldir(dirent, dbp->d_name, namelen,
					(loff_t) curr_offset & 0x7fffffff,
					(ino_t) dbp->d_ino,
					DT_UNKNOWN)) {
				goto done;
			}
			size -= dbp->d_reclen;
			curr_offset = (loff_t)dbp->d_off /* & 0x7fffffff */;
			dbp = nextdp(dbp);
		}
	}
done:
	if (!error) {
		if (size == 0)
			filp->f_pos = uio.uio_offset & 0x7fffffff;
		else if (dbp)
			filp->f_pos = curr_offset;
	}

	kfree(read_buf);
	return -error;
}


STATIC int
linvfs_file_mmap(
	struct file	*filp,
	struct vm_area_struct *vma)
{
	struct inode	*ip = filp->f_dentry->d_inode;
	vnode_t		*vp = LINVFS_GET_VP(ip);
	vattr_t		va = { .va_mask = XFS_AT_UPDATIME };
	int		error;

	if (vp->v_vfsp->vfs_flag & VFS_DMI) {
		xfs_mount_t	*mp = XFS_VFSTOM(vp->v_vfsp);

		error = -XFS_SEND_MMAP(mp, vma, 0);
		if (error)
			return error;
	}

	vma->vm_ops = &linvfs_file_vm_ops;

	VOP_SETATTR(vp, &va, XFS_AT_UPDATIME, NULL, error);
	if (!error)
		vn_revalidate(vp);	/* update Linux inode flags */
	return 0;
}


STATIC long
linvfs_ioctl(
	struct file	*filp,
	unsigned int	cmd,
	unsigned long	arg)
{
	int		error;
	struct inode *inode = filp->f_dentry->d_inode;
	vnode_t		*vp = LINVFS_GET_VP(inode);

	VOP_IOCTL(vp, inode, filp, 0, cmd, (void __user *)arg, error);
	VMODIFY(vp);

	/* 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
linvfs_ioctl_invis(
	struct file	*filp,
	unsigned int	cmd,
	unsigned long	arg)
{
	int		error;
	struct inode *inode = filp->f_dentry->d_inode;
	vnode_t		*vp = LINVFS_GET_VP(inode);

	ASSERT(vp);
	VOP_IOCTL(vp, inode, filp, IO_INVIS, cmd, (void __user *)arg, error);
	VMODIFY(vp);

	/* 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 HAVE_VMOP_MPROTECT
STATIC int
linvfs_mprotect(
	struct vm_area_struct *vma,
	unsigned int	newflags)
{
	vnode_t		*vp = LINVFS_GET_VP(vma->vm_file->f_dentry->d_inode);
	int		error = 0;

	if (vp->v_vfsp->vfs_flag & VFS_DMI) {
		if ((vma->vm_flags & VM_MAYSHARE) &&
		    (newflags & VM_WRITE) && !(vma->vm_flags & VM_WRITE)) {
			xfs_mount_t	*mp = XFS_VFSTOM(vp->v_vfsp);

			error = XFS_SEND_MMAP(mp, vma, VM_WRITE);
		    }
	}
	return error;
}
#endif /* HAVE_VMOP_MPROTECT */

#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
linvfs_open_exec(
	struct inode	*inode)
{
	vnode_t		*vp = LINVFS_GET_VP(inode);
	xfs_mount_t	*mp = XFS_VFSTOM(vp->v_vfsp);
	int		error = 0;
	bhv_desc_t	*bdp;
	xfs_inode_t	*ip;

	if (vp->v_vfsp->vfs_flag & VFS_DMI) {
		bdp = vn_bhv_lookup(VN_BHV_HEAD(vp), &xfs_vnodeops);
		if (!bdp) {
			error = -EINVAL;
			goto open_exec_out;
		}
		ip = XFS_BHVTOI(bdp);
		if (DM_EVENT_ENABLED(vp->v_vfsp, ip, DM_EVENT_READ)) {
			error = -XFS_SEND_DATA(mp, DM_EVENT_READ, vp,
					       0, 0, 0, NULL);
		}
	}
open_exec_out:
	return error;
}
#endif /* HAVE_FOP_OPEN_EXEC */

/*
 * Temporary workaround to the AIO direct IO write problem.
 * This code can go and we can revert to do_sync_write once
 * the writepage(s) rework is merged.
 */
STATIC ssize_t
linvfs_write(
	struct file	*filp,
	const char	__user *buf,
	size_t		len,
	loff_t		*ppos)
{
	struct kiocb	kiocb;
	ssize_t		ret;

	init_sync_kiocb(&kiocb, filp);
	kiocb.ki_pos = *ppos;
	ret = __linvfs_write(&kiocb, buf, 0, len, kiocb.ki_pos);
	*ppos = kiocb.ki_pos;
	return ret;
}
STATIC ssize_t
linvfs_write_invis(
	struct file	*filp,
	const char	__user *buf,
	size_t		len,
	loff_t		*ppos)
{
	struct kiocb	kiocb;
	ssize_t		ret;

	init_sync_kiocb(&kiocb, filp);
	kiocb.ki_pos = *ppos;
	ret = __linvfs_write(&kiocb, buf, IO_INVIS, len, kiocb.ki_pos);
	*ppos = kiocb.ki_pos;
	return ret;
}


struct file_operations linvfs_file_operations = {
	.llseek		= generic_file_llseek,
	.read		= do_sync_read,
	.write		= linvfs_write,
	.readv		= linvfs_readv,
	.writev		= linvfs_writev,
	.aio_read	= linvfs_aio_read,
	.aio_write	= linvfs_aio_write,
	.sendfile	= linvfs_sendfile,
	.unlocked_ioctl	= linvfs_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl   = xfs_compat_ioctl,
#endif
	.mmap		= linvfs_file_mmap,
	.open		= linvfs_open,
	.release	= linvfs_release,
	.fsync		= linvfs_fsync,
#ifdef HAVE_FOP_OPEN_EXEC
	.open_exec	= linvfs_open_exec,
#endif
};

struct file_operations linvfs_invis_file_operations = {
	.llseek		= generic_file_llseek,
	.read		= do_sync_read,
	.write		= linvfs_write_invis,
	.readv		= linvfs_readv_invis,
	.writev		= linvfs_writev_invis,
	.aio_read	= linvfs_aio_read_invis,
	.aio_write	= linvfs_aio_write_invis,
	.sendfile	= linvfs_sendfile,
	.unlocked_ioctl	= linvfs_ioctl_invis,
#ifdef CONFIG_COMPAT
	.compat_ioctl   = xfs_compat_invis_ioctl,
#endif
	.mmap		= linvfs_file_mmap,
	.open		= linvfs_open,
	.release	= linvfs_release,
	.fsync		= linvfs_fsync,
};


struct file_operations linvfs_dir_operations = {
	.read		= generic_read_dir,
	.readdir	= linvfs_readdir,
	.unlocked_ioctl	= linvfs_ioctl,
	.fsync		= linvfs_fsync,
};

static struct vm_operations_struct linvfs_file_vm_ops = {
	.nopage		= filemap_nopage,
	.populate	= filemap_populate,
#ifdef HAVE_VMOP_MPROTECT
	.mprotect	= linvfs_mprotect,
#endif
};