aboutsummaryrefslogtreecommitdiff
path: root/fs/9p/vfs_file.c
blob: 98c4307a1f035ee08673cf25a3cff9caf4afd363 (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
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
/*
 *  linux/fs/9p/vfs_file.c
 *
 * This file contians vfs file ops for 9P2000.
 *
 *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
 *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License version 2
 *  as published by the Free Software Foundation.
 *
 *  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, write to:
 *  Free Software Foundation
 *  51 Franklin Street, Fifth Floor
 *  Boston, MA  02111-1301  USA
 *
 */

#include <linux/module.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/file.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/inet.h>
#include <linux/list.h>
#include <linux/pagemap.h>
#include <linux/utsname.h>
#include <asm/uaccess.h>
#include <linux/idr.h>
#include <net/9p/9p.h>
#include <net/9p/client.h>

#include "v9fs.h"
#include "v9fs_vfs.h"
#include "fid.h"
#include "cache.h"

static const struct vm_operations_struct v9fs_file_vm_ops;

/**
 * v9fs_file_open - open a file (or directory)
 * @inode: inode to be opened
 * @file: file being opened
 *
 */

int v9fs_file_open(struct inode *inode, struct file *file)
{
	int err;
	struct v9fs_inode *v9inode;
	struct v9fs_session_info *v9ses;
	struct p9_fid *fid;
	int omode;

	P9_DPRINTK(P9_DEBUG_VFS, "inode: %p file: %p\n", inode, file);
	v9inode = V9FS_I(inode);
	v9ses = v9fs_inode2v9ses(inode);
	if (v9fs_proto_dotl(v9ses))
		omode = file->f_flags;
	else
		omode = v9fs_uflags2omode(file->f_flags,
					v9fs_proto_dotu(v9ses));
	fid = file->private_data;
	if (!fid) {
		fid = v9fs_fid_clone(file->f_path.dentry);
		if (IS_ERR(fid))
			return PTR_ERR(fid);

		err = p9_client_open(fid, omode);
		if (err < 0) {
			p9_client_clunk(fid);
			return err;
		}
		if (file->f_flags & O_TRUNC) {
			i_size_write(inode, 0);
			inode->i_blocks = 0;
		}
		if ((file->f_flags & O_APPEND) &&
			(!v9fs_proto_dotu(v9ses) && !v9fs_proto_dotl(v9ses)))
			generic_file_llseek(file, 0, SEEK_END);
	}

	file->private_data = fid;
	if (v9ses->cache && !v9inode->writeback_fid) {
		/*
		 * clone a fid and add it to writeback_fid
		 * we do it during open time instead of
		 * page dirty time via write_begin/page_mkwrite
		 * because we want write after unlink usecase
		 * to work.
		 */
		fid = v9fs_writeback_fid(file->f_path.dentry);
		if (IS_ERR(fid)) {
			err = PTR_ERR(fid);
			goto out_error;
		}
		v9inode->writeback_fid = (void *) fid;
	}
#ifdef CONFIG_9P_FSCACHE
	if (v9ses->cache)
		v9fs_cache_inode_set_cookie(inode, file);
#endif
	return 0;
out_error:
	p9_client_clunk(file->private_data);
	file->private_data = NULL;
	return err;
}

/**
 * v9fs_file_lock - lock a file (or directory)
 * @filp: file to be locked
 * @cmd: lock command
 * @fl: file lock structure
 *
 * Bugs: this looks like a local only lock, we should extend into 9P
 *       by using open exclusive
 */

static int v9fs_file_lock(struct file *filp, int cmd, struct file_lock *fl)
{
	int res = 0;
	struct inode *inode = filp->f_path.dentry->d_inode;

	P9_DPRINTK(P9_DEBUG_VFS, "filp: %p lock: %p\n", filp, fl);

	/* No mandatory locks */
	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
		return -ENOLCK;

	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
		filemap_write_and_wait(inode->i_mapping);
		invalidate_mapping_pages(&inode->i_data, 0, -1);
	}

	return res;
}

static int v9fs_file_do_lock(struct file *filp, int cmd, struct file_lock *fl)
{
	struct p9_flock flock;
	struct p9_fid *fid;
	uint8_t status;
	int res = 0;
	unsigned char fl_type;

	fid = filp->private_data;
	BUG_ON(fid == NULL);

	if ((fl->fl_flags & FL_POSIX) != FL_POSIX)
		BUG();

	res = posix_lock_file_wait(filp, fl);
	if (res < 0)
		goto out;

	/* convert posix lock to p9 tlock args */
	memset(&flock, 0, sizeof(flock));
	flock.type = fl->fl_type;
	flock.start = fl->fl_start;
	if (fl->fl_end == OFFSET_MAX)
		flock.length = 0;
	else
		flock.length = fl->fl_end - fl->fl_start + 1;
	flock.proc_id = fl->fl_pid;
	flock.client_id = utsname()->nodename;
	if (IS_SETLKW(cmd))
		flock.flags = P9_LOCK_FLAGS_BLOCK;

	/*
	 * if its a blocked request and we get P9_LOCK_BLOCKED as the status
	 * for lock request, keep on trying
	 */
	for (;;) {
		res = p9_client_lock_dotl(fid, &flock, &status);
		if (res < 0)
			break;

		if (status != P9_LOCK_BLOCKED)
			break;
		if (status == P9_LOCK_BLOCKED && !IS_SETLKW(cmd))
			break;
		schedule_timeout_interruptible(P9_LOCK_TIMEOUT);
	}

	/* map 9p status to VFS status */
	switch (status) {
	case P9_LOCK_SUCCESS:
		res = 0;
		break;
	case P9_LOCK_BLOCKED:
		res = -EAGAIN;
		break;
	case P9_LOCK_ERROR:
	case P9_LOCK_GRACE:
		res = -ENOLCK;
		break;
	default:
		BUG();
	}

	/*
	 * incase server returned error for lock request, revert
	 * it locally
	 */
	if (res < 0 && fl->fl_type != F_UNLCK) {
		fl_type = fl->fl_type;
		fl->fl_type = F_UNLCK;
		res = posix_lock_file_wait(filp, fl);
		fl->fl_type = fl_type;
	}
out:
	return res;
}

static int v9fs_file_getlock(struct file *filp, struct file_lock *fl)
{
	struct p9_getlock glock;
	struct p9_fid *fid;
	int res = 0;

	fid = filp->private_data;
	BUG_ON(fid == NULL);

	posix_test_lock(filp, fl);
	/*
	 * if we have a conflicting lock locally, no need to validate
	 * with server
	 */
	if (fl->fl_type != F_UNLCK)
		return res;

	/* convert posix lock to p9 tgetlock args */
	memset(&glock, 0, sizeof(glock));
	glock.type = fl->fl_type;
	glock.start = fl->fl_start;
	if (fl->fl_end == OFFSET_MAX)
		glock.length = 0;
	else
		glock.length = fl->fl_end - fl->fl_start + 1;
	glock.proc_id = fl->fl_pid;
	glock.client_id = utsname()->nodename;

	res = p9_client_getlock_dotl(fid, &glock);
	if (res < 0)
		return res;
	if (glock.type != F_UNLCK) {
		fl->fl_type = glock.type;
		fl->fl_start = glock.start;
		if (glock.length == 0)
			fl->fl_end = OFFSET_MAX;
		else
			fl->fl_end = glock.start + glock.length - 1;
		fl->fl_pid = glock.proc_id;
	} else
		fl->fl_type = F_UNLCK;

	return res;
}

/**
 * v9fs_file_lock_dotl - lock a file (or directory)
 * @filp: file to be locked
 * @cmd: lock command
 * @fl: file lock structure
 *
 */

static int v9fs_file_lock_dotl(struct file *filp, int cmd, struct file_lock *fl)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	int ret = -ENOLCK;

	P9_DPRINTK(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %s\n", filp,
				cmd, fl, filp->f_path.dentry->d_name.name);

	/* No mandatory locks */
	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
		goto out_err;

	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
		filemap_write_and_wait(inode->i_mapping);
		invalidate_mapping_pages(&inode->i_data, 0, -1);
	}

	if (IS_SETLK(cmd) || IS_SETLKW(cmd))
		ret = v9fs_file_do_lock(filp, cmd, fl);
	else if (IS_GETLK(cmd))
		ret = v9fs_file_getlock(filp, fl);
	else
		ret = -EINVAL;
out_err:
	return ret;
}

/**
 * v9fs_file_flock_dotl - lock a file
 * @filp: file to be locked
 * @cmd: lock command
 * @fl: file lock structure
 *
 */

static int v9fs_file_flock_dotl(struct file *filp, int cmd,
	struct file_lock *fl)
{
	struct inode *inode = filp->f_path.dentry->d_inode;
	int ret = -ENOLCK;

	P9_DPRINTK(P9_DEBUG_VFS, "filp: %p cmd:%d lock: %p name: %s\n", filp,
				cmd, fl, filp->f_path.dentry->d_name.name);

	/* No mandatory locks */
	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
		goto out_err;

	if (!(fl->fl_flags & FL_FLOCK))
		goto out_err;

	if ((IS_SETLK(cmd) || IS_SETLKW(cmd)) && fl->fl_type != F_UNLCK) {
		filemap_write_and_wait(inode->i_mapping);
		invalidate_mapping_pages(&inode->i_data, 0, -1);
	}
	/* Convert flock to posix lock */
	fl->fl_owner = (fl_owner_t)filp;
	fl->fl_start = 0;
	fl->fl_end = OFFSET_MAX;
	fl->fl_flags |= FL_POSIX;
	fl->fl_flags ^= FL_FLOCK;

	if (IS_SETLK(cmd) | IS_SETLKW(cmd))
		ret = v9fs_file_do_lock(filp, cmd, fl);
	else
		ret = -EINVAL;
out_err:
	return ret;
}

/**
 * v9fs_fid_readn - read from a fid
 * @fid: fid to read
 * @data: data buffer to read data into
 * @udata: user data buffer to read data into
 * @count: size of buffer
 * @offset: offset at which to read data
 *
 */
ssize_t
v9fs_fid_readn(struct p9_fid *fid, char *data, char __user *udata, u32 count,
	       u64 offset)
{
	int n, total, size;

	P9_DPRINTK(P9_DEBUG_VFS, "fid %d offset %llu count %d\n", fid->fid,
		   (long long unsigned) offset, count);
	n = 0;
	total = 0;
	size = fid->iounit ? fid->iounit : fid->clnt->msize - P9_IOHDRSZ;
	do {
		n = p9_client_read(fid, data, udata, offset, count);
		if (n <= 0)
			break;

		if (data)
			data += n;
		if (udata)
			udata += n;

		offset += n;
		count -= n;
		total += n;
	} while (count > 0 && n == size);

	if (n < 0)
		total = n;

	return total;
}

/**
 * v9fs_file_readn - read from a file
 * @filp: file pointer to read
 * @data: data buffer to read data into
 * @udata: user data buffer to read data into
 * @count: size of buffer
 * @offset: offset at which to read data
 *
 */
ssize_t
v9fs_file_readn(struct file *filp, char *data, char __user *udata, u32 count,
	       u64 offset)
{
	return v9fs_fid_readn(filp->private_data, data, udata, count, offset);
}

/**
 * v9fs_file_read - read from a file
 * @filp: file pointer to read
 * @udata: user data buffer to read data into
 * @count: size of buffer
 * @offset: offset at which to read data
 *
 */

static ssize_t
v9fs_file_read(struct file *filp, char __user *udata, size_t count,
	       loff_t * offset)
{
	int ret;
	struct p9_fid *fid;
	size_t size;

	P9_DPRINTK(P9_DEBUG_VFS, "count %zu offset %lld\n", count, *offset);
	fid = filp->private_data;

	size = fid->iounit ? fid->iounit : fid->clnt->msize - P9_IOHDRSZ;
	if (count > size)
		ret = v9fs_file_readn(filp, NULL, udata, count, *offset);
	else
		ret = p9_client_read(fid, NULL, udata, *offset, count);

	if (ret > 0)
		*offset += ret;

	return ret;
}

ssize_t
v9fs_file_write_internal(struct inode *inode, struct p9_fid *fid,
			 const char __user *data, size_t count,
			 loff_t *offset, int invalidate)
{
	int n;
	size_t total = 0;
	struct p9_client *clnt;
	loff_t origin = *offset;
	unsigned long pg_start, pg_end;

	P9_DPRINTK(P9_DEBUG_VFS, "data %p count %d offset %x\n", data,
		(int)count, (int)*offset);

	clnt = fid->clnt;
	do {
		n = p9_client_write(fid, NULL, data+total, origin+total, count);
		if (n <= 0)
			break;
		count -= n;
		total += n;
	} while (count > 0);

	if (invalidate && (total > 0)) {
		pg_start = origin >> PAGE_CACHE_SHIFT;
		pg_end = (origin + total - 1) >> PAGE_CACHE_SHIFT;
		if (inode->i_mapping && inode->i_mapping->nrpages)
			invalidate_inode_pages2_range(inode->i_mapping,
						      pg_start, pg_end);
		*offset += total;
		i_size_write(inode, i_size_read(inode) + total);
		inode->i_blocks = (i_size_read(inode) + 512 - 1) >> 9;
	}
	if (n < 0)
		return n;

	return total;
}

/**
 * v9fs_file_write - write to a file
 * @filp: file pointer to write
 * @data: data buffer to write data from
 * @count: size of buffer
 * @offset: offset at which to write data
 *
 */
static ssize_t
v9fs_file_write(struct file *filp, const char __user * data,
		size_t count, loff_t *offset)
{
	ssize_t retval = 0;
	loff_t origin = *offset;


	retval = generic_write_checks(filp, &origin, &count, 0);
	if (retval)
		goto out;

	retval = -EINVAL;
	if ((ssize_t) count < 0)
		goto out;
	retval = 0;
	if (!count)
		goto out;

	return v9fs_file_write_internal(filp->f_path.dentry->d_inode,
					filp->private_data,
					data, count, offset, 1);
out:
	return retval;
}


static int v9fs_file_fsync(struct file *filp, int datasync)
{
	struct p9_fid *fid;
	struct p9_wstat wstat;
	int retval;

	P9_DPRINTK(P9_DEBUG_VFS, "filp %p datasync %x\n", filp, datasync);

	fid = filp->private_data;
	v9fs_blank_wstat(&wstat);

	retval = p9_client_wstat(fid, &wstat);
	return retval;
}

int v9fs_file_fsync_dotl(struct file *filp, int datasync)
{
	struct p9_fid *fid;
	int retval;

	P9_DPRINTK(P9_DEBUG_VFS, "v9fs_file_fsync_dotl: filp %p datasync %x\n",
			filp, datasync);

	fid = filp->private_data;

	retval = p9_client_fsync(fid, datasync);
	return retval;
}

static int
v9fs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	int retval;

	retval = generic_file_mmap(file, vma);
	if (!retval)
		vma->vm_ops = &v9fs_file_vm_ops;

	return retval;
}

static int
v9fs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct v9fs_inode *v9inode;
	struct page *page = vmf->page;
	struct file *filp = vma->vm_file;
	struct inode *inode = filp->f_path.dentry->d_inode;


	P9_DPRINTK(P9_DEBUG_VFS, "page %p fid %lx\n",
		   page, (unsigned long)filp->private_data);

	v9inode = V9FS_I(inode);
	/* make sure the cache has finished storing the page */
	v9fs_fscache_wait_on_page_write(inode, page);
	BUG_ON(!v9inode->writeback_fid);
	lock_page(page);
	if (page->mapping != inode->i_mapping)
		goto out_unlock;

	return VM_FAULT_LOCKED;
out_unlock:
	unlock_page(page);
	return VM_FAULT_NOPAGE;
}

static const struct vm_operations_struct v9fs_file_vm_ops = {
	.fault = filemap_fault,
	.page_mkwrite = v9fs_vm_page_mkwrite,
};

const struct file_operations v9fs_cached_file_operations = {
	.llseek = generic_file_llseek,
	.read = do_sync_read,
	.write = do_sync_write,
	.aio_read = generic_file_aio_read,
	.aio_write = generic_file_aio_write,
	.open = v9fs_file_open,
	.release = v9fs_dir_release,
	.lock = v9fs_file_lock,
	.mmap = v9fs_file_mmap,
	.fsync = v9fs_file_fsync,
};

const struct file_operations v9fs_cached_file_operations_dotl = {
	.llseek = generic_file_llseek,
	.read = do_sync_read,
	.write = do_sync_write,
	.aio_read = generic_file_aio_read,
	.aio_write = generic_file_aio_write,
	.open = v9fs_file_open,
	.release = v9fs_dir_release,
	.lock = v9fs_file_lock_dotl,
	.flock = v9fs_file_flock_dotl,
	.mmap = v9fs_file_mmap,
	.fsync = v9fs_file_fsync_dotl,
};

const struct file_operations v9fs_file_operations = {
	.llseek = generic_file_llseek,
	.read = v9fs_file_read,
	.write = v9fs_file_write,
	.open = v9fs_file_open,
	.release = v9fs_dir_release,
	.lock = v9fs_file_lock,
	.mmap = generic_file_readonly_mmap,
	.fsync = v9fs_file_fsync,
};

const struct file_operations v9fs_file_operations_dotl = {
	.llseek = generic_file_llseek,
	.read = v9fs_file_read,
	.write = v9fs_file_write,
	.open = v9fs_file_open,
	.release = v9fs_dir_release,
	.lock = v9fs_file_lock_dotl,
	.flock = v9fs_file_flock_dotl,
	.mmap = generic_file_readonly_mmap,
	.fsync = v9fs_file_fsync_dotl,
};