file.c 12.5 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
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
/*
 *  linux/fs/nfs/file.c
 *
 *  Copyright (C) 1992  Rick Sladkey
 *
 *  Changes Copyright (C) 1994 by Florian La Roche
 *   - Do not copy data too often around in the kernel.
 *   - In nfs_file_read the return value of kmalloc wasn't checked.
 *   - Put in a better version of read look-ahead buffering. Original idea
 *     and implementation by Wai S Kok elekokws@ee.nus.sg.
 *
 *  Expire cache on write to a file by Wai S Kok (Oct 1994).
 *
 *  Total rewrite of read side for new NFS buffer cache.. Linus.
 *
 *  nfs regular file handling functions
 */

#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/fcntl.h>
#include <linux/stat.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/smp_lock.h>

#include <asm/uaccess.h>
#include <asm/system.h>

#include "delegation.h"

#define NFSDBG_FACILITY		NFSDBG_FILE

static int nfs_file_open(struct inode *, struct file *);
static int nfs_file_release(struct inode *, struct file *);
static int  nfs_file_mmap(struct file *, struct vm_area_struct *);
static ssize_t nfs_file_sendfile(struct file *, loff_t *, size_t, read_actor_t, void *);
static ssize_t nfs_file_read(struct kiocb *, char __user *, size_t, loff_t);
static ssize_t nfs_file_write(struct kiocb *, const char __user *, size_t, loff_t);
static int  nfs_file_flush(struct file *);
static int  nfs_fsync(struct file *, struct dentry *dentry, int datasync);
static int nfs_check_flags(int flags);
static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl);
static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl);

struct file_operations nfs_file_operations = {
	.llseek		= remote_llseek,
	.read		= do_sync_read,
	.write		= do_sync_write,
	.aio_read		= nfs_file_read,
	.aio_write		= nfs_file_write,
	.mmap		= nfs_file_mmap,
	.open		= nfs_file_open,
	.flush		= nfs_file_flush,
	.release	= nfs_file_release,
	.fsync		= nfs_fsync,
	.lock		= nfs_lock,
	.flock		= nfs_flock,
	.sendfile	= nfs_file_sendfile,
	.check_flags	= nfs_check_flags,
};

struct inode_operations nfs_file_inode_operations = {
	.permission	= nfs_permission,
	.getattr	= nfs_getattr,
	.setattr	= nfs_setattr,
};

/* Hack for future NFS swap support */
#ifndef IS_SWAPFILE
# define IS_SWAPFILE(inode)	(0)
#endif

static int nfs_check_flags(int flags)
{
	if ((flags & (O_APPEND | O_DIRECT)) == (O_APPEND | O_DIRECT))
		return -EINVAL;

	return 0;
}

/*
 * Open file
 */
static int
nfs_file_open(struct inode *inode, struct file *filp)
{
	struct nfs_server *server = NFS_SERVER(inode);
	int (*open)(struct inode *, struct file *);
	int res;

	res = nfs_check_flags(filp->f_flags);
	if (res)
		return res;

	lock_kernel();
	/* Do NFSv4 open() call */
	if ((open = server->rpc_ops->file_open) != NULL)
		res = open(inode, filp);
	unlock_kernel();
	return res;
}

static int
nfs_file_release(struct inode *inode, struct file *filp)
{
	/* Ensure that dirty pages are flushed out with the right creds */
	if (filp->f_mode & FMODE_WRITE)
		filemap_fdatawrite(filp->f_mapping);
	return NFS_PROTO(inode)->file_release(inode, filp);
}

/*
 * Flush all dirty pages, and check for write errors.
 *
 */
static int
nfs_file_flush(struct file *file)
{
	struct nfs_open_context *ctx = (struct nfs_open_context *)file->private_data;
	struct inode	*inode = file->f_dentry->d_inode;
	int		status;

	dfprintk(VFS, "nfs: flush(%s/%ld)\n", inode->i_sb->s_id, inode->i_ino);

	if ((file->f_mode & FMODE_WRITE) == 0)
		return 0;
	lock_kernel();
	/* Ensure that data+attribute caches are up to date after close() */
	status = nfs_wb_all(inode);
	if (!status) {
		status = ctx->error;
		ctx->error = 0;
		if (!status && !nfs_have_delegation(inode, FMODE_READ))
			__nfs_revalidate_inode(NFS_SERVER(inode), inode);
	}
	unlock_kernel();
	return status;
}

static ssize_t
nfs_file_read(struct kiocb *iocb, char __user * buf, size_t count, loff_t pos)
{
	struct dentry * dentry = iocb->ki_filp->f_dentry;
	struct inode * inode = dentry->d_inode;
	ssize_t result;

#ifdef CONFIG_NFS_DIRECTIO
	if (iocb->ki_filp->f_flags & O_DIRECT)
		return nfs_file_direct_read(iocb, buf, count, pos);
#endif

	dfprintk(VFS, "nfs: read(%s/%s, %lu@%lu)\n",
		dentry->d_parent->d_name.name, dentry->d_name.name,
		(unsigned long) count, (unsigned long) pos);

	result = nfs_revalidate_inode(NFS_SERVER(inode), inode);
	if (!result)
		result = generic_file_aio_read(iocb, buf, count, pos);
	return result;
}

static ssize_t
nfs_file_sendfile(struct file *filp, loff_t *ppos, size_t count,
		read_actor_t actor, void *target)
{
	struct dentry *dentry = filp->f_dentry;
	struct inode *inode = dentry->d_inode;
	ssize_t res;

	dfprintk(VFS, "nfs: sendfile(%s/%s, %lu@%Lu)\n",
		dentry->d_parent->d_name.name, dentry->d_name.name,
		(unsigned long) count, (unsigned long long) *ppos);

	res = nfs_revalidate_inode(NFS_SERVER(inode), inode);
	if (!res)
		res = generic_file_sendfile(filp, ppos, count, actor, target);
	return res;
}

static int
nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
{
	struct dentry *dentry = file->f_dentry;
	struct inode *inode = dentry->d_inode;
	int	status;

	dfprintk(VFS, "nfs: mmap(%s/%s)\n",
		dentry->d_parent->d_name.name, dentry->d_name.name);

	status = nfs_revalidate_inode(NFS_SERVER(inode), inode);
	if (!status)
		status = generic_file_mmap(file, vma);
	return status;
}

/*
 * Flush any dirty pages for this process, and check for write errors.
 * The return status from this call provides a reliable indication of
 * whether any write errors occurred for this process.
 */
static int
nfs_fsync(struct file *file, struct dentry *dentry, int datasync)
{
	struct nfs_open_context *ctx = (struct nfs_open_context *)file->private_data;
	struct inode *inode = dentry->d_inode;
	int status;

	dfprintk(VFS, "nfs: fsync(%s/%ld)\n", inode->i_sb->s_id, inode->i_ino);

	lock_kernel();
	status = nfs_wb_all(inode);
	if (!status) {
		status = ctx->error;
		ctx->error = 0;
	}
	unlock_kernel();
	return status;
}

/*
 * This does the "real" work of the write. The generic routine has
 * allocated the page, locked it, done all the page alignment stuff
 * calculations etc. Now we should just copy the data from user
 * space and write it back to the real medium..
 *
 * If the writer ends up delaying the write, the writer needs to
 * increment the page use counts until he is done with the page.
 */
static int nfs_prepare_write(struct file *file, struct page *page, unsigned offset, unsigned to)
{
	return nfs_flush_incompatible(file, page);
}

static int nfs_commit_write(struct file *file, struct page *page, unsigned offset, unsigned to)
{
	long status;

	lock_kernel();
	status = nfs_updatepage(file, page, offset, to-offset);
	unlock_kernel();
	return status;
}

struct address_space_operations nfs_file_aops = {
	.readpage = nfs_readpage,
	.readpages = nfs_readpages,
	.set_page_dirty = __set_page_dirty_nobuffers,
	.writepage = nfs_writepage,
	.writepages = nfs_writepages,
	.prepare_write = nfs_prepare_write,
	.commit_write = nfs_commit_write,
#ifdef CONFIG_NFS_DIRECTIO
	.direct_IO = nfs_direct_IO,
#endif
};

/* 
 * Write to a file (through the page cache).
 */
static ssize_t
nfs_file_write(struct kiocb *iocb, const char __user *buf, size_t count, loff_t pos)
{
	struct dentry * dentry = iocb->ki_filp->f_dentry;
	struct inode * inode = dentry->d_inode;
	ssize_t result;

#ifdef CONFIG_NFS_DIRECTIO
	if (iocb->ki_filp->f_flags & O_DIRECT)
		return nfs_file_direct_write(iocb, buf, count, pos);
#endif

	dfprintk(VFS, "nfs: write(%s/%s(%ld), %lu@%lu)\n",
		dentry->d_parent->d_name.name, dentry->d_name.name,
		inode->i_ino, (unsigned long) count, (unsigned long) pos);

	result = -EBUSY;
	if (IS_SWAPFILE(inode))
		goto out_swapfile;
	result = nfs_revalidate_inode(NFS_SERVER(inode), inode);
	if (result)
		goto out;

	result = count;
	if (!count)
		goto out;

	result = generic_file_aio_write(iocb, buf, count, pos);
out:
	return result;

out_swapfile:
	printk(KERN_INFO "NFS: attempt to write to active swap file!\n");
	goto out;
}

static int do_getlk(struct file *filp, int cmd, struct file_lock *fl)
{
	struct inode *inode = filp->f_mapping->host;
	int status = 0;

	lock_kernel();
	/* Use local locking if mounted with "-onolock" */
	if (!(NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM))
		status = NFS_PROTO(inode)->lock(filp, cmd, fl);
	else {
		struct file_lock *cfl = posix_test_lock(filp, fl);

		fl->fl_type = F_UNLCK;
		if (cfl != NULL)
			memcpy(fl, cfl, sizeof(*fl));
	}
	unlock_kernel();
	return status;
}

static int do_vfs_lock(struct file *file, struct file_lock *fl)
{
	int res = 0;
	switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) {
		case FL_POSIX:
			res = posix_lock_file_wait(file, fl);
			break;
		case FL_FLOCK:
			res = flock_lock_file_wait(file, fl);
			break;
		default:
			BUG();
	}
	if (res < 0)
		printk(KERN_WARNING "%s: VFS is out of sync with lock manager!\n",
				__FUNCTION__);
	return res;
}

static int do_unlk(struct file *filp, int cmd, struct file_lock *fl)
{
	struct inode *inode = filp->f_mapping->host;
	sigset_t oldset;
	int status;

	rpc_clnt_sigmask(NFS_CLIENT(inode), &oldset);
	/*
	 * Flush all pending writes before doing anything
	 * with locks..
	 */
	filemap_fdatawrite(filp->f_mapping);
	down(&inode->i_sem);
	nfs_wb_all(inode);
	up(&inode->i_sem);
	filemap_fdatawait(filp->f_mapping);

	/* NOTE: special case
	 * 	If we're signalled while cleaning up locks on process exit, we
	 * 	still need to complete the unlock.
	 */
	lock_kernel();
	/* Use local locking if mounted with "-onolock" */
	if (!(NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM))
		status = NFS_PROTO(inode)->lock(filp, cmd, fl);
	else
		status = do_vfs_lock(filp, fl);
	unlock_kernel();
	rpc_clnt_sigunmask(NFS_CLIENT(inode), &oldset);
	return status;
}

static int do_setlk(struct file *filp, int cmd, struct file_lock *fl)
{
	struct inode *inode = filp->f_mapping->host;
	sigset_t oldset;
	int status;

	rpc_clnt_sigmask(NFS_CLIENT(inode), &oldset);
	/*
	 * Flush all pending writes before doing anything
	 * with locks..
	 */
	status = filemap_fdatawrite(filp->f_mapping);
	if (status == 0) {
		down(&inode->i_sem);
		status = nfs_wb_all(inode);
		up(&inode->i_sem);
		if (status == 0)
			status = filemap_fdatawait(filp->f_mapping);
	}
	if (status < 0)
		goto out;

	lock_kernel();
	/* Use local locking if mounted with "-onolock" */
	if (!(NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM)) {
		status = NFS_PROTO(inode)->lock(filp, cmd, fl);
		/* If we were signalled we still need to ensure that
		 * we clean up any state on the server. We therefore
		 * record the lock call as having succeeded in order to
		 * ensure that locks_remove_posix() cleans it out when
		 * the process exits.
		 */
		if (status == -EINTR || status == -ERESTARTSYS)
			do_vfs_lock(filp, fl);
	} else
		status = do_vfs_lock(filp, fl);
	unlock_kernel();
	if (status < 0)
		goto out;
	/*
	 * Make sure we clear the cache whenever we try to get the lock.
	 * This makes locking act as a cache coherency point.
	 */
	filemap_fdatawrite(filp->f_mapping);
	down(&inode->i_sem);
	nfs_wb_all(inode);	/* we may have slept */
	up(&inode->i_sem);
	filemap_fdatawait(filp->f_mapping);
	nfs_zap_caches(inode);
out:
	rpc_clnt_sigunmask(NFS_CLIENT(inode), &oldset);
	return status;
}

/*
 * Lock a (portion of) a file
 */
static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
{
	struct inode * inode = filp->f_mapping->host;

	dprintk("NFS: nfs_lock(f=%s/%ld, t=%x, fl=%x, r=%Ld:%Ld)\n",
			inode->i_sb->s_id, inode->i_ino,
			fl->fl_type, fl->fl_flags,
			(long long)fl->fl_start, (long long)fl->fl_end);

	if (!inode)
		return -EINVAL;

	/* No mandatory locks over NFS */
	if ((inode->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID)
		return -ENOLCK;

	if (IS_GETLK(cmd))
		return do_getlk(filp, cmd, fl);
	if (fl->fl_type == F_UNLCK)
		return do_unlk(filp, cmd, fl);
	return do_setlk(filp, cmd, fl);
}

/*
 * Lock a (portion of) a file
 */
static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
{
	struct inode * inode = filp->f_mapping->host;

	dprintk("NFS: nfs_flock(f=%s/%ld, t=%x, fl=%x)\n",
			inode->i_sb->s_id, inode->i_ino,
			fl->fl_type, fl->fl_flags);

	if (!inode)
		return -EINVAL;

	/*
	 * No BSD flocks over NFS allowed.
	 * Note: we could try to fake a POSIX lock request here by
	 * using ((u32) filp | 0x80000000) or some such as the pid.
	 * Not sure whether that would be unique, though, or whether
	 * that would break in other places.
	 */
	if (!(fl->fl_flags & FL_FLOCK))
		return -ENOLCK;

	/* We're simulating flock() locks using posix locks on the server */
	fl->fl_owner = (fl_owner_t)filp;
	fl->fl_start = 0;
	fl->fl_end = OFFSET_MAX;

	if (fl->fl_type == F_UNLCK)
		return do_unlk(filp, cmd, fl);
	return do_setlk(filp, cmd, fl);
}