inode.c 56.6 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
/*
 *  linux/fs/nfs/inode.c
 *
 *  Copyright (C) 1992  Rick Sladkey
 *
 *  nfs inode and superblock handling functions
 *
 *  Modularised by Alan Cox <Alan.Cox@linux.org>, while hacking some
 *  experimental NFS changes. Modularisation taken straight from SYS5 fs.
 *
 *  Change to nfs_read_super() to permit NFS mounts to multi-homed hosts.
 *  J.S.Peatfield@damtp.cam.ac.uk
 *
 */

#include <linux/config.h>
#include <linux/module.h>
#include <linux/init.h>

#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/errno.h>
#include <linux/unistd.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/stats.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include <linux/nfs4_mount.h>
#include <linux/lockd/bind.h>
#include <linux/smp_lock.h>
#include <linux/seq_file.h>
#include <linux/mount.h>
#include <linux/nfs_idmap.h>
#include <linux/vfs.h>

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

42
#include "nfs4_fs.h"
Linus Torvalds's avatar
Linus Torvalds committed
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
#include "delegation.h"

#define NFSDBG_FACILITY		NFSDBG_VFS
#define NFS_PARANOIA 1

/* Maximum number of readahead requests
 * FIXME: this should really be a sysctl so that users may tune it to suit
 *        their needs. People that do NFS over a slow network, might for
 *        instance want to reduce it to something closer to 1 for improved
 *        interactive response.
 */
#define NFS_MAX_READAHEAD	(RPC_DEF_SLOT_TABLE - 1)

static void nfs_invalidate_inode(struct inode *);
static int nfs_update_inode(struct inode *, struct nfs_fattr *, unsigned long);

static struct inode *nfs_alloc_inode(struct super_block *sb);
static void nfs_destroy_inode(struct inode *);
static int nfs_write_inode(struct inode *,int);
static void nfs_delete_inode(struct inode *);
static void nfs_clear_inode(struct inode *);
static void nfs_umount_begin(struct super_block *);
static int  nfs_statfs(struct super_block *, struct kstatfs *);
static int  nfs_show_options(struct seq_file *, struct vfsmount *);
67
static void nfs_zap_acl_cache(struct inode *);
Linus Torvalds's avatar
Linus Torvalds committed
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

static struct rpc_program	nfs_program;

static struct super_operations nfs_sops = { 
	.alloc_inode	= nfs_alloc_inode,
	.destroy_inode	= nfs_destroy_inode,
	.write_inode	= nfs_write_inode,
	.delete_inode	= nfs_delete_inode,
	.statfs		= nfs_statfs,
	.clear_inode	= nfs_clear_inode,
	.umount_begin	= nfs_umount_begin,
	.show_options	= nfs_show_options,
};

/*
 * RPC cruft for NFS
 */
static struct rpc_stat		nfs_rpcstat = {
	.program		= &nfs_program
};
static struct rpc_version *	nfs_version[] = {
	NULL,
	NULL,
	&nfs_version2,
#if defined(CONFIG_NFS_V3)
	&nfs_version3,
#elif defined(CONFIG_NFS_V4)
	NULL,
#endif
#if defined(CONFIG_NFS_V4)
	&nfs_version4,
#endif
};

static struct rpc_program	nfs_program = {
	.name			= "nfs",
	.number			= NFS_PROGRAM,
	.nrvers			= sizeof(nfs_version) / sizeof(nfs_version[0]),
	.version		= nfs_version,
	.stats			= &nfs_rpcstat,
	.pipe_dir_name		= "/nfs",
};

111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
#ifdef CONFIG_NFS_V3_ACL
static struct rpc_stat		nfsacl_rpcstat = { &nfsacl_program };
static struct rpc_version *	nfsacl_version[] = {
	[3]			= &nfsacl_version3,
};

struct rpc_program		nfsacl_program = {
	.name =			"nfsacl",
	.number =		NFS_ACL_PROGRAM,
	.nrvers =		sizeof(nfsacl_version) / sizeof(nfsacl_version[0]),
	.version =		nfsacl_version,
	.stats =		&nfsacl_rpcstat,
};
#endif  /* CONFIG_NFS_V3_ACL */

Linus Torvalds's avatar
Linus Torvalds committed
126
127
128
129
130
131
132
133
134
135
136
137
static inline unsigned long
nfs_fattr_to_ino_t(struct nfs_fattr *fattr)
{
	return nfs_fileid_to_ino_t(fattr->fileid);
}

static int
nfs_write_inode(struct inode *inode, int sync)
{
	int flags = sync ? FLUSH_WAIT : 0;
	int ret;

138
	ret = nfs_commit_inode(inode, flags);
Linus Torvalds's avatar
Linus Torvalds committed
139
140
141
142
143
144
145
146
147
148
	if (ret < 0)
		return ret;
	return 0;
}

static void
nfs_delete_inode(struct inode * inode)
{
	dprintk("NFS: delete_inode(%s/%ld)\n", inode->i_sb->s_id, inode->i_ino);

149
150
	truncate_inode_pages(&inode->i_data, 0);

Linus Torvalds's avatar
Linus Torvalds committed
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
	nfs_wb_all(inode);
	/*
	 * The following should never happen...
	 */
	if (nfs_have_writebacks(inode)) {
		printk(KERN_ERR "nfs_delete_inode: inode %ld has pending RPC requests\n", inode->i_ino);
	}

	clear_inode(inode);
}

static void
nfs_clear_inode(struct inode *inode)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	struct rpc_cred *cred;

	nfs_wb_all(inode);
	BUG_ON (!list_empty(&nfsi->open_files));
170
	nfs_zap_acl_cache(inode);
Linus Torvalds's avatar
Linus Torvalds committed
171
172
173
174
175
176
177
178
179
	cred = nfsi->cache_access.cred;
	if (cred)
		put_rpccred(cred);
	BUG_ON(atomic_read(&nfsi->data_updates) != 0);
}

void
nfs_umount_begin(struct super_block *sb)
{
180
	struct rpc_clnt	*rpc = NFS_SB(sb)->client;
Linus Torvalds's avatar
Linus Torvalds committed
181
182

	/* -EIO all pending I/O */
183
	if (!IS_ERR(rpc))
Linus Torvalds's avatar
Linus Torvalds committed
184
		rpc_killall_tasks(rpc);
185
186
187
	rpc = NFS_SB(sb)->client_acl;
	if (!IS_ERR(rpc))
		rpc_killall_tasks(rpc);
Linus Torvalds's avatar
Linus Torvalds committed
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
}


static inline unsigned long
nfs_block_bits(unsigned long bsize, unsigned char *nrbitsp)
{
	/* make sure blocksize is a power of two */
	if ((bsize & (bsize - 1)) || nrbitsp) {
		unsigned char	nrbits;

		for (nrbits = 31; nrbits && !(bsize & (1 << nrbits)); nrbits--)
			;
		bsize = 1 << nrbits;
		if (nrbitsp)
			*nrbitsp = nrbits;
	}

	return bsize;
}

/*
 * Calculate the number of 512byte blocks used.
 */
static inline unsigned long
nfs_calc_block_size(u64 tsize)
{
	loff_t used = (tsize + 511) >> 9;
	return (used > ULONG_MAX) ? ULONG_MAX : used;
}

/*
 * Compute and set NFS server blocksize
 */
static inline unsigned long
nfs_block_size(unsigned long bsize, unsigned char *nrbitsp)
{
	if (bsize < 1024)
		bsize = NFS_DEF_FILE_IO_BUFFER_SIZE;
	else if (bsize >= NFS_MAX_FILE_IO_BUFFER_SIZE)
		bsize = NFS_MAX_FILE_IO_BUFFER_SIZE;

	return nfs_block_bits(bsize, nrbitsp);
}

/*
 * Obtain the root inode of the file system.
 */
static struct inode *
nfs_get_root(struct super_block *sb, struct nfs_fh *rootfh, struct nfs_fsinfo *fsinfo)
{
	struct nfs_server	*server = NFS_SB(sb);
	struct inode *rooti;
	int			error;

	error = server->rpc_ops->getroot(server, rootfh, fsinfo);
	if (error < 0) {
		dprintk("nfs_get_root: getattr error = %d\n", -error);
		return ERR_PTR(error);
	}

	rooti = nfs_fhget(sb, rootfh, fsinfo->fattr);
	if (!rooti)
		return ERR_PTR(-ENOMEM);
	return rooti;
}

/*
 * Do NFS version-independent mount processing, and sanity checking
 */
static int
nfs_sb_init(struct super_block *sb, rpc_authflavor_t authflavor)
{
	struct nfs_server	*server;
	struct inode		*root_inode;
	struct nfs_fattr	fattr;
	struct nfs_fsinfo	fsinfo = {
					.fattr = &fattr,
				};
	struct nfs_pathconf pathinfo = {
			.fattr = &fattr,
	};
	int no_root_error = 0;
	unsigned long max_rpc_payload;

	/* We probably want something more informative here */
	snprintf(sb->s_id, sizeof(sb->s_id), "%x:%x", MAJOR(sb->s_dev), MINOR(sb->s_dev));

	server = NFS_SB(sb);

	sb->s_magic      = NFS_SUPER_MAGIC;

	root_inode = nfs_get_root(sb, &server->fh, &fsinfo);
	/* Did getting the root inode fail? */
	if (IS_ERR(root_inode)) {
		no_root_error = PTR_ERR(root_inode);
		goto out_no_root;
	}
	sb->s_root = d_alloc_root(root_inode);
	if (!sb->s_root) {
		no_root_error = -ENOMEM;
		goto out_no_root;
	}
	sb->s_root->d_op = server->rpc_ops->dentry_ops;

	/* Get some general file system info */
	if (server->namelen == 0 &&
	    server->rpc_ops->pathconf(server, &server->fh, &pathinfo) >= 0)
		server->namelen = pathinfo.max_namelen;
	/* Work out a lot of parameters */
	if (server->rsize == 0)
		server->rsize = nfs_block_size(fsinfo.rtpref, NULL);
	if (server->wsize == 0)
		server->wsize = nfs_block_size(fsinfo.wtpref, NULL);

	if (fsinfo.rtmax >= 512 && server->rsize > fsinfo.rtmax)
		server->rsize = nfs_block_size(fsinfo.rtmax, NULL);
	if (fsinfo.wtmax >= 512 && server->wsize > fsinfo.wtmax)
		server->wsize = nfs_block_size(fsinfo.wtmax, NULL);

	max_rpc_payload = nfs_block_size(rpc_max_payload(server->client), NULL);
	if (server->rsize > max_rpc_payload)
		server->rsize = max_rpc_payload;
	if (server->wsize > max_rpc_payload)
		server->wsize = max_rpc_payload;

	server->rpages = (server->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
	if (server->rpages > NFS_READ_MAXIOV) {
		server->rpages = NFS_READ_MAXIOV;
		server->rsize = server->rpages << PAGE_CACHE_SHIFT;
	}

	server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
        if (server->wpages > NFS_WRITE_MAXIOV) {
		server->wpages = NFS_WRITE_MAXIOV;
                server->wsize = server->wpages << PAGE_CACHE_SHIFT;
	}

	if (sb->s_blocksize == 0)
		sb->s_blocksize = nfs_block_bits(server->wsize,
							 &sb->s_blocksize_bits);
	server->wtmult = nfs_block_bits(fsinfo.wtmult, NULL);

	server->dtsize = nfs_block_size(fsinfo.dtpref, NULL);
	if (server->dtsize > PAGE_CACHE_SIZE)
		server->dtsize = PAGE_CACHE_SIZE;
	if (server->dtsize > server->rsize)
		server->dtsize = server->rsize;

	if (server->flags & NFS_MOUNT_NOAC) {
		server->acregmin = server->acregmax = 0;
		server->acdirmin = server->acdirmax = 0;
		sb->s_flags |= MS_SYNCHRONOUS;
	}
	server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD;

	sb->s_maxbytes = fsinfo.maxfilesize;
	if (sb->s_maxbytes > MAX_LFS_FILESIZE) 
		sb->s_maxbytes = MAX_LFS_FILESIZE; 

	server->client->cl_intr = (server->flags & NFS_MOUNT_INTR) ? 1 : 0;
	server->client->cl_softrtry = (server->flags & NFS_MOUNT_SOFT) ? 1 : 0;

	/* We're airborne Set socket buffersize */
	rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100);
	return 0;
	/* Yargs. It didn't work out. */
out_no_root:
	dprintk("nfs_sb_init: get root inode failed: errno %d\n", -no_root_error);
	if (!IS_ERR(root_inode))
		iput(root_inode);
	return no_root_error;
}

/*
 * Create an RPC client handle.
 */
static struct rpc_clnt *
nfs_create_client(struct nfs_server *server, const struct nfs_mount_data *data)
{
	struct rpc_timeout	timeparms;
	struct rpc_xprt		*xprt = NULL;
	struct rpc_clnt		*clnt = NULL;
	int			tcp   = (data->flags & NFS_MOUNT_TCP);

	/* Initialize timeout values */
	timeparms.to_initval = data->timeo * HZ / 10;
	timeparms.to_retries = data->retrans;
	timeparms.to_maxval  = tcp ? RPC_MAX_TCP_TIMEOUT : RPC_MAX_UDP_TIMEOUT;
	timeparms.to_exponential = 1;

	if (!timeparms.to_initval)
		timeparms.to_initval = (tcp ? 600 : 11) * HZ / 10;
	if (!timeparms.to_retries)
		timeparms.to_retries = 5;

	/* create transport and client */
	xprt = xprt_create_proto(tcp ? IPPROTO_TCP : IPPROTO_UDP,
				 &server->addr, &timeparms);
	if (IS_ERR(xprt)) {
387
388
		dprintk("%s: cannot create RPC transport. Error = %ld\n",
				__FUNCTION__, PTR_ERR(xprt));
Linus Torvalds's avatar
Linus Torvalds committed
389
390
391
392
393
		return (struct rpc_clnt *)xprt;
	}
	clnt = rpc_create_client(xprt, server->hostname, &nfs_program,
				 server->rpc_ops->version, data->pseudoflavor);
	if (IS_ERR(clnt)) {
394
395
		dprintk("%s: cannot create RPC client. Error = %ld\n",
				__FUNCTION__, PTR_ERR(xprt));
Linus Torvalds's avatar
Linus Torvalds committed
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
		goto out_fail;
	}

	clnt->cl_intr     = 1;
	clnt->cl_softrtry = 1;
	clnt->cl_chatty   = 1;

	return clnt;

out_fail:
	return clnt;
}

/*
 * The way this works is that the mount process passes a structure
 * in the data argument which contains the server's IP address
 * and the root file handle obtained from the server's mount
 * daemon. We stash these away in the private superblock fields.
 */
static int
nfs_fill_super(struct super_block *sb, struct nfs_mount_data *data, int silent)
{
	struct nfs_server	*server;
	rpc_authflavor_t	authflavor;

	server           = NFS_SB(sb);
	sb->s_blocksize_bits = 0;
	sb->s_blocksize = 0;
	if (data->bsize)
		sb->s_blocksize = nfs_block_size(data->bsize, &sb->s_blocksize_bits);
	if (data->rsize)
		server->rsize = nfs_block_size(data->rsize, NULL);
	if (data->wsize)
		server->wsize = nfs_block_size(data->wsize, NULL);
	server->flags    = data->flags & NFS_MOUNT_FLAGMASK;

	server->acregmin = data->acregmin*HZ;
	server->acregmax = data->acregmax*HZ;
	server->acdirmin = data->acdirmin*HZ;
	server->acdirmax = data->acdirmax*HZ;

	/* Start lockd here, before we might error out */
	if (!(server->flags & NFS_MOUNT_NONLM))
		lockd_up();

	server->namelen  = data->namlen;
	server->hostname = kmalloc(strlen(data->hostname) + 1, GFP_KERNEL);
	if (!server->hostname)
		return -ENOMEM;
	strcpy(server->hostname, data->hostname);

	/* Check NFS protocol revision and initialize RPC op vector
	 * and file handle pool. */
#ifdef CONFIG_NFS_V3
450
	if (server->flags & NFS_MOUNT_VER3) {
Linus Torvalds's avatar
Linus Torvalds committed
451
452
453
454
455
		server->rpc_ops = &nfs_v3_clientops;
		server->caps |= NFS_CAP_READDIRPLUS;
	} else {
		server->rpc_ops = &nfs_v2_clientops;
	}
456
457
458
#else
	server->rpc_ops = &nfs_v2_clientops;
#endif
Linus Torvalds's avatar
Linus Torvalds committed
459
460
461
462
463
464
465
466
467
468
469
470
471

	/* Fill in pseudoflavor for mount version < 5 */
	if (!(data->flags & NFS_MOUNT_SECFLAVOUR))
		data->pseudoflavor = RPC_AUTH_UNIX;
	authflavor = data->pseudoflavor;	/* save for sb_init() */
	/* XXX maybe we want to add a server->pseudoflavor field */

	/* Create RPC client handles */
	server->client = nfs_create_client(server, data);
	if (IS_ERR(server->client))
		return PTR_ERR(server->client);
	/* RFC 2623, sec 2.3.2 */
	if (authflavor != RPC_AUTH_UNIX) {
472
473
		struct rpc_auth *auth;

Linus Torvalds's avatar
Linus Torvalds committed
474
475
476
		server->client_sys = rpc_clone_client(server->client);
		if (IS_ERR(server->client_sys))
			return PTR_ERR(server->client_sys);
477
478
479
		auth = rpcauth_create(RPC_AUTH_UNIX, server->client_sys);
		if (IS_ERR(auth))
			return PTR_ERR(auth);
Linus Torvalds's avatar
Linus Torvalds committed
480
481
482
483
484
	} else {
		atomic_inc(&server->client->cl_count);
		server->client_sys = server->client;
	}
	if (server->flags & NFS_MOUNT_VER3) {
485
486
487
488
489
490
491
492
493
494
#ifdef CONFIG_NFS_V3_ACL
		if (!(server->flags & NFS_MOUNT_NOACL)) {
			server->client_acl = rpc_bind_new_program(server->client, &nfsacl_program, 3);
			/* No errors! Assume that Sun nfsacls are supported */
			if (!IS_ERR(server->client_acl))
				server->caps |= NFS_CAP_ACLS;
		}
#else
		server->flags &= ~NFS_MOUNT_NOACL;
#endif /* CONFIG_NFS_V3_ACL */
495
496
497
498
499
		/*
		 * The VFS shouldn't apply the umask to mode bits. We will
		 * do so ourselves when necessary.
		 */
		sb->s_flags |= MS_POSIXACL;
Linus Torvalds's avatar
Linus Torvalds committed
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
		if (server->namelen == 0 || server->namelen > NFS3_MAXNAMLEN)
			server->namelen = NFS3_MAXNAMLEN;
		sb->s_time_gran = 1;
	} else {
		if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN)
			server->namelen = NFS2_MAXNAMLEN;
	}

	sb->s_op = &nfs_sops;
	return nfs_sb_init(sb, authflavor);
}

static int
nfs_statfs(struct super_block *sb, struct kstatfs *buf)
{
	struct nfs_server *server = NFS_SB(sb);
	unsigned char blockbits;
	unsigned long blockres;
	struct nfs_fh *rootfh = NFS_FH(sb->s_root->d_inode);
	struct nfs_fattr fattr;
	struct nfs_fsstat res = {
			.fattr = &fattr,
	};
	int error;

	lock_kernel();

	error = server->rpc_ops->statfs(server, rootfh, &res);
	buf->f_type = NFS_SUPER_MAGIC;
	if (error < 0)
		goto out_err;

	/*
	 * Current versions of glibc do not correctly handle the
	 * case where f_frsize != f_bsize.  Eventually we want to
	 * report the value of wtmult in this field.
	 */
	buf->f_frsize = sb->s_blocksize;

	/*
	 * On most *nix systems, f_blocks, f_bfree, and f_bavail
	 * are reported in units of f_frsize.  Linux hasn't had
	 * an f_frsize field in its statfs struct until recently,
	 * thus historically Linux's sys_statfs reports these
	 * fields in units of f_bsize.
	 */
	buf->f_bsize = sb->s_blocksize;
	blockbits = sb->s_blocksize_bits;
	blockres = (1 << blockbits) - 1;
	buf->f_blocks = (res.tbytes + blockres) >> blockbits;
	buf->f_bfree = (res.fbytes + blockres) >> blockbits;
	buf->f_bavail = (res.abytes + blockres) >> blockbits;

	buf->f_files = res.tfiles;
	buf->f_ffree = res.afiles;

	buf->f_namelen = server->namelen;
 out:
	unlock_kernel();

	return 0;

 out_err:
	printk(KERN_WARNING "nfs_statfs: statfs error = %d\n", -error);
	buf->f_bsize = buf->f_blocks = buf->f_bfree = buf->f_bavail = -1;
	goto out;

}

static int nfs_show_options(struct seq_file *m, struct vfsmount *mnt)
{
	static struct proc_nfs_info {
		int flag;
		char *str;
		char *nostr;
	} nfs_info[] = {
		{ NFS_MOUNT_SOFT, ",soft", ",hard" },
		{ NFS_MOUNT_INTR, ",intr", "" },
		{ NFS_MOUNT_POSIX, ",posix", "" },
		{ NFS_MOUNT_TCP, ",tcp", ",udp" },
		{ NFS_MOUNT_NOCTO, ",nocto", "" },
		{ NFS_MOUNT_NOAC, ",noac", "" },
		{ NFS_MOUNT_NONLM, ",nolock", ",lock" },
583
		{ NFS_MOUNT_NOACL, ",noacl", "" },
Linus Torvalds's avatar
Linus Torvalds 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
		{ 0, NULL, NULL }
	};
	struct proc_nfs_info *nfs_infop;
	struct nfs_server *nfss = NFS_SB(mnt->mnt_sb);

	seq_printf(m, ",v%d", nfss->rpc_ops->version);
	seq_printf(m, ",rsize=%d", nfss->rsize);
	seq_printf(m, ",wsize=%d", nfss->wsize);
	if (nfss->acregmin != 3*HZ)
		seq_printf(m, ",acregmin=%d", nfss->acregmin/HZ);
	if (nfss->acregmax != 60*HZ)
		seq_printf(m, ",acregmax=%d", nfss->acregmax/HZ);
	if (nfss->acdirmin != 30*HZ)
		seq_printf(m, ",acdirmin=%d", nfss->acdirmin/HZ);
	if (nfss->acdirmax != 60*HZ)
		seq_printf(m, ",acdirmax=%d", nfss->acdirmax/HZ);
	for (nfs_infop = nfs_info; nfs_infop->flag; nfs_infop++) {
		if (nfss->flags & nfs_infop->flag)
			seq_puts(m, nfs_infop->str);
		else
			seq_puts(m, nfs_infop->nostr);
	}
	seq_puts(m, ",addr=");
	seq_escape(m, nfss->hostname, " \t\n\\");
	return 0;
}

/*
 * Invalidate the local caches
 */
void
nfs_zap_caches(struct inode *inode)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	int mode = inode->i_mode;

620
621
	spin_lock(&inode->i_lock);

Linus Torvalds's avatar
Linus Torvalds committed
622
623
624
625
626
	NFS_ATTRTIMEO(inode) = NFS_MINATTRTIMEO(inode);
	NFS_ATTRTIMEO_UPDATE(inode) = jiffies;

	memset(NFS_COOKIEVERF(inode), 0, sizeof(NFS_COOKIEVERF(inode)));
	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))
627
		nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE;
Linus Torvalds's avatar
Linus Torvalds committed
628
	else
629
		nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE;
630
631

	spin_unlock(&inode->i_lock);
632
633
634
635
636
637
638
639
640
}

static void nfs_zap_acl_cache(struct inode *inode)
{
	void (*clear_acl_cache)(struct inode *);

	clear_acl_cache = NFS_PROTO(inode)->clear_acl_cache;
	if (clear_acl_cache != NULL)
		clear_acl_cache(inode);
641
	spin_lock(&inode->i_lock);
642
	NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_ACL;
643
	spin_unlock(&inode->i_lock);
Linus Torvalds's avatar
Linus Torvalds committed
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
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
}

/*
 * Invalidate, but do not unhash, the inode
 */
static void
nfs_invalidate_inode(struct inode *inode)
{
	umode_t save_mode = inode->i_mode;

	make_bad_inode(inode);
	inode->i_mode = save_mode;
	nfs_zap_caches(inode);
}

struct nfs_find_desc {
	struct nfs_fh		*fh;
	struct nfs_fattr	*fattr;
};

/*
 * In NFSv3 we can have 64bit inode numbers. In order to support
 * this, and re-exported directories (also seen in NFSv2)
 * we are forced to allow 2 different inodes to have the same
 * i_ino.
 */
static int
nfs_find_actor(struct inode *inode, void *opaque)
{
	struct nfs_find_desc	*desc = (struct nfs_find_desc *)opaque;
	struct nfs_fh		*fh = desc->fh;
	struct nfs_fattr	*fattr = desc->fattr;

	if (NFS_FILEID(inode) != fattr->fileid)
		return 0;
	if (nfs_compare_fh(NFS_FH(inode), fh))
		return 0;
	if (is_bad_inode(inode) || NFS_STALE(inode))
		return 0;
	return 1;
}

static int
nfs_init_locked(struct inode *inode, void *opaque)
{
	struct nfs_find_desc	*desc = (struct nfs_find_desc *)opaque;
	struct nfs_fattr	*fattr = desc->fattr;

	NFS_FILEID(inode) = fattr->fileid;
	nfs_copy_fh(NFS_FH(inode), desc->fh);
	return 0;
}

/* Don't use READDIRPLUS on directories that we believe are too large */
#define NFS_LIMIT_READDIRPLUS (8*PAGE_SIZE)

/*
 * This is our front-end to iget that looks up inodes by file handle
 * instead of inode number.
 */
struct inode *
nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
{
	struct nfs_find_desc desc = {
		.fh	= fh,
		.fattr	= fattr
	};
	struct inode *inode = NULL;
	unsigned long hash;

	if ((fattr->valid & NFS_ATTR_FATTR) == 0)
		goto out_no_inode;

	if (!fattr->nlink) {
		printk("NFS: Buggy server - nlink == 0!\n");
		goto out_no_inode;
	}

	hash = nfs_fattr_to_ino_t(fattr);

	if (!(inode = iget5_locked(sb, hash, nfs_find_actor, nfs_init_locked, &desc)))
		goto out_no_inode;

	if (inode->i_state & I_NEW) {
		struct nfs_inode *nfsi = NFS_I(inode);

		/* We set i_ino for the few things that still rely on it,
		 * such as stat(2) */
		inode->i_ino = hash;

		/* We can't support update_atime(), since the server will reset it */
		inode->i_flags |= S_NOATIME|S_NOCMTIME;
		inode->i_mode = fattr->mode;
		/* Why so? Because we want revalidate for devices/FIFOs, and
		 * that's precisely what we have in nfs_file_inode_operations.
		 */
740
		inode->i_op = NFS_SB(sb)->rpc_ops->file_inode_ops;
Linus Torvalds's avatar
Linus Torvalds committed
741
742
743
744
745
746
747
748
749
		if (S_ISREG(inode->i_mode)) {
			inode->i_fop = &nfs_file_operations;
			inode->i_data.a_ops = &nfs_file_aops;
			inode->i_data.backing_dev_info = &NFS_SB(sb)->backing_dev_info;
		} else if (S_ISDIR(inode->i_mode)) {
			inode->i_op = NFS_SB(sb)->rpc_ops->dir_inode_ops;
			inode->i_fop = &nfs_dir_operations;
			if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS)
			    && fattr->size <= NFS_LIMIT_READDIRPLUS)
750
				set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_FLAGS(inode));
Linus Torvalds's avatar
Linus Torvalds committed
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
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
		} else if (S_ISLNK(inode->i_mode))
			inode->i_op = &nfs_symlink_inode_operations;
		else
			init_special_inode(inode, inode->i_mode, fattr->rdev);

		nfsi->read_cache_jiffies = fattr->timestamp;
		inode->i_atime = fattr->atime;
		inode->i_mtime = fattr->mtime;
		inode->i_ctime = fattr->ctime;
		if (fattr->valid & NFS_ATTR_FATTR_V4)
			nfsi->change_attr = fattr->change_attr;
		inode->i_size = nfs_size_to_loff_t(fattr->size);
		inode->i_nlink = fattr->nlink;
		inode->i_uid = fattr->uid;
		inode->i_gid = fattr->gid;
		if (fattr->valid & (NFS_ATTR_FATTR_V3 | NFS_ATTR_FATTR_V4)) {
			/*
			 * report the blocks in 512byte units
			 */
			inode->i_blocks = nfs_calc_block_size(fattr->du.nfs3.used);
			inode->i_blksize = inode->i_sb->s_blocksize;
		} else {
			inode->i_blocks = fattr->du.nfs2.blocks;
			inode->i_blksize = fattr->du.nfs2.blocksize;
		}
		nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
		nfsi->attrtimeo_timestamp = jiffies;
		memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
		nfsi->cache_access.cred = NULL;

		unlock_new_inode(inode);
	} else
		nfs_refresh_inode(inode, fattr);
	dprintk("NFS: nfs_fhget(%s/%Ld ct=%d)\n",
		inode->i_sb->s_id,
		(long long)NFS_FILEID(inode),
		atomic_read(&inode->i_count));

out:
	return inode;

out_no_inode:
	printk("nfs_fhget: iget failed\n");
	goto out;
}

#define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET)

int
nfs_setattr(struct dentry *dentry, struct iattr *attr)
{
	struct inode *inode = dentry->d_inode;
	struct nfs_fattr fattr;
	int error;

	if (attr->ia_valid & ATTR_SIZE) {
		if (!S_ISREG(inode->i_mode) || attr->ia_size == i_size_read(inode))
			attr->ia_valid &= ~ATTR_SIZE;
	}

	/* Optimization: if the end result is no change, don't RPC */
	attr->ia_valid &= NFS_VALID_ATTRS;
	if (attr->ia_valid == 0)
		return 0;

	lock_kernel();
	nfs_begin_data_update(inode);
	/* Write all dirty data if we're changing file permissions or size */
	if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE)) != 0) {
		if (filemap_fdatawrite(inode->i_mapping) == 0)
			filemap_fdatawait(inode->i_mapping);
		nfs_wb_all(inode);
	}
	error = NFS_PROTO(inode)->setattr(dentry, &fattr, attr);
825
	if (error == 0)
Linus Torvalds's avatar
Linus Torvalds committed
826
		nfs_refresh_inode(inode, &fattr);
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
	nfs_end_data_update(inode);
	unlock_kernel();
	return error;
}

/**
 * nfs_setattr_update_inode - Update inode metadata after a setattr call.
 * @inode: pointer to struct inode
 * @attr: pointer to struct iattr
 *
 * Note: we do this in the *proc.c in order to ensure that
 *       it works for things like exclusive creates too.
 */
void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
{
	if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) {
Linus Torvalds's avatar
Linus Torvalds committed
843
		if ((attr->ia_valid & ATTR_MODE) != 0) {
844
845
			int mode = attr->ia_mode & S_IALLUGO;
			mode |= inode->i_mode & ~S_IALLUGO;
Linus Torvalds's avatar
Linus Torvalds committed
846
847
848
849
850
851
			inode->i_mode = mode;
		}
		if ((attr->ia_valid & ATTR_UID) != 0)
			inode->i_uid = attr->ia_uid;
		if ((attr->ia_valid & ATTR_GID) != 0)
			inode->i_gid = attr->ia_gid;
852
		spin_lock(&inode->i_lock);
853
		NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
854
		spin_unlock(&inode->i_lock);
855
856
857
858
859
	}
	if ((attr->ia_valid & ATTR_SIZE) != 0) {
		inode->i_size = attr->ia_size;
		vmtruncate(inode, attr->ia_size);
	}
Linus Torvalds's avatar
Linus Torvalds committed
860
861
}

862
863
864
865
866
867
868
869
static int nfs_wait_schedule(void *word)
{
	if (signal_pending(current))
		return -ERESTARTSYS;
	schedule();
	return 0;
}

Linus Torvalds's avatar
Linus Torvalds committed
870
871
872
/*
 * Wait for the inode to get unlocked.
 */
873
static int nfs_wait_on_inode(struct inode *inode)
Linus Torvalds's avatar
Linus Torvalds committed
874
875
876
{
	struct rpc_clnt	*clnt = NFS_CLIENT(inode);
	struct nfs_inode *nfsi = NFS_I(inode);
877
	sigset_t oldmask;
Linus Torvalds's avatar
Linus Torvalds committed
878
	int error;
879
880
881
882
883
884

	rpc_clnt_sigmask(clnt, &oldmask);
	error = wait_on_bit_lock(&nfsi->flags, NFS_INO_REVALIDATING,
					nfs_wait_schedule, TASK_INTERRUPTIBLE);
	rpc_clnt_sigunmask(clnt, &oldmask);

Linus Torvalds's avatar
Linus Torvalds committed
885
886
887
	return error;
}

888
889
890
891
892
893
894
895
896
static void nfs_wake_up_inode(struct inode *inode)
{
	struct nfs_inode *nfsi = NFS_I(inode);

	clear_bit(NFS_INO_REVALIDATING, &nfsi->flags);
	smp_mb__after_clear_bit();
	wake_up_bit(&nfsi->flags, NFS_INO_REVALIDATING);
}

Linus Torvalds's avatar
Linus Torvalds committed
897
898
899
int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
{
	struct inode *inode = dentry->d_inode;
900
	int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME;
Linus Torvalds's avatar
Linus Torvalds committed
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
	int err;

	if (__IS_FLG(inode, MS_NOATIME))
		need_atime = 0;
	else if (__IS_FLG(inode, MS_NODIRATIME) && S_ISDIR(inode->i_mode))
		need_atime = 0;
	/* We may force a getattr if the user cares about atime */
	if (need_atime)
		err = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
	else
		err = nfs_revalidate_inode(NFS_SERVER(inode), inode);
	if (!err)
		generic_fillattr(inode, stat);
	return err;
}

struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, struct rpc_cred *cred)
{
	struct nfs_open_context *ctx;

	ctx = (struct nfs_open_context *)kmalloc(sizeof(*ctx), GFP_KERNEL);
	if (ctx != NULL) {
		atomic_set(&ctx->count, 1);
		ctx->dentry = dget(dentry);
		ctx->cred = get_rpccred(cred);
		ctx->state = NULL;
		ctx->lockowner = current->files;
		ctx->error = 0;
929
		ctx->dir_cookie = 0;
Linus Torvalds's avatar
Linus Torvalds committed
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
	}
	return ctx;
}

struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx)
{
	if (ctx != NULL)
		atomic_inc(&ctx->count);
	return ctx;
}

void put_nfs_open_context(struct nfs_open_context *ctx)
{
	if (atomic_dec_and_test(&ctx->count)) {
		if (!list_empty(&ctx->list)) {
			struct inode *inode = ctx->dentry->d_inode;
			spin_lock(&inode->i_lock);
			list_del(&ctx->list);
			spin_unlock(&inode->i_lock);
		}
		if (ctx->state != NULL)
			nfs4_close_state(ctx->state, ctx->mode);
		if (ctx->cred != NULL)
			put_rpccred(ctx->cred);
		dput(ctx->dentry);
		kfree(ctx);
	}
}

/*
 * Ensure that mmap has a recent RPC credential for use when writing out
 * shared pages
 */
void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx)
{
	struct inode *inode = filp->f_dentry->d_inode;
	struct nfs_inode *nfsi = NFS_I(inode);

	filp->private_data = get_nfs_open_context(ctx);
	spin_lock(&inode->i_lock);
	list_add(&ctx->list, &nfsi->open_files);
	spin_unlock(&inode->i_lock);
}

struct nfs_open_context *nfs_find_open_context(struct inode *inode, int mode)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_open_context *pos, *ctx = NULL;

	spin_lock(&inode->i_lock);
	list_for_each_entry(pos, &nfsi->open_files, list) {
		if ((pos->mode & mode) == mode) {
			ctx = get_nfs_open_context(pos);
			break;
		}
	}
	spin_unlock(&inode->i_lock);
	return ctx;
}

void nfs_file_clear_open_context(struct file *filp)
{
	struct inode *inode = filp->f_dentry->d_inode;
	struct nfs_open_context *ctx = (struct nfs_open_context *)filp->private_data;

	if (ctx) {
		filp->private_data = NULL;
		spin_lock(&inode->i_lock);
		list_move_tail(&ctx->list, &NFS_I(inode)->open_files);
		spin_unlock(&inode->i_lock);
		put_nfs_open_context(ctx);
For faster browsing, not all history is shown. View entire blame