summaryrefslogtreecommitdiff
path: root/fs/nfs/namespace.c
blob: b9a593d056b3f2bd8761065100231fac06e8dff0 (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
/*
 * linux/fs/nfs/namespace.c
 *
 * Copyright (C) 2005 Trond Myklebust <Trond.Myklebust@netapp.com>
 * - Modified by David Howells <dhowells@redhat.com>
 *
 * NFS namespace
 */

#include <linux/dcache.h>
#include <linux/gfp.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/nfs_fs.h>
#include <linux/string.h>
#include <linux/sunrpc/clnt.h>
#include <linux/vfs.h>
#include <linux/sunrpc/gss_api.h>
#include "internal.h"

#define NFSDBG_FACILITY		NFSDBG_VFS

static void nfs_expire_automounts(struct work_struct *work);

static LIST_HEAD(nfs_automount_list);
static DECLARE_DELAYED_WORK(nfs_automount_task, nfs_expire_automounts);
int nfs_mountpoint_expiry_timeout = 500 * HZ;

static struct vfsmount *nfs_do_submount(struct dentry *dentry,
					struct nfs_fh *fh,
					struct nfs_fattr *fattr,
					rpc_authflavor_t authflavor);

/*
 * nfs_path - reconstruct the path given an arbitrary dentry
 * @base - used to return pointer to the end of devname part of path
 * @dentry - pointer to dentry
 * @buffer - result buffer
 * @buflen - length of buffer
 *
 * Helper function for constructing the server pathname
 * by arbitrary hashed dentry.
 *
 * This is mainly for use in figuring out the path on the
 * server side when automounting on top of an existing partition
 * and in generating /proc/mounts and friends.
 */
char *nfs_path(char **p, struct dentry *dentry, char *buffer, ssize_t buflen)
{
	char *end;
	int namelen;
	unsigned seq;
	const char *base;

rename_retry:
	end = buffer+buflen;
	*--end = '\0';
	buflen--;

	seq = read_seqbegin(&rename_lock);
	rcu_read_lock();
	while (1) {
		spin_lock(&dentry->d_lock);
		if (IS_ROOT(dentry))
			break;
		namelen = dentry->d_name.len;
		buflen -= namelen + 1;
		if (buflen < 0)
			goto Elong_unlock;
		end -= namelen;
		memcpy(end, dentry->d_name.name, namelen);
		*--end = '/';
		spin_unlock(&dentry->d_lock);
		dentry = dentry->d_parent;
	}
	if (read_seqretry(&rename_lock, seq)) {
		spin_unlock(&dentry->d_lock);
		rcu_read_unlock();
		goto rename_retry;
	}
	if (*end != '/') {
		if (--buflen < 0) {
			spin_unlock(&dentry->d_lock);
			rcu_read_unlock();
			goto Elong;
		}
		*--end = '/';
	}
	*p = end;
	base = dentry->d_fsdata;
	if (!base) {
		spin_unlock(&dentry->d_lock);
		rcu_read_unlock();
		WARN_ON(1);
		return end;
	}
	namelen = strlen(base);
	/* Strip off excess slashes in base string */
	while (namelen > 0 && base[namelen - 1] == '/')
		namelen--;
	buflen -= namelen;
	if (buflen < 0) {
		spin_unlock(&dentry->d_lock);
		rcu_read_unlock();
		goto Elong;
	}
	end -= namelen;
	memcpy(end, base, namelen);
	spin_unlock(&dentry->d_lock);
	rcu_read_unlock();
	return end;
Elong_unlock:
	spin_unlock(&dentry->d_lock);
	rcu_read_unlock();
	if (read_seqretry(&rename_lock, seq))
		goto rename_retry;
Elong:
	return ERR_PTR(-ENAMETOOLONG);
}

#ifdef CONFIG_NFS_V4
rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors)
{
	struct gss_api_mech *mech;
	struct xdr_netobj oid;
	int i;
	rpc_authflavor_t pseudoflavor = RPC_AUTH_UNIX;

	for (i = 0; i < flavors->num_flavors; i++) {
		struct nfs4_secinfo_flavor *flavor;
		flavor = &flavors->flavors[i];

		if (flavor->flavor == RPC_AUTH_NULL || flavor->flavor == RPC_AUTH_UNIX) {
			pseudoflavor = flavor->flavor;
			break;
		} else if (flavor->flavor == RPC_AUTH_GSS) {
			oid.len  = flavor->gss.sec_oid4.len;
			oid.data = flavor->gss.sec_oid4.data;
			mech = gss_mech_get_by_OID(&oid);
			if (!mech)
				continue;
			pseudoflavor = gss_svc_to_pseudoflavor(mech, flavor->gss.service);
			gss_mech_put(mech);
			break;
		}
	}

	return pseudoflavor;
}

static int nfs_negotiate_security(const struct dentry *parent,
				  const struct dentry *dentry,
				  rpc_authflavor_t *flavor)
{
	struct page *page;
	struct nfs4_secinfo_flavors *flavors;
	int (*secinfo)(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *);
	int ret = -EPERM;

	secinfo = NFS_PROTO(parent->d_inode)->secinfo;
	if (secinfo != NULL) {
		page = alloc_page(GFP_KERNEL);
		if (!page) {
			ret = -ENOMEM;
			goto out;
		}
		flavors = page_address(page);
		ret = secinfo(parent->d_inode, &dentry->d_name, flavors);
		*flavor = nfs_find_best_sec(flavors);
		put_page(page);
	}

out:
	return ret;
}

static int nfs_lookup_with_sec(struct nfs_server *server, struct dentry *parent,
			       struct dentry *dentry, struct path *path,
			       struct nfs_fh *fh, struct nfs_fattr *fattr,
			       rpc_authflavor_t *flavor)
{
	struct rpc_clnt *clone;
	struct rpc_auth *auth;
	int err;

	err = nfs_negotiate_security(parent, path->dentry, flavor);
	if (err < 0)
		goto out;
	clone  = rpc_clone_client(server->client);
	auth   = rpcauth_create(*flavor, clone);
	if (!auth) {
		err = -EIO;
		goto out_shutdown;
	}
	err = server->nfs_client->rpc_ops->lookup(clone, parent->d_inode,
						  &path->dentry->d_name,
						  fh, fattr);
out_shutdown:
	rpc_shutdown_client(clone);
out:
	return err;
}

static struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir,
					      struct qstr *name,
					      struct nfs_fh *fh,
					      struct nfs_fattr *fattr)
{
	int err;

	if (NFS_PROTO(dir)->version == 4)
		return nfs4_proc_lookup_mountpoint(dir, name, fh, fattr);

	err = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, name, fh, fattr);
	if (err)
		return ERR_PTR(err);
	return rpc_clone_client(NFS_SERVER(dir)->client);
}
#else /* CONFIG_NFS_V4 */
static inline int nfs_lookup_with_sec(struct nfs_server *server,
				      struct dentry *parent, struct dentry *dentry,
				      struct path *path, struct nfs_fh *fh,
				      struct nfs_fattr *fattr,
				      rpc_authflavor_t *flavor)
{
	return -EPERM;
}

static inline struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir,
						     struct qstr *name,
						     struct nfs_fh *fh,
						     struct nfs_fattr *fattr)
{
	int err = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, name, fh, fattr);
	if (err)
		return ERR_PTR(err);
	return rpc_clone_client(NFS_SERVER(dir)->client);
}
#endif /* CONFIG_NFS_V4 */

/*
 * nfs_d_automount - Handle crossing a mountpoint on the server
 * @path - The mountpoint
 *
 * When we encounter a mountpoint on the server, we want to set up
 * a mountpoint on the client too, to prevent inode numbers from
 * colliding, and to allow "df" to work properly.
 * On NFSv4, we also want to allow for the fact that different
 * filesystems may be migrated to different servers in a failover
 * situation, and that different filesystems may want to use
 * different security flavours.
 */
struct vfsmount *nfs_d_automount(struct path *path)
{
	struct vfsmount *mnt;
	struct dentry *parent;
	struct nfs_fh *fh = NULL;
	struct nfs_fattr *fattr = NULL;
	struct rpc_clnt *client;
	rpc_authflavor_t flavor = RPC_AUTH_UNIX;

	dprintk("--> nfs_d_automount()\n");

	mnt = ERR_PTR(-ESTALE);
	if (IS_ROOT(path->dentry))
		goto out_nofree;

	mnt = ERR_PTR(-ENOMEM);
	fh = nfs_alloc_fhandle();
	fattr = nfs_alloc_fattr();
	if (fh == NULL || fattr == NULL)
		goto out;

	dprintk("%s: enter\n", __func__);

	/* Look it up again to get its attributes */
	parent = dget_parent(path->dentry);
	client = nfs_lookup_mountpoint(parent->d_inode, &path->dentry->d_name, fh, fattr);
	dput(parent);
	if (IS_ERR(client)) {
		mnt = ERR_CAST(client);
		goto out;
	}

	if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)
		mnt = nfs_do_refmount(client, path->dentry);
	else
		mnt = nfs_do_submount(path->dentry, fh, fattr, flavor);
	rpc_shutdown_client(client);

	if (IS_ERR(mnt))
		goto out;

	dprintk("%s: done, success\n", __func__);
	mntget(mnt); /* prevent immediate expiration */
	mnt_set_expiry(mnt, &nfs_automount_list);
	schedule_delayed_work(&nfs_automount_task, nfs_mountpoint_expiry_timeout);

out:
	nfs_free_fattr(fattr);
	nfs_free_fhandle(fh);
out_nofree:
	if (IS_ERR(mnt))
		dprintk("<-- %s(): error %ld\n", __func__, PTR_ERR(mnt));
	else
		dprintk("<-- %s() = %p\n", __func__, mnt);
	return mnt;
}

const struct inode_operations nfs_mountpoint_inode_operations = {
	.getattr	= nfs_getattr,
};

const struct inode_operations nfs_referral_inode_operations = {
};

static void nfs_expire_automounts(struct work_struct *work)
{
	struct list_head *list = &nfs_automount_list;

	mark_mounts_for_expiry(list);
	if (!list_empty(list))
		schedule_delayed_work(&nfs_automount_task, nfs_mountpoint_expiry_timeout);
}

void nfs_release_automount_timer(void)
{
	if (list_empty(&nfs_automount_list))
		cancel_delayed_work(&nfs_automount_task);
}

/*
 * Clone a mountpoint of the appropriate type
 */
static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server,
					   const char *devname,
					   struct nfs_clone_mount *mountdata)
{
#ifdef CONFIG_NFS_V4
	struct vfsmount *mnt = ERR_PTR(-EINVAL);
	switch (server->nfs_client->rpc_ops->version) {
		case 2:
		case 3:
			mnt = vfs_kern_mount(&nfs_xdev_fs_type, 0, devname, mountdata);
			break;
		case 4:
			mnt = vfs_kern_mount(&nfs4_xdev_fs_type, 0, devname, mountdata);
	}
	return mnt;
#else
	return vfs_kern_mount(&nfs_xdev_fs_type, 0, devname, mountdata);
#endif
}

/**
 * nfs_do_submount - set up mountpoint when crossing a filesystem boundary
 * @dentry - parent directory
 * @fh - filehandle for new root dentry
 * @fattr - attributes for new root inode
 * @authflavor - security flavor to use when performing the mount
 *
 */
static struct vfsmount *nfs_do_submount(struct dentry *dentry,
					struct nfs_fh *fh,
					struct nfs_fattr *fattr,
					rpc_authflavor_t authflavor)
{
	struct nfs_clone_mount mountdata = {
		.sb = dentry->d_sb,
		.dentry = dentry,
		.fh = fh,
		.fattr = fattr,
		.authflavor = authflavor,
	};
	struct vfsmount *mnt = ERR_PTR(-ENOMEM);
	char *page = (char *) __get_free_page(GFP_USER);
	char *devname;

	dprintk("--> nfs_do_submount()\n");

	dprintk("%s: submounting on %s/%s\n", __func__,
			dentry->d_parent->d_name.name,
			dentry->d_name.name);
	if (page == NULL)
		goto out;
	devname = nfs_devname(dentry, page, PAGE_SIZE);
	mnt = (struct vfsmount *)devname;
	if (IS_ERR(devname))
		goto free_page;
	mnt = nfs_do_clone_mount(NFS_SB(dentry->d_sb), devname, &mountdata);
free_page:
	free_page((unsigned long)page);
out:
	dprintk("%s: done\n", __func__);

	dprintk("<-- nfs_do_submount() = %p\n", mnt);
	return mnt;
}