summaryrefslogtreecommitdiff
path: root/fs/nfs/namespace.c
blob: 971132dfc93a81befd2098977925878c2a8b2a1e (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * 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/module.h>
#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"
#include "nfs.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;

/*
 * nfs_path - reconstruct the path given an arbitrary dentry
 * @base - used to return pointer to the end of devname part of path
 * @dentry_in - pointer to dentry
 * @buffer - result buffer
 * @buflen_in - length of buffer
 * @flags - options (see below)
 *
 * 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.
 *
 * Supported flags:
 * NFS_PATH_CANONICAL: ensure there is exactly one slash after
 *		       the original device (export) name
 *		       (if unset, the original name is returned verbatim)
 */
char *nfs_path(char **p, struct dentry *dentry_in, char *buffer,
	       ssize_t buflen_in, unsigned flags)
{
	char *end;
	int namelen;
	unsigned seq;
	const char *base;
	struct dentry *dentry;
	ssize_t buflen;

rename_retry:
	buflen = buflen_in;
	dentry = dentry_in;
	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 ((flags & NFS_PATH_CANONICAL) && *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);
	if (*end == '/') {
		/* 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);
}
EXPORT_SYMBOL_GPL(nfs_path);

/*
 * 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 nfs_fs_context *ctx;
	struct fs_context *fc;
	struct vfsmount *mnt = ERR_PTR(-ENOMEM);
	struct nfs_server *server = NFS_SB(path->dentry->d_sb);
	struct nfs_client *client = server->nfs_client;
	int timeout = READ_ONCE(nfs_mountpoint_expiry_timeout);
	int ret;

	if (IS_ROOT(path->dentry))
		return ERR_PTR(-ESTALE);

	/* Open a new filesystem context, transferring parameters from the
	 * parent superblock, including the network namespace.
	 */
	fc = fs_context_for_submount(path->mnt->mnt_sb->s_type, path->dentry);
	if (IS_ERR(fc))
		return ERR_CAST(fc);

	ctx = nfs_fc2context(fc);
	ctx->clone_data.dentry	= path->dentry;
	ctx->clone_data.sb	= path->dentry->d_sb;
	ctx->clone_data.fattr	= nfs_alloc_fattr();
	if (!ctx->clone_data.fattr)
		goto out_fc;

	if (fc->net_ns != client->cl_net) {
		put_net(fc->net_ns);
		fc->net_ns = get_net(client->cl_net);
	}

	/* for submounts we want the same server; referrals will reassign */
	memcpy(&ctx->nfs_server._address, &client->cl_addr, client->cl_addrlen);
	ctx->nfs_server.addrlen	= client->cl_addrlen;
	ctx->nfs_server.port	= server->port;

	ctx->version		= client->rpc_ops->version;
	ctx->minorversion	= client->cl_minorversion;
	ctx->nfs_mod		= client->cl_nfs_mod;
	__module_get(ctx->nfs_mod->owner);

	ret = client->rpc_ops->submount(fc, server);
	if (ret < 0) {
		mnt = ERR_PTR(ret);
		goto out_fc;
	}

	up_write(&fc->root->d_sb->s_umount);
	mnt = vfs_create_mount(fc);
	if (IS_ERR(mnt))
		goto out_fc;

	mntget(mnt); /* prevent immediate expiration */
	if (timeout <= 0)
		goto out_fc;

	mnt_set_expiry(mnt, &nfs_automount_list);
	schedule_delayed_work(&nfs_automount_task, timeout);

out_fc:
	put_fs_context(fc);
	return mnt;
}

static int
nfs_namespace_getattr(struct user_namespace *mnt_userns,
		      const struct path *path, struct kstat *stat,
		      u32 request_mask, unsigned int query_flags)
{
	if (NFS_FH(d_inode(path->dentry))->size != 0)
		return nfs_getattr(mnt_userns, path, stat, request_mask,
				   query_flags);
	generic_fillattr(&init_user_ns, d_inode(path->dentry), stat);
	return 0;
}

static int
nfs_namespace_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
		      struct iattr *attr)
{
	if (NFS_FH(d_inode(dentry))->size != 0)
		return nfs_setattr(idmap, dentry, attr);
	return -EACCES;
}

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

const struct inode_operations nfs_referral_inode_operations = {
	.getattr	= nfs_namespace_getattr,
	.setattr	= nfs_namespace_setattr,
};

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

	mark_mounts_for_expiry(list);
	if (!list_empty(list) && timeout > 0)
		schedule_delayed_work(&nfs_automount_task, timeout);
}

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

/**
 * nfs_do_submount - set up mountpoint when crossing a filesystem boundary
 * @fc: pointer to struct nfs_fs_context
 *
 */
int nfs_do_submount(struct fs_context *fc)
{
	struct nfs_fs_context *ctx = nfs_fc2context(fc);
	struct dentry *dentry = ctx->clone_data.dentry;
	struct nfs_server *server;
	char *buffer, *p;
	int ret;

	/* create a new volume representation */
	server = ctx->nfs_mod->rpc_ops->clone_server(NFS_SB(ctx->clone_data.sb),
						     ctx->mntfh,
						     ctx->clone_data.fattr,
						     ctx->selected_flavor);

	if (IS_ERR(server))
		return PTR_ERR(server);

	ctx->server = server;

	buffer = kmalloc(4096, GFP_USER);
	if (!buffer)
		return -ENOMEM;

	ctx->internal		= true;
	ctx->clone_data.inherited_bsize = ctx->clone_data.sb->s_blocksize_bits;

	p = nfs_devname(dentry, buffer, 4096);
	if (IS_ERR(p)) {
		nfs_errorf(fc, "NFS: Couldn't determine submount pathname");
		ret = PTR_ERR(p);
	} else {
		ret = vfs_parse_fs_string(fc, "source", p, buffer + 4096 - p);
		if (!ret)
			ret = vfs_get_tree(fc);
	}
	kfree(buffer);
	return ret;
}
EXPORT_SYMBOL_GPL(nfs_do_submount);

int nfs_submount(struct fs_context *fc, struct nfs_server *server)
{
	struct nfs_fs_context *ctx = nfs_fc2context(fc);
	struct dentry *dentry = ctx->clone_data.dentry;
	struct dentry *parent = dget_parent(dentry);
	int err;

	/* Look it up again to get its attributes */
	err = server->nfs_client->rpc_ops->lookup(d_inode(parent), dentry,
						  ctx->mntfh, ctx->clone_data.fattr);
	dput(parent);
	if (err != 0)
		return err;

	ctx->selected_flavor = server->client->cl_auth->au_flavor;
	return nfs_do_submount(fc);
}
EXPORT_SYMBOL_GPL(nfs_submount);

static int param_set_nfs_timeout(const char *val, const struct kernel_param *kp)
{
	long num;
	int ret;

	if (!val)
		return -EINVAL;
	ret = kstrtol(val, 0, &num);
	if (ret)
		return -EINVAL;
	if (num > 0) {
		if (num >= INT_MAX / HZ)
			num = INT_MAX;
		else
			num *= HZ;
		*((int *)kp->arg) = num;
		if (!list_empty(&nfs_automount_list))
			mod_delayed_work(system_wq, &nfs_automount_task, num);
	} else {
		*((int *)kp->arg) = -1*HZ;
		cancel_delayed_work(&nfs_automount_task);
	}
	return 0;
}

static int param_get_nfs_timeout(char *buffer, const struct kernel_param *kp)
{
	long num = *((int *)kp->arg);

	if (num > 0) {
		if (num >= INT_MAX - (HZ - 1))
			num = INT_MAX / HZ;
		else
			num = (num + (HZ - 1)) / HZ;
	} else
		num = -1;
	return sysfs_emit(buffer, "%li\n", num);
}

static const struct kernel_param_ops param_ops_nfs_timeout = {
	.set = param_set_nfs_timeout,
	.get = param_get_nfs_timeout,
};
#define param_check_nfs_timeout(name, p) __param_check(name, p, int)

module_param(nfs_mountpoint_expiry_timeout, nfs_timeout, 0644);
MODULE_PARM_DESC(nfs_mountpoint_expiry_timeout,
		"Set the NFS automounted mountpoint timeout value (seconds)."
		"Values <= 0 turn expiration off.");