summaryrefslogtreecommitdiff
path: root/fs/nsfs.c
blob: 3887da470f7eb6af9112fc4897ad71d977c93026 (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
#include <linux/mount.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/proc_ns.h>
#include <linux/magic.h>
#include <linux/ktime.h>
#include <linux/seq_file.h>
#include <linux/user_namespace.h>
#include <linux/nsfs.h>

static struct vfsmount *nsfs_mnt;

static long ns_ioctl(struct file *filp, unsigned int ioctl,
			unsigned long arg);
static const struct file_operations ns_file_operations = {
	.llseek		= no_llseek,
	.unlocked_ioctl = ns_ioctl,
};

static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
{
	struct inode *inode = d_inode(dentry);
	const struct proc_ns_operations *ns_ops = dentry->d_fsdata;

	return dynamic_dname(dentry, buffer, buflen, "%s:[%lu]",
		ns_ops->name, inode->i_ino);
}

static void ns_prune_dentry(struct dentry *dentry)
{
	struct inode *inode = d_inode(dentry);
	if (inode) {
		struct ns_common *ns = inode->i_private;
		atomic_long_set(&ns->stashed, 0);
	}
}

const struct dentry_operations ns_dentry_operations =
{
	.d_prune	= ns_prune_dentry,
	.d_delete	= always_delete_dentry,
	.d_dname	= ns_dname,
};

static void nsfs_evict(struct inode *inode)
{
	struct ns_common *ns = inode->i_private;
	clear_inode(inode);
	ns->ops->put(ns);
}

static void *__ns_get_path(struct path *path, struct ns_common *ns)
{
	struct vfsmount *mnt = mntget(nsfs_mnt);
	struct qstr qname = { .name = "", };
	struct dentry *dentry;
	struct inode *inode;
	unsigned long d;

	rcu_read_lock();
	d = atomic_long_read(&ns->stashed);
	if (!d)
		goto slow;
	dentry = (struct dentry *)d;
	if (!lockref_get_not_dead(&dentry->d_lockref))
		goto slow;
	rcu_read_unlock();
	ns->ops->put(ns);
got_it:
	path->mnt = mnt;
	path->dentry = dentry;
	return NULL;
slow:
	rcu_read_unlock();
	inode = new_inode_pseudo(mnt->mnt_sb);
	if (!inode) {
		ns->ops->put(ns);
		mntput(mnt);
		return ERR_PTR(-ENOMEM);
	}
	inode->i_ino = ns->inum;
	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
	inode->i_flags |= S_IMMUTABLE;
	inode->i_mode = S_IFREG | S_IRUGO;
	inode->i_fop = &ns_file_operations;
	inode->i_private = ns;

	dentry = d_alloc_pseudo(mnt->mnt_sb, &qname);
	if (!dentry) {
		iput(inode);
		mntput(mnt);
		return ERR_PTR(-ENOMEM);
	}
	d_instantiate(dentry, inode);
	dentry->d_fsdata = (void *)ns->ops;
	d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry);
	if (d) {
		d_delete(dentry);	/* make sure ->d_prune() does nothing */
		dput(dentry);
		mntput(mnt);
		cpu_relax();
		return ERR_PTR(-EAGAIN);
	}
	goto got_it;
}

void *ns_get_path(struct path *path, struct task_struct *task,
			const struct proc_ns_operations *ns_ops)
{
	struct ns_common *ns;
	void *ret;

again:
	ns = ns_ops->get(task);
	if (!ns)
		return ERR_PTR(-ENOENT);

	ret = __ns_get_path(path, ns);
	if (IS_ERR(ret) && PTR_ERR(ret) == -EAGAIN)
		goto again;
	return ret;
}

static int open_related_ns(struct ns_common *ns,
		   struct ns_common *(*get_ns)(struct ns_common *ns))
{
	struct path path = {};
	struct file *f;
	void *err;
	int fd;

	fd = get_unused_fd_flags(O_CLOEXEC);
	if (fd < 0)
		return fd;

	while (1) {
		struct ns_common *relative;

		relative = get_ns(ns);
		if (IS_ERR(relative)) {
			put_unused_fd(fd);
			return PTR_ERR(relative);
		}

		err = __ns_get_path(&path, relative);
		if (IS_ERR(err) && PTR_ERR(err) == -EAGAIN)
			continue;
		break;
	}
	if (IS_ERR(err)) {
		put_unused_fd(fd);
		return PTR_ERR(err);
	}

	f = dentry_open(&path, O_RDONLY, current_cred());
	path_put(&path);
	if (IS_ERR(f)) {
		put_unused_fd(fd);
		fd = PTR_ERR(f);
	} else
		fd_install(fd, f);

	return fd;
}

static long ns_ioctl(struct file *filp, unsigned int ioctl,
			unsigned long arg)
{
	struct ns_common *ns = get_proc_ns(file_inode(filp));

	switch (ioctl) {
	case NS_GET_USERNS:
		return open_related_ns(ns, ns_get_owner);
	default:
		return -ENOTTY;
	}
}

int ns_get_name(char *buf, size_t size, struct task_struct *task,
			const struct proc_ns_operations *ns_ops)
{
	struct ns_common *ns;
	int res = -ENOENT;
	ns = ns_ops->get(task);
	if (ns) {
		res = snprintf(buf, size, "%s:[%u]", ns_ops->name, ns->inum);
		ns_ops->put(ns);
	}
	return res;
}

struct file *proc_ns_fget(int fd)
{
	struct file *file;

	file = fget(fd);
	if (!file)
		return ERR_PTR(-EBADF);

	if (file->f_op != &ns_file_operations)
		goto out_invalid;

	return file;

out_invalid:
	fput(file);
	return ERR_PTR(-EINVAL);
}

static int nsfs_show_path(struct seq_file *seq, struct dentry *dentry)
{
	struct inode *inode = d_inode(dentry);
	const struct proc_ns_operations *ns_ops = dentry->d_fsdata;

	seq_printf(seq, "%s:[%lu]", ns_ops->name, inode->i_ino);
	return 0;
}

static const struct super_operations nsfs_ops = {
	.statfs = simple_statfs,
	.evict_inode = nsfs_evict,
	.show_path = nsfs_show_path,
};
static struct dentry *nsfs_mount(struct file_system_type *fs_type,
			int flags, const char *dev_name, void *data)
{
	return mount_pseudo(fs_type, "nsfs:", &nsfs_ops,
			&ns_dentry_operations, NSFS_MAGIC);
}
static struct file_system_type nsfs = {
	.name = "nsfs",
	.mount = nsfs_mount,
	.kill_sb = kill_anon_super,
};

void __init nsfs_init(void)
{
	nsfs_mnt = kern_mount(&nsfs);
	if (IS_ERR(nsfs_mnt))
		panic("can't set nsfs up\n");
	nsfs_mnt->mnt_sb->s_flags &= ~MS_NOUSER;
}